The application of data mining has been utilized in different fields ranging from agriculture, finance, education, security, medicine, research etc. Data mining derives useful information from careful examination of data. In Nigeria, Agriculture plays a critical role in the economy as it provides high level of employment for many people. It is typical of farmers in Nigeria to plant crops without paying considerate attention to the soil and crop requirements as most farmers inherit the lands used for farming from their fathers and just continue in the pattern of farming they had always known. This is not favorable in the level of productivity they can actually attain as the effect can be seen in same level of crop yield year after year if not even worse. Modern farming techniques make use of data mining from previous data considering soil types, and other factors like weather and climatic conditions. This study built a model that enables possible prediction of crop yield from the historic data collected and offers suggestions to farmers on the right soil nutrients requirements that would enhance crop yield. This will enable early prediction of crop yield and prior idea to improve on the soil to increase productivity. The research used XGBoost algorithm for the crop yield prediction and the Support Vector Machine algorithm for the recommendation of appropriate improvement of soil nutrient requirements. The accuracy obtained for the prediction with XGBoost was 95.28%, while that obtained for the recommendation of fertilizer using SVM was 97.86%.

No abstract

This study aimed at developing a system using support vector machine (SVM) that will forecast sales of farm products for an agricultural farm so that managers can take strategic decisions timely to better market the excess farm products which some by nature are perishable. The sales prediction model used SVMs and Fuzzy Theory. The implementation was done using Python Programming Language. The system comprised of three (3) modules: web interface, flask and the SVM Framework. To evaluate the result of the SVM model, the RBF neural network was used as a benchmark. Data of previous sales records from University of Agriculture Makurdi (UAM) farm was used to train and test the system. After training the network with data which covered the time period from 21st January, 2017 to 30th June, 2019, the remaining data which covered from 1st July 2019 up to the 31st December, 2019 was used to test and validate the forecasting performance of the system. The Forecasting Precision (FP) value for the SVM was 96.75% and that of the RBF neural network forecasting value was 90.55%. Analysis from the results shows that the forecasting system with SVM had a greater precision in the sales of agricultural products.

With the explosive growth in the world’s population which has little or no corresponding rise in the food production, food insecurity has become eminent, and hence, the need to seek for opportunities to increase food production in order to cater for this population is paramount. The second goal of the Sustainable Development Goals (SDGs) (i.e., ending hunger, achieving food security and improved nutrition, and promoting sustainable agriculture) set by the United Nations (UN) for the year 2030 clearly acknowledged this fact. Improving food production cannot be achieved using the obsolete conventional methods of agriculture by our farmers; hence, this study focuses on developing a model for predicting climatic conditions with a view to reducing their negative impact, and boosting the yield of crop. Temperature, wind, humidity and rainfall were considered as the effect of these factors is more devastating in Nigeria as compared to sun light which is always in abundance. We implemented random forest algorithm using Python programming language to predict the aforementioned climate parameters. The data used was gotten from the Nigerian Meteorological (NiMet) Agency, Lokoja, Kogi State between 1988 and 2018. The result shows that random forest algorithm is effective in climate prediction as the accuracy from the model based on the climatic factors considered was 94.64%. With this, farmers would be able to plan ahead to prevent the impact of the fluctuations in these climatic factors; thus, the yield of crops would be increased. This would dwarf the negative impact of food insecurity to the populace.

This study engaged the convolutional neural network in curbing losses in terms of resources that farmers spends in treating animals where injuries must have emancipated from violence among other animals and in worst case scenario could eventually lead to death of animals. Animals in a ranch was the target and the study proposed a method that detects and reports activities of violence to ranchers such that farmers are relieved of the stress of close supervision and monitoring to avoid violence among animals. The scope of the study is limited to violence detection in cattle, goat, horse and sheep. Different machine learning models were built for each animal. The models yielded good results; the horse violence detection model had an outstanding performance of 93% accuracy, 93% accuracy for the sheep model, 88% accuracy for the goat model and 84% accuracy for the cattle model.