Abstract
In the present research, we developed an application that measures acceleration by a smartphone located at the waist, along with a deep learning system that automatically detects six behavioral activities (walking, running, standing, walking downstairs, walking upstairs, and falling). Specifically, we use a human activity database provided by the University of California–Irvine (UCI) to create a deep learning model with the UCI data. Next, transfer learning was applied to the learning model for the measurement data obtained by the acceleration acquisition application developed in this research. Using Sony’s Neural Network Console development environment as a deep learning tool, in recognition experiments, our proposed method for automatic identification of activities and prediction of falling accidents caused by behavior achieved a high accuracy rate of almost 95%.
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
References
García, E., Villar, M., Fáñez, M., Villar, J.R., de la Cal, E., Cho, S.-B.: Towards effective detection of elderly falls with CNN-LSTM neural networks. Neurocomputing 500, 231–240 (2022)
Li, H., et al.: Bi-LSTM network for multimodal continuous human activity recognition and fall detection. IEEE Sens. J. 20(3), 1191–1201 (2019)
LIN, C.-B., et al.: A framework for fall detection based on OpenPose skeleton and LSTM/GRU models. Appl. Sci. 11(1), 329 (2020)
Maitre, J., Bouchard, K., Gaboury, S.: Fall detection with UWB radars and CNN-LSTM architecture. IEEE J. Biomed. Health Inform. 25(4), 1273–1283 (2021)
Dataset of Human Activity Recognition Using Smartphones, UC Irvine Machine Learning Repository. https://archive-beta.ics.uci.edu/dataset/240/human+activity+recognition+using+smartphones. Accessed 12 Jan 2023
Neural Network Console. https://dl.sony.com/. Accessed 12 Jan 2023
IMS-SD: Data logger type inertial sensor (IMU: Inertial measurement Unit). https://www.tecgihan.co.jp/products/ims-sd-imu. Accessed 11 Feb 2023
Kawaguchi, N., et al.: HASC challenge 2010: construction of wearable accelerometer sensor corpus for activity recognition. In: Proceedings of Multimedia, Distributed Cooperation and Mobile Symposium, vol. 2011, pp. 69–75 (2011)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Hayashi, S., Nakajima, A. (2023). Automatic Identification of Daily Life Activities and Prediction of Falling Accidents Caused by Behavior. In: Stephanidis, C., Antona, M., Ntoa, S., Salvendy, G. (eds) HCI International 2023 Posters. HCII 2023. Communications in Computer and Information Science, vol 1833. Springer, Cham. https://doi.org/10.1007/978-3-031-35992-7_62
Download citation
DOI: https://doi.org/10.1007/978-3-031-35992-7_62
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-35991-0
Online ISBN: 978-3-031-35992-7
eBook Packages: Computer ScienceComputer Science (R0)