Technologies

Article

12 pages, 3271 KiB

Open AccessEditor’s ChoiceArticle

Parasitic Coupling in 3D Sequential Integration: The Example of a Two-Layer 3D Pixel

by Petros Sideris, Arnaud Peizerat, Perrine Batude, Gilles Sicard and Christoforos Theodorou

Technologies 2022, 10(2), 38; https://doi.org/10.3390/technologies10020038 - 28 Feb 2022

Cited by 1 | Viewed by 4831

In this paper, we present a thorough analysis of parasitic coupling effects between different electrodes for a 3D Sequential Integration circuit example comprising stacked devices. More specifically, this study is performed for a Back-Side Illuminated, 4T–APS, 3D Sequential Integration pixel with both its [...] Read more.

In this paper, we present a thorough analysis of parasitic coupling effects between different electrodes for a 3D Sequential Integration circuit example comprising stacked devices. More specifically, this study is performed for a Back-Side Illuminated, 4T–APS, 3D Sequential Integration pixel with both its photodiode and Transfer Gate at the bottom tier and the other parts of the circuit on the top tier. The effects of voltage bias and 3D inter-tier contacts are studied by using TCAD simulations. Coupling-induced electrical parameter variations are compared against variations due to temperature change, revealing that these two effects can cause similar levels of readout error for the top-tier readout circuit. On the bright side, we also demonstrate that in the case of a rolling shutter pixel readout, the coupling effect becomes nearly negligible. Therefore, we estimate that the presence of an inter-tier ground plane, normally used for electrical isolation, is not strictly mandatory for Monolithic 3D pixels. Full article

(This article belongs to the Special Issue MOCAST 2021)

► Show Figures

Figure 1

13 pages, 1030 KiB

Open AccessEditor’s ChoiceArticle

Lightweight Neural Network for COVID-19 Detection from Chest X-ray Images Implemented on an Embedded System

by Theodora Sanida, Argyrios Sideris, Dimitris Tsiktsiris and Minas Dasygenis

Technologies 2022, 10(2), 37; https://doi.org/10.3390/technologies10020037 - 25 Feb 2022

Cited by 27 | Viewed by 5789

Abstract

At the end of 2019, a severe public health threat named coronavirus disease (COVID-19) spread rapidly worldwide. After two years, this coronavirus still spreads at a fast rate. Due to its rapid spread, the immediate and rapid diagnosis of COVID-19 is of utmost [...] Read more.

At the end of 2019, a severe public health threat named coronavirus disease (COVID-19) spread rapidly worldwide. After two years, this coronavirus still spreads at a fast rate. Due to its rapid spread, the immediate and rapid diagnosis of COVID-19 is of utmost importance. In the global fight against this virus, chest X-rays are essential in evaluating infected patients. Thus, various technologies that enable rapid detection of COVID-19 can offer high detection accuracy to health professionals to make the right decisions. The latest emerging deep-learning (DL) technology enhances the power of medical imaging tools by providing high-performance classifiers in X-ray detection, and thus various researchers are trying to use it with limited success. Here, we propose a robust, lightweight network where excellent classification results can diagnose COVID-19 by evaluating chest X-rays. The experimental results showed that the modified architecture of the model we propose achieved very high classification performance in terms of accuracy, precision, recall, and f1-score for four classes (COVID-19, normal, viral pneumonia and lung opacity) of 21.165 chest X-ray images, and at the same time meeting real-time constraints, in a low-power embedded system. Finally, our work is the first to propose such an optimized model for a low-power embedded system with increased detection accuracy. Full article

(This article belongs to the Special Issue MOCAST 2021)

► Show Figures

Figure 1

24 pages, 1663 KiB

Open AccessEditor’s ChoiceArticle

Sovereign Digital Consent through Privacy Impact Quantification and Dynamic Consent

by Arno Appenzeller, Marina Hornung, Thomas Kadow, Erik Krempel and Jürgen Beyerer

Technologies 2022, 10(1), 35; https://doi.org/10.3390/technologies10010035 - 21 Feb 2022

Cited by 7 | Viewed by 3921

Abstract

Digitization is becoming more and more important in the medical sector. Through electronic health records and the growing amount of digital data of patients available, big data research finds an increasing amount of use cases. The rising amount of data and the imposing [...] Read more.

Digitization is becoming more and more important in the medical sector. Through electronic health records and the growing amount of digital data of patients available, big data research finds an increasing amount of use cases. The rising amount of data and the imposing privacy risks can be overwhelming for patients, so they can have the feeling of being out of control of their data. Several previous studies on digital consent have tried to solve this problem and empower the patient. However, there are no complete solution for the arising questions yet. This paper presents the concept of Sovereign Digital Consent by the combination of a consent privacy impact quantification and a technology for proactive sovereign consent. The privacy impact quantification supports the patient to comprehend the potential risk when sharing the data and considers the personal preferences regarding acceptance for a research project. The proactive dynamic consent implementation provides an implementation for fine granular digital consent, using medical data categorization terminology. This gives patients the ability to control their consent decisions dynamically and is research friendly through the automatic enforcement of the patients’ consent decision. Both technologies are evaluated and implemented in a prototypical application. With the combination of those technologies, a promising step towards patient empowerment through Sovereign Digital Consent can be made. Full article

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

► Show Figures

Figure 1

15 pages, 7368 KiB

Open AccessEditor’s ChoiceArticle

Self-Supervised Human Activity Representation for Embodied Cognition Assessment

by Mohammad Zaki Zadeh, Ashwin Ramesh Babu, Ashish Jaiswal and Fillia Makedon

Technologies 2022, 10(1), 33; https://doi.org/10.3390/technologies10010033 - 17 Feb 2022

Cited by 6 | Viewed by 3534

Abstract

Physical activities, according to the embodied cognition theory, are an important manifestation of cognitive functions. As a result, in this paper, the Activate Test of Embodied Cognition (ATEC) system is proposed to assess various cognitive measures. It consists of physical exercises with different [...] Read more.

Physical activities, according to the embodied cognition theory, are an important manifestation of cognitive functions. As a result, in this paper, the Activate Test of Embodied Cognition (ATEC) system is proposed to assess various cognitive measures. It consists of physical exercises with different variations and difficulty levels designed to provide assessment of executive and motor functions. This work focuses on obtaining human activity representation from recorded videos of ATEC tasks in order to automatically assess embodied cognition performance. A self-supervised approach is employed in this work that can exploit a small set of annotated data to obtain an effective human activity representation. The performance of different self-supervised approaches along with a supervised method are investigated for automated cognitive assessment of children performing ATEC tasks. The results show that the supervised learning approach performance decreases as the training set becomes smaller, whereas the self-supervised methods maintain their performance by taking advantage of unlabeled data. Full article

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

► Show Figures

Figure 1

18 pages, 1305 KiB

Open AccessEditor’s ChoiceArticle

Visible Light Communications for Internet of Things: Prospects and Approaches, Challenges, Solutions and Future Directions

by Stephen S. Oyewobi, Karim Djouani and Anish Matthew Kurien

Technologies 2022, 10(1), 28; https://doi.org/10.3390/technologies10010028 - 5 Feb 2022

Cited by 76 | Viewed by 9236

Abstract

Visible light communications (VLC) is an emerging and promising concept that is capable of solving the major challenges of 5G and Internet of Things (IoT) communication systems. Moreover, due to the usage of light-emitting diodes (LEDs) in almost every aspect of our daily [...] Read more.

Visible light communications (VLC) is an emerging and promising concept that is capable of solving the major challenges of 5G and Internet of Things (IoT) communication systems. Moreover, due to the usage of light-emitting diodes (LEDs) in almost every aspect of our daily life VLC is providing massive connectivity for various types of massive IoT communications ranging from machine-to-machine, vehicle-to-infrastructure, infrastructure-to-vehicle, chip-to-chip as well as device-to-device. In this paper, we undertake a comprehensive review of the prospects of implementing VLC for IoT. Moreover, we investigate existing and proposed approaches implemented in the application of VLC for IoT. Additionally, we look at the challenges faced in applying VLC for IoT and offer solutions where applicable. Then, we identify future research directions in the implementation of VLC for IoT. Full article

► Show Figures

Figure 1

18 pages, 5237 KiB

Open AccessEditor’s ChoiceArticle

Reliable IoT-Based Monitoring and Control of Hydroponic Systems

by Konstantinos Tatas, Ahmad Al-Zoubi, Nicholas Christofides, Chrysostomos Zannettis, Michael Chrysostomou, Stavros Panteli and Anthony Antoniou

Technologies 2022, 10(1), 26; https://doi.org/10.3390/technologies10010026 - 2 Feb 2022

Cited by 50 | Viewed by 18829

Abstract

This paper presents the design and implementation of iPONICS: an intelligent, low-cost IoT-based control and monitoring system for hydroponics greenhouses. The system is based on three types of sensor nodes. The main (master) node is responsible for controlling the pump, monitoring the quality [...] Read more.

This paper presents the design and implementation of iPONICS: an intelligent, low-cost IoT-based control and monitoring system for hydroponics greenhouses. The system is based on three types of sensor nodes. The main (master) node is responsible for controlling the pump, monitoring the quality of the water in the greenhouse and aggregating and transmitting the data from the slave nodes. Environment sensing slave nodes monitor the ambient conditions in the greenhouse and transmit the data to the main node. Security nodes monitor activity (movement in the area). The system monitors water quality and greenhouse temperature and humidity, ensuring that crops grow under optimal conditions according to hydroponics guidelines. Remote monitoring for the greenhouse keepers is facilitated by monitoring these parameters via connecting to a website. An innovative fuzzy inference engine determines the plant irrigation duration. The system is optimized for low power consumption in order to facilitate off-grid operation. Preliminary reliability analysis indicates that the system can tolerate various transient faults without requiring intervention. Full article

(This article belongs to the Special Issue MOCAST 2021)

► Show Figures

Figure 1

16 pages, 2472 KiB

Open AccessEditor’s ChoiceArticle

Performance Analysis of 2D and 3D Bufferless NoCs Using Markov Chain Models

by Konstantinos Tatas

Technologies 2022, 10(1), 27; https://doi.org/10.3390/technologies10010027 - 2 Feb 2022

Cited by 1 | Viewed by 2825

Abstract

Performance analysis and design space exploration of bufferless Networks-on-Chip is done mainly through time-consuming cycle-accurate simulation, due to the chaotic nature of packet deflections, which have thus far prevented the development of an accurate analytical model. In order to raise the level of [...] Read more.

Performance analysis and design space exploration of bufferless Networks-on-Chip is done mainly through time-consuming cycle-accurate simulation, due to the chaotic nature of packet deflections, which have thus far prevented the development of an accurate analytical model. In order to raise the level of abstraction as well as capture the inherently probabilistic behavior of deflection routing, this paper presents a methodology for employing Markov chain models in the analysis of the behavior of bufferless Networks-on-Chip. A formal way of describing a bufferless NoC topology as a set of discrete-time Markov chains is presented. It is demonstrated that by combining this description with the network average distance, it is possible to obtain the expectation of the number of hops between any pair of nodes in the network as a function of the flit deflection probability. Comparisons between the proposed model and cycle-accurate simulation demonstrate the accuracy achieved by the model, with negligible computational cost. The useful range of the proposed model is quantified, demonstrating that it has an error of less than 10% for a significant proportion (between 33 and 75%) of the injection rate range below saturation. Finally, a simple equation for comparing mesh topologies with a “back-of-the-envelope” calculation is introduced. Full article

(This article belongs to the Special Issue MOCAST 2021)

► Show Figures

Figure 1

17 pages, 2806 KiB

Open AccessEditor’s ChoiceArticle

User-Centric Design Methodology for mHealth Apps: The PainApp Paradigm for Chronic Pain

by Yiannis Koumpouros

Technologies 2022, 10(1), 25; https://doi.org/10.3390/technologies10010025 - 31 Jan 2022

Cited by 15 | Viewed by 6378

Abstract

The paper presents a user-centric methodology in order to design successful mobile health (mHealth) applications. In addition to the theoretical background, such an example is presented with an application targeting chronic pain. The pain domain was decided due to its significance in many [...] Read more.

The paper presents a user-centric methodology in order to design successful mobile health (mHealth) applications. In addition to the theoretical background, such an example is presented with an application targeting chronic pain. The pain domain was decided due to its significance in many aspects: its complexity, dispersion in the population, the financial burden it causes, etc. The paper presents a step-by-step plan in order to build mobile health applications. Participatory design and interdisciplinarity are only some of the critical issues towards the desired result. In the given example (development of the PainApp), a participatory design was followed with a team of seventeen stakeholders that drove the design and development phases. Three physicians, one behavioral scientist, three IT and UX experts, and ten patients collaborated together to develop the final solution. The several features implemented in the PainApp solution are presented in details. The application is threefold: it supports the management, reporting, and treatment effectiveness monitoring. The paper is giving details on the methodological approach while presenting insights on the actual plan and the steps followed for having a patient-centric solution. Key success factors and barriers to mobile health applications that support the need for such an approach are also presented. Full article

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

► Show Figures

Figure 1

10 pages, 1457 KiB

Open AccessEditor’s ChoiceArticle

Results of Preliminary Studies on the Perception of the Relationships between Objects Presented in a Cartesian Space

by Ira Woodring and Charles Owen

Technologies 2022, 10(1), 20; https://doi.org/10.3390/technologies10010020 - 30 Jan 2022

Viewed by 2428

Abstract

Visualizations often use the paradigm of a Cartesian space for the presentation of objects and information. Unified Modeling Language (UML) is a visual language used to describe relationships in processes and systems and is heavily used in computer science and software engineering. Visualizations [...] Read more.

Visualizations often use the paradigm of a Cartesian space for the presentation of objects and information. Unified Modeling Language (UML) is a visual language used to describe relationships in processes and systems and is heavily used in computer science and software engineering. Visualizations are a powerful development tool, but are not necessarily accessible to all users, as individuals may differ in their level of visual ability or perceptual biases. Sonfication methods can be used to supplement or, in some cases, replace visual models. This paper describes two studies created to determine the ability of users to perceive relationships between objects in a Cartesian space when presented in a sonified form. Results from this study will be used to guide the creation of sonified UML software. Full article

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

► Show Figures

Figure 1

14 pages, 2847 KiB

Open AccessEditor’s ChoiceArticle

On the Exploration of Automatic Building Extraction from RGB Satellite Images Using Deep Learning Architectures Based on U-Net

by Anastasios Temenos, Nikos Temenos, Anastasios Doulamis and Nikolaos Doulamis

Technologies 2022, 10(1), 19; https://doi.org/10.3390/technologies10010019 - 29 Jan 2022

Cited by 17 | Viewed by 4612

Abstract

Detecting and localizing buildings is of primary importance in urban planning tasks. Automating the building extraction process, however, has become attractive given the dominance of Convolutional Neural Networks (CNNs) in image classification tasks. In this work, we explore the effectiveness of the CNN-based [...] Read more.

Detecting and localizing buildings is of primary importance in urban planning tasks. Automating the building extraction process, however, has become attractive given the dominance of Convolutional Neural Networks (CNNs) in image classification tasks. In this work, we explore the effectiveness of the CNN-based architecture U-Net and its variations, namely, the Residual U-Net, the Attention U-Net, and the Attention Residual U-Net, in automatic building extraction. We showcase their robustness in feature extraction and information processing using exclusively RGB images, as they are a low-cost alternative to multi-spectral and LiDAR ones, selected from the SpaceNet 1 dataset. The experimental results show that U-Net achieves a

91.9 %

accuracy, whereas introducing residual blocks, attention gates, or a combination of both improves the accuracy of the vanilla U-Net to

93.6 %

,

94.0 %

, and

93.7 %

, respectively. Finally, the comparison between U-Net architectures and typical deep learning approaches from the literature highlights their increased performance in accurate building localization around corners and edges. Full article

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

► Show Figures

Figure 1

18 pages, 1780 KiB

Open AccessEditor’s ChoiceArticle

Stacking-Based Ensemble Learning Method for Multi-Spectral Image Classification

by Tagel Aboneh, Abebe Rorissa and Ramasamy Srinivasagan

Technologies 2022, 10(1), 17; https://doi.org/10.3390/technologies10010017 - 26 Jan 2022

Cited by 33 | Viewed by 6338

Abstract

Higher dimensionality, Hughes phenomenon, spatial resolution of image data, and presence of mixed pixels are the main challenges in a multi-spectral image classification process. Most of the classical machine learning algorithms suffer from scoring optimal classification performance over multi-spectral image data. In this [...] Read more.

Higher dimensionality, Hughes phenomenon, spatial resolution of image data, and presence of mixed pixels are the main challenges in a multi-spectral image classification process. Most of the classical machine learning algorithms suffer from scoring optimal classification performance over multi-spectral image data. In this study, we propose stack-based ensemble-based learning approach to optimize image classification performance. In addition, we integrate the proposed ensemble learning with XGBoost method to further improve its classification accuracy. To conduct the experiment, the Landsat image data has been acquired from Bishoftu town located in the Oromia region of Ethiopia. The current study’s main objective was to assess the performance of land cover and land use analysis using multi-spectral image data. Results from our experiment indicate that, the proposed ensemble learning method outperforms any strong base classifiers with 99.96% classification performance accuracy. Full article

(This article belongs to the Special Issue Multimedia Indexing and Retrieval)

► Show Figures

Figure 1

23 pages, 5508 KiB

Open AccessEditor’s ChoiceArticle

Novel Benes Network Routing Algorithm and Hardware Implementation

by Dimitris Nikolaidis, Panos Groumas, Christos Kouloumentas and Hercules Avramopoulos

Technologies 2022, 10(1), 16; https://doi.org/10.3390/technologies10010016 - 25 Jan 2022

Cited by 7 | Viewed by 8131

Abstract

Benes/Clos networks constitute a particularly important part of interconnection networks and have been used in numerous areas, such as multi-processor systems, data centers and on-chip networks. They have also attracted great interest in the field of optical communications due to the increasing popularity [...] Read more.

Benes/Clos networks constitute a particularly important part of interconnection networks and have been used in numerous areas, such as multi-processor systems, data centers and on-chip networks. They have also attracted great interest in the field of optical communications due to the increasing popularity of optical switches based on these architectures. There are numerous algorithms aimed at routing these types of networks, with varying degrees of utility. Linear algorithms, such as Sun Tsu and Opferman, were historically the first attempt to standardize the routing procedure of this types of networks. They require matrix-based calculations, which are very demanding in terms of resources and in some cases involve backtracking, which impairs their efficiency. Parallel solutions, such as Lee’s algorithm, were introduced later and provide a different answer that satisfy the requirements of high-performance networks. They are, however, extremely complex and demand even more resources. In both cases, hardware implementations reflect their algorithmic characteristics. In this paper, we attempt to design an algorithm that is simple enough to be implemented on a small field programmable gate array board while simultaneously efficient enough to be used in practical scenarios. The design itself is of a generic nature; therefore, its behavior across different sizes (8 × 8, 16 × 16, 32 × 32, 64 × 64) is examined. The platform of implementation is a medium range FPGA specifically selected to represent the average hardware prototyping device. In the end, an overview of the algorithm’s imprint on the device is presented alongside other approaches, which include both hard and soft computing techniques. Full article

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

► Show Figures

Figure 1

12 pages, 1985 KiB

Open AccessEditor’s ChoiceArticle

IoT Framework for Measurement and Precision Agriculture: Predicting the Crop Using Machine Learning Algorithms

by Kalaiselvi Bakthavatchalam, Balaguru Karthik, Vijayan Thiruvengadam, Sriram Muthal, Deepa Jose, Ketan Kotecha and Vijayakumar Varadarajan

Technologies 2022, 10(1), 13; https://doi.org/10.3390/technologies10010013 - 20 Jan 2022

Cited by 90 | Viewed by 11551

Abstract

IoT architectures facilitate us to generate data for large and remote agriculture areas and the same can be utilized for Crop predictions using this machine learning algorithm. Recommendations are based on the following N, P, K, pH, Temperature, Humidity, and Rainfall these attributes [...] Read more.

IoT architectures facilitate us to generate data for large and remote agriculture areas and the same can be utilized for Crop predictions using this machine learning algorithm. Recommendations are based on the following N, P, K, pH, Temperature, Humidity, and Rainfall these attributes decide the crop to be recommended. The data set has 2200 instances and 8 attributes. Nearly 22 different crops are recommended for a different combination of 8 attributes. Using the supervised learning method, the optimum model is attained using selected machine learning algorithms in WEKA. The Machine learning algorithm selected for classifying is multilayer perceptron rules-based classifier JRip, and decision table classifier. The main objective of this case study is to end up with a model which predicts the high yield crop and precision agriculture. The proposed system modeling incorporates the trending technology, IoT, and Agriculture needy measurements. The performance assessed by the selected classifiers is 98.2273%, the Weighted average Receiver Operator Characteristics is 1 with the maximum time taken to build the model being 8.05 s. Full article

► Show Figures

Figure 1

15 pages, 782 KiB

Open AccessEditor’s ChoiceArticle

Efficient Stochastic Computing FIR Filtering Using Sigma-Delta Modulated Signals

by Nikos Temenos, Anastasis Vlachos and Paul P. Sotiriadis

Technologies 2022, 10(1), 14; https://doi.org/10.3390/technologies10010014 - 20 Jan 2022

Cited by 7 | Viewed by 3125

Abstract

This work presents a soft-filtering digital signal processing architecture based on sigma-delta modulators and stochastic computing. A sigma-delta modulator converts the input high-resolution signal to a single-bit stream enabling filtering structures to be realized using stochastic computing’s negligible-area multipliers. Simulation in the spectral [...] Read more.

This work presents a soft-filtering digital signal processing architecture based on sigma-delta modulators and stochastic computing. A sigma-delta modulator converts the input high-resolution signal to a single-bit stream enabling filtering structures to be realized using stochastic computing’s negligible-area multipliers. Simulation in the spectral domain demonstrates the filter’s proper operation and its roll-off behavior, as well as the signal-to-noise ratio improvement using the sigma-delta modulator, compared to typical stochastic computing filter realizations. The proposed architecture’s hardware advantages are showcased with synthesis results for two FIR filters using FPGA and synopsys tools, while comparisons with standard stochastic computing-based hardware realizations, as well as with conventional binary ones, demonstrate its efficacy. Full article

(This article belongs to the Special Issue MOCAST 2021)

► Show Figures

Figure 1

17 pages, 4039 KiB

Open AccessEditor’s ChoiceArticle

Assistive Technologies for Supporting the Wellbeing of Older Adults

by Ioanna Dratsiou, Annita Varella, Evangelia Romanopoulou, Oscar Villacañas, Sara Cooper, Pavlos Isaris, Manex Serras, Luis Unzueta, Tatiana Silva, Alexia Zurkuhlen, Malcolm MacLachlan and Panagiotis D. Bamidis

Technologies 2022, 10(1), 8; https://doi.org/10.3390/technologies10010008 - 14 Jan 2022

Cited by 12 | Viewed by 6069

Abstract

As people age, they are more likely to develop multiple chronic diseases and experience a decline in some of their physical and cognitive functions, leading to the decrease in their ability to live independently. Innovative technology-based interventions tailored to older adults’ functional levels [...] Read more.

As people age, they are more likely to develop multiple chronic diseases and experience a decline in some of their physical and cognitive functions, leading to the decrease in their ability to live independently. Innovative technology-based interventions tailored to older adults’ functional levels and focused on healthy lifestyles are considered imperative. This work proposed a framework of active and healthy ageing through the integration of a broad spectrum of digital solutions into an open Pan-European technological platform in the context of the SHAPES project, an EU-funded innovation action. In conclusion, the SHAPES project can potentially engage older adults in a holistic technological ecosystem and, therefore, facilitate the maintenance of a high-quality standard of life. Full article

(This article belongs to the Section Assistive Technologies)

► Show Figures

Figure 1

10 pages, 4927 KiB

Open AccessEditor’s ChoiceArticle

A Simulated Environment for Robot Vision Experiments

by Christos Sevastopoulos, Stasinos Konstantopoulos, Keshav Balaji, Mohammad Zaki Zadeh and Fillia Makedon

Technologies 2022, 10(1), 7; https://doi.org/10.3390/technologies10010007 - 12 Jan 2022

Cited by 6 | Viewed by 3449

Abstract

Training on simulation data has proven invaluable in applying machine learning in robotics. However, when looking at robot vision in particular, simulated images cannot be directly used no matter how realistic the image rendering is, as many physical parameters (temperature, humidity, wear-and-tear in [...] Read more.

Training on simulation data has proven invaluable in applying machine learning in robotics. However, when looking at robot vision in particular, simulated images cannot be directly used no matter how realistic the image rendering is, as many physical parameters (temperature, humidity, wear-and-tear in time) vary and affect texture and lighting in ways that cannot be encoded in the simulation. In this article we propose a different approach for extracting value from simulated environments: although neither of the trained models can be used nor are any evaluation scores expected to be the same on simulated and physical data, the conclusions drawn from simulated experiments might be valid. If this is the case, then simulated environments can be used in early-stage experimentation with different network architectures and features. This will expedite the early development phase before moving to (harder to conduct) physical experiments in order to evaluate the most promising approaches. In order to test this idea we created two simulated environments for the Unity engine, acquired simulated visual datasets, and used them to reproduce experiments originally carried out in a physical environment. The comparison of the conclusions drawn in the physical and the simulated experiments is promising regarding the validity of our approach. Full article

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

► Show Figures

Figure 1

11 pages, 2094 KiB

Open AccessEditor’s ChoiceArticle

Traffic Flow Prediction for Smart Traffic Lights Using Machine Learning Algorithms

by Alfonso Navarro-Espinoza, Oscar Roberto López-Bonilla, Enrique Efrén García-Guerrero, Esteban Tlelo-Cuautle, Didier López-Mancilla, Carlos Hernández-Mejía and Everardo Inzunza-González

Technologies 2022, 10(1), 5; https://doi.org/10.3390/technologies10010005 - 10 Jan 2022

Cited by 89 | Viewed by 24666

Abstract

Nowadays, many cities have problems with traffic congestion at certain peak hours, which produces more pollution, noise and stress for citizens. Neural networks (NN) and machine-learning (ML) approaches are increasingly used to solve real-world problems, overcoming analytical and statistical methods, due to their [...] Read more.

Nowadays, many cities have problems with traffic congestion at certain peak hours, which produces more pollution, noise and stress for citizens. Neural networks (NN) and machine-learning (ML) approaches are increasingly used to solve real-world problems, overcoming analytical and statistical methods, due to their ability to deal with dynamic behavior over time and with a large number of parameters in massive data. In this paper, machine-learning (ML) and deep-learning (DL) algorithms are proposed for predicting traffic flow at an intersection, thus laying the groundwork for adaptive traffic control, either by remote control of traffic lights or by applying an algorithm that adjusts the timing according to the predicted flow. Therefore, this work only focuses on traffic flow prediction. Two public datasets are used to train, validate and test the proposed ML and DL models. The first one contains the number of vehicles sampled every five minutes at six intersections for 56 days using different sensors. For this research, four of the six intersections are used to train the ML and DL models. The Multilayer Perceptron Neural Network (MLP-NN) obtained better results (R-Squared and EV score of 0.93) and took less training time, followed closely by Gradient Boosting then Recurrent Neural Networks (RNNs), with good metrics results but the longer training time, and finally Random Forest, Linear Regression and Stochastic Gradient. All ML and DL algorithms scored good performance metrics, indicating that they are feasible for implementation on smart traffic light controllers. Full article

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

► Show Figures

Figure 1

16 pages, 2920 KiB

Open AccessEditor’s ChoiceArticle

A Simplified Tantalum Oxide Memristor Model, Parameters Estimation and Application in Memory Crossbars

by Valeri Mladenov and Stoyan Kirilov

Technologies 2022, 10(1), 6; https://doi.org/10.3390/technologies10010006 - 10 Jan 2022

Cited by 6 | Viewed by 4132

Abstract

In this paper, an improved and simplified modification of a tantalum oxide memristor model is presented. The proposed model is applied and analyzed in hybrid and passive memory crossbars in LTSPICE environment and is based on the standard Ta₂O₅ memristor [...] Read more.

In this paper, an improved and simplified modification of a tantalum oxide memristor model is presented. The proposed model is applied and analyzed in hybrid and passive memory crossbars in LTSPICE environment and is based on the standard Ta₂O₅ memristor model proposed by Hewlett–Packard. The discussed modified model has several main enhancements—inclusion of a simplified window function, improvement of its effectiveness by the use of a simple expression for the i–v relationship, and replacement of the classical Heaviside step function with a differentiable and flat step-like function. The optimal values of coefficients of the tantalum oxide memristor model are derived by comparison of experimental current–voltage relationships and by using a procedure for parameter estimation. A simplified LTSPICE library model, correspondent to the analyzed tantalum oxide memristor, is created in accordance with the considered mathematical model. The improved and altered Ta₂O₅ memristor model is tested and simulated in hybrid and passive memory crossbars for a state near to a hard-switching operation. After a comparison of several of the best existing memristor models, the main pros of the proposed memristor model are highlighted—its improved implementation, better operating rate, and good switching properties. Full article

(This article belongs to the Special Issue MOCAST 2021)

► Show Figures

Figure 1

12 pages, 944 KiB

Open AccessEditor’s ChoiceArticle

Artwork Style Recognition Using Vision Transformers and MLP Mixer

by Lazaros Alexios Iliadis, Spyridon Nikolaidis, Panagiotis Sarigiannidis, Shaohua Wan and Sotirios K. Goudos

Technologies 2022, 10(1), 2; https://doi.org/10.3390/technologies10010002 - 28 Dec 2021

Cited by 8 | Viewed by 4589

Abstract

Through the extensive study of transformers, attention mechanisms have emerged as potentially more powerful than sequential recurrent processing and convolution. In this realm, Vision Transformers have gained much research interest, since their architecture changes the dominant paradigm in Computer Vision. An interesting and [...] Read more.

Through the extensive study of transformers, attention mechanisms have emerged as potentially more powerful than sequential recurrent processing and convolution. In this realm, Vision Transformers have gained much research interest, since their architecture changes the dominant paradigm in Computer Vision. An interesting and difficult task in this field is the classification of artwork styles, since the artistic style of a painting is a descriptor that captures rich information about the painting. In this paper, two different Deep Learning architectures—Vision Transformer and MLP Mixer (Multi-layer Perceptron Mixer)—are trained from scratch in the task of artwork style recognition, achieving over 39% prediction accuracy for 21 style classes on the WikiArt paintings dataset. In addition, a comparative study between the most common optimizers was conducted obtaining useful information for future studies. Full article

(This article belongs to the Special Issue MOCAST 2021)

► Show Figures

Figure 1

10 pages, 2049 KiB

Open AccessEditor’s ChoiceArticle

Encoding Two-Qubit Logical States and Quantum Operations Using the Energy States of a Physical System

by Dimitrios Ntalaperas and Nikos Konofaos

Technologies 2022, 10(1), 1; https://doi.org/10.3390/technologies10010001 - 22 Dec 2021

Cited by 7 | Viewed by 3606

Abstract

In this paper, we introduce a novel coding scheme, which allows single quantum systems to encode multi-qubit registers. This allows for more efficient use of resources and the economy in designing quantum systems. The scheme is based on the notion of encoding logical [...] Read more.

In this paper, we introduce a novel coding scheme, which allows single quantum systems to encode multi-qubit registers. This allows for more efficient use of resources and the economy in designing quantum systems. The scheme is based on the notion of encoding logical quantum states using the charge degree of freedom of the discrete energy spectrum that is formed by introducing impurities in a semiconductor material. We propose a mechanism of performing single qubit operations and controlled two-qubit operations, providing a mechanism for achieving these operations using appropriate pulses generated by Rabi oscillations. The above architecture is simulated using the Armonk single qubit quantum computer of IBM to encode two logical quantum states into the energy states of Armonk’s qubit and using custom pulses to perform one and two-qubit quantum operations. Full article

(This article belongs to the Special Issue MOCAST 2021)

► Show Figures

Figure 1

17 pages, 4910 KiB

Open AccessEditor’s ChoiceArticle

Efficient Sandstorm Image Enhancement Using the Normalized Eigenvalue and Adaptive Dark Channel Prior

by Ho Sang Lee

Technologies 2021, 9(4), 101; https://doi.org/10.3390/technologies9040101 - 17 Dec 2021

Cited by 7 | Viewed by 2604

Abstract

A sandstorm image has features similar to those of a hazy image with regard to the obtaining process. However, the difference between a sand dust image and a hazy image is the color channel balance. In general, a hazy image has no color [...] Read more.

A sandstorm image has features similar to those of a hazy image with regard to the obtaining process. However, the difference between a sand dust image and a hazy image is the color channel balance. In general, a hazy image has no color cast and has a balanced color channel with fog and dust. However, a sand dust image has a yellowish or reddish color cast due to sand particles, which cause the color channels to degrade. When the sand dust image is enhanced without color channel compensation, the improved image also has a new color cast. Therefore, to enhance the sandstorm image naturally without a color cast, the color channel compensation step is needed. Thus, to balance the degraded color channel, this paper proposes the color balance method using each color channel’s eigenvalue. The eigenvalue reflects the image’s features. The degraded image and the undegraded image have different eigenvalues on each color channel. Therefore, if using the eigenvalue of each color channel, the degraded image can be improved naturally and balanced. Due to the color-balanced image having the same features as the hazy image, this work, to improve the hazy image, uses dehazing methods such as the dark channel prior (DCP) method. However, because the ordinary DCP method has weak points, this work proposes a compensated dark channel prior and names it the adaptive DCP (ADCP) method. The proposed method is objectively and subjectively superior to existing methods when applied to various images. Full article

► Show Figures

Figure 1

11 pages, 1148 KiB

Open AccessEditor’s ChoiceArticle

Functional Model of a Self-Driving Car Control System

by Kirill Sviatov, Nadejda Yarushkina, Daniil Kanin, Ivan Rubtcov, Roman Jitkov, Vladislav Mikhailov and Pavel Kanin

Technologies 2021, 9(4), 100; https://doi.org/10.3390/technologies9040100 - 10 Dec 2021

Cited by 6 | Viewed by 5123

Abstract

The article describes a structural and functional model of a self-driving car control system, which generates a wide class of mathematical problems. Currently, control systems for self-driving cars are considered at several levels of abstraction and implementation: Mechanics, electronics, perception, scene recognition, control, [...] Read more.

The article describes a structural and functional model of a self-driving car control system, which generates a wide class of mathematical problems. Currently, control systems for self-driving cars are considered at several levels of abstraction and implementation: Mechanics, electronics, perception, scene recognition, control, security, integration of all subsystems into a solid system. Modern research often considers particular problems to be solved for each of the levels separately. In this paper, a parameterized model of the integration of individual components into a complex control system for a self-driving car is considered. Such a model simplifies the design and development of self-driving control systems with configurable automation tools, taking into account the specifics of the solving problem. The parameterized model can be used for CAD design in the field of self-driving car development. A full cycle of development of a control system for a self-driving truck was implemented, which was rub in the “Robocross 2021” competition. The software solution was tested on more than 40 launches of a self-driving truck. Parameterization made it possible to speed up the development of the control system, expressed in man-hours, by 1.5 times compared to the experience of the authors of the article who participated in the same competition in 2018 and 2019. The proposed parameterization was used in the development of individual CAD elements described in this article. Additionally, the implementation of specific modules and functions is a field for experimental research. Full article

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

► Show Figures

Figure 1

20 pages, 7877 KiB

Open AccessEditor’s ChoiceArticle

On the Part Quality, Process Parameters and In-Die Pressures in Indirect Squeeze Casting

by Anders E. W. Jarfors, Jie Zhou, Andong Du, Jinchuan Zheng and Gegang Yu

Technologies 2021, 9(4), 95; https://doi.org/10.3390/technologies9040095 - 2 Dec 2021

Cited by 2 | Viewed by 2898

Abstract

Squeeze casting is a process that can produce the highest quality castings. In the current study, the effect of the process settings and the in-die conditions on rejection rates is studied through a full-scale experimental study. Factors affecting the as-cast part quality were [...] Read more.

Squeeze casting is a process that can produce the highest quality castings. In the current study, the effect of the process settings and the in-die conditions on rejection rates is studied through a full-scale experimental study. Factors affecting the as-cast part quality were investigated in the current study from two different viewpoints. The first part of the study was to investigate the influence of the process settings on the part rejection rate, and the second was to understand the conditions in the die and the effects on the part rejection rate to understand better the reasons and sensitivity of the squeeze casting process. Full article

(This article belongs to the Section Manufacturing Technology)

► Show Figures

Figure 1

15 pages, 29424 KiB

Open AccessEditor’s ChoiceArticle

A Deep Learning-Based Dirt Detection Computer Vision System for Floor-Cleaning Robots with Improved Data Collection

by Daniel Canedo, Pedro Fonseca, Petia Georgieva and António J. R. Neves

Technologies 2021, 9(4), 94; https://doi.org/10.3390/technologies9040094 - 1 Dec 2021

Cited by 13 | Viewed by 10842

Abstract

Floor-cleaning robots are becoming increasingly more sophisticated over time and with the addition of digital cameras supported by a robust vision system they become more autonomous, both in terms of their navigation skills but also in their capabilities of analyzing the surrounding environment. [...] Read more.

Floor-cleaning robots are becoming increasingly more sophisticated over time and with the addition of digital cameras supported by a robust vision system they become more autonomous, both in terms of their navigation skills but also in their capabilities of analyzing the surrounding environment. This document proposes a vision system based on the YOLOv5 framework for detecting dirty spots on the floor. The purpose of such a vision system is to save energy and resources, since the cleaning system of the robot will be activated only when a dirty spot is detected and the quantity of resources will vary according to the dirty area. In this context, false positives are highly undesirable. On the other hand, false negatives will lead to a poor cleaning performance of the robot. For this reason, a synthetic data generator found in the literature was improved and adapted for this work to tackle the lack of real data in this area. This synthetic data generator allows for large datasets with numerous samples of floors and dirty spots. A novel approach in selecting floor images for the training dataset is proposed. In this approach, the floor is segmented from other objects in the image such that dirty spots are only generated on the floor and do not overlap those objects. This helps the models to distinguish between dirty spots and objects in the image, which reduces the number of false positives. Furthermore, a relevant dataset of the Automation and Control Institute (ACIN) was found to be partially labelled. Consequently, this dataset was annotated from scratch, tripling the number of labelled images and correcting some poor annotations from the original labels. Finally, this document shows the process of generating synthetic data which is used for training YOLOv5 models. These models were tested on a real dataset (ACIN) and the best model attained a mean average precision (mAP) of 0.874 for detecting solid dirt. These results further prove that our proposal is able to use synthetic data for the training step and effectively detect dirt on real data. According to our knowledge, there are no previous works reporting the use of YOLOv5 models in this application. Full article

(This article belongs to the Special Issue Smart Systems (SmaSys2021))

► Show Figures

Graphical abstract

17 pages, 511 KiB

Open AccessEditor’s ChoiceArticle

Incremental Lagrangian Relaxation Based Discrete Gate Sizing and Threshold Voltage Assignment

by Dimitrios Mangiras and Giorgos Dimitrakopoulos

Technologies 2021, 9(4), 92; https://doi.org/10.3390/technologies9040092 - 26 Nov 2021

Cited by 2 | Viewed by 3004

Abstract

Timing closure remains one of the most critical challenges of a physical synthesis flow, especially when the design operates under multiple operating conditions. Even if timing is almost closed at the end of the flow, last-mile placement and routing congestion optimizations may introduce [...] Read more.

Timing closure remains one of the most critical challenges of a physical synthesis flow, especially when the design operates under multiple operating conditions. Even if timing is almost closed at the end of the flow, last-mile placement and routing congestion optimizations may introduce new timing violations. Correcting such violations needs minimally disruptive techniques such as threshold voltage reassignment and gate sizing that affect only marginally the placement and routing of the almost finalized design. To this end, we transform a powerful Lagrangian-relaxation-based optimizer, used for global timing optimization early in the design flow, into a practical incremental timing optimizer that corrects small timing violations with fast runtime and without increasing the area/power of the design. The proposed approach was applied to already optimized designs of the ISPD 2013 benchmarks assuming that they experience new timing violations due to local wire rerouting. Experimental results show that in single corner designs, timing is improved by more than 36% on average, using 45% less runtime. Correspondingly, in a multicorner context, timing is improved by 39% when compared to the fully-fledged version of the timing optimizer. Full article

(This article belongs to the Special Issue MOCAST 2021)

► Show Figures

Figure 1

17 pages, 5585 KiB

Open AccessEditor’s ChoiceArticle

An Interactive Task Conditioning System Featuring Personal Comfort Models and Non-Intrusive Sensing Techniques: A Field Study in Shanghai

by Siliang Lu and Erica Cochran Hameen

Technologies 2021, 9(4), 90; https://doi.org/10.3390/technologies9040090 - 21 Nov 2021

Cited by 4 | Viewed by 3043

Abstract

Heating, ventilation and air-conditioning (HVAC) systems play a key role in shaping office environments. However, open-plan office buildings nowadays are also faced with problems like unnecessary energy waste and an unsatisfactory shared indoor thermal environment. Therefore, it is significant to develop a new [...] Read more.

Heating, ventilation and air-conditioning (HVAC) systems play a key role in shaping office environments. However, open-plan office buildings nowadays are also faced with problems like unnecessary energy waste and an unsatisfactory shared indoor thermal environment. Therefore, it is significant to develop a new paradigm of an HVAC system framework so that everyone could work under their preferred thermal environment and the system can achieve higher energy efficiency such as task ambient conditioning system (TAC). However, current task conditioning systems are not responsive to personal thermal comfort dynamically. Hence, this research aims to develop a dynamic task conditioning system featuring personal thermal comfort models with machine learning and the wireless non-intrusive sensing system. In order to evaluate the proposed task conditioning system performance, a field study was conducted in a shared office space in Shanghai from July to August. As a result, personal thermal comfort models with indoor air temperature, relative humidity and cheek (side face) skin temperature have better performances than baseline models with indoor air temperature only. Moreover, compared to personal thermal satisfaction predictions, 90% of subjects have better performances in thermal sensation predictions. Therefore, personal thermal comfort models could be further implemented into the task conditioning control of TAC systems. Full article

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

► Show Figures

Figure 1

14 pages, 3803 KiB

Open AccessEditor’s ChoiceArticle

Electrospun PVP/TiO₂ Nanofibers for Filtration and Possible Protection from Various Viruses like COVID-19

by Ankush Sharma, Dinesh Pathak, Deepak S. Patil, Naresh Dhiman, Viplove Bhullar and Aman Mahajan

Technologies 2021, 9(4), 89; https://doi.org/10.3390/technologies9040089 - 19 Nov 2021

Cited by 18 | Viewed by 5404

Abstract

In this study, TiO₂ nanofibers were prepared with Polyvinylpyrrolidone (PVP) polymer using sol-gel method via electrospinning technique. Owing to the advantages of small fiber diameter, tunable porosity, low cost, large surface to volume ratio, structure control, light-weight, and less energy consumption, electrospun [...] Read more.

In this study, TiO₂ nanofibers were prepared with Polyvinylpyrrolidone (PVP) polymer using sol-gel method via electrospinning technique. Owing to the advantages of small fiber diameter, tunable porosity, low cost, large surface to volume ratio, structure control, light-weight, and less energy consumption, electrospun nanofibers are evolving as an adaptable material with a number of applications, in this case for filtration and environmental/virus protection. Different samples of TiO₂/PVP nanofibers have been prepared by changing the parameters to achieve the best result. As the polymer concentration was increased from 6 to 8 wt.% of PVP, diameter of the resultant fibers was seen to be increased, implying decrease in the pore-size of the fibers up to 1.4 nm. Surface morphology has been checked via Scanning Electron Microscope (SEM) images. Crystalline nature has been analyzed by X-ray Crystallography. Using the Bruanauer-Emmett-Teller (BET) test, surface area and porosity has been checked for the suitable application. The synthesized TiO₂/PVP nanofibers have tremendous practical potentials in filtration and environmental remediation applications. Full article

(This article belongs to the Special Issue Glass, Glass-Ceramics, and Ceramics for Nuclear Waste Immobilization and Other Environmental Applications)

► Show Figures

Figure 1

13 pages, 290 KiB

Open AccessEditor’s ChoiceArticle

Smart Additive Manufacturing: The Path to the Digital Value Chain

by Nuno Araújo, Vânia Pacheco and Leonardo Costa

Technologies 2021, 9(4), 88; https://doi.org/10.3390/technologies9040088 - 17 Nov 2021

Cited by 21 | Viewed by 6719

Abstract

The aim of this article is to characterize the impacts of Smart Additive Manufacturing (SAM) on industrial production, digital supply chains (DSCs) and corresponding digital value chains (DVCs), logistics and inventory management. The method used consists of a critical review of the literature, [...] Read more.

The aim of this article is to characterize the impacts of Smart Additive Manufacturing (SAM) on industrial production, digital supply chains (DSCs) and corresponding digital value chains (DVCs), logistics and inventory management. The method used consists of a critical review of the literature, enriched by the authors’ field experience. The results show that digital transformation of manufacturing is affecting business models, from resource acquisition to the end user. Smart manufacturing is considered a successful improvement introduced by Industry 4.0. Additive Manufacturing (AM) plays a crucial role in this digital transformation, changing the way manufacturers think about the entire lifecycle of a product. SAM combines AM in a smart factory environment. SAM reduces the complexity of DSCs and contributes to a more flexible approach to logistics and inventory management. It has also spurred the growth and popularization of customized mass production as well as decentralized manufacturing, rapid prototyping, unprecedented flexibility in product design, production and delivery, and resource efficiency and sustainability. SAM technology impacts all five Fletcher’s stages in DVCs. However, the need for clear definitions and regulations on 3D printing of digital files and their reproduction, as well as product health, safety, and integrity issues, cannot be ignored. Furthermore, investment in this technology is still expensive and can be prohibitive for many companies, namely SMEs. Full article

(This article belongs to the Special Issue 3D Printing and Additive Manufacturing: Principles and Applications)

16 pages, 1360 KiB

Open AccessEditor’s ChoiceArticle

Visual Robotic Perception System with Incremental Learning for Child–Robot Interaction Scenarios

by Niki Efthymiou, Panagiotis Paraskevas Filntisis, Gerasimos Potamianos and Petros Maragos

Technologies 2021, 9(4), 86; https://doi.org/10.3390/technologies9040086 - 15 Nov 2021

Cited by 4 | Viewed by 3821

Abstract

This paper proposes a novel lightweight visual perception system with Incremental Learning (IL), tailored to child–robot interaction scenarios. Specifically, this encompasses both an action and emotion recognition module, with the former wrapped around an IL system, allowing novel actions to be easily added. [...] Read more.

This paper proposes a novel lightweight visual perception system with Incremental Learning (IL), tailored to child–robot interaction scenarios. Specifically, this encompasses both an action and emotion recognition module, with the former wrapped around an IL system, allowing novel actions to be easily added. This IL system enables the tutor aspiring to use robotic agents in interaction scenarios to further customize the system according to children’s needs. We perform extensive evaluations of the developed modules, achieving state-of-the-art results on both the children’s action BabyRobot dataset and the children’s emotion EmoReact dataset. Finally, we demonstrate the robustness and effectiveness of the IL system for action recognition by conducting a thorough experimental analysis for various conditions and parameters. Full article

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

► Show Figures

Figure 1

21 pages, 4793 KiB

Open AccessEditor’s ChoiceArticle

A Novel In Vitro Simulator to Investigate Promotion of Reconstruction of Damaged Neuronal Cell Colony Differentiated from iPS Cells with the Aid of Micro Dynamic Stimulation

by Tadashi Kosawada, Taku Kitsunai, Zhonggang Feng and Kaoru Goto

Technologies 2021, 9(4), 83; https://doi.org/10.3390/technologies9040083 - 4 Nov 2021

Viewed by 2866

Abstract

Neuronal cells are equipped with the function of a sensor that senses stimulation and elongates neurites to connect nearby neuronal cells in forming a neuronal network, as they are generally said to be hard to recover from physical damage, such as in the [...] Read more.

Neuronal cells are equipped with the function of a sensor that senses stimulation and elongates neurites to connect nearby neuronal cells in forming a neuronal network, as they are generally said to be hard to recover from physical damage, such as in the case of a spinal cord injury. Therefore, in this study, a novel in vitro simulator in which micro dynamic stimulations are applied to a damaged neuronal cell colony artificially is proposed to investigate the possibility of promoting the reconstruction of damaged neuronal cells on a colony basis. A neuronal cell colony differentiated from iPS cells is physically damaged by cutting off treatment, and micro dynamic stimulations are applied to the colony by utilizing a developed mini-vibration table system. NeuroFluor NeuO is used to establish a method for fluorescent staining of the living neuronal cells, and morphologies of the reconstructing neurons are analysed, revealing a relationship between the stimulation and the reconstructing process of the damaged neurons. It is found that significant differences are observed in the reconstructing efficiency between the statically cultured damaged neuronal cell colony and the dynamically stimulated one. The results suggest that applying appropriate micro dynamic stimulations is a promising approach to promote the reconstruction of a damaged neuronal cell colony. Full article

► Show Figures

Graphical abstract

22 pages, 501 KiB

Open AccessEditor’s ChoiceArticle

Multiclass Confusion Matrix Reduction Method and Its Application on Net Promoter Score Classification Problem

by Ioannis Markoulidakis, Ioannis Rallis, Ioannis Georgoulas, George Kopsiaftis, Anastasios Doulamis and Nikolaos Doulamis

Technologies 2021, 9(4), 81; https://doi.org/10.3390/technologies9040081 - 2 Nov 2021

Cited by 137 | Viewed by 18211

Abstract

The current paper presents a novel method for reducing a multiclass confusion matrix into a

2 \times 2

version enabling the exploitation of the relevant performance metrics and methods such as the receiver operating characteristic and area under the curve for the assessment [...] Read more.

The current paper presents a novel method for reducing a multiclass confusion matrix into a

2 \times 2

version enabling the exploitation of the relevant performance metrics and methods such as the receiver operating characteristic and area under the curve for the assessment of different classification algorithms. The reduction method is based on class grouping and leads to a special type of matrix called the reduced confusion matrix. The developed method is then exploited for the assessment of state of the art machine learning algorithms applied on the net promoter score classification problem in the field of customer experience analytics indicating the value of the proposed method in real world classification problems. Full article

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

► Show Figures

Figure 1

10 pages, 497 KiB

Open AccessEditor’s ChoiceArticle

Lifetime of Catalyst under Voltage Cycling in Polymer Electrolyte Fuel Cell Due to Platinum Oxidation and Dissolution

by Victor A. Kovtunenko and Larisa Karpenko-Jereb

Technologies 2021, 9(4), 80; https://doi.org/10.3390/technologies9040080 - 31 Oct 2021

Cited by 8 | Viewed by 2849

Abstract

The durability of a platinum catalyst in a polymer electrolyte membrane fuel cell is studied at various operating conditions with respect to the different electric potential difference (called voltage) applied in accelerated stress tests. The electrochemical reactions of Pt ion dissolution and Pt [...] Read more.

The durability of a platinum catalyst in a polymer electrolyte membrane fuel cell is studied at various operating conditions with respect to the different electric potential difference (called voltage) applied in accelerated stress tests. The electrochemical reactions of Pt ion dissolution and Pt oxide coverage of the catalyst lead to the degradation of platinum described by a one-dimensional Holby–Morgan model. The theoretical study of the underlying reaction–diffusion system with the nonlinear reactions is presented by numerical simulations which allow to predict a lifetime of the catalyst under applied voltage cycling. The computer simulation investigates how the Pt mass loss depends on the voltage slope and the upper potential level in cycles. Full article

(This article belongs to the Section Environmental Technology)

► Show Figures

Figure 1

13 pages, 4359 KiB

Open AccessEditor’s ChoiceArticle

Robot Operations for Pine Tree Resin Collection

by Vladimir Gurau, Beau Ragland, Daniel Cox, Andrew Michaud and Lloyd Busby

Technologies 2021, 9(4), 79; https://doi.org/10.3390/technologies9040079 - 27 Oct 2021

Cited by 5 | Viewed by 3601

Abstract

A robotic technology consisting of an industrial robot mounted on an autonomous rover used to tap slash pine trees and collect their oleoresin for processing is introduced, and the technological challenges related to the robotic operations are discussed in detail. Unlike the case [...] Read more.

A robotic technology consisting of an industrial robot mounted on an autonomous rover used to tap slash pine trees and collect their oleoresin for processing is introduced, and the technological challenges related to the robotic operations are discussed in detail. Unlike the case of industrial automated manufacturing systems where the relative position between the tool and workpiece can be controlled within a few hundredths of a millimeter accuracy, when used in highly unstructured environments characteristic to forestry or agriculture, the positioning accuracy between the industrial robot and the target on which it operates can be much lower than the accuracy required for the operation of the industrial robot. The paper focuses on presenting the robotic operations necessary for drilling three converging boreholes in the pine tree, spraying the boreholes with chemicals, inserting a plastic tube with pre-attached collection bag in one borehole and inserting two plugs in other two boreholes. The challenges related to performing these robotic operations in conditions of large variations in the actual shape of the pine tree trunk and variations in the relative position between the robot and the pine tree after the autonomous vehicle positions itself in front of the tree are presented. The technical solutions used to address these challenges are also described. The strategies used to programmatically adjust the robot toolpath based on detection of the borehole entry points and on the measurement of the insertion force are presented. Full article

(This article belongs to the Special Issue Advances and Innovations in Manufacturing Technologies)

► Show Figures

Figure 1

18 pages, 4656 KiB

Open AccessEditor’s ChoiceArticle

An Open-Source, Low-Cost Measurement System for Collecting Hydrometeorological Data in the Open Field

by Kenichi Tatsumi, Tomoya Yamazaki and Hirohiko Ishikawa

Technologies 2021, 9(4), 78; https://doi.org/10.3390/technologies9040078 - 22 Oct 2021

Cited by 2 | Viewed by 3441

Abstract

To realize precision agriculture at multiple locations in the field, a low-cost measurement system should be developed for easy collection of hydrometeorological data, such as temperature, moisture, and light. In this study, a compact and low-cost hydrometeorological measurement system with a simplified wire [...] Read more.

To realize precision agriculture at multiple locations in the field, a low-cost measurement system should be developed for easy collection of hydrometeorological data, such as temperature, moisture, and light. In this study, a compact and low-cost hydrometeorological measurement system with a simplified wire code, which is customizable according to the purpose of observation, was built using a circuit board that connects Arduino to the sensors, which was then implemented and analyzed. The developed system measures air and soil temperatures, soil water content, and photosynthetic photon flux density using a sensor connected to Arduino Uno and saves the continuous, high-temporal-resolution output to an SD card. The results obtained from continuous measurement showed that the data collected using this system was significantly better than those collected using commercially available equipment. Anyone can easily measure the weather environments by using this fully open, highly versatile, portable, and user-friendly system. This system can contribute to the growth and expansion of precision agriculture, field management, development of crop models, and laborsaving. It can also provide a global solution to ongoing agricultural issues and improve the efficiency of farming operations, particularly in developing and low-income countries. Full article

(This article belongs to the Topic Smart Technologies in Food Packaging and Sensors)

► Show Figures

Figure 1

10 pages, 7712 KiB

Open AccessEditor’s ChoiceArticle

Heat Treatment Consideration in Structural Simulations of Machine Elements: Analysis of a Starter Clutch Barrel

by Domen Šeruga, Matija Kavčič, Jernej Klemenc and Marko Nagode

Technologies 2021, 9(4), 73; https://doi.org/10.3390/technologies9040073 - 9 Oct 2021

Viewed by 2964

Abstract

Consideration of heat treatment in simulations of structural components and its impact on predictions of behaviour during operation is analysed here. An automotive machine element with a complex geometry and dynamic load is analysed rather than a standard laboratory specimen under controlled conditions. [...] Read more.

Consideration of heat treatment in simulations of structural components and its impact on predictions of behaviour during operation is analysed here. An automotive machine element with a complex geometry and dynamic load is analysed rather than a standard laboratory specimen under controlled conditions. The heat treatment analysis of a starter clutch barrel has been performed in DANTE followed by a structural analysis in ANSYS 2019 R3 during operation simulating a load cycle due to the start of an internal combustion engine. The heat treatment simulation consisted of carburisation, quenching and tempering. First, the carbon content and its distribution have been simulated. Next, the hardness of the starter clutch barrel and its distribution have been analysed with respect to the carbon distribution and hardness-dependent material properties of the AISI/SAE 4142 steel. Finally, the stress field after the heat treatment and during the operation of the starter clutch barrel has been thoroughly evaluated and compared to the simulation without the consideration of the heat treatment. Results of the simulation show that the heat treatment introduces favourable compressive stresses at the critical location of the starter clutch barrel and reduces the effective amplitude of the equivalent stress during the operation. Furthermore, the results of the simulation prove that heat treatment should be considered already during the early stages of the R & D process as it can have a decisive effect on the operational behaviour of the structural component. Moreover, a non-consideration of the heat treatment can lead into erroneous conclusions regarding the suitability of machine elements. Full article

(This article belongs to the Section Manufacturing Technology)

► Show Figures

Figure 1

18 pages, 3785 KiB

Open AccessEditor’s ChoiceArticle

Open-Source Script for Design and 3D Printing of Porous Structures for Soil Science

by Romain Bedell, Alaa Hassan, Anne-Julie Tinet, Javier Arrieta-Escobar, Delphine Derrien, Marie-France Dignac, Vincent Boly, Stéphanie Ouvrard and Joshua M. Pearce

Technologies 2021, 9(3), 67; https://doi.org/10.3390/technologies9030067 - 15 Sep 2021

Cited by 1 | Viewed by 6172

Abstract

Three-dimensional (3D) printing in soil science is relatively rare but offers promising directions for research. Having 3D-printed soil samples will help academics and researchers conduct experiments in a reproducible and participatory research network and gain a better understanding of the studied soil parameters. [...] Read more.

Three-dimensional (3D) printing in soil science is relatively rare but offers promising directions for research. Having 3D-printed soil samples will help academics and researchers conduct experiments in a reproducible and participatory research network and gain a better understanding of the studied soil parameters. One of the most important challenges in utilizing 3D printing techniques for soil modeling is the manufacturing of a soil structure. Until now, the most widespread method for printing porous soil structures is based on scanning a real sample via X-ray tomography. The aim of this paper is to design a porous soil structure based on mathematical models rather than on samples themselves. This can allow soil scientists to design and parameterize their samples according to their desired experiments. An open-source toolchain is developed using a Lua script, in the IceSL slicer, with graphical user interface to enable researchers to create and configure their digital soil models, called monoliths, without using meshing algorithms or STL files which reduce the resolution of the model. Examples of monoliths are 3D-printed in polylactic acid using fused filament fabrication technology with a layer thickness of 0.20, 0.12, and 0.08 mm. The images generated from the digital model slicing are analyzed using open-source ImageJ software to obtain information about internal geometrical shape, porosity, tortuosity, grain size distribution, and hydraulic conductivities. The results show that the developed script enables designing reproducible numerical models that imitate soil structures with defined pore and grain sizes in a range between coarse sand (from 1 mm diameter) to fine gravel (up to 12 mm diameter). Full article

(This article belongs to the Special Issue Open Source Agriculture Technology)

► Show Figures

Figure 1

12 pages, 4449 KiB

Open AccessFeature PaperEditor’s ChoiceArticle

Design, Construction and Tests of a Low-Cost Myoelectric Thumb

by Murat Ayvali, Inge Wickenkamp and Andrea Ehrmann

Technologies 2021, 9(3), 63; https://doi.org/10.3390/technologies9030063 - 3 Sep 2021

Cited by 4 | Viewed by 5369

Abstract

Myoelectric signals can be used to control prostheses or exoskeletons as well as robots, i.e., devices assisting the user or replacing a missing part of the body. A typical application of myoelectric prostheses is the human hand. Here, the development of a low-cost [...] Read more.

Myoelectric signals can be used to control prostheses or exoskeletons as well as robots, i.e., devices assisting the user or replacing a missing part of the body. A typical application of myoelectric prostheses is the human hand. Here, the development of a low-cost myoelectric thumb is described, which can either be used as an additional finger or as prosthesis. Combining 3D printing with inexpensive sensors, electrodes, and electronics, the recent project offers the possibility to produce an individualized myoelectric thumb at significantly lower costs than commercial myoelectric prostheses. Alternatively, a second thumb may be supportive for people with special manual tasks. These possibilities are discussed together with disadvantages of a second thumb and drawbacks of the low-cost solution in terms of mechanical properties and wearing comfort. The study shows that a low-cost customized myoelectric thumb can be produced in this way, but further research on controlling the thumb as well as improving motorization are necessarily to make it fully usable for daily tasks. Full article

(This article belongs to the Section Assistive Technologies)

► Show Figures

Figure 1

10 pages, 1695 KiB

Open AccessEditor’s ChoiceCommunication

A Design Study of Orthotic Shoe Based on Pain Pressure Measurement Using Algometer for Calcaneal Spur Patients

by Dwi Basuki Wibowo, Agus Suprihanto, Wahyu Caesarendra, Adam Glowacz, Rudiansyah Harahap, Ryszard Tadeusiewicz, Eliasz Kańtoch and Pg Emeroylariffion Abas

Technologies 2021, 9(3), 62; https://doi.org/10.3390/technologies9030062 - 30 Aug 2021

Viewed by 3253

Abstract

The pressure pain threshold (PPT) is a useful tool for evaluating mechanical sensitivity in individuals suffering from various musculoskeletal disorders. The aim of this study is to investigate PPT at the heel area in order to assist in the design of orthotic shoes [...] Read more.

The pressure pain threshold (PPT) is a useful tool for evaluating mechanical sensitivity in individuals suffering from various musculoskeletal disorders. The aim of this study is to investigate PPT at the heel area in order to assist in the design of orthotic shoes for sufferers of heel pain due to a calcaneal spur. The size and location of the calcaneal spur was determined by x-ray images, with PPT data measured around the spur at five points by using algometer FDIX 25. The pain test experiment was conducted by pressing each point to obtain the pain minimum compressive pressure (PMCP) and its location. The information of shoe size, spur location and dimensions, and the PMCP location for each individual is used to obtain the exact point location for applying a softer material to the shoe in-sole, in order to reduce heel pain. The results are significant as it can be used by designers to design appropriate shoe in-soles for individuals suffering from heel pain. Full article

► Show Figures

Figure 1

22 pages, 3163 KiB

Open AccessEditor’s ChoiceArticle

Evaluation of Thoracic Equivalent Multiport Circuits Using an Electrical Impedance Tomography Hardware Simulation Interface

by Christos Dimas, Vassilis Alimisis, Ioannis Georgakopoulos, Nikolaos Voudoukis, Nikolaos Uzunoglu and Paul P. Sotiriadis

Technologies 2021, 9(3), 58; https://doi.org/10.3390/technologies9030058 - 9 Aug 2021

Cited by 4 | Viewed by 3928

Abstract

Electrical impedance tomography is a low-cost, safe, and high temporal resolution medical imaging modality which finds extensive application in real-time thoracic impedance imaging. Thoracic impedance changes can reveal important information about the physiological condition of patients’ lungs. In this way, electrical impedance tomography [...] Read more.

Electrical impedance tomography is a low-cost, safe, and high temporal resolution medical imaging modality which finds extensive application in real-time thoracic impedance imaging. Thoracic impedance changes can reveal important information about the physiological condition of patients’ lungs. In this way, electrical impedance tomography can be a valuable tool for monitoring patients. However, this technique is very sensitive to measurement noise or possible minor signal errors, coming from either the hardware, the electrodes, or even particular biological signals. Thus, the design of a good performance electrical impedance tomography hardware setup which properly interacts with the tissue examined is both an essential and a challenging concept. In this paper, we adopt an extensive simulation approach, which combines the system’s analogue and digital hardware, along with equivalent circuits of 3D finite element models that represent thoracic cavities. Each thoracic finite element model is created in MATLAB based on existing CT images, while the tissues’ conductivity and permittivity values for a selected frequency are acquired from a database using Python. The model is transferred to a multiport RLC network, embedded in the system’s hardware which is simulated at LT SPICE. The voltage output data are transferred to MATLAB where the electrical impedance tomography signal sampling and digital processing is also simulated. Finally, image reconstructions are performed in MATLAB, using the EIDORS library tool and considering the signal noise levels and different electrode and signal sampling configurations (ADC bits, sampling frequency, number of taps). Full article

► Show Figures

Figure 1

20 pages, 1163 KiB

Open AccessEditor’s ChoiceArticle

Exploiting Biomedical Sensors for a Home Monitoring System for Paediatric Patients with Congenital Heart Disease

by Massimiliano Donati, Silvia Panicacci, Alessio Ruiu, Stefano Dalmiani, Pierluigi Festa, Lamia Ait-Ali, Francesca Mastorci, Alessandro Pingitore, Wanda Pennè, Luca Fanucci and Sergio Saponara

Technologies 2021, 9(3), 56; https://doi.org/10.3390/technologies9030056 - 31 Jul 2021

Cited by 3 | Viewed by 3742

Abstract

Congenital heart disease, the most frequent malformation at birth, is usually not fatal but leads to multiple hospitalisations and outpatient visits, with negative impact on the quality of life and psychological profile not only of children but also of their families. In this [...] Read more.

Congenital heart disease, the most frequent malformation at birth, is usually not fatal but leads to multiple hospitalisations and outpatient visits, with negative impact on the quality of life and psychological profile not only of children but also of their families. In this paper, we describe the entire architecture of a system for remotely monitoring paediatric/neonatal patients with congenital heart disease, with the final aim of improving quality of life of the whole family and reducing hospital admissions. The interesting vital parameters for the disease are ECG, heart rate, oxygen saturation, body temperature and body weight. They are collected at home using some biomedical sensors specifically selected and calibrated for the paediatric field. These data are then sent to the smart hub, which proceeds with the synchronisation to the remote e-Health care center. Here, the doctors can log and evaluate the patient’s parameters. Preliminary results underline the sensor suitability for children and infants and good usability and data management of the smart-hub technology (E@syCare). In the clinical trial, some patients from the U.O.C. Paediatric and Adult Congenital Cardiology- Monasterio Foundation are enrolled. They receive a home monitoring kit according to the group they belong to. The trial aims to evaluate the effects of the system on quality of life. Psychological data are collected through questionnaires filled in by parents/caregivers in self-administration via the gateway at the beginning and at the end of the study. Results highlight an overall improvement in well-being and sleep quality, with a consequent reduction in anxious and stressful situations during daily life thanks to telemonitoring. At the same time, users reported a good level of usability, ease of data transmission and management of the devices. Full article

► Show Figures

Figure 1

17 pages, 477 KiB

Open AccessEditor’s ChoiceArticle

Effect of Data Scaling Methods on Machine Learning Algorithms and Model Performance

by Md Manjurul Ahsan, M. A. Parvez Mahmud, Pritom Kumar Saha, Kishor Datta Gupta and Zahed Siddique

Technologies 2021, 9(3), 52; https://doi.org/10.3390/technologies9030052 - 24 Jul 2021

Cited by 464 | Viewed by 21858

Abstract

Heart disease, one of the main reasons behind the high mortality rate around the world, requires a sophisticated and expensive diagnosis process. In the recent past, much literature has demonstrated machine learning approaches as an opportunity to efficiently diagnose heart disease patients. However, [...] Read more.

Heart disease, one of the main reasons behind the high mortality rate around the world, requires a sophisticated and expensive diagnosis process. In the recent past, much literature has demonstrated machine learning approaches as an opportunity to efficiently diagnose heart disease patients. However, challenges associated with datasets such as missing data, inconsistent data, and mixed data (containing inconsistent missing data both as numerical and categorical) are often obstacles in medical diagnosis. This inconsistency led to a higher probability of misprediction and a misled result. Data preprocessing steps like feature reduction, data conversion, and data scaling are employed to form a standard dataset—such measures play a crucial role in reducing inaccuracy in final prediction. This paper aims to evaluate eleven machine learning (ML) algorithms—Logistic Regression (LR), Linear Discriminant Analysis (LDA), K-Nearest Neighbors (KNN), Classification and Regression Trees (CART), Naive Bayes (NB), Support Vector Machine (SVM), XGBoost (XGB), Random Forest Classifier (RF), Gradient Boost (GB), AdaBoost (AB), Extra Tree Classifier (ET)—and six different data scaling methods—Normalization (NR), Standscale (SS), MinMax (MM), MaxAbs (MA), Robust Scaler (RS), and Quantile Transformer (QT) on a dataset comprising of information of patients with heart disease. The result shows that CART, along with RS or QT, outperforms all other ML algorithms with 100% accuracy, 100% precision, 99% recall, and 100% F1 score. The study outcomes demonstrate that the model’s performance varies depending on the data scaling method. Full article

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

► Show Figures

Figure 1

11 pages, 823 KiB

Open AccessEditor’s ChoiceArticle

Behavioral Pattern Analysis between Bilingual and Monolingual Listeners’ Natural Speech Perception on Foreign-Accented English Language Using Different Machine Learning Approaches

by Md Tanvir Ahad, Md Manjurul Ahsan, Ishrat Jahan, Redwan Nazim, Munshi Md. Shafwat Yazdan, Pedro Huebner and Zahed Siddique

Technologies 2021, 9(3), 51; https://doi.org/10.3390/technologies9030051 - 23 Jul 2021

Cited by 2 | Viewed by 4163

Abstract

Speech perception in an adverse background/noisy environment is a complex and challenging human process, which is made even more complicated in foreign-accented language for bilingual and monolingual individuals. Listeners who have difficulties in hearing are affected most by such a situation. Despite considerable [...] Read more.

Speech perception in an adverse background/noisy environment is a complex and challenging human process, which is made even more complicated in foreign-accented language for bilingual and monolingual individuals. Listeners who have difficulties in hearing are affected most by such a situation. Despite considerable efforts, the increase in speech intelligibility in noise remains elusive. Considering this opportunity, this study investigates Bengali–English bilinguals and native American English monolinguals’ behavioral patterns on foreign-accented English language considering bubble noise, gaussian or white noise, and quiet sound level. Twelve regular hearing participants (Six Bengali–English bilinguals and Six Native American English monolinguals) joined in this study. Statistical computation shows that speech with different noise has a significant effect (p = 0.009) on listening for both bilingual and monolingual under different sound levels (e.g., 55 dB, 65 dB, and 75 dB). Here, six different machine learning approaches (Logistic Regression (LR), Linear Discriminant Analysis (LDA), K-nearest neighbors (KNN), Naïve Bayes (NB), Classification and regression trees (CART), and Support vector machine (SVM)) are tested and evaluated to differentiate between bilingual and monolingual individuals from their behavioral patterns in both noisy and quiet environments. Results show that most optimal performances were observed using LDA by successfully differentiating between bilingual and monolingual 60% of the time. A deep neural network-based model is proposed to improve this measure further and achieved an accuracy of nearly 100% in successfully differentiating between bilingual and monolingual individuals. Full article

► Show Figures

Figure 1

17 pages, 3734 KiB

Open AccessEditor’s ChoiceArticle

Municipal Solid Waste Management Practices for Achieving Green Architecture Concepts in Addis Ababa, Ethiopia

by Eshetu Gelan

Technologies 2021, 9(3), 48; https://doi.org/10.3390/technologies9030048 - 11 Jul 2021

Cited by 22 | Viewed by 12111

Abstract

Solid waste is one of the social and environmental challenges that urban areas are facing. The study assesses the state of solid waste in Addis Ababa during 2016–2020 to provide implications for achieving green architecture concepts through better management of solid waste and [...] Read more.

Solid waste is one of the social and environmental challenges that urban areas are facing. The study assesses the state of solid waste in Addis Ababa during 2016–2020 to provide implications for achieving green architecture concepts through better management of solid waste and its economic contribution. The study uses secondary and primary data. Quantitative and qualitative data are analyzed through descriptive statistics and context analysis, respectively. The result reveals that most solid waste is generated from households, followed by commercial centers, street sweeping, industries/factories, hotels, and hospitals, respectively. From 2016 to 2020, an average of 80.28% of solid waste is collected, whereas 19.72% of the waste is not collected. There are little or no efforts made to segregate solid waste at the source. The generated waste is disposed of in the Reppi open landfill. Together with Ethiopian electric power (EEP) and the City Government of Addis Ababa, waste has been converted to energy since 2019. The study suggests minimizing waste from its source by reducing generation, composting, reusing, recycling, waste-to-energy strategy, and well-designed buildings to achieve the concept of green architecture in Addis Ababa through better solid waste management. Full article

► Show Figures

Figure 1

18 pages, 641 KiB

Open AccessEditor’s ChoiceArticle

Computer Vision Framework for Wheat Disease Identification and Classification Using Jetson GPU Infrastructure

by Tagel Aboneh, Abebe Rorissa, Ramasamy Srinivasagan and Ashenafi Gemechu

Technologies 2021, 9(3), 47; https://doi.org/10.3390/technologies9030047 - 2 Jul 2021

Cited by 42 | Viewed by 6707

Abstract

Diseases have adverse effects on crop production and yield loss. Various diseases such as leaf rust, stem rust, and strip rust can affect yield quality and quantity for a studied area. In addition, manual wheat disease identification and interpretation is time-consuming and cumbersome. [...] Read more.

Diseases have adverse effects on crop production and yield loss. Various diseases such as leaf rust, stem rust, and strip rust can affect yield quality and quantity for a studied area. In addition, manual wheat disease identification and interpretation is time-consuming and cumbersome. Currently, decisions related to plants mainly rely on the level of expertise in the domain. To resolve these challenges and to identify wheat disease as early as possible, we implemented different deep learning models such as Inceptionv3, Resnet50, and VGG16/19. This research was conducted in collaboration with Bishoftu Agricultural Research Institute, Ethiopia. Our main objective was to automate plant-disease identification using advanced deep learning approaches and image data. For the experiment, RGB image data were collected from the Bishoftu area. From the experimental results, the VGG19 model classified wheat disease with 99.38% accuracy. Full article

(This article belongs to the Special Issue Multimedia Indexing and Retrieval)

► Show Figures

Figure 1

22 pages, 6941 KiB

Open AccessEditor’s ChoiceArticle

Multi-Agent Reinforcement Learning Framework in SDN-IoT for Transient Load Detection and Prevention

by Delali Kwasi Dake, James Dzisi Gadze, Griffith Selorm Klogo and Henry Nunoo-Mensah

Technologies 2021, 9(3), 44; https://doi.org/10.3390/technologies9030044 - 29 Jun 2021

Cited by 30 | Viewed by 6142

Abstract

The fast emergence of IoT devices and its accompanying big and complex data has necessitated a shift from the traditional networking architecture to software-defined networks (SDNs) in recent times. Routing optimization and DDoS protection in the network has become a necessity for mobile [...] Read more.

The fast emergence of IoT devices and its accompanying big and complex data has necessitated a shift from the traditional networking architecture to software-defined networks (SDNs) in recent times. Routing optimization and DDoS protection in the network has become a necessity for mobile network operators in maintaining a good QoS and QoE for customers. Inspired by the recent advancement in Machine Learning and Deep Reinforcement Learning (DRL), we propose a novel MADDPG integrated Multiagent framework in SDN for efficient multipath routing optimization and malicious DDoS traffic detection and prevention in the network. The two MARL agents cooperate within the same environment to accomplish network optimization task within a shorter time. The state, action, and reward of the proposed framework were further modelled mathematically using the Markov Decision Process (MDP) and later integrated into the MADDPG algorithm. We compared the proposed MADDPG-based framework to DDPG for network metrics: delay, jitter, packet loss rate, bandwidth usage, and intrusion detection. The results show a significant improvement in network metrics with the two agents. Full article

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

► Show Figures

Figure 1

19 pages, 6117 KiB

Open AccessEditor’s ChoiceArticle

Range-Based Localization of a Wireless Sensor Network for Internet of Things Using Received Signal Strength Indicator and the Most Valuable Player Algorithm

by Mohammed A. Alanezi, Houssem R.E.H. Bouchekara and Mohammed. S. Javaid

Technologies 2021, 9(2), 42; https://doi.org/10.3390/technologies9020042 - 15 Jun 2021

Cited by 14 | Viewed by 3834

Abstract

The localization of the nodes in wireless sensor networks is essential in establishing effective communication among different devices connected, within the Internet of Things. This paper proposes a novel method to accurately determine the position and distance of the wireless sensors linked in [...] Read more.

The localization of the nodes in wireless sensor networks is essential in establishing effective communication among different devices connected, within the Internet of Things. This paper proposes a novel method to accurately determine the position and distance of the wireless sensors linked in a local network. The method utilizes the signal strength received at the target node to identify its location in the localized grid system. The Most Valuable Player Algorithm is used to solve the localization problem. Initially, the algorithm is implemented on four test cases with a varying number of sensor nodes to display its robustness under different network occupancies. Afterward, the study is extended to incorporate actual readings from both indoor and outdoor environments. The results display higher accuracy in the localization of unknown sensor nodes than previously reported. Full article

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

► Show Figures

Figure 1

16 pages, 22437 KiB

Open AccessEditor’s ChoiceArticle

On the Use of Conformal Cooling in High-Pressure Die-Casting and Semisolid Casting

by Anders E. W. Jarfors, Ruslan Sevastopol, Karamchedu Seshendra, Qing Zhang, Jacob Steggo and Roland Stolt

Technologies 2021, 9(2), 39; https://doi.org/10.3390/technologies9020039 - 21 May 2021

Cited by 13 | Viewed by 4600

Abstract

Today, tool life in high pressure die casting (HPDC) is of growing interest. A common agreement is that die life is primarily decided by the thermal load and temperature gradients in the die materials. Conformal cooling with the growth of additive manufacturing has [...] Read more.

Today, tool life in high pressure die casting (HPDC) is of growing interest. A common agreement is that die life is primarily decided by the thermal load and temperature gradients in the die materials. Conformal cooling with the growth of additive manufacturing has raised interest as a means of extending die life. In the current paper, conformal cooling channels’ performance and effect on the thermal cycle in high-pressure die casting and rheocasting are investigated for conventional HPDC and semisolid processing. It was found that conformal cooling aids die temperature reduction, and the use of die spray may be reduced and support the die-life extension. For the die filling, the increased temperature was possibly counterproductive. Instead, it was found that the main focus for conformal cooling should be focused to manage temperature around the in-let bushing and possibly the runner system. Due to the possible higher inlet pressures for semisolid casting, particular benefits could be seen. Full article

(This article belongs to the Section Manufacturing Technology)

► Show Figures

Figure 1

10 pages, 3220 KiB

Open AccessEditor’s ChoiceArticle

Surface Modification of Polyethersulfone (PES) with UV Photo-Oxidation

by Ibrahim Cisse, Sarah Oakes, Shreen Sachdev, Marc Toro, Shin Lutondo, Devon Shedden, Kristen Margaret Atkinson, Joel Shertok, Michael Mehan, Surendra K. Gupta and Gerald A. Takacs

Technologies 2021, 9(2), 36; https://doi.org/10.3390/technologies9020036 - 11 May 2021

Cited by 10 | Viewed by 4098

Abstract

Polyethersulfone (PES) films are widely employed in the construction of membranes where there is a desire to make the surface more hydrophilic. Therefore, UV photo-oxidation was studied in order to oxidize the surface of PES and increase hydrophilicity. UV photo-oxidation using low pressure [...] Read more.

Polyethersulfone (PES) films are widely employed in the construction of membranes where there is a desire to make the surface more hydrophilic. Therefore, UV photo-oxidation was studied in order to oxidize the surface of PES and increase hydrophilicity. UV photo-oxidation using low pressure mercury lamps emitting both 253.7 and 184.9 nm radiation were compared with only 253.7 nm photons. The modified surfaces were characterized using X-ray photoelectron spectroscopy (XPS), atomic force microscopy (AFM), and water contact angle (WCA) measurements. Both sets of lamps gave similar results, showing an increase of the oxygen concentration up to a saturation level of ca. 29 at.% and a decrease in the WCA, i.e., an increase in hydrophilicity, down to ca. 40°. XPS detected a decrease of sp² C-C aromatic group bonding and an increase in the formation of C-O, C=O, O=C-O, O=C-OH, O-(C=O)-O, and sulphonate and sulphate moieties. Since little change in surface roughness was observed by AFM, the oxidation of the surface caused the increase in hydrophilicity. Full article

(This article belongs to the Special Issue Advances and Innovations in Manufacturing Technologies)

► Show Figures

Figure 1

18 pages, 6306 KiB

Open AccessEditor’s ChoiceArticle

Augmented Reality in Industry 4.0 and Future Innovation Programs

by Gian Maria Santi, Alessandro Ceruti, Alfredo Liverani and Francesco Osti

Technologies 2021, 9(2), 33; https://doi.org/10.3390/technologies9020033 - 29 Apr 2021

Cited by 70 | Viewed by 11431

Abstract

Augmented Reality (AR) is worldwide recognized as one of the leading technologies of the 21st century and one of the pillars of the new industrial revolution envisaged by the Industry 4.0 international program. Several papers describe, in detail, specific applications of Augmented Reality [...] Read more.

Augmented Reality (AR) is worldwide recognized as one of the leading technologies of the 21st century and one of the pillars of the new industrial revolution envisaged by the Industry 4.0 international program. Several papers describe, in detail, specific applications of Augmented Reality developed to test its potentiality in a variety of fields. However, there is a lack of sources detailing the current limits of this technology in the event of its introduction in a real working environment where everyday tasks could be carried out by operators using an AR-based approach. A literature analysis to detect AR strength and weakness has been carried out, and a set of case studies has been implemented by authors to find the limits of current AR technologies in industrial applications outside the laboratory-protected environment. The outcome of this paper is that, even though Augmented Reality is a well-consolidated computer graphic technique in research applications, several improvements both from a software and hardware point of view should be introduced before its introduction in industrial operations. The originality of this paper lies in the detection of guidelines to improve the Augmented Reality potentialities in factories and industries. Full article

► Show Figures

Figure 1

12 pages, 728 KiB

Open AccessEditor’s ChoiceArticle

Evaluating the Performance of Eigenface, Fisherface, and Local Binary Pattern Histogram-Based Facial Recognition Methods under Various Weather Conditions

by Md Manjurul Ahsan, Yueqing Li, Jing Zhang, Md Tanvir Ahad and Kishor Datta Gupta

Technologies 2021, 9(2), 31; https://doi.org/10.3390/technologies9020031 - 27 Apr 2021

Cited by 23 | Viewed by 8686

Abstract

Facial recognition (FR) in unconstrained weather is still challenging and surprisingly ignored by many researchers and practitioners over the past few decades. Therefore, this paper aims to evaluate the performance of three existing popular facial recognition methods considering different weather conditions. As a [...] Read more.

Facial recognition (FR) in unconstrained weather is still challenging and surprisingly ignored by many researchers and practitioners over the past few decades. Therefore, this paper aims to evaluate the performance of three existing popular facial recognition methods considering different weather conditions. As a result, a new face dataset (Lamar University database (LUDB)) was developed that contains face images captured under various weather conditions such as foggy, cloudy, rainy, and sunny. Three very popular FR methods—Eigenface (EF), Fisherface (FF), and Local binary pattern histogram (LBPH)—were evaluated considering two other face datasets, AT&T and 5_Celebrity, along with LUDB in term of accuracy, precision, recall, and F1 score with 95% confidence interval (CI). Computational results show a significant difference among the three FR techniques in terms of overall time complexity and accuracy. LBPH outperforms the other two FR algorithms on both LUDB and 5_Celebrity datasets by achieving 40% and 95% accuracy, respectively. On the other hand, with minimum execution time of 1.37, 1.37, and 1.44 s per image on AT&T,5_Celebrity, and LUDB, respectively, Fisherface achieved the best result. Full article

► Show Figures

Figure 1

Journal Menu

Journal Browser

Editor’s Choice Articles

Article

Further Information

Guidelines

MDPI Initiatives

Follow MDPI