The IUBAR digital repository system captures, stores, indexes, preserves, and distributes digital research material. http://ar.iub.edu.bd:80 2026-05-13T07:12:06Z 2026-05-13T07:12:06Z Rahman, Sayed Rakinur Suraiya, Amanta Rafsan, Md. Turan https://ar.iub.edu.bd/handle/11348/1198 2026-05-12T10:45:27Z 2026-04-01T00:00:00Z

Anomaly Detection in Petroleum Production Wells Using Machine Learning: A Comparative Study on the Petrobras 3W Dataset Rahman, Sayed Rakinur; Suraiya, Amanta; Rafsan, Md. Turan Anomaly detection in offshore oil production systems is a safety-critical task, with un-detected faults contributing directly to equipment failures, environmental incidents, and significant production losses. Machine Learning (ML) has shown significant potential for fault classification in industrial time-series data. However, few comparative studies sys-thematically evaluate models across multiple learning paradigms, including classical, super-vised deep learning, and unsupervised learning on real-world operational data. Existing studies tend to evaluate individual model architectures, offering limited analysis across fault types, class-imbalance conditions, and temporal data characteristics. Multi-class fault detection in oil wells presents multiple challenges, such as severe class imbalance, overlapping faults, and the risk of temporal data leakage as a result of splitting strategies applied to sensor time series. This report presents an extensive comparison study of machine learning approaches for multi-class anomaly detection using the Petrobras 3W dataset across eight fault types, a publicly available benchmark containing real-world sensor data from offshore oil wells. Five distinct models are evaluated: Random Forest (RF) as a classical machine-learning baseline, while Long Short-Term Memory (LSTM) and Transformer classifiers as supervised deep-learning approaches. An LSTM Autoen- coder for unsupervised anomaly detection. This study proposes an Advanced Stacking Ensemble that combines all three supervised paradigms using cross-validated out-of-fold (OOF) prediction generation, meta-feature engineering including prediction entropy, inter- model agreement, confidence statistics and an eXtreme Gradient Boosting (XGBoost) meta-learner. A thorough preprocessing pipeline is implemented, including file-level data splitting to prevent temporal leakage, sliding-window segmentation, statistical feature engineering, and Synthetic Minority Over-sampling Technique (SMOTE) for class balancing. On the held-out test set, the Stacking Ensemble achieves the highest accuracy of 96.25%, while the RF has an accuracy of 95.98%. The RF also attains weighted F1-score of 0.9558. The Transformer (F1: 0.9295) and LSTM (F1: 0.9237) demonstrate competitive performance, with the Transformer offering the advantage of temporal modeling. The LSTM Autoencoder achieves an F1-score of 0.8588 for binary anomaly detection without requiring labeled anomaly data. Model interpretability is addressed through Shap-ley AdditiveexPlanations (SHAP) based feature-level importance analysis and Transformer attention-weight visualization for revealing fault-specific temporal interpretability attended to by the model.

2026-04-01T00:00:00Z Ullah, G. M. Wali Mahtab, Farhan Ahmed, Samiul Parvez Ahmed, Sarwar Uddin https://ar.iub.edu.bd/handle/11348/1197 2026-05-12T08:29:43Z 2018-05-01T00:00:00Z

Valuation of startup firms: a case study on Pathao Ullah, G. M. Wali; Mahtab, Farhan; Ahmed, Samiul Parvez; Ahmed, Sarwar Uddin The article discusses the concept of startups, their sources of financing, and the stages of funding such as seed capital, Series A, and Series B financing. It further explains different startup valuation methods including the Cost-to-Duplicate Approach, Market Approach, Discounted Cash Flow (DCF) Approach, and Development Stage Approach. Using Pathao as a case example, the study demonstrates how startup valuation differs from traditional company valuation due to uncertainty, limited historical data, and future growth potential. Additionally, the paper analyzes how Pathao successfully raised investments from local and foreign investors, including funding from Go-Jek. The study also explores Pathao’s future expansion plans, digital payment initiatives, and challenges such as competition, regulatory pressure, customer expectations, and safety concerns. Overall, the case study provides valuable insights into startup financing, valuation techniques, and the growth potential of technology-based businesses in emerging economies like Bangladesh.

2018-05-01T00:00:00Z Mahtab, Naheem Safiuddin, Md. Mandal, Susmita Alam, Md. Shohidul Razzaque, Rushdi https://ar.iub.edu.bd/handle/11348/1196 2026-05-12T08:15:00Z 2018-05-01T00:00:00Z

Simple costing analysis at FARR Ceramics Limited Mahtab, Naheem; Safiuddin, Md.; Mandal, Susmita; Alam, Md. Shohidul; Razzaque, Rushdi In this case study we first start by determining variable & fixed costs of FARR Ceramics and then figure out breakeven point and output level needed to achieve a target operating income for FARR Ceramics. Then we further analyze how the managers at FARR Ceramics use CVP analysis to make their decisions.

2018-05-01T00:00:00Z Hossain, Md. Mahabbat https://ar.iub.edu.bd/handle/11348/1195 2026-05-12T06:00:16Z 2017-07-01T00:00:00Z

Sustainability report of financial services industry in SAARC countries: special reference to Bangladesh Hossain, Md. Mahabbat Global warming and climate change have become important considerations for all types of entities in doing their regular activities and financial services industry is not exception to that. Only a good financial indicator may not ensure sustainability of an entity. Therefore, various legislations bind financial services industry for thinking about profit, people and planet all Together. At the same time, it is crucial for stakeholders to have sufficient, accurate and timely Information regarding organizational stance in these aspects for proper evaluation. An annual Sustainability report may serve the purpose. The main objective of the study is to reveal the practice of annual sustainability reporting by the financial services industry of Bangladesh. The Study is based on banks and non-bank financial institutions of Bangladesh as other financial organizations do publish sustainability report. Both primary and secondary data have been used to achieve the objectives of the study. Besides, interviews have been conducted to compile perceptions of reporting entities and regulatory bodies. It is observed that only four financial services firms are now preparing and publishing such reports following guidelines given by Global Reporting Initiative. Regulatory driven like intensive monitoring by the regulators may promote financial services sector to publish the report regularly.

2017-07-01T00:00:00Z