Technological advancements and AI-based research have significantly influenced our daily lives. Human activity recognition (HAR) is a key area at the intersection of various AI technologies and application domains. In this study, we present our novel time series classification approach for monitoring the physical behaviors of the elderly and patients. This approach, which integrates supervised and unsupervised methods with generative models, has been validated for HAR, showing promising results. Our method was specifically adapted for healthcare and surveillance applications, enhancing the classification of physical behaviors in the elderly. The hybrid approach proved its effectiveness on the HAR70+ dataset, surpassing traditional recurrent convolutional network-based approaches. We further evaluated the surveillance system for the elderly (Surv-Sys-Elderly) model on the HARTH and HAR70+ datasets, achieving an accuracy of 94,3% on the HAR70+ dataset for recognizing elderly behaviors, highlighting its robustness and suitability for both clinical and domestic environments.
With the advances in generative models, it is becoming crucial to exploit their performance in the analysis of temporal data. Unlike discriminative models, which focus on distinguishing between different classes, generative models focus on representing the distribution of data and their ability to generate new data. However, these models present added complexity due to the need to model the joint distribution in order to generate realistic data. This complexity is even higher for temporal data. Therefore, the scientific community has experimented with different approaches to temporal data augmentation. This in-depth analysis explores the current state of knowledge in this field, providing a summary of the algorithms available and presenting a comparative assessment of existing approaches. We assess the performance of these temporal data augmentation techniques based on their overall impact on the Time-Series Classification (TSC), using metrics specifically in the context of human activity recognition (HAR) on datasets dedicated to this domain.