Toll Free Helpline (India): 1800 1234 070

Rest of World: +91-9810852116

Free Publication Certificate

Vol. 11, Special Issue 10 (2022)

Enhance ANN classifier performance using feature selection technique for detection of potato tuber diseases

Author(s):
Kumar Sanjeev and Suneeta Paswan
Abstract:
Plant growth can be hampered by disease, which has negative impacts on crop output. The disease and pests caused a 10–20% annual reduction in crop productivity. Because they are a cheap food, potatoes give the human diet a source of cheap energy. Diseases in the potato crop significantly reduce yield. For image capture, image pre-processing, image segmentation, feature extraction, feature selection, and picture recognition, the image processing technique is utilised. These photos are used to extract the 76 colour, texture, and area attributes. Both prediction and classification are done using the Feed Forward Neural Network (FFNN) Model. For the selection of features, Relieff approaches were employed. Without feature selection, the model's accuracy is 84.76%. By selecting features using the Relieff approach, the model's accuracy is 85.23%. Therefore, improving classifier performance is helpful for disease detection that is accurate.
Pages: 627-630  |  154 Views  52 Downloads
How to cite this article:
Kumar Sanjeev and Suneeta Paswan. Enhance ANN classifier performance using feature selection technique for detection of potato tuber diseases. The Pharma Innovation Journal. 2022; 11(10S): 627-630.

Call for book chapter