Editor's Choice Articles

Editor’s Choice articles are based on recommendations by the scientific editors of MDPI journals from around the world. Editors select a small number of articles recently published in the journal that they believe will be particularly interesting to authors, or important in this field. The aim is to provide a snapshot of some of the most exciting work published in the various research areas of the journal.

Order results
Result details
Results per page
Select all
Export citation of selected articles as:

Article

Article
Examining Attention Mechanisms in Deep Learning Models for Sentiment Analysis
Appl. Sci. 2021, 11(9), 3883; https://doi.org/10.3390/app11093883 - 25 Apr 2021
Cited by 9 | Viewed by 1172
Abstract
Attention-based methods for deep neural networks constitute a technique that has attracted increased interest in recent years. Attention mechanisms can focus on important parts of a sequence and, as a result, enhance the performance of neural networks in a variety of tasks, including [...] Read more.
Attention-based methods for deep neural networks constitute a technique that has attracted increased interest in recent years. Attention mechanisms can focus on important parts of a sequence and, as a result, enhance the performance of neural networks in a variety of tasks, including sentiment analysis, emotion recognition, machine translation and speech recognition. In this work, we study attention-based models built on recurrent neural networks (RNNs) and examine their performance in various contexts of sentiment analysis. Self-attention, global-attention and hierarchical-attention methods are examined under various deep neural models, training methods and hyperparameters. Even though attention mechanisms are a powerful recent concept in the field of deep learning, their exact effectiveness in sentiment analysis is yet to be thoroughly assessed. A comparative analysis is performed in a text sentiment classification task where baseline models are compared with and without the use of attention for every experiment. The experimental study additionally examines the proposed models’ ability in recognizing opinions and emotions in movie reviews. The results indicate that attention-based models lead to great improvements in the performance of deep neural models showcasing up to a 3.5% improvement in their accuracy. Full article
(This article belongs to the Section Computing and Artificial Intelligence)
Show Figures

Figure 1

Article
Augmented Reality, Virtual Reality and Artificial Intelligence in Orthopedic Surgery: A Systematic Review
Appl. Sci. 2021, 11(7), 3253; https://doi.org/10.3390/app11073253 - 05 Apr 2021
Cited by 7 | Viewed by 1434
Abstract
Background: The application of virtual and augmented reality technologies to orthopaedic surgery training and practice aims to increase the safety and accuracy of procedures and reducing complications and costs. The purpose of this systematic review is to summarise the present literature on this [...] Read more.
Background: The application of virtual and augmented reality technologies to orthopaedic surgery training and practice aims to increase the safety and accuracy of procedures and reducing complications and costs. The purpose of this systematic review is to summarise the present literature on this topic while providing a detailed analysis of current flaws and benefits. Methods: A comprehensive search on the PubMed, Cochrane, CINAHL, and Embase database was conducted from inception to February 2021. The Preferred Reporting Items for Systematic reviews and Meta-Analyses (PRISMA) guidelines were used to improve the reporting of the review. The Cochrane Risk of Bias Tool and the Methodological Index for Non-Randomized Studies (MINORS) was used to assess the quality and potential bias of the included randomized and non-randomized control trials, respectively. Results: Virtual reality has been proven revolutionary for both resident training and preoperative planning. Thanks to augmented reality, orthopaedic surgeons could carry out procedures faster and more accurately, improving overall safety. Artificial intelligence (AI) is a promising technology with limitless potential, but, nowadays, its use in orthopaedic surgery is limited to preoperative diagnosis. Conclusions: Extended reality technologies have the potential to reform orthopaedic training and practice, providing an opportunity for unidirectional growth towards a patient-centred approach. Full article
(This article belongs to the Collection Virtual and Augmented Reality Systems)
Show Figures

Figure 1

Article
A Survey on Bias in Deep NLP
Appl. Sci. 2021, 11(7), 3184; https://doi.org/10.3390/app11073184 - 02 Apr 2021
Cited by 11 | Viewed by 2988
Abstract
Deep neural networks are hegemonic approaches to many machine learning areas, including natural language processing (NLP). Thanks to the availability of large corpora collections and the capability of deep architectures to shape internal language mechanisms in self-supervised learning processes (also known as “pre-training”), [...] Read more.
Deep neural networks are hegemonic approaches to many machine learning areas, including natural language processing (NLP). Thanks to the availability of large corpora collections and the capability of deep architectures to shape internal language mechanisms in self-supervised learning processes (also known as “pre-training”), versatile and performing models are released continuously for every new network design. These networks, somehow, learn a probability distribution of words and relations across the training collection used, inheriting the potential flaws, inconsistencies and biases contained in such a collection. As pre-trained models have been found to be very useful approaches to transfer learning, dealing with bias has become a relevant issue in this new scenario. We introduce bias in a formal way and explore how it has been treated in several networks, in terms of detection and correction. In addition, available resources are identified and a strategy to deal with bias in deep NLP is proposed. Full article
(This article belongs to the Special Issue Trends in Artificial Intelligence and Data Mining: 2021 and Beyond)
Show Figures

Figure 1

Article
Enhancement of Antimicrobial Activity of Alginate Films with a Low Amount of Carbon Nanofibers (0.1% w/w)
Appl. Sci. 2021, 11(5), 2311; https://doi.org/10.3390/app11052311 - 05 Mar 2021
Cited by 14 | Viewed by 1049
Abstract
The World Health Organization has called for new effective and affordable alternative antimicrobial materials for the prevention and treatment of microbial infections. In this regard, calcium alginate has previously been shown to possess antiviral activity against the enveloped double-stranded DNA herpes simplex virus [...] Read more.
The World Health Organization has called for new effective and affordable alternative antimicrobial materials for the prevention and treatment of microbial infections. In this regard, calcium alginate has previously been shown to possess antiviral activity against the enveloped double-stranded DNA herpes simplex virus type 1. However, non-enveloped viruses are more resistant to inactivation than enveloped ones. Thus, the viral inhibition capacity of calcium alginate and the effect of adding a low amount of carbon nanofibers (0.1% w/w) were explored here against a non-enveloped double-stranded DNA virus model for the first time. The results of this study showed that neat calcium alginate films partly inactivated this type of non-enveloped virus and that including that extremely low percentage of carbon nanofibers (CNFs) significantly enhanced its antiviral activity. These calcium alginate/CNFs composite materials also showed antibacterial properties against the Gram-positive Staphylococcus aureus bacterial model and no cytotoxic effects in human keratinocyte HaCaT cells. Since alginate-based materials have also shown antiviral activity against four types of enveloped positive-sense single-stranded RNA viruses similar to SARS-CoV-2 in previous studies, these novel calcium alginate/carbon nanofibers composites are promising as broad-spectrum antimicrobial biomaterials for the current COVID-19 pandemic. Full article
(This article belongs to the Special Issue Nanomaterials in Medical Engineering)
Show Figures

Graphical abstract

Article
Neuroscope: An Explainable AI Toolbox for Semantic Segmentation and Image Classification of Convolutional Neural Nets
Appl. Sci. 2021, 11(5), 2199; https://doi.org/10.3390/app11052199 - 03 Mar 2021
Cited by 8 | Viewed by 1593
Abstract
Trust in artificial intelligence (AI) predictions is a crucial point for a widespread acceptance of new technologies, especially in sensitive areas like autonomous driving. The need for tools explaining AI for deep learning of images is thus eminent. Our proposed toolbox Neuroscope addresses [...] Read more.
Trust in artificial intelligence (AI) predictions is a crucial point for a widespread acceptance of new technologies, especially in sensitive areas like autonomous driving. The need for tools explaining AI for deep learning of images is thus eminent. Our proposed toolbox Neuroscope addresses this demand by offering state-of-the-art visualization algorithms for image classification and newly adapted methods for semantic segmentation of convolutional neural nets (CNNs). With its easy to use graphical user interface (GUI), it provides visualization on all layers of a CNN. Due to its open model-view-controller architecture, networks generated and trained with Keras and PyTorch are processable, with an interface allowing extension to additional frameworks. We demonstrate the explanation abilities provided by Neuroscope using the example of traffic scene analysis. Full article
(This article belongs to the Special Issue Explainable Artificial Intelligence (XAI))
Show Figures

Figure 1

Article
Human Activity Recognition through Recurrent Neural Networks for Human–Robot Interaction in Agriculture
Appl. Sci. 2021, 11(5), 2188; https://doi.org/10.3390/app11052188 - 02 Mar 2021
Cited by 16 | Viewed by 1413
Abstract
The present study deals with human awareness, which is a very important aspect of human–robot interaction. This feature is particularly essential in agricultural environments, owing to the information-rich setup that they provide. The objective of this investigation was to recognize human activities associated [...] Read more.
The present study deals with human awareness, which is a very important aspect of human–robot interaction. This feature is particularly essential in agricultural environments, owing to the information-rich setup that they provide. The objective of this investigation was to recognize human activities associated with an envisioned synergistic task. In order to attain this goal, a data collection field experiment was designed that derived data from twenty healthy participants using five wearable sensors (embedded with tri-axial accelerometers, gyroscopes, and magnetometers) attached to them. The above task involved several sub-activities, which were carried out by agricultural workers in real field conditions, concerning load lifting and carrying. Subsequently, the obtained signals from on-body sensors were processed for noise-removal purposes and fed into a Long Short-Term Memory neural network, which is widely used in deep learning for feature recognition in time-dependent data sequences. The proposed methodology demonstrated considerable efficacy in predicting the defined sub-activities with an average accuracy of 85.6%. Moreover, the trained model properly classified the defined sub-activities in a range of 74.1–90.4% for precision and 71.0–96.9% for recall. It can be inferred that the combination of all sensors can achieve the highest accuracy in human activity recognition, as concluded from a comparative analysis for each sensor’s impact on the model’s performance. These results confirm the applicability of the proposed methodology for human awareness purposes in agricultural environments, while the dataset was made publicly available for future research. Full article
(This article belongs to the Special Issue Applied Agri-Technologies)
Show Figures

Figure 1

Article
Assessment of Natural Radioactivity and Radiological Risks in River Sediments from Calabria (Southern Italy)
Appl. Sci. 2021, 11(4), 1729; https://doi.org/10.3390/app11041729 - 15 Feb 2021
Cited by 8 | Viewed by 954
Abstract
This study was developed to carry out a comprehensive radiological assessment of natural radioactivity for river sediment samples from Calabria, southern Italy, and to define a baseline background for the area on a radiation map. In the studied area, elevated levels of natural [...] Read more.
This study was developed to carry out a comprehensive radiological assessment of natural radioactivity for river sediment samples from Calabria, southern Italy, and to define a baseline background for the area on a radiation map. In the studied area, elevated levels of natural radionuclides are expected, due to the outcropping acidic intrusive and metamorphic rocks from which the radioactive elements derive. To identify and quantify the natural radioisotopes, ninety river sediment samples from nine selected coastal sampling points (ten samples for each point) were collected as representative of the Ionian and the Tyrrhenian coastline of Calabria. The samples were analyzed using a gamma ray spectrometer equipped with a high-purity germanium (HPGe) detector. The values of mean activity concentrations of 226Ra, 232Th and 40K measured for the studied samples are (21.3 ± 6.3) Bq kg−1, (30.3 ± 4.5) Bq kg−1 and (849 ± 79) Bq kg−1, respectively. The calculated radiological hazard indices showed average values of 63 nGy h−1 (absorbed dose rate), 0.078 mSv y−1 (effective dose outdoors), 0.111 mSv y−1 (effective dose indoors), 63 Bq kg−1 (radium equivalent), 0.35 (Hex), 0.41 (Hin), 0.50 (activity concentration index) and 458 µSv y−1 (Annual Gonadal Equivalent Dose, AGED). In order to delineate the spatial distribution of natural radionuclides on the radiological map and to identify the areas with low, medium and high radioactivity values, the Surfer 10 software was employed. Finally, the multivariate statistical analysis was performed to deduce the interdependency and any existing relationships between the radiological indices and the concentrations of the radionuclides. The results of this study, also compared with values of other locations of the Italian Peninsula characterized by similar local geological conditions, can be used as a baseline for future investigations about radioactivity background in the investigated area. Full article
(This article belongs to the Special Issue Advances in Environmental Applied Physics)
Show Figures

Figure 1

Article
Intelligent Cyber Attack Detection and Classification for Network-Based Intrusion Detection Systems
Appl. Sci. 2021, 11(4), 1674; https://doi.org/10.3390/app11041674 - 13 Feb 2021
Cited by 23 | Viewed by 2103
Abstract
With the latest advances in information and communication technologies, greater amounts of sensitive user and corporate information are shared continuously across the network, making it susceptible to an attack that can compromise data confidentiality, integrity, and availability. Intrusion Detection Systems (IDS) are important [...] Read more.
With the latest advances in information and communication technologies, greater amounts of sensitive user and corporate information are shared continuously across the network, making it susceptible to an attack that can compromise data confidentiality, integrity, and availability. Intrusion Detection Systems (IDS) are important security mechanisms that can perform the timely detection of malicious events through the inspection of network traffic or host-based logs. Many machine learning techniques have proven to be successful at conducting anomaly detection throughout the years, but only a few considered the sequential nature of data. This work proposes a sequential approach and evaluates the performance of a Random Forest (RF), a Multi-Layer Perceptron (MLP), and a Long-Short Term Memory (LSTM) on the CIDDS-001 dataset. The resulting performance measures of this particular approach are compared with the ones obtained from a more traditional one, which only considers individual flow information, in order to determine which methodology best suits the concerned scenario. The experimental outcomes suggest that anomaly detection can be better addressed from a sequential perspective. The LSTM is a highly reliable model for acquiring sequential patterns in network traffic data, achieving an accuracy of 99.94% and an f1-score of 91.66%. Full article
Show Figures

Figure 1

Article
A Serious Gaming Approach for Crowdsensing in Urban Water Infrastructure with Blockchain Support
Appl. Sci. 2021, 11(4), 1449; https://doi.org/10.3390/app11041449 - 05 Feb 2021
Cited by 7 | Viewed by 969
Abstract
This paper presents the current state of the gaming industry, which provides an important background for an effective serious game implementation in mobile crowdsensing. An overview of existing solutions, scientific studies and market research highlights the current trends and the potential applications for [...] Read more.
This paper presents the current state of the gaming industry, which provides an important background for an effective serious game implementation in mobile crowdsensing. An overview of existing solutions, scientific studies and market research highlights the current trends and the potential applications for citizen-centric platforms in the context of Cyber–Physical–Social systems. The proposed solution focuses on serious games applied in urban water management from the perspective of mobile crowdsensing, with a reward-driven mechanism defined for the crowdsensing tasks. The serious game is designed to provide entertainment value by means of gamified interaction with the environment, while the crowdsensing component involves a set of roles for finding, solving and validating water-related issues. The mathematical model of distance-constrained multi-depot vehicle routing problem with heterogeneous fleet capacity is evaluated in the context of the proposed scenario, with random initial conditions given by the location of players, while the Vickrey–Clarke–Groves auction model provides an alternative to the centralized task allocation strategy, subject to the same evaluation method. A blockchain component based on the Hyperledger Fabric architecture provides the level of trust required for achieving overall platform utility for different stakeholders in mobile crowdsensing. Full article
(This article belongs to the Special Issue Secure and Intelligent Mobile Systems)
Show Figures

Figure 1

Article
Attention-Based Transfer Learning for Efficient Pneumonia Detection in Chest X-ray Images
Appl. Sci. 2021, 11(3), 1242; https://doi.org/10.3390/app11031242 - 29 Jan 2021
Cited by 7 | Viewed by 1328
Abstract
Pneumonia is a form of acute respiratory infection commonly caused by germs, viruses, and fungi, and can prove fatal at any age. Chest X-rays is the most common technique for diagnosing pneumonia. There have been several attempts to apply transfer learning based on [...] Read more.
Pneumonia is a form of acute respiratory infection commonly caused by germs, viruses, and fungi, and can prove fatal at any age. Chest X-rays is the most common technique for diagnosing pneumonia. There have been several attempts to apply transfer learning based on a Convolutional Neural Network to build a stable model in computer-aided diagnosis. Recently, with the appearance of an attention mechanism that automatically focuses on the critical part of the image that is crucial for the diagnosis of disease, it is possible to increase the performance of previous models. The goal of this study is to improve the accuracy of a computer-aided diagnostic approach that medical professionals can easily use as an auxiliary tool. In this paper, we proposed the attention-based transfer learning framework for efficient pneumonia detection in chest X-ray images. We collected features from three-types of pre-trained models, ResNet152, DenseNet121, ResNet18 as a role of feature extractor. We redefined the classifier for a new task and applied the attention mechanism as a feature selector. As a result, the proposed approach achieved accuracy, F-score, Area Under the Curve(AUC), precision and recall of 96.63%, 0.973, 96.03%, 96.23% and 98.46%, respectively. Full article
(This article belongs to the Special Issue Medical Artificial Intelligence)
Show Figures

Figure 1

Article
Novel Derivatives of 4-Methyl-1,2,3-Thiadiazole-5-Carboxylic Acid Hydrazide: Synthesis, Lipophilicity, and In Vitro Antimicrobial Activity Screening
Appl. Sci. 2021, 11(3), 1180; https://doi.org/10.3390/app11031180 - 27 Jan 2021
Cited by 9 | Viewed by 852
Abstract
Bacterial infections, especially those caused by strains resistant to commonly used antibiotics and chemotherapeutics, are still a current threat to public health. Therefore, the search for new molecules with potential antimicrobial activity is an important research goal. In this article, we present the [...] Read more.
Bacterial infections, especially those caused by strains resistant to commonly used antibiotics and chemotherapeutics, are still a current threat to public health. Therefore, the search for new molecules with potential antimicrobial activity is an important research goal. In this article, we present the synthesis and evaluation of the in vitro antimicrobial activity of a series of 15 new derivatives of 4-methyl-1,2,3-thiadiazole-5-carboxylic acid. The potential antimicrobial effect of the new compounds was observed mainly against Gram-positive bacteria. Compound 15, with the 5-nitro-2-furoyl moiety, showed the highest bioactivity: minimum inhibitory concentration (MIC) = 1.95–15.62 µg/mL and minimum bactericidal concentration (MBC)/MIC = 1–4 µg/mL. Full article
Show Figures

Figure 1

Article
Arundo donax L. Biomass Production in a Polluted Area: Effects of Two Harvest Timings on Heavy Metals Uptake
Appl. Sci. 2021, 11(3), 1147; https://doi.org/10.3390/app11031147 - 27 Jan 2021
Cited by 15 | Viewed by 950
Abstract
Within the framework of energy biomass production, Arundo donax L. is very promising for its capability to grow on marginal lands with high yields. This potential can be realized in unused polluted areas where the energy production can be coupled with phytoremediation, and [...] Read more.
Within the framework of energy biomass production, Arundo donax L. is very promising for its capability to grow on marginal lands with high yields. This potential can be realized in unused polluted areas where the energy production can be coupled with phytoremediation, and harvested biomass represents a resource and a means to remove contaminants from the soil. Two main processes are considered to evaluate A. donax L. biomass as an energy crop, determined by the timing of harvest: anaerobic digestion with fresh biomass before winter and combustion (e.g., pyrolysis and gasification) of dry canes in late winter. The aim of this work was to evaluate the use of A. donax L. in an area polluted by heavy metals for phytoextraction and energy production at two different harvest times (October and February). For that purpose, we established in polluted area in northern Italy (Caffaro area, Brescia) an experimental field of A. donax, and included switchgrass (Panicum virgatum L.) and mixed meadow species as controls. The results obtained by ICP-MS analysis performed on harvested biomasses highlighted a differential uptake of heavy metals depending on harvest time. In particular, considering the yield in the third year, A. donax was able to remove from the soil 3.87 kg ha−1 of Zn, 2.09 kg ha−1 of Cu and 0.007 kg ha−1 of Cd when harvested in October. Production of A. donax L. for anaerobic digestion or combustion in polluted areas represents a potential solution for both energy production and phytoextraction of heavy metals, in particular Cu, Zn and Cd. Full article
(This article belongs to the Special Issue Heavy Metals in the Environment – Causes and Consequences)
Show Figures

Figure 1

Article
Intrinsically Motivated Open-Ended Multi-Task Learning Using Transfer Learning to Discover Task Hierarchy
Appl. Sci. 2021, 11(3), 975; https://doi.org/10.3390/app11030975 - 21 Jan 2021
Cited by 5 | Viewed by 1003
Abstract
In open-ended continuous environments, robots need to learn multiple parameterised control tasks in hierarchical reinforcement learning. We hypothesise that the most complex tasks can be learned more easily by transferring knowledge from simpler tasks, and faster by adapting the complexity of the actions [...] Read more.
In open-ended continuous environments, robots need to learn multiple parameterised control tasks in hierarchical reinforcement learning. We hypothesise that the most complex tasks can be learned more easily by transferring knowledge from simpler tasks, and faster by adapting the complexity of the actions to the task. We propose a task-oriented representation of complex actions, called procedures, to learn online task relationships and unbounded sequences of action primitives to control the different observables of the environment. Combining both goal-babbling with imitation learning, and active learning with transfer of knowledge based on intrinsic motivation, our algorithm self-organises its learning process. It chooses at any given time a task to focus on; and what, how, when and from whom to transfer knowledge. We show with a simulation and a real industrial robot arm, in cross-task and cross-learner transfer settings, that task composition is key to tackle highly complex tasks. Task decomposition is also efficiently transferred across different embodied learners and by active imitation, where the robot requests just a small amount of demonstrations and the adequate type of information. The robot learns and exploits task dependencies so as to learn tasks of every complexity. Full article
(This article belongs to the Special Issue Cognitive Robotics)
Show Figures

Figure 1

Article
A Tool for the Rapid Seismic Assessment of Historic Masonry Structures Based on Limit Analysis Optimisation and Rocking Dynamics
Appl. Sci. 2021, 11(3), 942; https://doi.org/10.3390/app11030942 - 21 Jan 2021
Cited by 20 | Viewed by 1643
Abstract
This paper presents a user-friendly, CAD-interfaced methodology for the rapid seismic assessment of historic masonry structures. The proposed multi-level procedure consists of a two-step analysis that combines upper bound limit analysis with non-linear dynamic (rocking) analysis to solve for seismic collapse in a [...] Read more.
This paper presents a user-friendly, CAD-interfaced methodology for the rapid seismic assessment of historic masonry structures. The proposed multi-level procedure consists of a two-step analysis that combines upper bound limit analysis with non-linear dynamic (rocking) analysis to solve for seismic collapse in a computationally-efficient manner. In the first step, the failure mechanisms are defined by means of parameterization of the failure surfaces. Hence, the upper bound limit theorem of the limit analysis, coupled with a heuristic solver, is subsequently adopted to search for the load multiplier’s minimum value and the macro-block geometry. In the second step, the kinematic constants defining the rocking equation of motion are automatically computed for the refined macro-block model, which can be solved for representative time-histories. The proposed methodology has been entirely integrated in the user-friendly visual programming environment offered by Rhinoceros3D + Grasshopper, allowing it to be used by students, researchers and practicing structural engineers. Unlike time-consuming advanced methods of analysis, the proposed method allows users to perform a seismic assessment of masonry buildings in a rapid and computationally-efficient manner. Such an approach is particularly useful for territorial scale vulnerability analysis (e.g., for risk assessment and mitigation historic city centres) or as post-seismic event response (when the safety and stability of a large number of buildings need to be assessed with limited resources). The capabilities of the tool are demonstrated by comparing its predictions with those arising from the literature as well as from code-based assessment methods for three case studies. Full article
Show Figures

Figure 1

Article
Human-Centered Artificial Intelligence for Designing Accessible Cultural Heritage
Appl. Sci. 2021, 11(2), 870; https://doi.org/10.3390/app11020870 - 19 Jan 2021
Cited by 8 | Viewed by 2820
Abstract
This paper reviews the literature concerning technology used for creating and delivering accessible museum and cultural heritage sites experiences. It highlights the importance of the delivery suited for everyone from different areas of expertise, namely interaction design, pedagogical and participatory design, and it [...] Read more.
This paper reviews the literature concerning technology used for creating and delivering accessible museum and cultural heritage sites experiences. It highlights the importance of the delivery suited for everyone from different areas of expertise, namely interaction design, pedagogical and participatory design, and it presents how recent and future artificial intelligence (AI) developments can be used for this aim, i.e.,improving and widening online and in situ accessibility. From the literature review analysis, we articulate a conceptual framework that incorporates key elements that constitute museum and cultural heritage online experiences and how these elements are related to each other. Concrete opportunities for future directions empirical research for accessibility of cultural heritage contents are suggested and further discussed. Full article
Show Figures

Figure 1

Article
Deep Learning-Based Methods for Prostate Segmentation in Magnetic Resonance Imaging
Appl. Sci. 2021, 11(2), 782; https://doi.org/10.3390/app11020782 - 15 Jan 2021
Cited by 26 | Viewed by 2125
Abstract
Magnetic Resonance Imaging-based prostate segmentation is an essential task for adaptive radiotherapy and for radiomics studies whose purpose is to identify associations between imaging features and patient outcomes. Because manual delineation is a time-consuming task, we present three deep-learning (DL) approaches, namely UNet, [...] Read more.
Magnetic Resonance Imaging-based prostate segmentation is an essential task for adaptive radiotherapy and for radiomics studies whose purpose is to identify associations between imaging features and patient outcomes. Because manual delineation is a time-consuming task, we present three deep-learning (DL) approaches, namely UNet, efficient neural network (ENet), and efficient residual factorized convNet (ERFNet), whose aim is to tackle the fully-automated, real-time, and 3D delineation process of the prostate gland on T2-weighted MRI. While UNet is used in many biomedical image delineation applications, ENet and ERFNet are mainly applied in self-driving cars to compensate for limited hardware availability while still achieving accurate segmentation. We apply these models to a limited set of 85 manual prostate segmentations using the k-fold validation strategy and the Tversky loss function and we compare their results. We find that ENet and UNet are more accurate than ERFNet, with ENet much faster than UNet. Specifically, ENet obtains a dice similarity coefficient of 90.89% and a segmentation time of about 6 s using central processing unit (CPU) hardware to simulate real clinical conditions where graphics processing unit (GPU) is not always available. In conclusion, ENet could be efficiently applied for prostate delineation even in small image training datasets with potential benefit for patient management personalization. Full article
Show Figures

Figure 1

Article
Genetic Algorithm Based Deep Learning Neural Network Structure and Hyperparameter Optimization
Appl. Sci. 2021, 11(2), 744; https://doi.org/10.3390/app11020744 - 14 Jan 2021
Cited by 11 | Viewed by 1987
Abstract
Alzheimer’s disease is one of the major challenges of population ageing, and diagnosis and prediction of the disease through various biomarkers is the key. While the application of deep learning as imaging technologies has recently expanded across the medical industry, empirical design of [...] Read more.
Alzheimer’s disease is one of the major challenges of population ageing, and diagnosis and prediction of the disease through various biomarkers is the key. While the application of deep learning as imaging technologies has recently expanded across the medical industry, empirical design of these technologies is very difficult. The main reason for this problem is that the performance of the Convolutional Neural Networks (CNN) differ greatly depending on the statistical distribution of the input dataset. Different hyperparameters also greatly affect the convergence of the CNN models. With this amount of information, selecting appropriate parameters for the network structure has became a large research area. Genetic Algorithm (GA), is a very popular technique to automatically select a high-performance network architecture. In this paper, we show the possibility of optimising the network architecture using GA, where its search space includes both network structure configuration and hyperparameters. To verify the performance of our Algorithm, we used an amyloid brain image dataset that is used for Alzheimer’s disease diagnosis. As a result, our algorithm outperforms Genetic CNN by 11.73% on a given classification task. Full article
(This article belongs to the Section Computing and Artificial Intelligence)
Show Figures

Figure 1

Article
The Effect of Chairside Verbal Instructions Matched with Instagram Social Media on Oral Hygiene of Young Orthodontic Patients: A Randomized Clinical Trial
Appl. Sci. 2021, 11(2), 706; https://doi.org/10.3390/app11020706 - 13 Jan 2021
Cited by 9 | Viewed by 1196
Abstract
Objective: To investigate the effectiveness of Instagram in improving oral hygiene compliance and knowledge in young orthodontic patients compared to traditional chairside verbal instructions. Design: Single-center, parallel, randomized controlled trial. Setting: Section of Dentistry of University of Pavia. Participants: 40 patients having fixed [...] Read more.
Objective: To investigate the effectiveness of Instagram in improving oral hygiene compliance and knowledge in young orthodontic patients compared to traditional chairside verbal instructions. Design: Single-center, parallel, randomized controlled trial. Setting: Section of Dentistry of University of Pavia. Participants: 40 patients having fixed appliances in both arches were recruited and randomly divided into an intervention (n = 20) and a control group (n = 20). Intervention: At a first appointment, both groups were given verbal instructions and motivated to oral hygiene. In addition, multimedia contents on Instagram were sent weekly to trial participants for six months. Main outcome measures: For all participants, the bleeding index (BI), modified gingival index (MGI), and plaque index (PI) were assessed at baseline (T0), after one (T1), three (T2), and six months (T3). A questionnaire was administered at the beginning (T0) and at the end of the study (T3) to assess participants’ knowledge. Results: In both groups, BI, MGI, and PI significantly decreased (p < 0.05) at T1 (means control group: BI 0.26 ± 0.22, MGI 0.77 ± 0.36, PI 0.53 ± 0.20; means test group: BI 0.24 ± 0.22, MGI 0.65 ± 0.46, PI 0.49 ± 0.21) compared to baseline (means control group: BI 0.56 ± 0.27, MGI 1.23 ± 0.41, PI 0.87 ± 0.23; means test group: BI 0.54 ± 0.26, MGI 1.18 ± 0.39, PI 0.93 ± 0.20) but no significant differences in clinical measures were showed between T1, T2, and T3 (p > 0.05) (intragroup differences). Trial patients demonstrated significant improvements in knowledge with respect to controls comparing scores at T0 and T3 (p < 0.05) but despite this result in the test group clinical outcomes did not report significant intergroup differences at any time (p > 0.05). Conclusions: Presenting multimedia information through Instagram resulted in a significant improvement in knowledge. Therefore, this social media represents an aid to the standard verbal motivation performed by orthodontists towards young patients under an orthodontic treatment. Full article
(This article belongs to the Special Issue Clinical Applications for Dentistry and Oral Health)
Show Figures

Figure 1

Article
Accelerating Detection of Lung Pathologies with Explainable Ultrasound Image Analysis
Appl. Sci. 2021, 11(2), 672; https://doi.org/10.3390/app11020672 - 12 Jan 2021
Cited by 34 | Viewed by 4575
Abstract
Care during the COVID-19 pandemic hinges upon the existence of fast, safe, and highly sensitive diagnostic tools. Considering significant practical advantages of lung ultrasound (LUS) over other imaging techniques, but difficulties for doctors in pattern recognition, we aim to leverage machine learning toward [...] Read more.
Care during the COVID-19 pandemic hinges upon the existence of fast, safe, and highly sensitive diagnostic tools. Considering significant practical advantages of lung ultrasound (LUS) over other imaging techniques, but difficulties for doctors in pattern recognition, we aim to leverage machine learning toward guiding diagnosis from LUS. We release the largest publicly available LUS dataset for COVID-19 consisting of 202 videos from four classes (COVID-19, bacterial pneumonia, non-COVID-19 viral pneumonia and healthy controls). On this dataset, we perform an in-depth study of the value of deep learning methods for the differential diagnosis of lung pathologies. We propose a frame-based model that correctly distinguishes COVID-19 LUS videos from healthy and bacterial pneumonia data with a sensitivity of 0.90±0.08 and a specificity of 0.96±0.04. To investigate the utility of the proposed method, we employ interpretability methods for the spatio-temporal localization of pulmonary biomarkers, which are deemed useful for human-in-the-loop scenarios in a blinded study with medical experts. Aiming for robustness, we perform uncertainty estimation and demonstrate the model to recognize low-confidence situations which also improves performance. Lastly, we validated our model on an independent test dataset and report promising performance (sensitivity 0.806, specificity 0.962). The provided dataset facilitates the validation of related methodology in the community and the proposed framework might aid the development of a fast, accessible screening method for pulmonary diseases. Dataset and all code are publicly available at: https://github.com/BorgwardtLab/covid19_ultrasound. Full article
Show Figures

Figure 1

Article
Evaluation of the Reaction Time and Accuracy Rate in Normal Subjects, MCI, and Dementia Using Serious Games
Appl. Sci. 2021, 11(2), 628; https://doi.org/10.3390/app11020628 - 11 Jan 2021
Cited by 8 | Viewed by 1138
Abstract
The main purpose of this research is to evaluate the differences in the reaction time and accuracy rate of three categories of subjects using our serious games. Thirty-seven subjects were divided into three groups: normal (n1 = 16), MCI (Mild Cognitive [...] Read more.
The main purpose of this research is to evaluate the differences in the reaction time and accuracy rate of three categories of subjects using our serious games. Thirty-seven subjects were divided into three groups: normal (n1 = 16), MCI (Mild Cognitive Impairment) (n2 = 10), and dementia—moderate-to-severe (n3 = 11) groups based on the MMSE (Mini Mental State Examination). Two serious games were designed: (1) whack-a-mole and (2) hit-the-ball. Two dependent variables, reaction time and accuracy rate, were statistically analyzed to compare elders’ performances in the games among the three groups for three levels of speed: slow, medium, and fast. There were significance differences between the normal group, the MCI group, and the moderate-to-severe dementia group in both the reaction-time and accuracy-rate analyses. We determined that the reaction times of the MCI and dementia groups were shorter compared to those of the normal group, with poorer results also observed in accuracy rate. Therefore, we conclude that our serious games have the feasibility to evaluate reaction performance and could be used in the daily lives of elders followed by clinical treatment in the future. Full article
(This article belongs to the Special Issue Serious Games and Mixed Reality Applications for Healthcare)
Show Figures

Figure 1

Article
Detection of Cardiac Structural Abnormalities in Fetal Ultrasound Videos Using Deep Learning
Appl. Sci. 2021, 11(1), 371; https://doi.org/10.3390/app11010371 - 02 Jan 2021
Cited by 23 | Viewed by 3262
Abstract
Artificial Intelligence (AI) technologies have recently been applied to medical imaging for diagnostic support. With respect to fetal ultrasound screening of congenital heart disease (CHD), it is still challenging to achieve consistently accurate diagnoses owing to its manual operation and the technical differences [...] Read more.
Artificial Intelligence (AI) technologies have recently been applied to medical imaging for diagnostic support. With respect to fetal ultrasound screening of congenital heart disease (CHD), it is still challenging to achieve consistently accurate diagnoses owing to its manual operation and the technical differences among examiners. Hence, we proposed an architecture of Supervised Object detection with Normal data Only (SONO), based on a convolutional neural network (CNN), to detect cardiac substructures and structural abnormalities in fetal ultrasound videos. We used a barcode-like timeline to visualize the probability of detection and calculated an abnormality score of each video. Performance evaluations of detecting cardiac structural abnormalities utilized videos of sequential cross-sections around a four-chamber view (Heart) and three-vessel trachea view (Vessels). The mean value of abnormality scores in CHD cases was significantly higher than normal cases (p < 0.001). The areas under the receiver operating characteristic curve in Heart and Vessels produced by SONO were 0.787 and 0.891, respectively, higher than the other conventional algorithms. SONO achieves an automatic detection of each cardiac substructure in fetal ultrasound videos, and shows an applicability to detect cardiac structural abnormalities. The barcode-like timeline is informative for examiners to capture the clinical characteristic of each case, and it is also expected to acquire one of the important features in the field of medical AI: the development of “explainable AI.” Full article
(This article belongs to the Special Issue Machine Learning in Medical Applications)
Show Figures

Figure 1

Article
Development of 340-GHz Transceiver Front End Based on GaAs Monolithic Integration Technology for THz Active Imaging Array
Appl. Sci. 2020, 10(21), 7924; https://doi.org/10.3390/app10217924 - 09 Nov 2020
Cited by 57 | Viewed by 1467
Abstract
Frequency multipliers and mixers based on Schottky barrier diodes (SBDs) are widely used in terahertz (THz) imaging applications. However, they still face obstacles, such as poor performance consistency caused by discrete flip-chip diodes, as well as low efficiency and large receiving noise temperature. [...] Read more.
Frequency multipliers and mixers based on Schottky barrier diodes (SBDs) are widely used in terahertz (THz) imaging applications. However, they still face obstacles, such as poor performance consistency caused by discrete flip-chip diodes, as well as low efficiency and large receiving noise temperature. It is very hard to meet the requirement of multiple channels in THz imaging array. In order to solve this problem, 12-μm-thick gallium arsenide (GaAs) monolithic integrated technology was adopted. In the process, the diode chip shared the same GaAs substrate with the transmission line, and the diode’s pads were seamlessly connected to the transmission line without using silver glue. A three-dimensional (3D) electromagnetic (EM) model of the diode chip was established in Ansys High Frequency Structure Simulator (HFSS) to accurately characterize the parasitic parameters. Based on the model, by quantitatively analyzing the influence of the surface channel width and the diode anode junction area on the best efficiency, the final parameters and dimensions of the diode were further optimized and determined. Finally, three 0.34 THz triplers and subharmonic mixers (SHMs) were manufactured, assembled, and measured for demonstration, all of which comprised a waveguide housing, a GaAs circuit integrated with diodes, and other external connectors. Experimental results show that all the triplers and SHMs had great performance consistency. Typically, when the input power was 100 mW, the output power of the THz tripler was greater than 1 mW in the frequency range of 324 GHz to 352 GHz, and a peak efficiency of 6.8% was achieved at 338 GHz. The THz SHM exhibited quite a low double sideband (DSB) noise temperature of 900~1500 K and a DSB conversion loss of 6.9~9 dB over the frequency range of 325~352 GHz. It is indicated that the GaAs monolithic integrated process, diodes modeling, and circuits simulation method in this paper provide an effective way to design THz frequency multiplier and mixer circuits. Full article
(This article belongs to the Special Issue Terahertz Sensing and Imaging)
Show Figures

Figure 1

Article
Incorporation of Bioactive Glasses Containing Mg, Sr, and Zn in Electrospun PCL Fibers by Using Benign Solvents
Appl. Sci. 2020, 10(16), 5530; https://doi.org/10.3390/app10165530 - 10 Aug 2020
Cited by 12 | Viewed by 1091
Abstract
Poly(ε-caprolactone) (PCL) and PCL/bioactive glass composite fiber mats were produced by electrospinning technique. To improve cell adhesion and proliferation (i) 45S5, (ii) a bioactive glass containing strontium and magnesium oxides, and (iii) a bioactive glass containing zinc oxide were separately added to the [...] Read more.
Poly(ε-caprolactone) (PCL) and PCL/bioactive glass composite fiber mats were produced by electrospinning technique. To improve cell adhesion and proliferation (i) 45S5, (ii) a bioactive glass containing strontium and magnesium oxides, and (iii) a bioactive glass containing zinc oxide were separately added to the starting PCL solution before electrospinning. A good incorporation of bioactive glass particles in PCL electrospun mats was confirmed by SEM and FTIR analyses. Bioactivity was evaluated by immersion of PCL mats and PCL/bioactive glass electrospun fiber mats in simulated body fluid (SBF). Bone murine stromal cells (ST-2) were employed in WST-8 assay to assess cell viability, cell morphology, and proliferation. The results showed that the presence of bioactive glass particles in the fibers enhances cell adhesion and proliferation compared to neat PCL mats. Furthermore, PCL/bioactive glass electrospun mats showed higher wound-healing rate (measured as cell migration rate) in vitro compared to neat PCL electrospun mats. Therefore, the characteristics of the PCL matrix combined with biological properties of bioactive glasses make PCL/bioactive glass composite ideal candidate for biomedical application. Full article
Show Figures

Figure 1

Article
A New Concept of Digital Twin Supporting Optimization and Resilience of Factories of the Future
Appl. Sci. 2020, 10(13), 4482; https://doi.org/10.3390/app10134482 - 28 Jun 2020
Cited by 42 | Viewed by 3369
Abstract
In the context of Industry 4.0, a growing use is being made of simulation-based decision-support tools commonly named Digital Twins. Digital Twins are replicas of the physical manufacturing assets, providing means for the monitoring and control of individual assets. Although extensive research on [...] Read more.
In the context of Industry 4.0, a growing use is being made of simulation-based decision-support tools commonly named Digital Twins. Digital Twins are replicas of the physical manufacturing assets, providing means for the monitoring and control of individual assets. Although extensive research on Digital Twins and their applications has been carried out, the majority of existing approaches are asset specific. Little consideration is made of human factors and interdependencies between different production assets are commonly ignored. In this paper, we address those limitations and propose innovations for cognitive modeling and co-simulation which may unleash novel uses of Digital Twins in Factories of the Future. We introduce a holistic Digital Twin approach, in which the factory is not represented by a set of separated Digital Twins but by a comprehensive modeling and simulation capacity embracing the full manufacturing process including external network dependencies. Furthermore, we introduce novel approaches for integrating models of human behavior and capacities for security testing with Digital Twins and show how the holistic Digital Twin can enable new services for the optimization and resilience of Factories of the Future. To illustrate this approach, we introduce a specific use-case implemented in field of Aerospace System Manufacturing. Full article
(This article belongs to the Special Issue Cyber Factories – Intelligent and Secure Factories of the Future)
Show Figures

Figure 1

Article
Levels and Changes of Physical Activity in Adolescents during the COVID-19 Pandemic: Contextualizing Urban vs. Rural Living Environment
Appl. Sci. 2020, 10(11), 3997; https://doi.org/10.3390/app10113997 - 09 Jun 2020
Cited by 70 | Viewed by 6593
Abstract
The COVID-19 pandemic and the social distancing implemented shortly after influence physical activity levels (PALs). The purpose of this investigation was to evaluate the changes in PAL and factors associated with PALs among Croatian adolescents while considering the impact of community (urban vs. [...] Read more.
The COVID-19 pandemic and the social distancing implemented shortly after influence physical activity levels (PALs). The purpose of this investigation was to evaluate the changes in PAL and factors associated with PALs among Croatian adolescents while considering the impact of community (urban vs. rural living environment). The sample included 823 adolescents (mean age: 16.5 ± 2.1 years) who were tested on baseline (from October 2019 to March 2020; before COVID-19 pandemic in Croatia) and follow-up (in April 2020; during the COVID-19 pandemic and imposed rules of social distancing). Baseline testing included anthropometrics, physical fitness status, and evaluation of PALs, while follow-up included only PALs (evaluated by a standardized questionnaire through an internet application). The results showed a significant influence of the living environment on the decrease of PAL, with a larger decrease in urban adolescents. Logistic regression showed a higher likelihood for normal PALs at baseline in adolescents who had better fitness status, with no strong confounding effect of the urban/rural environment. The fitness status of urban adolescents predicted their PALs at follow-up. The differences between urban and rural adolescents with regard to the established changes in PALs and relationships between the predictors and PALs are explained by the characteristics of the living communities (lack of organized sports in rural areas), and the level of social distancing in the studied period and region/country. Full article
(This article belongs to the Special Issue COVID-19: Impact on Human Health and Behavior)
Show Figures

Figure 1

Article
COVID-19: A Comparison of Time Series Methods to Forecast Percentage of Active Cases per Population
Appl. Sci. 2020, 10(11), 3880; https://doi.org/10.3390/app10113880 - 03 Jun 2020
Cited by 58 | Viewed by 6322
Abstract
The ongoing COVID-19 pandemic has caused worldwide socioeconomic unrest, forcing governments to introduce extreme measures to reduce its spread. Being able to accurately forecast when the outbreak will hit its peak would significantly diminish the impact of the disease, as it would allow [...] Read more.
The ongoing COVID-19 pandemic has caused worldwide socioeconomic unrest, forcing governments to introduce extreme measures to reduce its spread. Being able to accurately forecast when the outbreak will hit its peak would significantly diminish the impact of the disease, as it would allow governments to alter their policy accordingly and plan ahead for the preventive steps needed such as public health messaging, raising awareness of citizens and increasing the capacity of the health system. This study investigated the accuracy of a variety of time series modeling approaches for coronavirus outbreak detection in ten different countries with the highest number of confirmed cases as of 4 May 2020. For each of these countries, six different time series approaches were developed and compared using two publicly available datasets regarding the progression of the virus in each country and the population of each country, respectively. The results demonstrate that, given data produced using actual testing for a small portion of the population, machine learning time series methods can learn and scale to accurately estimate the percentage of the total population that will become affected in the future. Full article
Show Figures

Figure 1

Article
Performance Evaluation of Two Machine Learning Techniques in Heating and Cooling Loads Forecasting of Residential Buildings
Appl. Sci. 2020, 10(11), 3829; https://doi.org/10.3390/app10113829 - 31 May 2020
Cited by 36 | Viewed by 1677
Abstract
Nowadays, since energy management of buildings contributes to the operation cost, many efforts are made to optimize the energy consumption of buildings. In addition, the most consumed energy in the buildings is assigned to the indoor heating and cooling comforts. In this regard, [...] Read more.
Nowadays, since energy management of buildings contributes to the operation cost, many efforts are made to optimize the energy consumption of buildings. In addition, the most consumed energy in the buildings is assigned to the indoor heating and cooling comforts. In this regard, this paper proposes a heating and cooling load forecasting methodology, which by taking this methodology into the account energy consumption of the buildings can be optimized. Multilayer perceptron (MLP) and support vector regression (SVR) for the heating and cooling load forecasting of residential buildings are employed. MLP and SVR are the applications of artificial neural networks and machine learning, respectively. These methods commonly are used for modeling and regression and produce a linear mapping between input and output variables. Proposed methods are taught using training data pertaining to the characteristics of each sample in the dataset. To apply the proposed methods, a simulated dataset will be used, in which the technical parameters of the building are used as input variables and heating and cooling loads are selected as output variables for each network. Finally, the simulation and numerical results illustrates the effectiveness of the proposed methodologies. Full article
(This article belongs to the Special Issue Renewable Energy Systems 2020)
Show Figures

Figure 1

Article
Automatically Processing IFC Clipping Representation for BIM and GIS Integration at the Process Level
Appl. Sci. 2020, 10(6), 2009; https://doi.org/10.3390/app10062009 - 15 Mar 2020
Cited by 73 | Viewed by 4919
Abstract
The integration of building information modeling (BIM) and geographic information system (GIS) is attracting more attention than ever due to its potential benefits for both the architecture, engineering, and construction (AEC) domain and the geospatial industry. The main challenge in BIM and GIS [...] Read more.
The integration of building information modeling (BIM) and geographic information system (GIS) is attracting more attention than ever due to its potential benefits for both the architecture, engineering, and construction (AEC) domain and the geospatial industry. The main challenge in BIM and GIS integrated application comes from the fundamental data conversion, especially for the geometric information. BIM and GIS use different modeling paradigms to represent objects. The BIM dataset takes, for example, Industry Foundation Classes (IFC) that use solid models, such as boundary representation (B-Rep), swept solid, constructive solid geometry (CSG), and clipping, while the GIS dataset mainly uses surface models or B-Rep. The fundamental data conversion between BIM and GIS is the foundation of BIM and GIS integrated application. However, the efficiency of data conversion has been greatly impaired by the human intervention needed, especially for the conversion of the clipping geometry. The goal of this study is to automate the conversion of IFC clipping representation into the shapefile format. A process-level approach was developed with an algorithm for instantiating unbounded half spaces using B-Rep. Four IFC models were used to validate the proposed method. The results show that (1) the proposed approach can successfully automate the conversion of IFC clipping representation into the shapefile format; and (2) increasing boundary size has no effect on the file size of unbounded half spaces, but slightly increases the producing time of half spaces and processing time of building components. The efficiency of this study can be further improved by using an open-source package, instead of using the low-efficiency packages provided by ArcGIS. Full article
(This article belongs to the Special Issue BIM and GIS Integration for Driving Smarter Decisions)
Show Figures

Figure 1

Article
Real-Time Remote Maintenance Support Based on Augmented Reality (AR)
Appl. Sci. 2020, 10(5), 1855; https://doi.org/10.3390/app10051855 - 08 Mar 2020
Cited by 46 | Viewed by 3041
Abstract
In the realm of the current industrial revolution, interesting innovations as well as new techniques are constantly being introduced by offering fertile ground for further investigation and improvement in the industrial engineering domain. More specifically, cutting-edge digital technologies in the field of Extended [...] Read more.
In the realm of the current industrial revolution, interesting innovations as well as new techniques are constantly being introduced by offering fertile ground for further investigation and improvement in the industrial engineering domain. More specifically, cutting-edge digital technologies in the field of Extended Reality (XR) have become mainstream including Augmented Reality (AR). Furthermore, Cloud Computing has enabled the provision of high-quality services, especially in the controversial field of maintenance. However, since modern machines are becoming more complex, maintenance must be carried out from experienced and well-trained personnel, while overseas support is timely and financially costly. Although AR is a back-bone technology facilitating the development of robust maintenance support tools, they are limited to the provision of predefined scenarios, covering only a limited number of scenarios. This research work aims to address this emerging challenge with the design and development of a framework, for the support of remote maintenance and repair operation based on AR, by creating suitable communication channels between the shop-floor technicians and the expert engineers who are utilizing real-time feedback from the operator’s field of view. The applicability of the developed framework is tested in vitro in a lab-based machine shop and in a real-life industrial scenario. Full article
(This article belongs to the Special Issue Novel Industry 4.0 Technologies and Applications)
Show Figures

Figure 1

Article
Sehaa: A Big Data Analytics Tool for Healthcare Symptoms and Diseases Detection Using Twitter, Apache Spark, and Machine Learning
Appl. Sci. 2020, 10(4), 1398; https://doi.org/10.3390/app10041398 - 19 Feb 2020
Cited by 48 | Viewed by 3990
Abstract
Smartness, which underpins smart cities and societies, is defined by our ability to engage with our environments, analyze them, and make decisions, all in a timely manner. Healthcare is the prime candidate needing the transformative capability of this smartness. Social media could enable [...] Read more.
Smartness, which underpins smart cities and societies, is defined by our ability to engage with our environments, analyze them, and make decisions, all in a timely manner. Healthcare is the prime candidate needing the transformative capability of this smartness. Social media could enable a ubiquitous and continuous engagement between healthcare stakeholders, leading to better public health. Current works are limited in their scope, functionality, and scalability. This paper proposes Sehaa, a big data analytics tool for healthcare in the Kingdom of Saudi Arabia (KSA) using Twitter data in Arabic. Sehaa uses Naive Bayes, Logistic Regression, and multiple feature extraction methods to detect various diseases in the KSA. Sehaa found that the top five diseases in Saudi Arabia in terms of the actual afflicted cases are dermal diseases, heart diseases, hypertension, cancer, and diabetes. Riyadh and Jeddah need to do more in creating awareness about the top diseases. Taif is the healthiest city in the KSA in terms of the detected diseases and awareness activities. Sehaa is developed over Apache Spark allowing true scalability. The dataset used comprises 18.9 million tweets collected from November 2018 to September 2019. The results are evaluated using well-known numerical criteria (Accuracy and F1-Score) and are validated against externally available statistics. Full article
Show Figures

Figure 1

Article
Numerical Study on Hysteretic Behaviour of Horizontal-Connection and Energy-Dissipation Structures Developed for Prefabricated Shear Walls
Appl. Sci. 2020, 10(4), 1240; https://doi.org/10.3390/app10041240 - 12 Feb 2020
Cited by 72 | Viewed by 4329
Abstract
This study proposed a developed horizontal-connection and energy-dissipation structure (HES), which could be employed for horizontal connection of prefabricated shear wall structural system. The HES consists of an external replaceable energy dissipation (ED) zone mainly for energy dissipation and an internal stiffness lifting [...] Read more.
This study proposed a developed horizontal-connection and energy-dissipation structure (HES), which could be employed for horizontal connection of prefabricated shear wall structural system. The HES consists of an external replaceable energy dissipation (ED) zone mainly for energy dissipation and an internal stiffness lifting (SL) zone for enhancing the load-bearing capacity. By the predicted displacement threshold control device, the ED zone made in bolted low-yielding steel plates could firstly dissipate the energy and can be replaced after damage, the SL zone could delay the load-bearing and the load-displacement curves of the HES would exhibit “double-step” characteristics. Detailed finite element models are established and validated in software ABAQUS. parametric analysis including aspect ratio, the shape of the steel plate in the ED zone and the displacement threshold in the SL zone, is conducted. It is found that the HES depicts high energy dissipation ability and its bearing capacity could be obtained again after the yielding of the ED zone. The optimized X-shaped steel plate in the ED zone exhibit better performance. The “double-step” design of the HES is a potential way of improving the seismic and anti-collapsing performance of prefabricated shear wall structures against large and super-large earthquakes. Full article
Show Figures

Figure 1

Article
A Novel Transfer Learning Based Approach for Pneumonia Detection in Chest X-ray Images
Appl. Sci. 2020, 10(2), 559; https://doi.org/10.3390/app10020559 - 12 Jan 2020
Cited by 260 | Viewed by 14067
Abstract
Pneumonia is among the top diseases which cause most of the deaths all over the world. Virus, bacteria and fungi can all cause pneumonia. However, it is difficult to judge the pneumonia just by looking at chest X-rays. The aim of this study [...] Read more.
Pneumonia is among the top diseases which cause most of the deaths all over the world. Virus, bacteria and fungi can all cause pneumonia. However, it is difficult to judge the pneumonia just by looking at chest X-rays. The aim of this study is to simplify the pneumonia detection process for experts as well as for novices. We suggest a novel deep learning framework for the detection of pneumonia using the concept of transfer learning. In this approach, features from images are extracted using different neural network models pretrained on ImageNet, which then are fed into a classifier for prediction. We prepared five different models and analyzed their performance. Thereafter, we proposed an ensemble model that combines outputs from all pretrained models, which outperformed individual models, reaching the state-of-the-art performance in pneumonia recognition. Our ensemble model reached an accuracy of 96.4% with a recall of 99.62% on unseen data from the Guangzhou Women and Children’s Medical Center dataset. Full article
(This article belongs to the Special Issue Signal Processing and Machine Learning for Biomedical Data)
Show Figures

Figure 1

Article
Evaluation of the Ecotoxicological Potential of Fly Ash and Recycled Concrete Aggregates Use in Concrete
Appl. Sci. 2020, 10(1), 351; https://doi.org/10.3390/app10010351 - 03 Jan 2020
Cited by 19 | Viewed by 1574
Abstract
This study applies a methodology to evaluate the ecotoxicological potential of raw materials and cement-based construction materials. In this study, natural aggregates and Portland cement were replaced with non-conventional recycled concrete aggregates (RA) and fly ash (FA), respectively, in the production of two [...] Read more.
This study applies a methodology to evaluate the ecotoxicological potential of raw materials and cement-based construction materials. In this study, natural aggregates and Portland cement were replaced with non-conventional recycled concrete aggregates (RA) and fly ash (FA), respectively, in the production of two concrete products alternative to conventional concrete (used as reference). The experimental program involved assessing both the chemical properties (non-metallic and metallic parameters) and ecotoxicity data (battery of tests with the luminescent bacterium Vibrio fischeri, the freshwater crustacean Daphnia magna, and the yeast Saccharomyces cerevisiae) of eluates obtained from leaching tests of RA, FA, and the three concrete mixes. Even though the results indicated that RA and FA have the ability to release some chemicals into the water and induce its alkalinisation, the respective eluate samples presented no or low levels of potential ecotoxicity. However, eluates from concrete mixes produced with a replacement ratio of Portland cement with 60% of FA and 100% of natural aggregates and produced with 60% of FA and 100% of RA were classified as clearly ecotoxic mainly towards Daphnia magna mobility. Therefore, raw materials with weak evidences of ecotoxicity could lead to the production of concrete products with high ecotoxicological potential. Overall, the results obtained highlight the importance of integrating data from the chemical and ecotoxicological characterization of materials’ eluate samples aiming to assess the possible environmental risk of the construction materials, namely of incorporating non-conventional raw materials in concrete, and contributing to achieve construction sustainability. Full article
(This article belongs to the Special Issue Low Binder Concrete and Mortars)
Show Figures

Figure 1

Article
Application of a Hybrid Artificial Neural Network-Particle Swarm Optimization (ANN-PSO) Model in Behavior Prediction of Channel Shear Connectors Embedded in Normal and High-Strength Concrete
Appl. Sci. 2019, 9(24), 5534; https://doi.org/10.3390/app9245534 - 16 Dec 2019
Cited by 146 | Viewed by 3034
Abstract
Channel shear connectors are known as an appropriate alternative for common shear connectors due to having a lower manufacturing cost and an easier installation process. The behavior of channel connectors is generally determined through conducting experiments. However, these experiments are not only costly [...] Read more.
Channel shear connectors are known as an appropriate alternative for common shear connectors due to having a lower manufacturing cost and an easier installation process. The behavior of channel connectors is generally determined through conducting experiments. However, these experiments are not only costly but also time-consuming. Moreover, the impact of other parameters cannot be easily seen in the behavior of the connectors. This paper aims to investigate the application of a hybrid artificial neural network–particle swarm optimization (ANN-PSO) model in the behavior prediction of channel connectors embedded in normal and high-strength concrete (HSC). To generate the required data, an experimental project was conducted. Dimensions of the channel connectors and the compressive strength of concrete were adopted as the inputs of the model, and load and slip were predicted as the outputs. To evaluate the ANN-PSO model, an ANN model was also developed and tuned by a backpropagation (BP) learning algorithm. The results of the paper revealed that an ANN model could properly predict the behavior of channel connectors and eliminate the need for conducting costly experiments to some extent. In addition, in this case, the ANN-PSO model showed better performance than the ANN-BP model by resulting in superior performance indices. Full article
Show Figures

Figure 1

Article
Finite Element Analysis of Thermo-Diffusion and Multi-Slip Effects on MHD Unsteady Flow of Casson Nano-Fluid over a Shrinking/Stretching Sheet with Radiation and Heat Source
Appl. Sci. 2019, 9(23), 5217; https://doi.org/10.3390/app9235217 - 30 Nov 2019
Cited by 58 | Viewed by 1254
Abstract
In this article, we probe the multiple-slip effects on magnetohydrodynamic unsteady Casson nano-fluid flow over a penetrable stretching sheet, sheet entrenched in a porous medium with thermo-diffusion effect, and injection/suction in the presence of heat source. The flow is engendered due to the [...] Read more.
In this article, we probe the multiple-slip effects on magnetohydrodynamic unsteady Casson nano-fluid flow over a penetrable stretching sheet, sheet entrenched in a porous medium with thermo-diffusion effect, and injection/suction in the presence of heat source. The flow is engendered due to the unsteady time-dependent stretching sheet retained inside the porous medium. The leading non-linear partial differential equations are transmuted in the system of coupled nonlinear ordinary differential equations by using appropriate transformations, then the transformed equations are solved by using the variational finite element method numerically. The velocity, temperature, solutal concentration, and nano-particles concentration, as well as the rate of heat transfer, the skin friction coefficient, and Sherwood number for solutal concentration, are presented for several physical parameters. Next, the effects of these various physical parameters are conferred with graphs and tables. The exact values of flow velocity, skin friction, and Nusselt number are compared with a numerical solution acquired with the finite element method (FEM), and also with numerical results accessible in literature. In the end, we rationalize the convergence of the finite element numerical solution, and the calculations are carried out by reducing the mesh size. Full article
(This article belongs to the Section Nanotechnology and Applied Nanosciences)
Show Figures

Figure 1

Article
Comparing AutoDock and Vina in Ligand/Decoy Discrimination for Virtual Screening
Appl. Sci. 2019, 9(21), 4538; https://doi.org/10.3390/app9214538 - 25 Oct 2019
Cited by 38 | Viewed by 3238
Abstract
AutoDock and Vina are two of the most widely used protein–ligand docking programs. The fact that these programs are free and available under an open source license, also makes them a very popular first choice for many users and a common starting point [...] Read more.
AutoDock and Vina are two of the most widely used protein–ligand docking programs. The fact that these programs are free and available under an open source license, also makes them a very popular first choice for many users and a common starting point for many virtual screening campaigns, particularly in academia. Here, we evaluated the performance of AutoDock and Vina against an unbiased dataset containing 102 protein targets, 22,432 active compounds and 1,380,513 decoy molecules. In general, the results showed that the overall performance of Vina and AutoDock was comparable in discriminating between actives and decoys. However, the results varied significantly with the type of target. AutoDock was better in discriminating ligands and decoys in more hydrophobic, poorly polar and poorly charged pockets, while Vina tended to give better results for polar and charged binding pockets. For the type of ligand, the tendency was the same for both Vina and AutoDock. Bigger and more flexible ligands still presented a bigger challenge for these docking programs. A set of guidelines was formulated, based on the strengths and weaknesses of both docking program and their limits of validation. Full article
(This article belongs to the Section Applied Biosciences and Bioengineering)
Show Figures

Figure 1

Article
Improving Electric Energy Consumption Prediction Using CNN and Bi-LSTM
Appl. Sci. 2019, 9(20), 4237; https://doi.org/10.3390/app9204237 - 10 Oct 2019
Cited by 79 | Viewed by 4177
Abstract
The electric energy consumption prediction (EECP) is an essential and complex task in intelligent power management system. EECP plays a significant role in drawing up a national energy development policy. Therefore, this study proposes an Electric Energy Consumption Prediction model utilizing the combination [...] Read more.
The electric energy consumption prediction (EECP) is an essential and complex task in intelligent power management system. EECP plays a significant role in drawing up a national energy development policy. Therefore, this study proposes an Electric Energy Consumption Prediction model utilizing the combination of Convolutional Neural Network (CNN) and Bi-directional Long Short-Term Memory (Bi-LSTM) that is named EECP-CBL model to predict electric energy consumption. In this framework, two CNNs in the first module extract the important information from several variables in the individual household electric power consumption (IHEPC) dataset. Then, Bi-LSTM module with two Bi-LSTM layers uses the above information as well as the trends of time series in two directions including the forward and backward states to make predictions. The obtained values in the Bi-LSTM module will be passed to the last module that consists of two fully connected layers for finally predicting the electric energy consumption in the future. The experiments were conducted to compare the prediction performances of the proposed model and the state-of-the-art models for the IHEPC dataset with several variants. The experimental results indicate that EECP-CBL framework outperforms the state-of-the-art approaches in terms of several performance metrics for electric energy consumption prediction on several variations of IHEPC dataset in real-time, short-term, medium-term and long-term timespans. Full article
(This article belongs to the Special Issue Actionable Pattern-Driven Analytics and Prediction)
Show Figures

Figure 1

Article
Swing Vibration Control of Suspended Structure Using Active Rotary Inertia Driver System: Parametric Analysis and Experimental Verification
Appl. Sci. 2019, 9(15), 3144; https://doi.org/10.3390/app9153144 - 02 Aug 2019
Cited by 81 | Viewed by 1584
Abstract
The Active Rotary Inertia Driver (ARID) system is a novel vibration control system that can effectively mitigate the swing vibration of suspended structures. Parametric analysis is carried out using Simulink based on the mathematical model and the effectiveness is further validated by a [...] Read more.
The Active Rotary Inertia Driver (ARID) system is a novel vibration control system that can effectively mitigate the swing vibration of suspended structures. Parametric analysis is carried out using Simulink based on the mathematical model and the effectiveness is further validated by a series of experiments. Firstly, the active controller is designed based on the system mathematical model and the LQR (linear quadratic regulator) algorithm. Next, the parametric analysis is carried out using Simulink to study the key parameters such as the coefficient of the control algorithm, the rotary inertia ratio. Lastly, the ARID system control effectiveness and the parametric analysis results are further validated by the shaking table experiments. The effectiveness and robustness of the ARID system are well verified. The dynamic characteristics of this system are further studied, and the conclusions of this paper provide a theoretical basis for further development of such unique control system. Full article
Show Figures

Figure 1

Article
When Energy Trading Meets Blockchain in Electrical Power System: The State of the Art
Appl. Sci. 2019, 9(8), 1561; https://doi.org/10.3390/app9081561 - 15 Apr 2019
Cited by 85 | Viewed by 4308
Abstract
With the rapid growth of renewable energy resources, energy trading has been shifting from the centralized manner to distributed manner. Blockchain, as a distributed public ledger technology, has been widely adopted in the design of new energy trading schemes. However, there are many [...] Read more.
With the rapid growth of renewable energy resources, energy trading has been shifting from the centralized manner to distributed manner. Blockchain, as a distributed public ledger technology, has been widely adopted in the design of new energy trading schemes. However, there are many challenging issues in blockchain-based energy trading, e.g., low efficiency, high transaction cost, and security and privacy issues. To tackle these challenges, many solutions have been proposed. In this survey, the blockchain-based energy trading in the electrical power system is thoroughly investigated. Firstly, the challenges in blockchain-based energy trading are identified and summarized. Then, the existing energy trading schemes are studied and classified into three categories based on their main focuses: energy transaction, consensus mechanism, and system optimization. Blockchain-based energy trading has been a popular research topic, new blockchain architectures, models and products are continually emerging to overcome the limitations of existing solutions, forming a virtuous circle. The internal combination of different blockchain types and the combination of blockchain with other technologies improve the blockchain-based energy trading system to better satisfy the practical requirements of modern power systems. However, there are still some problems to be solved, for example, the lack of regulatory system, environmental challenges and so on. In the future, we will strive for a better optimized structure and establish a comprehensive security assessment model for blockchain-based energy trading system. Full article
(This article belongs to the Special Issue Intelligent Energy Management of Electrical Power Systems)
Show Figures

Figure 1

Article
Effect of Process Parameters on the Generated Surface Roughness of Down-Facing Surfaces in Selective Laser Melting
Appl. Sci. 2019, 9(6), 1256; https://doi.org/10.3390/app9061256 - 26 Mar 2019
Cited by 66 | Viewed by 4255
Abstract
Additive manufacturing provides a number of benefits in terms of infinite freedom to design complex parts and reduced lead-times while globally reducing the size of supply chains as it brings all production processes under one roof. However, additive manufacturing (AM) lags far behind [...] Read more.
Additive manufacturing provides a number of benefits in terms of infinite freedom to design complex parts and reduced lead-times while globally reducing the size of supply chains as it brings all production processes under one roof. However, additive manufacturing (AM) lags far behind conventional manufacturing in terms of surface quality. This proves a hindrance for many companies considering investment in AM. The aim of this work is to investigate the effect of varying process parameters on the resultant roughness of the down-facing surfaces in selective laser melting (SLM). A systematic experimental study was carried out and the effects of the interaction of the different parameters and their effect on the surface roughness (Sa) were analyzed. It was found that the interaction and interdependency between parameters were of greatest significance to the obtainable surface roughness, though their effects vary greatly depending on the applied levels. This behavior was mainly attributed to the difference in energy absorbed by the powder. Predictive process models for optimization of process parameters for minimizing the obtained Sa in 45° and 35° down-facing surface, individually, were achieved with average error percentages of 5% and 6.3%, respectively, however further investigation is still warranted. Full article
(This article belongs to the Special Issue Micro/Nano Manufacturing)
Show Figures

Graphical abstract

Article
Assessing Dynamic Conditions of the Retaining Wall: Developing Two Hybrid Intelligent Models
Appl. Sci. 2019, 9(6), 1042; https://doi.org/10.3390/app9061042 - 13 Mar 2019
Cited by 99 | Viewed by 2859
Abstract
The precise estimation and forecast of the safety factor (SF) in civil engineering applications is considered as an important issue to reduce engineering risk. The present research investigates new artificial intelligence (AI) techniques for the prediction of SF values of retaining walls, as [...] Read more.
The precise estimation and forecast of the safety factor (SF) in civil engineering applications is considered as an important issue to reduce engineering risk. The present research investigates new artificial intelligence (AI) techniques for the prediction of SF values of retaining walls, as important and resistant structures for ground forces. These structures have complicated performances in dynamic conditions. Consequently, more than 8000 designs of these structures were dynamically evaluated. Two AI models, namely the imperialist competitive algorithm (ICA)-artificial neural network (ANN), and the genetic algorithm (GA)-ANN were used for the forecasting of SF values. In order to design intelligent models, parameters i.e., the wall thickness, stone density, wall height, soil density, and internal soil friction angle were examined under different dynamic conditions and assigned as inputs to predict SF of retaining walls. Various models of these systems were constructed and compared with each other to obtain the best one. Results of models indicated that although both hybrid models are able to predict SF values with a high accuracy and they can be introduced as new models in the field, the retaining wall performance could be properly predicted in dynamic conditions using the ICA-ANN model. Under these conditions, a combination of engineering design and artificial intelligence techniques can be used to control and secure retaining walls in dynamic conditions. Full article
(This article belongs to the Special Issue Soft Computing Techniques in Structural Engineering and Materials)
Show Figures

Figure 1

Article
Behavior of Fiber-Reinforced and Lime-Stabilized Clayey Soil in Triaxial Tests
Appl. Sci. 2019, 9(5), 900; https://doi.org/10.3390/app9050900 - 03 Mar 2019
Cited by 57 | Viewed by 2596
Abstract
The beneficial role of combining fiber reinforcement with lime stabilization in altering soil behavior has been established in the literature. However, the coupling effect of their combination still remains unclear in terms of its magnitude and microscopic mechanism, especially for natural fibers with [...] Read more.
The beneficial role of combining fiber reinforcement with lime stabilization in altering soil behavior has been established in the literature. However, the coupling effect of their combination still remains unclear in terms of its magnitude and microscopic mechanism, especially for natural fibers with special microstructures. The objective of this study was to investigate the coupling effect of wheat straw fiber reinforcement and lime stabilization on the mechanical behavior of Hefei clayey soil. To achieve this, an experimental program including unconsolidated–undrained (UU) triaxial tests and SEM analysis was implemented. Static compaction test samples were prepared on untreated soil, fiber-reinforced soil, lime-stabilized soil, and lime-stabilized/fiber-reinforced soil at optimum moisture content with determining of the maximum dry density of the untreated soil. The lime was added in three different contents of 2%, 4%, and 6%, and 13 mm long wheat straw fiber slices with a cross section one-quarter that of the intact ones were mixed in at 0.2%, 0.4%, and 0.6% by dry weight of soil. Analysis of the derived results indicated that the addition of a small amount of wheat straw fibers into lime-stabilized soil improved the intensity of the strain-softening behavior associated with mere lime stabilization. The observed evidence that the shear strength increase brought by a combination of 0.4% fiber reinforcement and 4% lime stabilization was smaller than the summation of the shear strength increases brought by their presence alone in a sample demonstrated a coupling effect between fiber reinforcement and lime stabilization. This coupling effect was also detected in the comparisons of the secant modulus and failure pattern between the combined treatment and the individual treatments. These manifestations of the coupling effect were explained by a microscopic mechanism wherein the fiber reinforcing effect was made more effective by the ways in which lime chemically stabilized the soil and lime stabilization development was quickened by the water channels passing through the surfaces and honeycomb pores of the wheat straw fibers. Full article
(This article belongs to the Section Civil Engineering)
Show Figures

Figure 1

Article
Optimization of EPB Shield Performance with Adaptive Neuro-Fuzzy Inference System and Genetic Algorithm
Appl. Sci. 2019, 9(4), 780; https://doi.org/10.3390/app9040780 - 22 Feb 2019
Cited by 66 | Viewed by 2494
Abstract
The prediction of earth pressure balance (EPB) shield performance is an essential part of project scheduling and cost estimation of tunneling projects. This paper establishes an efficient multi-objective optimization model to predict the shield performance during the tunneling process. This model integrates the [...] Read more.
The prediction of earth pressure balance (EPB) shield performance is an essential part of project scheduling and cost estimation of tunneling projects. This paper establishes an efficient multi-objective optimization model to predict the shield performance during the tunneling process. This model integrates the adaptive neuro-fuzzy inference system (ANFIS) with the genetic algorithm (GA). The hybrid model uses shield operational parameters as inputs and computes the advance rate as output. GA enhances the accuracy of ANFIS for runtime parameters tuning by multi-objective fitness function. Prior to modeling, datasets were established, and critical operating parameters were identified through principal component analysis. Then, the tunneling case for Guangzhou metro line number 9 was adopted to verify the applicability of the proposed model. Results were then compared with those of the ANFIS model. The comparison showed that the multi-objective ANFIS-GA model is more successful than the ANFIS model in predicting the advance rate with a high accuracy, which can be used to guide the tunnel performance in the field. Full article
Show Figures

Figure 1

Article
S-Box Based Image Encryption Application Using a Chaotic System without Equilibrium
Appl. Sci. 2019, 9(4), 781; https://doi.org/10.3390/app9040781 - 22 Feb 2019
Cited by 74 | Viewed by 2497
Abstract
Chaotic systems without equilibrium are of interest because they are the systems with hidden attractors. A nonequilibrium system with chaos is introduced in this work. Chaotic behavior of the system is verified by phase portraits, Lyapunov exponents, and entropy. We have implemented a [...] Read more.
Chaotic systems without equilibrium are of interest because they are the systems with hidden attractors. A nonequilibrium system with chaos is introduced in this work. Chaotic behavior of the system is verified by phase portraits, Lyapunov exponents, and entropy. We have implemented a real electronic circuit of the system and reported experimental results. By using this new chaotic system, we have constructed S-boxes which are applied to propose a novel image encryption algorithm. In the designed encryption algorithm, three S-boxes with strong cryptographic properties are used for the sub-byte operation. Particularly, the S-box for the sub-byte process is selected randomly. In addition, performance analyses of S-boxes and security analyses of the encryption processes have been presented. Full article
(This article belongs to the Special Issue Applied Sciences Based on and Related to Computer and Control)
Show Figures

Figure 1

Article
Effects of Graphene Nanoplatelets and Multiwall Carbon Nanotubes on the Structure and Mechanical Properties of Poly(lactic acid) Composites: A Comparative Study
Appl. Sci. 2019, 9(3), 469; https://doi.org/10.3390/app9030469 - 30 Jan 2019
Cited by 56 | Viewed by 2263
Abstract
Poly(lactic acid)/graphene and poly(lactic acid)/carbon nanotube nanocomposites were prepared by an easy and low-cost method of melt blending of preliminary grinded poly(lactic acid) (PLA) with nanosized carbon fillers used as powder. Morphological, structural and mechanical properties were investigated to reveal the influence of [...] Read more.
Poly(lactic acid)/graphene and poly(lactic acid)/carbon nanotube nanocomposites were prepared by an easy and low-cost method of melt blending of preliminary grinded poly(lactic acid) (PLA) with nanosized carbon fillers used as powder. Morphological, structural and mechanical properties were investigated to reveal the influence of carbon nanofiller on the PLA–based composite. The dependence of tensile strength on nanocomposite loading was defined by a series of experiments over extruded filaments using a universal mechanical testing instrument. The applying the XRD technique disclosed that compounds crystallinity significantly changed upon addition of multi walled carbon nanotubes. We demonstrated that Raman spectroscopy can be used as a quick and unambiguous method to determine the homogeneity of the nanocomposites in terms of carbon filler dispersion in a polymer matrix. Full article
(This article belongs to the Special Issue Polymer Nanocomposite for 3D Printing and Applications)
Show Figures

Figure 1

Article
Landslide Susceptibility Modeling Using Integrated Ensemble Weights of Evidence with Logistic Regression and Random Forest Models
Appl. Sci. 2019, 9(1), 171; https://doi.org/10.3390/app9010171 - 04 Jan 2019
Cited by 83 | Viewed by 2937
Abstract
The main aim of this study was to compare the performances of the hybrid approaches of traditional bivariate weights of evidence (WoE) with multivariate logistic regression (WoE-LR) and machine learning-based random forest (WoE-RF) for landslide susceptibility mapping. The performance of the three landslide [...] Read more.
The main aim of this study was to compare the performances of the hybrid approaches of traditional bivariate weights of evidence (WoE) with multivariate logistic regression (WoE-LR) and machine learning-based random forest (WoE-RF) for landslide susceptibility mapping. The performance of the three landslide models was validated with receiver operating characteristic (ROC) curves and area under the curve (AUC). The results showed that the areas under the curve obtained using the WoE, WoE-LR, and WoE-RF methods were 0.720, 0.773, and 0.802 for the training dataset, and were 0.695, 0.763, and 0.782 for the validation dataset, respectively. The results demonstrate the superiority of hybrid models and that the resultant maps would be useful for land use planning in landslide-prone areas. Full article
Show Figures

Figure 1

Article
Recognition of Acoustic Signals of Commutator Motors
Appl. Sci. 2018, 8(12), 2630; https://doi.org/10.3390/app8122630 - 15 Dec 2018
Cited by 46 | Viewed by 2171
Abstract
Most faults can stop a motor, and time is lost in fixing the damaged motor. This is a reason why it is essential to develop fault-detection methods. This paper describes the acoustic-based fault detection of two commutator motors: the commutator motor of an [...] Read more.
Most faults can stop a motor, and time is lost in fixing the damaged motor. This is a reason why it is essential to develop fault-detection methods. This paper describes the acoustic-based fault detection of two commutator motors: the commutator motor of an electric impact drill and the commutator motor of a blender. Acoustic signals were recorded by a smartphone. Five states of the electric impact drill and three states of the blender were analysed: for the electric impact drill, these states were healthy, damaged gear train, faulty fan with five broken rotor blades, faulty fan with 10 broken rotor blades, and shifted brush (motor off); for the blender, these states were healthy, faulty fan with two broken rotor blades, and faulty fan with five broken rotor blades. A feature extraction method, MSAF-RATIO-27-MULTIEXPANDED-4-GROUPS (Method of Selection of Amplitudes of Frequency Ratio of 27% Multiexpanded 4 Groups), was developed and used for the computation of feature vectors. The nearest mean (NM) and support vector machine (SVM) classifiers were used for data classification. Analysis of the recognition of acoustic signals was carried out. The analysed value of TEEID (the total efficiency of recognition of the electric impact drill) was equal to 96% for the NM classifier and 88.8% for SVM. The analysed value of TEB (the total efficiency of recognition of the blender) was equal to 100% for the NM classifier and 94.11% for SVM. Full article
(This article belongs to the Special Issue Fault Diagnosis of Rotating Machine)
Show Figures

Figure 1

Article
Classification of Heart Sound Signal Using Multiple Features
Appl. Sci. 2018, 8(12), 2344; https://doi.org/10.3390/app8122344 - 22 Nov 2018
Cited by 94 | Viewed by 5807
Abstract
Cardiac disorders are critical and must be diagnosed in the early stage using routine auscultation examination with high precision. Cardiac auscultation is a technique to analyze and listen to heart sound using electronic stethoscope, an electronic stethoscope is a device which provides the [...] Read more.
Cardiac disorders are critical and must be diagnosed in the early stage using routine auscultation examination with high precision. Cardiac auscultation is a technique to analyze and listen to heart sound using electronic stethoscope, an electronic stethoscope is a device which provides the digital recording of the heart sound called phonocardiogram (PCG). This PCG signal carries useful information about the functionality and status of the heart and hence several signal processing and machine learning technique can be applied to study and diagnose heart disorders. Based on PCG signal, the heart sound signal can be classified to two main categories i.e., normal and abnormal categories. We have created database of 5 categories of heart sound signal (PCG signals) from various sources which contains one normal and 4 are abnormal categories. This study proposes an improved, automatic classification algorithm for cardiac disorder by heart sound signal. We extract features from phonocardiogram signal and then process those features using machine learning techniques for classification. In features extraction, we have used Mel Frequency Cepstral Coefficient (MFCCs) and Discrete Wavelets Transform (DWT) features from the heart sound signal, and for learning and classification we have used support vector machine (SVM), deep neural network (DNN) and centroid displacement based k nearest neighbor. To improve the results and classification accuracy, we have combined MFCCs and DWT features for training and classification using SVM and DWT. From our experiments it has been clear that results can be greatly improved when Mel Frequency Cepstral Coefficient and Discrete Wavelets Transform features are fused together and used for classification via support vector machine, deep neural network and k-neareast neighbor(KNN). The methodology discussed in this paper can be used to diagnose heart disorders in patients up to 97% accuracy. The code and dataset can be accessed at “https://github.com/yaseen21khan/Classification-of-Heart-Sound-Signal-Using-Multiple-Features-/blob/master/README.md”. Full article
(This article belongs to the Special Issue Deep Learning and Big Data in Healthcare)
Show Figures

Figure 1

Article
Feasibility Study of Steel Bar Corrosion Monitoring Using a Piezoceramic Transducer Enabled Time Reversal Method
Appl. Sci. 2018, 8(11), 2304; https://doi.org/10.3390/app8112304 - 19 Nov 2018
Cited by 55 | Viewed by 2142
Abstract
Steel bars, which are commonly used as reinforcements in concrete structures, are slender rods and are good conduits for stress wave propagation. In this paper, a lead zirconate titanate (PZT)-based steel bar corrosion monitoring approach was proposed. Two PZT transducers are surface-bonded on [...] Read more.
Steel bars, which are commonly used as reinforcements in concrete structures, are slender rods and are good conduits for stress wave propagation. In this paper, a lead zirconate titanate (PZT)-based steel bar corrosion monitoring approach was proposed. Two PZT transducers are surface-bonded on the two ends of a steel rod, respectively. One works as actuator to generate stress waves, and the other functions as a sensor to detect the propagated stress waves. Time reverse technology was applied in this research to monitor the corrosion of the steel bars with a high signal to noise ratio (SNR). Accelerated corrosion experiments of steel bars were conducted. The anti-corrosion performance of the protected piezoceramic transducers was tested first, and then they were used to monitor the corrosion of the steel bar using the time reversal method. The degree of corrosion in the steel bar was determined by the ratio of mass loss during the experiment. The experimental results show that the peak values of the signal that were obtained by time reversal operation are linearly related to the degree of corrosion of the steel bar, which demonstrates the feasibility of the proposed approach for monitoring the corrosion of steel bars using the time reversal method enabled by piezoceramic transducers. Full article
(This article belongs to the Special Issue Structural Damage Detection and Health Monitoring)
Show Figures

Figure 1

Article
Cu-Doped TiO2: Visible Light Assisted Photocatalytic Antimicrobial Activity
Appl. Sci. 2018, 8(11), 2067; https://doi.org/10.3390/app8112067 - 26 Oct 2018
Cited by 110 | Viewed by 6150
Abstract
Surface contamination by microbes is a major public health concern. A damp environment is one of potential sources for microbe proliferation. Smart photocatalytic coatings on building surfaces using semiconductors like titania (TiO2) can effectively curb this growing threat. Metal-doped titania in [...] Read more.
Surface contamination by microbes is a major public health concern. A damp environment is one of potential sources for microbe proliferation. Smart photocatalytic coatings on building surfaces using semiconductors like titania (TiO2) can effectively curb this growing threat. Metal-doped titania in anatase phase has been proven as a promising candidate for energy and environmental applications. In this present work, the antimicrobial efficacy of copper (Cu)-doped TiO2 (Cu-TiO2) was evaluated against Escherichia coli (Gram-negative) and Staphylococcus aureus (Gram-positive) under visible light irradiation. Doping of a minute fraction of Cu (0.5 mol %) in TiO2 was carried out via sol-gel technique. Cu-TiO2 further calcined at various temperatures (in the range of 500–700 °C) to evaluate the thermal stability of TiO2 anatase phase. The physico-chemical properties of the samples were characterized through X-ray diffraction (XRD), Raman spectroscopy, X-ray photo-electron spectroscopy (XPS) and UV–visible spectroscopy techniques. XRD results revealed that the anatase phase of TiO2 was maintained well, up to 650 °C, by the Cu dopant. UV–vis results suggested that the visible light absorption property of Cu-TiO2 was enhanced and the band gap is reduced to 2.8 eV. Density functional theory (DFT) studies emphasize the introduction of Cu+ and Cu2+ ions by replacing Ti4+ ions in the TiO2 lattice, creating oxygen vacancies. These further promoted the photocatalytic efficiency. A significantly high bacterial inactivation (99.9999%) was attained in 30 min of visible light irradiation by Cu-TiO2. Full article
(This article belongs to the Special Issue Cu and Cu-Based Nanoparticles: Applications in Catalysis)
Show Figures

Graphical abstract

Back to TopTop