Thesis (Bachelor of Science in Computer Science)

Browse

Has files: NoSubject: search.filters.subject.XGBoost

Search Results

Now showing 1 - 2 of 2
  • No Thumbnail Available
    Item
    Attention-deficit/hyperactivity disorder detection leveraging an ensemble of encoder-decoder transformer and XGBoost models
    (BRAC University, 2024-10) Sarker, Sharon Rose; Mehjabin, Saowmi; Piper, Meherin Majid; Rahman, Rafeed
    "Early detection of neurodevelopmental disorders such as Attention-Deficit/ Hyperactivity Disorder(ADHD), can lead to improved outcomes and prompt intervention. Traditional detection methods have been facing challenges due to judgment and misinterpretations, lack of resources, and biasness which may cause under-diagnosing or over-diagnosing. Early detection of these neurodevelopmental disorders, not only helps individuals to get proper ministrations but also it can improve their social, cognitive and mental development. In this study, our aim is to build an ensemble model leveraging a custom Transformer with various attention mechanisms alongside an XGBoost model to improve diagnostic accuracy. By comparing the proposed model with other traditional machine learning and deep learning models, this study aims to enhance the accuracy and efficiency of diagnosis. By using a pre-processed EEG dataset and customized ensemble model, the proposed model has achieved 83% of accuracy, highest accuracy among the traditional models. Moreover, this research aims for future development in the field, by offering methodologies that can be useful to further studies focused on disorder detection. In conclusion, this research will use an ensemble model leveraging a custom Transformer with various attention mechanisms alongside an XGBoost model for early ADHD aiming to create a new precision and accessibility in identifying neurodevelopmental disorders. "
  • No Thumbnail Available
    Item
    Yield prediction for precision agriculture using extreme gradient boosting and support vector regression
    (BRAC University, 2021-01) Ahmed, Md. Sabbir; Tazwar, Md. Tasin; Khan, Haseen; Roy, Swadhin; Iqbal, Junaed; Alam, Md. Golam Rabiul
    The rate of population growth of southern Asia is rising dramatically. As a part of this area, Bangladesh is no different. Moreover, the cultivable lands are declining at a huge rate. So to maintain the balance between the food production and consumer demand, we need to know the yield of the crop earlier to maintain the balance as well as ensuring the food security of the people. Hence, food production in a precise manner needs to be introduced to get more production in a small amount of land. From this concept “Precision Agriculture” term has come. Since rice is the staple food of Bangladesh so this research tries to demonstrate precision agriculture in terms of paddy. This research proposes a system which is capable of predicting yield of paddy based on different parameters. For this prediction, two machine learning approaches are used, such as XGBoost and Support Vector Machine (SVM) that can predict the yield of aus, aman and boro based on the relevant features. The main objective of this system is to optimum paddy production using the minimum inputs to demonstrate precision agriculture in terms of paddy production. The result of the prediction will assist the farmers to take necessary steps if needed to increase the production. Again, the prediction result will help the government to take their decisions regarding agricultural perspective. There is some research in precision agriculture, however, there exist many scopes to use machine learning techniques to predict the yield of the harvest which will eventually help them economically. Therefore, this research focuses on developing an intelligent system for precision agriculture of paddy using yield prediction of it.