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
Fri Apr 28 2023
Journal Name
Mathematical Modelling Of Engineering Problems
Design Optimal Neural Network for Solving Unsteady State Confined Aquifer Problem
...Show More Authors

View Publication Preview PDF
Scopus (9)
Crossref (4)
Scopus Crossref
Publication Date
Sat Dec 01 2018
Journal Name
Al-khwarizmi Engineering Journal
Wireless Network Control System for Electro Stati Precipitator in Cement Plants
...Show More Authors

    Wireless control networks (WCNs), based on distributed control systems of wireless sensor and actuator networks, integrate four technologies: control, computer network and wireless communications. Electrostatic precipitator (ESP) in cement plants reduces the emissions from rotary kiln by 99.8% approximately. It is an important thing to change the existing systems (wireline) to wireless because of dusty and hazardous environments. In this paper, we designed a wireless control system for ESP using Truetime 2 beta 6 simulator, depending on the mathematical model that have been built using identification toolbox of Matlab v7.1.1. We also study the effect ofusing wireless network on performance and stability of the closed l

... Show More
View Publication Preview PDF
Crossref
Publication Date
Tue Nov 01 2016
Journal Name
Journal Of Economics And Administrative Sciences
Use Dynamic Bayesian network to estimate the reliability of Adamia Water Network
...Show More Authors

Abstract\

In this research, estimated the reliability of water system network in Baghdad was done. to assess its performance during a specific period. a fault tree through static and dynamic gates was belt and these gates represent logical relationships between the main events in the network and analyzed using dynamic Bayesian networks . As it has been applied Dynamic Bayesian networks estimate reliability by translating dynamic fault tree to Dynamic Bayesian networks and reliability of the system appreciated. As was the potential for the expense of each phase of the network for each gate . Because there are two parts to the Dynamic Bayesian networks and two part of gate (AND), which includes the three basic units of the

... Show More
View Publication Preview PDF
Crossref
Publication Date
Tue Feb 14 2023
Journal Name
Journal Of Educational And Psychological Researches
Analyzing the Literary Criticism Book Questions for High School Stage According to Bloom's Classification
...Show More Authors

Abstract

 The current research aims to identify the analysis of the questions for the book of literary criticism for the preparatory stage according to Bloom's classification. The research community consists of (34) exercises and (45) questions. The researcher used the method of analyzing questions and prepared a preliminary list that includes criteria that are supposed to measure exercises, which were selected based on Bloom's classification and the extant literature related to the topic. The scales were exposed to a jury of experts and specialists in curricula and methods of teaching the Arabic language. The scales obtained a complete agreement. Thus, it was adapted to become a reliable instrument in this

... Show More
View Publication Preview PDF
Publication Date
Wed Sep 23 2020
Journal Name
Artificial Intelligence Research
Hybrid approaches to feature subset selection for data classification in high-dimensional feature space
...Show More Authors

This paper proposes two hybrid feature subset selection approaches based on the combination (union or intersection) of both supervised and unsupervised filter approaches before using a wrapper, aiming to obtain low-dimensional features with high accuracy and interpretability and low time consumption. Experiments with the proposed hybrid approaches have been conducted on seven high-dimensional feature datasets. The classifiers adopted are support vector machine (SVM), linear discriminant analysis (LDA), and K-nearest neighbour (KNN). Experimental results have demonstrated the advantages and usefulness of the proposed methods in feature subset selection in high-dimensional space in terms of the number of selected features and time spe

... Show More
View Publication
Crossref
Publication Date
Wed Aug 24 2022
Journal Name
Journal Of Tikrit University For Humanities
A Training Program Based on Integrating Future Thinking Skills and Classroom Interaction Patterns for Mathematics Teachers and Providing Their Students with Creative Solution Skills
...Show More Authors

The research aims to recognize the impact of the training program based on integrating future thinking skills and classroom interaction patterns for mathematics teachers and providing their students with creative solution skills. To achieve the goal of the research, the following hypothesis was formulated: There is no statistically significant difference at the level (0.05) between the mean scores of students of mathematics teachers whose teachers trained according to the proposed training program (the experimental group) and whose teachers were not trained according to the proposed training program (the control group) in Pre-post creative solution skills test. Research sample is consisted of (31) teachers and schools were distribut

... Show More
View Publication
Crossref (1)
Crossref
Publication Date
Mon Jan 01 2024
Journal Name
Bio Web Of Conferences
An overview of machine learning classification techniques
...Show More Authors

Machine learning (ML) is a key component within the broader field of artificial intelligence (AI) that employs statistical methods to empower computers with the ability to learn and make decisions autonomously, without the need for explicit programming. It is founded on the concept that computers can acquire knowledge from data, identify patterns, and draw conclusions with minimal human intervention. The main categories of ML include supervised learning, unsupervised learning, semisupervised learning, and reinforcement learning. Supervised learning involves training models using labelled datasets and comprises two primary forms: classification and regression. Regression is used for continuous output, while classification is employed

... Show More
View Publication Preview PDF
Scopus (112)
Crossref (98)
Scopus Crossref
Publication Date
Mon Jan 01 2024
Journal Name
Ieee Access
Patient Monitoring System Based on Internet of Things: A Review and Related Challenges With Open Research Issues
...Show More Authors

View Publication
Scopus (63)
Crossref (60)
Scopus Crossref
Publication Date
Sun Apr 17 2016
Journal Name
Al-academy
Design trends of family dual-used in small spaces: محمد سعد الجميلي
...Show More Authors

Comes interest in the subject matter in the selection of the Family industry globally as one of the important industries which have developed a clear and significant in recent years, to look at these products and designs to their functional importance have appeared in recent years, the phenomenon of the small spaces because of housing Population density showed the need to find a spare Furniture fit these small spaces On this basis, determine the objective of this research is to arrive at a design techniques for dual-family employee for small spaces research sample included a double family manufactured in laboratories industry Furniture in Baghdad and local research sample includes family double Decker.Research focused on the first four c

... Show More
View Publication Preview PDF
Crossref
Publication Date
Sun Feb 01 2026
Journal Name
Agricultural Engineering
DEVELOPMENT AND EVALUATION OF A YOLO ALGORITHM-BASED ROBOTIC SPRAYER FOR REAL-TIME WEED DETECTION
...Show More Authors
Abstract<p> Weed control with chemicals is a challenging process that should be performed in a rational way to reduce their negative impact on the surrounding environment. The growth of artificial intelligence algorithms encourages researchers to develop smart spraying robots that detect and spray weeds and distinguish them from the main crop which leads to sustainable use of these chemicals and achieves some of the sustainable development goals. However, few studies are available to comprehensively compare different versions of YOLO algorithm to detect weed. In this research, seven versions of YOLO algorithms were evaluated for their performance to detect and spray four t</p> ... Show More
View Publication
Scopus Crossref