Abstract
The global statistics on health monitoring show that 15% of humans in the world live with some kind of disability. One of the fundamental rights of such people is the existence of companion to supervise their day-to-day activities. Smartphones are beneficial for this purpose of monitoring human activity and provide means that give high accuracy while estimating activities. Sensors such as accelerometer and gyroscope available in any smartphone can be used to record basic activities like walking, sitting, standing, etc., with the ones that involve postural transitions for example sit-to-lie, stand-to-sit, etc. This paper proposes a methodology in order to overcome the difficulty that lies in recognition of such activities with transitions using filtering, windowing and outlier detection. The results of the proposed methodology show that logistic regression classifier provides the highest accuracy of 96.16%. The analysis and approach outperform in comparison with the previous works of the researchers.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Anguita, D., Ghio, A., Oneto, L., Parra, X., Reyes-Ortiz, J.L.: Human activity recognition on smart phones using a multiclass hardware-friendly support vector machine. In: International Workshop of Ambient Assisted Living (IWAAL2012), Vitoria-Gasteiz, pp. 216–223, Spain (2012)
Anguita, D., Ghio, A., Oneto, L., Parra, X., Reyes-Ortiz, J.L.: A public domain dataset for human activity recognition using smart phones. In: 21st European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, Bruges, pp. 437–442, Belgium (2013)
Reyes-Ortiz, J.-L., Oneto, L., Ghio, A., Samá, A., Anguita, D., Parra, X.: Human activity recognition on smart phones with awareness of basic activities and postural transitions. In: Artificial Neural Networks and Machine Learning ICANN 2014, Lecture Notes in Computer Science, pp. 177–184, Springer (2014)
Zhang, S., Wei, Z., Nie, J., Huang, L., Wang, S., Li, Z.: A review on human activity recognition using vision-based method. J. Healthcare Eng. 2017, 1–31 (2017)
Xu, S., Tang, Q., Jin, L., Pan, Z.: A cascade ensemble learning model for human activity recognition with smart phones. Sensors MDPI J. 19, 1–17 (2019)
Sousa, W., Souto, E., Rodrigres, J.: A comparative analysis of the impact of features on human activity recognition with smartphone sensors. In: The 23rd Brazillian Symposium, pp. 397–404 (2017)
Zhowu, Z.W., Zhangst, S.Z., Zhang, C.: Human Activity Recognition Using Wearable Devices Sensor Data. Stanford.edu, pp. 1–6 (2015)
Wainwright, R., Shenfield, A.: Human activity recognition making use of long short-term memory techniques. Athens J. Sci. 6(1), 19–34 (2019)
Yong, Z.A., Yu, Z.A., Zhao, Z.A., Baoa, J., Song, Y.: Human Activity Recognition Based on Time Series Analysis Using U-Net. A School of Electronic Engineering, Beijing University of Posts and Telecommunications, pp. 1–10, Beijing, China (2018)
Yulita, I.N., Saori, S.: Human activities and postural transitions classification using support vector machine and K-nearest neighbor methods. IOP Conf. Ser. Earth Environ. Sci. 248, 012025, 1–7 (2019)
Liu, J., Lu, M., Huang, T.: Smartphone Based Recognition System of Human Activities And Postural Transitions, EECS349, Machine Learning. Northwestern University, pp. 1–5 (2017)
Gusain, K., Gupta, A., Popli, B.: Transition Aware Human Activity Recognition Using eXtreme Gradient Boosted Decision Trees, Advanced Computing and Communication Technologies, pp. 41–49, Springer (2017)
Chi, J.I.N., Zhijun, L.I., Dayang, S.U.N., Fengye, H.U.: Human activity recognition algorithm based on the spatial feature for WBAN. Chinese J. Internet Things, 70–75 (2019)
Mehrotra, K.G., Mohan, C.K., Huang, H.M.: Anomaly Detection Principles and Algorithms, Terrorism, Security and Computation, pp. 191–217, Springer International Publishing AG (2017)
Hubert, M., Van der Veeken, S.: Outlier detection for skewed data. J. Chemometrics 235–246 (2008)
Hossin, M., Sulaiman, M.N.: A review on evaluation metrics for data classification evaluations. Int. J. Data Min. Knowl. Manage. Process (IJDKP) 5(2), 1–12 (2015)
Jurafsky, D., Martin, J.H.: Logistic Regression, Speech and Language Processing, Chapter 5, pp. 1–20, IEEE (2019)
Jurek, A., Bi, Y.: A survey of commonly used ensemble-based classification techniques. Knowl. Eng. Rev. 29(5), 551–581 (2013)
Raschka, S.: STAT479 FS18. L01: Intro to Machine Learning. Department of Statistics, University of Wisconsin–Madison, pp. 1–2 (2018)
Chen, L., Hoey, J., Cook, D.J.: Sensor-Based Activity Recognition. IEEE Transactions on Systems Man and Cybernetics Part C (Applications and Reviews), pp. 790–808 (2012)
Author information
Authors and Affiliations
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
Kolluri, P., Chilamkuri, P., NagaDeepa, C., Padmaja, V. (2021). Classification of Human Postural Transition and Activity Recognition Using Smartphone Sensor Data. In: Sharma, H., Saraswat, M., Yadav, A., Kim, J.H., Bansal, J.C. (eds) Congress on Intelligent Systems. CIS 2020. Advances in Intelligent Systems and Computing, vol 1335. Springer, Singapore. https://doi.org/10.1007/978-981-33-6984-9_35
Download citation
DOI: https://doi.org/10.1007/978-981-33-6984-9_35
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-33-6983-2
Online ISBN: 978-981-33-6984-9
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)