Healthcare-based Human Activity Recognition and Transportation Mode Detection Using IoT Sensors
R. Dilip, Maria Shalini, Ms. K Manasa, N. Tejashwini, L. Chandrashekhar, Bai V. Bhagirathi · 2024
The paper presents a study on human activity recognition and transportation mode detection. Readings from the accelerometer, gyroscope, and sound measurements taken by the sensors are reflected in the data used in the study. The study tries to categorize human activities such as walking, running, sitting, and types of transportation such as cars, buses, and trains into various groups. In their experiments, the authors attain high accuracy rates using machine learning algorithms for categorization, such as random forest, decision tree, and logistic regression. The paper offers insights into how IoT sensors could be used for recognizing human activities and modes of mobility in order to monitor and improve healthcare outcomes. Our findings suggest that our study is accurate and dependable for healthcare monitoring and mode identification, with potential applications in workplace wellness, urban planning, and environmental sustainability.