https://scholars.lib.ntu.edu.tw/handle/123456789/572831
標題: | Online semi-supervised learning applied to an automated insect pest monitoring system | 作者: | Rustia D.J.A Lu C.-Y Chao J.-J Wu Y.-F Chung J.-Y JU-CHUN HSU TA-TE LIN |
關鍵字: | Automation; Classification (of information); Data acquisition; Deep learning; Deep neural networks; Image classification; Image recognition; Learning systems; Monitoring; Semi-supervised learning; Adaptive solution; Cluster densities; Continuous learning; Image monitoring systems; Monitoring system; Neural network model; Supervised learning approaches; Supervised learning methods; E-learning | 公開日期: | 2021 | 卷: | 208 | 起(迄)頁: | 28-44 | 來源出版物: | Biosystems Engineering | 摘要: | The unavailability and variability of training samples are the two essential concerns in the training of deep neural network models for image classification. For automated image monitoring systems, these problems are difficult when training a model through supervised learning methods because of the time and effort required. This paper proposes an adaptive solution to this problem by applying online semi-supervised learning to an automated insect pest monitoring system. The method used includes unsupervised pseudo-labelling of insect images and the training of semi-supervised classifier models for insect image recognition. The pseudo-labelling algorithm includes three major components: image labelling, label reconfirmation, and sample cleaning. Experiments were conducted on two unlabelled 1-year insect image datasets to evaluate the efficacy of the proposed method. It was found that the pseudo-labelling algorithm could achieve accuracy up to 0.963, hence enabling automated training data collection. The temporal improvement of the insect recognition performance by including new training data to retrain the classifier model was comparable in performance to the supervised learning approach as evaluated by cluster density, silhouette score, and F1-score. The proposed method was also able to automatically collect quality samples and train models regardless of the complexity of the images, making it a good alternative to replace laborious supervised learning. The proposed method can prevent contamination of a training dataset when images from new locations are collected. The presented techniques may also be used in other continuous learning applications that require automated training data collection and online model update. ? 2021 IAgrE |
URI: | https://www.scopus.com/inward/record.uri?eid=2-s2.0-85107280315&doi=10.1016%2fj.biosystemseng.2021.05.006&partnerID=40&md5=01616a0eefd3843ecb76b62b6f6c9831 https://scholars.lib.ntu.edu.tw/handle/123456789/572831 |
ISSN: | 15375110 | DOI: | 10.1016/j.biosystemseng.2021.05.006 |
顯示於: | 昆蟲學系 |
在 IR 系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。