Classification of Human Activities Using Extreme Learning Machine and Information Gain Feature Selection
Abstract
Human activity recognition has various benefits in daily lives. However, research in this area is still facing problems that is, unobtrusive data gathering, high dimensionality features, and the algorithm used to classify human activities. Those problems could impact in the result of the developed model. This research is a preliminary study in human activity recognition. Five common human activity will be recognized that is, walking, walking upstairs, walking downstairs, sitting, and standing. The dataset used in this study consist of 1500 data rows and 561 features. Feature selection is performed prior to the modeling step. Information Gain is used as the feature selection in which percentile method is used to subset the number of features in the dataset. The features are then normalized and will classified using ELM. Number of optimal hidden neuron will be searched to yield high predictive accuracy. The results show 240 feature subsets return the higher accuracy. A number of 100 hidden neuron results in highest predictive classification of human activity recognition. The classification results yield accuracy, precision, recall, and F1-score of 0.85.
References
A. Perez, M. Labrador, dan S. Barbeau, “G-Sense: A Scalable Architecture for Global Sensing and Monitoring,” IEEE Network, Vol. 24, No. 4, hal. 57–64, 2010.
T. Starner, B. Rhodes, J. Weaver, dan A. Pentland, ”Everyday-user Wearable Computers,” Int. Symp. on Wearable Comput., 1999, hal. 1-12.
P. Dohnalek, P. Gajdos, T. Peterek, dan V. Snasel, ”An Overview of Classification Techniques for Human Activity Recognition,” Vibroengineering PROCEDIA, Vol. 2, hal. 117-122, 2013.
M. Vrigkas, C. Nikou, dan I.A. Kakadiaris, “A Review of Human Activity Recognition Methods,” Frontiers in Robotics and AI, Vol. 2, hal. 1-28, 2015.
P. Paliyawan, C. Nukoolkit, dan P. Mongkolnam, “Prolonged Sitting Detection for Office Workers Syndrome Prevention Using Kinect,” 2014 11th Int. Conf. on Elec. Eng./Electron., Comput., Telecom. and Inf. Technol. (ECTI-CON), 2014, hal. 1-6.
Y. Jia, “Diatetic and Exercise Therapy against Diabetes Mellitus,” 2009 Second Int. Conf. on Intel. Net. and Intel. Sys., 2009, hal. 693-696.
J. Yin, Q. Yang, dan J. Pan, “Sensor-Based Abnormal Human-Activity Detection,” IEEE Trans. on Knowledge and Data Eng., Vol. 20, No. 8, hal. 1082–1090, 2008.
E. Kim, S. Helal, dan D. Cook, “Human Activity Recognition and Pattern Discovery,” IEEE Pervasive Comput., Vol. 9, No. 1, hal. 48–53, 2010.
T.D. Le dan C.V. Nguyen, “Human Activity Recognition by Smartphone,” 2015 2nd Nat. Found. for Sci. and Technol. Dev. Conf. on Inf. and Comput. Sci. (NICS), 2015, hal. 219-224.
W.C. Hung, F. Shen, Y.L. Wu, M.K. Hor, dan C.Y. Tang, “Activity Recognition with Sensors on Mobile Devices,” 2014 Int. Conf. on Mach. Learn. and Cybernetics, 2014, hal. 449-454.
M. Zhang, dan A.A. Sawchuk, “A Feature Selection-based Framework for Human Activity Recognition Using Wearable Multimodal Sensors,” BodyNets 2011, 2011, hal. 92-98.
G. De Leonardis, R. Samanta, B. Gabriella, A. Valentina, E. Panero, G. Laura, dan K. Marco, “Human Activity Recognition by Wearable Sensors: Comparison of Different Classifiers for Real-time Applications,” 2018 IEEE Int. Symp. on Med. Meas. and Appl. (MeMeA), 2018, hal. 1-6.
X. Su, T. Hanghang, dan J. Ping, “Activity Recognition with Smartphone Sensors,” Tsinghua Sci. and Technol., Vol. 19, No. 3, hal. 235-249, 2014.
A. Jain dan V. Kanhangad, “Human Activity Classification in Smartphones Using Accelerometer and Gyroscope Sensors,” IEEE Sensors J., Vol. 18, No. 3, hal. 1169-1177, 2017.
H. Ghasemzadeh dan J. Roozbeh, “Physical Movement Monitoring Using Body Sensor Networks: A Phonological Approach to Construct Spatial Decision Trees,” IEEE Trans. on Ind. Inform., Vol. 7, No. 1, hal. 66-77, 2011.
D. Anguita, G. Alessandro, O. Luca, P. Xavier, dan J.L. Reyes-Ortiz, “A Public Domain Dataset for Human Activity Recognition Using Smartphones,” European Symp. on Artif. Neural Net., Comput. Intel. and Mach. Learning (ESANN), 2013, hal. 437-442.
G.B. Huang, Q.Y. Zhu, dan C.K. Siew, “Extreme Learning Machine: A New Learning Scheme of Feedforward Neural Networks,” 2004 IEEE Int. Joint Conf. on Neural Net. (IEEE Cat. No. 04CH37541), 2004, hal. 985-990.
© Jurnal Nasional Teknik Elektro dan Teknologi Informasi, under the terms of the Creative Commons Attribution-ShareAlike 4.0 International License.
1.png)
