Early Detection of Plant Diseases Using IoT Sensors and Machine Learning Algorithms
- Title
- Early Detection of Plant Diseases Using IoT Sensors and Machine Learning Algorithms
- Creator
- Das, Vishal; George, Jossy; Kumar, Pawan
- Description
- Agriculture is one of the most important and necessitates of the world. This paper is a study to detect plant diseases using IoT sensors and ML Algorithms for early detection of plant diseases using IoT sensors and machine learning algorithms. A primary dataset from Indian Agricultural Research Institute (ICAR) was used for the research. The dataset comprised the following features: temperature, humidity, soil moisture, leaf wetness, and dew point. Five different machine learning algorithms were explored for the implementation: Logistic Regression, Random Forest, XGBoost, CatBoost, and LightGBM. Upon comparative analysis, it was found that the LightBGM model performed the best with an accuracy of 93.4 % using cross-validation, implying remarkable performance for real-time plant disease monitoring. 2025 IEEE.
- Source
- Proceedings - 2025 International Conference on Transformative Computing Technologies, ICTCT 2025;pp.344-350
- Date
- 01-01-2025
- Publisher
- Institute of Electrical and Electronics Engineers Inc.
- Subject
- CatBoost; Gradient Boosting; Internet of Things (IoT); Machine Learning; Plant Disease Detection; Precision Agriculture
- Coverage
- Das V., CHRIST (Deemed to be University), India; George J., CHRIST (Deemed to be University), India; Kumar P., CHRIST (Deemed to be University), India
- Rights
- Restricted Access; Hardcopy may be available in the library
- Relation
- ISBN: 979-833159195-3;
- Format
- online
- Language
- English
- Type
- Conference paper
Collection
Citation
Das, Vishal; George, Jossy; Kumar, Pawan, “Early Detection of Plant Diseases Using IoT Sensors and Machine Learning Algorithms,” CHRIST (Deemed To Be University) Institutional Repository, accessed June 18, 2026, https://archives.christuniversity.in/items/show/26135.