Browsing by Author "Whaiduzzaman, Md"

Now showing 1 - 5 of 5

Anomaly Prediction in Solar Photovoltaic (PV) Systems via Rayleigh Distribution with Integrated Internet of Sensing Things (IoST) Monitoring and Dynamic Sun-Tracking
(Multidisciplinary Digital Publishing Institute, 2024-09-01) Akhund, Tajim Md. Niamat Ullah; Nice, Nafisha Tamanna; Joy, Muftain Ahmed; Ahmed, Tanvir; Whaiduzzaman, Md
The proliferation of solar panel installations presents significant societal and environmental advantages. However, many panels are situated in remote or inaccessible locations, like rooftops or vast desert expanses. Moreover, monitoring individual panel performance in large-scale systems poses a logistical challenge. Addressing this issue necessitates an efficient surveillance system leveraging wide area networks. This paper introduces an Internet of Sensing Things (IoST)-based monitoring system integrated with sun-tracking capabilities for solar panels. Cutting-edge sensors and microcontrollers collect real-time data and securely store it in a cloud-based server infrastructure, enabling global accessibility and comprehensive analysis for future optimization. Innovative techniques are proposed to maximize power generation from sunlight radiation, achieved through continuous panel alignment with the sun’s position throughout the day. A solar tracking mechanism, utilizing light-dependent sensors and servo motors, dynamically adjusts panel orientation based on the sun’s angle of elevation and direction. This research contributes to the advancement of efficient and sustainable solar energy systems. Integrating state-of-the-art technologies ensures reliability and effectiveness, paving the way for enhanced performance and the widespread adoption of solar energy. Additionally, the paper explores anomaly prediction using Rayleigh distribution, offering insights into potential irregularities in solar panel performance.
Exploring Significant Family Income Ranges of Career Decision Difficulties of Adolescents in Bangladesh Applying Regression Techniques
(2nd International Conference on Electrical, Computer and Communication Engineering, IEEE, 2019-04-04) Satu, Md. Shahriare; Ahamed, Sharif; Chowdhury, Asive; Whaiduzzaman, Md
Career Decision Making is essential part of human life. Most of the people are thinking about this since adolescence. Therefore, we should analyze significant features about career decision difficulties of adolescents in Bangladesh. The goal of this work to explore the most affected class of adolescents about career decision difficulties considering family income ranges in Bangladesh. In this situation, we gathered several records of high school going adolescents at Faridganj, Chandpur, Bangladesh using career decision difficulties questionnaire which was proposed by I. Gati et. al. Hence, several regression algorithms were considered for experimental analysis based on the characteristics of our primary career decision difficulties dataset. After that, these algorithms were applied into career decision difficulties dataset of adolescents and explored the best regression algorithm based on experimental results from them. Then, our selected best algorithm was implemented throughout different datasets (split from primary dataset) and interpreted their findings. Finally, we observed that middle level family income ranges (10000-21000 BDT) of adolescents were faced more difficulties to take proper decision about career than others. This analysis is suggested as a complementary tool for further psychological treatment about career decisions
Exploring Significant Family Income Ranges of Career Decision Difficulties of Adolescents in Bangladesh Applying Regression Techniques
(2nd International Conference on Electrical, Computer and Communication Engineering, ECCE 2019, 2019-04-04) Satu, Md. Shahriare; Ahamed, Sharif; Chowdhury, Asive; Whaiduzzaman, Md
Career Decision Making is essential part of human life. Most of the people are thinking about this since adolescence. Therefore, we should analyze significant features about career decision difficulties of adolescents in Bangladesh. The goal of this work to explore the most affected class of adolescents about career decision difficulties considering family income ranges in Bangladesh. In this situation, we gathered several records of high school going adolescents at Faridganj, Chandpur, Bangladesh using career decision difficulties questionnaire which was proposed by I. Gati et. al. Hence, several regression algorithms were considered for experimental analysis based on the characteristics of our primary career decision difficulties dataset. After that, these algorithms were applied into career decision difficulties dataset of adolescents and explored the best regression algorithm based on experimental results from them. Then, our selected best algorithm was implemented throughout different datasets (split from primary dataset) and interpreted their findings. Finally, we observed that middle level family income ranges (10000-21000 BDT) of adolescents were faced more difficulties to take proper decision about career than others. This analysis is suggested as a complementary tool for further psychological treatment about career decisions
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
Unmasking Banking Fraud: Unleashing the Power of Machine Learning and Explainable AI (XAI) on Imbalanced Data
(MDPI, 2024-05-23) Nobel, S. M. Nuruzzaman; Sultana, Shirin; Singha, Sondip Poul; Chaki, Sudipto; Mahi, Md. Julkar Nayeen; Jan, Tony; Barros, 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.