{"title":"基于轻量级随机森林方法的植物病害图像分类初探","authors":"Mashitah Ibrahim, Muzaffar Hamzah, M. F. Asli","doi":"10.1109/ICOCO56118.2022.10031846","DOIUrl":null,"url":null,"abstract":"In recent years, the rapid development of environmental sensors and artificial intelligence is changing the traditional mode of agricultural production and moving towards intelligent and efficient precision agriculture. According to the demand of developing precision agriculture, this study plans to carry out comprehensive improvise research on the intelligent unmanned plant disease detection technology for agricultural ecosystems. The production can be adversely affected if plant disease problems cannot be detected in the early stage. Therefore, the biggest challenge in disease detection is the accurate early diagnosis for loss prevention. However, achieving high accuracy requires a computationally intensive approach to the system, which can cause overhead and high technical costs. Random Forest is a special kind of ensemble learning technique and it turns out to perform very well compared to other classification algorithms such as Support Vector Machines (SVM) and Artificial Neural Networks (ANN). In this study, we modified the structure of, RF model to improve the overall accuracy and accessibility, to transform it into a lightweight detection system. This lightweight framework is for cost-effective distribution with high performance without requiring extensive computational resources or complex algorithms. With that, this system can be more practical and easier to use.","PeriodicalId":319652,"journal":{"name":"2022 IEEE International Conference on Computing (ICOCO)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-11-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":"{\"title\":\"A Preliminary Lightweight Random Forest Approach-Based Image Classification for Plant Disease Detection\",\"authors\":\"Mashitah Ibrahim, Muzaffar Hamzah, M. F. Asli\",\"doi\":\"10.1109/ICOCO56118.2022.10031846\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"In recent years, the rapid development of environmental sensors and artificial intelligence is changing the traditional mode of agricultural production and moving towards intelligent and efficient precision agriculture. According to the demand of developing precision agriculture, this study plans to carry out comprehensive improvise research on the intelligent unmanned plant disease detection technology for agricultural ecosystems. The production can be adversely affected if plant disease problems cannot be detected in the early stage. Therefore, the biggest challenge in disease detection is the accurate early diagnosis for loss prevention. However, achieving high accuracy requires a computationally intensive approach to the system, which can cause overhead and high technical costs. Random Forest is a special kind of ensemble learning technique and it turns out to perform very well compared to other classification algorithms such as Support Vector Machines (SVM) and Artificial Neural Networks (ANN). In this study, we modified the structure of, RF model to improve the overall accuracy and accessibility, to transform it into a lightweight detection system. This lightweight framework is for cost-effective distribution with high performance without requiring extensive computational resources or complex algorithms. With that, this system can be more practical and easier to use.\",\"PeriodicalId\":319652,\"journal\":{\"name\":\"2022 IEEE International Conference on Computing (ICOCO)\",\"volume\":\"1 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2022-11-14\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"1\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2022 IEEE International Conference on Computing (ICOCO)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ICOCO56118.2022.10031846\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2022 IEEE International Conference on Computing (ICOCO)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICOCO56118.2022.10031846","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
A Preliminary Lightweight Random Forest Approach-Based Image Classification for Plant Disease Detection
In recent years, the rapid development of environmental sensors and artificial intelligence is changing the traditional mode of agricultural production and moving towards intelligent and efficient precision agriculture. According to the demand of developing precision agriculture, this study plans to carry out comprehensive improvise research on the intelligent unmanned plant disease detection technology for agricultural ecosystems. The production can be adversely affected if plant disease problems cannot be detected in the early stage. Therefore, the biggest challenge in disease detection is the accurate early diagnosis for loss prevention. However, achieving high accuracy requires a computationally intensive approach to the system, which can cause overhead and high technical costs. Random Forest is a special kind of ensemble learning technique and it turns out to perform very well compared to other classification algorithms such as Support Vector Machines (SVM) and Artificial Neural Networks (ANN). In this study, we modified the structure of, RF model to improve the overall accuracy and accessibility, to transform it into a lightweight detection system. This lightweight framework is for cost-effective distribution with high performance without requiring extensive computational resources or complex algorithms. With that, this system can be more practical and easier to use.