{"title":"山竹成熟阶段的深度学习自动分类","authors":"I. A. Mohtar, Nurhariyanni Ramli, Zaaba Ahmad","doi":"10.1109/AiDAS47888.2019.8970933","DOIUrl":null,"url":null,"abstract":"The retail quality of mangosteen depends on the harvesting of the fruit at the right ripening stage. Mangosteen harvested too early or too late will compromise the quality and consequently affect the yield for the season. The ability to automate the classification of the ripening stage of mangosteen will help the farmers during the harvesting phase to determine under-matured, matured and over-matured mangosteen. This study proposes a Convolutional Neural Network architecture utilizing the V3 Inception model, to classify the ripening stages of mangosteen. A total of 800 images were used to train the model. The model was able to achieve training accuracy of 99%, validation accuracy of 97% and testing accuracy of 91.9% after 500 epochs. The precision, recall and F1 score achieved were 0.88, 0.96, and 0.92 respectively. As a conclusion, the V3 Inception model is able to classify the ripening stages of mangosteen. It is hoped that this study will initiate the commercialization of this effort to assist the mangosteen industry.","PeriodicalId":227508,"journal":{"name":"2019 1st International Conference on Artificial Intelligence and Data Sciences (AiDAS)","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"6","resultStr":"{\"title\":\"Automatic Classification of Mangosteen Ripening Stages using Deep Learning\",\"authors\":\"I. A. Mohtar, Nurhariyanni Ramli, Zaaba Ahmad\",\"doi\":\"10.1109/AiDAS47888.2019.8970933\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"The retail quality of mangosteen depends on the harvesting of the fruit at the right ripening stage. Mangosteen harvested too early or too late will compromise the quality and consequently affect the yield for the season. The ability to automate the classification of the ripening stage of mangosteen will help the farmers during the harvesting phase to determine under-matured, matured and over-matured mangosteen. This study proposes a Convolutional Neural Network architecture utilizing the V3 Inception model, to classify the ripening stages of mangosteen. A total of 800 images were used to train the model. The model was able to achieve training accuracy of 99%, validation accuracy of 97% and testing accuracy of 91.9% after 500 epochs. The precision, recall and F1 score achieved were 0.88, 0.96, and 0.92 respectively. As a conclusion, the V3 Inception model is able to classify the ripening stages of mangosteen. It is hoped that this study will initiate the commercialization of this effort to assist the mangosteen industry.\",\"PeriodicalId\":227508,\"journal\":{\"name\":\"2019 1st International Conference on Artificial Intelligence and Data Sciences (AiDAS)\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2019-09-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"6\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2019 1st International Conference on Artificial Intelligence and Data Sciences (AiDAS)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/AiDAS47888.2019.8970933\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2019 1st International Conference on Artificial Intelligence and Data Sciences (AiDAS)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/AiDAS47888.2019.8970933","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Automatic Classification of Mangosteen Ripening Stages using Deep Learning
The retail quality of mangosteen depends on the harvesting of the fruit at the right ripening stage. Mangosteen harvested too early or too late will compromise the quality and consequently affect the yield for the season. The ability to automate the classification of the ripening stage of mangosteen will help the farmers during the harvesting phase to determine under-matured, matured and over-matured mangosteen. This study proposes a Convolutional Neural Network architecture utilizing the V3 Inception model, to classify the ripening stages of mangosteen. A total of 800 images were used to train the model. The model was able to achieve training accuracy of 99%, validation accuracy of 97% and testing accuracy of 91.9% after 500 epochs. The precision, recall and F1 score achieved were 0.88, 0.96, and 0.92 respectively. As a conclusion, the V3 Inception model is able to classify the ripening stages of mangosteen. It is hoped that this study will initiate the commercialization of this effort to assist the mangosteen industry.