Abstract
Using unsupervised learning methods for clinical diagnosis is very meaningful. In this study, we propose an unsupervised multi-view & multi-medoid variant-entropy-based fuzzy clustering (M2VEFC) method for epilepsy EEG signals detecting. Comparing with existing related studies, M2VEFC has four main merits and contributions: (1) Features in original EEG data are represented from different perspectives that can provide more pattern information for epilepsy signals detecting. (2) During multi-view modeling, multi-medoids are used to capture the structure of clusters in each view. Furthermore, we assume that the medoids in a cluster observed from different views should keep invariant, which is taken as one of the collaborative learning mechanisms in this study. (3) A variant entropy is designed as another collaborative learning mechanism in which view weight learning is controlled by a user-free parameter. The parameter is derived from the distribution of samples in each view such that the learned weights have more discrimination. (4) M2VEFC does not need original data as its input—it only needs a similarity matrix and feature statistical information. Therefore, the original data are not exposed to users and hence the privacy is protected. We use several different kinds of feature extraction techniques to extract several groups of features as multi-view data from original EEG data to test the proposed method M2VEFC. Experimental results indicate M2VEFC achieves a promising performance that is better than benchmarking models.
- Y. Jiang et al. 2017. Recognition of epileptic EEG signals using a novel multiview TSK fuzzy system. IEEE Transactions on Fuzzy Systems 25, 1 (2017), 3–20.Google Scholar
Cross Ref
- J. Long, Z. Yan, Y. Shen, W. Liu, and Q. Wei. 2018. Detection of epilepsy using MFCC-based feature and XGBoost. 2018 11th international congress on image and signal processing. BioMedical Engineering and Informatics (CISP-BMEI), Beijing, China, 2018, 1–4.Google Scholar
- S. Coelli, E. Maggioni, A. Rubino, C. Campana, L. Nobili, and A. M. Bianchi. 2019. Multiscale functional clustering reveals frequency dependent brain organization in type II focal cortical dysplasia with sleep hypermotor epilepsy. IEEE Transactions on Biomedical Engineering 66, 10 (2019), 2831–2839.Google Scholar
Cross Ref
- S. Rampogu et al. 2019. Identification of novel scaffolds with dual role as antiepileptic and anti-breast cancer. IEEE/ACM Transactions on Computational Biology and Bioinformatics 16, 5 (2019), 1663–1674. Google Scholar
Digital Library
- J. Zheng, H. Fushing and L. Ge. A data-driven approach to predict and classify epileptic seizures from brain-wide calcium imaging video data. IEEE/ACM Transactions on Computational Biology and Bioinformatics, In press.Google Scholar
- C. Gan, J. Wu, S. Yang, Y. Hu, and W. Cao. 2016. Wavelet packet decomposition-based fault diagnosis scheme for SRM drives with a single current sensor. IEEE Transactions on Energy Conversion 31, 1 (2016), 303–313.Google Scholar
Cross Ref
- W. Lu and Q. Zhang. 2009. Deconvolutive short-time fourier transform spectrogram. IEEE Signal Processing Letters 16, 7 (2009), 576–579.Google Scholar
Cross Ref
- C. M. Alaíz, M. Fanuel, and J. A. K. Suykens. 2018. Convex formulation for kernel PCA and its use in semisupervised learning. IEEE Transactions on Neural Networks and Learning Systems 29, 8 (2018), 3863–3869.Google Scholar
Cross Ref
- Y. Jiang et al. 2017. Seizure classification from EEG signals using transfer learning, semi-supervised learning and TSK fuzzy system. IEEE Transactions on Neural Systems and Rehabilitation Engineering 25, 12 (2017), 2270–2284.Google Scholar
Cross Ref
- J. Zhu et al. 2019. A novel double-index-constrained, multi-view, fuzzy-clustering algorithm and its application for detecting epilepsy electroencephalogram signals. IEEE Access 7 (2019), 103823–103832.Google Scholar
Cross Ref
- Y. Zhang, J. Dong, J. Zhu, and C. Wu. 2019. Common and special knowledge-driven TSK fuzzy system and its modeling and application for epileptic EEG signals recognition. IEEE Access 7 (2019), 127600–127614.Google Scholar
Cross Ref
- Y. Zhang, F. Chung, and S. Wang. 2019. A multiview and multiexemplar fuzzy clustering approach: Theoretical analysis and experimental studies. IEEE Transactions on Fuzzy Systems 27, 8 (2019), 1543–1557.Google Scholar
Cross Ref
- C. Xu, D. Tao, and C. Xu. 2015. Multi-view intact space learning. IEEE Transactions on Pattern Analysis and Machine Intelligence 37, 12 (2015), 2531–2544. Google Scholar
Digital Library
- Y. Li, M. Yang, and Z. Zhang. 2019. A survey of multi-view representation learning. IEEE Transactions on Knowledge and Data Engineering 31, 10 (2019), 1863–1883.Google Scholar
Cross Ref
- G. F. Tzortzis and A. C. Likas. 2012. Kernel-based weighted multi-view clustering. In Proc. IEEE 12th Int. Conf. Data Mining, Brussels, Belgium 2012, 675–684. Google Scholar
Digital Library
- Y. Jiang et al. 2017. Recognition of epileptic EEG signals using a novel multiview TSK fuzzy system. IEEE Transactions on Fuzzy Systems 25, 1 (2017), 3–20.Google Scholar
Cross Ref
- L. Sun and C. Guo. 2014. Incremental affinity propagation clustering based on message passing. IEEE Trans. Knowl. Data Eng 26, 11 (2014), 2731–2744.Google Scholar
Cross Ref
- H. G. Jung. 2013. Medoid selection from sub-tree leaf nodes for k-medoid clustering-based hierarchical template tree construction. Electronics Letters 49, 2 (2013), 108–109.Google Scholar
Cross Ref
- Y. Wang, L. Chen, and J. P. Mei. 2014. Incremental fuzzy clustering with multiple medoids for large data. In IEEE Transactions on Fuzzy Systems 22, 6 (2014), 1557–1568.Google Scholar
Cross Ref
- C. D. Wang, J. H. Lai, C. Y. Suen, and J. Y. Zhu. 2013. Multi-exemplar affinity propagation. IEEE Transactions on Pattern Analysis and Machine Intelligence 35, 9 (2013), 2223–2237. Google Scholar
Digital Library
- L. Kaufman, P. J. Rousseeuw. 1987. In Statistical Data Analysis Based on the L1–Norm and Related Methods, Y. Dodge (Ed.), North-Holland, Amsterdam 1987, 405–416.Google Scholar
- L. Kaufman, P. J. Rousseeuw. 1990. Finding groups in data: An introduction to cluster analysis. Wiley, New York, 1990.Google Scholar
- R. Krishnapuram, A. Joshi, O. Nasraoui, and L. Yi. 2001. Low-complexity fuzzy relational clustering algorithms for Web mining. IEEE Transactions on Fuzzy Systems 9, 4 (2001), 595–607. Google Scholar
Digital Library
- Y. Kanzawa. 2014. On a maximizing model of spherical bezdek-type possibilistic c-means and fuzzy multi-medoids clustering. Granular Computing (GrC), 2014 IEEE International Conference on, Noboribetsu, 2014, 121–126.Google Scholar
Cross Ref
- J. P Mei and L. Chen. 2011. Fuzzy relation clustering around medoids: A unified vew. Fuzzy Sets and Systems 183 (2011), 44–56. Google Scholar
Digital Library
- Francisco de A. T. de Carvalho, Filipe M. de Melo, and Yves Lechevallier. 2015. A multi-view relational fuzzy c-medoid vectors clustering algorithm. Neurocomputing 163, 115–123. Google Scholar
Digital Library
- P. Qian, Y. Jiang, Z. Deng, L. Hu, S. i. Sun, S. Wang, and R. F. Muzic. 2016. Cluster prototypes and fuzzy memberships jointly leveraged cross-domain maximum entropy clustering. IEEE Transactions on Cybernetics 46, 1 (2016), 181–193.Google Scholar
Cross Ref
- X. Chen, X. Xu, J. Z. Huang, and Y. Ye. 2013. TW-k-means: Automated two-level variable weighting clustering algorithm for multiview data. IEEE Trans. Knowl. Data Eng 25, 4 (2013), 932–944. Google Scholar
Digital Library
- Y. Jiang, Fu-Lai Chung, S. Wang, Z. H. Deng, J. Wang, and P. J. Qian. 2015. Collaborative fuzzy clustering from multiple weighted views. IEEE Trans. Cybernetics 45, 4 (2015), 688–701.Google Scholar
Cross Ref
- A. Strehl and J. Ghosh. 2002. Cluster ensembles—A knowledge reuse framework for combining multiple partitions. Mach. Learn. Res. 3, 583–617. Google Scholar
Digital Library
- B. Long, P. S. Yu, and Z. M. Zhang. 2008. A general model for multiple view unsupervised learning. In Proc. 8th SIAM Int. Conf. Data Mining, Atlanta, GA, USA, 2008, 822–833.Google Scholar
- G. F. Tzortzis and A. C. Likas. 2012. Kernel-based weighted multi-view clustering. In Proc. IEEE 12th Int. Conf. Data Mining, Brussels, Belgium 2012, 675–684. Google Scholar
Digital Library
- G. Li, K. Chang, and S. C. Hoi. 2012. Multiview semi-supervised learning with consensus. IEEE Trans. Knowl. Data Eng 24, 1 (2012), 2040–2051. Google Scholar
Digital Library
- A. Kumar, P. Rai, and H. Daume III. 2011. Co-regularized multi-view spectral clustering. In Proc. Adv. Neural Inf. Process. Syst. 2011, 1413–1421. Google Scholar
Digital Library
- D. R. Cox and P. A. Lewis. 1966. The Statistical Analysis of Series of Events. London: Methuen & Co. 1966.Google Scholar
- J. C. Bezdek and N. R. Pal. 1998. Some new indexes of cluster validity. IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics) 28, 3 (1998), 301–315. Google Scholar
Digital Library
- C. Wang, J. Lai and P. S. Yu. 2016. Multi-view clustering based on belief propagation. In IEEE Transactions on Knowledge and Data Engineering 28, 4 (2016), 1007–1021. Google Scholar
Digital Library
- J. Zhu et al. 2019. A novel double-index-constrained, multi-view, fuzzy-clustering algorithm and its application for detecting epilepsy electroencephalogram signals. In IEEE Access 7 (2019), 103823–103832.Google Scholar
Cross Ref
Index Terms
Epilepsy Diagnosis Using Multi-view & Multi-medoid Entropy-based Clustering with Privacy Protection
Recommendations
A Novel Multi-view Agglomerative Clustering Algorithm Based on Ensemble of Partitions on Different Views
ICPR '10: Proceedings of the 2010 20th International Conference on Pattern RecognitionIn this paper, we propose a new algorithm for extending the hierarchical clustering methods and introduce a Multi-View Agglomerative Clustering approach to handle multi-view represented objects. Experiments on real world datasets indicate that our ...
Application of entropies for automated diagnosis of epilepsy using EEG signals
Epilepsy can be detected using EEG signals.The entropy indicates the complexity of the EEG signal.Various entropies are used to diagnose epilepsy.Unique ranges for various entropies are proposed. Epilepsy is the neurological disorder of the brain which ...
Multi-Task Multi-View Clustering
Multi-task clustering and multi-view clustering have severally found wide applications and received much attention in recent years. Nevertheless, there are many clustering problems that involve both multi-task clustering and multi-view clustering, i.e., ...






Comments