A Novel Hybrid Framework for Optimal Feature Selection and Classification of Human Activity Recognition

  • Authors

    • Nilam Dhatrak
    • Anil Kumar Dudyala
    2018-07-07
    https://doi.org/10.14419/ijet.v7i3.8.15221
  • feature selection, classification, Human Activity Recognition, SVM-RFE, BPSO.

  • Abstract

    In today’s world individuals health concern has improved a lot with the help of advancement in the technology. To monitor an age old person or a person with disability, now-a-days modern wearable smartphone devices are available in the market which are equipped with good collection of built in sensors that can be used for Human Activity Recognition (HAR). These type of devices generate lot of data with many number of features. When this data is used for classification, the classifier may be over trained or will definitely give high error rate. Hence, in this paper, we propose a two hybrid frameworks which gives us optimal number of features that can be used with different classifiers to recognize the Human Activity accurately. It is observed from our experiments that SVM was able to classify the HAR accurately.

     

     

  • References

    1. [1] JL Reyes-Ortiz,A Ghio,X Parra, D Anguita,J Cabestany, A Catala, “Human Activity and Motion Disorder Recognition: towards smarter Interactive Cognitive Environments,†InESANN Apr 2013.

      [2] P CasalE, O Pujol, P Radeva, “Human activity recognition from accelerometer data using a wearable device,â€. InIberian Conference on Pattern Recognition and Image Analysis, 8 June 2011, Springer, Berlin, Heidelberg, pp. 289-296.

      [3] G Chandrashekar,F Sahin, “A survey on feature selection methods,†Computers & Electrical Engineering, vol. 40, pp. 16-28, 1 Jan 2014.

      [4] L Cervante L, B Xue B, M Zhang M, L Shang L, “Binary particle swarm optimisation for feature selection: A filter based approach,†InEvolutionary Computation (CEC), IEEE Congress , 10 Jun 2012 , IEEE, pp. 1-8

      [5] J Kennedy, “Particle swarm optimization,†InEncyclopedia of machine learning 2011, Springer, US, pp. 760-766.

      [6] I Guyon,J Weston,S Barnhill,V Vapnik, “Gene selection for cancer classification using support vector machines,â€Machine learning vol. 46, pp. 389-422,1 Jan 2002.

      [7] Z Feng, L Mo, M Li, “A Random Forest-based ensemble method for activity recognition,†InEngineering in Medicine and Biology Society (EMBC), 37th Annual International Conference of the IEEE , IEEE, 25 Aug 2015,pp. 5074-5077.

      [8] I Jain, VK Jain, R Jain, “Correlation feature selection based improved-Binary Particle Swarm Optimization for gene selection and cancer classification,†Applied Soft Computing vol. 62, 1 Jan 2018, pp. 203-215.

      [9] J Wang, G Shan, X Duan, B Wen, “Improved SVM-RFE feature selection method for multi-SVM classifier,†InElectrical and Control Engineering (ICECE), IEEE, 16 Sep 2011,pp. 1592-1595.

      [10] D Anguita, A Ghio, L Oneto, FX Llanas Parra, JL Reyes Ortiz, “Energy efficient smartphone-based activity recognition using fixed-point arithmetic,†Journal of universal computer science vol. 19, 2013, pp. 1295-314.

      [11] L Breiman, “Random forests,†Machine learning vol. 45, 1 Oct 2001, pp. 5-32.

      [12] R Díaz-Uriarte, SA De Andres, “Gene selection and classification of microarray data using random forest,†BMC bioinformatics vol. 7, Dec 2006, pp. 3.

      [13] MT Uddin, MA Uddiny, “A guided random forest based feature selection approach for activity recognition,†InElectrical Engineering and Information Communication Technology (ICEEICT), IEEE, 21 May 2015, pp. 1-6

      [14] B Romera-Paredes, MS Aung, N Bianchi-Berthouze, “A one-vs-one classifier ensemble with majority voting for activity recognition,†InESANN 2013 proceedings, 21st European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning 11 Nov 2013, pp. 443-448.

      [15] Davide Anguita, Alessandro Ghio, Luca Oneto, Xavier Parra and Jorge L. Reyes-Ortiz, “A Public Domain Dataset for Human Activity Recognition Using Smartphones,†21th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, ESANN 2013. Bruges, Belgium 24-26 April 2013.

      [16] A Bayat, M Pomplun, DA Tran, “A study on human activity recognition using accelerometer data from smartphones,†Procedia Computer Science vol. 34,1 Jan 2014, pp. 450-457.

      [17] J Usharani, U Sakthivel, “Human Activity Recognition using Android Smartphone,†International Journal of Advanced Networking & Applications (IJANA) ISSN: 0975-0282.

      [18] MA Hall, “Correlation-based feature selection of discrete and numeric class machine learningâ€, In Proceedings of the Seventeenth International Conference on Machine Learning (ICML '00), Pat Langley (Ed.). Morgan Kaufmann Publishers Inc., San Francisco, CA, USA, 2000, pp. 359-366.

      [19] DN Tran, DD Phan, “Human activities recognition in android smartphone using support vector machine,†InIntelligent Systems, Modelling and Simulation (ISMS), 7th International Conference, IEEE, 25 Jan 2016, pp. 64-68.

      [20] H Peng, F Long, C Ding, “Feature selection based on mutual information criteria of max-dependency, max-relevance, and min-redundancy,†IEEE Transactions on pattern analysis and machine intelligence vol. 27, Aug 2005, pp. 1226-1238.

      [21] H Liu, R Setiono, “Incremental feature selection,†Applied Intelligence vol. 9, 1 Nov 1998, pp.217-230.

      [22] P. Bermejo, L. de la Ossa, J.A. Gámez, J.M. Puerta, “Fast wrapper feature subset selection in high-dimensional datasets by means of filter re-ranking,†Knowledge-Based Systems vol. 25, 2012, pp.35-44.

  • Downloads

  • How to Cite

    Dhatrak, N., & Kumar Dudyala, A. (2018). A Novel Hybrid Framework for Optimal Feature Selection and Classification of Human Activity Recognition. International Journal of Engineering & Technology, 7(3.8), 63-68. https://doi.org/10.14419/ijet.v7i3.8.15221

    Received date: 2018-07-06

    Accepted date: 2018-07-06

    Published date: 2018-07-07