• P-ISSN 0974-6846 E-ISSN 0974-5645

Indian Journal of Science and Technology


Indian Journal of Science and Technology

Year: 2023, Volume: 16, Issue: 16, Pages: 1221-1229

Original Article

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

Received Date:27 January 2023, Accepted Date:30 March 2023, Published Date:24 April 2023


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

Keywords: Deep Learning; 2D Convolution Neural Network (CNN); Human Behavior Classification; ADAM Optimizer; VGG16; ResNet50


  1. Xia K, Huang J, Wang H. LSTM-CNN Architecture for Human Activity Recognition. IEEE Access. 2020;8:56855–56866. Available from: https://doi.org/10.1109/ACCESS.2020.2982225
  2. Nafea O, Abdul W, Muhammad G. Multi-sensor human activity recognition using CNN and GRU. International Journal of Multimedia Information Retrieval. 2022;11:135–147. Available from: https://doi.org/10.1007/s13735-022-00234-9
  3. Khan IU, Afzal S, Lee JW. Human Activity Recognition via Hybrid Deep Learning Based Model. Sensors. 2022;22(1):323. Available from: https://doi.org/10.3390/s22010323
  4. Prasad A, Tyagi AK, Althobaiti MM, Almulihi A, Mansour RF, Mahmoud AM. Human Activity Recognition Using Cell Phone-Based Accelerometer and Convolutional Neural Network. Applied Sciences. 2021;11(24):12099. Available from: https://doi.org/10.3390/app112412099
  5. Chakraborty M, Pramanick A, Dhavale SV. Two-Stream Mid-Level Fusion Network for Human Activity Detection. In: International Conference on Innovative Computing and Communications. Singapore. Springer Singapore. p. 331–343.
  6. Athavale VA, Gupta SC, Kumar D, Savita. Human Action Recognition Using CNN-SVM Model. Advances in Science and Technology. 2021;105:282–290. Available from: https://doi.org/10.4028/www.scientific.net/AST.105.282
  7. Anagnostis A, Benos L, Tsaopoulos D, Tagarakis A, Tsolakis N, Bochtis D. Human Activity Recognition through Recurrent Neural Networks for Human–Robot Interaction in Agriculture. Applied Sciences. 2021;11(5):2188. Available from: https://doi.org/10.3390/app11052188
  8. Habib S, Hussain A, Albattah W, Islam M, Khan S, Khan RU, et al. Abnormal Activity Recognition from Surveillance Videos Using Convolutional Neural Network. Sensors. 2021;21(24):8291. Available from: https://doi.org/10.3390/s21248291


© 2023 Sowmya et al. This is an open-access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. Published By Indian Society for Education and Environment (iSee


Subscribe now for latest articles and news.