Downloads: 6 | Views: 125 | Weekly Hits: ⮙6 | Monthly Hits: ⮙6
Experimental Result Paper | Electrical & Electronics Engineering | India | Volume 13 Issue 1, January 2024 | Popularity: 6.5 / 10
Efficient Human-Machine Interface through Deep Learning Fusion
Jayapal P
Abstract: The Human-Machine Interface (HMI) has developed into an essential tool for natural communication between people and machines, revolutionising many fields. By synergistically merging a ResNet deep learning architecture, a VGG16-based feature extraction, and a lightweight narrow architecture, this research provides a novel technique to improve the HMI paradigm. The main emphasis is on defining parameter ranges using supervised data learning and improving virtual management procedures through precise sensor parameter predictions. It was decided to use a thorough technique that included a study of the literature, data gathering, analysis, and model construction, and it was then rigorously evaluated using metrics including accuracy, precision, recall, and F1 score. The ResNet model has the potential to be used to enhance the HMI because the suggested architecture uses VGG16 for feature extraction. Performance is improved by the streamlined, thin design, which solves hardware limitations. The effectiveness of the method is demonstrated by testing it on the CIFAR-10 dataset. This results in a model that is more accurate, faster to compute, and more efficient, which is a big development for HMI models. The advancement of human-machine interaction and virtual management systems will be made possible in the future thanks to the insights provided by this research into the fusion of deep learning techniques.
Keywords: Human-Machine Interface, ResNet Architecture, VGG16-based Feature Extraction, Lightweight Narrow Architecture, Deep Learning, Virtual Management, Pattern Recognition
Edition: Volume 13 Issue 1, January 2024
Pages: 680 - 686
DOI: https://www.doi.org/10.21275/SR24109210845
Make Sure to Disable the Pop-Up Blocker of Web Browser