Summary
This paper presents a fusion model construction and optimisation method for multi-device image recognition collaboration, designed to operate efficiently within resource-constrained edge computing environments. The approach integrates information at feature and decision layers, implements data alignment and preprocessing mechanisms, and applies model lightweighting, task scheduling, and energy-efficiency optimisation strategies. Experimental validation demonstrates the method achieves practical balance between accuracy, speed, and energy efficiency across real-world deployment scenarios.
UK applicability
This is a computer science and edge computing paper with no explicit connection to agriculture, food systems, soil health, or nutrient density. It does not appear applicable to Vitagri's Pulse Brain catalogue, which focuses on farming systems and human health outcomes.
Key measures
Recognition accuracy, inference speed, system energy consumption
Outcomes reported
The study reports the development and optimisation of an image recognition fusion model that balances recognition accuracy, inference speed, and system energy consumption across multiple collaborative devices in real-world scenarios.
Topic tags
Dig deeper with Pulse AI.
Pulse AI has read the whole catalogue. Ask about this record, its theme, or how the findings apply to UK farming and policy — every answer cites the underlying studies.