About this document

Deep Learning for Human Activity Recognition by sajaysahoo521 is a document available to read on EtoBox.

This paper explores Human Activity Recognition (HAR) using Deep Learning techniques on sensor data, focusing on real-time detection of activities like sitting, standing, walking, and running. The model employs a Convolutional Neural Network (CNN) architecture and achieves over 90% accuracy with an average inference time of 220ms. The research highlights potential applications in healthcare, fitness tracking, and intelligent surveillance, with future work aimed at optimizing the model for mobile platforms.

Author

sajaysahoo521

Language

EN