Browsing by Author "Nuruzzaman, S. M."

Now showing 1 - 2 of 2

Effect of partial replacement of diesel by natural gas on the performance of diesel engine and fuel economy
(Department of Mechanical Engineering, 1998-08) Nuruzzaman, S. M.; Hossain, Dr. Md. Imtiaz
The study investigated the use of natural gas (NG) for partial replacement of diesel from supply line in a single cylinder stationary diesel engine. The NG ,vas introduced through the intake mainfold along with air. The experiments have been carried out for different shaft power output and diesel replacement under the conditions of constant engine speed (2200 rpm). The experimental results show that the substitution of diesel by NG affect the brake specitic fuel consumption adversely. This is also reHeeted in the brake thermal efficiency of the engine. The use of NG as a partial replacement of diesel is found to be more etIective in cases of higher shaft power output. The results even suggest that the replacement of diesel by NG enables the engine to produce more engine power and thereby carry higher load. <, While considering specific cost estimation it is found that the specific cost of operation at higher substitution of diesel is much less than that at lower substitution of diesel when compared at the most economic operating point and at the current market price.
Unmasking Banking Fraud: Unleashing the Power of Machine Learning and Explainable AI (XAI) on Imbalanced Data
(Scopus, 2024-05-23) Nuruzzaman, S. M.; Sultana, Shirin; Singha, Sondip Poul; Chaki, Sudipto; Julkar, Md.; Tony, Nayeen Mahi; Barros, Jan Alistair; Whaiduzzaman, Md
Recognizing fraudulent activity in the banking system is essential due to the significant risks involved. When fraudulent transactions are vastly outnumbered by non-fraudulent ones, dealing with imbalanced datasets can be difficult. This study aims to determine the best model for detecting fraud by comparing four commonly used machine learning algorithms: Support Vector Machine (SVM), XGBoost, Decision Tree, and Logistic Regression. Additionally, we utilized the Synthetic Minority Over-sampling Technique (SMOTE) to address the issue of class imbalance. The XGBoost Classifier proved to be the most successful model for fraud detection, with an accuracy of 99.88%. We utilized SHAP and LIME analyses to provide greater clarity into the decision-making process of the XGBoost model and improve overall comprehension. This research shows that the XGBoost Classifier is highly effective in detecting banking fraud on imbalanced datasets, with an impressive accuracy score. The interpretability of the XGBoost Classifier model was further enhanced by applying SHAP and LIME analysis, which shed light on the significant features that contribute to fraud detection. The insights and findings presented here are valuable contributions to the ongoing efforts aimed at developing effective fraud detection systems for the banking industry