William Macdonald , Yuksel Asli Sari , Majid Pahlevani
{"title":"利用轻量级深度学习进行植物病害分类的生长光智能监控系统","authors":"William Macdonald , Yuksel Asli Sari , Majid Pahlevani","doi":"10.1016/j.aiia.2024.03.003","DOIUrl":null,"url":null,"abstract":"<div><p>This work focuses on a novel lightweight machine learning approach to the task of plant disease classification, posing as a core component of a larger grow-light smart monitoring system. To the extent of our knowledge, this work is the first to implement lightweight convolutional neural network architectures leveraging down-scaled versions of inception blocks, residual connections, and dense residual connections applied without pre-training to the PlantVillage dataset. The novel contributions of this work include the proposal of a smart monitoring framework outline; responsible for detection and classification of ailments via the devised lightweight networks as well as interfacing with LED grow-light fixtures to optimize environmental parameters and lighting control for the growth of plants in a greenhouse system. Lightweight adaptation of dense residual connections achieved the best balance of minimizing model parameters and maximizing performance metrics with accuracy, precision, recall, and F1-scores of 96.75%, 97.62%, 97.59%, and 97.58% respectively, while consisting of only 228,479 model parameters. These results are further compared against various full-scale state-of-the-art model architectures trained on the PlantVillage dataset, of which the proposed down-scaled lightweight models were capable of performing equally to, if not better than many large-scale counterparts with drastically less computational requirements.</p></div>","PeriodicalId":52814,"journal":{"name":"Artificial Intelligence in Agriculture","volume":null,"pages":null},"PeriodicalIF":8.2000,"publicationDate":"2024-04-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2589721724000126/pdfft?md5=92380011c829045a5c9cecbd59eb4f0b&pid=1-s2.0-S2589721724000126-main.pdf","citationCount":"0","resultStr":"{\"title\":\"Grow-light smart monitoring system leveraging lightweight deep learning for plant disease classification\",\"authors\":\"William Macdonald , Yuksel Asli Sari , Majid Pahlevani\",\"doi\":\"10.1016/j.aiia.2024.03.003\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><p>This work focuses on a novel lightweight machine learning approach to the task of plant disease classification, posing as a core component of a larger grow-light smart monitoring system. To the extent of our knowledge, this work is the first to implement lightweight convolutional neural network architectures leveraging down-scaled versions of inception blocks, residual connections, and dense residual connections applied without pre-training to the PlantVillage dataset. The novel contributions of this work include the proposal of a smart monitoring framework outline; responsible for detection and classification of ailments via the devised lightweight networks as well as interfacing with LED grow-light fixtures to optimize environmental parameters and lighting control for the growth of plants in a greenhouse system. Lightweight adaptation of dense residual connections achieved the best balance of minimizing model parameters and maximizing performance metrics with accuracy, precision, recall, and F1-scores of 96.75%, 97.62%, 97.59%, and 97.58% respectively, while consisting of only 228,479 model parameters. These results are further compared against various full-scale state-of-the-art model architectures trained on the PlantVillage dataset, of which the proposed down-scaled lightweight models were capable of performing equally to, if not better than many large-scale counterparts with drastically less computational requirements.</p></div>\",\"PeriodicalId\":52814,\"journal\":{\"name\":\"Artificial Intelligence in Agriculture\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":8.2000,\"publicationDate\":\"2024-04-04\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.sciencedirect.com/science/article/pii/S2589721724000126/pdfft?md5=92380011c829045a5c9cecbd59eb4f0b&pid=1-s2.0-S2589721724000126-main.pdf\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Artificial Intelligence in Agriculture\",\"FirstCategoryId\":\"1087\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S2589721724000126\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"AGRICULTURE, MULTIDISCIPLINARY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Artificial Intelligence in Agriculture","FirstCategoryId":"1087","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2589721724000126","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"AGRICULTURE, MULTIDISCIPLINARY","Score":null,"Total":0}
引用次数: 0
摘要
这项工作的重点是采用一种新颖的轻量级机器学习方法来完成植物病害分类任务,并将其作为大型光生长智能监控系统的核心组件。据我们所知,这项工作是首次在植物村数据集上实施轻量级卷积神经网络架构,利用了缩减版的初始块、残差连接和密集残差连接。这项工作的新贡献包括提出了一个智能监控框架大纲,负责通过所设计的轻量级网络进行病症检测和分类,并与 LED 种植灯具连接,以优化温室系统中植物生长的环境参数和照明控制。密集残差连接的轻量级适配在最小化模型参数和最大化性能指标之间实现了最佳平衡,准确率、精确度、召回率和 F1 分数分别为 96.75%、97.62%、97.59% 和 97.58%,而模型参数只有 228479 个。这些结果进一步与在 PlantVillage 数据集上训练的各种最先进的完整模型架构进行了比较,其中所提出的缩小比例轻量级模型的性能与许多大型同类模型相当,甚至更好,而计算要求却大大降低。
Grow-light smart monitoring system leveraging lightweight deep learning for plant disease classification
This work focuses on a novel lightweight machine learning approach to the task of plant disease classification, posing as a core component of a larger grow-light smart monitoring system. To the extent of our knowledge, this work is the first to implement lightweight convolutional neural network architectures leveraging down-scaled versions of inception blocks, residual connections, and dense residual connections applied without pre-training to the PlantVillage dataset. The novel contributions of this work include the proposal of a smart monitoring framework outline; responsible for detection and classification of ailments via the devised lightweight networks as well as interfacing with LED grow-light fixtures to optimize environmental parameters and lighting control for the growth of plants in a greenhouse system. Lightweight adaptation of dense residual connections achieved the best balance of minimizing model parameters and maximizing performance metrics with accuracy, precision, recall, and F1-scores of 96.75%, 97.62%, 97.59%, and 97.58% respectively, while consisting of only 228,479 model parameters. These results are further compared against various full-scale state-of-the-art model architectures trained on the PlantVillage dataset, of which the proposed down-scaled lightweight models were capable of performing equally to, if not better than many large-scale counterparts with drastically less computational requirements.