Journal of Scientific and Industrial Research

Open Access Open Access  Restricted Access Subscription Access

Hyperparameter Optimization for Transfer Learning-based Disease Detection in Cassava Plants


Affiliations
1 Velagapudi Ramakrishna Siddhartha Engineering College, Vijayawada 520 007, Andhra Pradesh, India., India
2 Tejas Networks, Bengaluru 560 100, India., India
3 Prasad V. Potluri Siddhartha Institute of Technology, Vijayawada 520 007, Andhra Pradesh, India., India
4 School of computing, Mohan Babu University, Tirupati 517102, Andhra Pradesh, India., India
 

Cassava is quite possibly the mostwidely recognized staple food crop. It isa nutty-flavored, starchy root vegetable that is a primary energy source and carbs for individuals. During cropcultivation, cassava plant infections can influence the leaf and root, bringing about a tremendous loss to the harvest and financial market esteem. Hence, it isvital to detect diseases in cassava plants. But it requires enormous labor, longer time planning, and thoroughplant-specific knowledge. If disease detection is possible at the initial stages, then actions can betaken on time. Hence, there is a need to develop automatic detection methods for monitoring different parts of cassava plants. This study evaluates the efficiency of applying transfer learning to the pre-trained models for identifying diseases in cassava plants. The pre-trained EfficientNet model detects the disorders using data augmentation, fine-tuning the hyperparameters, cross-validation, and transfer learning. The experimentation is done with the cassava dataset provided by Kaggle, which contains cassava plant leaf images belonging to five classes. An experimental investigation shows that EfficientNet with transfer learning attains up to 89% accuracy. The effect of transfer learning is significant; consider getting the results of high accuracy and less dispersion; in very few cases, the model forecasts the wrong class labels. The outcomes give a promising strength tothe objective of this work, i.e., a model trained explicitly for agriculture with transfer learningcan assist the farmers with highly accurate results during farming to get a high yield.

Keywords

Cassava Leaf Diseases, Deep Learning, EfficientNet, Plant Disease Detection, Precision Agriculture.
User
Notifications
Font Size

  • Himani G, An analysis of agriculture sector in Indian economy, IOSR J Humanit Soc Sci (IOSR-JHSS) 19(1)(2014) 47–54.

  • Shruthi U, Nagaveni V & Raghavendra B K, A review on machine learning classification techniques for plant disease detection, Proc.2019 5 th Int Conf Adv Comput Commun Syst (ICACCS), IEEE (2019) 281–284.

  • LeCun Y, Bengio Y & Hinton G, Deep learning, Nature, 521 (2015) 436–444.

  • LeCun Y, Bottou L, BengioY & Haffner P, Gradient-based learning applied to document recognition, Proc IEEE,86(11) (1998) 2278–2324.

  • Dan C, Meier U, Masci J, Gambardella L M & Schmidhuber J, Flexible, high performance convolutional neural networks for image classification, Proc 22 nd Int Joint Conf Artif Intell, 2 (2011) 1237–1242.

  • Hinton G, Deng L, Yu D, Dahl G E, Mohamed A R, Jaitly N, Senior A, Vanhoucke V, NguyenP, Sainath T N & Kingsbury B, Deep neural networks for acoustic modeling in speech recognition: The shared views of four research groups, IEEE Signal processmag, 29(6)(2012) 82–97.

  • LeCun Y & Bengio Y, Convolutional networks for images, speech, and time series, in The handbook of brain theory and neural networks,3361(10) (1995).

  • Carranza-Rojas J, Goeau H, Bonnet P, Mata-Montero E & Joly A, Going deeper in the automated identification of Herbarium specimens, BMC Evol Biol, 17, 181 (2017), https://doi.org/10.1186/s12862-017-1014-z.

  • Yang X, Guo T, Machine learning in plant disease research, Eur J Bio Med Res 3(1) (2017) 6–9, DOI:10.18088/ ejbmr.3.1.2017.pp6-9.

  • Ahmed K, Shahidi T R, Alam I & Momen S, Rice leaf disease detection using machine learning techniques, 2019 Int Conf Sustain Technol Ind 4.0 (STI),IEEE, Dhaka, Bangladesh, (2019) 1–5.

  • Naik M R & Sivappagari C M R, Plant leaf and disease detection by using HSV features and SVM classifier,Int J Eng Sci,6(12)(2016) 1–4.

  • Panigrahi K P, Das H, Sahoo A K & Moharana S C, Maize leaf disease detection and classification usingmachine learning algorithms, inProgress in Computing, Analytics and Networking. Advances in Intelligent Systems and Computing edited by H Das, P Pattnaik, S Rautaray, K C Li, 1119 (Springer, Singapore), 659–669, https://doi.org/10.1007/978-981-15-2414-1_66.

  • Rao D R, Krishna M & Ramakrishna B, Smart ailment identification system for Paddy crop using machine learning, Int J Innov Eng Manag Res,9(3)(2020) 96–100.

  • Ashraf T & Khan Y N, Weed density classification in rice crop using computer vision, Comput Electron Agric,175 (2020) 105590.

  • Chen J, Chen J, Zhang D, Sun Y & Nanehkaran Y A, Using deep transfer learning for image-based plant disease identification, Comput Electron Agric,173 (2020) 105393.

  • Karlekar A & Seal A, SoyNet: soybean leaf diseases classification, Comput Electron Agric,172 (2020) 105342.

  • Kim W S, Lee D H & Kim Y J, Machine vision-based automatic disease symptom detection of onion downy mildew, Comput Electron Agric,168(2020) 105099.

  • Janakiramaiah B, Kalyani G, Prasad L V, Karuna A & Krishna M, Intelligent system for leaf disease detection using capsule networks for horticulture, J Intell Fuzzy Syst, 41(6) (2021) 6697–6713, 10.3233/JIFS-210593.

  • Subramanian M, Narasimha Prasad L V, Janakiramaiah B, Mohan Babu A & Sathishkumar V E, Hyperparameter optimization for transfer learning of VGG16 for disease identification in corn leaves using bayesian optimization, Big Data, 10(3)(2022) 215–229, https://doi.org/10.1089/ big.2021.0218.

  • Taiwo K A, Utilization potentials of cassava in Nigeria: the domestic and industrial products, Food Rev Int, 22(1)(2006) 29–42.

  • Singh V & Misra A K, Detection of plant leaf diseases using image segmentation and soft computing techniques, Inf process Agric, 4(1)(2017) 41–49.

  • Ufuan A A, Ajayi O A, Bokanga M & Maziya-Dixon B, The use of cassava leaves as food in Africa, Ecol Food Nutr, 44(6)(2005) 423–435, https://doi.org/10.1080/ 0367024050 0348771.

  • Akila M & Deepan P, Detection and classification of plant leaf diseases by using deep learning algorithm, Int J Eng Res Technol, 6 (2018) 2–7.

  • Ren S, He K, Girshick R & Sun J, Faster R-CNN: Towards real-time object detection with region proposal networks, NIPS'15: Proc 28 th Int Conf Neural Inf Process Syst, 2015, 91–99.

  • Dai J, Li Y, He K & Sun J, R-FCN: Object detection via region-based fully convolutional networks, NIPS'16: Proc 30 th Int Conf Neural Inf Process Syst, 2016, 379–387.

  • Liu W, Anguelov D, Erhan D, Szegedy C, Reed S, Fu C Y & Berg A C, SSD: Single shot multibox detector, in Computer Vision – ECCV 2016, ECCV 2016, Lecture Notes in Computer Science, edited by B Leibe, J Matas, Sebe N & M Welling, 9905(Springer, Cham) 2016, 21–37, https://doi.org/10.1007/978-3-319-46448-0_2.

  • Adhikari S, Saban K K, Balkumari L, Shrestha B & Baiju B, Tomato plant diseases detection system using image processing, Proc 1 st KEC Conf Eng Technol(Lalitpur) 1 (2018) 81–86.

  • Redmon J, Divvala S, Girshick R & Farhadi A, You only look once: Unified, real-time object detection, Proc IEEE Conf Comput Vis Pattern Recognit, (2016) 779–788.

  • Karthik R, Hariharan M, Anand S, Mathikshara P, Johnson A & Menaka R, Attention embedded residual CNN for disease detection in tomato leaves, Appl Soft Comput, 86 (2020) 105933.

  • Agarwal M, Singh A, Arjaria S,Sinha A & Gupta S, Toled: Tomato leaf disease detection using convolution neural network, Procedia Comput Sci, 167 (2020) 293–301.

  • Elhassouny A & Smarandache F, Smart mobile application to recognize tomato leaf diseases using convolutional neural networks, 2019 Int Conf Comput Sci Renew Energies (ICCSRE) IEEE (Agadir, Morocco) 2019, 1–4, doi: 10.1109/ICCSRE.2019.8807737.

  • Howard A G, Zhu M, Chen B,Kalenichenko D, Wang W, Weyand T, Andreetto M & Adam H, Mobilenets: Efficient convolutional neural networks for mobile vision applications, arXiv preprint arXiv:1704.04861 (2017).

  • Widiyanto S, Fitrianto R & Wardani D T, Implementation of convolutional neural network method for classification of diseases in tomato leaves, in 2019 Fourth Int Conf Inf Comput (ICIC)IEEE (Semarang, Indonesia) 2019, 1–5, doi: 10.1109/ICIC47613.2019.8985909.

  • Aduwo J R, Mwebaze E & Quinn J A, Automated vision-based diagnosis of Cassava mosaic disease, Ind Conf Data Mining- Workshops(New York, NY) (2010) 114–122.

  • Abdullakasim W, Powbunthorn K, Unartngam J & Takigama T, An images analysis technique for recognition of brown leaf spot disease in cassava, Tarım MakinalarıBilimi Dergisi, 7 (2011) 165–169.

  • Mwebaze E & Owomugisha G, Machine learning for plant disease incidence and severity measurements from leaf images, in Mach Learn Appl (ICMLA),15 th IEEE Int Conf, IEEE (Anaheim, CA) 2016.

  • Janakiramaiah B, Kalyani G, Prasad L V, Karuna A & Krishna M, Intelligent system for leaf disease detection using capsule networks for horticulture', J Intell Fuzzy Syst, (2021) 6697 – 6713.

  • Fuentes A, Yoon S, Kim S C & Park D S, A robust deep-learning-based detector for real-time tomato plant diseases and pests recognition, Sensors, 17(9)(2017) 2022, doi: 10.3390/s17092022.

  • Ashqar B A M & Abu-Naser S S, Image-based tomato leaves diseases detection using deep learning, Int J Acad Eng Res, 2(12) (2018) 10–16.

  • Zhang K, Wu Q, Liu A & Meng X, Can deep learning identify tomato leaf disease? Advances in Multimedia, 2018 ID 6710865, (2018), https://doi.org/10.1155/2018/ 6710865.

  • DurmuşH, GüneşE O & KırcıM, Disease detection on the leaves of the tomato plants by using deep learning, Proc 2017 6 th Int Conf Agro- GeoinfIEEE (2017) 1–5.

  • Ferentinos K P, Deep learning models for plant disease detection and diagnosis, Comput Electron Agric, 45 (2018) 311–318.

  • Türkoğlu M & Hanbay D, Plant disease and pest detection using deep learning‐based features, Turk J Electr Eng Comput Sci,27 (2019) 1636–1651.

  • Amara J, Bouaziz B & Algergawy A, A Deep learning‐based approach for banana leaf diseases classification, Proc BTW (Workshops)(Stuttgart, Germany) (2017) 79–88.

  • Kaggle competition, https://www.kaggle.com/c/cassava-disease/overview, (2019).

  • Tan M & Le Q, Efficientnet: Rethinking model scaling for convolutional neural networks, Int Conf Mach Learn PMLR, (2019).

  • Reza & Ali M, Realization of the contrast limited adaptive histogram equalization (CLAHE) for real-time image enhancement, J Signal Process Syst, 38(1)(2004) 35–44, https://doi.org/10.1023/B:VLSI.0000028532.53893.82


Abstract Views: 117

PDF Views: 90




  • Hyperparameter Optimization for Transfer Learning-based Disease Detection in Cassava Plants

Abstract Views: 117  |  PDF Views: 90

Authors

Kalyani G
Velagapudi Ramakrishna Siddhartha Engineering College, Vijayawada 520 007, Andhra Pradesh, India., India
Sai Sudheer K
Tejas Networks, Bengaluru 560 100, India., India
Janakiramaiah B
Prasad V. Potluri Siddhartha Institute of Technology, Vijayawada 520 007, Andhra Pradesh, India., India
Narendra Kumar Rao B
School of computing, Mohan Babu University, Tirupati 517102, Andhra Pradesh, India., India

Abstract


Cassava is quite possibly the mostwidely recognized staple food crop. It isa nutty-flavored, starchy root vegetable that is a primary energy source and carbs for individuals. During cropcultivation, cassava plant infections can influence the leaf and root, bringing about a tremendous loss to the harvest and financial market esteem. Hence, it isvital to detect diseases in cassava plants. But it requires enormous labor, longer time planning, and thoroughplant-specific knowledge. If disease detection is possible at the initial stages, then actions can betaken on time. Hence, there is a need to develop automatic detection methods for monitoring different parts of cassava plants. This study evaluates the efficiency of applying transfer learning to the pre-trained models for identifying diseases in cassava plants. The pre-trained EfficientNet model detects the disorders using data augmentation, fine-tuning the hyperparameters, cross-validation, and transfer learning. The experimentation is done with the cassava dataset provided by Kaggle, which contains cassava plant leaf images belonging to five classes. An experimental investigation shows that EfficientNet with transfer learning attains up to 89% accuracy. The effect of transfer learning is significant; consider getting the results of high accuracy and less dispersion; in very few cases, the model forecasts the wrong class labels. The outcomes give a promising strength tothe objective of this work, i.e., a model trained explicitly for agriculture with transfer learningcan assist the farmers with highly accurate results during farming to get a high yield.

Keywords


Cassava Leaf Diseases, Deep Learning, EfficientNet, Plant Disease Detection, Precision Agriculture.

References