Detection of Human Activities and Human Fall Recognition Using Deep Learning Techniques
Abstract
Smartphones are
quickly becoming the most important communication device in people's lives in
today's world. Human Activity Recognition has grown in popularity as a field of
study in a variety of areas, including medical care, tracking, and education.
The sensors in smartphones allow us to use them for a wide range of
applications. Healthcare is one of the major domains where human activity
recognition is widely used. In this paper, a human activity recognition system
has been developed that can detect six activities of daily living (ADL) along
with human fall. Human fall occurs due to an accident that can cause serious
injuries which may lead to significant medical problems when the issue is not
addressed properly. The proposed system uses a variant of deep learning
technique to detect human activities and human fall. The accuracy is
significantly increased by nearly 4% when compared with previous results.
Country : India
1 Dr Joseph Prakash Mosiganti
Professor, Department of Computer Science and Engineering, Malla Reddy College of Engineering for Women, Hyderabad -500100, Telangana, India
Preeti Agarwal, Mansaf Alam (2019),
“A Lightweight Deep Learning Model for Human Activity Recognition on Edge Devices”.
International Conference on Computational Intelligence and Data Science
(ICCIDS), Procedia Computer Science 167, pp.2364-2373, Elsevier, pp. 2364-2373.
Casilari E., Lora-Rivera R.,
García-Lagos F. (2019), “A Wearable Fall Detection System Using Deep Learning”.
In: Wotawa F., Friedrich G., Pill I., Koitz-Hristov R., Ali M. (eds) Advances
and Trends in Artificial Intelligence. From Theory to Practice. IEA/AIE 2019.
Lecture Notes in Computer Science, vol 11606. Springer, Cham.
https://doi.org/10.1007/978-3-030-22999-3_39
Pienaar, S. W., &
Malekian,R.(2019), “Human Activity Recognition using LSTM-RNN Deep Neural
Network Architecture”. arXiv preprint ArXiv: 1905:00599.
Ignatov, A. (2018), “Real-time human
activity recognition from accelerometer data using Convolutional Neural
Networks”. Applied Soft Computing, 62, pp. 915-922.
Dua, N., Singh, S.N. & Semwal,
V.B. Multi-input CNN-GRU based human activity recognition using wearable
sensors. Computing (2021). https://doi.org/10.1007/s00607-021-00928-8
Ferrari, D. Micucci, M. Mobilio and
P. Napoletano, "On the Personalization of ClassificationModels for Human
Activity Recognition," in IEEE Access, vol. 8, pp. 32066-32079, 2020, doi:
10.1109/ACCESS.2020.2973425.
Wan, S., Qi, L., Xu, X. et al. Deep
Learning Models for Real-time Human Activity Recognition with Smartphones.
Mobile Netw Appl 25, 743–755 (2020). https://doi.org/10.1007/s11036-019-
Coelho Y., Rangel L., dos Santos F.,
Frizera-Neto A., Bastos-Filho T. (2019), “Human Activity Recognition Based on
Convolutional Neural Network”. In: Costa-Felix R., Machado J., Alvarenga A(eds)
XXVI Brazilian Congress on Biomedical Engineering. IFMBE Proceedings, Vol.
70/2. Springer, Singapore. https://doi.org/10.1007/978-981-13-2517-5_38
