Predicting User-specific Future Activities using LSTM-based Multi-label Classification
Abstract
User-specific future activity prediction in the healthcare domain based on previous activities can drastically improve the services provided by the nurses. It is challenging because, unlike other domains, activities in healthcare involve both nurses and patients, and they also vary from hour to hour. In this paper, we employ various data processing techniques to organize and modify the data structure and an LSTM-based multi-label classifier for a novel 2-stage training approach (user-agnostic pre-training and user-specific fine-tuning). Our experiment achieves a validation accuracy of 31.58\%, precision 57.94%, recall 68.31%, and F1 score 60.38%. We concluded that proper data pre-processing and a 2-stage training process resulted in better performance. This experiment is a part of the "Fourth Nurse Care Activity Recognition Challenge" by our team "Not A Fan of Local Minima".
Cite
@article{arxiv.2211.03100,
title = {Predicting User-specific Future Activities using LSTM-based Multi-label Classification},
author = {Mohammad Sabik Irbaz and Fardin Ahsan Sakib and Lutfun Nahar Lota},
journal= {arXiv preprint arXiv:2211.03100},
year = {2023}
}
Comments
Accepted at the Proceedings of the 4th International Conference on Activity and Behavior Computing 2022 (ABC 2022) Reference: https://abc-research.github.io/challenge2022/results/