Optimal Feature Selection in Stream Data Classification Using Improved Ensemble Classifier for High Dimension Data
Keywords:
Stream Data Classification, POS, Ensemble, Optimal Feature, Genetic Algorithm (GA)Abstract
Dynamic feature evaluation and concept evaluation is major challenging task in the field of stream data classification. The continuity of data induced a new feature during classification process, but the classification process is predefined task for assigning data into class. Stream data comes into multiple feature sub-set format into infinite length. The infinite length not decided the how many class are assigned. Genetic algorithm is well known population based method. The performance of genetic algorithm is better than other optimization technique such as POS and ANT colony optimization. The dynamic nature of genetic algorithm maintains the dynamic feature evaluation. The optimization process goes through multiple stages in terms of selection of feature and optimization of feature. The optimized feature reduces the unclassified region of class during classification. The proposed method for stream data classification is MMCM-GA is implemented in MATLAB 7.8.0. And test the validation process used some reputed data set from UCI machine learning prosperity. These data are corpus, forest and finally used glass dataset. Our empirical evaluation of result shows better feature evaluation and minimization of error rate in comprehension of MCM stream data classification
References
Dayong Wang, Pengcheng Wu, Peilin Zhao, Yue Wu, Chunyan Miao, Steven C.H. Hoi “High-dimensional Data Stream Classification via Sparse Online Learning” IEEE International Conference on Data Mining, 2014. Pp 1007-1012.
Mohammad M. Masud,Jing Gao, Latifur Khan, , Jiawei Han and Bhavani Thurai singham “Classification and Novel Class Detection in Concept-Drifting Data Streams under Time Constraints” IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING, VOL. 23, NO. 6, JUNE 2011. Pp 859-874.
Ge Song, Yunming Ye “A New Ensemble Method for Multi-label Data Stream Classification in Non-stationary Environment” 2014 International Joint Conference on Neural Networks July 6-11, 2014, Beijing, China, Pp 1776-1783.
Rashmi Dutta Baruah, PlamenAngelov, Diganta Baruah “Dynamically Evolving Fuzzy Classifier for Real-time Classification of Data Streams” IEEE International Conference on Fuzzy Systems (FUZZ-IEEE) , July 6-11, 2014, Beijing, China , Pp 383-389.
Justin Ma, Alex Kulesza, Mark Dredze, Koby Crammer, Lawrence K. Saul, Fernando Pereira “Exploiting Feature Covariance in High-Dimensional Online Learning” 2009, Pp 493-500.
Mohammad M. Masud , Qing Chen , Latifur Khan, Charu Aggarwal ,Jing Gao, Jiawei Han and Bhavani Thurai singham “Addressing Concept-Evolution in Concept-Drifting Data Streams” 2009, Pp 124-130
Mohammad M. Masud, Tahseen M. Al-Khateeb, Latifur Khan,Charu Aggarwal, Jing Gao Jiawei Hanand Bhavani Thuraisingham“Detecting Recurring and Novel Classes in Concept-Drifting Data Streams” 2012. Pp 897-902.
Mohammad M. Masud, Qing Chen, Jing Gao, Latifur Khan, Jiawei Han, and Bhavani Thuraisingham “Classification and Novel Class Detection of Data Streams in a Dynamic Feature Space” J.L. Balcazar et al. (Eds.): ECML PKDD 2010, Pp. 337–352.
Zhihui Lai, Zhong Jin, Jian Yang, W.K Wong “Sparse Local Discriminant Projections for Face Feature Extraction” IEEE, 2010, Pp1051-1060.
Clay Woolam, Mohammad M. Masud, and Latifur Khan “Lacking Labels in the Stream: Classifying Evolving Stream Data with Few Labels” 2009, LNAI 5722. Pp. 552–562.
Li Su, Hong-yanLiu, Zhen-Hui Song, “A New Classification Algorithm for Data Stream” , I.J.Modern Education and Computer Science, 2011. Pp 32-39
Manjeet Kaur, Manoj agnihotri “A Hybrid technique using Genetic algorithm and ANT colony optimization for improving in cloud datacenter”. IJCSE, Volume 04, Issue-08.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors contributing to this journal agree to publish their articles under the Creative Commons Attribution 4.0 International License, allowing third parties to share their work (copy, distribute, transmit) and to adapt it, under the condition that the authors are given credit and that in the event of reuse or distribution, the terms of this license are made clear.
