ABSTRACT
Plant disease phenotyping using technology assures a promising step in sustainable agriculture. Solanum Tubrosum (Potato) is a highly cultivated vegetable plant, which is affected by fungal pathogens that leads to Early Blight and Late Blight diseases. Continuous monitoring of plant disease is a challenging task in identifying diseased leaves. This paper proposes a novel deep Convolutional Neural Network (CNN) for classifying the potato disease by reducing the computational time of learnable parameters using image phenotyping. A meta-heuristic algorithm known as the Whale Optimization Algorithm (WOA) is used in training to optimize the hyperparameters of the proposed CNN network. Potato disease is classified using optimized CNN called POT-Net, and the performance is analyzed using performance metrics: precision, recall, F1-score, and accuracy of each class. The performance POT-Net is compared with pre-trained DL and optimized algorithms using performance metrics and it is better than the state-of-the-art models, with an accuracy of 99.12%.
Acknowledgement
The authors acknowledge the Ministry of Education, Government of India, for providing financial support (as fellowship) for conducting research at the National Institute of Technology Silchar, Silchar,788010, Assam, India.
We thank the Department of Agriculture Engineering, Assam University, Silchar, India, for helping in collecting the dataset from the field.
Disclosure statement
No potential conflict of interest was reported by the author(s).
Additional information
Funding
Notes on contributors
D. N. Kiran Pandiri
D. N. Kiran Pandiri received the M.Tech degree in Embedded Systems from Amrita Vishwa Vidyapeetham University, India in 2012. He completed his B.Tech in the stream of Electronics and Communication Engineering from JNTU Kakinada, India, in 2009. He is currently pursuing Ph.D. in NIT Silchar, Assam.He worked as an Assistant Professor from 2014 to 2019 in the Department of Electronics and Communication Engineering, Madanapalle Institute of Technology & Science, Madanapalle, Andhra Pradesh, India. He worked as a Programmer Analyst in Cognizant Technology Solutions India Private Ltd., from 2012 to 2014.
R. Murugan
R. Murugan received the BE degree in Electronics and Communication Engineering, the ME degree in Embedded Systems Technologies from Anna University, Chennai, Tamilnadu, in 2005, 2010, respectively, and a Ph.D. degree from Information and Communication Engineering, Centre for Research, Anna University, Chennai, Tamilnadu, India.He worked as Assistant Professor in the Department of Electronics and Communication Engineering, Aalim Muhammed Salegh College of Engineering, Chennai from August 2010 to December 2017 and St.peter's Engineering College, Hyderabad, from January 2018 to May 2018. He joined as an Assistant Professor at the National Institute of Technology (NIT) in June 2018. His area of interest is Retinal Image Analysis, Medical Imaging, Digital Image Processing, Digital Signal Processing, Embedded systems, Machine Learning, and Deep Learning.Dr Murugan is invited as reviewer for IEEE Transactions on Medical Imaging (IEEE), Biomedical signal processing and control (Elsevier); Journal of Intelligent Systems (Springer); Journal of IEEE Access the journals of IEEE.
Tripti Goel
Tripti Goel received her BE from Maharishi Dayanand University in 2004, MTech in 2008 from Chottu Ram State College of Engineering, Haryana, and PhD in 2017 from BPS Mahilla Vishwavidyalaya, Haryana.She worked as a lecturer in Guru Premsukh Memorial College of Engg, Haryana, from 2009–2012. She joined NIT, Delhi, as an Assistant Professor in July 2015. After that she worked in National Brain Research Center, Gurugram as Research Scientist in February 2018. She joined NIT, Silchar, as an Assistant Professor in June 2018. Her area of interest is Pattern Recognition, Soft Computing, and Neuroimaging. She acted as a reviewer of Journal IET Biometrics.