Human Behavior Classification using 2D – Convolutional Neural Network, VGG16 and ResNet50

Objective: To develop a real-time application for human behavior classification using 2- Dimensional Convolution Neural Network, VGG16 and ResNet50. Methods: This study provides novel system which considers sitting, standing walking as normal behaviors. It consists of three major steps: dataset collection, training, testing. In this work real time images are used. there 2271 trained 539 testing images. Findings: The Network (CNN), ResNet50 Novelty: namely is used in the experimental results has shown that on outperformed with accuracy 99.72% compared to 2D-CNN. can detect behaviors humans an unconstrained laboratory environment. Keywords: Deep Learning; 2D (CNN); Human Behavior Classification; ADAM Optimizer; VGG16;