A Fuzzy Logic-Based Crop Recommendation System
Soil, geographical and meteorological parameters have major impacts on sustained crop production. Most of the rural farmers have no adequate knowledge about the effects of these parameters on crop production. The rural farmers generally rely on their trad
- PDF / 815,894 Bytes
- 13 Pages / 439.37 x 666.142 pts Page_size
- 79 Downloads / 538 Views
Abstract Soil, geographical and meteorological parameters have major impacts on sustained crop production. Most of the rural farmers have no adequate knowledge about the effects of these parameters on crop production. The rural farmers generally rely on their traditional knowledge to select a crop which often leads to huge economic loss. A scientific system considering these site-specific parameters along with the traditional knowledge of the farmers may be an effective solution. This paper suggests a fuzzy logic-based crop recommendation system to assist rural farmers. The proposed model has been designed to deal with eight major crops grown in the state of West Bengal. Separate fuzzy rule bases were created for each crop to achieve faster parallel processing. The performance of the model has been validated by a diverse dataset and achieved an accuracy of about 92%. Keywords Crop recommendation system · Fuzzy logic · Fuzzy system in agriculture
G. Banerjee Department of Computer Science, Ananda Chandra College, Jalpaiguri, West Bengal 735101, India e-mail: [email protected] U. Sarkar National Informatics Centre, Ministry of Electronics & Information Technology, Government of India, Jalpaiguri, West Bengal 735101, India e-mail: [email protected] I. Ghosh (B) Department of Computer Science, Ananda Chandra College, Jalpaiguri, West Bengal 735101, India e-mail: [email protected] © Springer Nature Singapore Pte Ltd. 2021 D. Bhattacharjee et al. (eds.), Proceedings of International Conference on Frontiers in Computing and Systems, Advances in Intelligent Systems and Computing 1255, https://doi.org/10.1007/978-981-15-7834-2_6
57
58
G. Banerjee et al.
1 Introduction The selection of suitable crops for agriculture is fundamentally dependent on several factors. Some of them include the nutrients of the soil, average rainfall and terrain. A crop that is not compatible with these features will not give a profitable return. Traditionally, rural farmers select crops for cultivation based on their experiences without having sufficient knowledge about the soil and other influencing factors. Use of modern scientific tools and technologies can enable a farmer to make more accurate and site-specific decisions for the selection of crops. Several kinds of researches have been carried out in this direction. In 2016, Arooj et al., compared four different data mining-models for classifying soils based on different parameters such as pH, texture, electrical conductivity [1]. In 2017, some researchers in Bangladesh used multiple linear regression and k-nearest neighbour models for prediction of yield [2]. An expert system based approach was proposed by Nevo et al., in determining the crop suitability based on different parameters [3]. Some researchers have used Geographic Information Systems (GIS) and other parameters for suggesting favourable crops for cultivation [4, 5]. Based on Agricultural Information Systems (AIS), Laliwala et al., has devised a rule-based recommendation system that covers multiple aspects of farming [6
Data Loading...
