디지털융복합연구 (Journal of Digital Convergence)

  • 제12권8호
  • /
  • Pages.321-327
  • /
  • 2014
  • /
  • 2713-6434(pISSN)
  • /
  • 2713-6442(eISSN)
한국디지털정책학회 (The Society of Digital Policy and Management)
권호 표지
DOI QR코드

DOI QR Code

거리 기반의 특징 선택을 이용한 간질 분류

Classification of Epilepsy Using Distance-Based Feature Selection

  • 이상홍 (안양대학교 컴퓨터공학과)
  • Lee, Sang-Hong (Department of Computer Science & Engineering, Anyang University)
  • 투고 : 2014.06.08
  • 심사 : 2014.08.20
  • 발행 : 2014.08.28
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

특징 선택은 중복 또는 서로간의 관련이 없는 특징을 제거하여 분류 성능을 향상시키는 기술이다. 본 논문에서는 가중 퍼지소속함수 기반 신경망 (Neural Network with Weighted Fuzzy Membership Functions; NEWFM)에서 제공하는 가중 퍼지소속함수의 경계합 (Bounded Sum of Weighted Fuzzy Membership functions, BSWFM)의 무게중심간의 거리를 이용한 새로운 특징 선택을 제안하여 분류 성능을 향상시켰다. 이러한 거리 기반의 특징 선택을 이용하여 초기 24개의 특징으로부터 무게중심간의 거리가 짧은 특징을 하나씩 제거되면서 분류 성능이 가능 높은 22개의 최소 특징을 선택하였다. 이들 22개의 최소 특징을 NEWFM의 입력으로 사용하여 97.7%, 99.7%, 98.7%의 민감도, 특이도, 정확도를 각각 구하였다.

Feature selection is the technique to improve the classification performance by using a minimal set by removing features that are not related with each other and characterized by redundancy. This study proposed new feature selection using the distance between the center of gravity of the bounded sum of weighted fuzzy membership functions (BSWFMs) provided by the neural network with weighted fuzzy membership functions (NEWFM) in order to improve the classification performance. The distance-based feature selection selects the minimum features by removing the worst features with the shortest distance between the center of gravity of BSWFMs from the 24 initial features one by one, and then 22 minimum features are selected with the highest performance result. The proposed methodology shows that sensitivity, specificity, and accuracy are 97.7%, 99.7%, and 98.7% with 22 minimum features, respectively.

키워드

참고문헌

  1. Admi, H. and Shaham, B., Living with epilepsy: ordinary people coping with extraordinary situations, Qualitative Health Research, Vol.17, pp.1178-1187, 2007. https://doi.org/10.1177/1049732307307548
  2. Korean Neurological Association. Neurology, Seoul: Koonja Publishing Co., 2007.
  3. Abdulhamit Subasi, EEG signal classification using wavelet feature extraction and a mixture of expert model, Expert Systems with Applications, Vol.32, Issue 4, pp.1084-1093, 2007. https://doi.org/10.1016/j.eswa.2006.02.005
  4. Sang-Hong Lee and Joon S. Lim, Extracting Input Features and Fuzzy Rules for Classifying Epilepsy Based on NEWFM, Journal of Internet Computing and Services, Vol.10, No.5, pp.127-133, 2009.
  5. Joon S. Lim, Finding Features for Real-Time Premature Ventricular Contraction Detection Using a Fuzzy Neural Network System, IEEE Transactions on Neural Networks, Vol.20, No.3, pp.522-527, 2009. https://doi.org/10.1109/TNN.2008.2012031
  6. Andrzejak, R. G., Lehnertz, K., Mormann, F., Rieke, C., David, P., and Elger, C. E., Indications of nonlinear deterministic and finite dimensional structures in time series of brain electrical activity: Dependence on recording region and brain state, Physical Review E, 64, 061907, 2001. https://doi.org/10.1103/PhysRevE.64.061907
  7. Minh Hoai Nguyen and Fernando de la Torre, Optimal feature selection for support vector machines, Pattern Recognition, Vol.43, pp.584-591, 2010. https://doi.org/10.1016/j.patcog.2009.09.003
  8. Patricia E.N. Lutu and Andries P. Engelbrecht, A decision rule-based method for feature selection in predictive data mining, Expert Systems with Applications, Vol.37, pp.602-609, 2010. https://doi.org/10.1016/j.eswa.2009.06.031
  9. Kabir M, Shahjahan, and Murase K, A new local search based hybrid genetic algorithm for feature selection, Neurocomputing, Vol.74, pp.2914-2928, 2011. https://doi.org/10.1016/j.neucom.2011.03.034
  10. Lee CP and Leu Y, A novel hybrid feature selection method for microarray data analysis, Applied Soft Computing, Vol.11, pp.208-213, 2011. https://doi.org/10.1016/j.asoc.2009.11.010
  11. F Shayegha, S Sadria, R Amirfattahia, K Ansari-Aslb. A model-based method for computation ofcorrelation dimension, Lyapunov exponents andsynchronization from depth-EEG signals, COMPUT METH PROG BIO, Vol.113, pp.323-337, 2014. https://doi.org/10.1016/j.cmpb.2013.08.014
  12. Guler NH, UbeyliED, Guler I. Recurrent neural networks employing Lyapunov exponents for EEG signal classification, Expert Sys Appl, Vol.25, pp.506-514, 2005.
  13. Lehnertz K, Elger CE. Spatio-temporal dynamics of the primary epileptogenic area in temporal lobe epilepsy characterized by neuronal complexity loss, Electroencephalogr Clin Neurophysiol, Vol.95, pp.108-117, 1995. https://doi.org/10.1016/0013-4694(95)00071-6
  14. Avci E, Hanbay D, Varol A. An expert discrete wavelet adaptive network based fuzzy inference system for digital modulation recognition, Expert Syst Appl, Vol.33, pp.582-589, 2007. https://doi.org/10.1016/j.eswa.2006.06.001
  15. Guler I, Ubeyli ED. Adaptive neuro-fuzzy inference system for classification of EEG signals using wavelet coefficients, J Neurosci Methods, Vol.148, pp.113-121, 2005. https://doi.org/10.1016/j.jneumeth.2005.04.013
  16. Chandaka S, Chatterjee A, Munshi S. Cross-correlation aided support vector machine classifier for classification of EEG signals, Expert Syst Appl, Vol.36, pp.1329-1336, 2009. https://doi.org/10.1016/j.eswa.2007.11.017
  17. Ling G., Daniel R., Jose A.S., Alejandro P. Classification of EEG Signals Using Relative Wavelet Energy and Artificial Neural Networks, GEC (June), pp.177-183, 2009.
  18. M. Setnes and H. Roubos, GA-Fuzzy Modeling and Classification : Complexity and Performance, IEEE Trans., Fuzzy Systems, Vol.8, No.5, pp.509-522, 2000. https://doi.org/10.1109/91.873575
  19. Kemal Polat and Salih Gunes, Artificial immune recognition system with fuzzy resource allocation mechanism classifier, principal component analysis and FFT method based new hybrid automated identification system for classification of EEG signals, Expert Systems with Applications, Vol.34, Issue 3, pp.2039-2048, 2008 https://doi.org/10.1016/j.eswa.2007.02.009