Time Series Data Analysis using Machine Learning-(ML) Approach

Authors

MVV PRASAD KANTIPUDI Dr., Sreyas Institute Of Engineering and TechnologyFollow
Pradeep Kumar N.S Dr., S.E.A.CETFollow
S.Sreenath Kashyap Dr., KPRITFollow
SS Anusha Vemuri Ms, Sreyas Institute Of Engineering and TechnologyFollow

Date of this Version

1-18-2021

Document Type

Article

Abstract

Healthcare benefits related to continuous monitoring of human movement and physical activity can potentially reduce the risk of accidents associated with elderly living alone at home. Based on the literature review, it is found that many studies focus on human activity recognition and are still active towards achieving practical solutions to support the elderly care system. The proposed system has introduced a joint approach of machine learning and signal processing technology for the recognition of human's physical movements using signal data generated by accelerometer sensors. The framework adopts the concept of DSP to select very descriptive feature sets and uses ML-based supervised learning techniques for effective classification. The simulation result demonstrates the efficiency of the proposed system regarding the prediction of human movement based on sensor signals.