Preferred Language
Articles
/
QHgTxKABuRolNscLv_Oa
EEG-ChTABNet: A Dual-Branch Channel-Wise Transformer with Gated Attention-Branch Network for EEG-Based Classification of Dementia
...Show More Authors

Background/Objectives: Early and accurate discrimination of neurological conditions, dementia, stroke and healthy aging, remains a critical clinical challenge. Electroencephalography (EEG) is a non-invasive measure of brain dynamics and entropy-based features obtained from multichannel EEG have shown strong discriminative ability. However, existing deep learning approaches do not sufficiently address the combined challenges of small clinical cohorts and high-dimensional entropy feature spaces. In this study, a novel architecture is proposed for multi-class neurological EEG classification under extreme small-sample conditions. Methods: A novel dual-branch Channel-wise Transformer and Attention-Branch Network (EEG-ChTABNet) are pr to classify 19-channel EEG entropy features into three classes (dementia, stroke, healthy control; N = 45; 15 per class). The architecture suggests four new designs. First, the Channel Importance Attention (CIA) block, which adaptively learns to re-weight the importance of electrodes via squeeze-excitation. Second, the dual-branch encoder, which combines the global multi-head self-attention with the local depthwise-separable convolution. Third, the gated sigmoid fusion mechanism. Fourth, the bottleneck residual classification head, to solve overfitting. Eight entropy feature sets: Amplitude-Aware Permutation Entropy (AAPE), Attention Entropy (AttEn), Dispersion Entropy (DisEn), Distribution Entropy (DistrEn), Fluctuation-based Dispersion Entropy (FDispEn), Fuzzy Entropy (FuzEn), Linear Gaussian Estimation of the Conditional Entropy (LinEn), and Symbolic Dynamics (SyDy) were evaluated individually with stratified 5-fold cross-validation on within-fold SMOTE augmentation. Results: EEG-ChTABNet consistently outperformed the baseline Transformer on all 8 feature sets. DisEn and SyDy features yielded peak classification accuracy of 73.3% (AUC: 0.823 and 0.857, respectively) compared to the corresponding baseline of 57.8% and 55.6%. SyDy achieved the best overall AUC of 0.857 and the dementia detection sensitivity was up to 86.7% over multiple feature sets. Conclusions: EEG-ChTABNet shows the effectiveness of channel-adaptive, dual-branch Transformer Designs for EEG-based neurological classification from Small-Sample Entropy Feature Data, and Identifying SyDy and DisEn as the Most Discriminative Feature Representations for Three-Class Neurological EEG Classification.

Scopus Crossref
View Publication
Publication Date
Wed Jul 01 2026
Journal Name
Journal Of Energy Storage
Novel multi-lobed tube designs for efficient latent thermal energy storage: A comprehensive study of single and dual-tube configurations
...Show More Authors

View Publication
Scopus Crossref
Publication Date
Tue Sep 01 2020
Journal Name
Journal Of Engineering
An Adaptive Digital Neural Network-Like-PID Control Law Design for Fuel Cell System Based on FPGA Technique
...Show More Authors

This paper proposes an on-line adaptive digital Proportional Integral Derivative (PID) control algorithm based on Field Programmable Gate Array (FPGA) for Proton Exchange Membrane Fuel Cell (PEMFC) Model. This research aims to design and implement Neural Network like a digital PID using FPGA in order to generate the best value of the hydrogen partial pressure action (PH2) to control the stack terminal output voltage of the (PEMFC) model during a variable load current applied. The on-line Particle Swarm Optimization (PSO) algorithm is used for finding and tuning the optimal value of the digital PID-NN controller (kp, ki, and kd) parameters that improve the dynamic behavior of the closed-loop digital control fue

... Show More
View Publication Preview PDF
Crossref (1)
Crossref
Publication Date
Sun Oct 05 2025
Journal Name
Mesopotamian Journal Of Computer Science
DGEN: A Dynamic Generative Encryption Network for Adaptive and Secure Image Processing
...Show More Authors

Cyber-attacks keep growing. Because of that, we need stronger ways to protect pictures. This paper talks about DGEN, a Dynamic Generative Encryption Network. It mixes Generative Adversarial Networks with a key system that can change with context. The method may potentially mean it can adjust itself when new threats appear, instead of a fixed lock like AES. It tries to block brute‑force, statistical tricks, or quantum attacks. The design adds randomness, uses learning, and makes keys that depend on each image. That should give very good security, some flexibility, and keep compute cost low. Tests still ran on several public image sets. Results show DGEN beats AES, chaos tricks, and other GAN ideas. Entropy reached 7.99 bits per pix

... Show More
View Publication
Scopus Crossref
Publication Date
Sat Oct 22 2022
Journal Name
Aro-the Scientific Journal Of Koya University
Classification of Different Shoulder Girdle Motions for Prosthesis Control Using a Time-Domain Feature Extraction Technique
...Show More Authors

Abstract—The upper limb amputation exerts a significant burden on the amputee, limiting their ability to perform everyday activities, and degrading their quality of life. Amputee patients’ quality of life can be improved if they have natural control over their prosthetic hands. Among the biological signals, most commonly used to predict upper limb motor intentions, surface electromyography (sEMG), and axial acceleration sensor signals are essential components of shoulder-level upper limb prosthetic hand control systems. In this work, a pattern recognition system is proposed to create a plan for categorizing high-level upper limb prostheses in seven various types of shoulder girdle motions. Thus, combining seven feature groups, w

... Show More
View Publication Preview PDF
Scopus (6)
Crossref (3)
Scopus Clarivate Crossref
Publication Date
Tue Feb 01 2022
Journal Name
Int. J. Nonlinear Anal. Appl.
Finger Vein Recognition Based on PCA and Fusion Convolutional Neural Network
...Show More Authors

Finger vein recognition and user identification is a relatively recent biometric recognition technology with a broad variety of applications, and biometric authentication is extensively employed in the information age. As one of the most essential authentication technologies available today, finger vein recognition captures our attention owing to its high level of security, dependability, and track record of performance. Embedded convolutional neural networks are based on the early or intermediate fusing of input. In early fusion, pictures are categorized according to their location in the input space. In this study, we employ a highly optimized network and late fusion rather than early fusion to create a Fusion convolutional neural network

... Show More
Publication Date
Wed Aug 31 2022
Journal Name
International Journal Of Intelligent Engineering And Systems
Performance Evaluation Based on Multi-UAV in Airborne Computer Network System
...Show More Authors

View Publication
Scopus (5)
Crossref (1)
Scopus Crossref
Publication Date
Sun Feb 03 2019
Journal Name
Journal Of Accounting And Financial Studies ( Jafs )
Effect of The Mental image Building Dimensions for The Company to Aattract Attention of Iraqi Consumers for local Products: Exploratory Study
...Show More Authors

The survey showed sample opinions of officials in the general company for vegetable oils industry, and the statement of the order of the effect of these dimensions depending on the degree of importance, the questionnaire was used as a key tool in collecting data and information of the sample consisted of 30 officials, arithmetic mean, standard deviation, percentages, Spearman correlation coefficient and the global statistical analysis as a statistical methods that based on statistical program (SPSS), The researcher came to several conclusions, most important that there is high agreement by the respondents of the importance of the dimensions of building a mental picture of the company and to attract the consumer's attention, Also research

... Show More
View Publication Preview PDF
Crossref
Publication Date
Tue Feb 20 2018
Journal Name
Reporters, Markers, Dyes, Nanoparticles, And Molecular Probes For Biomedical Applications X
Dual-radiolabeled nanoparticle probes for depth-independent in vivo imaging of enzyme activation
...Show More Authors

View Publication
Scopus Clarivate Crossref
Publication Date
Wed Dec 25 2019
Journal Name
Journal Of Engineering
Link Failure Recovery for a Large-Scale Video Surveillance System using a Software-Defined Network
...Show More Authors

The software-defined network (SDN) is a new technology that separates the control plane from data ‎plane for the network devices. One of the most significant issues in the video ‎surveillance system is the link failure. When the path failure occurs, the monitoring center cannot receive the ‎video from the cameras. In this paper, two methods are proposed to solve this problem.  The first ‎method uses the Dijkstra algorithm to re-find the path at the source node switch. The second method ‎uses the Dijkstra algorithm to re-find the path at the ingress node switch (or failed link).

... Show More
View Publication Preview PDF
Crossref (1)
Crossref
Publication Date
Sun Dec 01 2019
Journal Name
Al-khwarizmi Engineering Journal
Improving the Network Lifetime in Wireless Sensor Network for Internet of Thing Applications
...Show More Authors

Mobile Wireless sensor networks have acquired a great interest recently due to their capability to provide good solutions and low-priced in multiple fields. Internet of Things (IoT) connects different technologies such as sensing, communication, networking, and cloud computing. It can be used in monitoring, health care and smart cities. The most suitable infrastructure for IoT application is wireless sensor networks. One of the main defiance of WSNs is the power limitation of the sensor node. Clustering model is an actual way to eliminate the inspired power during the transmission of the sensed data to a central point called a Base Station (BS). In this paper, efficient clustering protocols are offered to prolong network lifetime. A kern

... Show More
View Publication Preview PDF
Crossref (5)
Crossref