شبکه عصبی فازی مین- ماکس چندسطحی با باکس‌های وزن‌دار
محورهای موضوعی : مهندسی برق و کامپیوتررضا داوطلب 1 , محمدعلی بالافر 2 , محمدرضا فیضی درخشی 3
1 - دانشگاه تبریز
2 - دانشگاه تبریز
3 - دانشگاه تبریز
کلید واژه: طبقه‌بندی شبکه عصبی فازی مین- ماکس یادگیری ماشین وزن‌دار,
چکیده مقاله :
در این مقاله شبکه عصبی فازی مین- ماکس چندسطحی با باکس‌های وزن‌دار (WL-FMM) برای استفاده در کلاس‌بندی ارائه می‌گردد که یک ابزار یادگیری با نظارت بسیار سریع بوده و قادر به یادگیری داده‌ها به صورت برخط و تک‌گذار است. در این روش برای حل مشکل نواحی همپوشان که از مشکلات همیشگی روش‌های فازی مین- ماکس بوده، از باکس‌هایی با اندازه کوچک‌تر و وزن بیشتر استفاده می‌شود. این کار باعث افزایش دقت طبقه‌بندی شبکه در نواحی مرزی نمونه‌ها می‌گردد. همچنین با توجه به تغییراتی که در ساختار الگوریتم داده شده و بر اساس نتایج آزمایشی به دست آمده، روش ارائه‌شده نسبت به روش‌های مشابه از پیچیدگی زمانی و مکانی کمتری برخوردار بوده و نسبت به پارامترهایی که از طرف کاربر مشخص می‌شود، حساسیت کمتری دارد.
In this paper a weighted Fuzzy min-max classifier (WL-FMM) which is a type of fuzzy min-max neural network is described. This method is a quick supervised learning tool which capable to learn online and single pass through data. WL-FMM uses smaller size with higher weight to manipulate overlapped area. According to experimental results, proposed method has less time and space complexity rather than other FMM classifiers, and also user manual parameters has less effect on the results of proposed method.
[1] L. A. Zadeh, "Fuzzy Sets," Inform. and Control, vol. 8, pp. 189-200, 1965.
[2] J. C. Bezdek, S. K. Pal, and IEEE Neural Networks Council., Fuzzy models for pattern recognition: methods that search for structures in data, New York: Institute of Electrical and Electronics Engineers, 1992.
[3] J. Vieira, F. M. Dias, and A. Mota, Neuro-Fuzzy Systems: A Survey, 2004.
[4] S. Mitra and Y. Hayashi, "Neuro-fuzzy rule generation: survey in soft computing framework," Neural Networks, IEEE Trans. on, vol. 11, no. 3, pp. 748-768, May 2000.
[5] D. Nauck and R. Kruse, What Are Neuro-Fuzzy Classifiers?, 1997.
[6] A. Bargiela, W. Pedrycz, and M. Tanaka, "An inclusion/exclusion fuzzy hyperbox classifier," International J. of Knowledge Based Intelligent Engineering Systems, vol. 8, no. 2, pp. 91-98, Aug. 2004.
[7] B. Gabrys and A. Bargiela, "General fuzzy min-max neural network for clustering and classification," IEEE Trans. on Neural Networks, vol. 11, no. 3, pp. 769-783, May 2000.
[8] A. V. Nandedkar and P. K. Biswas, "A fuzzy min-max neural network classifier with compensatory neuron architecture," IEEE Trans. on Neural Networks, vol. 18, no. 1, pp. 42-54, Jan. 2007.
[9] P. K. Simpson, "Fuzzy min-max neural networks I: classification," IEEE Trans. on Neural Networks, vol. 3, no. 5, pp. 776-786, Sep. 1992.
[10] A. Joshi, N. Ramakrishman, E. N. Houstis, and J. R. Rice, "On neurobiological, neuro-fuzzy, machine learning, and statistical pattern recognition techniques," IEEE Trans. on Neural Networks, vol. 8, no. 1, pp. 18-31, Jan. 1997.
[11] P. K. Simpson, "Fuzzy min-max neural networks, part 2, clustering," IEEE Trans. on Fuzzy Systems, vol. 1, no. 1, pp. 32-45, Feb. 1993.
[12] A. V. Nandedkar and P. K. Biswas, "A reflex fuzzy min max neural network for semi-supervised learning," J. of Intelligent Systems, vol. 17, no. 1, pp. 5-18, Aug. 2008.
[13] A. V. Nandedkar and P. K. Biswas, "A granular reflex fuzzy min-max neural network for classification," IEEE Trans. on Neural Networks, vol. 20, no. 7, pp. 1117-1134, Jul. 2009.
[14] H. Zhang, J. Liu, D. Ma, and Z. Wang, "Data-core-based fuzzy min-max neural network for pattern classification," IEEE Trans. on Neural Networks, vol. 22, no. 12, pp. 2339-2352, Nov. 2011.
[15] R. Davtalab, M. H. Dezfoulian, and M. Mansoorizadeh, "Multi-level fuzzy min-max neural network classifier," IEEE Trans. Neural Netw Learn Syst, vol. 25, no. 3, pp. 470-482, Mar. 2014.
[16] Q. Hua, "A new union-set learning algorithm in fuzzy min-max neural networks," Moshi Shibie yu Rengong Zhineng/Pattern Recognition and Artificial Intelligence, vol. 14, no. 4, p. 413, 2001.
[17] B. Gabrys, "Agglomerative learning algorithms for general fuzzy min-max neural network," J. of VLSI Signal Processing Systems for Signal, Image, and Video Technology, vol. 32, no. 1, pp. 67-82, Aug. 2002.
[18] A. V. Nandedkar and P. K. Biswas, "A general fuzzy min max neural network with compensatory neuron architecture," in Proc. Int. Conf. on Knowledge-Based and Intelligent Information and Engineering Systems, pp. 1160-1167, 2005.
[19] P. F. Peng, L. J. Yang, and Q. G. Zhang, "Improvement and application based on general fuzzy min-max neural network," Wuhan Ligong Daxue Xuebao/J. of Wuhan University of Technology, vol. 26, no. 10, p. 87, Oct. 2004.
[20] P. F. Peng, L. J. Yang, and Q. G. Zhang, "Unsupervised general fuzzy min-max artificial neural network," Xi Tong Gong Cheng Yu Dian Zi Ji Shu/Systems Engineering and Electronics, vol. 26, no. 10, pp. 1503-1505+1536, Oct. 2004.
[21] G. Tang, Y. Dai, and G. Liu, "Radar range profile classification based on fuzzy min-max neural networks," Binggong Xuebao/Acta Armamentarii, vol. 25, no. 2, pp. 218-221, Feb. 2004.
[22] H. J. Kim and H. S. Yang, "A weighted fuzzy min-max neural network and its application to feature analysis," in Proc. of the First Int. Conf. on Advances in Natural Computation, vol. 3, pp. 1178-1181, Changsha, China 27-29 Aug. 2005.
[23] C. C. Chen, "Design of a fuzzy min-max hyperbox classifier using a supervised learning method," Cybernetics and Systems, vol. 37, pp. 329-346, 2006.
[24] J. Hu, J. Yang, and J. Gao, "Ordination-fuzzy min-max neural network classifier on unlabelled pattern classification," Moshi Shibie yu Rengong Zhineng/Pattern Recognition and Artificial Intelligence, vol. 20, no. 2, pp. 173-179, Feb. 2007.
[25] J. Yang, J. Gao, X. H. Xu, and X. Liu, "Hierarchical fuzzy min-max clustering algorithm," Moshi Shibie yu Rengong Zhineng/Pattern Recognition and Artificial Intelligence, vol. 20, no. 4, pp. 558-564, Apr. 2007.
[26] A. Quteishat and C. P. Lim, "A modified fuzzy min-max neural network with rule extraction and its application to fault detection and classification," Applied Soft Computing J., vol. 8, no. 2, pp. 985-995, Mar. 2008.
[27] R. Zemouri, D. Racoceanu, N. Zerhouni, E. Minca, and F. Filip, "Training the recurrent neural network by the fuzzy min-max algorithm for fault prediction," in Proc. 2nd Mediterranean Conference on Intelligent Systems and Automation. CISA'09, pp. 85-90, Zarzis, Tunisia, 23-25 Mar. 2009.
[28] X. Ge and E. J. Ding, "Research on parameters of fuzzy min-max neural networks," Kongzhi yu Juece/Control and Decision, vol. 25, no. 8, pp. 295-298, Aug. 2010.
[29] A. Quteishat, C. P. Lim, and K. S. Tan, "A modified fuzzy min-max neural network with a genetic-algorithm-based rule extractor for pattern classification," IEEE Trans. on Systems, Man, and Cybernetics Part A: Systems and Humans, vol. 40, no. 3, pp. 641-650, May 2010.
[30] P. Rey-del-Castillo and J. Cardenosa, "Fuzzy min-max neural networks for categorical data: application to missing data imputation," Neural Computing and Applications, vol. 21, no. 6, pp. 1349-1362, Sep. 2012.
[31] R. Davtalab, M. Parchami, M. H. Dezfoulian, M. Mansourizade, and B. Akhtar, "M-FMCN: modified fuzzy min-max classifier using compensatory neurons," in the Proc. of the 11th WSEAS International Conf. on Artificial Intelligence, Knowledge Engineering and Data Bases, Cambridge, UK, pp. 77-82, Feb. 2012.
[32] C. Blake, E. Keogh, and C. Merz, UCI Repository of Machine Learning Databases, Irvine: Department of Information and Computer Science, University of California, 1998.
