Autism spectrum disorder (ASD) is a type of neurodevelopmental disorder with core impairments in the social relationships, communication, imagination, or flexibility of thought and restricted repertoire of activity and interest. In this work, a new computer aided diagnosis (CAD) of autism based on electroencephalography (EEG) signal analysis is investigated. The proposed method is based on discrete wavelet transform (DWT), entropy (En), and artificial neural network (ANN). DWT is used to decompose EEG signals into approximation and details coefficients to obtain EEG subbands. The feature vector is constructed by computing Shannon entropy values from each EEG subband. ANN classifies the corresponding EEG signal into normal or autistic based on the extracted features. The experimental results show the effectiveness of the proposed method for assisting autism diagnosis. A receiver operating characteristic (ROC) curve metric is used to quantify the performance of the proposed method. The proposed method obtained promising results tested using real dataset provided by King Abdulaziz Hospital, Jeddah, Saudi Arabia.
Analysis of electroencephalogram (EEG) signals is essential because it is an efficient method to diagnose neurological brain disorders. In this work, a single system is developed to diagnose one or two neurological diseases at the same time (two-class mode and three-class mode). For this purpose, different EEG feature-extraction and classification techniques are investigated to aid in the accurate diagnosis of neurological brain disorders: epilepsy and autism spectrum disorder (ASD). Two different modes, single-channel and multi-channel, of EEG signals are analyzed for epilepsy and ASD. The independent components analysis (ICA) technique is used to remove the artifacts from EEG dataset. Then, the EEG dataset is segmented and filtered to remove noise and interference using an elliptic band-pass filter. Next, the EEG signal features are extracted from the filtered signal using a discrete wavelet transform (DWT) to decompose the filtered signal to its sub-bands delta, theta, alpha, beta and gamma. Subsequently, five statistical methods are used to extract features from the EEG sub-bands: the logarithmic band power (LBP), standard deviation, variance, kurtosis, and Shannon entropy (SE). Further, the features are fed into four different classifiers, linear discriminant analysis (LDA), support vector machine (SVM), k-nearest neighbor (KNN), and artificial neural networks (ANNs), to classify the features corresponding to their classes. The combination of DWT with SE and LBP produces the highest accuracy among all the classifiers. The overall classification accuracy approaches 99.9% using SVM and 97% using ANN for the three-class single-channel and multi-channel modes, respectively.
Hybrid energy systems (HESs) comprising photovoltaic (PV) arrays and wind turbines (WTs) are remarkable solutions for electrifying remote areas. These areas commonly fulfil their energy demands by means of a diesel genset (DGS). In the present study, a novel computational intelligence algorithm called supply-demand-based optimization (SDO) is applied to the HES sizing problem based on long-term cost analysis. The effectiveness of SDO is investigated, and its performance is compared with that of the genetic algorithm (GA), particle swarm optimization (PSO), gray wolf optimizer (GWO), grasshopper optimization algorithm (GOA), flower pollination algorithm (FPA), and big-bang-big-crunch (BBBC) algorithm. Three HES scenarios are implemented using measured solar radiation, wind speed, and load profile data to electrify an isolated village located in the northern region of Saudi Arabia. The optimal design is evaluated on the basis of technical (loss of power supply probability [LPSP]) and economic (annualized system cost [ASC]) criteria. The evaluation addresses two performance indicators: surplus energy and the renewable energy fraction (REF). The results reveal the validity and superiority of SDO in determining the optimal sizing of an HES with a higher convergence rate, lower ASC, lower LPSP, and higher REF than that of the GA, PSO, GWO, GOA, FPA, and BBBC algorithms. The performance analysis also reveals that an HES comprising PV arrays, WTs, battery banks, and DGS provides the best results: 238.
Parkinson’s disease (PD) is a very common brain abnormality that affects people all over the world. Early detection of such abnormality is critical in clinical diagnosis in order to prevent disease progression. Electroencephalography (EEG) is one of the most important PD diagnostic tools since this disease is linked to the brain. In this study, novel efficient common spatial pattern-based approaches for detecting Parkinson’s disease in two cases, off–medication and on–medication, are proposed. First, the EEG signals are preprocessed to remove major artifacts before spatial filtering using a common spatial pattern. Several features are extracted from spatially filtered signals using different metrics, namely, variance, band power, energy, and several types of entropy. Machine learning techniques, namely, random forest, linear/quadratic discriminant analysis, support vector machine, and k-nearest neighbor, are investigated to classify the extracted features. The impacts of frequency bands, segment length, and reduction number on the results are also investigated in this work. The proposed methods are tested using two EEG datasets: the SanDiego dataset (31 participants, 93 min) and the UNM dataset (54 participants, 54 min). The results show that the proposed methods, particularly the combination of common spatial patterns and log energy entropy, provide competitive results when compared to methods in the literature. The achieved results in terms of classification accuracy, sensitivity, and specificity in the case of off-medication PD detection are around 99%. In the case of on-medication PD, the results range from 95% to 98%. The results also reveal that features extracted from the alpha and beta bands have the highest classification accuracy.
Hybrid energy systems (HESs) are becoming popular for electrifying remote and rural regions to overcome the conventional energy generation system shortcomings and attain favorable technical and economic benefits. An optimal sizing of an autonomous HES consisting of photovoltaic technology, wind turbine generator, battery bank, and diesel generator is achieved by employing a new soft computing/metaheuristic algorithm called manta ray foraging optimizer (MRFO). This optimization problem is implemented and solved by employing MRFO based on minimizing the annualized system cost (ASC) and enhancing the system reliability in order to supply an off-grid northern area in Saudi Arabia. The hourly wind speed, solar irradiance, and load behavior over one year are used in this optimization problem. As for result verification, the MRFO is compared with five other soft computing algorithms, which are particle swarm optimization (PSO), genetic algorithm (GA), grasshopper optimization algorithm (GOA), big-bang-big-crunch (BBBC) algorithm, and Harris hawks optimization (HHO). The findings showed that the MRFO algorithm converges faster than all other five soft computing algorithms followed by PSO, and GOA, respectively. In addition, MRFO, PSO, and GOA can follow the optimal global solution while the HHO, GA and BBBC may fall into the local solution and take a longer time to converge. The MRFO provided the optimum sizing of the HES at the lowest ASC (USD 104,324.1), followed by GOA (USD 104,347.7) and PSO (USD 104,342.2) for a 0% loss of power supply probability. These optimization findings confirmed the supremacy of the MRFO algorithm over the other five soft computing techniques in terms of global solution capture and the convergence time.
Large-scale photovoltaic system (PV) installation can affect power system operation, stability, and reliability because of the non-linear characteristic of the PV system installation. DC/AC and DC/DC converters are the major devices use in connecting PV into the grid. These converters are liable to power quality problem if the proper control mechanism is not adopted. This study presents an optimal control technique to improve dynamic operation of PV grid-connected system. An optimal control method with use of Manta ray foraging optimization (MRFO), is implemented as a control strategy for tuning the proportionalintegral (PI) controllers of DC/DC and DC/AC converters for the integration of the PV system into the grid. The MRFO is chosen because of its ease of implementation and requirement of less adjusting parameters. The effectiveness of the proposed technique is studied under irradiance variation. The obtained results demonstrate the superior performance of the MRFO over five other metaheuristic algorithms (i.e., grey wolf optimization, whale optimization, grasshopper optimization, atom search optimization, and salp swarm algorithm) in terms of convergence rate and optimal global solution capture. The entire simulation model is established using MATLAB editor and Simulink. The acquired transient result shows the functionality and viability of the MRFO approach. INDEX TERMS Optimal control; power system dynamics; MRFO optimization; PV system. NOMENCLATURE Variables Ideality constant V DC_REF Reference voltage of dc-link a i Acceleration V DC ripple Ripple voltage C Dc-link capacitor V mpp Desired maximum voltage c 1 , c 2 , c 3 , r ⃗ 1 , r ⃗ 2 Random numbers V t Array thermal voltage d Drift factor V pv Photovoltaic voltage D ⃗ ⃗⃗ , A ⃗ ⃗⃗ , C ⃗⃗ Coefficient vectors Synchronous frequency dq0 Direct-quadrature-zero X ⃗ ⃗⃗ p (k) Wolves location E d Phase voltage of direct-axis X p (t) Vector position of the prey F i Reaction force Abbreviations F ij i Interaction force f s Switching frequency
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.