Advancing Human Action Recognition and Medical Image Segmentation using GRU Networks with V-Net Architecture

Human Action Recognition and Medical Image Segmentation study presents a novel framework that leverages advanced neural network architectures to improve Medical Image Segmentation and Human Action Recognition (HAR). Gated Recurrent Units (GRU) are used in the HAR domain to efficiently capture complex temporal correlations in video sequences, yielding better accuracy, precision, recall, and F1 Score than current models. In computer vision and medical imaging, the current research environment highlights the significance of advanced techniques, especially when addressing problems like computational complexity, resilience, and noise in real-world applications. Improved medical image segmentation and human action recognition (HAR) are of growing interest. While methods such as the V-Net architecture for medical picture segmentation and Spatial Temporal Graph Convolutional Networks (ST-GCNs) for HAR have shown promise, they are constrained by things like processing requirement and noise sensitivity. The suggested methods highlight the necessity of sophisticated neural network topologies and optimisation techniques for medical picture segmentation and HAR, with further study focusing on transfer learning and attention processes. A Python tool has been implemented to perform min-max normalization, utilize GRU for human action recognition, employ V-net for medical image segmentation, and optimize with the Adam optimizer, with performance evaluation metrics integrated for comprehensive analysis. This study provides an optimised GRU network strategy for Human Action Recognition with 92% accuracy, and a V-Net-based method for Medical Image Segmentation with 88% Intersection over Union and 92% Dice Coefficient.

@article{Rao2024,
  title     = {Advancing Human Action Recognition and Medical Image Segmentation using GRU Networks with V-Net Architecture},
  journal   = {International Journal of Advanced Computer Science and Applications},
  volume    = {15},
  number    = {2},
  year      = {2024},
  publisher = {The Science and Information Organization},
  author    = {Dustakar Surendra Rao and L. Koteswara Rao and Vipparthi Bhagyaraju and P. Rohini},
  doi       = {10.14569/IJACSA.2024.0150276},
  url       = {https://doi.org/10.14569/IJACSA.2024.0150276}
}