Research Article
Long Short Term Memory network for Recognition of Daily Human Activity
@INPROCEEDINGS{10.4108/eai.27-2-2020.2303125, author={Gaurav Arora and Anvaya Ahlawat and Mandeep Payal}, title={Long Short Term Memory network for Recognition of Daily Human Activity}, proceedings={Proceedings of the 2nd International Conference on ICT for Digital, Smart, and Sustainable Development, ICIDSSD 2020, 27-28 February 2020, Jamia Hamdard, New Delhi, India}, publisher={EAI}, proceedings_a={ICIDSSD}, year={2021}, month={3}, keywords={deep learning lstm neural networks machine learning human activity recognition convolution}, doi={10.4108/eai.27-2-2020.2303125} }- Gaurav Arora
Anvaya Ahlawat
Mandeep Payal
Year: 2021
Long Short Term Memory network for Recognition of Daily Human Activity
ICIDSSD
EAI
DOI: 10.4108/eai.27-2-2020.2303125
Abstract
Previously Human Activity Recognition has been solved by using the engineered features, but the main problem with this approach is that it requires specific domain knowledge. Adopting classical machine learning models has been effective but these methods completely ignore the time signal obtained from the sensors. But due to recent advancements, deep learning techniques like Long Short Term Model and recurrent neural networks have been effectively used to provide good results and classify human activities correctly as compared to machine learning models. So in this paper, we propose a LSTM framework to classify these activities and also compare its performance with classical machine learning models.
Copyright © 2020–2024 EAI
