Self-Learning TSK Fuzzy Epilepsy Assistant Detection Algorithm Incorporating Shallow and Deep Knowledge
SHI Qihuan1,2, ZHANG Xiongtao1,2
1. School of Information Engineering, Huzhou University, Huzhou 313000; 2. Zhejiang Province Key Laboratory of Smart Management and Application of Modern Agricultural Resources, Huzhou University, Huzhou 313000
Abstract：The Takagi-Sugeno-Kang (TSK) fuzzy classifier exhibits exceptional performance in handling fuzzy information for epilepsy detection. However, Due to the complexity of epileptic electroencephalogram(EEG)signals and the diverse manifestations of seizures among patients, first-order TSK fuzzy classifiers often struggle to achieve sufficient generalization from training samples.A TSK fuzzy classifier with deep and shallow self-learning knowledge integration, namely deep-shallow mix self-learning TSK(DSMT), is proposed. In DSMT, deep rules akin to human "reflection-induction" are introduced to enhance the ability of the model to mine latent information. The commonly used teacher model in knowledge distillation is replaced by the internal knowledge of the model through a static-dynamic Siamese network structure.In the static network, shallow knowledge hidden in the outputs from different batches is employed. In the dynamic network, the outputs of the static Siamese network are recorded as deep knowledge, and deep knowledge and shallow knowledge are combined. The sensitivity of the TSK fuzzy classifier to fuzzy information is leveraged to integrate both types of knowledge. DSMT enables self-learning of the first-order TSK model and improves the adaptability of the epilepsy detection system. Additionally, an optimal temperature distillation strategy is utilized to optimize knowledge transfer efficiency. Experiments on the real epilepsy datasets, CHB-MIT, TUAB, and TUEV, verify the effectiveness of DSMT.
[1] MACORIG G, CRESPEL A, NILO A, et al. Can Epilepsy Affect Normal EEG Variants? A Comparative Study between Subjects with and without Epilepsy. Neurophysiologie Clinique, 2024, 54(1). DOI: 10.1016/j.neucli.2023.102935. [2] SCHEFFER I E, ZUBERI S, MEFFORD H C, et al. Developmental and Epileptic Encephalopathies. Nature Reviews Disease Pri-mers, 2024, 10. DOI: 10.1038/s41572-024-00546-6. [3] ASADI-POOYA A A, SHAFAEI R, ABDOLREZAEE M, et al. Opinions about Epilepsy Surgery in Adults with Epilepsy. Epilepsy and Behavior, 2023, 142. DOI: 10.1016/j.yebeh.2023.109176. [4] HAGEMANN A, LAHR D, MAY T W, et al. Efficacy of a Specia-lized Inpatient Rehabilitation Program in Patients with Early Versus Chronic Epilepsy. Epilepsy and Behavior, 2023, 142. DOI: 10.1016/j.yebeh.2022.108999. [5] ZHANG Q, LI C, DING Y. An Epilepsy Diagnosis Method Based on a Transferred Alexnet Model and EEG Signals. Journal of Mechanics in Medicine and Biology, 2024, 24(2). DOI: 10.1142/S0219519424400050. [6] KOREN J, LANG C, GRITSCH G, et al. Idiopathic Generalized Epilepsies in the Epilepsy Monitoring Unit: Systematic Quantification of Focal EEG and Semiological Signs. Clinical Neurophysiology, 2024, 162: 82-90. [7] ZHANG Y P, ZHOU Z Y, PAN W J, et al. Epilepsy Signal Recognition Using Online Transfer TSK Fuzzy Classifier Underlying Classification Error and Joint Distribution Consensus Regularization. IEEE/ACM Transactions on Computational Biology and Bioinforma-tics, 2021, 18(5): 1667-1678. [8] 郑润泽,冯袁盟,胡丁寒,等.儿童癫痫综合征智能分析:综述与展望.模式识别与人工智能, 2024, 37(2): 144-161. (ZHENG R Z, FENG Y M, HU D H, et al. Intelligent Analysis of Childhood Epileptic Syndrome: Overview and Prospect. Pattern Recognition and Artificial Intelligence, 2024, 37(2): 144-161.) [9] YAǦMUR F D, SERTBAŞ A. A High-Performance Method Based on Features Fusion of EEG Brain Signal and MRI-Imaging Data for Epilepsy Classification. Measurement Science Review, 2024, 24(1): 1-8. [10] FANG S Z, ZHU C F, ZHANG J Y, et al. EEG Microstates in Epilepsy with and without Cognitive Dysfunction: Alteration in Intrinsic Brain Activity. Epilepsy and Behavior, 2024, 154. DOI: 10.1016/j.yebeh.2024.109729. [11] ZHOU E H, VONG C M, NOJIMA Y, et al. A Fully Interpretable First-Order TSK Fuzzy System and Its Training with Negative Entropic and Rule-Stability-Based Regularization. IEEE Transactions on Fuzzy Systems, 2023, 31(7): 2305-2319. [12] BIAN Z K, ZHANG J, NOJIMA Y, et al. Hybrid-Ensemble-Based Interpretable TSK Fuzzy Classifier for Imbalanced Data. Information Fusion, 2023, 98. DOI: 10.1016/j.inffus.2023.101845. [13] 张雄涛,李水苗,翁江玮,等.基于视角-规则的深度TSK模糊分类器及其在多元癫痫脑电信号识别中的应用.控制与决策, 2024, 39(4): 1315-1324. (ZHANG X T, LI S M, WENG J W, et al. Recognition of Multivariate Epilepsy EEG Signals Based on View-to-Rule Deep TSK Fuzzy Classifier. Control and Decision, 2024, 39(4): 1315-1324.) [14] JIANG Y L, WENG J W, ZHANG X T, et al. A CNN-Based Born-Again TSK Fuzzy Classifier Integrating Soft Label Information and Knowledge Distillation. IEEE Transactions on Fuzzy Systems, 2023, 31(6): 1843-1854. [15] JIANG Y Z, DENG Z H, CHUNG F L, et al. Recognition of Epileptic EEG Signals Using a Novel Multiview TSK Fuzzy System. IEEE Transactions on Fuzzy Systems, 2017, 25(1): 3-20. [16] 蒋云良,翁江玮,申情,等.基于增强深度特征和TSK模糊分类器的癫痫脑电信号识别.控制与决策, 2023, 38(1): 171-180. (JIANG Y L, WENG J W, SHEN Q, et al. TSK Fuzzy Classifier Based on Enhanced Deep Feature for Epilepsy EEG Signal Recognition. Control and Decision, 2023, 38(1): 171-180.) [17] QIN B, NOJIMA Y, ISHIBUCHI H, et al. Realizing Deep High-Order TSK Fuzzy Classifier by Ensembling Interpretable Zero-Order TSK Fuzzy Subclassifiers. IEEE Transactions on Fuzzy Systems, 2021, 29(11): 3441-3455. [18] 卞则康,张进,王士同.面向不平衡数据的深度TSK模糊分类器.模式识别与人工智能, 2023, 36(3): 211-224. (BIAN Z K, ZHANG J, WANG S T.A Deep Takagi-Sugeno-Kang Fuzzy Classifier for Imbalanced Data. Pattern Recognition and Artificial Intelligence, 2023, 36(3): 211-224.) [19] GOU J P, YU B S, MAYBANK S J, et al. Knowledge Distillation: A Survey. International Journal of Computer Vision, 2021, 129(6): 1789-1819. [20] YUAN M Y, LANG B, QUAN F N. Student-Friendly Knowledge Distillation. Knowledge-Based Systems, 2024, 296. DOI: 10.1016/j.knosys.2024.111915. [21] LIANG P, ZHANG W W, WANG J H, et al. Neighbor Self-Knowledge Distillation. Information Sciences, 2024, 654. DOI: 10.1016/j.ins.2023.119859. [22] PARK W, KIM D, LU Y, et al. Relational Knowledge Distillation//Proc of the IEEE/CVF Conference on Computer Vision and Pa-ttern Recognition. Washington, USA: IEEE, 2019: 3962-3971. [23] LEE H, PARK Y, SEO H, et al. Self-Knowledge Distillation via Dropout. Computer Vision and Image Understanding, 2023, 233. DOI: 10.1016/j.cviu.2023.103720. [24] LI Z, LI X, YANG L F, et al. Dual Teachers for Self-Knowledge Distillation. Pattern Recognition, 2024, 151. DOI: 10.1016/j.patcog.2024.110422. [25] ZHANG L F, SONG J B, GAO A N, et al. Be Your Own Tea-cher: Improve the Performance of Convolutional Neural Networks via Self Distillation//Proc of the IEEE/CVF International Confe-rence on Computer Vision. Washington, USA: IEEE, 2019: 3712-3721. [26] ZHAO H R, BI Y X, TIAN S W, et al. Self-Knowledge Distilla-tion via Progressive Associative Learning. Electronics, 2024, 13(11). DOI: 10.3390/electronics13112062. [27] HU M H, GAO R B, SUGANTHAN P N.Self-Distillation for Randomized Neural Networks. IEEE Transactions on Neural Networks and Learning Systems, 2024, 35(11): 16119-16128. [28] SERRANO N, BELLOGÍN A. Siamese Neural Networks in Recom-mendation. Neural Computing and Applications, 2023, 35(19): 13941-13953. [29] TENG Y, LI H X, CHEN S X, et al. Mapping the Neural Mechanism that Distinguishes between Holistic Thinking and Analytic Thinking. NeuroImage, 2024, 294. DOI: 10.1016/j.neuroimage.2024.120627. [30] ZHENG Y F, DENERVAUD S, DURRLEMAN S.Bilingualism and Creativity across Development: Evidence from Divergent Thinking and Convergent Thinking. Frontiers in Human Neuroscience, 2023, 16. DOI: 10.3389/fnhum.2022.1058803. [31] FOOK J.Developing Critical Reflection as a Research Method//HIGGS J, TITCHEN A, HORSFALL D, et al., eds. Creative Spaces for Qualitative Researching: Living Research. Berlin, Germany: Springer, 2011: 55-64. [32] GOLDBERGER A L, AMARAL L A N, GLASS L, et al. PhysioBank, PhysioToolkit, and PhysioNet: Components of a New Research Resource for Complex Physiologic Signals. Circulation, 2000, 101(23): e215-e220. [33] JIANG W B, ZHAO L M, LU B L.Large Brain Model for Learning Generic Representations with Tremendous EEG Data in BCI[C/OL].[2024-08-17]. https://arxiv.org/pdf/2405.18765. [34] SUBASI A, KEVRIC J, CANBAZ M A.Epileptic Seizure Detection Using Hybrid Machine Learning Methods. Neural Computing and Applications, 2019, 31(1): 317-325. [35] LI A D, DENG Z H, ZHANG W, et al. Multiview Transfer Representation Learning with TSK Fuzzy System for EEG Epilepsy Detection. IEEE Transactions on Fuzzy Systems, 2024, 32(1): 38-52. [36] JIANG Y Z, GU X Q, JI D C, et al. Smart Diagnosis: A Multiple-Source Transfer TSK Fuzzy System for EEG Seizure Identification. ACM Transactions on Multimedia Computing, Communications, and Applications, 2020, 16(2s). DOI: 10.1145/334024.
2025, Vol. 38 
