Title: Multimodal information interaction and fusion for the parallel computing system using AI techniques
Authors: Yang Li; Wei Li; Na Li; Xiaoli Qiu; Karthik Bala Manokaran
Addresses: Information Technology and Cultural Management Institute, Hebei Institute of Communications, Shijiazhuang, 051430, China ' Information Technology and Cultural Management Institute, Hebei Institute of Communications, Shijiazhuang, 051430, China ' HR Office, Hebei Institute of Communications, Shijiazhuang, 051430, China ' Information Technology and Cultural Management Institute, Hebei Institute of Communications, Shijiazhuang, 051430, China ' Pannai College of Engineering and Technology, Sivaganga 630561, India
Abstract: Recently multimodal information fusion systems are popularly used to increase the reliability of recognition systems. These systems employ data from different modalities. Since different modalities capture information with different attributes, the fusion of this information aids in achieving better solutions. In this research, they present a Multimodal Fusion for Parallel Computing scheme. Here, a novel multi-modal fusion-based parallel computing (MMFPC) Model is being proposed. Besides, a new technique for the generation of history images is as well proposed. Feature extraction using GLCM and HOG features is performed. The fusion of multimodal features using the weighted fusion technique prioritises the modes that contain more valuable data. Classification is analysed using different artificial intelligence algorithms. Finally, the proposed scheme is evaluated using a public fall detection dataset. It was observed that the proposed system achieves a high accuracy of 96.77% and a high specificity of 93.52%.
Keywords: multi-modal; parallel computing; artificial intelligence; classification; feature extraction; fusion model; accuracy.
DOI: 10.1504/IJHPSA.2021.121022
International Journal of High Performance Systems Architecture, 2021 Vol.10 No.3/4, pp.185 - 196
Received: 20 Mar 2021
Accepted: 26 May 2021
Published online: 22 Feb 2022 *