What is it about?

Human activity recognition (HAR) is the classification of different human activities influenced by their behavior and movements. The number of smartphone users and capacity sensors is increasing, and most users carry their phones. Smartphone data boosts HAR’s prominence and appeal. The gadget is used to recognize gestures or actions and perform specified activities in response to the informa- tion acquired by these recognition systems.

Featured Image

Why is it important?

Human Activity Recognition is the problem of using different sen- sors to make predictions based on human behavior and movements. To understand how the recognition of human activity works, HAR classifies the data of human activity into a set using various sensors. and subsequently reviews the data using various machine learning algorithms. Why Human Activity Recognition? This is because it investigates the fundamental difficulty of detecting many users’ activities from sensor data in any environment, such as a home as well as a company, and proposes a fancy pattern mining method to recognize user activity in an integrated solution.

Perspectives

Our study will examine several literary survey approaches. The KU-HAR dataset has uti- lized containing sensors data like accelerometers, and gyroscopes in various locations. This research’s goal is to identify human ac- tivity in smartphone sensors using machine learning classification algorithms. Sensors data from smartphone accelerometers and gy- roscope identify human activity. These data samples are utilized using smartphone sensors. Different machine learning techniques such as Decision Tree, Random Forest (RF), Gradient Boosting, Gaussian NB, KNN, Logistic Regression, and SVC has been applied to classify the human activity and achieved satisfactory outcome. This research can helps researchers to establish an expert system to detect any movements of human.

Md. Mehedi Hassan
North Western University

Read the Original

This page is a summary of: Human Activity Recognition using Time Series and Machine Learning Techniques, March 2022, ACM (Association for Computing Machinery),
DOI: 10.1145/3542954.3543011.
You can read the full text:

Read

Contributors

The following have contributed to this page