Article
Acoustics
Supriya Supriya, Siuly Siuly, Hua Wang, Yanchun Zhang
Summary: The study proposes an innovative framework based on graph theory and complex network features for automated classification of EEG signals to detect epilepsy. By mapping time-series EEG signals to complex networks and extracting edge weight fluctuations, the proposed methodology achieves accuracies of 99% and 100% on two benchmark EEG databases.
Article
Computer Science, Information Systems
Lijuan Duan, Zeyu Wang, Yuanhua Qiao, Yue Wang, Zhaoyang Huang, Baochang Zhang
Summary: This study proposes an automatic method for detecting epileptic seizures based on deep metric learning, achieving high accuracy and specificity through one-dimensional convolutional embedding modules and stage-wise training strategy. It can effectively reduce the workload of neurologists.
IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS
(2022)
Article
Engineering, Biomedical
N. J. Sairamya, M. S. P. Subathra, Easter S. Suviseshamuthu, S. Thomas George
Summary: This study proposes a comprehensive feature representation using a one-dimensional quad binary pattern for effective epileptic focus localization in EEG signals. Different strategies are employed, including local pattern transformation, nonlinear feature computation, and histogram feature extraction, to classify non-focal and focal EEG signals with high accuracy.
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
(2021)
Article
Engineering, Biomedical
Daria Kleeva, Gurgen Soghoyan, Ilia Komoltsev, Mikhail Sinkin, Alexei Ossadtchi
Summary: This study proposes a novel biomimetic approach for automatic spike detection based on fast parametric curve matching (FPCM). Results from simulations show the robustness and high receiver operating characteristic AUC values of the FPCM method compared to conventional approaches. The FPCM technique demonstrates reliable detection of interictal events and localization of epileptogenic zones in real MEG and EEG data from human patients and rat ECoG data.
JOURNAL OF NEURAL ENGINEERING
(2022)
Article
Computer Science, Information Systems
Dwi Sunaryono, Riyanarto Sarno, Joko Siswantoro
Summary: This study proposes a classification method for automatic epilepsy detection from EEG signals. The method processes the original signals using DFT and DWT, and classifies the signals using GBMs fusion. A genetic algorithm is utilized to select important features. The experimental results demonstrate that the proposed GBMs fusion improves the classification performance and achieves perfect epilepsy detection.
JOURNAL OF KING SAUD UNIVERSITY-COMPUTER AND INFORMATION SCIENCES
(2022)
Article
Biochemistry & Molecular Biology
Ling Zhang, Xiaolu Wang, Jun Jiang, Naian Xiao, Jiayang Guo, Kailong Zhuang, Ling Li, Houqiang Yu, Tong Wu, Ming Zheng, Duo Chen
Summary: Clinical diagnosis of epilepsy relies on identifying interictal epileptiform discharge (IED) in electroencephalogram (EEG). Current manual interpretation of IED is time-consuming and expert-biased, leading to missed diagnosis and misdiagnosis. This study uses a convolutional neural network (CNN) framework for automatic IED detection, achieving high classification accuracy of up to 87% on long-term EEG data of pediatric patients with epilepsy. The research provides a reference for future application of deep learning in automatic IED detection.
FRONTIERS IN MOLECULAR BIOSCIENCES
(2023)
Article
Engineering, Biomedical
Supriya Supriya, Siuly Siuly, Hua Wang, Yanchun Zhang
Summary: Epilepsy, a chronic brain disorder, poses challenges in diagnosis and treatment. Graph-theory based automated epilepsy detection methods have emerged as a promising approach to analyze the complex nature of EEG signals and understand brain activity. This paper provides a comprehensive review of such methods, aiming to assist neurologists and researchers in improving epilepsy diagnosis and developing intelligent systems.
IEEE REVIEWS IN BIOMEDICAL ENGINEERING
(2023)
Article
Engineering, Multidisciplinary
Chengang Lyu, Yuxin Chen, Zhijuan Chen, Yuheng Liu, Zengguang Wang
Summary: The proposed epilepsy detection method based on GCPL shows high sensitivity, specificity, and accuracy in classifying clinical EEG signals, and can complete a test within 2 seconds to meet actual clinical needs.
Article
Engineering, Biomedical
Taku Shoji, Noboru Yoshida, Toshihisa Tanaka
Summary: This paper presents the development of an automated model using compact convolutional neural networks to detect abnormal patterns in EEGs related to epilepsy, achieving good performance on a large clinical dataset with fewer parameters.
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
(2021)
Article
Engineering, Biomedical
Jingwei Zhang, Christos Chatzichristos, Kaat Vandecasteele, Lauren Swinnen, Victoria Broux, Evy Cleeren, Wim Van Paesschen, Maarten De Vos
Summary: This paper presents an automatic annotation correction approach for training seizure detection algorithms using wearable EEG data. The approach improves the sensitivity and reduces false-positive detections compared to visually corrected and original seizure annotations.
JOURNAL OF NEURAL ENGINEERING
(2022)
Article
Mathematical & Computational Biology
Bei Liu, Hongzi Bai, Wei Chen, Huaquan Chen, Zhen Zhang
Summary: This paper proposes an automatic detection method for epilepsy based on improved refined composite multi-scale dispersion entropy (IRCMDE) and particle swarm algorithm optimization support vector machine (PSO-SVM). By introducing refined composite multi-scale dispersion entropy (RCMDE) and using local maximum calculation, the problem of information loss is solved. The entropy value is normalized to improve the robustness of characteristic parameters. Simulated results show that IRCMDE can eliminate information loss and weaken the entropy change caused by parameter selections, achieving more accurate recognition results compared to MDE-PSO-SVM and RCMDE-PSO-SVM methods.
MATHEMATICAL BIOSCIENCES AND ENGINEERING
(2023)
Article
Engineering, Electrical & Electronic
Weidong Dang, Dongmei Lv, Linge Rui, Ziang Liu, Guanrong Chen, Zhongke Gao
Summary: A novel method for epilepsy detection using multi-frequency multilayer brain network and deep learning is proposed. Experimental results show high accuracy, sensitivity, and specificity on CHB-MIT datasets, providing an efficient solution for characterizing complex brain states using multi-channel EEG signals.
IEEE SENSORS JOURNAL
(2021)
Article
Automation & Control Systems
Shixiang Sun, Tao Ren, Yanjie Xu
Summary: In this paper, a novel method for identifying influential spreaders based on potential edge weights is proposed. The method considers the degree and k-shell of a node and its neighbors as the weight of the edge directly connected to the node. The proposed method improves node mining accuracy and has approximately linear time complexity, making it suitable for large-scale networks.
TRANSACTIONS OF THE INSTITUTE OF MEASUREMENT AND CONTROL
(2023)
Article
Chemistry, Analytical
Fernando Moncada Martins, Victor Manuel Gonzalez Suarez, Jose Ramon Villar Flecha, Beatriz Garcia Lopez
Summary: Photosensitivity is a neurological disorder where the brain produces epileptic discharges in response to certain visual stimuli. The standardized diagnosis process involves using Intermittent Photic Stimulation and an EEG to identify these discharges. Due to the limited occurrence of discharges in long EEG recordings, this study focused on using data augmentation to create synthetic segments and improve the performance of machine learning techniques for automatic detection. The results showed a significant improvement in accuracy and specificity without any loss in sensitivity.
Article
Engineering, Industrial
Shen Yan, Haidong Shao, Zhishan Min, Jiangji Peng, Baoping Cai, Bin Liu
Summary: This paper proposes a new machinery anomaly detection method called full graph dynamic autoencoder (FGDAE) for complex operating conditions. It develops a full connected graph (FCG) to obtain global structure information and constructs a graph adaptive autoencoder (GAAE) model to aggregate multi-perspective feature information between channels. The method achieves better performance compared to other popular anomaly detection methods on machinery datasets.
RELIABILITY ENGINEERING & SYSTEM SAFETY
(2023)
Review
Computer Science, Artificial Intelligence
Ashik Mostafa Alvi, Siuly Siuly, Hua Wang
Summary: Efficient detection of neurological abnormalities is crucial in clinical diagnosis for modern medical applications. EEG, as a non-invasive and inexpensive method, is widely used to diagnose neurological diseases. This paper provides a comprehensive survey on recent studies using EEG signals to detect diseases such as Dementia, Mild Cognitive Impairment, Alzheimer's, Schizophrenia, and Parkinson, focusing on key components of EEG signal processing, algorithms used, and signal processing techniques.
ARTIFICIAL INTELLIGENCE REVIEW
(2022)
Article
Engineering, Multidisciplinary
Mohammed Diykh, Firas Sabar Miften, Shahab Abdulla, Ravinesh C. Deo, Siuly Siuly, Jonathan H. Green, Atheer Y. Oudahb
Summary: This paper proposes a new framework for the automated detection of neonatal seizures based on the Morse Wavelet approach, local binary pattern algorithm, and graph-based community detection algorithm. The experimental results demonstrate that the proposed model is more accurate in detecting seizures compared to traditional approaches.
Article
Mathematics, Interdisciplinary Applications
Muhammad Tariq Sadiq, Hesam Akbari, Siuly Siuly, Yan Li, Peng Wen Paul
Summary: Alcoholism is a severe disorder that affects the brain and leads to cognitive, emotional, and behavioral impairments. This article proposes a novel framework for automatically detecting alcoholism using electroencephalogram (EEG) signals. The framework explores the chaotic nature and complexity of EEG signals, decodes the chaotic behavior using graphical features, and utilizes feature selection and machine learning classifiers to develop an efficient detection system. The experimental results show high classification performance, and the proposed system provides visual biomarkers and indexes for alcoholic detection.
CHAOS SOLITONS & FRACTALS
(2022)
Article
Biology
Muhammad Tariq Sadiq, Muhammad Zulkifal Aziz, Ahmad Almogren, Adnan Yousaf, Siuly Siuly, Ateeq Ur Rehman
Summary: This study presents a new automated framework based on pretrained CNN for robust BCI systems using motor and mental imagery EEG signals. ShuffleNet achieves the highest classification accuracy with low learning rates and specific optimizers.
COMPUTERS IN BIOLOGY AND MEDICINE
(2022)
Article
Computer Science, Artificial Intelligence
Ashik Mostafa Alvi, Siuly Siuly, Hua Wang, Kate Wang, Frank Whittaker
Summary: This study aims to design a deep learning-based framework for effective detection of MCI participants and compares it with other classifiers to improve the successful application of early identification and treatment strategies.
KNOWLEDGE-BASED SYSTEMS
(2022)
Article
Computer Science, Artificial Intelligence
Muhammad Tariq Sadiq, Xiaojun Yu, Zhaohui Yuan, Muhammad Zulkifal Aziz, Siuly Siuly, Weiping Ding
Summary: This study introduces a novel matrix determinant feature extraction approach for efficient classification of motor and mental imagery activities from EEG signals. Experimental results demonstrate that the proposed method achieves high accuracy with low computational complexity, making it promising for the development of automated brain-computer interfaces.
IEEE TRANSACTIONS ON COGNITIVE AND DEVELOPMENTAL SYSTEMS
(2022)
Article
Mathematical & Computational Biology
Siuly Siuly, Yan Li, Peng Wen, Omer Faruk Alcin
Summary: This study proposes a deep learning-based feature extraction scheme called SchizoGoogLeNet, which can efficiently and automatically distinguish schizophrenic patients from healthy control subjects. Experimental results demonstrate that the proposed model achieves high accuracy and outperforms other existing methods, indicating its importance in schizophrenia detection.
COMPUTATIONAL INTELLIGENCE AND NEUROSCIENCE
(2022)
Article
Medical Informatics
Hesam Akbari, Muhammad Tariq Sadiq, Siuly Siuly, Yan Li, Paul Wen
Summary: This paper proposes a novel method for depression detection using EEG signals, which includes preprocessing, mode selection, feature extraction, and classification. A new diagnostic index for depression is also proposed, aiding in faster and more objective identification of depression.
HEALTH INFORMATION SCIENCE AND SYSTEMS
(2022)
Article
Engineering, Biomedical
Supriya Supriya, Siuly Siuly, Hua Wang, Yanchun Zhang
Summary: Epilepsy, a chronic brain disorder, poses challenges in diagnosis and treatment. Graph-theory based automated epilepsy detection methods have emerged as a promising approach to analyze the complex nature of EEG signals and understand brain activity. This paper provides a comprehensive review of such methods, aiming to assist neurologists and researchers in improving epilepsy diagnosis and developing intelligent systems.
IEEE REVIEWS IN BIOMEDICAL ENGINEERING
(2023)
Article
Computer Science, Artificial Intelligence
Ashik Mostafa Alvi, Siuly Siuly, Hua Wang
Summary: Mild cognitive impairment (MCI) is an irreversible degenerative disorder that may lead to dementia in elderly people. Early identification is crucial for effective treatment. This research proposes a deep learning-based framework using EEG data to identify MCI individuals from healthy volunteers, achieving high accuracy and sensitivity. The proposed model provides a robust biomarker and can guide the development of an automatic diagnosis system for MCI detection.
IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTATIONAL INTELLIGENCE
(2023)
Article
Engineering, Electrical & Electronic
Md Nurul Ahad Tawhid, Siuly Siuly, Tianning Li
Summary: Epilepsy is a severe neurological disorder with a high risk of death. This study proposes an efficient framework based on a deep spatiotemporal neural network for epilepsy detection from EEG signals. The proposed model outperforms the current state-of-the-art results, making it suitable as an automated system for epilepsy diagnosis.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2022)
Article
Computer Science, Information Systems
Wei Pei, Yan Li, Siuly Siuly, Peng Wen
Summary: Sleep stage classification is crucial for the accurate diagnosis and treatment of sleep-related diseases. Traditional hand-crafted feature extraction methods have limitations in balancing efficiency and accuracy. This study proposes a deep learning-based scheme that combines Convolutional Neural Networks (CNNs) and Gated Recurrent Units (GRUs) to efficiently identify different sleep stages from multi-biological signal data.
CMC-COMPUTERS MATERIALS & CONTINUA
(2022)
Article
Computer Science, Information Systems
K. Venkatachalam, Siuly Siuly, M. Vinoth Kumar, Praveen Lalwani, Manas Kumar Mishra, Enamul Kabir
Summary: This study introduces a computational model involving deep learning and biogeography-based optimization for early detection and management of COVID-19. The model uses convolutional neural networks and image inputs, and enhances prediction capability through comparative analysis and classification accuracy. Experimental results show that the proposed model outperforms other existing models.
CMC-COMPUTERS MATERIALS & CONTINUA
(2022)
Proceedings Paper
Computer Science, Interdisciplinary Applications
Muhammad Tariq Sadiq, Siuly Siuly, Ateeq Ur Rehman, Hua Wang
Summary: This study recommends using a computer-aided diagnosis system to characterize normal and alcoholic EEG signals by segmenting the dataset, computing autocorrelation for each signal, considering autocorrelation coefficients as features, and testing these features using machine learning classifiers. The results support the effectiveness of autocorrelation coefficients as features for classification.
HEALTH INFORMATION SCIENCE, HIS 2021
(2021)
Proceedings Paper
Computer Science, Interdisciplinary Applications
Hesam Akbari, Muhammad Tariq Sadiq, Siuly Siuly, Yan Li, Paul Wen
Summary: This study introduces a novel method for depression detection using EEG signals, decomposing the signals and computing features for classification with neural network classifiers, achieving good performance compared to existing literature.
HEALTH INFORMATION SCIENCE, HIS 2021
(2021)