Authors:
Vasanthakumari Sundararajan, R. Steffi, T. Shynu

Addresses:
1Department of Pediatric and Neonatal Nursing, Institute of Health Sciences, Wollega University, Nekemte, Ethiopia. 2Department of Electronics and Communication, Vins Christian College of Engineering, Nagercoil, Tamil Nadu, India. 3Department of Biomedical Engineering, Agni College of Technology, Chennai, Tamil Nadu, India. vasantha@wollegauniversity.edu.et1, steffi12009@gmail.com2, shynu469@gmail.com3

Abstract:

Modern collaborative multi-sensor systems have emerged as a powerful tool for achieving enhanced observational accuracy and resilience. At the core of these systems lies the challenge of assimilating diverse sensor data to ensure a seamless and comprehensive understanding of the environment being monitored. To address this, many sophisticated data fusion methodologies have been proposed. This research delves deeply into these methodologies, meticulously analyzing their strengths and shortcomings. Moreover, it evaluates their effectiveness and applicability across various real-world scenarios. Through this rigorous comparative analysis, we have conceptualised a ground-breaking architecture for data fusion. This new approach focuses not just on the mere amalgamation of data but also on optimizing the fusion process by considering the intrinsic quality and contextual relevance of each sensor's data. Preliminary findings from our research are quite promising. They indicate significant improvements in the accuracy and robustness of multi-sensor systems, especially when deployed in environments characterized by challenging conditions. These advancements are not just incremental but transformative, paving the way for more reliable and efficient multi-sensor systems in the future. Overall, this study serves a dual purpose. Firstly, it offers a deep and foundational understanding of data fusion in multi-sensor systems. Secondly, it provides a pragmatic and innovative approach that practitioners can adopt to unlock the true potential of these collaborative systems.

Keywords: Data Fusion; Multi-Sensor Systems; Collaborative Sensing; Sensor Fusion; Fusion Strategies; Sensor Networks; Data Assimilation; System Accuracy.

Received on: 10/02/2023, Revised on: 06/05/2023, Accepted on: 11/07/2023, Published on: 27/11/2023

FMDB Transactions on Sustainable Computing Systems, 2023 Vol. 1 No. 3, Pages: 112-123

• Views : 155
• Downloads : 8
• Cited by: 1

Download PDF