Dr Po Yang’s paper has been selected as the Best Paper 2022 of TC-II by the Institute of Electrical and Electronics Industrial Electronics Society’s (IEEE-IES) Technical Committee of Industrial Informatics.
The paper on mobile pest recognition in crop production was one of 840 published in the IEEE Transactions on Industrial Informatics journal over the past year. It was then nominated and ultimately put to a ballot by members of the Technical Committee of Industrial Informatics.
Deep Learning based Automatic Multi-Class Wild Pest Monitoring Approach using Hybrid Global and Local Activated Features by Po Yang, Liu Liu, Chengjun Xie, Rujing Wang, Sud Sudirman, Jie Zhang, Rui Li, and Fangyuan Wang.
The paper proposes a new approach to tackling the low accuracy and lack of robustness in large scale image analytic pest recognition systems that are used to detect pests and diseases in industrial crop production.
Proposing a novel deep learning (DL) based automatic approach using hybrid and local activated features for pest monitoring, the paper aims to improve the accuracy, robustness and cost effectiveness of large-scale pest detection.
The work follows a previous paper on PestNet, which came 1st out of 428 papers at the IEEE International Conference on Industrial Informatics in 2019. It has since become one of best deep-learning based wheat pest recognition models in the world, and is currently being used by National Agriculture Technology Extension Service Center in China to detect pests in wheat fields and by the Wadhwani AI: AI for Social Impact in India to detect pests in cotton fields.
Dr Po Yang, Senior Lecturer in Large Scale Data Fusion at the University of Sheffield’s Department of Computer Science, said: “These sorts of technologies have a huge potential to be used to improve the safety, security and sustainability of food production throughout the world.
“All the papers submitted to the Society are evaluated on their potential impact in industry so we’re very pleased to have had our work recognised and celebrated by fellow members.”
