Programs
- M. Tech. in Automotive Engineering -
- Clinical Fellowship in Laboratory Genetics & Genomics - Fellowship
Publication Type : Conference Paper
Publisher : IEEE
Source : IEEE international Conference on Wireless Communications, Signal Processing and Networking (WiSPNET),
Url : https://ieeexplore.ieee.org/abstract/document/9032727
Campus : Chennai
School : School of Engineering
Department : Computer Science
Year : 2019
Abstract : This article is aimed to present a simple and efficient Internet of Things (IoT) enabled disease detection system to detect and classify the bunchy top of banana and sigatoka diseases in hill banana plant. The proposed system utilizes image processing and IoT to process the images of the plants and extract its texture features. From the GLCM features, classification is done using Random Forest Classification (RFC) technique at the monitoring site and analyzed by the agriculture experts to provide solutions. Apart from pathogens climatic changes also induce diseases in plants. Hence, it is mandatory to monitor the environmental parameters of the agriculture field including field temperature, soil moisture. These parameters are measured using temperature/ humidity sensor and soil moisture sensor that are interfaced with Raspberry Pi3. The proposed disease detection system has obtained an overall detection accuracy of around 99%. The performance results confirm that RFC- GLCM based classification performs better for hill banana dataset.
Cite this Research Publication : R. Deepika Devi, S. Aasha Nandhini, R. Hemalatha, S. Radha, "IoT Enabled Efficient Detection and Classification of Plant Diseases for Agricultural Applications”, IEEE international Conference on Wireless Communications, Signal Processing and Networking (WiSPNET), Chennai, India (2019)