Impact of Weather on Crops in Few Northern Parts of Bangladesh: HCI and Machine Learning Based Approach

Abstract

As Bangladesh is an agricultural country, the economy, as well as the food security of this country, mostly depends on the production level of different crops over the year. Therefore, there exists immense pressure on exaggerated crop production due to the fast growth of the population. But, the average production level is being hampered by the bad nature of the weather. We have conducted a survey on near about 100 farmers of two northern districts of Bangladesh: Pabna and Rajshahi and assessed the impact of rough nature on production. According to farmers and agriculturalists, it is noticed that rough weather causes about 30% to 70% production shortage than expectation with all other factors remaining constant. In this study, we have adopted Human-computer interaction (HCI) based approach (Soft System Methodology-SSM) to this aspect for efficacious collaboration with root-level farmers and agricultural trainers providing ease for understanding weather-related issues on the production of crops. Finally, some machine learning algorithms were also implemented on the obtained dataset to accurately classify the range of production level of rice and a comparison is made among the algorithms based on performance metrics. Moreover, an android based application is created to depict the summary of the study.

Prediction of Liver Diseases by Using Few Machine Learning Based Approaches

“…These classification algorithms can be implemented for other dominant diseases also like cardiac and diabetes prediction and classification. More than one dataset may be used for better approach and comparison (Ahmed et al, 2020). Another scope is to see whether by applying new algorithms will result any improvements over techniques which are used in this work in future.…”