Motor imagery (MI) signals recorded by electroencephalography provide the most practical basis for conceiving brain-computer interfaces (BCI). These interfaces offer a high degree of freedom. This helps people with motor disabilities communicate with the device by tackling a sequence of motor imagery tasks. However, the extracting user-specific features and increasing the accuracy of the classifier remain as difficult tasks in MI-based BCI. In this work, we propose a new method using artificial neural network (ANN) enhancing the performance of the motor imagery classification. Feature extraction techniques, like time domain parameters, band power features, signal power features, and wavelet packet decomposition (WPD), are studied and compared. Four classification algorithms are implemented which are Quadratic Discriminant Analysis, k-Nearest Neighbors, Linear Discriminant Analysis, and proposed ANN architecture. We added Batch Normalization layers to the proposed ANN architecture to improve the learning time and accuracy of the neural network. These layers also alleviate the effect of weight initialization and the addition of a regularization effect on the network. Our proposed method using ANN architecture achieves 0.5545 of kappa and 58.42% of accuracy on the BCI Competition IV-2a dataset. Our results show that the modified ANN method, with frequency and spatial features extracted by WPD and Common Spatial Pattern, respectively, offers a better classification compared to other current methods.

The photonic crystal fiber (PCF) based plasmonic sensors have drawn incredible attention from researchers in many research disciplines due to their versatility, quick response, label-free detection, design freedom, and low weight. Here, a gold-coated hexagonal lattice PCF sensor having an external analyte detection facility is proposed using the surface plasmon resonance (SPR) technology. The design and performance optimization of the proposed sensor has been completed using commercially available COMSOL Multiphysics 5.5. Firstly, design parameters were optimized by varying one parameter at a time then the sensor performance was calculated using well-known intensity and wavelength interrogation techniques in the analyte refractive index (RI) ranging from 1.33–1.405. Excellent amplitude sensitivity (AS), (609.023 RIU^-1 ), and wavelength sensitivity (WS), (18,000 nm/RIU), along with an outstanding resolution ( 5.56 × 10^-6 RIU), are attained with optimum design parameters. Secondly, the sensor performance is carried out with four bacteria (common pathogens in water) such as Enterococcus faecalis, Escherichia Coli (E. coli), Vibrio Cholera, and Bacillus Anthracis, and the sensor exhibits tremendous WS (nm/RIU) and AS ( RIU^-1 ) of 7317.07 and 918.77, respectively. Owing to its straightforward design and high sensitivity, the proposed sensor can be effectively applied in any healthcare system to ensure safe drinking water.

The using of Electroencephalography (EEG) signals for motor imagery (MI) has recently gained significant attention due to their remarkable ability to detect an individual’s intention to perform specific actions. MI signals have proven useful in enabling individuals with disabilities to control devices such as wheelchairs through neural commands, and have even expanded into applications like autonomous driving. Therefore, ensuring accurate classification of MI tasks from EEG signals is crucial for the development of a reliable Brain-Computer Interface (BCI) system. This article introduces a novel approach to classifying MI tasks using Deep Learning (DL) techniques. The proposed methodology encompasses several steps, including data preprocessing, feature extraction using Common Spatial Pattern (CSP) and Wavelet Packet Decomposition (WPD), and the evaluation of four distinct classifiers. These classifiers involve combinations of two, three, four, and five Convolutional Neural Networks (CNNs). Empirical evaluations highlight the effectiveness of employing five CNNs, which yield the most favorable results. Our approach demonstrates promising performance metrics such as accuracy, precision, recall, and F1 score. Specifically, the method achieves accuracy, precision, recall, and F1 score values of 64.75

Electroencephalography (EEG) motor imagery (MI) signals has recently attracted a great deal of attention as these signals encrypt a person's desire of executing a command. MI signals are used to assist disabled people and even for autonomous driving through some control devices like wheelchairs just by thinking about it. Therefore, an accurate MI tasks classification from EEG signals is cricial to get a reliable Brain Computer Interface (BCI) system. In this paper, we proposed a new method of classifying MI tasks based on Convolutional Neural Network (CNN) methods. We applied a simple preprocessing to the data followed by a feature extraction step using Common Spatial Pattern (CSP) to extract spatial features and Wavelet Packet Decomposition (WPD) to extract frequency-time features. We then tested our four proposed models: CNN, CNN+LSTM, CNN-SVM and CNN+LSTM-SVM using BCI Competition IV 2a dataset. The obtained experimental results show that the proposed CNN-SVM gives the best results. Our results are really promising achieving interesting accuracy, precision, recall, and F1 score of 64.33%, 65.05%, 66.11%, et 64.11%, respectively.

Epilepsy is a common neurological disorder that affects millions of people worldwide, and many patients do not respond well to traditional anti-epileptic drugs. To improve the lives of these patients, there is a need to develop accurate methods for predicting epileptic seizures. Seizure prediction involves classifying preictal and interictal states, which is a challenging classification problem. Deep learning techniques, such as convolutional neural networks (CNNs), have shown great promise in analyzing and classifying EEG signals related to epilepsy. In this study, we proposed four deep learning models (S-CNN, Modif-CNN, CNN-SVM, and Comb-2CNN) to classify epilepsy states, which we evaluated on an iEEG dataset from the American Epilepsy Society database. Our models achieved high accuracy rates, with the S-CNN and Comb-2CNN models achieving 96.53%, CNN-SVM achieving 96.99%, and the Modif-CNN model achieving 97.96% in our experiments. These findings suggest that deep learning models could be an effective approach for classifying epilepsy states and could potentially improve seizure prediction methods, ultimately enhancing the quality of life for people with epilepsy.

Infectious diseases pose a threat to human life and could affect the whole world in a very short time. Corona-2019 virus disease (COVID-19) is an example of such harmful diseases. COVID-19 is a pandemic of an emerging infectious disease, called coronavirus disease 2019 or COVID-19, caused by the coronavirus SARS-CoV-2, which first appeared in December 2019 in Wuhan, China, before spreading around the world on a very large scale. The continued rise in the number of positive COVID-19 cases has disrupted the health care system in many countries, creating a lot of stress for governing bodies around the world, hence the need for a rapid way to identify cases of this disease. Medical imaging is a widely accepted technique for early detection and diagnosis of the disease which includes different techniques such as Chest X-ray (CXR), Computed Tomography (CT) scan, etc. In this paper, we propose a methodology to investigate the potential of deep transfer learning in building a classifier to detect COVID-19 positive patients using CT scan and CXR images. Data augmentation technique is used to increase the size of the training dataset in order to solve overfitting and enhance generalization ability of the model. Our contribution consists of a comprehensive evaluation of a series of pre-trained deep neural networks: ResNet50, InceptionV3, VGGNet-19, and Xception, using data augmentation technique. The findings proved that deep learning is effective at detecting COVID-19 cases. From the results of the experiments it was found that by considering each modality separately, the VGGNet-19 model outperforms the other three models proposed by using the CT image dataset where it achieved 88.5% precision, 86% recall, 86.5% F1-score, and 87% accuracy while the refined Xception version gave the highest precision, recall, F1-score, and accuracy values which equal 98% using CXR images dataset. On the other hand, and by applying the average of the two modalities X-ray and CT, VGG-19 presents the best score which is 90.5% for the accuracy and the F1-score, 90.3% for the recall while the precision is 91.5%. These results enables to automatize the process of analyzing chest CT scans and X-ray images with high accuracy and can be used in cases where RT-PCR testing and materials are limited.

Coronavirus 2019 (COVID-19) is a highly transmissible and pathogenic virus caused by severe respiratory syndrome coronavirus 2 (SARS-CoV-2), which first appeared in Wuhan, China, and has since spread in the whole world. This pathology has caused a major health crisis in the world. However, the early detection of this anomaly is a key task to minimize their spread. Artificial intelligence is one of the approaches commonly used by researchers to discover the problems it causes and provide solutions. These estimates would help enable health systems to take the necessary steps to diagnose and track cases of COVID. In this review, we intend to offer a novel method of automatic detection of COVID-19 using tomographic images (CT) and radiographic images (Chest X-ray). In order to improve the performance of the detection system for this outbreak, we used two deep learning models: the VGG and ResNet. The results of the experiments show that our proposed models achieved the best accuracy of 99.35 and 96.77% respectively for VGG19 and ResNet50 with all the chest X-ray images.

One of the most prevalent and disabling neurologic disorders is epilepsy. Predicting epileptic seizures is a challenge to improve patients’ quality of life, as approximately 30% of them do not respond to anti-epileptic drugs. Currently, EEG investigations are used in deep learning networks, which have recently gained significant success. The efficient utilization of these signals, particularly in disease prediction, is critical in terms of both time and cost. Based on that, we suggested a robust automated technique for classifying epileptic states in this paper, which was evaluated using an iEEG dataset collected from the American Epilepsy Society database. Our strategy is to build two deep learning models: CNN and CNN-SVM. The experimental results show that the proposed method based on CNN presents the best score which is 97.41% for accuracy, 97% for the F1 score, and 97.5% for the recall and precision.

Lung disease is a major health problem due to air pollution, smoking, and an aging population. For this reason, early and accurate detection is essential to achieve overall control of the disease and greatly increase the chances of successful medical treatment. This study proposes two convolutional neural network (CNN) models that rely on transfer learning to classify and detect the presence of pneumonia from a collection of chest X-ray (or CXR) images belonging to 4 classes. The data augmentation algorithm is used to increase the size of the training dataset in order to reduce overfitting and improve the model's generalization capacity.Using the data augmentation algorithm, we conducted a detailed evaluation of two pre-trained deep neural networks: VGGNet-16 and MobileNet. Deep learning (DL) is excellent in detecting infections, according to the findings. The MobileNet model outperforms the VGGNet-16 model where it achieved 82% accuracy, 83.5% recall, and 82.5% F1 score, while VGGNet-16 version gave the highest precision value which equals 84.5% but accuracy, recall and F1 score were respectively equal to 80%, 76% and 79%. On the other hand, and by calculating the AUC of the two models, MobileNet presents the best score which is 95% while VGGNet-16 has a score of 94%.

We propose an electric field tunable nematic liquid crystal (NLC) infiltrated single-hole hollow fiber sensor for voltage measurement. Due to only an air hole, the proposed sensor got a straightforward structure, and the liquid-filling process will be uncomplicated. The addition of the gold wire successfully incorporated the surface plasmon resonance (SPR) phenomenon as a sensing methodology in the proposed sensor. Besides that, the use of metal wire instead of the metal film will reduce the complicacy associated with the acquisition of uniform film thickness. The sensor characterization and performance evaluation have been done using the finite element method (FEM) for a wide voltage range from 200V to 400V. The sensor exhibits wavelength sensitivity (WS) and linearity as high as 5 nm/V and 0.9935, respectively. In addition, maximum amplitude sensitivity (AS) and wavelength resolution ( R ) is attained of −353.46 RIU −1 and 0.02V, respectively. Due to its excellent performance with a wide sensing range, and a simple and compact structure, the proposed sensor can be used for voltage measurement in a sophisticated place.

: Brain-Computer Interfaces (BCIs) are systems that can help people with limited motor skills interact with their environment without the need for outside help. Therefore, the signal is representative of a motor area in the active brain system. It is used to recognize MI-EEG tasks via a deep learning techniques such as Convolutional Neural Network (CNN), which poses a potential problem in maintaining the integrity of frequency-time-space information and then the need for exploring the CNNs fusion. In this work, we propose a method based on the fusion of three CNN (3CNNs). Our proposed method achieves an interesting precision, recall, F1-score, and accuracy of 61.88%, 62.50%, 61.47%, 64.75% respectively when tested on the 9 subjects from the BCI Competition IV 2a dataset. The 3CNNs model achieved higher results compared to the state-of-the-art.

Recently, Electroencephalography (EEG) motor imagery (MI) signals have received increasing attention because it became possible to use these signals to encode a person’s intention to perform an action. Researchers have used MI signals to help people with partial or total paralysis, control devices such as exoskeletons, wheelchairs, prostheses, and even independent driving. Therefore, classifying the motor imagery tasks of these signals is important for a Brain-Computer Interface (BCI) system. Classifying the MI tasks from EEG signals is difficult to offer a good decoder due to the dynamic nature of the signal, its low signal-to-noise ratio, complexity, and dependence on the sensor positions. In this paper, we investigate five multilayer methods for classifying MI tasks: proposed methods based on Artificial Neural Network, Convolutional Neural Network 1 (CNN1), CNN2, CNN1 with CNN2 merged, and the modified CNN1 with CNN2 merged. These proposed methods use different spatial and temporal characteristics extracted from raw EEG data. We demonstrate that our proposed CNN1-based method outperforms state-of-the-art machine/deep learning techniques for EEG classification by an accuracy value of 68.77% and use spatial and frequency characteristics on the BCI Competition IV-2a dataset, which includes nine subjects performing four MI tasks (left/right hand, feet, and tongue). The experimental results demonstrate the feasibility of this proposed method for the classification of MI-EEG signals and can be applied successfully to BCI systems where the amount of data is large due to daily recording.

Brain-Computer Interfaces (BCI) based on Motor Imagery (MI) extract commands in real time and can be used to control a cursor, wheelchair, robot or prosthesis by performing only mental imaging tasks, such as imagining a movement of the right hand while the corresponding brain activity is measured and processed by the system. Because MI-based BCI offers a high degree of freedom, it helps people with motor disabilities communicate with the device by performing a sequence of MI tasks. Several techniques are being developed to improve the classification performance of the MI signals used in BCI. Most researches focused on improving methods for feature extraction and selection, but relied on linear classifiers for class prediction. In this paper, we investigate the use of ensemble learning methods to improve classification accuracy in a BCI paradigm based on 2-class MIs. We propose and compare eight combinations of classifiers on the BCI Competition III dataset IVb. The results obtained show that the combination of three classifiers: Radial Basis Function-Kernel Support Vector Machine (RBF-Kernel SVM), Linear Support Vector Machine (Linear SVM) and Decision Tree, gives the best value of kappa which is equal to 0.783. This combination can be successfully applied to BCI systems where the amount of data stems largely from daily recording.

Electroencephalogram (EEG) signals based on Motor Imagery (MI) are a widely used form of input in Brain Computer Interface (BCI). Although there are several ways to classify data, a question remains as to which method to use in EEG signals based on motor imagery. This article presents an attempt to reach the best classification method based on deep learning methods by comparing two models: Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM), on the same basic data set. The BCI Competition IV dataset 2a was used as the base dataset to test the two classification methods. Experimental results show that the proposed CNN model outperforms the LSTM model, with an accuracy value of 74%, and other stateof-the-art methods.

Classification of EEG signals based on motor imagery is an important task in Brain-Computer Interface (BCI). Deep learning approaches have been successfully used in several recent applications to learn features and classify different types of data. However, the number of researches using these approaches in BCI applications is very limited. In this paper, we aim at using the fusion of Convolutional Neural Networks (CNN) methods to improve the classification performance of EEG motor imagery signals in the framework of e-health Internet of Things. We propose and compare two classification methods based on the fusion of two CNNs. Our results show that the fusion of the CNNs with the Long Short-Term Memory (LSTM) layers offers a better classification performance compared to other state-of-the-art methods. The classification performance achieved by our proposed method using the BCI competition IV 2a dataset in terms of accuracy value is 61.68%. This method can be successfully applied to BCI systems where the amount of data is large due to daily recording.

Since being first detected in China, coronavirus disease 2019 (COVID-19) has spread rapidly across the world, triggering a global pandemic with no viable cure in sight. As a result, national responses have focused on the effective minimization of the spread. Border control measures and travel restrictions have been implemented in a number of countries to limit the import and export of the virus. The detection of COVID-19 is a key task for physicians. The erroneous results of early laboratory tests and their delays led researchers to focus on different options. Information obtained from computed tomography (CT) and radiological images is important for clinical diagnosis. Therefore, it is worth developing a rapid method of detection of viral diseases through the analysis of radiographic images. We propose a novel method of detection of COVID-19. The purpose is to provide clinical decision support to healthcare workers and researchers. The article is to support researchers working on early detection of COVID-19 as well as similar viral diseases.

The Red Palm Weevil (RPW) is one of the most dangerous pests of palms in the world. Among several techniques that have been applied to combat the RPW pest such as phytosanitation, chemical insecticides, pheromone traps and biological control, the use of microwave energy for heat disinfestation seems to be a promoting solution. Its main advantages are rapid heat transfer, volumetric and selective heating, speed of switching on and off and no pollution to the environment. This article presents the design of microwave antenna system for microwave disinfection of date palms application. The microwave system consists of a 3-D circular array of 16 Vivaldi elements. We present an electromagnetic-thermal model, including palm and adult/Larva RPW models, to test their thermal reactions for microwave heating. The 3-D numerical model shows the capability of the microwave system to heat the outer layer of the palm, and reach the RPW lethal temperature. Also, the research discusses the effect of varying the input power and treatment duration to control the RPW. This work provides a powerful tool to simulate the thermal distribution of the palm and RPW insects for different input cases; which help fight against the RPW.

In this work a novel design of an ultra-wideband and highly directive Vivaldi photoconductive antenna (PCA) is reported for the first time for the THz sensing and imaging applications. The optical-to-THz conversion efficiency for the enhanced directivity of the reported PCA is enhanced by adding a hemispherical silicon-based lens with the PCA gold electrode and quartz substrate (Epsilon r = 3.78, tan delta = 0.0001). The optimization of the antenna design parameters is performed in CST MWS for the frequency range of 1-6 THz. The design antenna has UWB -10 dB impedance and 3-dB AR bandwidths of 6 THz, maximum directivity of 10 dBi and maximum total radiation efficiency of > 40%.

In electroencephalogram (EEG) recordings, physiological and non-physiological artifacts pose many problems. Independent Component Analysis (ICA) is a widely used algorithm for removing different artifacts from EEG signals. It separates data in linearly Independent Components (IC). However, the evaluation and classification of the calculated ICs as an EEG or artifact is not currently automated which requires manual intervention to reject ICs with visually detected artifacts after decomposition. In this paper, we propose a new automated approach for artifacts detection using the ICA algorithm. The best result of mean square error was achieved using SOBI-ICA (Second Order Blind Identification) and ADJUST algorithms. Compared with the existing automated solutions, our approach is not limited to electrode configurations, number of EEG channels, or specific types of artifacts. It provides a practical tool, reliable, automatic, and real-time capable, which avoids the need for the time-consuming manual selection of ICs during artifacts rejection.

Brain-Computer Interface (BCI) systems are widely based on steady-state visual evoked potentials (SSVEP) detection using electroencephalography (EEG) signals. SSVEP-based BCIs are becoming attractive due to their higher signal-to-noise ratio (SNR) as well as faster information transfer rate (ITR). However, their performances are largely affected by the interference coming from the spontaneous EEG activities which intrinsically restrict their efficiency in distinguishing between SSVEPs and background EEG activities. In this paper, we introduce a new approach for the detection of SSVEP based on bispectral analysis to palliate the frequency-dependent bias. A COMB filter associated with a wavelet denoising filter is firstly used to minimize the noise while improving the SNR of phase signals. Next, the complementary orthogonal projections and the principle component analysis (PCA) are used to decompose the components related to SSVEPs and components related to brain activities. Finally, the bispectrum, a powerful tool for the analysis and the characterization of nonlinear properties of stochastic signals, is used to extract the features of the EEG signal benefiting from the information about the phase coupling of the signal components. The results of experiments, using two databases on five (or ten) subjects, show that the proposed approach significantly outperformed the standard CCA approach in distinguishing the target frequency and in average information transfer rate.