Signals

Early detection and evaluation of children at risk of neurodevelopmental disorders and/or communication deficits is critical. While the current literature indicates a high prevalence of neurodevelopmental disorders, many children remain undiagnosed, resulting in missed opportunities for effective interventions that could have had a greater impact if administered earlier. Clinicians face a variety of complications during neurodevelopmental disorders’ evaluation procedures and must elevate their use of digital tools to aid in early detection efficiently. Artificial intelligence enables novelty in taking decisions, classification, and diagnosis. The current research investigates the efficacy of various machine learning approaches on the biometric SmartSpeech datasets. These datasets come from a new innovative system that includes a serious game which gathers children’s responses to specifically designed speech and language activities and their manifestations, intending to assist during the clinical evaluation of neurodevelopmental disorders. The machine learning approaches were used by utilizing the algorithms Radial Basis Function, Neural Network, Deep Learning Neural Networks, and a variation of Grammatical Evolution (GenClass). The most significant results show improved accuracy (%) when using the eye tracking dataset; more specifically: (i) for the class Disorder with GenClass (92.83%), (ii) for the class Autism Spectrum Disorders with Deep Learning Neural Networks layer 4 (86.33%), (iii) for the class Attention Deficit Hyperactivity Disorder with Deep Learning Neural Networks layer 4 (87.44%), (iv) for the class Intellectual Disability with GenClass (86.93%), (v) for the class Specific Learning Disorder with GenClass (88.88%), and (vi) for the class Communication Disorders with GenClass (88.70%). Overall, the results indicated GenClass to be nearly the top competitor, opening up additional probes for future studies toward automatically classifying and assisting clinical assessments for children with neurodevelopmental disorders. Full article

In this work, an effective Fault Detection and Diagnosis (FDD) strategy designed to increase the performance and accuracy of fault diagnosis in grid-connected photovoltaic (GCPV) systems is developed. The evolved approach is threefold: first, a pre-processing of the training dataset is applied using a multiscale scheme that decomposes the data at multiple scales using high-pass/low-pass filters to separate the noise from the informative attributes and prevent the stochastic samples. Second, a principal component analysis (PCA) technique is applied to the newly obtained data to select, extract, and preserve only the more relevant, informative, and uncorrelated attributes; and finally, to distinguish between the diverse conditions, the extracted attributes are utilized to train the NNs classifiers. In this study, an effort is made to take into consideration all potential and frequent faults that might occur in PV systems. Thus, twenty-one faulty scenarios (line-to-line, line-to-ground, connectivity faults, and faults that can affect the normal operation of the bay-pass diodes) have been introduced and treated at different levels and locations; each scenario comprises various and diverse conditions, including the occurrence of simple faults in the $P{V}_1$ array, simple faults in the $P{V}_2$ array, multiple faults in $P{V}_1$, multiple faults in $P{V}_2$, and mixed faults in both PV arrays, in order to ensure a complete and global analysis, thereby reducing the loss of generated energy and maintaining the reliability and efficiency of such systems. The obtained outcomes demonstrate that the proposed approach not only achieves good accuracies but also reduces runtimes during the diagnosis process by avoiding noisy and stochastic data, thereby removing irrelevant and correlated samples from the original dataset. Full article

Computer-based job interview training, including virtual reality (VR) simulations, have gained popularity in recent years to support and aid autistic individuals, who face significant challenges and barriers in finding and maintaining employment. Although popular, these training systems often fail to resemble the complexity and dynamism of the employment interview, as the dialogue management for the virtual conversation agent either relies on choosing from a menu of prespecified answers, or dialogue processing is based on keyword extraction from the transcribed speech of the interviewee, which depends on the interview script. We address this limitation through automated dialogue act classification via transfer learning. This allows for recognizing intent from user speech, independent of the domain of the interview. We also redress the lack of training data for a domain general job interview dialogue act classifier by providing an original dataset with responses to interview questions within a virtual job interview platform from 22 autistic participants. Participants’ responses to a customized interview script were transcribed to text and annotated according to a custom 13-class dialogue act scheme. The best classifier was a fine-tuned bidirectional encoder representations from transformers (BERT) model, with an f1-score of 87%. Full article

This paper investigates the use of micro-Doppler spectrogram signatures of flying targets, such as drones and birds, to aid in their remote classification. Using a custom-designed 10-GHz continuous wave (CW) radar system, measurements from different scenarios on a variety of targets were recorded to create datasets for image classification. Time/velocity spectrograms generated for micro-Doppler analysis of multiple drones and birds were used for target identification and movement classification using TensorFlow. Using support vector machines (SVMs), the results showed an accuracy of about 90% for drone size classification, about 96% for drone vs. bird classification, and about 85% for individual drone and bird distinction between five classes. Different characteristics of target detection were explored, including the landscape and behavior of the target. Full article

Emergency Communication Systems (ECS) are network-based systems that may enable people to exchange information during crises and physical disasters when basic communication options have collapsed. They may be used to restore communication in off-grid areas or even when normal telecommunication networks have failed. These systems may use technologies such as Low-Power Wide-Area(LPWAN) and Software-Defined Wide Area Networks (SD-WAN), which can be specialized as software applications and Internet of Things (IoT) platforms. In this article, we present a comprehensive discussion of the existing ECS use cases and current research directions regarding the use of unconventional and hybrid methods for establishing communication between a specific site and the outside world. The ECS system proposed and simulated in this article consists of an autonomous wireless 4G/LTE base station and a LoRa network utilizing a hybrid IoT communication platform combining LPWAN and SD-WAN technologies. The LoRa-based wireless network was simulated using Network Simulator 3 (NS3), referring basically to firm and sufficient data transfer between an appropriate gateway and LP-WAN sensor nodes to provide trustworthy communications. The proposed scheme provided efficient data transfer posing low data losses by optimizing the installation of the gateway within the premises, while the SD-WAN scheme that was simulated using the MATLAB simulator and LTE Toolbox in conjunction with an ADALM PLUTO SDR device proved to be an outstanding alternative communication solution as well. Its performance was measured after recombining all received data blocks, leading to a beneficial proposal to researchers and practitioners regarding the benefits of using an on-premises IoT communication platform. Full article

Through the development of artificial intelligence, some capabilities of human beings have been replicated in computers. Among the developed models, convolutional neural networks stand out considerably because they make it possible for systems to have the inherent capabilities of humans, such as pattern recognition in images and signals. However, conventional methods are based on deterministic models, which cannot express the epistemic uncertainty of their predictions. The alternative consists of probabilistic models, although these are considerably more difficult to develop. To address the problems related to the development of probabilistic networks and the choice of network architecture, this article proposes the development of an application that allows the user to choose the desired architecture with the trained model for the given data. This application, named “Graphical User Interface for Probabilistic Neural Networks”, allows the user to develop or to use a standard convolutional neural network for the provided data, with networks already adapted to implement a probabilistic model. Contrary to the existing models for generic use, which are deterministic and already pre-trained on databases to be used in transfer learning, the approach followed in this work creates the network layer by layer, with training performed on the provided data, originating a specific model for the data in question. Full article

Currently, Internet of Things (IoT) has become common in various applications, including smart factories, smart cities, and smart homes. In them, wireless local-area networks (WLANs) are widely used due to their high-speed data transfer, flexible coverage ranges, and low costs. To enhance the performance, the WLAN configuration should be optimized in dense WLAN environments where multiple access points (APs) and hosts exist. Previously, we have studied the active AP configuration algorithm for dual interfaces using IEEE802.11n and 11ac protocols at each AP under non-channel bonding (non-CB). In this paper, we study the algorithm considering the channel bonding (CB) to enhance its capacity by bonding two channels together. To improve the throughput estimation accuracy of the algorithm, the reduction factor is introduced at contending hosts for the same AP. For evaluations, we conducted extensive experiments using the WIMENT simulator and the testbed system using Raspberry Pi 4B APs. The results show that the estimated throughput is well matched with the measured one, and the proposal achieves the higher throughput with a smaller number of active APs than the previous configurations. Full article

Mobile networks of the fifth generation have stringent requirements for data throughput, latency and reliability. Dual or multi-connectivity is implemented to meet the mobility requirements for certain essential 5G use cases, and this ensures the user’s connection to one or more radio links. Packet duplication (PD) over multi-connectivity is a method of compensating for lost packets by reducing re-transmissions on the same erroneous wireless channel. Utilizing two or more uncorrelated links, a high degree of availability can be attained with this strategy. However, complete packet duplication is inefficient and frequently unnecessary. The wireless channel conditions can change frequently and not allow for a PD. We provide a novel adaptive fractional packet duplication (A-FPD) mechanism for enabling and disabling packet duplication based on a variety of parameters. The signal-to-interference-plus-noise ratio (SINR) and fade duration outage probability (FDOP) are important performance indicators for wireless networks and are used to evaluate and contrast several packet duplication scenarios. Using ns-3 and MATLAB, we present our simulation results for the multi-connectivity and proposed A-FPD schemes. Our technique merely duplicates enough packets across multiple connections to meet the outage criteria. Full article

Multiclass motor imagery classification is essential for brain–computer interface systems such as prosthetic arms. The compressive sensing of EEG helps classify brain signals in real-time, which is necessary for a BCI system. However, compressive sensing is limited, despite its flexibility and data efficiency, because of its sparsity and high computational cost in reconstructing signals. Although the constraint of sparsity in compressive sensing has been addressed through neural networks, its signal reconstruction remains slow, and the computational cost increases to classify the signals further. Therefore, we propose a 1D-Convolutional Residual Network that classifies EEG features in the compressed (sparse) domain without reconstructing the signal. First, we extract only wavelet features (energy and entropy) from raw EEG epochs to construct a dictionary. Next, we classify the given test EEG data based on the sparse representation of the dictionary. The proposed method is computationally inexpensive, fast, and has high classification accuracy as it uses a single feature to classify without preprocessing. The proposed method is trained, validated, and tested using multiclass motor imagery data of 109 subjects from the PhysioNet database. The results demonstrate that the proposed method outperforms state-of-the-art classifiers with 96.6% accuracy. Full article

Next-generation wireless communications aim to utilize mmWave/subTHz bands. In this regime, signal propagation is vulnerable to interferences and path losses. To overcome this issue, a novel technology has been introduced, which is called reconfigurable intelligent surface (RIS). RISs control digitally the reflecting signals using many passive reflector arrays and implement a smart and modifiable radio environment for wireless communications. Nonetheless, channel estimation is the main problem of RIS-assisted systems because of their direct dependence on the system architecture design, the transmission channel configuration and methods used to compute channel state information (CSI) on a base station (BS) and RIS. In this paper, a concise survey on the up-to-date RIS-assisted wireless communications is provided and includes the massive multiple input-multiple output (mMIMO), multiple input-single output (MISO) and cell-free systems with an emphasis on effective algorithms computing CSI. In addition, we will present the effectiveness of the algorithms computing CSI for different communication systems and their techniques, and we will represent the most important ones. Full article

EEG (electroencephalogram) signals could be used reliably to extract critical information regarding ADHD (attention deficit hyperactivity disorder), a childhood neurodevelopmental disorder. The early detection of ADHD is important to lessen the development of this disorder and reduce its long-term impact. This study aimed to develop a computer algorithm to identify children with ADHD automatically from the characteristic brain waves. An EEG machine learning pipeline is presented here, including signal preprocessing and data preparation steps, with thorough explanations and rationale. A large public dataset of 120 children was selected, containing large variability and minimal measurement bias in data collection and reproducible child-friendly visual attentional tasks. Unlike other studies, EEG linear features were extracted to train a Gaussian SVM-based model from only the first four sub-bands of EEG. This eliminates signals more than 30 Hz, thus reducing the computational load for model training while keeping mean accuracy of ~94%. We also performed rigorous validation (obtained 93.2% and 94.2% accuracy, respectively, for holdout and 10-fold cross-validation) to ensure that the developed model is minimally impacted by bias and overfitting that commonly appear in the ML pipeline. These performance metrics indicate the ability to automatically identify children with ADHD from a local clinical setting and provide a baseline for further clinical evaluation and timely therapeutic attempts. Full article

Wearable sensor data can be integrated and interpreted to improve the treatment of chronic conditions, such as diabetes, by enabling adjustments in treatment decisions based on physical activity and psychological stress assessments. The challenges in using biological analytes to frequently detect physical activity (PA) and acute psychological stress (APS) in daily life necessitate the use of data from noninvasive sensors in wearable devices, such as wristbands. We developed a recurrent multi-task deep neural network (NN) with long-short-term-memory architecture to integrate data from multiple sensors (blood volume pulse, skin temperature, galvanic skin response, three-axis accelerometers) and simultaneously detect and classify the type of PA, namely, sedentary state, treadmill run, stationary bike, and APS, such as non-stress, emotional anxiety stress, mental stress, and estimate the energy expenditure (EE). The objective was to assess the feasibility of using the multi-task recurrent NN (RNN) rather than independent RNNs for detection and classification of AP and APS. The multi-task RNN achieves comparable performance to independent RNNs, with the multi-task RNN having F1 scores of 98.00% for PA and 98.97% for APS, and a root mean square error (RMSE) of 0.728 $\frac{\mathrm{cal}}{\mathrm{hr}.\mathrm{kg}}$ for EE estimation for testing data. The independent RNNs have F1 scores of 99.64% for PA and 98.83% for APS, and an RMSE of 0.666 $\frac{\mathrm{cal}}{\mathrm{hr}.\mathrm{kg}}$ for EE estimation. The results indicate that a multi-task RNN can effectively interpret the signals from wearable sensors. Additionally, we developed individual and multi-task extreme gradient boosting (XGBoost) for separate and simultaneous classification of PA types and APS types. Multi-task XGBoost achieved F1 scores of 99.89% and 98.31% for the classification of PA types and APS types, respectively, while the independent XGBoost achieved F1 scores of 99.68% and 96.77%, respectively. The results indicate that both multi-task RNN and XGBoost can be used for the detection and classification of PA and APS without loss of performance with respect to individual separate classification systems. People with diabetes can achieve better outcomes and quality of life by including physical activity and psychological stress assessments in treatment decision-making. Full article

Three-phase induction motors (IMs) are considered an essential part of electromechanical systems. Despite the fact that IMs operate efficiently under harsh environments, there are many cases where they indicate deterioration. A crucial type of fault that must be diagnosed early is stator winding faults as a consequence of short circuits. Motor current signature analysis is a promising method for the failure diagnosis of power systems. Wavelets are ideal for both time- and frequency-domain analyses of the electrical current of nonstationary signals. In this paper, the signal data are obtained from simulations of an induction motor for various stator winding fault conditions and one normal operating condition. Our main contribution is the presentation of a fault diagnostic system based on a hybrid discrete wavelet–CNN method. First, the time series of the currents are processed with discrete wavelet analysis. In this way, the harmonic frequencies of the faults are successfully captured, and features can be extracted that comprise valuable information. Next, the features are fed into a convolutional neural network (CNN) model that achieves competitive accuracy and needs significantly reduced training time. The motivations for integrating CNNs into wavelet analysis results for fault diagnosis are as follows: (1) the monitoring is automated, as no human operators are needed to examine the results; (2) deep learning algorithms have the potential to identify even more indistinguishable and complex faults than those that human eyes could. Full article

When a fault occurs on the transmission line, the relay should send the faulty signal to the circuit breaker to trip or isolate the line. Timely detection is integral to fault protection and the management of transmission lines in power systems. This paper focuses on using the threshold current and voltage to reduce the time of delay and trip time of the instantaneous overcurrent relay protection for a 330 kV transmission line. The wavelet transforms toolbox from MATLAB and a Simulink model were used to design the model to detect the threshold value and the coordination time for the backup relay to trip if the primary relay did not operate or clear the fault on time. The difference between the proposed model and the model without the threshold value was analysed. The simulated result shows that the trip time of the two relays demonstrates a fast and precise trip time of 60% to 99.87% compared to other techniques used without the threshold values. The proposed model can eliminate the trial-and-error in programming the instantaneous overcurrent relay setting for optimal performance. Full article

In recent years, tremendous advances have been made in the design and applications of wireless networks and embedded sensors. The combination of sophisticated sensors with wireless communication has introduced new applications, which can simplify humans’ daily activities, increase independence, and improve quality of life. Although numerous positioning techniques and wireless technologies have been introduced over the last few decades, there is still a need for improvements, in terms of efficiency, accuracy, and performance for the various applications. Localization importance increased even more recently, due to the coronavirus pandemic, which made people spend more time indoors. Improvements can be achieved by integrating sensor fusion and combining various wireless technologies for taking advantage of their individual strengths. Integrated sensing is also envisaged in the coming technologies, such as 6G. The primary aim of this review article is to discuss and evaluate the different wireless positioning techniques and technologies available for both indoor and outdoor localization. This, in combination with the analysis of the various discussed methods, including active and passive positioning, SLAM, PDR, integrated sensing, and sensor fusion, will pave the way for designing the future wireless positioning systems. Full article

Motor imagery (MI)-based brain–computer interfaces (BCI) have shown increased potential for the rehabilitation of stroke patients; nonetheless, their implementation in clinical practice has been restricted due to their low accuracy performance. To date, although a lot of research has been carried out in benchmarking and highlighting the most valuable classification algorithms in BCI configurations, most of them use offline data and are not from real BCI performance during the closed-loop (or online) sessions. Since rehabilitation training relies on the availability of an accurate feedback system, we surveyed articles of current and past EEG-based BCI frameworks who report the online classification of the movement of two upper limbs in both healthy volunteers and stroke patients. We found that the recently developed deep-learning methods do not outperform the traditional machine-learning algorithms. In addition, patients and healthy subjects exhibit similar classification accuracy in current BCI configurations. Lastly, in terms of neurofeedback modality, functional electrical stimulation (FES) yielded the best performance compared to non-FES systems. Full article

This paper deals with the implementation of an adaptive speed controller applied for two electrical machines coupled by a long shaft. The two main parts of the study are the synthesis of the neural adaptive controller and hardware implementation using a low-cost system based on an STM Discovery board. The framework between the control system, the power converters, and the motors is established with an ARM device. A radial basis function neural network (RBFNN) is used as an adaptive speed controller. The net coefficients are updated (online mode) to ensure high dynamics of the system and correct work under disturbance. The results contain transients achieved in simulations and experimental tests. Full article