Analyzing and Recognizing Human Activity Patterns Through Machine Learning Techniques

Human activity recognition (HAR) has gained popularity in recent years, owing to its applicability in monitoring human behaviour via machine learning (ML) models. This article describes a comprehensive study that uses wearable sensor data to recognise human behaviours using a variety of classification approaches such as logistic regression, random forest, and k-Nearest Neighbour (kNN). A feature selection method is used to increase model accuracy by lowering dimensionality. The experimental results show that logistic regression beats other classifiers in terms of accuracy. However, it demands more memory and processing time. This work helps to advance the construction of efficient ML models for HAR.