Bulanık Sınıflandırma için Yeni Bir Üyelik Fonksiyon Tanımlaması

Bu çalışmada gözetimli öğrenme yaklaşımı kullanılarak bulanık kümeler için yeni bir üyelik fonksiyonu tanımlanmıştır. İlk olarak, gözetimli öğrenme yaklaşımında, eğitim veri kümesi, önceden tanımlanmış çokyüzlü konik fonksiyonlarla ayrılmış ve daha sonra elde edilen bu çokyüzlü konik fonksiyonlar yeni bir üyelik fonksiyonu tanımlamak için kullanılmıştır. Sonrasında ise bu fonksiyon kullanılarak benzer yapıda bulanık kümeleri sınıflandırmak için yeni bir bulanık sınıflandırma algoritması tanımlanmıştır. Önerilen tüm yöntemler bir algoritmada birleştirilerek, veri kümeleri üzerinde denenmiş ve performans değerleri, literatürde yer alan sınıflandırma algoritmalarıyla karşılaştırılmıştır.

A Novel Membership Function Definition for Fuzzy Classification

In this paper, a novel membership function is defined for fuzzy sets using a supervised learning approach. Firstly, the training dataset is separated using the previously defined polyhedral conic functions in a supervised learning approach. Then obtained polyhedral conic functions are used for defining a new membership function. After that, a new fuzzy classification algorithm is formed to classify fuzzy sets with a similar structure. The algorithm with all suggested methods is implemented on real-world datasets, and the performance values are compared with the state of art classification algorithms.

___

  • Alpaydın, E. (2010). Introduction to Machine Learning (2nd ed.). Cambridge, MA, USA: The MIT Press.
  • Azam, M. H., Hasan, M. H., Kadir, S. J. A., & Hassan, S. (2021). Prediction of sunspots using fuzzy logic: A triangular membership function-based fuzzy C-means approach. International Journal of Advanced Computer Science and Applications, 12(2), 357-362. doi:10.14569/IJACSA.2021.0120245
  • Bhattacharyya, R. & Mukherjee, S. (2020). Fuzzy membership function evaluation by non-linear regression: An algorithmic approach. Fuzzy Information and Engineering, 12(4), 412-434. doi:10.1080/16168658.2021.1911567
  • Borkar, S. & Rajeswari, K. (2013). Predicting students academic performance using education data mining. IJCSMC International Journal of Computer Science and Mobile Computing, 2(7), 273 279.
  • Cao, X. H., Stojkovic, I., & Obradovic, Z. (2016). A robust data scaling algorithm to improve classification accuracies in biomedical data. BMC Bioinformatics, 17(1), 359. doi:10.1186/s12859-016-1236-x
  • Gasimov, R. N., & Ozturk, G. (2006). Separation via polyhedral conic functions. Optimization Methods and Software, 21(4), 527-540. doi:10.1080/10556780600723252
  • Jamsandekar, S. & Mudholkar, R. R. (2014). Fuzzy classification system by self generated membership function using clustering technique. International Journal of Information Technology, 6(1), 697-704.
  • Makrehchi, M. & Kamel, M. S. (2011). An information theoretic approach to generating fuzzy hypercubes for if-then classifiers. Journal of Intelligent & Fuzzy Systems, 22(1), 33-52. doi:10.3233/IFS-2010-0472
  • Mendes, R. R. F., de Voznika, F. B., Freitas, A. A., & Nievola, J. C. (2001, September). Discovering fuzzy classification rules with genetic programming and co-evolution. Paper presented at Principles of Data Mining and Knowledge Discovery, PKDD 2001, Freiburg, Germany. doi:10.1007/3-540-44794-6_26
  • Ozturk, G., & Citfci, M. (2015). Clustering based polyhedral conic functions algorithm in classification. Journal of Industrial and Management Optimization, 11(3), 921-932. doi:10.3934/jimo.2015.11.921
  • Rapheal, A. B. & Bhattacharya, S. (2020, January). A Study on the effect of fuzzy membership function on fuzzified RIPPER for stock market prediction. Paper presented at 4th International Conference on Machine Learning and Soft Computing, Copenhagen, Denmark. doi:10.1145/3380688.3380716
  • Sanz, J., Fernandez, A., Bustince, H., & Herrera, F. (2010, July). A genetic algorithm for tuning fuzzy rule-based classification systems with interval-valued fuzzy sets. Paper presented at WCCI 2010 IEEE World Congress on Computational Intelligence, Barcelona, Spain. doi:10.1109/FUZZY.2010.5584097
  • Satı N. U. (2020). A novel semisupervised classification method via membership and polyhedral conic functions. Turkish Journal of Electrical Engineering and Computer Sciences, 28(1), 80-92. doi:10.3906/elk-1905-45.
  • Singh, H., Gupta, M. M., Meitzler, T., Hou, Z. G., Garg, K. K., Solo, A. M. G., & Zadeh, L. A. (2013). Real-life applications of fuzzy logic. Advances in Fuzzy Systems, 2013, 581879. doi:10.1155/2013/581879
  • Uylaş Satı, N. (2015). A binary classification algorithm based on polyhedral conic functions. Düzce Üniversitesi Bilim ve Teknoloji Dergisi, 3(1), 152-161. Retrieved from https://dergipark.org.tr/en/pub/dubited/issue/4809/66263.
  • Xie, W. B., Sang, S., Lam, H. K. & Zhang, J., (2021). A polynomial membership function approach for stability analysis of fuzzy systems. IEEE Transactions on Fuzzy Systems, 29(8), 2077-2087. doi:10.1109/TFUZZ.2020.2991149