Citation

Sungheetha, Akey and R., Rajesh Sharma (2026) AgriSense-AI: An Intelligent Framework for Precision Agriculture with Stream Processing Analytics and Disease Detection. Procedia Computer Science, 283. pp. 5357-5365. ISSN 18770509

Text 10.pdf - Published Version Restricted to Repository staff only Download (383kB)

Abstract

Modern agriculture faces its most difficult situations because of climate changes and limited resources and the growing needs of the population, which demands new technological solutions. Traditional farming methods show their boundaries because they cannot make instant decisions about crop health assessment and resource management throughout their entire farming area. This research presents AgriSense-AI which operates as an all-in-one smart system that merges real-time data processing with cuttingedge disease identification systems to achieve a detection success rate of 94.7 percent. The proposed system implements Enhanced Adaptive Stream Fusion Architecture incorporating multi-modal sensor integration with processing latency of 1.3 seconds and resource efficiency enhanced by 87.2 percent. Experimental validation across 15,000 hectares demonstrates yield prediction accuracy of 96.4 percent with energy consumption reduced by 42.6 percent through intelligent edge computing. Results indicate substantial potential for commercial deployment supporting sustainable agriculture.

Item Type:	Article
Uncontrolled Keywords:	Stream processing, Disease detection, IoT sensors
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:	02 Sep 2026 07:56
Last Modified:	02 Sep 2026 07:56
URII:	http://shdl.mmu.edu.my/id/eprint/16544

Downloads

Edit (login required)