Browse > Article
http://dx.doi.org/10.3837/tiis.2013.11.018

A Genetic Algorithm-based Classifier Ensemble Optimization for Activity Recognition in Smart Homes  

Fatima, Iram (Department of Computer Engineering, Kyung Hee University)
Fahim, Muhammad (Department of Computer Engineering, Kyung Hee University)
Lee, Young-Koo (Department of Computer Engineering, Kyung Hee University)
Lee, Sungyoung (Department of Computer Engineering, Kyung Hee University)
Publication Information
KSII Transactions on Internet and Information Systems (TIIS) / v.7, no.11, 2013 , pp. 2853-2873 More about this Journal
Abstract
Over the last few years, one of the most common purposes of smart homes is to provide human centric services in the domain of u-healthcare by analyzing inhabitants' daily living. Currently, the major challenges in activity recognition include the reliability of prediction of each classifier as they differ according to smart homes characteristics. Smart homes indicate variation in terms of performed activities, deployed sensors, environment settings, and inhabitants' characteristics. It is not possible that one classifier always performs better than all the other classifiers for every possible situation. This observation has motivated towards combining multiple classifiers to take advantage of their complementary performance for high accuracy. Therefore, in this paper, a method for activity recognition is proposed by optimizing the output of multiple classifiers with Genetic Algorithm (GA). Our proposed method combines the measurement level output of different classifiers for each activity class to make up the ensemble. For the evaluation of the proposed method, experiments are performed on three real datasets from CASAS smart home. The results show that our method systematically outperforms single classifier and traditional multiclass models. The significant improvement is achieved from 0.82 to 0.90 in the F-measures of recognized activities as compare to existing methods.
Keywords
Activity recognition; Classifier ensemble; Weisghted classification; Genetic algorithm; Smart Homes;
Citations & Related Records
연도 인용수 순위
  • Reference
1 M.C. Mozer, The Adaptive House. [Online]. http://www.cs.colorado.edu/-mozer/index.php?dir=/Research/Projects/Adaptive (accessed Sept. 10, 2012).
2 R.C. Parisa, J.H. Diane, B. Lawrence and S. Maureen "Discovering Activities to Recognize Track in a Smart Environment". IEEE Transactions on Knowledge and Data Engineering, vol. 23, no. 4, pp.527-539, 2011.   DOI   ScienceOn
3 D. Cook, CASAS Smart Home project. [Online]. http://www.ailab.wsu.edu/casas/ (accessed Sept. 10, 2012).
4 B. Jones Aware Home. [Online]. http://awarehome.imtc.gatech.edu/ (accessed Sept. 10, 2012).
5 K. Larson House_n. [Online]. http://architecture.mit.edu/house_n/ (accessed Sept. 10, 2012).
6 T. Kasteren, A .Noulas, G. Englebienn and K. Ben "Accurate Activity Recognition in a Home Setting," in Proc. of the Tenth International Conference on Ubiquitous Computing, Korea, pp. 1-9, 2008.
7 T.L.M. Kasteren, G. Englebienne and B.J.A. Krose "An Activity Monitoring System for Elderly Care using Generative and Discriminative Models", Personal and Ubiquitous Computing, vol. 14, no. 6, pp. 489-498. 2010.   DOI   ScienceOn
8 M. A. Seenay and I. Sminu. "A Survey: Evaluation of Ensemble Classifiers and Data Level Methods to Deal with Imbalanced Data Problem in Protein Protein Interactions", Review of Bioinformatics and Biometrics (RBB), vol 2 no. 1, pp. 2013.
9 L. Bull, M. Studley, A. Bagnall and I. Whittley, "Learning Classifier System Ensembles with Rule-Sharing". IEEE Transactions on Evolutionary Computation, vol. 11, no. 4, pp. 496-502, 2007.   DOI   ScienceOn
10 X. Rongwu and H. Lin. "GACEM: Genetic Algorithm Based Classifier Ensemble in a Multi-sensor System", Sensors ,vol. 8, no.10, pp. 6203-622, 2008.   DOI
11 K. Kyung-Joong and C. Sung-Bae, "An Evolutionary Algorithm Approach to Optimal Ensemble Classifiers for DNA Microarray Data Analysis". IEEE Transactions on Evolutionary Computation, vol. 12, no. 3, pp. 377-388, 2008.   DOI   ScienceOn
12 L. Chen, C.D. Nugent and H. Wang. "A Knowledge-Driven Approach to Activity Recognition in Smart Homes". IEEE Transactions on Knowledge and Data Engineering, vol. 24, no. 6, pp. 961-974, 2011.
13 L. Chen and C.D. Nugent, "Ontology-based activity recognition in intelligent pervasive environments:. Int. J. Web Inf. Syst., vol. 5, no. 4, pp. 410-430, 2009.   DOI
14 G. Okeyo, L. Chen, and H. Wang, "Ontology-based learning framework for activity assistance in an adaptive smart home, in Activity Recognition in Pervasive Intelligent Environments", Atlantis Ambient and Pervasive Intelligence, vol 4, pp. 237-262, 2011.   DOI
15 C. Liming, H. Jesse, D.N. Chris, J.C. Diane and Y. Zhiwen, "Sensor-Based Activity Recognition", IEEE Transactions on Systems, Man, and Cybernetics,vol. 99, pp. 1-19, 2012.
16 M. H. Kamrul Hasan and L. Sungyoung, L. Young-Koo Lee, "Using Sensor Sequences for Activity Recognition by Mining and Multi-Class Adaboost", The 2010 International Conference on Artificial Intelligence, Las Vegas, USA, pp. 735-740., 2010.
17 T. Mitchell, Machine Learning. McGraw Hill, Columbus, 1997.
18 Neural Network Toolbox [Online]. http://www.mathworks.co.kr/products/neural-network/index.html (accessed Sept. 10, 2012).
19 B.J.A. Krose, T.L.M. Kasteren, C.H.S. Gibson and T. Dool, "CARE: Context Awareness in Residences for Elderly," in Proc. of 6th International Conference of the International Society for Gerontechnology, pp. 101-105, 2008.
20 J.K. Aggarwal and M.S. Ryoo, "Human activity analysis: A review", ACM Comput. Survey, vol. 43, no. 3, pp. 1-43, 2011.
21 S. Helal, E. Kim and S. Hossain. "Scalable Approaches to Activity Recognition Research," in Proc. of the workshop of How to do good activity recognition research? Experimental methodologies, evaluation metrics, and reproducibility issues, pp. 450-453, 2010.
22 A. Fleury, M. Vacher and N. Noury "SVM-Based Multimodal Classification of Activities of Daily Living in Health Smart Homes: Sensors, Algorithms, and First Experimental Results". IEEE Transactions on Information Technology in Biomedicine, vol. 14, no. 2, pp.274-83, 2010.   DOI   ScienceOn
23 A. Ekbal and S. Saha, "Weighted Vote-Based Classifier Ensemble for Named Entity Recognition: A Genetic Algorithm-Based Approach". ACM Trans. Asian Lang. Inf. Process. vol. 10, no. 2, pp. 1-37., 2011.
24 M. Behrouz, K. Gerd and F. William, "Optimizing classification ensembles via a genetic algorithm for a web-based educational system," in Proc. of the International Workshop on Syntactical and Structural Pattern Recognition and Statistical Pattern Recognition, pp. 397-406, 2004.
25 M. Kim, S. Min and I. Han. "An evolutionary approach to the combination of multiple classifiers to predict a stock price index". Expert Systems with Applications. vol. 31, no. 2 pp. 241-247 , 2006.   DOI   ScienceOn
26 M. Bahrepour, N. Meratnia, Z. Taghikhaki and P.J.M. Havinga. "Sensor Fusion-based Activity Recognition for Parkinson Patients". Sensor Fusion - Foundation and Applications. InTech, pp. 171-190. ISBN: 978-953-307-446-7
27 A.B. Jon , K. Josef and R. Fabio, "Multiple Classifier Systems", Lecture Notes in Computer Science, 5519, Iceland, Springer, 540, 2009
28 L.I. Kuncheva and L.C. Jain. "Designing classifier fusion systems by genetic algorithms". IEEE Transactions on Evolutionary Computation, vol. 4, no. 4, pp. 327-336, 2000.   DOI   ScienceOn
29 M. Piccardi, "Hidden Markov Models with Kernel Density Estimation of Emission Probabilities and their Use in Activity Recognition". In proceeding of IEEE conference of Computer Vision and Pattern Recognition, pp. 1 - 8, 2007.
30 LIBSVM [Online]. http://www.csie.ntu.edu.tw/-cjlin/libsvm/(accessed Sept. 10, 2012).
31 crfChain [Online]. http://www.di.ens.fr/-mschmidt/Software/crfChain.html (accessed Sept. 10, 2012).
32 UGM [Online]. http://www.di.ens.fr/-mschmidt/Software/UGM.html (accessed Sept. 10, 2012).
33 S. Guan and F. Zhu, "An incremental approach to genetic-algorithms-based classification:. IEEE Transactions on Systems, Man, and Cybernetics, vol.35, no 2, pp. 227-239, 2005.   DOI   ScienceOn
34 T.L.M Kasteren, H. Alemdar and C. Ersoy, "Effective Performance Metrics for Evaluating activity Recognition Methods". In proceedings of 2nd Workshop on Context-Systems Design", Evaluation and Optimization. Italy , (2011).
35 D. Ruta and B. Gabrys, "Classifier Selection for Majority Voting". Information fusion, vol. 6, no.1, pp. 63-81, 2005.   DOI   ScienceOn