The Key Criteria for Predicting Unusual Behavior in the Elderly With Deep Learning Models Under 5G Technology

Abstract

Deep learning algorithms and technology based on 5G networks may be able to help identify unusual behavior in elderly people. Because 5G networks have a lower latency and a greater bandwidth, it is possible to use more complex algorithms and larger data sets for training and detection in a real-time. On top of that, real-time analysis of the data gathered through in-home monitoring of the elderly can become much simpler to carry out with the help of 5G's potential to simplify the process. However, the system needs to be developed in a way that it considers the preferences of the most important criteria of elderly people, who have more requirements in terms of their living situation and the environment in which they live. Therefore, this study advocated using ''Decision Making Trial and Evaluation Laboratory'' (DEMATEL) to analyze the most crucial criteria (feature) required for creating a model for identifying odd behavior in elderly persons. Convolutional Neural Networks (CNNs) and Long Short-Term Memories (LSTMs) are adopted in detecting unusual behavior in the elderly after the analysis key criteria for predicting unusual behavior in the elderly by DEMATEL. The research established a concept by linking the SIMADL dataset with the dimension of elderly people's behavior and performed an experimental analysis using both CNN and LSTM. Performance evaluations show that the LSTM performs better in detecting unusual behavior in elderly persons with 96% accuracy. Depressive disorder is the most significant aspect of ageing that might lead to a typical unusual behavior in elderly persons, according to DEMATEL analysis.

An Elderly Fall Detection System Using Enhanced Random Forest in Machine Learning

“…From the literature survey, the identified that the drawbacks of the Existing System are limited accuracy, dependency on wearable devices, a lack of continuous monitoring, environmental limitations, the inability to distinguish falls from other activities, and a lack of real-time assistance [14].…”