Transparent Peer Review By Scholar9
AN EFFECTIVE CROP YIELD PREDICTION USING KNN CLASSIFICATION METHOD FOR DECISION SUPPORT SYSTEM
Abstract
Agriculture is a backbone of Indian economy that is the main income source for most of the population in India. So farmers are always curious about yield prediction. Crop yield depends on various factors like soil, weather, rain, fertilizers and pesticides. Several factors have different impacts on agriculture, which can be quantified using appropriate statistical methodologies. Applying such methodologies and techniques on historical yield of crops, it is possible to obtain information or knowledge which can be helpful to farmers and government organizations for making better decision and policies which lead to increased production. The decision support system will help the farmers to cut the losses, farmer suicides and also will improve the crop yield due to proactive planning. This paper discusses and compares the various data mining techniques available for the decision support systems i.e. crop yield prediction. Crop yield prediction will assist the farmers and other stakeholders for better crop planning i.e. selling, warehousing, market prices etc. Mainly data mining techniques for DSS is based on artificial neural networks, Bayesian networks, vector support system etc. There are various researchers working on this area and proposed several techniques to attain the accuracy for crop yield, but the utmost accuracy and error free information is still need the enhancement to extract data from the bigger data sets. The decision support system will help the farmers to cut the losses, farmer suicides and also will improve the crop yield due to proactive planning. This paper discusses and compares the various data mining techniques available for the decision support systems crop yield prediction. proposed a crop prediction methodology based on parameters soil, PH, nitrogen, phosphate, potassium, organic carbon etc using the k-nearest neighbors (KNN).
Shreyas Mahimkar Reviewer
17 Sep 2024 03:58 PM
Approved
Relevance and Originality
The Research Article is highly relevant to the Indian agricultural sector, focusing on improving crop yield prediction through data mining techniques. Given that agriculture is a major economic driver in India, the paper’s exploration of decision support systems (DSS) to enhance crop management is both timely and important. The originality lies in the comparison of various data mining techniques, including artificial neural networks, Bayesian networks, and k-nearest neighbors (KNN), for yield prediction.
Methodology
The methodology involves applying statistical and data mining techniques to historical crop yield data. The Research Article outlines the use of artificial neural networks, Bayesian networks, and KNN, among other methods, to predict crop yield. While the general approach is sound, the paper would benefit from a more detailed explanation of how these models are trained, validated, and compared, including any specific algorithms or software used.
Validity & Reliability
The Research Article aims to enhance crop yield prediction accuracy through various data mining techniques. However, it lacks detailed information on the validation process and how the models' reliability is ensured. Including specifics on how the models are tested against real-world data and the methods used to handle potential data issues would enhance the study’s validity and reliability.
Clarity and Structure
The Research Article is generally clear in its objectives and discussion of data mining techniques. Nonetheless, the presentation of information could be improved by structuring the discussion on each technique more distinctly and ensuring that comparisons are easy to follow. A more organized structure, including sections on methodology, results, and discussion, would make the paper more accessible.
Result Analysis
The Research Article discusses the potential benefits of using DSS for crop yield prediction but lacks a thorough analysis of results. It would be beneficial to include detailed comparisons of model performance, supported by metrics such as accuracy, precision, and recall. Additionally, discussing how each technique affects decision-making processes and crop management practices would provide a deeper understanding of the results.
IJ Publication Publisher
Done Sir
Shreyas Mahimkar Reviewer