Abstract
Perceiving human activity has earned a great amount of interest and has brought noteworthy research in recognizing logical data helpful to human activity recognition. It is the most essential technology behind different applications including health care, survey systems, surveillance, and many more. This paper presents work on human activity detection based on data collected from smartphones inertial sensors. Smartphones have installed inbuilt sensors that are fit to detect logical data of its clients, having a wide range capability of network connections. Installed sensors which include gyroscope sensor, tri-axial linear accelerometer, tri-axial accelerometer, and direction sensors are utilized for movement information assortment. Dataset used includes six activities: sitting, standing, laying, walking, walking upstairs and walking downstairs. In this paper, support vector machine learning algorithm with Gaussian radial basis kernel to classify all the six activities uniquely is used which resulted in better performance rate and less error rate as compared to the previous works already done in the area of HAR. Overlapping of dynamic and non-dynamic activity is improved with the overall accuracy of 98% which is more than the previous work results.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
WHO: World Population Ageing. Technical Report, UN World Health Organization, vol. 374, pp. 1–95 (2013)
Zheng, Y.: HAR Based on the Hierarchical Feature Selection and Classification Framework. J. Electr. Comput. Eng. (2015)
Nguyen, H.-D., Tran, K.P., Zeng, X., Koehl, L.: Wearable Sensor Data Based Human Activity Recognition Using ML: A New Approach (2019)
Wang, L., Gu, T., Chen, H., Tao, X., Lu, J.: Real-time activity recognition in wireless body sensor networks: from simple gestures to complex activities. In: 6th IEEE International Conference on Real-Time Computing Systems and Applications (2010)
Corchado, J.M., Bajo, J., Tapia, D., Abraham, A., et al.: Using heterogeneous wireless sensor networks in a telemonitoring system for healthcare. IEEE Trans. Inform. Technol. Biomed. 14(2), 234–240 (2010)
Curone, D., Bertolotti, G.M., Cristiani, A., Secco, E.L., Magenes, G.: A real-time and self-calibrating algorithm based on triaxial accelerometer signals for the detection of human posture and activity. IEEE Trans. Inf Technol. Biomed. 14(4), 1098–1105 (2010)
Palaniappan, A., Bhargavi, R., Vaidehi, V.: Abnormal human activity recognition using SVM based approach. In: ICRTIT-2012 IEEE International Conference (2012)
Shin, J.H., Lee, B., Park, K.S.: Detection of abnormal living patterns for elderly living alone using support vector data description. IEEE Trans. Inform. Technol. Biomed. 15(3), 438–448 (2011)
Ann, O.C., Theng, L.B.: Human activity recognition: a review. In: Control System, Computing and Engineering (ICCSCE), 2014 IEEE International Conference (2014)
Bülbül, E., Çetin, A., Doğru, İ.A.: HAR Using Smartphones. IEEE (2018)
Tran, D.N., Phan, D.D.: Human Activities Recognition in Android Smartphone Using Support Vector Machine. University of IT Ho Chi Minh, Vietnam (2016)
Yin, X., Shen, W., Samarabandu, J., Wang, X.: Human Activity Detection Based on Multiple Smart Phone Sensors and Machine Learning Algorithms. University of West em Ontario London, Canada. 2015 IEEE 19th International Conference on (CSCWD)
Rasekh, A., Chen, C.A., Lu, Y.: Human Activity Recognition Using Smartphone. Texas A&M University, Fall CSCE666 Project Report (2011)
Anguita, D., Ghio, A., Oneto, L., Parra, X., Reyes-Ortiz, J.L.: A Public Domain Dataset for Human Activity Recognition Using Smartphones. 21st ESANN 2013. Bruges, Belgium 24–26 April 2013
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Swarnakar, S.K., Agrawal, H., Goel, A. (2021). Smartphone Inertial Sensors-Based Human Activity Detection Using Support Vector Machine. In: Sharma, T.K., Ahn, C.W., Verma, O.P., Panigrahi, B.K. (eds) Soft Computing: Theories and Applications. Advances in Intelligent Systems and Computing, vol 1381. Springer, Singapore. https://doi.org/10.1007/978-981-16-1696-9_22
Download citation
DOI: https://doi.org/10.1007/978-981-16-1696-9_22
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-16-1695-2
Online ISBN: 978-981-16-1696-9
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)