{"title":"EEG- symnet:基于多通道EEG信号的精神分裂症诊断,基于通道再校准和对称时空变压器网络","authors":"Naif Alsharabi , Rakesh Kumar Mahendran , Gharbi Alshammari","doi":"10.1016/j.jestch.2025.102116","DOIUrl":null,"url":null,"abstract":"<div><div>Schizophrenia is a severe mental disorder characterized by distorted thinking, perceptions, emotions, and behavior, which can significantly impair an individual’s ability to function in daily life. Early and effective diagnosis is crucial, as it enables timely intervention, which can improve outcomes and reduce the burden on patients and healthcare systems. Existing research in schizophrenia diagnosis often faces challenges related to the use of single-channel frequency EEG signals, which can overlook critical information provided by multi-channel data and limit the model’s ability to accurately capture the spatial and temporal dynamics of brain activity. In our proposed work, we introduce a novel model named EEG-SymNet: Spatial-Temporal Channel Recalibration Network for Schizophrenia Diagnosis using EEG signals, designed to enhance schizophrenia diagnosis through the utilization of multi-channel frequency EEG signals. Our approach begins with noise correction and power spectrum analysis to improve the quality of the EEG signals, ensuring a more reliable foundation for subsequent analysis. The pre-processed signals are then fed into our model, which consists of four main modules. First, Hierarchical Spatial Temporal Graph Neural Network (HSTG-Net) captures spatial features across channels, allowing for a comprehensive understanding of the EEG data. Next, the Multi-Channel Frequency Recalibration Module (CRFM) refines the model’s ability to interpret complex inter-channel relationships, enhancing inter-channel communication. Following this, Symmetric Transformer (Sym-T) enhances the learned temporal relations in the features, effectively capturing time-dependent patterns relevant to schizophrenia. Finally, a classifier layer is employed to provide accurate classification of the signals into schizophrenia and non-schizophrenia categories. The proposed STCR-Net model, which achieved an accuracy of 92.34 %, sensitivity of 91.78 %, specificity of 92.67 %, F1-Score of 0.92, and AUC of 0.95, demonstrating significant diagnostic improvements. Our proposed model addresses existing limitations and offers a robust framework for advancing the diagnosis of schizophrenia.</div></div>","PeriodicalId":48609,"journal":{"name":"Engineering Science and Technology-An International Journal-Jestech","volume":"69 ","pages":"Article 102116"},"PeriodicalIF":5.4000,"publicationDate":"2025-06-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"EEG-SymNet: multi-channel EEG signal-based schizophrenia diagnosis using channel recalibration and symmetric spatial temporal transformer network\",\"authors\":\"Naif Alsharabi , Rakesh Kumar Mahendran , Gharbi Alshammari\",\"doi\":\"10.1016/j.jestch.2025.102116\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><div>Schizophrenia is a severe mental disorder characterized by distorted thinking, perceptions, emotions, and behavior, which can significantly impair an individual’s ability to function in daily life. Early and effective diagnosis is crucial, as it enables timely intervention, which can improve outcomes and reduce the burden on patients and healthcare systems. Existing research in schizophrenia diagnosis often faces challenges related to the use of single-channel frequency EEG signals, which can overlook critical information provided by multi-channel data and limit the model’s ability to accurately capture the spatial and temporal dynamics of brain activity. In our proposed work, we introduce a novel model named EEG-SymNet: Spatial-Temporal Channel Recalibration Network for Schizophrenia Diagnosis using EEG signals, designed to enhance schizophrenia diagnosis through the utilization of multi-channel frequency EEG signals. Our approach begins with noise correction and power spectrum analysis to improve the quality of the EEG signals, ensuring a more reliable foundation for subsequent analysis. The pre-processed signals are then fed into our model, which consists of four main modules. First, Hierarchical Spatial Temporal Graph Neural Network (HSTG-Net) captures spatial features across channels, allowing for a comprehensive understanding of the EEG data. Next, the Multi-Channel Frequency Recalibration Module (CRFM) refines the model’s ability to interpret complex inter-channel relationships, enhancing inter-channel communication. Following this, Symmetric Transformer (Sym-T) enhances the learned temporal relations in the features, effectively capturing time-dependent patterns relevant to schizophrenia. Finally, a classifier layer is employed to provide accurate classification of the signals into schizophrenia and non-schizophrenia categories. The proposed STCR-Net model, which achieved an accuracy of 92.34 %, sensitivity of 91.78 %, specificity of 92.67 %, F1-Score of 0.92, and AUC of 0.95, demonstrating significant diagnostic improvements. Our proposed model addresses existing limitations and offers a robust framework for advancing the diagnosis of schizophrenia.</div></div>\",\"PeriodicalId\":48609,\"journal\":{\"name\":\"Engineering Science and Technology-An International Journal-Jestech\",\"volume\":\"69 \",\"pages\":\"Article 102116\"},\"PeriodicalIF\":5.4000,\"publicationDate\":\"2025-06-20\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Engineering Science and Technology-An International Journal-Jestech\",\"FirstCategoryId\":\"5\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S2215098625001715\",\"RegionNum\":2,\"RegionCategory\":\"工程技术\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"ENGINEERING, MULTIDISCIPLINARY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Engineering Science and Technology-An International Journal-Jestech","FirstCategoryId":"5","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2215098625001715","RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ENGINEERING, MULTIDISCIPLINARY","Score":null,"Total":0}
EEG-SymNet: multi-channel EEG signal-based schizophrenia diagnosis using channel recalibration and symmetric spatial temporal transformer network
Schizophrenia is a severe mental disorder characterized by distorted thinking, perceptions, emotions, and behavior, which can significantly impair an individual’s ability to function in daily life. Early and effective diagnosis is crucial, as it enables timely intervention, which can improve outcomes and reduce the burden on patients and healthcare systems. Existing research in schizophrenia diagnosis often faces challenges related to the use of single-channel frequency EEG signals, which can overlook critical information provided by multi-channel data and limit the model’s ability to accurately capture the spatial and temporal dynamics of brain activity. In our proposed work, we introduce a novel model named EEG-SymNet: Spatial-Temporal Channel Recalibration Network for Schizophrenia Diagnosis using EEG signals, designed to enhance schizophrenia diagnosis through the utilization of multi-channel frequency EEG signals. Our approach begins with noise correction and power spectrum analysis to improve the quality of the EEG signals, ensuring a more reliable foundation for subsequent analysis. The pre-processed signals are then fed into our model, which consists of four main modules. First, Hierarchical Spatial Temporal Graph Neural Network (HSTG-Net) captures spatial features across channels, allowing for a comprehensive understanding of the EEG data. Next, the Multi-Channel Frequency Recalibration Module (CRFM) refines the model’s ability to interpret complex inter-channel relationships, enhancing inter-channel communication. Following this, Symmetric Transformer (Sym-T) enhances the learned temporal relations in the features, effectively capturing time-dependent patterns relevant to schizophrenia. Finally, a classifier layer is employed to provide accurate classification of the signals into schizophrenia and non-schizophrenia categories. The proposed STCR-Net model, which achieved an accuracy of 92.34 %, sensitivity of 91.78 %, specificity of 92.67 %, F1-Score of 0.92, and AUC of 0.95, demonstrating significant diagnostic improvements. Our proposed model addresses existing limitations and offers a robust framework for advancing the diagnosis of schizophrenia.
期刊介绍:
Engineering Science and Technology, an International Journal (JESTECH) (formerly Technology), a peer-reviewed quarterly engineering journal, publishes both theoretical and experimental high quality papers of permanent interest, not previously published in journals, in the field of engineering and applied science which aims to promote the theory and practice of technology and engineering. In addition to peer-reviewed original research papers, the Editorial Board welcomes original research reports, state-of-the-art reviews and communications in the broadly defined field of engineering science and technology.
The scope of JESTECH includes a wide spectrum of subjects including:
-Electrical/Electronics and Computer Engineering (Biomedical Engineering and Instrumentation; Coding, Cryptography, and Information Protection; Communications, Networks, Mobile Computing and Distributed Systems; Compilers and Operating Systems; Computer Architecture, Parallel Processing, and Dependability; Computer Vision and Robotics; Control Theory; Electromagnetic Waves, Microwave Techniques and Antennas; Embedded Systems; Integrated Circuits, VLSI Design, Testing, and CAD; Microelectromechanical Systems; Microelectronics, and Electronic Devices and Circuits; Power, Energy and Energy Conversion Systems; Signal, Image, and Speech Processing)
-Mechanical and Civil Engineering (Automotive Technologies; Biomechanics; Construction Materials; Design and Manufacturing; Dynamics and Control; Energy Generation, Utilization, Conversion, and Storage; Fluid Mechanics and Hydraulics; Heat and Mass Transfer; Micro-Nano Sciences; Renewable and Sustainable Energy Technologies; Robotics and Mechatronics; Solid Mechanics and Structure; Thermal Sciences)
-Metallurgical and Materials Engineering (Advanced Materials Science; Biomaterials; Ceramic and Inorgnanic Materials; Electronic-Magnetic Materials; Energy and Environment; Materials Characterizastion; Metallurgy; Polymers and Nanocomposites)