Technologies

18 pages, 2838 KB

Open AccessEditor’s ChoiceArticle

Neonatal Hypoxic-Ischemic Encephalopathy Grading from Multi-Channel EEG Time-Series Data Using a Fully Convolutional Neural Network

by Shuwen Yu, William P. Marnane, Geraldine B. Boylan and Gordon Lightbody

Technologies 2023, 11(6), 151; https://doi.org/10.3390/technologies11060151 - 25 Oct 2023

Cited by 7 | Viewed by 4594

Abstract

A deep learning classifier is proposed for grading hypoxic-ischemic encephalopathy (HIE) in neonates. Rather than using handcrafted features, this architecture can be fed with raw EEG. Fully convolutional layers were adopted both in the feature extraction and classification blocks, which makes this architecture [...] Read more.

A deep learning classifier is proposed for grading hypoxic-ischemic encephalopathy (HIE) in neonates. Rather than using handcrafted features, this architecture can be fed with raw EEG. Fully convolutional layers were adopted both in the feature extraction and classification blocks, which makes this architecture simpler, and deeper, but with fewer parameters. Here, two large (335 h and 338 h, respectively) multi-center neonatal continuous EEG datasets were used for training and testing. The model was trained based on weak labels and channel independence. A majority vote method was used for the post-processing of the classifier results (across time and channels) to increase the robustness of the prediction. A dimension reduction tool, UMAP, was used to visualize the model classification effect. The proposed system achieved an accuracy of 86.09% (95% confidence interval: 82.41–89.78%), an MCC of 0.7691, and an AUC of 86.23% on the large unseen test set. Two convolutional neural network architectures which utilized time-frequency distribution features were selected as the baseline as they had been developed or tested on the same datasets. A relative improvement of 23.65% in test accuracy was obtained as compared with the best baseline. In addition, if only one channel was available, the test accuracy was only reduced by 2.63–5.91% compared with making decisions based on the eight channels. Full article

(This article belongs to the Special Issue Selected Papers from ICNC-FSKD 2023 Conference)

► Show Figures

Figure 1

28 pages, 2632 KB

Open AccessEditor’s ChoiceReview

Green Electrospun Nanofibers for Biomedicine and Biotechnology

by Elyor Berdimurodov, Omar Dagdag, Khasan Berdimuradov, Wan Mohd Norsani Wan Nik, Ilyos Eliboev, Mansur Ashirov, Sherzod Niyozkulov, Muslum Demir, Chinmurot Yodgorov and Nizomiddin Aliev

Technologies 2023, 11(5), 150; https://doi.org/10.3390/technologies11050150 - 23 Oct 2023

Cited by 15 | Viewed by 5493

Abstract

Green electrospinning harnesses the potential of renewable biomaterials to craft biodegradable nanofiber structures, expanding their utility across a spectrum of applications. In this comprehensive review, we summarize the production, characterization and application of electrospun cellulose, collagen, gelatin and other biopolymer nanofibers in tissue [...] Read more.

Green electrospinning harnesses the potential of renewable biomaterials to craft biodegradable nanofiber structures, expanding their utility across a spectrum of applications. In this comprehensive review, we summarize the production, characterization and application of electrospun cellulose, collagen, gelatin and other biopolymer nanofibers in tissue engineering, drug delivery, biosensing, environmental remediation, agriculture and synthetic biology. These applications span diverse fields, including tissue engineering, drug delivery, biosensing, environmental remediation, agriculture, and synthetic biology. In the realm of tissue engineering, nanofibers emerge as key players, adept at mimicking the intricacies of the extracellular matrix. These fibers serve as scaffolds and vascular grafts, showcasing their potential to regenerate and repair tissues. Moreover, they facilitate controlled drug and gene delivery, ensuring sustained therapeutic levels essential for optimized wound healing and cancer treatment. Biosensing platforms, another prominent arena, leverage nanofibers by immobilizing enzymes and antibodies onto their surfaces. This enables precise glucose monitoring, pathogen detection, and immunodiagnostics. In the environmental sector, these fibers prove invaluable, purifying water through efficient adsorption and filtration, while also serving as potent air filtration agents against pollutants and pathogens. Agricultural applications see the deployment of nanofibers in controlled release fertilizers and pesticides, enhancing crop management, and extending antimicrobial food packaging coatings to prolong shelf life. In the realm of synthetic biology, these fibers play a pivotal role by encapsulating cells and facilitating bacteria-mediated prodrug activation strategies. Across this multifaceted landscape, nanofibers offer tunable topographies and surface functionalities that tightly regulate cellular behavior and molecular interactions. Importantly, their biodegradable nature aligns with sustainability goals, positioning them as promising alternatives to synthetic polymer-based technologies. As research and development continue to refine and expand the capabilities of green electrospun nanofibers, their versatility promises to advance numerous applications in the realms of biomedicine and biotechnology, contributing to a more sustainable and environmentally conscious future. Full article

(This article belongs to the Special Issue Electrospinning Technologies for Biomedical and Biotechnological Applications—Volume II)

► Show Figures

Figure 1

16 pages, 1564 KB

Open AccessEditor’s ChoiceArticle

Exploring the Digital Atmosphere of Museums: Perspectives and Potential

by Sofia Paschou and Georgios Papaioannou

Technologies 2023, 11(5), 149; https://doi.org/10.3390/technologies11050149 - 22 Oct 2023

Cited by 4 | Viewed by 4381

Abstract

This paper contributes to the field of museum and visitor experience in terms of atmosphere by discussing the “museum digital atmosphere” or MDA, a notion that has been introduced and found across museums in Greece. Research on museum atmospherics has tended to focus [...] Read more.

This paper contributes to the field of museum and visitor experience in terms of atmosphere by discussing the “museum digital atmosphere” or MDA, a notion that has been introduced and found across museums in Greece. Research on museum atmospherics has tended to focus on physical museum spaces and exhibits. By “atmosphere”, we mean the emotional state that is a result of public response adding to the overall museum experience. The MDA is therefore studied as the specific emotional state caused by the use of digital applications and technologies. The stimulus–organism–response or SOR model is used to define the MDA, so as to confirm and reinforce the concept. To that end, a qualitative methodological approach is used; we conduct semi-structured interviews and evaluate findings via content analysis. The sample consists of 17 specialists and professionals from the field, namely museologists, museographers, museum managers, and digital application developers working in Greek museums. Ultimately, this research uses the SOR model to reveal the effect of digital tools on the digital atmosphere in Greek museums. It also enriches the SOR model with additional concepts and emotions taken from real-life situations, adding new categories of variables. This research provides the initial data and knowledge regarding the concept of the MDA, along with its importance. Full article

(This article belongs to the Special Issue Immersive Technologies and Applications on Arts, Culture and Tourism)

► Show Figures

Figure 1

18 pages, 6018 KB

Open AccessEditor’s ChoiceArticle

Preparation and Characterization of Thermoresponsive Polymer Scaffolds Based on Poly(N-isopropylacrylamide-co-N-tert-butylacrylamide) for Cell Culture

by Gilyana K. Kazakova, Victoria S. Presniakova, Yuri M. Efremov, Svetlana L. Kotova, Anastasia A. Frolova, Sergei V. Kostjuk, Yury A. Rochev and Peter S. Timashev

Technologies 2023, 11(5), 145; https://doi.org/10.3390/technologies11050145 - 18 Oct 2023

Cited by 4 | Viewed by 3143

Abstract

In the realm of scaffold-free cell therapies, there is a questto develop organotypic three-dimensional (3D) tissue surrogates in vitro, capitalizing on the inherent ability of cells to create tissues with an efficiency and sophistication that still remains unmatched by human-made devices. In this [...] Read more.

In the realm of scaffold-free cell therapies, there is a questto develop organotypic three-dimensional (3D) tissue surrogates in vitro, capitalizing on the inherent ability of cells to create tissues with an efficiency and sophistication that still remains unmatched by human-made devices. In this study, we explored the properties of scaffolds obtained by the electrospinning of a thermosensitive copolymer, poly(N-isopropylacrylamide-co-N-tert-butylacrylamide) (P(NIPAM-co-NtBA)), intended for use in such therapies. Two copolymers with molecular weights of 123 and 137 kDa and a content of N-tert-butylacrylamide of ca. 15 mol% were utilized to generate 3D scaffolds via electrospinning. We examined the morphology, solution viscosity, porosity, and thickness of the spun matrices as well as the mechanical properties and hydrophobic–hydrophilic characteristics of the scaffolds. Particular attention was paid to studying the influence of the thermosensitive polymer’s molecular weight and dispersity on the resultant scaffolds’ properties and the role of electroforming parameters on the morphology and mechanical characteristics of the scaffolds. The cytotoxicity of the copolymers and interaction of cells with the scaffolds were also studied. Our findings provide significant insight into approaches to optimizing scaffolds for specific cell cultures, thereby offering new opportunities for scaffold-free cell therapies. Full article

(This article belongs to the Special Issue Electrospinning Technologies for Biomedical and Biotechnological Applications—Volume II)

► Show Figures

Figure 1

39 pages, 25112 KB

Open AccessEditor’s ChoiceReview

Recent Advances in the 3D Printing of Pure Copper Functional Structures for Thermal Management Devices

by Yue Hao Choong, Manickavasagam Krishnan and Manoj Gupta

Technologies 2023, 11(5), 141; https://doi.org/10.3390/technologies11050141 - 15 Oct 2023

Cited by 18 | Viewed by 8006

Abstract

Thermal management devices such as heat exchangers and heat pipes are integral to safe and efficient performance in multiple engineering applications, including lithium-ion batteries, electric vehicles, electronics, and renewable energy. However, the functional designs of these devices have until now been created around [...] Read more.

Thermal management devices such as heat exchangers and heat pipes are integral to safe and efficient performance in multiple engineering applications, including lithium-ion batteries, electric vehicles, electronics, and renewable energy. However, the functional designs of these devices have until now been created around conventional manufacturing constraints, and thermal performance has plateaued as a result. While 3D printing offers the design freedom to address these limitations, there has been a notable lack in high thermal conductivity materials beyond aluminium alloys. Recently, the 3D printing of pure copper to sufficiently high densities has finally taken off, due to the emergence of commercial-grade printers which are now equipped with 1 kW high-power lasers or short-wavelength lasers. Although the capabilities of these new systems appear ideal for processing pure copper as a bulk material, the performance of advanced thermal management devices are strongly dependent on topology-optimised filigree structures, which can require a very different processing window. Hence, this article presents a broad overview of the state-of-the-art in various additive manufacturing technologies used to fabricate pure copper functional filigree geometries comprising thin walls, lattice structures, and porous foams, and identifies opportunities for future developments in the 3D printing of pure copper for advanced thermal management devices. Full article

(This article belongs to the Collection Review Papers Collection for Advanced Technologies)

► Show Figures

Figure 1

13 pages, 3366 KB

Open AccessEditor’s ChoiceArticle

Detecting Airborne Pathogens: A Computational Approach Utilizing Surface Acoustic Wave Sensors for Microorganism Detection

by Sharon P. Varughese, S. Merlin Gilbert Raj, T. Jesse Joel and Sneha Gautam

Technologies 2023, 11(5), 135; https://doi.org/10.3390/technologies11050135 - 2 Oct 2023

Cited by 4 | Viewed by 3011

Abstract

The persistent threat posed by infectious pathogens remains a formidable challenge for humanity. Rapidly spreading infectious diseases caused by airborne microorganisms have far-reaching global consequences, imposing substantial costs on society. While various detection technologies have emerged, including biochemical, immunological, and molecular approaches, these [...] Read more.

The persistent threat posed by infectious pathogens remains a formidable challenge for humanity. Rapidly spreading infectious diseases caused by airborne microorganisms have far-reaching global consequences, imposing substantial costs on society. While various detection technologies have emerged, including biochemical, immunological, and molecular approaches, these methods still exhibit significant limitations such as time-intensive procedures, instability, and the need for specialized operators. This study presents an innovative solution that harnesses the potential of surface acoustic wave (SAW) sensors for the detection of airborne microorganisms. The research involves the establishment of a sensor model within the framework of COMSOL Multiphysics, utilizing a predefined piezoelectric multi-physics interface and employing a 2D modeling approach. Chitosan, selected as the sensing film for the model, interfaces with lithium niobate (LiNbO3), the chosen piezoelectric material responsible for detecting airborne pathogens. The analysis of microbe presence centers on solid displacement and electric potential frequencies, operating within the 850–900 MHz range. Notably, the first and second resonant frequencies are identified at 856 and 859 MHz, respectively. To enhance understanding, this study proposes a novel mathematical model grounded in Stokes’ Law and mass balance equations. This model serves to analyze microbe concentration, offering a fresh perspective on quantifying the presence of airborne pathogens. Through these endeavors, this research contributes to advancing the field of airborne microorganism detection, offering a promising avenue for addressing the challenges posed by infectious diseases. Full article

(This article belongs to the Section Environmental Technology)

► Show Figures

Figure 1

42 pages, 13997 KB

Open AccessEditor’s ChoiceArticle

Multi-Scale CNN: An Explainable AI-Integrated Unique Deep Learning Framework for Lung-Affected Disease Classification

by Ovi Sarkar, Md. Robiul Islam, Md. Khalid Syfullah, Md. Tohidul Islam, Md. Faysal Ahamed, Mominul Ahsan and Julfikar Haider

Technologies 2023, 11(5), 134; https://doi.org/10.3390/technologies11050134 - 30 Sep 2023

Cited by 32 | Viewed by 6251

Abstract

Lung-related diseases continue to be a leading cause of global mortality. Timely and precise diagnosis is crucial to save lives, but the availability of testing equipment remains a challenge, often coupled with issues of reliability. Recent research has highlighted the potential of Chest [...] Read more.

Lung-related diseases continue to be a leading cause of global mortality. Timely and precise diagnosis is crucial to save lives, but the availability of testing equipment remains a challenge, often coupled with issues of reliability. Recent research has highlighted the potential of Chest X-ray (CXR) images in identifying various lung diseases, including COVID-19, fibrosis, pneumonia, and more. In this comprehensive study, four publicly accessible datasets have been combined to create a robust dataset comprising 6650 CXR images, categorized into seven distinct disease groups. To effectively distinguish between normal and six different lung-related diseases (namely, bacterial pneumonia, COVID-19, fibrosis, lung opacity, tuberculosis, and viral pneumonia), a Deep Learning (DL) architecture called a Multi-Scale Convolutional Neural Network (MS-CNN) is introduced. The model is adapted to classify multiple numbers of lung disease classes, which is considered to be a persistent challenge in the field. While prior studies have demonstrated high accuracy in binary and limited-class scenarios, the proposed framework maintains this accuracy across a diverse range of lung conditions. The innovative model harnesses the power of combining predictions from multiple feature maps at different resolution scales, significantly enhancing disease classification accuracy. The approach aims to shorten testing duration compared to the state-of-the-art models, offering a potential solution toward expediting medical interventions for patients with lung-related diseases and integrating explainable AI (XAI) for enhancing prediction capability. The results demonstrated an impressive accuracy of 96.05%, with average values for precision, recall, F1-score, and AUC at 0.97, 0.95, 0.95, and 0.94, respectively, for the seven-class classification. The model exhibited exceptional performance across multi-class classifications, achieving accuracy rates of 100%, 99.65%, 99.21%, 98.67%, and 97.47% for two, three, four, five, and six-class scenarios, respectively. The novel approach not only surpasses many pre-existing state-of-the-art (SOTA) methodologies but also sets a new standard for the diagnosis of lung-affected diseases using multi-class CXR data. Furthermore, the integration of XAI techniques such as SHAP and Grad-CAM enhanced the transparency and interpretability of the model’s predictions. The findings hold immense promise for accelerating and improving the accuracy and confidence of diagnostic decisions in the field of lung disease identification. Full article

(This article belongs to the Special Issue Medical Imaging & Image Processing III)

► Show Figures

Figure 1

17 pages, 6492 KB

Open AccessEditor’s ChoiceArticle

Multi-Classification of Lung Infections Using Improved Stacking Convolution Neural Network

by Usharani Bhimavarapu, Nalini Chintalapudi and Gopi Battineni

Technologies 2023, 11(5), 128; https://doi.org/10.3390/technologies11050128 - 17 Sep 2023

Cited by 5 | Viewed by 2743

Abstract

Lung disease is a respiratory disease that poses a high risk to people worldwide and includes pneumonia and COVID-19. As such, quick and precise identification of lung disease is vital in medical treatment. Early detection and diagnosis can significantly reduce the life-threatening nature [...] Read more.

Lung disease is a respiratory disease that poses a high risk to people worldwide and includes pneumonia and COVID-19. As such, quick and precise identification of lung disease is vital in medical treatment. Early detection and diagnosis can significantly reduce the life-threatening nature of lung diseases and improve the quality of life of human beings. Chest X-ray and computed tomography (CT) scan images are currently the best techniques to detect and diagnose lung infection. The increase in the chest X-ray or CT scan images at the time of training addresses the overfitting dilemma, and multi-class classification of lung diseases will deal with meaningful information and overfitting. Overfitting deteriorates the performance of the model and gives inaccurate results. This study reduces the overfitting issue and computational complexity by proposing a new enhanced kernel convolution function. Alongside an enhanced kernel convolution function, this study used convolution neural network (CNN) models to determine pneumonia and COVID-19. Each CNN model was applied to the collected dataset to extract the features and later applied these features as input to the classification models. This study shows that extracting deep features from the common layers of the CNN models increased the performance of the classification procedure. The multi-class classification improves the diagnostic performance, and the evaluation metrics improved significantly with the improved support vector machine (SVM). The best results were obtained using the improved SVM classifier fed with the features provided by CNN, and the success rate of the improved SVM was 99.8%. Full article

(This article belongs to the Special Issue Medical Imaging & Image Processing III)

► Show Figures

Figure 1

13 pages, 766 KB

Open AccessEditor’s ChoiceArticle

Using Simple Interactive Technology to Help People with Intellectual and Visual Disabilities Exercise Functional Physical Responses: A Case Series Study

by Giulio E. Lancioni, Gloria Alberti, Chiara Filippini, Valeria Chiariello, Nirbhay N. Singh, Mark F. O’Reilly and Jeff Sigafoos

Technologies 2023, 11(5), 120; https://doi.org/10.3390/technologies11050120 - 7 Sep 2023

Cited by 5 | Viewed by 2441

Abstract

The study assessed a new interactive technology system for helping six people with intellectual and visual disabilities exercise relevant physical responses embedded within a fairly straightforward activity (i.e., placing objects in containers). Activity responses consisted of the participants taking objects from the floor [...] Read more.

The study assessed a new interactive technology system for helping six people with intellectual and visual disabilities exercise relevant physical responses embedded within a fairly straightforward activity (i.e., placing objects in containers). Activity responses consisted of the participants taking objects from the floor or a low shelf and placing those objects in a container high up in front of them (thus bending their body and legs and stretching their arms and hands). The technology involved a portable computer, a webcam, and three mini speakers whose basic functions included monitoring the participants’ responses, delivering preferred stimulation contingent on the responses and verbal encouragements/prompts for lack of responses, and assisting in data recording. The study was conducted following a non-concurrent multiple baseline design across participants. During baseline (i.e., when the system was used only for data recording), the participants’ mean frequency of responses per session varied between zero and nearly 12. During intervention (i.e., when the system was fully working), the participants’ mean frequency of responses per session increased to between about 34 and 59. Mean session duration varied between nearly 10 and over 14 min. The new system may be a valuable tool for supporting relevant physical activity engagement in people with intellectual and multiple disabilities. Full article

(This article belongs to the Section Assistive Technologies)

► Show Figures

Figure 1

63 pages, 2451 KB

Open AccessEditor’s ChoiceReview

Connected and Automated Vehicles: Infrastructure, Applications, Security, Critical Challenges, and Future Aspects

by Memoona Sadaf, Zafar Iqbal, Abdul Rehman Javed, Irum Saba, Moez Krichen, Sajid Majeed and Arooj Raza

Technologies 2023, 11(5), 117; https://doi.org/10.3390/technologies11050117 - 4 Sep 2023

Cited by 116 | Viewed by 58737

Abstract

Autonomous vehicles (AV) are game-changing innovations that promise a safer, more convenient, and environmentally friendly mode of transportation than traditional vehicles. Therefore, understanding AV technologies and their impact on society is critical as we continue this revolutionary journey. Generally, there needs to be [...] Read more.

Autonomous vehicles (AV) are game-changing innovations that promise a safer, more convenient, and environmentally friendly mode of transportation than traditional vehicles. Therefore, understanding AV technologies and their impact on society is critical as we continue this revolutionary journey. Generally, there needs to be a detailed study available to assist a researcher in understanding AV and its challenges. This research presents a comprehensive survey encompassing various aspects of AVs, such as public adoption, driverless city planning, traffic management, environmental impact, public health, social implications, international standards, safety, and security. Furthermore, it presents emerging technologies such as artificial intelligence (AI), integration of cloud computing, and solar power usage in automated vehicles. It also presents forensics approaches, tools used, standards involved, and challenges associated with conducting digital forensics in the context of autonomous vehicles. Moreover, this research provides an overview of cyber attacks affecting autonomous vehicles, attack management, traditional security devices, threat modeling, authentication schemes, over-the-air updates, zero-trust architectures, data privacy, and the corresponding defensive strategies to mitigate such risks. It also presents international standards, guidelines, and best practices for AVs. Finally, it outlines the future directions of AVs and the challenges that must be addressed to achieve widespread adoption. Full article

(This article belongs to the Section Information and Communication Technologies)

► Show Figures

Figure 1

22 pages, 5470 KB

Open AccessEditor’s ChoiceArticle

An Intelligent System-Based Coffee Plant Leaf Disease Recognition Using Deep Learning Techniques on Rwandan Arabica Dataset

by Eric Hitimana, Omar Janvier Sinayobye, J. Chrisostome Ufitinema, Jane Mukamugema, Peter Rwibasira, Theoneste Murangira, Emmanuel Masabo, Lucy Cherono Chepkwony, Marie Cynthia Abijuru Kamikazi, Jeanne Aline Ukundiwabo Uwera, Simon Martin Mvuyekure, Gaurav Bajpai and Jackson Ngabonziza

Technologies 2023, 11(5), 116; https://doi.org/10.3390/technologies11050116 - 1 Sep 2023

Cited by 16 | Viewed by 6549

Abstract

Rwandan coffee holds significant importance and immense value within the realm of agriculture, serving as a vital and valuable commodity. Additionally, coffee plays a pivotal role in generating foreign exchange for numerous developing nations. However, the coffee plant is vulnerable to pests and [...] Read more.

Rwandan coffee holds significant importance and immense value within the realm of agriculture, serving as a vital and valuable commodity. Additionally, coffee plays a pivotal role in generating foreign exchange for numerous developing nations. However, the coffee plant is vulnerable to pests and diseases weakening production. Farmers in cooperation with experts use manual methods to detect diseases resulting in human errors. With the rapid improvements in deep learning methods, it is possible to detect and recognize plan diseases to support crop yield improvement. Therefore, it is an essential task to develop an efficient method for intelligently detecting, identifying, and predicting coffee leaf diseases. This study aims to build the Rwandan coffee plant dataset, with the occurrence of coffee rust, miner, and red spider mites identified to be the most popular due to their geographical situations. From the collected coffee leaves dataset of 37,939 images, the preprocessing, along with modeling used five deep learning models such as InceptionV3, ResNet50, Xception, VGG16, and DenseNet. The training, validation, and testing ratio is 80%, 10%, and 10%, respectively, with a maximum of 10 epochs. The comparative analysis of the models’ performances was investigated to select the best for future portable use. The experiment proved the DenseNet model to be the best with an accuracy of 99.57%. The efficiency of the suggested method is validated through an unbiased evaluation when compared to existing approaches with different metrics. Full article

(This article belongs to the Special Issue Image and Signal Processing)

► Show Figures

Figure 1

27 pages, 27415 KB

Open AccessEditor’s ChoiceArticle

Efficient Deep Learning-Based Data-Centric Approach for Autism Spectrum Disorder Diagnosis from Facial Images Using Explainable AI

by Mohammad Shafiul Alam, Muhammad Mahbubur Rashid, Ahmed Rimaz Faizabadi, Hasan Firdaus Mohd Zaki, Tasfiq E. Alam, Md Shahin Ali, Kishor Datta Gupta and Md Manjurul Ahsan

Technologies 2023, 11(5), 115; https://doi.org/10.3390/technologies11050115 - 29 Aug 2023

Cited by 24 | Viewed by 9014

Abstract

The research describes an effective deep learning-based, data-centric approach for diagnosing autism spectrum disorder from facial images. To classify ASD and non-ASD subjects, this method requires training a convolutional neural network using the facial image dataset. As a part of the data-centric approach, [...] Read more.

The research describes an effective deep learning-based, data-centric approach for diagnosing autism spectrum disorder from facial images. To classify ASD and non-ASD subjects, this method requires training a convolutional neural network using the facial image dataset. As a part of the data-centric approach, this research applies pre-processing and synthesizing of the training dataset. The trained model is subsequently evaluated on an independent test set in order to assess the performance matrices of various data-centric approaches. The results reveal that the proposed method that simultaneously applies the pre-processing and augmentation approach on the training dataset outperforms the recent works, achieving excellent 98.9% prediction accuracy, sensitivity, and specificity while having 99.9% AUC. This work enhances the clarity and comprehensibility of the algorithm by integrating explainable AI techniques, providing clinicians with valuable and interpretable insights into the decision-making process of the ASD diagnosis model. Full article

(This article belongs to the Special Issue Medical Imaging & Image Processing III)

► Show Figures

Figure 1

22 pages, 2712 KB

Open AccessEditor’s ChoiceArticle

An Exposimetric Electromagnetic Comparison of Mobile Phone Emissions: 5G versus 4G Signals Analyses by Means of Statistics and Convolutional Neural Networks Classification

by Simona Miclaus, Delia B. Deaconescu, David Vatamanu and Andreea M. Buda

Technologies 2023, 11(5), 113; https://doi.org/10.3390/technologies11050113 - 24 Aug 2023

Cited by 7 | Viewed by 9002

Abstract

To gain a deeper understanding of the hotly contested topic of the non-thermal biological effects of microwaves, new metrics and methodologies need to be adopted. The direction proposed in the current work, which includes peak exposure analysis and not just time-averaged analysis, aligns [...] Read more.

To gain a deeper understanding of the hotly contested topic of the non-thermal biological effects of microwaves, new metrics and methodologies need to be adopted. The direction proposed in the current work, which includes peak exposure analysis and not just time-averaged analysis, aligns well with this objective. The proposed methodology is not intended to facilitate a comparison of the general characteristics between 4G and 5G mobile communication signals. Instead, its purpose is to provide a means for analyzing specific real-life exposure conditions that may vary based on multiple parameters. A differentiation based on amplitude-time features of the 4G versus 5G signals is followed, with the aim of describing the peculiarities of a user’s exposure when he runs four types of mobile applications on his mobile phone on either of the two mobile networks. To achieve the goals, we used signal and spectrum analyzers with adequate real-time analysis bandwidths and statistical descriptions provided by the amplitude probability density (APD) function, the complementary cumulative distribution function (CCDF), channel power measurements, and recorded spectrogram databases. We compared the exposimetric descriptors of emissions specific to file download, file upload, Internet video streaming, and video call usage in both 4G and 5G networks based on the specific modulation and coding schemes. The highest and lowest electric field strengths measured in the air at a 10 cm distance from the phone during emissions are indicated. The power distribution functions with the highest prevalence are highlighted and commented on. Afterwards, the capability of a convolutional neural network that belongs to the family of single-shot detectors is proven to recognize and classify the emissions with a very high degree of accuracy, enabling traceability of the dynamics of human exposure. Full article

(This article belongs to the Special Issue Intelligent Reflecting Surfaces for 5G and Beyond)

► Show Figures

Figure 1

18 pages, 13150 KB

Open AccessEditor’s ChoiceArticle

Challenges of Using the L-Band and S-Band for Direct-to-Cellular Satellite 5G-6G NTN Systems

by Alexander Pastukh, Valery Tikhvinskiy, Svetlana Dymkova and Oleg Varlamov

Technologies 2023, 11(4), 110; https://doi.org/10.3390/technologies11040110 - 10 Aug 2023

Cited by 48 | Viewed by 14105

Abstract

This article presents a comprehensive study of the potential utilization of the L-band and S-band frequency ranges for satellite non-terrestrial network (NTN) technologies. This study encompasses an interference analysis in the S-band, investigating the coexistence of NTN satellite systems with mobile satellite networks [...] Read more.

This article presents a comprehensive study of the potential utilization of the L-band and S-band frequency ranges for satellite non-terrestrial network (NTN) technologies. This study encompasses an interference analysis in the S-band, investigating the coexistence of NTN satellite systems with mobile satellite networks such as Omnispace and Lyra, and an interference analysis in the L-band between NTN satellites and the mobile satellite network Inmarsat. This study simulates an NTN satellite network with typical characteristics defined by 3GPP and ITU-R for the n255 and n256 bands. Furthermore, it provides calculations illustrating the signal-to-noise ratio degradation of low-Earth-orbit (LEO), medium-Earth-orbit (MEO), and geostationary-Earth-orbit (GEO) satellite networks operating in the L-band and S-band when exposed to interference from NTN satellites. Full article

(This article belongs to the Special Issue Intelligent Reflecting Surfaces for 5G and Beyond)

► Show Figures

Figure 1

20 pages, 747 KB

Open AccessEditor’s ChoiceArticle

Fuzzy Logic System for Classifying Multiple Sclerosis Patients as High, Medium, or Low Responders to Interferon-Beta

by Edgar Rafael Ponce de Leon-Sanchez, Jorge Domingo Mendiola-Santibañez, Omar Arturo Dominguez-Ramirez, Ana Marcela Herrera-Navarro, Alberto Vazquez-Cervantes, Hugo Jimenez-Hernandez and Horacio Senties-Madrid

Technologies 2023, 11(4), 109; https://doi.org/10.3390/technologies11040109 - 9 Aug 2023

Cited by 2 | Viewed by 2716

Abstract

Interferon-beta is one of the most widely prescribed disease-modifying therapies for multiple sclerosis patients. However, this treatment is only partially effective, and a significant proportion of patients do not respond to this drug. This paper proposes an alternative fuzzy logic system, based on [...] Read more.

Interferon-beta is one of the most widely prescribed disease-modifying therapies for multiple sclerosis patients. However, this treatment is only partially effective, and a significant proportion of patients do not respond to this drug. This paper proposes an alternative fuzzy logic system, based on the opinion of a neurology expert, to classify relapsing–remitting multiple sclerosis patients as high, medium, or low responders to interferon-beta. Also, a pipeline prediction model trained with biomarkers associated with interferon-beta responses is proposed, for predicting whether patients are potential candidates to be treated with this drug, in order to avoid ineffective therapies. The classification results showed that the fuzzy system presented 100% efficiency, compared to an unsupervised hierarchical clustering method (52%). So, the performance of the prediction model was evaluated, and 0.8 testing accuracy was achieved. Hence, a pipeline model, including data standardization, data compression, and a learning algorithm, could be a useful tool for getting reliable predictions about responses to interferon-beta. Full article

(This article belongs to the Special Issue The Future of Healthcare: Biomedical Technology and Integrated Artificial Intelligence)

► Show Figures

Figure 1

18 pages, 2301 KB

Open AccessEditor’s ChoiceArticle

The U-Net Family for Epicardial Adipose Tissue Segmentation and Quantification in Low-Dose CT

by Lu Liu, Runlei Ma, Peter M. A. van Ooijen, Matthijs Oudkerk, Rozemarijn Vliegenthart, Raymond N. J. Veldhuis and Christoph Brune

Technologies 2023, 11(4), 104; https://doi.org/10.3390/technologies11040104 - 5 Aug 2023

Cited by 6 | Viewed by 3723

Abstract

Epicardial adipose tissue (EAT) is located between the visceral pericardium and myocardium, and EAT volume is correlated with cardiovascular risk. Nowadays, many deep learning-based automated EAT segmentation and quantification methods in the U-net family have been developed to reduce the workload for radiologists. [...] Read more.

Epicardial adipose tissue (EAT) is located between the visceral pericardium and myocardium, and EAT volume is correlated with cardiovascular risk. Nowadays, many deep learning-based automated EAT segmentation and quantification methods in the U-net family have been developed to reduce the workload for radiologists. The automatic assessment of EAT on non-contrast low-dose CT calcium score images poses a greater challenge compared to the automatic assessment on coronary CT angiography, which requires a higher radiation dose to capture the intricate details of the coronary arteries. This study comprehensively examined and evaluated state-of-the-art segmentation methods while outlining future research directions. Our dataset consisted of 154 non-contrast low-dose CT scans from the ROBINSCA study, with two types of labels: (a) region inside the pericardium and (b) pixel-wise EAT labels. We selected four advanced methods from the U-net family: 3D U-net, 3D attention U-net, an extended 3D attention U-net, and U-net++. For evaluation, we performed both four-fold cross-validation and hold-out tests. Agreement between the automatic segmentation/quantification and the manual quantification was evaluated with the Pearson correlation and the Bland–Altman analysis. Generally, the models trained with label type (a) showed better performance compared to models trained with label type (b). The U-net++ model trained with label type (a) showed the best performance for segmentation and quantification. The U-net++ model trained with label type (a) efficiently provided better EAT segmentation results (hold-out test: DCS =

80.18 \pm 0.20 %

, mIoU =

67.13 \pm 0.39 %

, sensitivity =

81.47 \pm 0.43 %

, specificity =

99.64 \pm 0.00 %

, Pearson correlation = 0.9405) and EAT volume compared to the other U-net-based networks and the recent EAT segmentation method. Interestingly, our findings indicate that 3D convolutional neural networks do not consistently outperform 2D networks in EAT segmentation and quantification. Moreover, utilizing labels representing the region inside the pericardium proved advantageous in training more accurate EAT segmentation models. These insights highlight the potential of deep learning-based methods for achieving robust EAT segmentation and quantification outcomes. Full article

(This article belongs to the Special Issue Medical Imaging & Image Processing III)

► Show Figures

Figure 1

14 pages, 6158 KB

Open AccessEditor’s ChoiceCommunication

Adapting the H.264 Standard to the Internet of Vehicles

by Yair Wiseman

Technologies 2023, 11(4), 103; https://doi.org/10.3390/technologies11040103 - 3 Aug 2023

Cited by 13 | Viewed by 3167

Abstract

We suggest two steps of reducing the amount of data transmitted on Internet of Vehicle networks. The first step shifts the image from a full-color resolution to only an 8-color resolution. The reduction of the color numbers is noticeable; however, the 8-color images [...] Read more.

We suggest two steps of reducing the amount of data transmitted on Internet of Vehicle networks. The first step shifts the image from a full-color resolution to only an 8-color resolution. The reduction of the color numbers is noticeable; however, the 8-color images are enough for the requirements of common vehicles’ applications. The second step suggests modifying the quantization tables employed by H.264 to different tables that will be more suitable to an image with only 8 colors. The first step usually reduces the size of the image by more than 30%, and when continuing and performing the second step, the size of the image decreases by more than 40%. That is to say, the combination of the two steps can provide a significant reduction in the amount of data required to be transferred on vehicular networks. Full article

(This article belongs to the Special Issue Image and Signal Processing)

► Show Figures

Figure 1

27 pages, 5171 KB

Open AccessEditor’s ChoiceReview

Modern DC–DC Power Converter Topologies and Hybrid Control Strategies for Maximum Power Output in Sustainable Nanogrids and Picogrids—A Comprehensive Survey

by Anupama Ganguly, Pabitra Kumar Biswas, Chiranjit Sain and Taha Selim Ustun

Technologies 2023, 11(4), 102; https://doi.org/10.3390/technologies11040102 - 1 Aug 2023

Cited by 21 | Viewed by 5504

Abstract

Sustainable energy exhibited immense growth in the last few years. As compared to other sustainable sources, solar power is proved to be the most feasible source due to some unanticipated characteristics, such as being clean, noiseless, ecofriendly, etc. The output from the solar [...] Read more.

Sustainable energy exhibited immense growth in the last few years. As compared to other sustainable sources, solar power is proved to be the most feasible source due to some unanticipated characteristics, such as being clean, noiseless, ecofriendly, etc. The output from the solar power is entirely unpredictable since solar power generation is dependent on the intensity of solar irradiation and solar panel temperature. Further, these parameters are weather dependent and thus intermittent in nature. To conquer intermittency, power converters play an important role in solar power generation. Generally, photovoltaic systems will eventually suffer from a decrease in energy conversion efficiency along with improper stability and intermittent properties. As a result, the maximum power point tracking (MPPT) algorithm must be incorporated to cultivate maximum power from solar power. To make solar power generation reliable, a proper control technique must be added to the DC–DC power converter topologies. Furthermore, this study reviewed the progress of the maximum power point tracking algorithm and included an in-depth discussion on modern and both unidirectional and bidirectional DC–DC power converter topologies for harvesting electric power. Lastly, for the reliability and continuity of the power demand and to allow for distributed generation, this article also established the possibility of integrating solar PV systems into nanogrids and picogrids in a sustainable environment. The outcome of this comprehensive survey would be of strong interest to the researchers, technologists, and the industry in the relevant field to carry out future research. Full article

(This article belongs to the Collection Electrical Technologies)

► Show Figures

Figure 1

20 pages, 349 KB

Open AccessEditor’s ChoiceArticle

Quantum Effects in General Relativity: Investigating Repulsive Gravity of Black Holes at Large Distances

by Piero Chiarelli

Technologies 2023, 11(4), 98; https://doi.org/10.3390/technologies11040098 - 14 Jul 2023

Cited by 2 | Viewed by 2688

Abstract

This paper proposes a theoretical study that investigates quantum effects on the gravity of black holes. This study utilizes a gravitational model that incorporates quantum mechanics derived from the classical-like quantum hydrodynamic representation. This research calculates the mass density distribution of quantum black [...] Read more.

This paper proposes a theoretical study that investigates quantum effects on the gravity of black holes. This study utilizes a gravitational model that incorporates quantum mechanics derived from the classical-like quantum hydrodynamic representation. This research calculates the mass density distribution of quantum black holes, specifically in the case of central symmetry. The gravity of a quantum black hole shows contributions coming from quantum potential energy, which is also sensitive to the presence of a background of gravitational noise. The additional energy, stored in quantum potential fluctuations and constituting a form of dark energy, leads to a repulsive gravity in the weak gravity limit. This repulsive gravity overcomes the attractive classical Newtonian force at large distances of order of the intergalactic length. Full article

(This article belongs to the Section Quantum Technologies)

13 pages, 1160 KB

Open AccessEditor’s ChoiceArticle

Optical Properties of AgInS₂ Quantum Dots Synthesized in a 3D-Printed Microfluidic Chip

by Konstantin Baranov, Ivan Reznik, Sofia Karamysheva, Jacobus W. Swart, Stanislav Moshkalev and Anna Orlova

Technologies 2023, 11(4), 93; https://doi.org/10.3390/technologies11040093 - 12 Jul 2023

Cited by 3 | Viewed by 4166

Abstract

Colloidal nanoparticles, and quantum dots in particular, are a new class of materials that can significantly improve the functionality of photonics, electronics, sensor devices, etc. The main challenge addressed in the article is modification of the syntheses of colloidal NP to launch them [...] Read more.

Colloidal nanoparticles, and quantum dots in particular, are a new class of materials that can significantly improve the functionality of photonics, electronics, sensor devices, etc. The main challenge addressed in the article is modification of the syntheses of colloidal NP to launch them into mass production. It is proposed to use an additive printing method of chips for microfluidic synthesis, and it is shown that our approach allows to offer a cheap, easily scalable and automated synthesis method which allows to increase the product yield up to 60% with improved optical properties of

{AgInS}_{2}

quantum dots. Full article

(This article belongs to the Special Issue Advanced Processing Technologies of Innovative Materials)

► Show Figures

Figure 1

24 pages, 7842 KB

Open AccessEditor’s ChoiceArticle

Field Performance Monitoring of Energy-Generating High-Transparency Agrivoltaic Glass Windows

by Mikhail Vasiliev, Victor Rosenberg, Jamie Lyford and David Goodfield

Technologies 2023, 11(4), 95; https://doi.org/10.3390/technologies11040095 - 12 Jul 2023

Cited by 11 | Viewed by 4966

Abstract

Currently, there are strong and sustained growth trends observed in multi-disciplinary industrial technologies such as building-integrated photovoltaics and agrivoltaics, where renewable energy production is featured in building envelopes of varying degrees of transparency. Novel glass products can provide a combination of thermal energy [...] Read more.

Currently, there are strong and sustained growth trends observed in multi-disciplinary industrial technologies such as building-integrated photovoltaics and agrivoltaics, where renewable energy production is featured in building envelopes of varying degrees of transparency. Novel glass products can provide a combination of thermal energy savings and solar energy harvesting, enabled by either patterned-semiconductor thin-film energy converters on glass substrates, or by using luminescent concentrator-type approaches to achieve high transparency. Significant progress has been demonstrated recently in building integrated solar windows featuring visible light transmission of up to 70%, with electric power outputs of up to P_max ~ 30–33 W_p/m². Several slightly different designs were tested during 2021–2023 in a greenhouse installation at Murdoch University in Perth, Western Australia; their long-term energy harvesting performance differences were found to be on the scale of ~10% in wall-mounted locations. Solar greenhouse generated electricity at rates of up to 19 kWh/day, offsetting nearly 40% of energy costs. The objective of this paper is to report on the field performance of these PV windows in the context of agrivoltaics and to provide some detail of the performance differences measured in several solar window designs related to their glazing structure materials. Methods for the identification and quantification of long-term field performance differences and energy generation trends in solar windows of marginally different design types are reported. The paper also aims to outline the practical application potential of these transparent construction materials in built environments, focusing on the measured renewable energy figures and seasonal trends observed during the long-term study. Full article

(This article belongs to the Topic Emerging Technologies for Grid-Interactive Efficient Buildings and Communities)

► Show Figures

Figure 1

15 pages, 3248 KB

Open AccessEditor’s ChoiceArticle

Regenerating Iron-Based Adsorptive Media Used for Removing Arsenic from Water

by Ilaria Ceccarelli, Luca Filoni, Massimiliano Poli, Ciro Apollonio and Andrea Petroselli

Technologies 2023, 11(4), 94; https://doi.org/10.3390/technologies11040094 - 12 Jul 2023

Cited by 5 | Viewed by 2474

Abstract

Of all the substances that can be present in water intended for human consumption, arsenic (As) is one of the most toxic. Many treatment technologies can be used for removing As from water, for instance, adsorption onto iron media, where commercially available adsorbents [...] Read more.

Of all the substances that can be present in water intended for human consumption, arsenic (As) is one of the most toxic. Many treatment technologies can be used for removing As from water, for instance, adsorption onto iron media, where commercially available adsorbents are removed and replaced with new media when they are exhausted. Since this is an expensive operation, in this work, a novel and portable plant for regenerating iron media has been developed and tested in four real case studies in Central Italy. The obtained results highlight the good efficiency of the system, which was able, from 2019 to 2023, to regenerate the iron media and to restore its capability to adsorb the As from water almost entirely. Indeed, when the legal threshold value of 10 μg/L is exceeded, the regeneration process is performed and, after that, the As concentration in the water effluent is at the minimum level in all the investigated case studies. Full article

(This article belongs to the Special Issue Advanced Processing Technologies of Innovative Materials)

► Show Figures

Figure 1

26 pages, 7475 KB

Open AccessEditor’s ChoiceArticle

A Deep Reinforcement Learning Method for Economic Power Dispatch of Microgrid in OPAL-RT Environment

by Faa-Jeng Lin, Chao-Fu Chang, Yu-Cheng Huang and Tzu-Ming Su

Technologies 2023, 11(4), 96; https://doi.org/10.3390/technologies11040096 - 12 Jul 2023

Cited by 9 | Viewed by 4497

Abstract

This paper focuses on the economic power dispatch (EPD) operation of a microgrid in an OPAL-RT environment. First, a long short-term memory (LSTM) network is proposed to forecast the load information of a microgrid to determine the output of a power generator and [...] Read more.

This paper focuses on the economic power dispatch (EPD) operation of a microgrid in an OPAL-RT environment. First, a long short-term memory (LSTM) network is proposed to forecast the load information of a microgrid to determine the output of a power generator and the charging/discharging control strategy of a battery energy storage system (BESS). Then, a deep reinforcement learning method, the deep deterministic policy gradient (DDPG), is utilized to develop the power dispatch of a microgrid to minimize the total energy expense while considering power constraints, load uncertainties and electricity price. Moreover, a microgrid built in Cimei Island of Penghu Archipelago, Taiwan, is investigated to examine the compliance with the requirements of equality and inequality constraints and the performance of the deep reinforcement learning method. Furthermore, a comparison of the proposed method with the experience-based energy management system (EMS), Newton particle swarm optimization (Newton-PSO) and the deep Q-learning network (DQN) is provided to evaluate the obtained solutions. In this study, the average deviation of the LSTM forecast accuracy is less than 5%. In addition, the daily operating cost of the proposed method obtains a 3.8% to 7.4% lower electricity cost compared to that of the other methods. Finally, a detailed emulation in the OPAL-RT environment is carried out to validate the effectiveness of the proposed method. Full article

(This article belongs to the Topic Emerging Technologies for Grid-Interactive Efficient Buildings and Communities)

► Show Figures

Figure 1

18 pages, 753 KB

Open AccessEditor’s ChoiceReview

Digital Technologies to Provide Humanization in the Education of the Healthcare Workforce: A Systematic Review

by María Gonzalez-Moreno, Carlos Monfort-Vinuesa, Antonio Piñas-Mesa and Esther Rincon

Technologies 2023, 11(4), 88; https://doi.org/10.3390/technologies11040088 - 5 Jul 2023

Cited by 4 | Viewed by 4117

Abstract

Objectives: The need to incentivize the humanization of healthcare providers coincides with the development of a more technological approach to medicine, which gives rise to depersonalization when treating patients. Currently, there is a culture of humanization that reflects the awareness of health professionals, [...] Read more.

Objectives: The need to incentivize the humanization of healthcare providers coincides with the development of a more technological approach to medicine, which gives rise to depersonalization when treating patients. Currently, there is a culture of humanization that reflects the awareness of health professionals, patients, and policy makers, although it is unknown if there are university curricula incorporating specific skills in humanization, or what these may include. Therefore, the objectives of this study are as follows: (1) to identify what type of education in humanization is provided to university students of Health Sciences using digital technologies; and (2) determine the strengths and weaknesses of this education. The authors propose a curriculum focusing on undergraduate students to strengthen the humanization skills of future health professionals, including digital health strategies. Methods: A systematic review, based on the scientific literature published in EBSCO, Ovid, PubMed, Scopus, and Web of Science, over the last decade (2012–2022), was carried out in November 2022. The keywords used were “humanization of care” and “humanization of healthcare” combined both with and without “students”. Results: A total of 475 articles were retrieved, of which 6 met the inclusion criteria and were subsequently analyzed, involving a total of 295 students. Three of them (50%) were qualitative studies, while the other three (50%) involved mixed methods. Only one of the studies (16.7%) included digital health strategies to train humanization. Meanwhile, another study (16.7%) measured the level of humanization after training. Conclusions: There is a clear lack of empirically tested university curricula that combine education in humanization and digital technology for future health professionals. Greater focus on the training of future health professionals is needed, in order to guarantee that they begin their professional careers with the precept of medical humanities as a basis. Full article

(This article belongs to the Special Issue The Future of Healthcare: Biomedical Technology and Integrated Artificial Intelligence)

► Show Figures

Figure 1

22 pages, 597 KB

Open AccessEditor’s ChoiceArticle

Optimizing EMG Classification through Metaheuristic Algorithms

by Marcos Aviles, Juvenal Rodríguez-Reséndiz and Danjela Ibrahimi

Technologies 2023, 11(4), 87; https://doi.org/10.3390/technologies11040087 - 2 Jul 2023

Cited by 20 | Viewed by 3706

Abstract

This work proposes a metaheuristic-based approach to hyperparameter selection in a multilayer perceptron to classify EMG signals. The main goal of the study is to improve the performance of the model by optimizing four important hyperparameters: the number of neurons, the learning rate, [...] Read more.

This work proposes a metaheuristic-based approach to hyperparameter selection in a multilayer perceptron to classify EMG signals. The main goal of the study is to improve the performance of the model by optimizing four important hyperparameters: the number of neurons, the learning rate, the epochs, and the training batches. The approach proposed in this work shows that hyperparameter optimization using particle swarm optimization and the gray wolf optimizer significantly improves the performance of a multilayer perceptron in classifying EMG motion signals. The final model achieves an average classification rate of 93% for the validation phase. The results obtained are promising and suggest that the proposed approach may be helpful for the optimization of deep learning models in other signal processing applications. Full article

(This article belongs to the Special Issue The Future of Healthcare: Biomedical Technology and Integrated Artificial Intelligence)

► Show Figures

Figure 1

18 pages, 4056 KB

Open AccessEditor’s ChoiceArticle

Enhancement of Handshake Attraction through Tactile, Visual, and Auditory Multimodal Stimulation

by Taishu Kumagai and Yoshimune Nonomura

Technologies 2023, 11(4), 86; https://doi.org/10.3390/technologies11040086 - 1 Jul 2023

Cited by 3 | Viewed by 3731

Abstract

“Handshaking parties”, where pop idols shake hands with fans, can be exciting. The multimodal stimulation of tactile, visual, and auditory sensations can be captivating. In this study, we presented subjects with stimuli eliciting three sensory responses: tactile, visual, and auditory sensations. We found [...] Read more.

“Handshaking parties”, where pop idols shake hands with fans, can be exciting. The multimodal stimulation of tactile, visual, and auditory sensations can be captivating. In this study, we presented subjects with stimuli eliciting three sensory responses: tactile, visual, and auditory sensations. We found that the attraction scores of subjects increased because they felt the smoothness and obtained a human-like sensory experience grasping a grip handle covered with artificial skin, faux fur, and abrasive cloth with their dominant hand as they looked at a picture of a pop idol or listened to a song. When no pictures or songs were presented, a simple feeling of slight warmth was correlated with the attraction score. Results suggest that multimodal stimuli alter tactile sensations and the feelings evoked. This finding may be useful for designing materials that activate the human mind through tactile sensation and for developing humanoid robots and virtual reality systems. Full article

(This article belongs to the Section Information and Communication Technologies)

► Show Figures

Figure 1

13 pages, 2828 KB

Open AccessEditor’s ChoiceArticle

Two Fe-Zr-B-Cu Nanocrystalline Magnetic Alloys Produced by Mechanical Alloying Technique

by Jason Daza, Wael Ben Mbarek, Lluisa Escoda, Joan Saurina and Joan-Josep Suñol

Technologies 2023, 11(3), 78; https://doi.org/10.3390/technologies11030078 - 16 Jun 2023

Cited by 2 | Viewed by 4014

Abstract

Fe-rich soft magnetic alloys are candidates for applications as magnetic sensors and actuators. Spring magnets can be obtained when these alloys are added to hard magnetic compounds. In this work, two nanocrystalline Fe-Zr-B-Cu alloys are produced by mechanical alloying, MA. The increase in [...] Read more.

Fe-rich soft magnetic alloys are candidates for applications as magnetic sensors and actuators. Spring magnets can be obtained when these alloys are added to hard magnetic compounds. In this work, two nanocrystalline Fe-Zr-B-Cu alloys are produced by mechanical alloying, MA. The increase in boron content favours the reduction of the crystalline size. Thermal analysis (by differential scanning calorimetry) shows that, in the temperature range compressed between 450 and 650 K, wide exothermic processes take place, which are associated with the relaxation of the tensions of the alloys produced by MA. At high temperatures, a main crystallisation peak is found. A Kissinger and an isoconversional method were used to determine the apparent activation of the exothermic processes. The values are compared with those found in the scientific literature. Likewise, adapted thermogravimetry allowed for the determination of the Curie temperature. The functional response has been analysed by hysteresis loop cycles. According to the composition, the decrease of the Fe/B ratio diminishes the soft magnetic behaviour. Full article

(This article belongs to the Special Issue Advanced Processing Technologies of Innovative Materials)

► Show Figures

Figure 1

17 pages, 6271 KB

Open AccessEditor’s ChoiceArticle

Injectable Hydrated Calcium Phosphate Bone-like Paste: Synthesis, In Vitro, and In Vivo Biocompatibility Assessment

by Anastasia Yu. Teterina, Vladislav V. Minaychev, Polina V. Smirnova, Margarita I. Kobiakova, Igor V. Smirnov, Roman S. Fadeev, Alexey A. Egorov, Artem A. Ashmarin, Kira V. Pyatina, Anatoliy S. Senotov, Irina S. Fadeeva and Vladimir S. Komlev

Technologies 2023, 11(3), 77; https://doi.org/10.3390/technologies11030077 - 15 Jun 2023

Cited by 5 | Viewed by 3676

Abstract

The injectable hydrated calcium phosphate bone-like paste (hCPP) was developed with suitable rheological characteristics, enabling unhindered injection through standard 23G needles. In vitro assays showed the cytocompatibility of hCPP with mesenchymal embryonic C3H10T1/2 cell cultures. The hCPP was composed of aggregated micro-sized particles [...] Read more.

The injectable hydrated calcium phosphate bone-like paste (hCPP) was developed with suitable rheological characteristics, enabling unhindered injection through standard 23G needles. In vitro assays showed the cytocompatibility of hCPP with mesenchymal embryonic C3H10T1/2 cell cultures. The hCPP was composed of aggregated micro-sized particles with sphere-like shapes and low crystallinity. The ability of hCPP particles to adsorb serum proteins (FBS) was investigated. The hCPP demonstrated high protein adsorption capacity, indicating its potential in various biomedical applications. The results of the in vivo assay upon subcutaneous injection in Wistar rats indicated nontoxicity and biocompatibility of experimental hCPP, as well as gradual resorption of hCPP, comparable to the period of bone regeneration. The data obtained are of great interest for the development of commercial highly effective osteoplastic materials for bone tissue regeneration and augmentation. Full article

(This article belongs to the Special Issue Smart Systems (SmaSys2022))

► Show Figures

Figure 1

13 pages, 1635 KB

Open AccessEditor’s ChoiceArticle

Cross-Tier Interference Mitigation for RIS-Assisted Heterogeneous Networks

by Abdel Nasser Soumana Hamadou, Ciira wa Maina and Moussa Moindze Soidridine

Technologies 2023, 11(3), 73; https://doi.org/10.3390/technologies11030073 - 9 Jun 2023

Cited by 6 | Viewed by 4194

Abstract

With the development of the next generation of mobile networks, new research challenges have emerged, and new technologies have been proposed to address them. On the other hand, reconfigurable intelligent surface (RIS) technology is being investigated for partially controlling wireless channels. RIS is [...] Read more.

With the development of the next generation of mobile networks, new research challenges have emerged, and new technologies have been proposed to address them. On the other hand, reconfigurable intelligent surface (RIS) technology is being investigated for partially controlling wireless channels. RIS is a promising technology for improving signal quality by controlling the scattering of electromagnetic waves in a nearly passive manner. Heterogeneous networks (HetNets) are another promising technology that is designed to meet the capacity requirements of the network. RIS technology can be used to improve system performance in the context of HetNets. This study investigates the applications of reconfigurable intelligent surfaces (RISs) in heterogeneous downlink networks (HetNets). Due to the network densification, the small cell base station (SBS) interferes with the macrocell users (MUEs). In this paper, we utilise RIS to mitigate cross-tier interference in a HetNet via directional beamforming by adjusting the phase shift of the RIS. We consider RIS-assisted heterogeneous networks consisting of multiple SBS nodes and MUEs that utilise both direct paths and reflected paths. Therefore, the aim of this study is to maximise the sum rate of all MUEs by jointly optimising the transmit beamforming of the macrocell base station (MBS) and the phase shift of the RIS. An efficient RIS reflecting coefficient-based optimisation (RCO) is proposed based on a successive convex approximation approach. Simulation results are provided to show the effectiveness of the proposed scheme in terms of its sum rate in comparison with the scheme HetNet without RIS and the scheme HetNet with RIS but with random phase shifts. Full article

(This article belongs to the Special Issue Intelligent Reflecting Surfaces for 5G and Beyond)

► Show Figures

Figure 1

14 pages, 1840 KB

Open AccessEditor’s ChoiceArticle

Utilization of Artificial Neural Networks for Precise Electrical Load Prediction

by Christos Pavlatos, Evangelos Makris, Georgios Fotis, Vasiliki Vita and Valeri Mladenov

Technologies 2023, 11(3), 70; https://doi.org/10.3390/technologies11030070 - 26 May 2023

Cited by 52 | Viewed by 4077

Abstract

In the energy-planning sector, the precise prediction of electrical load is a critical matter for the functional operation of power systems and the efficient management of markets. Numerous forecasting platforms have been proposed in the literature to tackle this issue. This paper introduces [...] Read more.

In the energy-planning sector, the precise prediction of electrical load is a critical matter for the functional operation of power systems and the efficient management of markets. Numerous forecasting platforms have been proposed in the literature to tackle this issue. This paper introduces an effective framework, coded in Python, that can forecast future electrical load based on hourly or daily load inputs. The framework utilizes a recurrent neural network model, consisting of two simpleRNN layers and a dense layer, and adopts the Adam optimizer and tanh loss function during the training process. Depending on the size of the input dataset, the proposed system can handle both short-term and medium-term load-forecasting categories. The network was extensively tested using multiple datasets, and the results were found to be highly promising. All variations of the network were able to capture the underlying patterns and achieved a small test error in terms of root mean square error and mean absolute error. Notably, the proposed framework outperformed more complex neural networks, with a root mean square error of 0.033, indicating a high degree of accuracy in predicting future load, due to its ability to capture data patterns and trends. Full article

(This article belongs to the Collection Electrical Technologies)

► Show Figures

Figure 1

17 pages, 807 KB

Open AccessEditor’s ChoiceArticle

Preprocessing Selection for Deep Learning Classification of Arrhythmia Using ECG Time-Frequency Representations

by Rafael Holanda, Rodrigo Monteiro and Carmelo Bastos-Filho

Technologies 2023, 11(3), 68; https://doi.org/10.3390/technologies11030068 - 11 May 2023

Cited by 3 | Viewed by 5524

Abstract

The trend of using deep learning techniques to classify arbitrary tasks has grown significantly in the last decade. Such techniques in the background provide a stack of non-linear functions to solve tasks that cannot be solved in a linear manner. Naturally, deep learning [...] Read more.

The trend of using deep learning techniques to classify arbitrary tasks has grown significantly in the last decade. Such techniques in the background provide a stack of non-linear functions to solve tasks that cannot be solved in a linear manner. Naturally, deep learning models can always solve almost any problem with the right amount of functional parameters. However, with the right set of preprocessing techniques, these models might become much more accessible by negating the need for a large set of model parameters and the concomitant computational costs that accompany the need for many parameters. This paper studies the effects of such preprocessing techniques, and is focused, more specifically, on the resulting learning representations, so as to classify the arrhythmia task provided by the ECG MIT-BIH signal dataset. The types of noise we filter out from such signals are the Baseline Wander (BW) and the Powerline Interference (PLI). The learning representations we use as input to a Convolutional Neural Network (CNN) model are the spectrograms extracted by the Short-time Fourier Transform (STFT) and the scalograms extracted by the Continuous Wavelet Transform (CWT). These features are extracted using different parameter values, such as the window size of the Fourier Transform and the number of scales from the mother wavelet. We highlight that the noise with the most significant influence on a CNN’s classification performance is the BW noise. The most accurate classification performance was achieved using the 64 wavelet scales scalogram with the Mexican Hat and with only the BW noise suppressed. The deployed CNN has less than 90k parameters and achieved an average F1-Score of 90.11%. Full article

(This article belongs to the Section Assistive Technologies)

► Show Figures

Figure 1

11 pages, 2334 KB

Open AccessEditor’s ChoiceCommunication

Identifying Growth Patterns in Arid-Zone Onion Crops (Allium Cepa) Using Digital Image Processing

by David Duarte-Correa, Juvenal Rodríguez-Reséndiz, Germán Díaz-Flórez, Carlos Alberto Olvera-Olvera and José M. Álvarez-Alvarado

Technologies 2023, 11(3), 67; https://doi.org/10.3390/technologies11030067 - 10 May 2023

Cited by 4 | Viewed by 2881

Abstract

The agricultural sector is undergoing a revolution that requires sustainable solutions to the challenges that arise from traditional farming methods. To address these challenges, technical and sustainable support is needed to develop projects that improve crop performance. This study focuses on onion crops [...] Read more.

The agricultural sector is undergoing a revolution that requires sustainable solutions to the challenges that arise from traditional farming methods. To address these challenges, technical and sustainable support is needed to develop projects that improve crop performance. This study focuses on onion crops and the challenges presented throughout its phenological cycle. Unmanned aerial vehicles (UAVs) and digital image processing were used to monitor the crop and identify patterns such as humid areas, weed growth, vegetation deficits, and decreased harvest performance. An algorithm was developed to identify the patterns that most affected crop growth, as the average local production reported was 40.166 tons/ha. However, only 25.00 tons/ha were reached due to blight caused by constant humidity and limited sunlight. This resulted in the death of leaves and poor development of bulbs, with 50% of the production being medium-sized. Approximately 20% of the production was lost due to blight and unfavorable weather conditions. Full article

(This article belongs to the Special Issue Image and Signal Processing)

► Show Figures

Figure 1

7 pages, 460 KB

Open AccessEditor’s ChoiceBrief Report

A Deeper Look into Exercise Intensity Tracking through Mobile Applications: A Brief Report

by Alexie Elder, Gabriel Guillen, Rebecca Isip, Ruben Zepeda and Zakkoyya H. Lewis

Technologies 2023, 11(3), 66; https://doi.org/10.3390/technologies11030066 - 1 May 2023

Cited by 2 | Viewed by 5676

Abstract

Mobile fitness applications (apps) allow for time-efficient opportunities for physical activity. Current research suggests that fitness apps do not accurately comply with the frequency, intensity, time, and type (FITT) principle. FITT is an important principle in exercise prescription as it applies scientific evidence [...] Read more.

Mobile fitness applications (apps) allow for time-efficient opportunities for physical activity. Current research suggests that fitness apps do not accurately comply with the frequency, intensity, time, and type (FITT) principle. FITT is an important principle in exercise prescription as it applies scientific evidence to improve the quality of exercise. Based on app assessment using the Fitness Apps Scoring Instrument, most fitness apps adequately address FITT in their exercise plans. In particular, fitness apps do not adequately adhere to the FITT intensity guidelines. Many apps allow the users to track their heart rate as a method of assessing their exercise intensity, but few use that information to provide real-time feedback on the intensity of the workout. For app users, awareness and education of intensity standards should be put forth in coordination with exercise professionals, rather than relying on apps alone. Full article

(This article belongs to the Special Issue Wearable Technologies III)

► Show Figures

Figure 1

10 pages, 4236 KB

Open AccessEditor’s ChoiceCommunication

Towards Safe Visual Navigation of a Wheelchair Using Landmark Detection

by Christos Sevastopoulos, Mohammad Zaki Zadeh, Michail Theofanidis, Sneh Acharya, Nishi Patel and Fillia Makedon

Technologies 2023, 11(3), 64; https://doi.org/10.3390/technologies11030064 - 25 Apr 2023

Cited by 1 | Viewed by 2832

Abstract

This article presents a method for extracting high-level semantic information through successful landmark detection using 2D RGB images. In particular, the focus is placed on the presence of particular labels (open path, humans, staircase, doorways, obstacles) in the encountered scene, which can be [...] Read more.

This article presents a method for extracting high-level semantic information through successful landmark detection using 2D RGB images. In particular, the focus is placed on the presence of particular labels (open path, humans, staircase, doorways, obstacles) in the encountered scene, which can be a fundamental source of information enhancing scene understanding and paving the path towards the safe navigation of the mobile unit. Experiments are conducted using a manual wheelchair to gather image instances from four indoor academic environments consisting of multiple labels. Afterwards, the fine-tuning of a pretrained vision transformer (ViT) is conducted, and the performance is evaluated through an ablation study versus well-established state-of-the-art deep architectures for image classification such as ResNet. Results show that the fine-tuned ViT outperforms all other deep convolutional architectures while achieving satisfactory levels of generalization. Full article

(This article belongs to the Collection Selected Papers from the PETRA Conference Series)

► Show Figures

Figure 1

11 pages, 1896 KB

Open AccessEditor’s ChoiceCommunication

Research on Outdoor Mobile Music Speaker Battery Management Algorithm Based on Dynamic Redundancy

by Xiaofei Yu, Yanke Li, Xiaonan Li, Licheng Wang and Kai Wang

Technologies 2023, 11(2), 60; https://doi.org/10.3390/technologies11020060 - 18 Apr 2023

Cited by 31 | Viewed by 2804

Abstract

In terms of the battery management system of a mobile music speaker, reliability optimization has always been an important topic. This paper proposes a new dynamic redundant battery management algorithm based on the existing fault-tolerant structure of a lithium battery pack. The internal [...] Read more.

In terms of the battery management system of a mobile music speaker, reliability optimization has always been an important topic. This paper proposes a new dynamic redundant battery management algorithm based on the existing fault-tolerant structure of a lithium battery pack. The internal configuration is adjusted according to the SOC of each battery, and the power supply battery is dynamically allocated. This paper selects four batteries to experiment on with two different algorithms. The simulation results show that compared with the traditional battery management algorithm, the dynamic redundant battery management algorithm extends the battery pack working time by 18.75%, and the energy utilization rate of B₁ and B₄ increases by 96.0% and 99.8%, respectively. This proves that the dynamic redundant battery management algorithm can effectively extend battery working time and improve energy utilization. Full article

► Show Figures

Figure 1

14 pages, 2433 KB

Open AccessEditor’s ChoiceArticle

Photovoltaic Inverter Reliability Study through SiC Switches Redundant Structures

by Ignacio Villanueva, Nimrod Vázquez, Joaquín Vaquero, Claudia Hernández, Héctor López-Tapia and Rene Osorio-Sánchez

Technologies 2023, 11(2), 59; https://doi.org/10.3390/technologies11020059 - 14 Apr 2023

Cited by 5 | Viewed by 3094

Abstract

Reliability is a very important issue in power electronics; however, sometimes it is not considered, studied, or analyzed. At present, renewables have become more popular, and more complex setups are required to drive this type of system. In the specific case of inverters [...] Read more.

Reliability is a very important issue in power electronics; however, sometimes it is not considered, studied, or analyzed. At present, renewables have become more popular, and more complex setups are required to drive this type of system. In the specific case of inverters in photovoltaic systems, the user’s safety, quality, reliability, and the system’s useful life must be guaranteed. In this paper, the reliability of a full bridge inverter is predicted by calculating metrics such as failure rates and Mean Time Between Failures. Reliability is obtained using different types of structures for SiC MOSFETs: serial systems, active parallel redundant systems, and passive parallel redundant systems. Finally, the reliability study shows that a system with a passive parallel redundant structure is more reliable and has a higher useful life compared to the other structures. Full article

(This article belongs to the Collection Electrical Technologies)

► Show Figures

Figure 1

16 pages, 3584 KB

Open AccessEditor’s ChoiceArticle

Computational Investigation of a Tibial Implant Using Topology Optimization and Finite Element Analysis

by Nikolaos Kladovasilakis, Theologos Bountourelis, Konstantinos Tsongas and Dimitrios Tzetzis

Technologies 2023, 11(2), 58; https://doi.org/10.3390/technologies11020058 - 13 Apr 2023

Cited by 10 | Viewed by 3548

Abstract

Additive manufacturing methods enable the rapid fabrication of fully functional customized objects with complex geometry and lift the limitations of traditional manufacturing techniques, such as machining. Therefore, the structural optimization of parts has concentrated increased scientific interest and more especially for topology optimization [...] Read more.

Additive manufacturing methods enable the rapid fabrication of fully functional customized objects with complex geometry and lift the limitations of traditional manufacturing techniques, such as machining. Therefore, the structural optimization of parts has concentrated increased scientific interest and more especially for topology optimization (TO) processes. In this paper, the working principles and the two approaches of the TO procedures were analyzed along with an investigation and a comparative study of a novel case study for the TO processes of a tibial implant designed for additive manufacturing (DfAM). In detail, the case study focused on the TO of a tibial implant for knee replacement surgery in order to improve the overall design and enhance its efficiency and the rehabilitation process. An initial design of a customized tibial implant was developed utilizing reserve engineering procedures with DICOM files from a CT scan machine. The mechanical performance of the designed implant was examined via finite element analyses (FEA) under realistic static loads. The TO was conducted with two distinct approaches, namely density-based and discrete-based, to compare them and lead to the best approach for biomechanical applications. The overall performance of each approach was evaluated through FEA, and its contribution to the final mass reduction was measured. Through this study, the maximum reduction in the implant’s mass was achieved by maintaining the mechanical performance at the desired levels and the best approach was pointed out. To conclude, with the discrete-based approach, a mass reduction of around 45% was achieved, almost double of the density-based approach, offering on the part physical properties which provide comprehensive advantages for biomechanical application. Full article

► Show Figures

Figure 1

17 pages, 1314 KB

Open AccessEditor’s ChoiceArticle

A Novel Methodology for Human Kinematics Motion Detection Based on Smartphones Sensor Data Using Artificial Intelligence

by Ali Raza, Mohammad Rustom Al Nasar, Essam Said Hanandeh, Raed Abu Zitar, Ahmad Yacoub Nasereddin and Laith Abualigah

Technologies 2023, 11(2), 55; https://doi.org/10.3390/technologies11020055 - 11 Apr 2023

Cited by 22 | Viewed by 5691

Abstract

Kinematic motion detection aims to determine a person’s actions based on activity data. Human kinematic motion detection has many valuable applications in health care, such as health monitoring, preventing obesity, virtual reality, daily life monitoring, assisting workers during industry manufacturing, caring for the [...] Read more.

Kinematic motion detection aims to determine a person’s actions based on activity data. Human kinematic motion detection has many valuable applications in health care, such as health monitoring, preventing obesity, virtual reality, daily life monitoring, assisting workers during industry manufacturing, caring for the elderly. Computer vision-based activity recognition is challenging due to problems such as partial occlusion, background clutter, appearance, lighting, viewpoint, and changes in scale. Our research aims to detect human kinematic motions such as walking or running using smartphones’ sensor data within a high-performance framework. An existing dataset based on smartphones’ gyroscope and accelerometer sensor values is utilized for the experiments in our study. Sensor exploratory data analysis was conducted in order to identify valuable patterns and insights from sensor values. The six hyperparameters, tunned artificial indigence-based machine learning, and deep learning techniques were applied for comparison. Extensive experimentation showed that the ensemble learning-based novel ERD (ensemble random forest decision tree) method outperformed other state-of-the-art studies with high-performance accuracy scores. The proposed ERD method combines the random forest and decision tree models, which achieved a 99% classification accuracy score. The proposed method was successfully validated with the k-fold cross-validation approach. Full article

(This article belongs to the Special Issue Wearable Technologies III)

► Show Figures

Figure 1

15 pages, 1994 KB

Open AccessEditor’s ChoiceArticle

Visual Performance and Perceptual–Motor Skills of Late Preterm Children and Healthy Controls Using the TVPS-3rd and VMI-6th Editions

by Danjela Ibrahimi, Jorge D. Mendiola Santibañez and Juvenal Rodríguez-Reséndiz

Technologies 2023, 11(2), 53; https://doi.org/10.3390/technologies11020053 - 4 Apr 2023

Cited by 3 | Viewed by 3754

Abstract

Background: The visual system is key to the learning process, preterm births are commonly followed by visual dysfunctions and other neurological conditions. Objective: to measure, analyze and compare the visual efficacy, visual–perceptual, and visual–motor skills of 20 late preterm children (34–36 weeks) born [...] Read more.

Background: The visual system is key to the learning process, preterm births are commonly followed by visual dysfunctions and other neurological conditions. Objective: to measure, analyze and compare the visual efficacy, visual–perceptual, and visual–motor skills of 20 late preterm children (34–36 weeks) born by caesarean section and appropriate weight for gestational age with 20 healthy controls born at full term by natural birth, age 5 to 12 years, from Querétaro, México. Methods: This was an observational, transverse, and prospective study. Parametric and non-parametric tests were performed using the SPSS 25.0. The visual acuity at distance and near, the phoria state, and the degree of stereopsis were analyzed. The Test of Visual-Perceptual Skills, Third Edition, was used to assess the overall performance, basic, sequencing, and complex processes. Fine motor skills were evaluated using the Visual–Motor Integration Test of Beery, Sixth Edition. Results: Visual acuity at distance and near (

p < 0.001

), stereopsis (

p < 0.001

), and the amount of exophoria at distance (

p = 0.01

) showed statistically significant differences between the groups. The overall performance (

p = 0.006

), basic processes (

p = 0.001

), sequencing processes (

p = 0.02

), and General and Motor VMI (

p < 0.001

and

0.002

, respectively) presented lower values in children born preterm. Conclusion: This research showed that even late preterm children present visual deficiencies and are at risk of delays on perceptual–motor skills. Early evaluation of their visual and motor abilities should be considered in order to help improve their cognitive functioning. Full article

(This article belongs to the Special Issue Smart Systems (SmaSys2022))

► Show Figures

Figure 1

11 pages, 4140 KB

Open AccessEditor’s ChoiceCommunication

HAIS: Highways Automated-Inspection System

by Hossam A. Gabbar, Abderrazak Chahid, Manir U. Isham, Shashwat Grover, Karan Pal Singh, Khalid Elgazzar, Ahmad Mousa and Hossameldin Ouda

Technologies 2023, 11(2), 51; https://doi.org/10.3390/technologies11020051 - 1 Apr 2023

Cited by 9 | Viewed by 4108

Abstract

A smart city is a trending concept describing a new generation of cities operated intelligently with minimal human intervention. It promotes energy sustainability, minimal environmental impact, and better governance. In transportation, the remote highway infrastructure monitoring will enhance the driver’s safety, continuously report [...] Read more.

A smart city is a trending concept describing a new generation of cities operated intelligently with minimal human intervention. It promotes energy sustainability, minimal environmental impact, and better governance. In transportation, the remote highway infrastructure monitoring will enhance the driver’s safety, continuously report road conditions, and identify potential hazardous incidents such as accidents, floods, or snow storms. In addition, it facilitates the integration of future cuttingedge technologies such as self-driving vehicles. This paper presents a general introduction to a smart monitoring system for automated real-time road condition inspection. The proposed solution includes hardware devices/nodes and software applications for data processing, road condition inspection using hybrid algorithms based on digital signal processing, and artificial intelligence technologies. The proposed system has an interactive web interface for real-time data sharing, infrastructure monitoring, visualization, and management of inspection reports which can improve the maintenance process. Full article

(This article belongs to the Topic Emerging Technologies for Grid-Interactive Efficient Buildings and Communities)

► Show Figures

Figure 1

18 pages, 1984 KB

Open AccessEditor’s ChoiceArticle

Forecasting by Combining Chaotic PSO and Automated LSSVR

by Wei-Chang Yeh and Wenbo Zhu

Technologies 2023, 11(2), 50; https://doi.org/10.3390/technologies11020050 - 30 Mar 2023

Cited by 7 | Viewed by 2257

Abstract

An automatic least square support vector regression (LSSVR) optimization method that uses mixed kernel chaotic particle swarm optimization (CPSO) to handle regression issues has been provided. The LSSVR model is composed of three components. The position of the particles (solution) in a chaotic [...] Read more.

An automatic least square support vector regression (LSSVR) optimization method that uses mixed kernel chaotic particle swarm optimization (CPSO) to handle regression issues has been provided. The LSSVR model is composed of three components. The position of the particles (solution) in a chaotic sequence with good randomness and ergodicity of the initial characteristics is taken into consideration in the first section. The binary particle swarm optimization (PSO) used to choose potential input characteristic combinations makes up the second section. The final step involves using a chaotic search to narrow down the set of potential input characteristics before combining the PSO-optimized parameters to create CP-LSSVR. The CP-LSSVR is used to forecast the impressive datasets testing targets obtained from the UCI dataset for purposes of illustration and evaluation. The results suggest CP-LSSVR has a good predictive capability discussed in this paper and can build a projected model utilizing a limited number of characteristics. Full article

(This article belongs to the Special Issue 10th Anniversary of Technologies—Recent Advances and Perspectives)

► Show Figures

Figure 1

19 pages, 11909 KB

Open AccessEditor’s ChoiceArticle

Image-Based Quantification of Color and Its Machine Vision and Offline Applications

by Woo Sik Yoo, Kitaek Kang, Jung Gon Kim and Yeongsik Yoo

Technologies 2023, 11(2), 49; https://doi.org/10.3390/technologies11020049 - 29 Mar 2023

Cited by 5 | Viewed by 6261

Abstract

Image-based colorimetry has been gaining relevance due to the wide availability of smart phones with image sensors and increasing computational power. The low cost and portable designs with user-friendly interfaces, and their compatibility with data acquisition and processing, are very attractive for interdisciplinary [...] Read more.

Image-based colorimetry has been gaining relevance due to the wide availability of smart phones with image sensors and increasing computational power. The low cost and portable designs with user-friendly interfaces, and their compatibility with data acquisition and processing, are very attractive for interdisciplinary applications from art, the fashion industry, food science, medical science, oriental medicine, agriculture, geology, chemistry, biology, material science, environmental engineering, and many other applications. This work describes the image-based quantification of color and its machine vision and offline applications in interdisciplinary fields using specifically developed image analysis software. Examples of color information extraction from a single pixel to predetermined sizes/shapes of areas, including customized regions of interest (ROIs) from various digital images of dyed T-shirts, tongues, and assays, are demonstrated. Corresponding RGB, HSV, CIELAB, Munsell color, and hexadecimal color codes, from a single pixel to ROIs, are extracted for machine vision and offline applications in various fields. Histograms and statistical analyses of colors from a single pixel to ROIs are successfully demonstrated. Reliable image-based quantification of color, in a wide range of potential applications, is proposed and the validity is verified using color quantification examples in various fields of applications. The objectivity of color-based diagnosis, judgment and control can be significantly improved by the image-based quantification of color proposed in this study. Full article

(This article belongs to the Special Issue Image and Signal Processing)

► Show Figures

Figure 1

19 pages, 10511 KB

Open AccessEditor’s ChoiceArticle

Mobilenetv2_CA Lightweight Object Detection Network in Autonomous Driving

by Peicheng Shi, Long Li, Heng Qi and Aixi Yang

Technologies 2023, 11(2), 47; https://doi.org/10.3390/technologies11020047 - 23 Mar 2023

Cited by 3 | Viewed by 3196

Abstract

A lightweight network target detection algorithm was proposed, based on MobileNetv2_CA, focusing on the problem of high complexity, a large number of parameters, and the missed detection of small targets in the target detection network based on candidate regions and regression methods in [...] Read more.

A lightweight network target detection algorithm was proposed, based on MobileNetv2_CA, focusing on the problem of high complexity, a large number of parameters, and the missed detection of small targets in the target detection network based on candidate regions and regression methods in autonomous driving scenarios. First, Mosaic image enhancement technology is used in the data pre-processing stage to enhance the feature extraction of small target scenes and complex scenes; second, the Coordinate Attention (CA) mechanism is embedded into the Mobilenetv2 backbone feature extraction network, combined with the PANet and Yolo detection heads for multi-scale feature fusion; finally, a Lightweight Object Detection Network is built. The experimental test results show that the designed network obtained the highest average detection accuracy of 81.43% on the Voc2007 + 2012 dataset, and obtained the highest average detection accuracy of 85.07% and a detection speed of 31.84 FPS on the KITTI dataset. The total amount of network parameters is only 39.5 M. This is beneficial to the engineering application of MobileNetv2 network in automatic driving. Full article

(This article belongs to the Special Issue Image and Signal Processing)

► Show Figures

Figure 1

17 pages, 2022 KB

Open AccessEditor’s ChoiceReview

How to Bell the Cat? A Theoretical Review of Generative Artificial Intelligence towards Digital Disruption in All Walks of Life

by Subhra Mondal, Subhankar Das and Vasiliki G. Vrana

Technologies 2023, 11(2), 44; https://doi.org/10.3390/technologies11020044 - 17 Mar 2023

Cited by 204 | Viewed by 20493

Abstract

Generative Artificial Intelligence (GAI) has brought revolutionary changes to the world, enabling businesses to create new experiences by combining virtual and physical worlds. As the use of GAI grows along with the Metaverse, it is explored by academics, researchers, and industry communities for [...] Read more.

Generative Artificial Intelligence (GAI) has brought revolutionary changes to the world, enabling businesses to create new experiences by combining virtual and physical worlds. As the use of GAI grows along with the Metaverse, it is explored by academics, researchers, and industry communities for its endless possibilities. From ChatGPT by OpenAI to Bard AI by Google, GAI is a leading technology in physical and virtual business platforms. This paper focuses on GAI’s economic and societal impact and the challenges it poses. Businesses must rethink their operations and strategies to create hybrid physical and virtual experiences using GAI. This study proposes a framework that can help business managers develop effective strategies to enhance their operations. It analyzes the initial applications of GAI in multiple sectors to promote the development of future customer solutions and explores how GAI can help businesses create new value propositions and experiences for their customers, and the possibilities of digital communication and information technology. A research agenda is proposed for developing GAI for business management to enhance organizational efficiency. The results highlight a healthy conversation on the potential of GAI in various business sectors to improve customer experience. Full article

(This article belongs to the Section Information and Communication Technologies)

► Show Figures

Figure 1

14 pages, 277 KB

Open AccessEditor’s ChoiceReview

A Review of Deep Transfer Learning and Recent Advancements

by Mohammadreza Iman, Hamid Reza Arabnia and Khaled Rasheed

Technologies 2023, 11(2), 40; https://doi.org/10.3390/technologies11020040 - 14 Mar 2023

Cited by 455 | Viewed by 41703

Abstract

Deep learning has been the answer to many machine learning problems during the past two decades. However, it comes with two significant constraints: dependency on extensive labeled data and training costs. Transfer learning in deep learning, known as Deep Transfer Learning (DTL), attempts [...] Read more.

Deep learning has been the answer to many machine learning problems during the past two decades. However, it comes with two significant constraints: dependency on extensive labeled data and training costs. Transfer learning in deep learning, known as Deep Transfer Learning (DTL), attempts to reduce such reliance and costs by reusing obtained knowledge from a source data/task in training on a target data/task. Most applied DTL techniques are network/model-based approaches. These methods reduce the dependency of deep learning models on extensive training data and drastically decrease training costs. Moreover, the training cost reduction makes DTL viable on edge devices with limited resources. Like any new advancement, DTL methods have their own limitations, and a successful transfer depends on specific adjustments and strategies for different scenarios. This paper reviews the concept, definition, and taxonomy of deep transfer learning and well-known methods. It investigates the DTL approaches by reviewing applied DTL techniques in the past five years and a couple of experimental analyses of DTLs to discover the best practice for using DTL in different scenarios. Moreover, the limitations of DTLs (catastrophic forgetting dilemma and overly biased pre-trained models) are discussed, along with possible solutions and research trends. Full article

(This article belongs to the Special Issue Data Science and Big Data in Biology, Physical Science and Engineering)

► Show Figures

Figure 1

23 pages, 5488 KB

Open AccessEditor’s ChoiceArticle

Non-Contact In-Vehicle Occupant Monitoring System Based on Point Clouds from FMCW Radar

by Yixuan Chen, Yunlong Luo, Jianhua Ma, Alex Qi, Runhe Huang, Francesco De Paulis and Yihong Qi

Technologies 2023, 11(2), 39; https://doi.org/10.3390/technologies11020039 - 13 Mar 2023

Cited by 10 | Viewed by 4986

Abstract

In order to reduce the probability of automobile safety incidents, the in-vehicle occupant monitoring is indispensable. However, occupant monitoring using frequency-modulated continuous wave (FMCW) radar can be challenging due to the interference from passengers’ posture, movement, and the presence of multiple people. This [...] Read more.

In order to reduce the probability of automobile safety incidents, the in-vehicle occupant monitoring is indispensable. However, occupant monitoring using frequency-modulated continuous wave (FMCW) radar can be challenging due to the interference from passengers’ posture, movement, and the presence of multiple people. This paper proposes an improved method for generating point clouds using FMCW radar. The approach involves point cloud clustering, post-processing operations such as segmentation, merging, and filtering of the clustered point cloud to match the actual in-vehicle environment, and a state machine combination step. Experimental results show that the proposed method can achieve high recognition accuracy in scenarios with multiple passengers who are moving and sitting in a relaxed manner. Full article

(This article belongs to the Section Information and Communication Technologies)

► Show Figures

Figure 1

15 pages, 3882 KB

Open AccessEditor’s ChoiceReview

Aging Mechanism and Models of Supercapacitors: A Review

by Ning Ma, Dongfang Yang, Saleem Riaz, Licheng Wang and Kai Wang

Technologies 2023, 11(2), 38; https://doi.org/10.3390/technologies11020038 - 3 Mar 2023

Cited by 79 | Viewed by 10719

Abstract

Electrochemical supercapacitors are a promising type of energy storage device with broad application prospects. Developing an accurate model to reflect their actual working characteristics is of great research significance for rational utilization, performance optimization, and system simulation of supercapacitors. This paper presents the [...] Read more.

Electrochemical supercapacitors are a promising type of energy storage device with broad application prospects. Developing an accurate model to reflect their actual working characteristics is of great research significance for rational utilization, performance optimization, and system simulation of supercapacitors. This paper presents the fundamental working principle and applications of supercapacitors, analyzes their aging mechanism, summarizes existing supercapacitor models, and evaluates the characteristics and application scope of each model. By examining the current state and limitations of supercapacitor modeling research, this paper identifies future development trends and research focuses in this area. Full article

(This article belongs to the Special Issue 10th Anniversary of Technologies—Recent Advances and Perspectives)

► Show Figures

Figure 1

29 pages, 2313 KB

Open AccessEditor’s ChoiceArticle

Reconstruction of Industrial and Historical Heritage for Cultural Enrichment Using Virtual and Augmented Reality

by Lukas Paulauskas, Andrius Paulauskas, Tomas Blažauskas, Robertas Damaševičius and Rytis Maskeliūnas

Technologies 2023, 11(2), 36; https://doi.org/10.3390/technologies11020036 - 25 Feb 2023

Cited by 36 | Viewed by 7335

Abstract

Because of its benefits in providing an engaging and mobile environment, virtual reality (VR) has recently been rapidly adopted and integrated in education and professional training. Augmented reality (AR) is the integration of VR with the real world, where the real world provides [...] Read more.

Because of its benefits in providing an engaging and mobile environment, virtual reality (VR) has recently been rapidly adopted and integrated in education and professional training. Augmented reality (AR) is the integration of VR with the real world, where the real world provides context and the virtual world provides or reconstructs missing information. Mixed reality (MR) is the blending of virtual and physical reality environments allowing users to interact with both digital and physical objects at the same time. In recent years, technology for creating reality-based 3D models has advanced and spread across a diverse range of applications and research fields. The purpose of this paper is to design, develop, and test VR for kinaesthetic distance learning in a museum setting. A VR training program has been developed in which learners can select and perform pre-made scenarios in a virtual environment. The interaction in the program is based on kinaesthetic learning characteristics. Scenarios with VR controls simulate physical interaction with objects in a virtual environment for learners. Learners can grasp and lift objects to complete scenario tasks. There are also simulated devices in the virtual environment that learners can use to perform various actions. The study’s goal was to compare the effectiveness of the developed VR educational program to that of other types of educational material. Our innovation is the development of a system for combining their 3D visuals with rendering capable of providing a mobile VR experience for effective heritage enhancement. Full article

(This article belongs to the Special Issue Immersive Technologies and Applications on Arts, Culture and Tourism)

► Show Figures

Figure 1

15 pages, 14241 KB

Open AccessEditor’s ChoiceArticle

Dual-Band Rectifier Circuit Design for IoT Communication in 5G Systems

by Ioannis D. Bougas, Maria S. Papadopoulou, Achilles D. Boursianis, Spyridon Nikolaidis and Sotirios K. Goudos

Technologies 2023, 11(2), 34; https://doi.org/10.3390/technologies11020034 - 24 Feb 2023

Cited by 8 | Viewed by 4058

Abstract

Radio-frequency (RF) energy harvesting (EH) is emerging as a reliable and constantly available free energy source. The primary factor determining whether this energy can be utilized is how efficiently it can be collected. In this work, an RF EH system is presented. More [...] Read more.

Radio-frequency (RF) energy harvesting (EH) is emerging as a reliable and constantly available free energy source. The primary factor determining whether this energy can be utilized is how efficiently it can be collected. In this work, an RF EH system is presented. More particularly, we designed a dual-band RF to DC rectifier circuit at sub-6 GHz in the 5G bands, able to supply low-power sensors and microcontrollers used in agriculture, the military, or health services. The system operates at

3.5

GHz and 5 GHz in the 5G cellular network’s frequency band FR1. Numerical results reveal that the system provides maximum power conversion efficiency (PCE) equal to 53% when the output load (sensor or microcontroller) is

1.74

kΩ and the input power is 12 dBm. Full article

(This article belongs to the Special Issue Intelligent Reflecting Surfaces for 5G and Beyond)

► Show Figures

Figure 1

28 pages, 1321 KB

Open AccessEditor’s ChoiceArticle

A Layer-Wise Coupled Thermo-Elastic Shell Model for Three-Dimensional Stress Analysis of Functionally Graded Material Structures

by Salvatore Brischetto, Domenico Cesare and Roberto Torre

Technologies 2023, 11(2), 35; https://doi.org/10.3390/technologies11020035 - 24 Feb 2023

Cited by 8 | Viewed by 2919

Abstract

In this work, a coupled 3D thermo-elastic shell model is presented. The primary variables are the scalar sovra-temperature and the displacement vector. This model allows for the thermal stress analysis of one-layered and sandwich plates and shells embedding Functionally Graded Material (FGM) layers. [...] Read more.

In this work, a coupled 3D thermo-elastic shell model is presented. The primary variables are the scalar sovra-temperature and the displacement vector. This model allows for the thermal stress analysis of one-layered and sandwich plates and shells embedding Functionally Graded Material (FGM) layers. The 3D equilibrium equations and the 3D Fourier heat conduction equation for spherical shells are put together into a set of four coupled equations. They automatically degenerate in those for simpler geometries thanks to proper considerations about the radii of curvature and the use of orthogonal mixed curvilinear coordinates

α

,

β

, and z. The obtained partial differential governing the equations along the thickness direction are solved using the exponential matrix method. The closed form solution is possible assuming simply supported boundary conditions and proper harmonic forms for all the unknowns. The sovra-temperature amplitudes are directly imposed at the outer surfaces for each geometry in steady-state conditions. The effects of the thermal environment are related to the sovra-temperature profiles through the thickness. The static responses are evaluated in terms of displacements and stresses. After a proper and global preliminary validation, new cases are presented for different thickness ratios, geometries, and temperature values at the external surfaces. The considered FGM is metallic at the bottom and ceramic at the top. This FGM layer can be embedded in a sandwich configuration or in a one-layered configuration. This new fully coupled thermo-elastic model provides results that are coincident with the results proposed by the uncoupled thermo-elastic model that separately solves the 3D Fourier heat conduction equation. The differences are always less than 0.5% for each investigated displacement, temperature, and stress component. The differences between the present 3D full coupled model and the the advantages of this new model are clearly shown. Both the thickness layer and material layer effects are directly included in all the conducted coupled thermal stress analyses. Full article

(This article belongs to the Special Issue 10th Anniversary of Technologies—Recent Advances and Perspectives)

► Show Figures

Figure 1

Journal Menu

Journal Browser

Editor’s Choice Articles

Further Information

Guidelines

MDPI Initiatives

Follow MDPI