Research on Indoor Activity Trajectory Monitoring Model for Elderly Living Alone Based on CNN-LSTM
Authors/Creators
Description
This paper presents an innovative neural network model, integrating Convolutional Neural
Networks (CNN) and Long Short-Term Memory networks (LSTM), designed to longitudinally monitor
and predict the health status of elderly individuals living alone. In the model architecture, CNN is tasked
with extracting spatiotemporal features related to behavioral patterns and health from daily activity
trajectory maps, while LSTM leverages these feature sequences to learn the normal behavioral patterns of
the elderly, handling long-term dependencies in time-series data. This dual approach not only enables the
identification of immediate anomalies but also forecasts potential health issues, such as Alzheimer's
disease. By defining exceptional behavior tags and encoding them as supervised learning objectives, the
model achieves effective prediction of abnormal states among the elderly, providing a more
comprehensive and proactive solution for their healthcare monitoring.