Citation

R., Rajesh Sharma and Yogarayan, Sumendra and Kannan, Subarmaniam and Sungheetha, Akey (2026) NEPTUNE: Network-Enhanced Processing for Underwater Stream Data Analysis with Adaptive Resource Mapping Efficiency. In: 4th international conference on Machine Learning and Data Engineering, ICMLDE 2025, 6 November 2025 - 8 November 2025, Dehradun.

Text 14.pdf - Published Version Restricted to Repository staff only Download (481kB)

Abstract

This paper introduces NEPTUNE, a novel underwater data stream processing system designed for real-time analysis and mapping of marine resources. Traditional underwater exploration systems suffer from latency issues and processing inefficiencies due to the continuous influx of high-velocity data streams from multiple sensors. We propose an integrated framework that optimizes underwater data processing using a distributed architecture with edge computing capabilities. The system achieves an Adaptive Resource Mapping Efficiency (ARME) defined as ARMEω = η ∑n i=1 δi · ρi, where η represents the processing efficiency coefficient, δi indicates sensor data quality factor, and ρi denotes resource detection probability for sensor node i. Our experimental results demonstrate that NEPTUNE reduces processing latency by 67% while improving mapping accuracy by 42% compared to conventional methods. By implementing a three-tier data processing hierarchy and novel stream synchronization algorithms, the system achieves real-time analysis at depths exceeding 200 meters with data transmission rates of 2.4 Mbps. The proposed technology has significant applications in underwater mineral exploration, marine conservation, and underwater infrastructure monitoring, representing a substantial advancement in marine resource mapping technology with immediate commercial applications.

Item Type:	Conference or Workshop Item (Paper)
Uncontrolled Keywords:	Edge Computing, Distributed Sensor Networks
Subjects:	Q Science > QA Mathematics > QA71-90 Instruments and machines > QA75.5-76.95 Electronic computers. Computer science
Divisions:	Faculty of Information Science and Technology (FIST)
Depositing User:	Ms Rosnani Abd Wahab
Date Deposited:	04 Sep 2026 06:57
Last Modified:	04 Sep 2026 06:57
URII:	http://shdl.mmu.edu.my/id/eprint/16730

Downloads

Edit (login required)