Md Masud Karim Rabbi

Mr. Md Masud Karim Rabbi

orcid

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
6 January 2025 in Journal of Computer Science and Technology Studies
Verified
Journal Article
Closed access
PDF file
SRSyed Ali Reza
Syed Ali Reza
SHSakibul Hasan
Sakibul Hasan
MAMohammad Hamid Hasan Amjad
Mohammad Hamid Hasan Amjad
SIShafikul Islam
Shafikul Islam
Md Masud Karim RabbiMd Masud Karim Rabbi
Md Masud Karim Rabbi
TJTanaya Jakir
Tanaya Jakir
As urbanization continues to expand and evolve in the USA, power demand has increased manifold, and with it has arisen significant environmental problems in the form of increased greenhouse gas emissions and loss of resources. In this paper, we explore how future machine-learning techniques could predict power consumption in U.S. cities. The central aim of this research is to develop advanced machine learning models with the potential to effectively predict energy consumption in cities. This involves not only identifying the key variables behind energy consumption but also selecting and fine-tuning machine learning algorithms that are most capable of understanding the dynamics of urban energy intricacies. This study focuses on the energy consumption patterns in the large cities of the United States, recognizing the diversity of challenges and opportunities presented by different geographic and demographic situations. The dataset used in this research project offered a comprehensive view of energy consumption across various fields of household, commercial, and industrial consumption, giving a holistic view of energy dynamics within cities. It integrated data collected from smart meters that offer granular electricity consumption patterns at the level of individual households and businesses with weather reports that detail ambient conditions governing energy demand, such as temperature and humidity fluctuations. Government energy records add historical context and policy information, further enhancing the dataset and enabling close analysis of trends and patterns in energy consumption. The next phase was to select and train three distinct machine models to explore the energy consumption dataset, namely, Logistic Regression, Random Forest, and XG-Boost algorithms. Random Forest outperformed Logistic Regression and XG-Boost slightly in terms of accuracy and other evaluation metrics. However, all models exhibit relatively low accuracy, suggesting the need for further tuning, feature engineering, or alternative models to improve predictions. In major cities in the U.S. such as Los Angeles, Chicago, and New York, smart power forecasting based on AI is revolutionizing power distribution and power planning in cities. By utilizing advanced machine learning models, these cities can process vast amounts of information and predict power usage with high accuracy. The incorporation of artificial intelligence (AI) in urban power planning has been a defining feature of modern-day power management in the USA. Major cities such as Los Angeles, Chicago, and New York are increasingly adopting AI-powered power forecasting technologies to rationalize power distribution. The integration of machine learning insights in U.S. government-driven green construction is instrumental in driving sustainable construction in infrastructure. By utilizing data-driven approaches, policymakers are in a position to identify the optimal design methods and low-power technologies with high performance in buildings.

25 August 2023 in Journal of Economics, Finance and Accounting Studies
Verified
Journal Article
Open access
PDF file
TJTanaya Jakir
Tanaya Jakir
NRNazmul Shakir Rabbi
Nazmul Shakir Rabbi
Md Masud Karim RabbiMd Masud Karim Rabbi
Md Masud Karim Rabbi
AAAbdul Ahad
Abdul Ahad
ASAbubokor Siam
Abubokor Siam
AHArat Hossain
Arat Hossain
The advances in financial fraud schemes create serious challenges for the institutions responsible for securing monetary transactions in the USA. With the spread of digital payments, fraud has become increasingly common, and a transformation in the techniques of fraud detection has been required in America. The utmost objective of this research project was to curate and test machine learning models aimed at real-time identification of fraudulent financial transactions in the USA. Through the application of cutting-edge data analytics and machine learning techniques, aimed to design predictive models that not only enhance the accuracy of the detection but also the general efficacies of fraud detection mechanisms. The data for our analysis was derived from exhaustive transactional logs, which hold key data necessary for the identification of fraudulent behavior. Every entry in such logs comprises significant attributes like the amount of the transaction, and from it, we got an insight into the patterns of expenditure and the identification of potentially fraudulent transactions per the amount. Further, the time of the transaction is also captured so we can identify unusual patterns at unusual times. The merchant ID has been provided to make it easier to evaluate specific merchants who might have a greater likelihood of fraud, while user location provides insight into geographic anomalies that might represent account takeovers or fraudulent conduct. By using such a vast dataset, we purposed to create in-depth models that improve the identification of and prevention of financial fraud. Three credible algorithms were deployed, notably, Logistic Regression, Random Forest, and XG-Boost. Multiple testing metrics form a complete suite for evaluating how well the fraud detection models perform. The evaluation system incorporates accuracy and precision and recall and F1-score and ROC-AUC as its primary measurement tools. . The performances of the three models were very high, with very close ROC AUC scores of Looking at the bars, the highest score is achieved by XG-Boost, meaning the best generalization capability to differentiate between the classes. Random Forest comes very close but scores marginally better than Logistic Regression. The infusion of sophisticated fraud models into the banking systems is a major step toward the protection of financial transactions in the U.S. financial market. By implementing models like Logistic Regression, Random Forest, and XG-Boost into the operational systems of banks, financial institutions can get real-time fraud detection mechanisms in place that are necessary to act as a safeguard for fraud-related risks. Moreover, such integration into bank systems can be made more efficient through ongoing learning and adaptation. To overcome the described limitations of existing fraud detection models, the combination of deep learning and graph-based fraud detection methods provides a promising direction for augmenting predictive ability.

10 July 2026 in Multimedia
Verified
Journal Article
Open access
PDF file
MSMst Masuma Akter Semi
Mst Masuma Akter Semi
Md Masud Karim RabbiMd Masud Karim Rabbi
Md Masud Karim Rabbi
KAKhandakar Rabbi Ahmed
Khandakar Rabbi Ahmed
MIMd Asraful Islam
Md Asraful Islam
MRMohaimin Rashid
Mohaimin Rashid
RIRakibul Islam
Rakibul Islam
Modern digital infrastructure generates heterogeneous, multimodal software artifacts encompassing structured code metrics, unstructured textual data such as commit logs and inline comments, and dynamic runtime signals whose complexity renders traditional defect detection approaches increasingly inadequate. This paper presents a cloud-native, transformer-based multimodal intelligence framework that integrates Large Language Model (LLM) semantic encoding with deep neural learning to enable automated defect prediction and proactive maintenance of large-scale digital infrastructure. The proposed system employs a sentence-transformer encoder (all-MiniLM-L6-v2) to process multimodal software artifact data—including serialized structured metrics and available textual fields—into dense 384-dimensional semantic embeddings. These embeddings are subsequently refined through a hierarchical multi-layer perceptron (MLP) deployed on a scalable cloud architecture for real-time inference. Evaluated on a real-world dataset of approximately 60,000 software modules, the framework achieves 99.72% accuracy, 100% precision, and an ROC-AUC of 0.9998, substantially outperforming baseline models including Random Forest, XGBoost, LSTM, and standalone MLP architectures. To address potential concerns regarding result validity, we conducted repeated experiments with five different random seeds (42, 0, 1, 7, 123) and ten-fold stratified cross-validation, confirming that performance metrics are stable across runs (accuracy: 0.9972 ± 0.0003). Data leakage was ruled out through strict temporal split ordering and pre-split SMOTE application exclusively on training folds. Confusion matrix and threshold-based analyses confirm strong classification performance with minimal false positives. SHAP-based explainability analysis further enhances the trustworthiness of the system by identifying the most influential multimodal predictors—past defect history, static analysis signals, and cyclomatic complexity—thereby contributing to transparent and accountable AI-driven infrastructure management. The presented framework advances the state of the art in LLM-driven multimodal systems by demonstrating how transformer intelligence, when applied to heterogeneous software artifact data streams, can enable reproducible, cloud-scalable, and interpretable maintenance pipelines for complex digital environments.

17 April 2025 in American Journal of Education and Technology
Verified
Journal Article
Open access
PDF file
RPRam Paudel
Ram Paudel
STSanaz Tehrani
Sanaz Tehrani
VYVahick A. Yedgarian
Vahick A. Yedgarian
Md Masud Karim RabbiMd Masud Karim Rabbi
Md Masud Karim Rabbi
This study investigates the influence of socio-cultural adaptation, service quality (academic and non-academic) and institutional structure on student satisfaction and institutional competitiveness of private universities in the California context. For this, data was collected from 120 students using self-administered surveys using a quantitative research design. The data were analyzed using statistical tools such as SPSS, SEM and AMOS, Cronbach’s Alpha and EFA were done for reliability and validity. The study findings suggest that enhancing socio-cultural adaptation strategies and service quality, in particular, international students, will greatly help the student satisfaction and institutional competitiveness. These outcomes also depend on the strengthening of institutional structures. However, these mediation and moderation effects were weaker than we had anticipated, suggesting that there are additional factors to be explored in future research. The study provides insights into the effects of socio-cultural adaptation and service quality dimensions on student outcomes and institutional success in a globalized higher education market.