Abstract
Support vector domain description (SVDD) is a data description method inspired by support vector machine (SVM). This classifier describes a set of data points with a sphere that encloses the majority of them and has a minimal volume. The boundary of this sphere is used to classify new samples. SVDD has been successfully applied to many challenging classification problems and has shown a good generalization capability. However, this classifier still has some major weaknesses. This paper focuses on two of them: The first regards the large amount of memory and computational time required by SVDD in the training step. This problem manifests most strongly when dealing with large-size datasets and can hinder or prevent its use. This paper presents an approximate solution to this problem that permits to apply SVDD to large-scale datasets. This new version is based on divide-and-conquer strategy and it processes in two steps: It begins by dividing the whole large-size dataset into random subsets that each can be described efficiently with a small sphere using SVDD. Then, it applies our new algorithm that can find the smallest sphere that encloses the minimal spheres built in the previous step. The second weak point of standard SVDD concerns its static learning process. This classifier must be re-trained with the whole dataset each time when new training samples are available. This paper proposes a new dynamic approach that only trains the new samples with SVDD and incorporates the resulting minimal sphere with the previous one (s) to construct the smallest sphere that encloses all the samples. Like Support Vector Domain Description, the proposed approach can be extended to non-linear classification cases by using kernel functions. Experimental results on artificial and real datasets have successfully validated the performance of our approach.
Similar content being viewed by others
References
Allahyari Y, Sadoghi-Yazdi H (2012) Quasi support vector data description (QSVDD). Int J Signal Process Image Process Pattern Recogn 5(3):65–74
Chaudhuri A, Sadek C, Kakde D et al (2021) The trace kernel bandwidth criterion for support vector data description. Pattern Recogn 111:107662
Chen X, Cao C, Mai J (2020) Network anomaly detection based on deep support vector data description. In: Proceedings of the 5th IEEE international conference on big data analytics (ICBDA), Xiamen, China
Chu SC, Tsang IW, Kwok JT (2004) Scaling up support vector data description by using coresets. In: Proceedings of the international joint conference on neural networks, Budapest, Hungary, pp 425–430
Cortes C, Vapnik V (1995) Support-vector network. Mach Learn 20:273–297
Dai T (2018) Personal credit assessment based on improved SVDD algorithm. IOP Conf Ser Mater Sci Eng 439(4):042003
El Boujnouni M, Jedra M, Zahid N (2014) Support vector domain description with maximum between spheres separability. J Inf Sci Eng 30(6):1985–2002
Ghasemigol M, Reza M, Hadi SY (2009), Ellipse support vector data description. In: 11th international conference on engineering applications of neural networks-EANN
Hao PY, Lin YH (2007) A new multi-class support vector machine with multi-sphere in the feature space. In: HG Okuno, M Ali (Eds) IEA/AIE 2007, LNAI 4570, pp 756–765
Jinglong F, Wanliang W, Xingqi W et al (2012) A SVDD method basedon maximum distance between two centers of spheres. Chin J Electron 21(1):107–111
Lazli L, Boukadoum M, Ait MO (2019) Computer-aided diagnosis system of Alzheimer’s disease based on multimodal fusion: tissue quantification based on the hybrid fuzzy-genetic-possibilistic model and discriminative classification based on the SVDD model. Brain Sci 9(10):289. https://doi.org/10.3390/brainsci9100289
Lee KY, Kim DW, Lee KH et al (2007) Density-induced support vector data description. IEEE Trans Neural Netw 18(1):284–289
Le T, Tran D, Hoang T et al. (2012) A unified model for support vector machine and support vector data description. In: The international joint conference on neural networks (IJCNN). Brisbane, Australia
Liang J, Liu S, Wu D (2009) Fast training of SVDD by extracting boundary targets. Iran J Electr Comput Eng 8(2):133–137
Liu Y, Zheng YF (2006) Minimum enclosing and maximum excluding machine for pattern description and discrimination. Proc Int Conf Pattern Recogn 3:129–132
Mu T, Nandi AK (2009) Multiclass classification based on extended support vector data description. IEEE Trans Syst Man Cybern Part B 39(5):1206–1216
Mygdalis V, Tefas A, Pitas I (2020) K-Anonymity inspired adversarial attack and multiple one-class classification defense. Neural Netw 124:296–307
Perera P, Patel VM (2019) Learning deep features for one-class classification. IEEE Trans Image Process 28(11):1–15
Qu H, Zhao J, Zhao J et al. (2019), Towards support vector data description based on heuristic sample condensed rule. In: Chinese control and decision conference (CCDC), Nanchang, China, pp 4647–4653. https://doi.org/10.1109/CCDC.2019.8833182
Slimene A, Zagrouba E (2019) Towards fast and parameter-independent support vector data description for image and video segmentation. Expert Syst Appl 128:271–286
Sun QY, Sun YM, Liu XJ et al (2019) Study on fault diagnosis algorithm in WSN nodes based on RPCA model and SVDD for multi-class classification. Clust Comput 22(1):6043–6057
Tax D, Duin R (1999) Data domain description using support vectors. In: Proceedings of European symposium on artificial neural networks, pp 251–256
Tax D, Duin R (2004) Support vector data description. Mach Learn 54:45–66
UCI repository of machine learning databases. http://archive.ics.uci.edu/ml/
Vapnik V (1979) Estimation of dependences based on empirical data. Nauka, Moscow
Vapnik V (1998) Statistical learning theory. Wiley, New York
Wang J, Liu W, Qiu K et al (2019) Dynamic hypersphere SVDD without describing boundary for one-class classification. Neural Comput Appl 31:3295–3305
Wang J, Neskovic P, Cooper LN (2005) Pattern classification via single spheres. Comput Sci 3735:241–252
Wang K, Lan H (2020) Robust support vector data description for novelty detection with contaminated data. Eng Appl Artif Intell 91:103554
Wu M, Ye J (2009) A small sphere and large margin approach for novelty detection using training data with outliers. IEEE Trans Pattern Anal Mach Intell 31(11):2088–2092
Wu Q, Shen X, Li Y et al (2005) Classifying the multiplicity of the EEG source models using sphere-shaped support vector machines. IEEE Trans Magn 41(5):1912–1915
Zeng QS, Huang XY, Xiang XH et al (2019) Kernel analysis based on SVDD for face recognition from image set. J Intell Fuzzy Syst 36(6):5499–5511
Zheng S (2019) A fast iterative algorithm for support vector data description. Int J Mach Learn Cybern 10(5):1173–1187
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
El Boujnouni, M. Pseudo support vector domain description to train large-size and continuously growing datasets. Knowl Inf Syst 63, 2671–2692 (2021). https://doi.org/10.1007/s10115-021-01606-z
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10115-021-01606-z