Citation

R., Rajesh Sharma and Sungheetha, Akey and Yogarayan, Sumendra and Kannan, Subarmaniam (2026) Green Engineering AI-Driven System for Antibiotic-Resistant Bacteria Mitigation in Marine Healthcare Environment. In: 4th international conference on Machine Learning and Data Engineering, ICMLDE 2025, 6 November 2025 - 8 November 2025, Dehradun.

Text 2.pdf - Published Version Restricted to Repository staff only Download (385kB)

Abstract

This research proposes a novel Green Engineering AI-Driven Integrated Surveillance and Mitigation System combining deep learning-based pathogen detection through hybrid convolutional-recurrent neural architectures with attention mechanisms, realtime multi-modal environmental monitoring integrating optical microscopy at 4096 by 4096 pixel resolution with spectroscopic analysis covering 280 to 850 nanometer wavelength range and electrochemical biosensors measuring bacterial concentrations from 1000 to one billion colony forming units per milliliter, and adaptive intervention protocols deploying photocatalytic titanium dioxide nanoparticles with 15.3 nanometer mean particle size, UV-C irradiation at 254 nanometer wavelength with 2.8 milliwatt per square centimeter intensity, and ozone treatment at concentrations from 0.3 to 1.2 parts per million. The system achieves 96.8 percent detection accuracy representing 24.1 percent improvement over conventional methods, 89.2 second average response time indicating 80.2 percent latency reduction, and 94.3 percent mitigation effectiveness demonstrating 32.8 percent enhancement in pathogen neutralization validated across 847 marine healthcare facilities processing 18.6 million sensor measurements over 14 month operational deployment. The methodology integrates predictive intervention scheduling through reinforcement learning achieving 91.7 percent reduction in antibiotic-resistant bacterial colonization while maintaining ecological sustainability with 89.4 percent less hazardous waste generation and 67.8 percent lower carbon emissions compared to chemical disinfection approaches. This technology enables patent-worthy innovations in marine biosecurity facilitating technology transfer through modular deployment architectures suitable for offshore medical platforms processing 450 liters per hour, aquaculture health monitoring covering 12.4 hectares, and coastal hospital water treatment serving 890 beds with commercialization potential addressing 65,090 global deployment sites representing 4.2 billion dollar market opportunity.

Item Type:	Conference or Workshop Item (Paper)
Uncontrolled Keywords:	Marine Healthcare Systems, Deep Learning
Subjects:	Q Science > Q Science (General) > Q300-390 Cybernetics
Divisions:	Faculty of Information Science and Technology (FIST)
Depositing User:	Ms Rosnani Abd Wahab
Date Deposited:	04 Sep 2026 02:28
Last Modified:	04 Sep 2026 02:29
URII:	http://shdl.mmu.edu.my/id/eprint/16684

Downloads

Edit (login required)