Ml-KNN Algorithm Based on Frequent Item Sets

Abstract:

In order to solve the problem of ignoring the correlation between class labels, this paper describes a new method for multi-label classification based on the frequent item sets to classify an unseen instance on the basis of its k nearest neighbors ( MLFI-KNN). For each unseen instance, MLFI-KNN takes its k-nearest neighbors in the training set and counts the number of occurrences of each label in this neighborhood, and then utilizes the FP-growth algorithm to obtain the frequent item sets between the labels that these neighboring instances include, in order to determine the predicted label set. Experiments on benchmark dataset demonstrate the effectiveness of the proposed approach as compared to some existing well-known methods.

• Periodical: Applied Mechanics and Materials (Volumes 380-384)
• Pages: 1533-1537
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.380-384.1533
• Online since: August 2013
• Authors: Jia Li Mao, Hong Ying Jin, Ming Dong Li, Jia Li
• Keywords: Frequent Item Set, KNN, Multi-Label Classification

References

[1] Shantanu Godbole and Sunita Sarawagi, Discriminative methods for multi-labeled classification, " In PAKDD , 04: 8th Pacific-Asia Conference on Knowledge Discovery and Data Mining, p.22–30. Springer, (2004).

DOI: 10.1007/978-3-540-24775-3_5

[2] Celine Vens, Jan Struyf, Leander Schietgat, Saˇso Dˇzeroski, and Hendrik Block-eel. Decision trees for hierarchical multi-label classification, Machine Learning, 2(73), p.185–214, August (2008).

DOI: 10.1007/s10994-008-5077-3

[3] Tsoumakas G, Katakis I, Multi-label classification: An overview, International Journal of Data Warehousing and Mining, pp.1-13, 2007, 3(3).

DOI: 10.4018/jdwm.2007070101

[4] M.L. Zhang, Z.H. Zhou, ML-kNN: A lazy learning approach to multi-label learning, Pattern Recognition , pp.2038-2007, 40(7).

DOI: 10.1016/j.patcog.2006.12.019

[5] B. Liu, W. Hsu, and Y. Ma, Integrating classification andassociation rule mining, In Knowledge Discovery and DataMining, p.80–86, (1998).

[6] Junming Xu, Yuan Jiang, Zhihua Zhou, Bayesian Classifier Based on Frequent Item Sets Mining, Journal of Computer Research and Development, pp.1293-1300, 2007, 44(8).

DOI: 10.1360/crad20070803

[7] Xiaoyong LV , Hongbo SHI, Multi-label Text Classification Algorithm Based on Frequent Item Sets, Computer Engineering, pp.83-85, 2010, 36(15).

[8] Grigorios, Tsoumakas, and Ioannis Katakis, Multi label classification: An overview, International Journal of Data Warehousing and Mining, pp.1-13, 2007, 3(3).

DOI: 10.4018/jdwm.2007070101

[9] http: / www. daviddlewis. Com /resources /testcollections /~reuters21578.

[10] M. F. Porter, An algorithm for suffix stripping, Readings in information retrieval, p.313–316, (1997).

[11] A. Elisseeff and J. Weston, A kernel method for multi-labeled classification, Proceedings of Advances in Neural Information Processing Systems, Canada: Vancouver, VOI. 14, pp.681-687, Dec. (2003).