Technologies

36 pages, 817 KiB

Open AccessArticle

Empowering Government Efficiency Through Civic Intelligence: Merging Artificial Intelligence and Blockchain for Smart Citizen Proposals

by Andrey Nechesov and Janne Ruponen

Technologies 2024, 12(12), 271; https://doi.org/10.3390/technologies12120271 - 23 Dec 2024

Viewed by 914

Abstract

Civic intelligence (CI) represents the collective capacity of communities to address challenges, yet its integration with smart city infrastructure remains limited. This study bridges CI theory with technical implementation through a novel framework combining blockchain and AI technologies. Our approach maps core CI [...] Read more.

Civic intelligence (CI) represents the collective capacity of communities to address challenges, yet its integration with smart city infrastructure remains limited. This study bridges CI theory with technical implementation through a novel framework combining blockchain and AI technologies. Our approach maps core CI components (knowledge capital, system capital, and relational capital) to specific technical solutions: a civic engagement index for measuring participation quality, a tokenization framework for incentivizing meaningful engagement, and a governance optimization function for resource allocation. Using mixed-methods research, we developed and validated the conceptual CI governance (CIG) framework, which satisfies CI principles through smart contracts and AI-assisted interfaces. The empirical evaluation demonstrates both social and technical improvements: 40% increased civic participation rates, 85% governance efficiency maintenance, and significant gains in engagement quality metrics (knowledge sharing +32%, collective decision making +28%). While technical implementation shows promise, success requires the careful integration of social dynamics, digital literacy initiatives, and regulatory compliance. This research contributes to smart city development by providing a theoretically grounded, feasible framework that introduces the fusion of blockchain and AI technologies to enhance civic participation while preserving governance effectiveness. Full article

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

► Show Figures

Figure 1

11 pages, 4385 KiB

Open AccessArticle

The Impact of Autonomous Vehicle Accidents on Public Sentiment: A Decadal Analysis of Twitter Discourse Using roBERTa

by Romy Sauvayre, Jessica S. M. Gable, Adam Aalah, Melvin Fernandes Novo, Maxime Dehondt and Cédric Chauvière

Technologies 2024, 12(12), 270; https://doi.org/10.3390/technologies12120270 - 23 Dec 2024

Viewed by 709

Abstract

In the field of autonomous vehicle (AV) acceptance and opinion studies, questionnaires are widely used. Additionally, AV experiments and driving simulations are utilized. However, few AV studies have investigated social media, and fewer studies have analyzed the impact of AV crashes on public [...] Read more.

In the field of autonomous vehicle (AV) acceptance and opinion studies, questionnaires are widely used. Additionally, AV experiments and driving simulations are utilized. However, few AV studies have investigated social media, and fewer studies have analyzed the impact of AV crashes on public opinion, often relying on limited social media datasets. This study aims to address this gap by exploring a comprehensive dataset of six million tweets posted over a decade (2012–2021), and neural networks, sentiment analysis and knowledge graphs are applied. The results reveal that tweets predominantly convey negative sentiment (40.86%) rather than positive (32.52%) or neutral (26.62%) sentiment. A binary segmentation algorithm was used to distinguish an initial positive sentiment period (January 2012–May 2016) followed by a negative period (June 2016–December 2021), which was initiated by a fatal Tesla accident and reinforced by a pedestrian killed by an Uber AV. The sentiment polarity exhibited in the posted tweets was statistically significant (U = 24,914,037,786; p value < 0.001). The timeline analysis revealed that the negative sentiment period was initiated by fatal accidents involving a Tesla AV driver and a pedestrian hit by an Uber AV, which was amplified by the mainstream media. Full article

(This article belongs to the Special Issue Advanced Autonomous Systems and Artificial Intelligence Stage)

► Show Figures

Figure 1

25 pages, 1378 KiB

Open AccessArticle

UWB Chaotic Pulse-Based Ranging: Time-of-Flight Approach

by Vladimir A. Prokhorov, Lev V. Kuzmin, Andrey A. Krivenko, Pavel A. Vladyka and Elena V. Efremova

Technologies 2024, 12(12), 269; https://doi.org/10.3390/technologies12120269 - 20 Dec 2024

Viewed by 783

Abstract

Nowadays, indoor positioning using ultra-wideband (UWB) signals is actively being developed with the aim of implementing existing ideas and solutions, improving their performance, and searching for new measurement schemes. This paper proposes an approach to estimating the distance between wireless nodes by measuring [...] Read more.

Nowadays, indoor positioning using ultra-wideband (UWB) signals is actively being developed with the aim of implementing existing ideas and solutions, improving their performance, and searching for new measurement schemes. This paper proposes an approach to estimating the distance between wireless nodes by measuring radio signal propagation time using UWB chaotic radio pulses and UWB transceivers. This type of signal is a simple and practically interesting alternative to radio carriers of other types of UWB signals, which are based on packets of pulses (usually ultra-short pulses). The practical interest is caused by the noise-like nature of chaotic radio pulses, as well as their immunity to multipath fading and ease of generation. The aim of this work is to analyze such a system and identify the fundamental limitations inherent in the proposed approach. This paper describes a wireless system for measuring the signal propagation time based on the envelope of chaotic radio pulses using the SS-TWR (Single-Sided Two-Way Ranging) method. A difference scheme is used to determine the range. The characteristics of the proposed system are studied experimentally. The factors related to the threshold scheme for determining the time of arrival of a radio signal that introduce a systematic error into the measurement results are revealed, and approaches to correcting their influence are proposed. Full article

(This article belongs to the Special Issue IoT-Enabling Technologies and Applications)

► Show Figures

Figure 1

4 pages, 166 KiB

Open AccessEditorial

Networking, Computing and Immersive Technologies for Smart Environments

by Konstantinos Oikonomou and Vasileios Komianos

Technologies 2024, 12(12), 268; https://doi.org/10.3390/technologies12120268 - 20 Dec 2024

Viewed by 763

Abstract

Smart environments encompass a large set of technologies, including computer networking, wireless communication, computational infrastructures, sensor networks, and algorithm design [...] Full article

(This article belongs to the Special Issue Networking, Computing and Immersive Technologies for Smart Environments)

45 pages, 7034 KiB

Open AccessReview

A Review of Fused Filament Fabrication of Metal Parts (Metal FFF): Current Developments and Future Challenges

by Johnson Jacob, Dejana Pejak Simunec, Ahmad E. Z. Kandjani, Adrian Trinchi and Antonella Sola

Technologies 2024, 12(12), 267; https://doi.org/10.3390/technologies12120267 - 19 Dec 2024

Viewed by 1198

Abstract

Fused filament fabrication (FFF) is the most widespread and versatile material extrusion (MEX) technique. Although powder-based systems have dominated the metal 3D printing landscape in the past, FFF’s popularity for producing metal parts (“metal FFF”) is growing. Metal FFF starts from a polymer–metal [...] Read more.

Fused filament fabrication (FFF) is the most widespread and versatile material extrusion (MEX) technique. Although powder-based systems have dominated the metal 3D printing landscape in the past, FFF’s popularity for producing metal parts (“metal FFF”) is growing. Metal FFF starts from a polymer–metal composite feedstock and proceeds through three primary stages, namely shaping (i.e., printing), debinding, and sintering. As critically discussed in the present review, the final quality of metal FFF parts is influenced by the characteristics of the composite feedstock, such as the metal loading, polymer backbone, and presence of additives, as well as by the processing conditions. The literature shows that a diverse array of metals, including steel, copper, titanium, aluminium, nickel, and their alloys, can be successfully used in metal FFF. However, the formulation of appropriate polymer binders represents a hurdle to the adoption of new material systems. Meanwhile, intricate geometries are difficult to fabricate due to FFF-related surface roughness and sintering-induced shrinkage. Nonetheless, the comparison of metal FFF with other common metal AM techniques conducted herein suggests that metal FFF represents a convenient option, especially for prototyping and small-scale production. Whilst providing insights into the functioning mechanisms of metal FFF, the present review offers valuable recommendations, facilitating the broader uptake of metal FFF across various industries. Full article

(This article belongs to the Section Innovations in Materials Processing)

► Show Figures

Graphical abstract

20 pages, 5610 KiB

Open AccessArticle

Numerical Simulations of Thermodynamic Processes in the Chamber of a Liquid Piston Compressor for Hydrogen Applications

by Valerijs Bezrukovs, Vladislavs Bezrukovs, Marina Konuhova, Deniss Bezrukovs, Imants Kaldre and Anatoli I. Popov

Technologies 2024, 12(12), 266; https://doi.org/10.3390/technologies12120266 - 18 Dec 2024

Viewed by 854

Abstract

This paper presents the results of numerical simulations examining the thermodynamic processes during hydraulic hydrogen compression, using COMSOL Multiphysics^® 6.0. These simulations focus on the application of hydrogen compression systems, particularly in hydrogen refueling stations. The computational models employ the CFD and [...] Read more.

This paper presents the results of numerical simulations examining the thermodynamic processes during hydraulic hydrogen compression, using COMSOL Multiphysics^® 6.0. These simulations focus on the application of hydrogen compression systems, particularly in hydrogen refueling stations. The computational models employ the CFD and heat transfer modules, along with deforming mesh technology, to simulate gas compression and heat transfer dynamics. The superposition method was applied to simplify the analysis of hydrogen and liquid piston interactions within a stainless-steel chamber, accounting for heat exchange between the hydrogen, the oil (working fluid), and the cylinder walls. The study investigates the effects of varying compression stroke durations and initial hydrogen pressures, providing detailed insights into temperature distributions and energy consumption under different conditions. The results reveal that the upper region of the chamber experiences significant heating, highlighting the need for efficient cooling systems. Additionally, the simulations show that longer compression strokes reduce the power requirement for the liquid pump, offering potential for optimizing system design and reducing equipment costs. This study offers crucial data for enhancing the efficiency of hydraulic hydrogen compression systems, paving the way for improved energy consumption and thermal management in high-pressure applications. Full article

(This article belongs to the Special Issue Technological Advances in Science, Medicine, and Engineering 2024)

► Show Figures

Figure 1

17 pages, 810 KiB

Open AccessArticle

Unlocking Healthcare Data Potential: A Comprehensive Integration Approach with GraphQL, openEHR, Redis, and Pervasive Business Intelligence

by Regina Sousa, Vasco Abelha, Hugo Peixoto and José Machado

Technologies 2024, 12(12), 265; https://doi.org/10.3390/technologies12120265 - 17 Dec 2024

Viewed by 1018

Abstract

This paper investigates the transformative potential of integrating technical and methodological tools such as GraphQL, openEHR, Redis, and Pervasive Business Intelligence in healthcare. Modern healthcare systems face data silos, interoperability, and efficient data communication challenges. The integration of these technologies offers innovative solutions [...] Read more.

This paper investigates the transformative potential of integrating technical and methodological tools such as GraphQL, openEHR, Redis, and Pervasive Business Intelligence in healthcare. Modern healthcare systems face data silos, interoperability, and efficient data communication challenges. The integration of these technologies offers innovative solutions to address these challenges. GraphQL, known for its flexible data retrieval capabilities, simplifies data communication and integration. openEHR, a standards-based approach to healthcare data management, fosters interoperability through a unified data model. Redis, a scalable data storage and caching system, enhances application performance and real-time data processing. Pervasive Business Intelligence empowers healthcare analytics, aiding data-driven decision-making by enabling an integrated Electronic Health Record. This paper explores these technologies’ benefits, integration possibilities, and synergies. The practical implications of this integration are demonstrated through a real-world case study. The findings underscore the potential to revolutionize healthcare data management, communication, and analysis, improving patient care and operational efficiency. Full article

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

► Show Figures

Graphical abstract

25 pages, 3823 KiB

Open AccessArticle

Performance Evaluation of Various Deep Learning Models in Gait Recognition Using the CASIA-B Dataset

by Nakib Aman, Md. Rabiul Islam, Md. Faysal Ahamed and Mominul Ahsan

Technologies 2024, 12(12), 264; https://doi.org/10.3390/technologies12120264 - 17 Dec 2024

Viewed by 1009

Abstract

Human gait recognition (HGR) has been employed as a biometric technique for security purposes over the last decade. Various factors, including clothing, carrying items, and walking surfaces, can influence the performance of gait recognition. Additionally, identifying individuals from different viewpoints presents a significant [...] Read more.

Human gait recognition (HGR) has been employed as a biometric technique for security purposes over the last decade. Various factors, including clothing, carrying items, and walking surfaces, can influence the performance of gait recognition. Additionally, identifying individuals from different viewpoints presents a significant challenge in HGR. Numerous conventional and deep learning techniques have been introduced in the literature for HGR, but traditional methods are not well suited to handling large datasets. This research explores the effectiveness of four deep learning models for gait identification in the CASIA B dataset: the convolutional neural network (CNN), multi-layer perceptron (MLP), self-organizing map (SOMs), and transfer learning with EfficientNet. The selected deep learning techniques offer robust feature extraction and the efficient handling of large datasets, making them ideal in enhancing the accuracy of gait recognition. The collection includes gait sequences from 10 individuals, with a total of 92,596 images that have been reduced to 64 × 64 pixels for uniformity. A modified model was developed by integrating sequential convolutional layers for detailed spatial feature extraction, followed by dense layers for classification, optimized through rigorous hyperparameter tuning and regularization techniques, resulting in an accuracy of 97.12% for the test set. This work enhances our understanding of deep learning methods in gait analysis, offering significant insights for choosing optimal models in security and surveillance applications. Full article

► Show Figures

Figure 1

29 pages, 2090 KiB

Open AccessReview

SDN-Based Integrated Satellite Terrestrial Cyber–Physical Networks with 5G Resilience Infrastructure: Future Trends and Challenges

by Oluwatobiloba Alade Ayofe, Kennedy Chinedu Okafor, Omowunmi Mary Longe, Christopher Akinyemi Alabi, Abdoulie Momodu Sunkary Tekanyi, Aliyu Danjuma Usman, Mu’azu Jibrin Musa, Zanna Mohammed Abdullahi, Ezekiel Ehime Agbon, Agburu Ogah Adikpe, Kelvin Anoh, Bamidele Adebisi, Agbotiname Lucky Imoize and Hajara Idris

Technologies 2024, 12(12), 263; https://doi.org/10.3390/technologies12120263 - 16 Dec 2024

Viewed by 1209

Abstract

This paper reviews the state-of-the art technologies and techniques for integrating satellite and terrestrial networks within a 5G and Beyond Networks (5GBYNs). It highlights key limitations in existing architectures, particularly in addressing interoperability, resilience, and Quality of Service (QoS) for real-time applications. In [...] Read more.

This paper reviews the state-of-the art technologies and techniques for integrating satellite and terrestrial networks within a 5G and Beyond Networks (5GBYNs). It highlights key limitations in existing architectures, particularly in addressing interoperability, resilience, and Quality of Service (QoS) for real-time applications. In response, this work proposes a novel Software-Defined Networking (SDN)-based framework for reliable satellite–terrestrial integration. The proposed framework leverages intelligent traffic steering and dynamic access network selection to optimise real-time communications. By addressing gaps in the literature with a distributed SDN control approach spanning terrestrial and space domains, the framework enhances resilience against disruptions, such as natural disasters, while maintaining low latency and jitter. Future research directions are outlined to refine the design and explore its application in 6G systems. Full article

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

► Show Figures

Figure 1

12 pages, 11779 KiB

Open AccessCommunication

Normally-Off Trench-Gated AlGaN/GaN Current Aperture Vertical Electron Transistor with Double Superjunction

by Jong-Uk Kim, Do-Yeon Park, Byeong-Jun Park and Sung-Ho Hahm

Technologies 2024, 12(12), 262; https://doi.org/10.3390/technologies12120262 - 16 Dec 2024

Viewed by 890

Abstract

This study proposes an AlGaN/GaN current aperture vertical electron transistor (CAVET) featuring a double superjunction (SJ) to enhance breakdown voltage (BV) and investigates its electrical characteristics via technology computer-aided design (TCAD) Silvaco Atlas simulation. An additional p-pillar was formed beneath the gate [...] Read more.

This study proposes an AlGaN/GaN current aperture vertical electron transistor (CAVET) featuring a double superjunction (SJ) to enhance breakdown voltage (BV) and investigates its electrical characteristics via technology computer-aided design (TCAD) Silvaco Atlas simulation. An additional p-pillar was formed beneath the gate current blocking layer to create a lateral depletion region that provided a high off-state breakdown voltage. To address the tradeoff between the drain current and off-state breakdown voltage, the key design parameters were carefully optimized. The proposed device exhibited a higher off-state breakdown voltage (2933 V) than the device with a single SJ (2786 V), although the specific on-resistance of the proposed method (1.29 mΩ·cm⁻²) was slightly higher than that of the single SJ device (1.17 mΩ·cm⁻²). In addition, the reverse transfer capacitance was improved by 15.6% in the proposed device. Full article

(This article belongs to the Topic Advances in Microelectronics and Semiconductor Engineering)

► Show Figures

Figure 1

19 pages, 1008 KiB

Open AccessArticle

EEG-Based Mobile Robot Control Using Deep Learning and ROS Integration

by Bianca Ghinoiu, Victor Vlădăreanu, Ana-Maria Travediu, Luige Vlădăreanu, Abigail Pop, Yongfei Feng and Andreea Zamfirescu

Technologies 2024, 12(12), 261; https://doi.org/10.3390/technologies12120261 - 14 Dec 2024

Viewed by 1142

Abstract

Efficient BCIs (Brain-Computer Interfaces) harnessing EEG (Electroencephalography) have shown potential in controlling mobile robots, also presenting new possibilities for assistive technologies. This study explores the integration of advanced deep learning models—ASTGCN, EEGNetv4, and a combined CNN-LSTM architecture—with ROS (Robot Operating System) to control [...] Read more.

Efficient BCIs (Brain-Computer Interfaces) harnessing EEG (Electroencephalography) have shown potential in controlling mobile robots, also presenting new possibilities for assistive technologies. This study explores the integration of advanced deep learning models—ASTGCN, EEGNetv4, and a combined CNN-LSTM architecture—with ROS (Robot Operating System) to control a two-wheeled mobile robot. The models were trained using a published EEG dataset, which includes signals from subjects performing thought-based tasks. Each model was evaluated based on its accuracy, F1-score, and latency. The CNN-LSTM architecture model exhibited the best performance on the cross-subject strategy with an accuracy of 88.5%, demonstrating significant potential for real-time applications. Integration with ROS was facilitated through a custom middleware, enabling seamless translation of neural commands into robot movements. The findings indicate that the CNN-LSTM model not only outperforms existing EEG-based systems in terms of accuracy but also underscores the practical feasibility of implementing such systems in real-world scenarios. Considering its efficacy, CNN-LSTM shows a great potential for assistive technology in the future. This research contributes to the development of a more intuitive and accessible robotic control system, potentially enhancing the quality of life for individuals with mobility impairments. Full article

(This article belongs to the Special Issue Advanced Autonomous Systems and Artificial Intelligence Stage)

► Show Figures

Figure 1

29 pages, 6302 KiB

Open AccessReview

Impact of 3D Digitising Technologies and Their Implementation

by Paula Triviño-Tarradas, Diego Francisco García-Molina and José Ignacio Rojas-Sola

Technologies 2024, 12(12), 260; https://doi.org/10.3390/technologies12120260 - 14 Dec 2024

Viewed by 892

Abstract

In recent years, 3D digitalisation has experienced significant growth, revolutionising the way we capture, process and use geometric data. Initially conceived for industrial applications, these technologies have expanded to multiple fields, offering unprecedented accuracy and versatility. Depending on the accuracy and efficiency to [...] Read more.

In recent years, 3D digitalisation has experienced significant growth, revolutionising the way we capture, process and use geometric data. Initially conceived for industrial applications, these technologies have expanded to multiple fields, offering unprecedented accuracy and versatility. Depending on the accuracy and efficiency to be achieved in a specific field of application, and on the analytical capacity, a specific 3D digitalisation technique or another will be used. This review aims to delve into the application of 3D scanning techniques, according to the implementation sector. The optimal geometry capturing and processing 3D data techniques for a specific case are studied as well as their limitations. Full article

(This article belongs to the Section Assistive Technologies)

► Show Figures

Figure 1

26 pages, 3702 KiB

Open AccessArticle

Real-Time Scheduling with Independent Evaluators: Explainable Multi-Agent Approach

by Artem Isakov, Danil Peregorodiev, Ivan Tomilov, Chuyang Ye, Natalia Gusarova, Aleksandra Vatian and Alexander Boukhanovsky

Technologies 2024, 12(12), 259; https://doi.org/10.3390/technologies12120259 - 14 Dec 2024

Viewed by 881

Abstract

This study introduces a multi-agent reinforcement learning approach to address the challenges of real-time scheduling in dynamic environments, with a specific focus on healthcare operations. The proposed system integrates the Human-in-the-Loop (HITL) paradigm, providing continuous feedback from human evaluators, and it employs a [...] Read more.

This study introduces a multi-agent reinforcement learning approach to address the challenges of real-time scheduling in dynamic environments, with a specific focus on healthcare operations. The proposed system integrates the Human-in-the-Loop (HITL) paradigm, providing continuous feedback from human evaluators, and it employs a sophisticated reward function to attenuate the effects of human-driven events. Novel mapping between reinforcement learning (RL) concepts and the Belief–Desire–Intention (BDI) framework is developed to enhance the explainability of the agent’s decision-making. A system is designed to adapt to changes in patient conditions and preferences while minimizing disruptions to existing schedules. Experimental results show a notable decrease in patient waiting times compared to conventional methods while adhering to operator-induced constraints. This approach offers a robust, explainable, and adaptable solution for the challenging tasks of scheduling in the environments that require human-centered decision-making. Full article

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

► Show Figures

Figure 1

24 pages, 3202 KiB

Open AccessArticle

Monitoring Critical Health Conditions in the Elderly: A Deep Learning-Based Abnormal Vital Sign Detection Model

by Murad A. Rassam and Amal A. Al-Shargabi

Technologies 2024, 12(12), 258; https://doi.org/10.3390/technologies12120258 - 13 Dec 2024

Viewed by 990

Abstract

Global population aging creates distinct healthcare needs, particularly for older adults and those with serious illnesses. There are several gaps in current models for monitoring elderly individuals. These include the limited application of advanced deep learning techniques in elderly health monitoring, the lack [...] Read more.

Global population aging creates distinct healthcare needs, particularly for older adults and those with serious illnesses. There are several gaps in current models for monitoring elderly individuals. These include the limited application of advanced deep learning techniques in elderly health monitoring, the lack of real-time anomaly detection for vital signs, the absence of robust evaluations using real-world data, and the failure to tailor monitoring systems specifically for the unique needs of elderly individuals. This study addresses these gaps by proposing a Hierarchical Attention-based Temporal Convolutional Network (HATCN) model, which enhances anomaly detection accuracy and validates effectiveness using real-world datasets. While the HATCN approach has been used in other fields, it has not yet been applied to elderly healthcare monitoring, making this contribution novel. Specifically, this study introduces a Hierarchical Attention-based Temporal Convolutional Network with Anomaly Detection (HATCN-AD) model, based on the real-world MIMIC-II dataset. The model was validated using two subjects from the MIMIC-II dataset: Subject 330 (Dataset 1) and Subject 441 (Dataset 2). For Dataset 1 (Subject 330), the model achieved an accuracy of 99.15% and precision of 99.47%, with stable recall (99.45%) and F1-score (99.46%). Similarly, for Dataset 2 (Subject 441), the model achieved 99.11% accuracy, 99.35% precision, and an F1-score of 99.44% at 100 epochs. The results show that the HATCN-AD model outperformed similar models, achieving high recall and precision with low false positives and negatives. This ensures accurate anomaly detection for real-time healthcare monitoring. By combining Temporal Convolutional Networks and attention mechanisms, the HATCN-AD model effectively monitors elderly patients’ vital signs. Full article

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

► Show Figures

Figure 1

22 pages, 13321 KiB

Open AccessArticle

Particle Movement in DEM Models and Artificial Neural Network for Validation by Using Contrast Points

by Barbora Černilová, Jiří Kuře, Rostislav Chotěborský and Miloslav Linda

Technologies 2024, 12(12), 257; https://doi.org/10.3390/technologies12120257 - 12 Dec 2024

Viewed by 977

Abstract

The calibration and validation of input parameters in the Discrete Element Method (DEM) are crucial for accurately simulating physical processes, typically achieved through experimental particle behavior analysis. Enhancing the accuracy of DEM models allows for more reliable predictions of material behavior, which is [...] Read more.

The calibration and validation of input parameters in the Discrete Element Method (DEM) are crucial for accurately simulating physical processes, typically achieved through experimental particle behavior analysis. Enhancing the accuracy of DEM models allows for more reliable predictions of material behavior, which is essential for optimizing engineering applications that involve particulate materials. In this study, we present a methodology for analyzing the movement properties of particulate materials, employing a combination of Caliscope software to obtain the real-world co-ordinates based on pixel values from both cameras and artificial neural networks for regression as straightforward and efficient tools. This approach enables the validation and calibration of digital twins of particulate matter systems with respect to motion characteristics. The method of contrast points was utilized to acquire spatial co-ordinates of particulate material movement from experimental measurements, facilitating precise trajectory determination and the subsequent verification of simulation predictions. The neural network analysis demonstrated high accuracy, achieving R² values of 0.9988, 0.9972, and 0.9982 for the X–, Y–, and Z–axes, respectively. The standard deviation between the predicted and actual co-ordinates was found to be 1.8 mm. A comparative analysis of particle trajectories from both the model and experimental data indicated strong agreement, underscoring the soundness and reliability of this approach. Full article

► Show Figures

Figure 1

20 pages, 3968 KiB

Open AccessArticle

HybridFusionNet: Deep Learning for Multi-Stage Diabetic Retinopathy Detection

by Amar Shukla, Shamik Tiwari and Anurag Jain

Technologies 2024, 12(12), 256; https://doi.org/10.3390/technologies12120256 - 11 Dec 2024

Viewed by 970

Abstract

Diabetic retinopathy (DR) is one of the most common causes of visual impairment worldwide and requires reliable automated detection methods. Numerous research efforts have developed various conventional methods for early detection of DR. Research in the field of DR remains insufficient, indicating the [...] Read more.

Diabetic retinopathy (DR) is one of the most common causes of visual impairment worldwide and requires reliable automated detection methods. Numerous research efforts have developed various conventional methods for early detection of DR. Research in the field of DR remains insufficient, indicating the potential for advances in diagnosis. In this paper, a hybrid model (HybridFusionNet) that integrates vision transformer (VIT) and attention processes is presented. It improves classification in the binary (

B_{c l}

) and multi-class (

M_{c l}

) stages by utilizing deep features from the DR stages. As a result, both the SAN and VIT models improve the recognition accuracy

(A_{c c})

in both stages.The HybridFusionNet mechanism achieves a competitive improvement in multi-stage and binary stages, which is

A_{c c}

in

B_{c l}

and

M_{c l}

, with 91% and 99%, respectively. This illustrates that this model is suitable for a better diagnosis of DR. Full article

(This article belongs to the Special Issue Advancements in Medical and Assistive Technologies Using Artificial Intelligence and Deep Learning Techniques)

► Show Figures

Figure 1

16 pages, 5184 KiB

Open AccessArticle

Boa Fumigator: An Intelligent Robotic Approach for Mosquito Control

by Sriniketh Konduri, Prithvi Krishna Chittoor, Bhanu Priya Dandumahanti, Zhenyuan Yang, Mohan Rajesh Elara and Grace Hephzibah Jaichandar

Technologies 2024, 12(12), 255; https://doi.org/10.3390/technologies12120255 - 10 Dec 2024

Viewed by 1020

Abstract

The mosquitoe population is reaching critical levels globally, posing significant threats to public health and ecosystems due to their role as vectors for diseases. This paper presents the development of a mobile robotic platform named Boa Fumigator with autonomous fumigation and prioritized path [...] Read more.

The mosquitoe population is reaching critical levels globally, posing significant threats to public health and ecosystems due to their role as vectors for diseases. This paper presents the development of a mobile robotic platform named Boa Fumigator with autonomous fumigation and prioritized path planning capabilities in urban landscapes. The robot’s locomotion is based on a differential drive, facilitating easier maneuverability on semi-automated planar surfaces in landscaping infrastructure. The robot’s fumigator payload consists of a spray gun and a chemical tank, which can pan and fumigate up to 4.5 m from the ground. The system incorporates a wireless charging mechanism to allow for the autonomous charging of the mosquito catchers. A genetic algorithm fused with an A*-based prioritized path planning algorithm is developed for efficient navigation and charging of mosquito catchers. The algorithm, designed for maximizing charging efficiency, considers the initial charge percentage of mosquito catchers and the time required for fumigation to determine the optimal path for charging and fumigation. The experiment results show that the path planning algorithm can generate an optimized path for charging and fumigating multiple mosquito catchers based on their initial charge percentage. This paper concludes by summarizing the key findings and highlighting the significance of the fumigation robot in landscaping applications. Full article

(This article belongs to the Section Assistive Technologies)

► Show Figures

Figure 1

17 pages, 3073 KiB

Open AccessArticle

The Gradient of Spontaneous Oscillations Across Cortical Hierarchies Measured by Wearable Magnetoencephalography

by Xiaoyu Liang, Yuyu Ma, Huanqi Wu, Ruilin Wang, Ruonan Wang, Changzeng Liu, Yang Gao and Xiaolin Ning

Technologies 2024, 12(12), 254; https://doi.org/10.3390/technologies12120254 - 9 Dec 2024

Viewed by 1042

Abstract

The spontaneous oscillations within the brain are intimately linked to the hierarchical structures of the cortex, as evidenced by the cross-cortical gradient between parametrized spontaneous oscillations and cortical locations. Despite the significance of both peak frequency and peak time in characterizing these oscillations, [...] Read more.

The spontaneous oscillations within the brain are intimately linked to the hierarchical structures of the cortex, as evidenced by the cross-cortical gradient between parametrized spontaneous oscillations and cortical locations. Despite the significance of both peak frequency and peak time in characterizing these oscillations, limited research has explored the relationship between peak time and cortical locations. And no studies have demonstrated that the cross-cortical gradient can be measured by optically pumped magnetometer-based magnetoencephalography (OPM-MEG). Therefore, the cross-cortical gradient of parameterized spontaneous oscillation was analyzed for oscillations recorded by OPM-MEG using restricted maximum likelihood estimation with a linear mixed-effects model. It was validated that OPM-MEG can measure the cross-cortical gradient of spontaneous oscillations. Furthermore, results demonstrated the difference in the cross-cortical gradient between spontaneous oscillations during eye-opening and eye-closing conditions. The methods and conclusions offer potential to integrate electrophysiological and structural information of the brain, which contributes to the analysis of oscillatory fluctuations across the cortex recorded by OPM-MEG. Full article

(This article belongs to the Special Issue Technological Advances in Science, Medicine, and Engineering 2024)

► Show Figures

Figure 1

16 pages, 3359 KiB

Open AccessArticle

Integrated System of Reverse Osmosis and Forward Pressure-Assisted Osmosis from ZrO₂ Base Polymer Membranes for Desalination Technology

by Saleh O. Alaswad, Heba Abdallah and Eman S. Mansor

Technologies 2024, 12(12), 253; https://doi.org/10.3390/technologies12120253 - 6 Dec 2024

Viewed by 1001

Abstract

In this work, reverse osmosis and forward osmosis membranes were prepared using base cellulosic polymers with ZrO₂. The prepared membranes were rolled on the spiral-wound configuration module. The modules were tested on a pilot unit to investigate the efficiency of the [...] Read more.

In this work, reverse osmosis and forward osmosis membranes were prepared using base cellulosic polymers with ZrO₂. The prepared membranes were rolled on the spiral-wound configuration module. The modules were tested on a pilot unit to investigate the efficiency of the RO membrane and the hydraulic pressure effect on both sides of the FO membranes. The RO membrane provided a rejection of 99% for the seawater desalination, and the brine was used as a draw solution for the FO system. First, seawater was used as a draw solution to indicate the best hydraulic pressure, where the best one was 3 bar for the draw solution side, and 2 bar for the feed side, where the water flux reached 48.89 L/m²·h (LMH) with a dilution percentage of 80% and a low salt reverse flux of 0.128 g/m²·h (gMH) after 5 h of operation time. The integrated system of RO and forward-assisted osmosis (PAO) was investigated using river water as a feed and RO brine as a draw solute, where the results of PAO indicate a high-water flux of 68.6 LMH with a dilution of 93.2% and a salt reverse flux of 0.18 gMH. Therefore, using PAO improves the performance of the system. Full article

(This article belongs to the Section Innovations in Materials Processing)

► Show Figures

Figure 1

18 pages, 6729 KiB

Open AccessArticle

Experimental Study on Ignition and Pressure-Gain Achievement in Low-Vacuum Conditions for a Pulsed Detonation Combustor

by Andrei Vlad Cojocea, Mihnea Gall, George Ionuț Vrabie, Tudor Cuciuc, Ionuț Porumbel, Gabriel Ursescu and Daniel Eugeniu Crunţeanu

Technologies 2024, 12(12), 252; https://doi.org/10.3390/technologies12120252 - 2 Dec 2024

Viewed by 1260

Abstract

Pressure-gain combustion (PGC) represents a promising alternative to conventional propulsion systems for interplanetary travel due to its key advantages, including higher thermodynamic efficiency, increased specific impulse, and more compact engine designs. However, to elevate this technology to a sufficient technology readiness level (TRL) [...] Read more.

Pressure-gain combustion (PGC) represents a promising alternative to conventional propulsion systems for interplanetary travel due to its key advantages, including higher thermodynamic efficiency, increased specific impulse, and more compact engine designs. However, to elevate this technology to a sufficient technology readiness level (TRL) for practical application, extensive experimental validation, particularly under vacuum conditions, is essential. This study focuses on the performance of a pulsed-detonation combustor (PDC) under near-vacuum conditions, with two primary objectives: to assess the combustor’s ignition capabilities and to characterize the shock wave behavior at the exit plane. To achieve these objectives, high-frequency pressure sensors are strategically positioned within both the vacuum chamber and the combustor prototype to capture the pressure cycles during operation, providing insights into pressure augmentation over a period of approximately 0.5 s. Additionally, the Schlieren visualization technique is employed to analyze and interpret the flow structures of the exhaust jet. The combination of these experimental methods enables a comprehensive understanding of the ignition dynamics and the development of shock waves, contributing valuable data to advance PGC technology for space-exploration applications. Full article

(This article belongs to the Special Issue Technological Advances in Science, Medicine, and Engineering 2024)

► Show Figures

Figure 1

22 pages, 1503 KiB

Open AccessArticle

Deep Neural Networks for Estimating Regularization Parameter in Sparse Time–Frequency Reconstruction

by Vedran Jurdana

Technologies 2024, 12(12), 251; https://doi.org/10.3390/technologies12120251 - 1 Dec 2024

Viewed by 1415

Abstract

Time–frequency distributions (TFDs) are crucial for analyzing non-stationary signals. Compressive sensing (CS) in the ambiguity domain offers an approach for TFD reconstruction with high performance, but selecting the optimal regularization parameter for various signals remains challenging. Traditional methods for parameter selection, including manual [...] Read more.

Time–frequency distributions (TFDs) are crucial for analyzing non-stationary signals. Compressive sensing (CS) in the ambiguity domain offers an approach for TFD reconstruction with high performance, but selecting the optimal regularization parameter for various signals remains challenging. Traditional methods for parameter selection, including manual and experimental approaches, as well as existing optimization procedures, can be imprecise and time-consuming. This study introduces a novel approach using deep neural networks (DNNs) to predict regularization parameters based on Wigner–Ville distributions (WVDs). The proposed DNN is trained on a comprehensive dataset of synthetic signals featuring multiple linear and quadratic frequency-modulated components, with variations in component amplitudes and random positions, ensuring wide applicability and robustness. By utilizing DNNs, end-users need only provide the signal’s WVD, eliminating the need for manual parameter selection and lengthy optimization procedures. Comparisons between the reconstructed TFDs using the proposed DNN-based approach and existing optimization methods highlight significant improvements in both reconstruction performance and execution time. The effectiveness of this methodology is validated on noisy synthetic and real-world signals, emphasizing the potential of DNNs to automate regularization parameter determination for CS-based TFD reconstruction in diverse signal environments. Full article

► Show Figures

Figure 1

21 pages, 42074 KiB

Open AccessArticle

The Low-Cost Mechanism of a Defined Path Guide Slot-Based Passive Solar Tracker Intended for Developing Countries

by José Luis Pérez-Gudiño, Marco Antonio Gómez-Guzmán, Chayanne García-Valdez, Roberto Valentín Carrillo-Serrano, Gerardo Israel Pérez-Soto and Juvenal Rodríguez-Reséndiz

Technologies 2024, 12(12), 250; https://doi.org/10.3390/technologies12120250 - 30 Nov 2024

Viewed by 1241

Abstract

Solar trackers represent a significant advancement in enhancing the efficiency of solar energy collection. This study describes the development and implementation of a passive solar tracker featuring a single horizontal axis of rotation and an innovative guide slot mechanism. The tracker is designed [...] Read more.

Solar trackers represent a significant advancement in enhancing the efficiency of solar energy collection. This study describes the development and implementation of a passive solar tracker featuring a single horizontal axis of rotation and an innovative guide slot mechanism. The tracker is designed to be used with solar radiation-capturing devices. The guide slot mechanism is specifically engineered for a designated date, location, and period to follow the solar trajectory accurately. A contact follower moves along the guide slot, which drives a tracker disk to rotate by the solar trajectory. The mechanism is activated by the movement of a liquid container attached to a spring, thereby storing potential energy. The container releases the liquid through a mechanical valve that regulates the container’s movement, while the guide slot mechanism converts this movement into controlled rotational motion, which is transferred to a mobile structure mounting the solar panel. Notably, the majority of materials utilized in this construction are recycled. Furthermore, the solar tracker proposed in this work is designed to be operable by individuals with limited prior knowledge on the topic, emphasizing the primary contribution of this study: its potential to revolutionize energy collection in developing countries and marginalized urban areas. No similar systems are found upon comparison with existing models in the literature. Experiments conducted with a static solar panel and the same panel integrated into the passive solar tracker revealed a 30.87% improvement in energy collection efficiency over static solar panels. Full article

(This article belongs to the Special Issue Advanced Autonomous Systems and Artificial Intelligence Stage)

► Show Figures

Figure 1

22 pages, 17763 KiB

Open AccessArticle

Computer Vision Technology for Short Fiber Segmentation and Measurement in Scanning Electron Microscopy Images

by Evgenii Kurkin, Evgenii Minaev, Andrey Sedelnikov, Jose Gabriel Quijada Pioquinto, Vladislava Chertykovtseva and Andrey Gavrilov

Technologies 2024, 12(12), 249; https://doi.org/10.3390/technologies12120249 - 29 Nov 2024

Cited by 1 | Viewed by 1271

Abstract

Computer vision technology for the automatic recognition and geometric characterization of carbon and glass fibers in scanning electron microscopy images is proposed. The proposed pipeline, combining the SAM model and DeepLabV3+, provides the generalizability and accuracy of the foundational SAM model and the [...] Read more.

Computer vision technology for the automatic recognition and geometric characterization of carbon and glass fibers in scanning electron microscopy images is proposed. The proposed pipeline, combining the SAM model and DeepLabV3+, provides the generalizability and accuracy of the foundational SAM model and the ability to quickly train on a small amount of data via the DeepLabV3+ model. The pipeline was trained several times more rapidly with lower requirements for computing resources than fine-tuning the SAM model, with comparable inference time. On the basis of the pipeline, an end-to-end technology for processing images of electron microscopic fibers was developed, the input of which is images with metadata and the output of which is statistics on the distribution of the geometric characteristics of the fibers. This innovation is of great practical importance for modeling the physical characteristics of materials. This paper proposes a few-shot training procedure for the DeepLabV3+/SAM pipeline, combining the training of the DeepLabV3+ model weights and the SAM model parameters. It allows effective training of the pipeline using only 37 real labeled images. The pipeline was then adapted to a new type of fiber and background using 15 additional real labeled images. This article also proposes a method for generating synthetic data for training neural network models, which improves the quality of segmentation by the IoU and PixAcc metrics from 0.943 and 0.949 to 0.953 and 0.959, i.e., by 1% on average. The developed pipeline significantly reduces the time required to evaluate fiber length in scanning electron microscope images. Full article

► Show Figures

Figure 1

23 pages, 5895 KiB

Open AccessArticle

Energy-Efficient Data Fusion in WSNs Using Mobility-Aware Compression and Adaptive Clustering

by Emad S. Hassan, Marwa Madkour, Salah E. Soliman, Ahmed S. Oshaba, Atef El-Emary, Ehab S. Ali and Fathi E. Abd El-Samie

Technologies 2024, 12(12), 248; https://doi.org/10.3390/technologies12120248 - 28 Nov 2024

Viewed by 1194

Abstract

To facilitate energy-efficient information dissemination from multiple sensors to the sink within Wireless Sensor Networks (WSNs), in-network data fusion is imperative. This paper presents a new WSN topology that incorporates the Mobility-Efficient Data Fusion (MEDF) algorithm, which integrates a data-compression protocol with an [...] Read more.

To facilitate energy-efficient information dissemination from multiple sensors to the sink within Wireless Sensor Networks (WSNs), in-network data fusion is imperative. This paper presents a new WSN topology that incorporates the Mobility-Efficient Data Fusion (MEDF) algorithm, which integrates a data-compression protocol with an adaptive-clustering mechanism. The primary goals of this topology are, first, to determine a dynamic sequence of cluster heads (CHs) for each data transmission round, aiming to prolong network lifetime by implementing an adaptive-clustering mechanism resilient to network dynamics, where CH selection relies on residual energy and minimal communication distance; second, to enhance packet delivery ratio (PDR) through the application of a data-compression technique; and third, to mitigate the hot-spot issue, wherein sensor nodes nearest to the base station endure higher relay burdens, consequently influencing network longevity. To address this issue, mobility models provide a straightforward solution; specifically, a Random Positioning of Grid Mobility (RPGM) model is employed to alleviate the hot-spot problem. The simulation results show that the network topology incorporating the proposed MEDF algorithm effectively enhances network longevity, optimizes average energy consumption, and improves PDR. Compared to the Energy-Efficient Multiple Data Fusion (EEMDF) algorithm, the proposed algorithm demonstrates enhancements in PDR and energy efficiency, with gains of 5.2% and 7.7%, respectively. Additionally, it has the potential to extend network lifetime by 13.9%. However, the MEDF algorithm increases delay by 0.01% compared to EEMDF. The proposed algorithm is also evaluated against other algorithms, such as the tracking-anchor-based clustering method (TACM) and Energy-Efficient Dynamic Clustering (EEDC), the obtained results emphasize the MEDF algorithm’s ability to conserve energy more effectively than the other algorithms. Full article

(This article belongs to the Special Issue Perpetual Sensor Nodes for Sustainable Wireless Network Applications)

► Show Figures

Figure 1

12 pages, 4513 KiB

Open AccessArticle

Malaria Cell Image Classification Using Compact Deep Learning Architectures on Jetson TX2

by Adán-Antonio Alonso-Ramírez, Alejandro-Israel Barranco-Gutiérrez, Iris-Iddaly Méndez-Gurrola, Marcos Gutiérrez-López, Juan Prado-Olivarez, Francisco-Javier Pérez-Pinal, J. Jesús Villegas-Saucillo, Jorge-Alberto García-Muñoz and Carlos-Hugo García-Capulín

Technologies 2024, 12(12), 247; https://doi.org/10.3390/technologies12120247 - 27 Nov 2024

Viewed by 1416

Abstract

Malaria is a significant global health issue, especially in tropical regions. Accurate and rapid diagnosis is critical for effective treatment and reducing mortality rates. Traditional diagnostic methods, like blood smear microscopy, are time-intensive and prone to error. This study introduces a deep learning [...] Read more.

Malaria is a significant global health issue, especially in tropical regions. Accurate and rapid diagnosis is critical for effective treatment and reducing mortality rates. Traditional diagnostic methods, like blood smear microscopy, are time-intensive and prone to error. This study introduces a deep learning approach for classifying malaria-infected cells in blood smear images using convolutional neural networks (CNNs); Six CNN models were designed and trained using a large labeled dataset of malaria cell images, both infected and uninfected, and were implemented on the Jetson TX2 board to evaluate them. The model was optimized for feature extraction and classification accuracy, achieving 97.72% accuracy, and evaluated using precision, recall, and F1-score metrics and execution time. Results indicate deep learning significantly improves diagnostic time efficiency on embedded systems. This scalable, automated solution is particularly useful in resource-limited areas without access to expert microscopic analysis. Future work will focus on clinical validation. Full article

(This article belongs to the Special Issue The Future of Healthcare: Biomedical Technology and Integrated Artificial Intelligence 2nd Edition)

► Show Figures

Figure 1

18 pages, 5773 KiB

Open AccessArticle

Isolated High-Gain DC-DC Converter with Nanocrystalline-Core Transformer: Achieving 1:16 Voltage Boost for Renewable Energy Applications

by Tania Sandoval-Valencia, Dante Ruiz-Robles, Jorge Ortíz-Marín, Jesus Alejandro Franco, Quetzalcoatl Hernandez-Escobedo and Edgar Moreno-Goytia

Technologies 2024, 12(12), 246; https://doi.org/10.3390/technologies12120246 - 27 Nov 2024

Viewed by 1180

Abstract

This paper presents an isolated DC-DC converter with high voltage gain that features an advanced inter-built nanocrystalline-core medium-frequency transformer (NC-MFT). The isolated DC-DC converter with an NC-MFT is specifically designed for applications such as interconnect photovoltaic (PV) systems, DC microgrids, DC loads, and [...] Read more.

This paper presents an isolated DC-DC converter with high voltage gain that features an advanced inter-built nanocrystalline-core medium-frequency transformer (NC-MFT). The isolated DC-DC converter with an NC-MFT is specifically designed for applications such as interconnect photovoltaic (PV) systems, DC microgrids, DC loads, and DC buses, where voltage gain is one of the essential issues to consider. The NC-MFT inside the DC-DC converter is designed with a new approach that not only provides isolation but also contributes to achieving high efficiency and a higher step-up ratio. The high efficiency of the converters contributes to the integration of PV systems into DC microgrids. The converter yields a high voltage conversion ratio of 16.17. The experimental results obtained at 41.8 V/676 V and 275 W for the prototype revealed high efficiency (95.63% at full load). The experimental results validate the theoretical analysis and simulation, confirming that the converter achieves the main objective of high voltage conversion and high efficiency. These results will contribute to the interest in the use of this type of energy and its impact on the reduction in CO₂ emissions. Full article

► Show Figures

Figure 1

16 pages, 2379 KiB

Open AccessArticle

Resource Sizing for Virtual Environments of Networked Interconnected System Services

by Alexandr Albychev, Dmitry Ilin and Evgeny Nikulchev

Technologies 2024, 12(12), 245; https://doi.org/10.3390/technologies12120245 - 27 Nov 2024

Viewed by 1132

Abstract

Networked interconnected systems are often deployed in infrastructures with resource allocation using isolated virtual environments. The technological implementation of such systems varies significantly, making it difficult to accurately estimate the required volume of resources to allocate for each virtual environment. This leads to [...] Read more.

Networked interconnected systems are often deployed in infrastructures with resource allocation using isolated virtual environments. The technological implementation of such systems varies significantly, making it difficult to accurately estimate the required volume of resources to allocate for each virtual environment. This leads to overprovisioning of some services and underprovisioning of others. The problem of distributing the available computational resources between the system services arises. To efficiently use resources and reduce resource waste, the problem of minimizing free resources under conditions of unknown ratios of resource distribution between services is formalized; an approach to determining regression dependencies of computing resource consumption by services on the number of requests and a procedure for efficient resource distribution between services are proposed. The proposed solution is experimentally evaluated using the networked interconnected system model. The results show an increase in throughput by 20.75% compared to arbitrary resource distribution and a reduction in wasted resources by 55.59%. The dependences of the use of resources by networked interconnected system services on the number of incoming requests, identified using the proposed solution, can also be used for scaling in the event of an increase in the total volume of allocated resources. Full article

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

► Show Figures

Figure 1

28 pages, 771 KiB

Open AccessReview

Formal Verification of Code Conversion: A Comprehensive Survey

by Amira T. Mahmoud, Ahmad A. Mohammed, Mahitap Ayman, Walaa Medhat , Sahar Selim , Hala Zayed, Ahmed H. Yousef and Nahla Elaraby

Technologies 2024, 12(12), 244; https://doi.org/10.3390/technologies12120244 - 26 Nov 2024

Viewed by 1503

Abstract

Code conversion, encompassing translation, optimization, and generation, is becoming increasingly critical in information systems and the software industry. Traditional validation methods, such as test cases and code coverage metrics, often fail to ensure the correctness, completeness, and equivalence of converted code to its [...] Read more.

Code conversion, encompassing translation, optimization, and generation, is becoming increasingly critical in information systems and the software industry. Traditional validation methods, such as test cases and code coverage metrics, often fail to ensure the correctness, completeness, and equivalence of converted code to its original form. Formal verification emerges as a crucial methodology to address these limitations. Although numerous surveys have explored formal verification in various contexts, a significant research gap exists in pinpointing appropriate formal verification approaches to code conversion tasks. This paper provides a detailed survey of formal verification techniques applicable to code conversion. This survey identifies the strengths and limitations of contemporary adopted approaches while outlining a trajectory for future research, emphasizing the need for automated and scalable verification tools. The novel categorization of formal verification methods provided in this paper serves as a foundational guide for researchers seeking to enhance the reliability of code conversion processes. Full article

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

► Show Figures

Figure 1

27 pages, 7002 KiB

Open AccessArticle

Development of a Mobile Application for Musculoskeletal Rehabilitation Based on Computer Vision and Inertial Navigation Technologies

by Artem Obukhov, Andrey Volkov and Yuri Nikitnikov

Technologies 2024, 12(12), 243; https://doi.org/10.3390/technologies12120243 - 24 Nov 2024

Viewed by 1437

Abstract

Monitoring the process of musculoskeletal rehabilitation is of great importance for ensuring a person’s health after suffering from illnesses, especially during the outpatient period when medical supervision is absent. The aim of this study is to create an accessible tool (a mobile application) [...] Read more.

Monitoring the process of musculoskeletal rehabilitation is of great importance for ensuring a person’s health after suffering from illnesses, especially during the outpatient period when medical supervision is absent. The aim of this study is to create an accessible tool (a mobile application) that allows for the monitoring of the execution of musculoskeletal rehabilitation exercises. To achieve this goal, the architecture of a mobile application has been developed, along with its functioning algorithm, and the methods for processing information from two tracking systems (inertial navigation and computer vision) have been examined to assess the quality of performed exercises. During the experimental research, procedures for processing data from mobile inertial navigation sensors were refined, a solution to the classification task of musculoskeletal rehabilitation exercises was explored (with an accuracy of 93–100%), and prototyping of the mobile application was carried out. The results obtained can be used for evaluating outpatient rehabilitation and as a basis for more complex and functional mobile systems for musculoskeletal rehabilitation. Full article

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

► Show Figures

Figure 1

21 pages, 803 KiB

Open AccessArticle

One-Dimensional Deep Residual Network with Aggregated Transformations for Internet of Things (IoT)-Enabled Human Activity Recognition in an Uncontrolled Environment

by Sakorn Mekruksavanich and Anuchit Jitpattanakul

Technologies 2024, 12(12), 242; https://doi.org/10.3390/technologies12120242 - 24 Nov 2024

Viewed by 1387

Abstract

Human activity recognition (HAR) in real-world settings has gained significance due to the growth of Internet of Things (IoT) devices such as smartphones and smartwatches. Nonetheless, limitations such as fluctuating environmental conditions and intricate behavioral patterns have impacted the accuracy of the current [...] Read more.

Human activity recognition (HAR) in real-world settings has gained significance due to the growth of Internet of Things (IoT) devices such as smartphones and smartwatches. Nonetheless, limitations such as fluctuating environmental conditions and intricate behavioral patterns have impacted the accuracy of the current procedures. This research introduces an innovative methodology employing a modified deep residual network, called 1D-ResNeXt, for IoT-enabled HAR in uncontrolled environments. We developed a comprehensive network that utilizes feature fusion and a multi-kernel block approach. The residual connections and the split–transform–merge technique mitigate the accuracy degradation and reduce the parameter number. We assessed our suggested model on three available datasets, mHealth, MotionSense, and Wild-SHARD, utilizing accuracy metrics, cross-entropy loss, and F1 score. The findings indicated substantial enhancements in proficiency in recognition, attaining 99.97% on mHealth, 98.77% on MotionSense, and 97.59% on Wild-SHARD, surpassing contemporary methodologies. Significantly, our model attained these outcomes with considerably fewer parameters (24,130–26,118) than other models, several of which exceeded 700,000 parameters. The 1D-ResNeXt model demonstrated outstanding effectiveness under various ambient circumstances, tackling a significant obstacle in practical HAR applications. The findings indicate that our modified deep residual network presents a viable approach for improving the dependability and usability of IoT-based HAR systems in dynamic, uncontrolled situations while preserving the computational effectiveness essential for IoT devices. The results significantly impact multiple sectors, including healthcare surveillance, intelligent residences, and customized assistive devices. Full article

(This article belongs to the Special Issue IoT-Enabling Technologies and Applications)

► Show Figures

Figure 1

Journal Menu

Journal Browser

Technologies, Volume 12, Issue 12 (December 2024) – 37 articles

Further Information

Guidelines

MDPI Initiatives

Follow MDPI