Deep Learning Based Plant Disease Detection for Smart Agriculture. Ale, L., Sheta, A., Li, L., Wang, Y., & Zhang, N. In 2019 IEEE Globecom Workshops (GC Wkshps), pages 1–6, December, 2019. doi abstract bibtex Deep learning is a promising approach for fine- grained disease severity classification for smart agriculture, as it avoids the labor-intensive feature engineering and segmentation-based threshold. In this work, we first propose a Densely Connected Convolutional Networks (DenseNet) based transfer learning method to detect the plant diseases, which expects to run on edge servers with augmented computing resources. Then, we propose a lightweight Deep Neural Networks (DNN) approach that can run on Internet of Things (IoT) devices with constrained resources. To reduce the size and computation cost of the model, we further simplify the DNN model and reduce the size of input sizes. The proposed models are trained with different image sizes to find the appropriate size of the input images. Experiment results are provided to evaluate the performance of the proposed models based on real- world dataset, which demonstrate the proposed models can accurately detect plant disease using low computational resources.
@inproceedings{ale_deep_2019,
title = {Deep {Learning} {Based} {Plant} {Disease} {Detection} for {Smart} {Agriculture}},
doi = {10.1109/GCWkshps45667.2019.9024439},
abstract = {Deep learning is a promising approach for fine- grained disease severity classification for smart agriculture, as it avoids the labor-intensive feature engineering and segmentation-based threshold. In this work, we first propose a Densely Connected Convolutional Networks (DenseNet) based transfer learning method to detect the plant diseases, which expects to run on edge servers with augmented computing resources. Then, we propose a lightweight Deep Neural Networks (DNN) approach that can run on Internet of Things (IoT) devices with constrained resources. To reduce the size and computation cost of the model, we further simplify the DNN model and reduce the size of input sizes. The proposed models are trained with different image sizes to find the appropriate size of the input images. Experiment results are provided to evaluate the performance of the proposed models based on real- world dataset, which demonstrate the proposed models can accurately detect plant disease using low computational resources.},
booktitle = {2019 {IEEE} {Globecom} {Workshops} ({GC} {Wkshps})},
author = {Ale, Laha and Sheta, Alaa and Li, Longzhuang and Wang, Ye and Zhang, Ning},
month = dec,
year = {2019},
keywords = {Agriculture, Brain modeling, Computational efficiency, Computational modeling, DNN model, Deep learning, Diseases, Feature extraction, Internet of Things devices, Machine learning, agriculture, augmented computing resources, computation cost, constrained resources, convolutional neural nets, densely connected convolutional networks based transfer learning method, edge servers, grained disease severity classification, image classification, image segmentation, image sizes, input sizes, labor-intensive feature engineering, learning (artificial intelligence), lightweight Deep neural networks, low computational resources, plant disease detection, plant diseases, segmentation-based threshold, smart agriculture},
pages = {1--6},
}
Downloads: 0
{"_id":"5X2zHaHyJR4h9qiKT","bibbaseid":"ale-sheta-li-wang-zhang-deeplearningbasedplantdiseasedetectionforsmartagriculture-2019","author_short":["Ale, L.","Sheta, A.","Li, L.","Wang, Y.","Zhang, N."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","title":"Deep Learning Based Plant Disease Detection for Smart Agriculture","doi":"10.1109/GCWkshps45667.2019.9024439","abstract":"Deep learning is a promising approach for fine- grained disease severity classification for smart agriculture, as it avoids the labor-intensive feature engineering and segmentation-based threshold. In this work, we first propose a Densely Connected Convolutional Networks (DenseNet) based transfer learning method to detect the plant diseases, which expects to run on edge servers with augmented computing resources. Then, we propose a lightweight Deep Neural Networks (DNN) approach that can run on Internet of Things (IoT) devices with constrained resources. To reduce the size and computation cost of the model, we further simplify the DNN model and reduce the size of input sizes. The proposed models are trained with different image sizes to find the appropriate size of the input images. Experiment results are provided to evaluate the performance of the proposed models based on real- world dataset, which demonstrate the proposed models can accurately detect plant disease using low computational resources.","booktitle":"2019 IEEE Globecom Workshops (GC Wkshps)","author":[{"propositions":[],"lastnames":["Ale"],"firstnames":["Laha"],"suffixes":[]},{"propositions":[],"lastnames":["Sheta"],"firstnames":["Alaa"],"suffixes":[]},{"propositions":[],"lastnames":["Li"],"firstnames":["Longzhuang"],"suffixes":[]},{"propositions":[],"lastnames":["Wang"],"firstnames":["Ye"],"suffixes":[]},{"propositions":[],"lastnames":["Zhang"],"firstnames":["Ning"],"suffixes":[]}],"month":"December","year":"2019","keywords":"Agriculture, Brain modeling, Computational efficiency, Computational modeling, DNN model, Deep learning, Diseases, Feature extraction, Internet of Things devices, Machine learning, agriculture, augmented computing resources, computation cost, constrained resources, convolutional neural nets, densely connected convolutional networks based transfer learning method, edge servers, grained disease severity classification, image classification, image segmentation, image sizes, input sizes, labor-intensive feature engineering, learning (artificial intelligence), lightweight Deep neural networks, low computational resources, plant disease detection, plant diseases, segmentation-based threshold, smart agriculture","pages":"1–6","bibtex":"@inproceedings{ale_deep_2019,\n\ttitle = {Deep {Learning} {Based} {Plant} {Disease} {Detection} for {Smart} {Agriculture}},\n\tdoi = {10.1109/GCWkshps45667.2019.9024439},\n\tabstract = {Deep learning is a promising approach for fine- grained disease severity classification for smart agriculture, as it avoids the labor-intensive feature engineering and segmentation-based threshold. In this work, we first propose a Densely Connected Convolutional Networks (DenseNet) based transfer learning method to detect the plant diseases, which expects to run on edge servers with augmented computing resources. Then, we propose a lightweight Deep Neural Networks (DNN) approach that can run on Internet of Things (IoT) devices with constrained resources. To reduce the size and computation cost of the model, we further simplify the DNN model and reduce the size of input sizes. The proposed models are trained with different image sizes to find the appropriate size of the input images. Experiment results are provided to evaluate the performance of the proposed models based on real- world dataset, which demonstrate the proposed models can accurately detect plant disease using low computational resources.},\n\tbooktitle = {2019 {IEEE} {Globecom} {Workshops} ({GC} {Wkshps})},\n\tauthor = {Ale, Laha and Sheta, Alaa and Li, Longzhuang and Wang, Ye and Zhang, Ning},\n\tmonth = dec,\n\tyear = {2019},\n\tkeywords = {Agriculture, Brain modeling, Computational efficiency, Computational modeling, DNN model, Deep learning, Diseases, Feature extraction, Internet of Things devices, Machine learning, agriculture, augmented computing resources, computation cost, constrained resources, convolutional neural nets, densely connected convolutional networks based transfer learning method, edge servers, grained disease severity classification, image classification, image segmentation, image sizes, input sizes, labor-intensive feature engineering, learning (artificial intelligence), lightweight Deep neural networks, low computational resources, plant disease detection, plant diseases, segmentation-based threshold, smart agriculture},\n\tpages = {1--6},\n}\n\n","author_short":["Ale, L.","Sheta, A.","Li, L.","Wang, Y.","Zhang, N."],"key":"ale_deep_2019","id":"ale_deep_2019","bibbaseid":"ale-sheta-li-wang-zhang-deeplearningbasedplantdiseasedetectionforsmartagriculture-2019","role":"author","urls":{},"keyword":["Agriculture","Brain modeling","Computational efficiency","Computational modeling","DNN model","Deep learning","Diseases","Feature extraction","Internet of Things devices","Machine learning","agriculture","augmented computing resources","computation cost","constrained resources","convolutional neural nets","densely connected convolutional networks based transfer learning method","edge servers","grained disease severity classification","image classification","image segmentation","image sizes","input sizes","labor-intensive feature engineering","learning (artificial intelligence)","lightweight Deep neural networks","low computational resources","plant disease detection","plant diseases","segmentation-based threshold","smart agriculture"],"metadata":{"authorlinks":{}}},"bibtype":"inproceedings","biburl":"https://bibbase.org/zotero/mcrimaldi","dataSources":["dq7oSdLvMkrCCarLK"],"keywords":["agriculture","brain modeling","computational efficiency","computational modeling","dnn model","deep learning","diseases","feature extraction","internet of things devices","machine learning","agriculture","augmented computing resources","computation cost","constrained resources","convolutional neural nets","densely connected convolutional networks based transfer learning method","edge servers","grained disease severity classification","image classification","image segmentation","image sizes","input sizes","labor-intensive feature engineering","learning (artificial intelligence)","lightweight deep neural networks","low computational resources","plant disease detection","plant diseases","segmentation-based threshold","smart agriculture"],"search_terms":["deep","learning","based","plant","disease","detection","smart","agriculture","ale","sheta","li","wang","zhang"],"title":"Deep Learning Based Plant Disease Detection for Smart Agriculture","year":2019}