[1]WU Tao,LIU Xia,KONG Xiangzeng.Abnormal electroencephalography recognition via adaptive structured sparse regression[J].CAAI Transactions on Intelligent Systems,2025,20(6):1432-1443.[doi:10.11992/tis.202411006]
Copy

Abnormal electroencephalography recognition via adaptive structured sparse regression

CAAI Transactions on Intelligent Systems[ISSN 1673-4785/CN 23-1538/TP] Volume: 20 Number of periods: 2025 6 Page number: 1432-1443 Column: 学术论文—机器感知与模式识别 Public date: 2025-11-05
Title:
Abnormal electroencephalography recognition via adaptive structured sparse regression
Author(s):
WU Tao1;  LIU Xia2;  KONG Xiangzeng2
1. College of Computer and Information Sciences, Fujian Agriculture and Forestry University, Fuzhou 350117, China;
2. College of Future Technology, Fujian Agriculture and Forestry University, Fuzhou 350117, China
Keywords:
abnormal EEG recognition; aggregation; sparse structure; statistical features; discrete wavelet transform; regularization; group feature selection; adaptive aggregation
CLC:
TP391
DOI:
10.11992/tis.202411006
Abstract:
Feature reduction is a critical technique for enhancing the decoding accuracy of electroencephalography (EEG) pathology. However, conventional abnormal EEG identification methods generally employ single-scale aggregation for dimension reduction, overlooking the complementary nature of multiscale aggregated features. This oversight frequently leads to suboptimal classification performance. Furthermore, current approaches often overlook the inherent correlation structure present among EEG features. To this end, an abnormal EEG recognition model based on adaptive structured sparse regression and its two-stage construction method is proposed. First, a novel adaptive local-global aggregation mechanism is employed to integrate wavelet statistical features extracted from the original data. This mechanism aims to provide representative features for high-precision EEG pathology decoding. Second, a novel sparse regularization model is defined, which can automatically eliminate unimportant characteristics by the L1-norm constraint term. Concurrently, weighted piecewise structural regularization is employed to enable the group selection of highly correlated features. The experimental findings based on real-world abnormal EEG datasets demonstrate that the proposed method significantly enhances the accuracy and stability of the classification results.
References:
[1] 王振宇, 向泽锐, 支锦亦. 离散小波变换和自编码器耦合的脑电信号异常检测方法[J]. 北京邮电大学学报, 2024, 47(2): 66-73.
WANG Zhenyu, XIANG Zerui, ZHI Jinyi. Detection method for abnormal electroencephalographic signals coupled with discrete wavelet transform and autoencoder[J]. Journal of Beijing University of Posts and Telecommunications, 2024, 47(2): 66-73.
[2] 张军鹏, 施玉杰, 蒋睿, 等. 基于脑电信号的认知功能障碍识别与分类进展综述[J]. 计算机应用, 2023, 43(10): 3297-3308.
ZHANG Junpeng, SHI Yujie, JIANG Rui, et al. Review on advances in recognition and classification of cognitive impairment based on EEG signals[J]. Journal of computer applications, 2023, 43(10): 3297-3308.
[3] L?PEZ DE DIEGO S. Automated interpretation of abnormal adult electroencephalograms[D]. Philadelphia: Temple University, 2017.
[4] MEI Ning, GROSSBERG M D, NG K, et al. Identifying sleep spindles with multichannel EEG and classification optimization[J]. Computers in biology and medicine, 2017, 89: 441-453.
[5] GEMEIN L A W, SCHIRRMEISTER R T, CHRAB?SZCZ P, et al. Machine-learning-based diagnostics of EEG pathology[J]. NeuroImage, 2020, 220: 117021.
[6] TANG Fengzhen, ADAM L, SI Bailu. Group feature selection with multiclass support vector machine[J]. Neurocomputing, 2018, 317: 42-49.
[7] WANG Min, YIN Xuefei, ZHU Yanming, et al. Representation learning and pattern recognition in cognitive biometrics: a survey[J]. Sensors, 2022, 22(14): 5111.
[8] ALBAQAMI H, HASSAN G M, SUBASI A, et al. Automatic detection of abnormal EEG signals using wavelet feature extraction and gradient boosting decision tree[J]. Biomedical signal processing and control, 2021, 70: 102957.
[9] GOWTHAM R N, HAIT S R, GUHA D, et al. Classification of epileptic EEG signals with the utilization of Bonferroni mean based fuzzy pattern tree[J]. Expert systems with applications, 2024, 239: 122424.
[10] SHARMA M, PATEL S, ACHARYA U R. Automated detection of abnormal EEG signals using localized wavelet filter banks[J]. Pattern recognition letters, 2020, 133: 188-194.
[11] IDOWU O P, ADELOPO O, ILESANMI A E, et al. Neuro-evolutionary approach for optimal selection of EEG channels in motor imagery based BCI application[J]. Biomedical signal processing and control, 2021, 68: 102621.
[12] ZHONG Yunning, WEI Hongyu, CHEN Lifei, et al. Automated EEG pathology detection based on significant feature extraction and selection[J]. Mathematics, 2023, 11(7): 1619.
[13] 刘建伟, 崔立鹏, 罗雄麟. 结构稀疏模型[J]. 计算机学报, 2017, 40(6): 1309-1337.
LIU Jianwei, CUI Lipeng, LUO Xionglin. Structured sparse models[J]. Chinese journal of computers, 2017, 40(6): 1309-1337.
[14] ZHENG Wenming. Multichannel EEG-based emotion recognition via group sparse canonical correlation analysis[J]. IEEE transactions on cognitive and developmental systems, 2016, 9(3): 281-290.
[15] 徐雪远, 刘建红, 李子遇, 等. 基于正交回归和特征加权的脑电情感特征选择方法[J]. 中国科学: 信息科学, 2023, 53(1): 33-45.
XU Xueyuan, LIU Jianhong, LI Ziyu, et al. EEG emotional feature selection method based on orthogonal regression and feature weighting[J]. Scientia sinica (informationis), 2023, 53(1): 33-45.
[16] ALGAMAL Z Y, LEE M H. Penalized logistic regression with the adaptive LASSO for gene selection in high-dimensional cancer classification[J]. Expert systems with applications, 2015, 42(23): 9326-9332.
[17] LIU Cheng, WONG H S. Structured penalized logistic regression for gene selection in gene expression data analysis[J]. IEEE/ACM transactions on computational biology and bioinformatics, 2019, 16(1): 312-321.
[18] WANG Yadi, ZHANG Wenbo, FAN Minghu, et al. Regression with adaptive lasso and correlation based penalty[J]. Applied mathematical modelling, 2022, 105: 179-196.
[19] BLANCO D?AZ C F, RUIZ OLAYA A F. A novel method based on regularized logistic regression and CCA for P300 detection using a reduced number of EEG trials[J]. IEEE Latin America transactions, 2020, 18(12): 2147-2154.
[20] GARC?S P, BAUMEISTER S, MASON L, et al. Resting state EEG power spectrum and functional connectivity in autism: a cross-sectional analysis[J]. Molecular autism, 2022, 13(1): 22.
[21] WANG Yadi, YANG Xinguang, LU Yongjin. Informative gene selection for microarray classification via adaptive elastic net with conditional mutual information[J]. Applied mathematical modelling, 2019, 71: 286-297.
[22] PATIL A R, PARK B K, KIM S. Adaptive lasso with weights based on normalized filtering scores in molecular big data[J]. Journal of theoretical and computational chemistry, 2020, 19(4): 2040010.
[23] PARK H, SHIRAISHI Y, IMOTO S, et al. A novel adaptive penalized logistic regression for uncovering biomarker associated with anti-cancer drug sensitivity[J]. IEEE/ACM transactions on computational biology and bioinformatics, 2017, 14(4): 771-782.
[24] LI Juntao, WANG Yadi, XIAO Huimin, et al. Gene selection of rat hepatocyte proliferation using adaptive sparse group lasso with weighted gene co-expression network analysis[J]. Computational biology and chemistry, 2019, 80: 364-373.
[25] WANG Yadi, LI Xiaoping, RUIZ R. Feature selection with maximal relevance and minimal supervised redundancy[J]. IEEE transactions on cybernetics, 2023, 53(2): 707-717.
[26] BOU A E, NGUYEN D K, RIHANA S, et al. Towards accurate prediction of epileptic seizures: a review[J]. Biomedical signal processing and control, 2017, 34: 144-157.
[27] YAGER R R. On ordered weighted averaging aggregation operators in multicriteria decisionmaking[J]. IEEE transactions on systems, man, and cybernetics, 1988, 18(1): 183-190.
[28] WANG Lianxi, JIANG Shengyi, JIANG Siyu. A feature selection method via analysis of relevance, redundancy, and interaction[J]. Expert systems with applications, 2021, 183: 115365.
[29] FRIEDMAN J, HASTIE T, TIBSHIRANI R. Regularization paths for generalized linear models via coordinate descent[J]. Journal of statistical software, 2010, 33(1): 1-22.
[30] KHAN H A, AIN R U, KAMBOH A M, et al. The NMT scalp EEG dataset: an open-source annotated dataset of healthy and pathological EEG recordings for predictive modeling[J]. Frontiers in neuroscience, 2022, 15: 755817.
[31] ROY S, KIRAL-KORNEK I, HARRER S. ChronoNet: a deep recurrent neural network for abnormal EEG identification[M]//Artificial Intelligence in Medicine. Cham: Springer International Publishing, 2019: 47-56.
[32] ZHANG Zhongheng, TREVINO V, HOSEINI S S, et al. Variable selection in Logistic regression model with genetic algorithm[J]. Annals of translational medicine, 2018, 6(3): 45.
[33] MAATEN L V D, HINTON G. Visualizing data using t-SNE[J]. Journal of machine learning research, 2008, 9(86): 2579-2605.
[34] KHARE S K, ACHARYA U R. Adazd-Net: Automated adaptive and explainable Alzheimer’s disease detection system using EEG signals[J]. Knowledge-based systems, 2023, 278: 110858.
[35] YASUHARA A. Correlation between EEG abnormalities and symptoms of autism spectrum disorder (ASD)[J]. Brain and development, 2010, 32(10): 791-798.
[36] ALDEMIR R, DEMIRCI E, PER H, et al. Investigation of attention deficit hyperactivity disorder (ADHD) sub-types in children via EEG frequency domain analysis[J]. The international journal of neuroscience, 2018, 128(4): 349-360.
[37] ZHAO Qinglin, JIANG Hua, HU Bin, et al. Nonlinear dynamic complexity and sources of resting-state EEG in abstinent heroin addicts[J]. IEEE transactions on nanobioscience, 2017, 16(5): 349-355.
Similar References:

Memo

-

Last Update: 1900-01-01

Copyright © CAAI Transactions on Intelligent Systems