Rice is the most important crop in global food security and socioeconomic stability. A part of the world's population makes rice a food requirement but the problem is found that all rice varieties suffer from several diseases and pests. Therefore, it is necessary to ensure the quality of healthy and proper rice growth by detecting diseases present in rice plants and treatment of affected plants. In this study, the Convolutional Neural Network (CNN) algorithm was applied in classifying diseases on the leaves of rice plants by experimenting with several parameters and architecture to get the best accuracy. This study was conducted image classification of rice plant disease using CNN architecture ResNet-50V2 with data using preprocessing Augmentation. The test was conducted with three optimizers such as SGD, Adam, and RMSprop by combining various parameters, namely epoch, batch size, learning rate, and SGD and RMSprop optimizers. Division of image data with 70:30 ratio of training data and test data; 80:20; 90:10. From these results, it was found that Adam was the best optimizer in the 80:20 data division in this study with an accuracy level of 0.9992, followed by the SGD optimizer with an accuracy level of 0.9983, while the RMSProp optimizer was ranked third with an accuracy level of 0.9978.
{"title":"Application of Convolutional Neural Network ResNet-50 V2 on Image Classification of Rice Plant Disease","authors":"Delvi Hastari, Salsa Winanda, Aditya Rezky Pratama, Nana Nurhaliza, Ella Silvana Ginting","doi":"10.57152/predatecs.v1i2.865","DOIUrl":"https://doi.org/10.57152/predatecs.v1i2.865","url":null,"abstract":"Rice is the most important crop in global food security and socioeconomic stability. A part of the world's population makes rice a food requirement but the problem is found that all rice varieties suffer from several diseases and pests. Therefore, it is necessary to ensure the quality of healthy and proper rice growth by detecting diseases present in rice plants and treatment of affected plants. In this study, the Convolutional Neural Network (CNN) algorithm was applied in classifying diseases on the leaves of rice plants by experimenting with several parameters and architecture to get the best accuracy. This study was conducted image classification of rice plant disease using CNN architecture ResNet-50V2 with data using preprocessing Augmentation. The test was conducted with three optimizers such as SGD, Adam, and RMSprop by combining various parameters, namely epoch, batch size, learning rate, and SGD and RMSprop optimizers. Division of image data with 70:30 ratio of training data and test data; 80:20; 90:10. From these results, it was found that Adam was the best optimizer in the 80:20 data division in this study with an accuracy level of 0.9992, followed by the SGD optimizer with an accuracy level of 0.9983, while the RMSProp optimizer was ranked third with an accuracy level of 0.9978.","PeriodicalId":516904,"journal":{"name":"Public Research Journal of Engineering, Data Technology and Computer Science","volume":"39 3","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139894117","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The hallmarks of Obsessive-Compulsive Disorder (OCD) are intrusive, anxiety-inducing thoughts (called obsessions) and associated repeated activities (called compulsions). To understand the patterns and relationships between OCD data that have been obtained, data will be grouped (clustering). In clustering using several clustering algorithms, namely K-Means, BIRCH, In this work, hierarchical clustering was used to identify the optimal cluster value comparison, and the Davies Bouldin Index (DBI) was used to confirm the results. Then the results of the best cluster value in processing OCD data are using the BIRCH algorithm in the K10 experiment which gets a value of 1.3. While the K-Means algorithm obtained the best cluster at K10 with a value obtained of 1.36 and the Hierarchical clustering algorithm also at the K10 value of 2.03. Thus in this study, the comparison results of the application of 3 clustering algorithms obtained results, namely the BIRCH algorithm shows the value of the resulting cluster is the best in clustering OCD data. This means that the BIRCH algorithm can be used to cluster OCD data more accurately and efficiently.
{"title":"Comparison of K-Means, BIRCH and Hierarchical Clustering Algorithms in Clustering OCD Symptom Data","authors":"Alika Rahmarsyarah Rizalde, Haykal Alya Mubarak, Gilang Ramadhan, Mohd. Adzka Fatan","doi":"10.57152/predatecs.v1i2.1106","DOIUrl":"https://doi.org/10.57152/predatecs.v1i2.1106","url":null,"abstract":"The hallmarks of Obsessive-Compulsive Disorder (OCD) are intrusive, anxiety-inducing thoughts (called obsessions) and associated repeated activities (called compulsions). To understand the patterns and relationships between OCD data that have been obtained, data will be grouped (clustering). In clustering using several clustering algorithms, namely K-Means, BIRCH, In this work, hierarchical clustering was used to identify the optimal cluster value comparison, and the Davies Bouldin Index (DBI) was used to confirm the results. Then the results of the best cluster value in processing OCD data are using the BIRCH algorithm in the K10 experiment which gets a value of 1.3. While the K-Means algorithm obtained the best cluster at K10 with a value obtained of 1.36 and the Hierarchical clustering algorithm also at the K10 value of 2.03. Thus in this study, the comparison results of the application of 3 clustering algorithms obtained results, namely the BIRCH algorithm shows the value of the resulting cluster is the best in clustering OCD data. This means that the BIRCH algorithm can be used to cluster OCD data more accurately and efficiently.","PeriodicalId":516904,"journal":{"name":"Public Research Journal of Engineering, Data Technology and Computer Science","volume":"19 5","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139897583","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-02-01DOI: 10.57152/predatecs.v1i2.872
Puji Dwi Rinanda, Delvi Nur Aini, Tata Ayunita Pertiwi, Suryani Suryani, A. J. Prakash
Plant diseases pose a serious threat to a country's economy and food security. One way to identify diseases in plants is through the visible features on their leaves. Farmers need to conduct an active examination of the condition of the leaves of plants to eradicate this disease. In this case, automatic recognition and classification of diseases of leaf crops is required in order to obtain an accurate identification. Digital image processing technology can be used to solve this problem. One effective approach is the Convolutional Neural Network (CNN). The trial image used a dataset consisting of 4000 images of mango leaf disease, namely Anthracnose, Bacterial Canker, Cutting Weevil, Die Back, Gall Midge, Powdery Mildew, and Sooty Mould. This study aims to compare the accuracy of CNN, VGG16 and InceptionV3. Architectural modeling uses these drawings to train and test models in recognizing and classifying mango leaf diseases. The results of modeling trials in the three scenarios were most optimally obtained by VGG16 with an accuracy of 96.87%, then InceptionV3 with an acquisition of 96.50% and CNN by 81%.
{"title":"Implementation of Convolutional Neural Network (CNN) for Image Classification of Leaf Disease In Mango Plants Using Deep Learning Approach","authors":"Puji Dwi Rinanda, Delvi Nur Aini, Tata Ayunita Pertiwi, Suryani Suryani, A. J. Prakash","doi":"10.57152/predatecs.v1i2.872","DOIUrl":"https://doi.org/10.57152/predatecs.v1i2.872","url":null,"abstract":"Plant diseases pose a serious threat to a country's economy and food security. One way to identify diseases in plants is through the visible features on their leaves. Farmers need to conduct an active examination of the condition of the leaves of plants to eradicate this disease. In this case, automatic recognition and classification of diseases of leaf crops is required in order to obtain an accurate identification. Digital image processing technology can be used to solve this problem. One effective approach is the Convolutional Neural Network (CNN). The trial image used a dataset consisting of 4000 images of mango leaf disease, namely Anthracnose, Bacterial Canker, Cutting Weevil, Die Back, Gall Midge, Powdery Mildew, and Sooty Mould. This study aims to compare the accuracy of CNN, VGG16 and InceptionV3. Architectural modeling uses these drawings to train and test models in recognizing and classifying mango leaf diseases. The results of modeling trials in the three scenarios were most optimally obtained by VGG16 with an accuracy of 96.87%, then InceptionV3 with an acquisition of 96.50% and CNN by 81%.","PeriodicalId":516904,"journal":{"name":"Public Research Journal of Engineering, Data Technology and Computer Science","volume":"53 10","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139894065","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The hallmarks of Obsessive-Compulsive Disorder (OCD) are intrusive, anxiety-inducing thoughts (called obsessions) and associated repeated activities (called compulsions). To understand the patterns and relationships between OCD data that have been obtained, data will be grouped (clustering). In clustering using several clustering algorithms, namely K-Means, BIRCH, In this work, hierarchical clustering was used to identify the optimal cluster value comparison, and the Davies Bouldin Index (DBI) was used to confirm the results. Then the results of the best cluster value in processing OCD data are using the BIRCH algorithm in the K10 experiment which gets a value of 1.3. While the K-Means algorithm obtained the best cluster at K10 with a value obtained of 1.36 and the Hierarchical clustering algorithm also at the K10 value of 2.03. Thus in this study, the comparison results of the application of 3 clustering algorithms obtained results, namely the BIRCH algorithm shows the value of the resulting cluster is the best in clustering OCD data. This means that the BIRCH algorithm can be used to cluster OCD data more accurately and efficiently.
{"title":"Comparison of K-Means, BIRCH and Hierarchical Clustering Algorithms in Clustering OCD Symptom Data","authors":"Alika Rahmarsyarah Rizalde, Haykal Alya Mubarak, Gilang Ramadhan, Mohd. Adzka Fatan","doi":"10.57152/predatecs.v1i2.1106","DOIUrl":"https://doi.org/10.57152/predatecs.v1i2.1106","url":null,"abstract":"The hallmarks of Obsessive-Compulsive Disorder (OCD) are intrusive, anxiety-inducing thoughts (called obsessions) and associated repeated activities (called compulsions). To understand the patterns and relationships between OCD data that have been obtained, data will be grouped (clustering). In clustering using several clustering algorithms, namely K-Means, BIRCH, In this work, hierarchical clustering was used to identify the optimal cluster value comparison, and the Davies Bouldin Index (DBI) was used to confirm the results. Then the results of the best cluster value in processing OCD data are using the BIRCH algorithm in the K10 experiment which gets a value of 1.3. While the K-Means algorithm obtained the best cluster at K10 with a value obtained of 1.36 and the Hierarchical clustering algorithm also at the K10 value of 2.03. Thus in this study, the comparison results of the application of 3 clustering algorithms obtained results, namely the BIRCH algorithm shows the value of the resulting cluster is the best in clustering OCD data. This means that the BIRCH algorithm can be used to cluster OCD data more accurately and efficiently.","PeriodicalId":516904,"journal":{"name":"Public Research Journal of Engineering, Data Technology and Computer Science","volume":"75 ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139893815","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Extreme climate change is the most common problem in Indonesia. Extreme climate change for months can cause various natural disasters. Therefore, it is necessary to make predictions about climate change that will occur in order to avoid the risk of future conflicts. This study uses the Artificial Neural Network (ANN), Recurrent Neural Network (RNN) and Long Short Term Memory (LSTM) algorithms by comparing the performance of the three using Mean Squared Error (MSE), Root Mean Squared Error (RMSE) and Mean Absolute Percentage Error (MAPE) evaluations. The results of this study indicate that RNN is better at predicting temperature in Indonesia compared to ANN and LSTM. This is evidenced by the MAPE value generated by the RNN which is smaller than the ANN and LSTM, which is 1.852 %, the RMSE value is 1,870, and the MSE value is 3,497.
{"title":"Performance Comparison Between Artificial Neural Network, Recurrent Neural Network and Long Short-Term Memory for Prediction of Extreme Climate Change","authors":"Nanda Try Luchia, Ena Tasia, Indah Ramadhani, Akhas Rahmadeyan, Raudiatul Zahra","doi":"10.57152/predatecs.v1i2.864","DOIUrl":"https://doi.org/10.57152/predatecs.v1i2.864","url":null,"abstract":"Extreme climate change is the most common problem in Indonesia. Extreme climate change for months can cause various natural disasters. Therefore, it is necessary to make predictions about climate change that will occur in order to avoid the risk of future conflicts. This study uses the Artificial Neural Network (ANN), Recurrent Neural Network (RNN) and Long Short Term Memory (LSTM) algorithms by comparing the performance of the three using Mean Squared Error (MSE), Root Mean Squared Error (RMSE) and Mean Absolute Percentage Error (MAPE) evaluations. The results of this study indicate that RNN is better at predicting temperature in Indonesia compared to ANN and LSTM. This is evidenced by the MAPE value generated by the RNN which is smaller than the ANN and LSTM, which is 1.852 %, the RMSE value is 1,870, and the MSE value is 3,497.","PeriodicalId":516904,"journal":{"name":"Public Research Journal of Engineering, Data Technology and Computer Science","volume":"4 10","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139897468","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The changing needs of electrical energy result in the electrical power needed for everyday life being unstable, so planning and predicting how much electrical load is needed so that the electricity generated is always of good quality. So it is necessary to predict the consumption of electrical energy by using forecasting on the machine learning method. Support Vector Machine (SVM), Autoregressive Integrated Motion Average (ARIMA), and Long Short-Term Memory (LSTM) are models that are often used to overcome patterns in predictions. To find out the best models how to predict electricity consumption in the future and how the SVM, LSTM, and ARIMA algorithms perform in predicting electricity consumption. This research will look for the RMSE value and prediction time, then compare it with the best average value. The results of the study show that the ARIMA model is able to predict electricity usage for the next 1 year period, in the evaluation using the RMSE metric, where SVM shows a much lower value than ARIMA and LSTM. In this case, SVM achieved RMSE of 0.020, while ARIMA and LSTM achieved RMSE of 7.659 and 11.4183, respectively. Even though SVM has a lower RMSE, it is still unable to predict electricity usage for the next 1 year with sufficient accuracy.
{"title":"Performance Comparison of ARIMA, LSTM and SVM Models for Electric Energy Consumption Analysis","authors":"Nilam Wahdiaz Azani, Cintia Putri Trisya, Laras Mayangda Sari, Hani Handayani, Muhammad Rizki Miftha Alhamid","doi":"10.57152/predatecs.v1i2.869","DOIUrl":"https://doi.org/10.57152/predatecs.v1i2.869","url":null,"abstract":"The changing needs of electrical energy result in the electrical power needed for everyday life being unstable, so planning and predicting how much electrical load is needed so that the electricity generated is always of good quality. So it is necessary to predict the consumption of electrical energy by using forecasting on the machine learning method. Support Vector Machine (SVM), Autoregressive Integrated Motion Average (ARIMA), and Long Short-Term Memory (LSTM) are models that are often used to overcome patterns in predictions. To find out the best models how to predict electricity consumption in the future and how the SVM, LSTM, and ARIMA algorithms perform in predicting electricity consumption. This research will look for the RMSE value and prediction time, then compare it with the best average value. The results of the study show that the ARIMA model is able to predict electricity usage for the next 1 year period, in the evaluation using the RMSE metric, where SVM shows a much lower value than ARIMA and LSTM. In this case, SVM achieved RMSE of 0.020, while ARIMA and LSTM achieved RMSE of 7.659 and 11.4183, respectively. Even though SVM has a lower RMSE, it is still unable to predict electricity usage for the next 1 year with sufficient accuracy.","PeriodicalId":516904,"journal":{"name":"Public Research Journal of Engineering, Data Technology and Computer Science","volume":"112 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139897670","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The changing needs of electrical energy result in the electrical power needed for everyday life being unstable, so planning and predicting how much electrical load is needed so that the electricity generated is always of good quality. So it is necessary to predict the consumption of electrical energy by using forecasting on the machine learning method. Support Vector Machine (SVM), Autoregressive Integrated Motion Average (ARIMA), and Long Short-Term Memory (LSTM) are models that are often used to overcome patterns in predictions. To find out the best models how to predict electricity consumption in the future and how the SVM, LSTM, and ARIMA algorithms perform in predicting electricity consumption. This research will look for the RMSE value and prediction time, then compare it with the best average value. The results of the study show that the ARIMA model is able to predict electricity usage for the next 1 year period, in the evaluation using the RMSE metric, where SVM shows a much lower value than ARIMA and LSTM. In this case, SVM achieved RMSE of 0.020, while ARIMA and LSTM achieved RMSE of 7.659 and 11.4183, respectively. Even though SVM has a lower RMSE, it is still unable to predict electricity usage for the next 1 year with sufficient accuracy.
{"title":"Performance Comparison of ARIMA, LSTM and SVM Models for Electric Energy Consumption Analysis","authors":"Nilam Wahdiaz Azani, Cintia Putri Trisya, Laras Mayangda Sari, Hani Handayani, Muhammad Rizki Miftha Alhamid","doi":"10.57152/predatecs.v1i2.869","DOIUrl":"https://doi.org/10.57152/predatecs.v1i2.869","url":null,"abstract":"The changing needs of electrical energy result in the electrical power needed for everyday life being unstable, so planning and predicting how much electrical load is needed so that the electricity generated is always of good quality. So it is necessary to predict the consumption of electrical energy by using forecasting on the machine learning method. Support Vector Machine (SVM), Autoregressive Integrated Motion Average (ARIMA), and Long Short-Term Memory (LSTM) are models that are often used to overcome patterns in predictions. To find out the best models how to predict electricity consumption in the future and how the SVM, LSTM, and ARIMA algorithms perform in predicting electricity consumption. This research will look for the RMSE value and prediction time, then compare it with the best average value. The results of the study show that the ARIMA model is able to predict electricity usage for the next 1 year period, in the evaluation using the RMSE metric, where SVM shows a much lower value than ARIMA and LSTM. In this case, SVM achieved RMSE of 0.020, while ARIMA and LSTM achieved RMSE of 7.659 and 11.4183, respectively. Even though SVM has a lower RMSE, it is still unable to predict electricity usage for the next 1 year with sufficient accuracy.","PeriodicalId":516904,"journal":{"name":"Public Research Journal of Engineering, Data Technology and Computer Science","volume":"79 9","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139894062","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Rice is the most important crop in global food security and socioeconomic stability. A part of the world's population makes rice a food requirement but the problem is found that all rice varieties suffer from several diseases and pests. Therefore, it is necessary to ensure the quality of healthy and proper rice growth by detecting diseases present in rice plants and treatment of affected plants. In this study, the Convolutional Neural Network (CNN) algorithm was applied in classifying diseases on the leaves of rice plants by experimenting with several parameters and architecture to get the best accuracy. This study was conducted image classification of rice plant disease using CNN architecture ResNet-50V2 with data using preprocessing Augmentation. The test was conducted with three optimizers such as SGD, Adam, and RMSprop by combining various parameters, namely epoch, batch size, learning rate, and SGD and RMSprop optimizers. Division of image data with 70:30 ratio of training data and test data; 80:20; 90:10. From these results, it was found that Adam was the best optimizer in the 80:20 data division in this study with an accuracy level of 0.9992, followed by the SGD optimizer with an accuracy level of 0.9983, while the RMSProp optimizer was ranked third with an accuracy level of 0.9978.
{"title":"Application of Convolutional Neural Network ResNet-50 V2 on Image Classification of Rice Plant Disease","authors":"Delvi Hastari, Salsa Winanda, Aditya Rezky Pratama, Nana Nurhaliza, Ella Silvana Ginting","doi":"10.57152/predatecs.v1i2.865","DOIUrl":"https://doi.org/10.57152/predatecs.v1i2.865","url":null,"abstract":"Rice is the most important crop in global food security and socioeconomic stability. A part of the world's population makes rice a food requirement but the problem is found that all rice varieties suffer from several diseases and pests. Therefore, it is necessary to ensure the quality of healthy and proper rice growth by detecting diseases present in rice plants and treatment of affected plants. In this study, the Convolutional Neural Network (CNN) algorithm was applied in classifying diseases on the leaves of rice plants by experimenting with several parameters and architecture to get the best accuracy. This study was conducted image classification of rice plant disease using CNN architecture ResNet-50V2 with data using preprocessing Augmentation. The test was conducted with three optimizers such as SGD, Adam, and RMSprop by combining various parameters, namely epoch, batch size, learning rate, and SGD and RMSprop optimizers. Division of image data with 70:30 ratio of training data and test data; 80:20; 90:10. From these results, it was found that Adam was the best optimizer in the 80:20 data division in this study with an accuracy level of 0.9992, followed by the SGD optimizer with an accuracy level of 0.9983, while the RMSProp optimizer was ranked third with an accuracy level of 0.9978.","PeriodicalId":516904,"journal":{"name":"Public Research Journal of Engineering, Data Technology and Computer Science","volume":"61 5-6","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139897549","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-02-01DOI: 10.57152/predatecs.v1i2.872
Puji Dwi Rinanda, Delvi Nur Aini, Tata Ayunita Pertiwi, Suryani Suryani, A. J. Prakash
Plant diseases pose a serious threat to a country's economy and food security. One way to identify diseases in plants is through the visible features on their leaves. Farmers need to conduct an active examination of the condition of the leaves of plants to eradicate this disease. In this case, automatic recognition and classification of diseases of leaf crops is required in order to obtain an accurate identification. Digital image processing technology can be used to solve this problem. One effective approach is the Convolutional Neural Network (CNN). The trial image used a dataset consisting of 4000 images of mango leaf disease, namely Anthracnose, Bacterial Canker, Cutting Weevil, Die Back, Gall Midge, Powdery Mildew, and Sooty Mould. This study aims to compare the accuracy of CNN, VGG16 and InceptionV3. Architectural modeling uses these drawings to train and test models in recognizing and classifying mango leaf diseases. The results of modeling trials in the three scenarios were most optimally obtained by VGG16 with an accuracy of 96.87%, then InceptionV3 with an acquisition of 96.50% and CNN by 81%.
{"title":"Implementation of Convolutional Neural Network (CNN) for Image Classification of Leaf Disease In Mango Plants Using Deep Learning Approach","authors":"Puji Dwi Rinanda, Delvi Nur Aini, Tata Ayunita Pertiwi, Suryani Suryani, A. J. Prakash","doi":"10.57152/predatecs.v1i2.872","DOIUrl":"https://doi.org/10.57152/predatecs.v1i2.872","url":null,"abstract":"Plant diseases pose a serious threat to a country's economy and food security. One way to identify diseases in plants is through the visible features on their leaves. Farmers need to conduct an active examination of the condition of the leaves of plants to eradicate this disease. In this case, automatic recognition and classification of diseases of leaf crops is required in order to obtain an accurate identification. Digital image processing technology can be used to solve this problem. One effective approach is the Convolutional Neural Network (CNN). The trial image used a dataset consisting of 4000 images of mango leaf disease, namely Anthracnose, Bacterial Canker, Cutting Weevil, Die Back, Gall Midge, Powdery Mildew, and Sooty Mould. This study aims to compare the accuracy of CNN, VGG16 and InceptionV3. Architectural modeling uses these drawings to train and test models in recognizing and classifying mango leaf diseases. The results of modeling trials in the three scenarios were most optimally obtained by VGG16 with an accuracy of 96.87%, then InceptionV3 with an acquisition of 96.50% and CNN by 81%.","PeriodicalId":516904,"journal":{"name":"Public Research Journal of Engineering, Data Technology and Computer Science","volume":"72 1-2","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139897674","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：