Publication

Abstract : HAR is specified as the crucial task within the field of Computer vision and artificial intelligence. Main aim of HAR is to observing and labelling different human activity images of distinct data sources by machines such as computer. HAR has applications in various fields. CNN model is an appropriate model for HAR task, due to their ability to automaticaly acquire relevant spatial features, capture hierarchical representations, and handle input of various sizes and types. So it is utilized for developing HAR model. This model can detect objects and also can classify images. The model contains wide ranging catogories. ShuffleNetV2 is a particular architecture within it, mainly for efficient and lightweight deep learning task. This paper develops an intelligent HAR using ShuffleNetV2 model which acquired an accuracy about 69.52 percentage.