Skip to content

Opening book details…

About this document

Impact of Window Size on Activity Recognition by bsbavcacgauiambabavcafhajs is a document available to read on EtoBox.

This study investigates the impact of different window sizes on the classification accuracy of static and dynamic physical activities using a single accelerometer. It was found that a 1.5-second window size provides the best trade-off in recognition accuracy, achieving over 90% accuracy across various activities, including transitions. The results highlight the necessity for adaptive segmentation criteria based on activity duration to improve real-time activity recognition systems.

Author
bsbavcacgauiambabavcafhajs
Language
EN