TY - GEN
T1 - Early Fall Prediction Using Hybrid Recurrent Neural Network and Long Short-Term Memory
AU - Chui, Kwok Tai
AU - Lytras, Miltiadis D.
AU - Liu, Ryan Wen
AU - Zhao, Mingbo
AU - Ruiz, Miguel Torres
N1 - Publisher Copyright:
© 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.
PY - 2023
Y1 - 2023
N2 - Falls are unintentionally events that may occur in all age groups, particularly for elderly. Negative impacts include severe injuries and deaths. Although numerous machine learning models were proposed for fall detection, the formulations of the models are limited to prevent the occurrence of falls. Recently, the emerging research area namely early fall prediction receives an increasing attention. The major challenges of fall prediction are the long period of unseen future data and the nature of uncertainty in the time of occurrence of fall events. To extend the predictability (from 0.5 to 5 s) of the early fall prediction model, we propose a particle swarm optimization-based recurrent neural network and long short-term memory (RNN-LSTM). Results and analysis show that the algorithm yields accuracies of 89.8–98.2%, 88.4–97.1%, and 89.3–97.6% in three benchmark datasets UP Fall dataset, MOBIFALL dataset, and UR Fall dataset, respectively.
AB - Falls are unintentionally events that may occur in all age groups, particularly for elderly. Negative impacts include severe injuries and deaths. Although numerous machine learning models were proposed for fall detection, the formulations of the models are limited to prevent the occurrence of falls. Recently, the emerging research area namely early fall prediction receives an increasing attention. The major challenges of fall prediction are the long period of unseen future data and the nature of uncertainty in the time of occurrence of fall events. To extend the predictability (from 0.5 to 5 s) of the early fall prediction model, we propose a particle swarm optimization-based recurrent neural network and long short-term memory (RNN-LSTM). Results and analysis show that the algorithm yields accuracies of 89.8–98.2%, 88.4–97.1%, and 89.3–97.6% in three benchmark datasets UP Fall dataset, MOBIFALL dataset, and UR Fall dataset, respectively.
KW - Fall prediction
KW - Long short-term memory
KW - Predictive model
KW - Recurrent neural network
UR - http://www.scopus.com/inward/record.url?scp=85144571195&partnerID=8YFLogxK
U2 - 10.1007/978-3-031-19958-5_4
DO - 10.1007/978-3-031-19958-5_4
M3 - Contribución a la conferencia
AN - SCOPUS:85144571195
SN - 9783031199578
T3 - Lecture Notes in Networks and Systems
SP - 34
EP - 41
BT - Intelligent Computing and Optimization - Proceedings of the 5th International Conference on Intelligent Computing and Optimization, ICO 2022
A2 - Vasant, Pandian
A2 - Weber, Gerhard-Wilhelm
A2 - Marmolejo-Saucedo, José Antonio
A2 - Munapo, Elias
A2 - Thomas, J. Joshua
PB - Springer Science and Business Media Deutschland GmbH
T2 - 5th International Conference on Intelligent Computing and Optimization, ICO 2022
Y2 - 27 October 2022 through 28 October 2022
ER -