Sensor Based Human Physical Activities Evaluation on Multiple Classifiers


Authors : Safak Kayikci; Seda Postalcioglu

Volume/Issue : Volume 5 - 2020, Issue 11 - November

Google Scholar : http://bitly.ws/9nMw

Scribd : https://bit.ly/3mpL65l

Abstract : Recognition of human activities has become a very popular problem that has been widely studied with the development of sensors embedded in mobile devices and increasingly widespread methods of machine learning. For the solution of this problem, the sensor data of the different movements collected are labeled with the movements performed and turned into a classification problem. Different human activities are tried to be distinguished by applying Gradient Boosting, Random Forest, AdaBoost, Gaussian Naive Bayes classification algorithms on the collected data. Performance examinations and accuracy values are evaluated with the combination confusion matrix. It is observed that Gradient Boosting showed the best performance overall analysis. Human activity recognition is used in health practices, calculating personal daily calories, analyzing the health status, monitoring the movements performed by the elderly people in their environment, human position tracking, and various security applications

Keywords : Human activity recognition; Sensor; Gradient Boosting; Random Forest; AdaBoost; Gaussian Naive Bayes.

Recognition of human activities has become a very popular problem that has been widely studied with the development of sensors embedded in mobile devices and increasingly widespread methods of machine learning. For the solution of this problem, the sensor data of the different movements collected are labeled with the movements performed and turned into a classification problem. Different human activities are tried to be distinguished by applying Gradient Boosting, Random Forest, AdaBoost, Gaussian Naive Bayes classification algorithms on the collected data. Performance examinations and accuracy values are evaluated with the combination confusion matrix. It is observed that Gradient Boosting showed the best performance overall analysis. Human activity recognition is used in health practices, calculating personal daily calories, analyzing the health status, monitoring the movements performed by the elderly people in their environment, human position tracking, and various security applications

Keywords : Human activity recognition; Sensor; Gradient Boosting; Random Forest; AdaBoost; Gaussian Naive Bayes.

Never miss an update from Papermashup

Get notified about the latest tutorials and downloads.

Subscribe by Email

Get alerts directly into your inbox after each post and stay updated.
Subscribe
OR

Subscribe by RSS

Add our RSS to your feedreader to get regular updates from us.
Subscribe