Sakibul Hasan

Sakibul Hasan

Auto-generated profile, based on publicly available information

Sakibul Hasan

Information Technology Management, St Francis College

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.

6 January 2025 in Journal of Computer Science and Technology Studies
Verified
Journal Article
Closed access
AAAdib Ahmed
Adib Ahmed
TJTanaya Jakir
Tanaya Jakir
NMNazmul Hossain Mir
Nazmul Hossain Mir
AZAbdul Fahim Zeeshan
Abdul Fahim Zeeshan
AHArat Hossain
Arat Hossain
SHSakibul Hasan
Sakibul Hasan
In the USA, hospitals are confronted with significant challenges regarding energy consumption, which not only impacts operational costs but also contributes to environmental concerns. The primary objective of this research was to develop and evaluate machine learning models that are capable of accurately predicting energy consumption in U.S. hospitals. This study will be focused on United States hospital energy consumption data, recognizing the unique difficulties and opportunities present in the U.S. healthcare setting. The data used for this hospital energy consumption analysis has been carefully gathered from multiple credible sources, including the U.S. Department of Energy's Energy Star program, whole-building hospital energy audits, and information from local utility providers. This variety in sourcing guarantees a strong and complete dataset that accurately represents real-world energy dynamics in healthcare buildings. In the model selection phase, three powerful algorithms were employed: the Random Forest Classifier, XG-Boost, and Artificial Neural Network (ANN). XG-Boost outperformed other models after tuning, achieving an 81.8% accuracy on the test set. Random Forest showed a decent improvement post-tuning but still lagged behind XG-Boost. Hospital managers can utilize machine learning (ML)--based predictions to achieve substantial cost savings in operational expenditures related to energy usage. With predictive analytics, hospitals can anticipate energy needs based on several parameters, such as patient occupancy rates, time of day, and seasonality. Integration of AI-driven energy prediction in hospital sustainability plans has significant policy implications for the U.S. healthcare sector. The integration of machine learning models and the Internet of Things (IoT)-)-)-enabled energy management systems is a breakthrough step in embracing smart hospital initiatives.

14 January 2024 in Journal of Environmental and Agricultural Studies
Verified
Journal Article
Open access
PDF file
AHArat Hossain
Arat Hossain
MRMehedi Hasan Ridoy
Mehedi Hasan Ridoy
BCBivash Ranjan Chowdhury
Bivash Ranjan Chowdhury
MHMohammad Nazmul Hossain
Mohammad Nazmul Hossain
NRNazmul Shakir Rabbi
Nazmul Shakir Rabbi
SHSakibul Hasan
Sakibul Hasan
With the pace of the global transition toward smart grid technologies, more precise and responsive energy forecasting systems are essential to securing sustainable and effective power distribution. Smart grids, defined by their bidirectional communications and built-in sensing technologies, depend on time-series data analytics to control energy flow, forecast consumption patterns, and counter fluctuations. The chief objective of this research was to leverage the potential of machine learning algorithms to maximize the precision and flexibility of energy demand prediction within smart grid networks. The data used for this study consisted of high-resolution, time-stamped energy consumption data captured at 15-minute intervals for two years, both residential and commercial usage patterns. Every record contained the precise timestamp of consumption, which made it possible to undertake fine-grained temporal analysis that captures strong hourly cycles, daily patterns, and seasonal variations that are representative of user behavior and climatic factors. The authors selected three different models for effective energy demand level classification in this study. Our models received a time-based train-test split for their dataset to guarantee their robustness. A complete set of performance metrics for assessing our classification models included Accuracy alongside Precision, Recall, and F1-Score in addition to implementing a Confusion Matrix evaluation. Both KNN and SVM demonstrated a strong balance in precision against recall because their Accuracy and F1 Score bars overlap almost completely in the evaluation graph. The results indicate that KNN and SVM perform superior to Logistic Regression with very equivalent outcomes in this classification activity. One of the most direct and significant advantages of using machine learning-based energy demand forecasting for smart grids is improved operating efficiency through more intelligent scheduling of energy delivery. Furthermore, machine learning-driven operational efficiency makes an important contribution to cost savings throughout the energy value chain. By being able to forecast short-interval demand fluctuations, utilities are better positioned to more efficiently execute their procurement strategy, such as strategically selling and buying energy on wholesale markets. Load management is another essential function where machine learning-based forecasting greatly improves smart grid operations. Preplanning for grid expansion and maintenance is another strategic advantage that arises from the predictive potential of machine-learning-powered smart grids. In the future, various opportunities exist for enhancing the functionality of machine learning-based energy forecasting for the smart grid. First, incorporating more contextual sources of data, including online meteorological information, IoT sensor streams (e.g., appliance usage patterns, occupancy levels), and local grid status monitors, holds the potential to add to the feature inventory available to models.

28 June 2024 in Journal of Business and Management Studies
Verified
Journal Article
Open access
PDF file
SHSakibul Hasan
Sakibul Hasan
ASAbubokor Siam
Abubokor Siam
AAAbdul Ahad
Abdul Ahad
MHMohammad Nazmul Hossain
Mohammad Nazmul Hossain
MRMehedi Hasan Ridoy
Mehedi Hasan Ridoy
TJTanaya Jakir
Tanaya Jakir
The competitive e-commerce business environment in the USA now identifies customer retention as the critical factor in deciding long-term business achievement. Research shows that an organization reaps more benefits by retaining existing customers rather than spending money on customer acquisition. The main purpose of this research project was to develop highly precise machine learning algorithms that detect customers prone to leaving the company using multiple behavioral patterns combined with transaction histories and demographics. The dataset assembled for this analysis included a broad range of characteristics that reflect both static and dynamic facets of customer behavior in the online store. User attributes like age, gender, location, and account signup date give essential context regarding the profile of the customers. Adding depth to this are rich purchase behavior measures, such as frequency of purchase, basket size, overall spending, accepted methods of payment, and usage patterns for discounts. Order history is carefully documented, including the quantity of completed, canceled, and returned orders, and the time since the last orders. Top-level product category preferences are also monitored to discern preferences for types of merchandise (e.g., electronics, clothing, home, and garden), providing greater insight into changing interests. We used three very different models to best tackle the issues of churn prediction for customers. To ascertain the strength of our models, we adopted a systematic strategy for training and testing the models. XG-Boost generally has the best performance overall with the highest scores for all four measures, always above 0.9. Random Forest is second with scores slightly less than for XG-Boost but generally high (above 0.85). Implementing a machine learning-based churn alert system is a major advancement toward enabling customer retention tactics within e-commerce platforms. A churn alert system actively tracks user behavior and activity levels, using predictive algorithms to allocate the risk of churn within near real-time. Predictive analytics for churn is a key factor in safeguarding and forecasting revenue streams for Internet businesses, where even minor fluctuations in customer retention can have disproportionate effects on profitability. To provide richer, more practical insights from churn models, research and development must focus largely in the coming period on the incorporation of richer, more detailed data sources.

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.