Browse > Article

Clustering of Incomplete Data Using Autoencoder and fuzzy c-Means Algorithm  

박동철 (명지대학교 정보공학과)
장병근 (명지대학교 정보공학과)
Abstract
Clustering of incomplete data using the Autoencoder and the Fuzzy c-Means(PCM) is proposed in this paper. The Proposed algorithm, called Optimal Completion Autoencoder Fuzzy c-Means(OCAEFCM), utilizes the Autoencoder Neural Network (AENN) and the Gradiant-based FCM (GBFCM) for optimal completion of missing data and clustering of the reconstructed data. The proposed OCAEFCM is applied to the IRIS data and a data set from a financial institution to evaluate the performance. When compared with the existing Optimal Completion Strategy FCM (OCSFCM), the OCAEFCM shows 18%-20% improvement of performance over OCSFCM.
Keywords
Neural Network; OCAEFCM; GBFCM;
Citations & Related Records
연도 인용수 순위
  • Reference
1 /
[ A.Jain;R.Dubes ] / Algorithms for Clustering Data
2 Approxi-mate structured singular value compu- tation via Frobenius norms /
[ M.Manning;S.Banda ] / Proc. of IEEE Int. Conf on Systems Eng.
3 /
[ G.Sebestyen ] / Decision-making Processes in Pattern Recognition
4 Fuzzy c-Means Clustering of Incomplete Data /
[ R.Hathaway;J.Bezdek ] / IEEE Tr. Syst., Man, Cybern.   DOI   ScienceOn
5 /
[ J.Bezdek ] / Pattern recognition with Fuzzy Objective Function Algorithms
6 /
[ K.Fukunage ] / Introduction to Statistical Pattern Recognition(2nd ed.)
7 /
[ R.Reed;R.MarksⅡ ] / Neural Smithing : Supervised Learning in Feedforward Artificial Neural Network
8 Will the real IRIS data please stand up? /
[ J.Bezdek(et al.) ] / IEEE Tr. Fuzzy Syst.   DOI   ScienceOn
9 Implicit Learning in Autoencoder Novelty Assessment /
[ B.Thompson(et al.) ] / Proc. of IEEE IJCNN-2002
10 Gradient Based Fuzzy c_means (GBFCM) /
[ Dong C.Park;Issam Dagher ] / Proc. of IEEE ICNN-94
11 A convergence theroem for the fuzzy ISODATA clustering algorithms /
[ J.Bezdek ] / IEEE TR. Pattern Anal. Mach. Int.   DOI
12 Pattern Recognition with partly Missing Data /
[ J.Dixon ] / IEEE Trans. Syst., Man, Cybern.