Browsing by Author "Rahman, Mahfujur"

Now showing 1 - 8 of 8

BitterGNN: An Explainable Graph-Based Framework for Bitter Peptide Classification
(IEEE, 2025-12-19) Tanvir, Kazi; Gomes, Dipta; Rahman, Mahfujur; Mahmud, Mirza Asif; Noor, Mohammad Ashiqur; Bhuyan, Muhibul Haque
Bitter peptides play an important role in nutrition, sensory science, and pharmaceutical studies. However, identifying and classifying them is still difficult because their structural differences are often subtle, and available data is limited. This paper introduces BitterGNN, a graph-based learning framework created to improve the prediction of bitter peptides by capturing relationships that traditional feature-based models usually miss. The workflow begins with cleaning the data by correcting outliers, followed by using Recursive Feature Elimination with Cross-Validation (RFECV) to find the most meaningful descriptors. These selected features are then used to build a mutual knearest neighbor graph, allowing a GraphSAGE encoder to learn both local and global interactions among peptide samples. The proposed model achieves strong performance, with an accuracy of 0.9844, precision of 0.9848, recall of 0.9844, and a Cohen's kappa of 0.9688. Automated hyperparameter tuning helps reach these results. The AUC of 0.9993 shows that the model can clearly separate the classes. To make the predictions more transparent, LIME and gradient-based attribution highlight which biological traits influence the model's decisions. Overall, BitterGNN demonstrates that combining graph-based representations with feature selection is an effective way to improve peptide classification.
Does Globalization Trigger an Ecological Footprint? A Time Series Analysis of Bangladesh
(Daffodil International University, 2022-11-14) Rahman, Mahfujur; Chowdhury, Shanjida; Zayed, Nurul Mohammad; Hanzhurenko, Iryna; Nitsenko, Vitalii
Climate change has become a pitfall towards economic growth, sustainable development, and ecological balance, which is not different in Bangladesh. This study investigates the relationship between the ecological footprint and the globalisation of Bangladesh in 1980-2021. The auto-regressive distributed lag model (ARDL) bound test confirms the long-run relationship among carbon footprint, ecological footprint, globalisation, and other control variables. Long-run and short elasticity confirm that globalisation, population density, energy consumption, and political and economic globalisation stimulate ecological footprint. On the other hand, economic growth is a culprit of ecological footprint. It reflects alternative signs with an ecological footprint. On carbon footprint, results are similar to ecological footprint except for energy consumption. As ecological footprint increases, people consume more energy in the short run while less energy in the long run. Laws enforced in the last or previous decades regarding environmental issues need more strictness and acceptability to utilise energy through advanced technology and robust inflows from the foreign sector.
Impact of Social Media on Knowledge of the COVID-19 Pandemic on Bangladeshi University Students
(MDPI Publications, 2023-02-16) Chowdhury, Shanjida; Rahman, Mahfujur; Doddanavar, Indrajit Ajit; Zayed, Nurul Mohammad; Nitsenko, Vitalii; Melnykovych, Olena; Holik, Oksana
This study aimed to examine the role and impact of social media on the knowledge of the COVID-19 pandemic in Bangladesh through disseminating actual changes in health safety, trust and belief of social media’s coverage statistics, isolation, and psychological numbness among students. This study used a cross-sectional design in which a quantitative approach was adopted. Data from an online survey were collected in a short period of time during the early stages of COVID-19 to determine the relationship between social media activity and knowledge of the COVID-19 pandemic with accuracy. A total of 189 respondents were interviewed using structured questionnaires during the onset of the COVID-19 outbreak in Bangladeshi university students. Exploratory factor analysis (EFA) and path analysis were performed. Out of 189 respondents, about 80% were aged between 16 and 25 years, of which nearly 60.33% were students. This study explored four factors—knowledge and health safety, trust in social media news, social distancing or quarantine, and psychological effect—using factor analysis. These four factors are also found to be positively associated in path analysis. Validation of the model was assessed, revealing that the path diagram with four latent exogenous variables fit well. Each factor coefficient was treated as a factor loading (β = 0.564 to 0.973). The results suggested that the measurement models using four elements were appropriate. The coefficient of determination was 0.98, indicating that the model provided an adequate explanation. Social media is transforming the dynamics of health issues, providing information and warnings about the adverse effects of COVID-19, having a positive impact on lockdown or quarantine, and promoting psychological wellness. This comprehensive study suggested that social media plays a positive role in enhancing knowledge about COVID-19 and other pandemic circumstances.
Implementing Lean Production Techniques in the Garments Industry: Enhancing Efficiency and Reducing Waste
(Daffodil International University, 2025-07-22) Saha, Prottoy; Rahman, Mahfujur
This thesis explores the application of Lean Production techniques within the garments industry, with a focus on enhancing operational efficiency and minimizing waste. In an increasingly competitive global market, garment manufacturers are under pressure to optimize processes, reduce costs, and improve product quality without compromising lead times. Lean Production, originally derived from the Toyota Production System (TPS), offers a systematic approach to achieving these objectives by eliminating non-value-adding activities across the production line. The research identifies key Lean tools—such as 5S (Sort, Set in Order, Shine, Standardize,Sustain), Kaizen (Continuous Improvement), and Value Stream Mapping (VSM), —as critical to transforming conventional garment manufacturing operations. These tools help in streamlining workflow, reducing inventory, improving workplace organization, enhancing quality control, and increasing worker productivity. A combination of qualitative and quantitative methods, including factory visits, interviews with industry professionals, and data analysis, was used to evaluate the current production practices and assess the effectiveness of Lean implementation. Case studies from local and international garment factories illustrate how Lean tools have successfully led to reduced lead times, lower defect rates, better space utilization, and improved employee engagement. Findings suggest that while the garments industry in Bangladesh has begun integrating Lean concepts, challenges such as resistance to change, lack of training, and insufficient management commitment still hinder full-scale adoption. The thesis concludes with a proposed framework for Lean implementation tailored to the specific conditions of the Bangladeshi garments sector, alongside practical recommendations to overcome barriers and sustain continuous improvement. By adopting Lean Production techniques, garment manufacturers can achieve significant gains in productivity, quality, and sustainability—key factors in maintaining competitiveness in the global apparel market.
PAPR Reduction of OFDM Signal by Scrutiny of BER Assessment and SPS-SLM Method via AWGN Channel
(2021 6th International Conference on Inventive Computation Technologies (ICICT), IEEE, 2021-01-26) Ohidujjaman; Zannat, Raihana; Khatun, Tania; Rahman, Mahfujur; Raza, Salim; Huda, Mohammad Nurul
Orthogonal Frequency Division Multiplexing (OFDM) has been presently underneath powerful exploration for broadband radio transmission owing to its strength in opposition to multi-path diminishing. Nevertheless, implementation of the OFDM method necessitates numerous complications. The foremost downside is high Peak-to-Average Power Ratio (PAPR) that hints to rise Bit Error Rate (BER) on account of nonlinearity of the peak ability amplifier. The Selected Mapping (SLM) technique is prominent method to lessen PAPR of OFDM signal. With SLM technique, lateral evidence bits are required to recuperate actual data which lead to increase the proportion of data damage. In our article, an exact set of sequential phase sequences (SPS) has been developed to perform SLM technique along OFDM transceiver without requiring of side information. SPS based SLM (SPS-SLM) technique has been able to reduce almost same PAPR compared to the conventional SLM technique. Moreover, the BER performance has been studied considering different number of sub-carriers as well as modulation order.
Performance Analysis of Diabetic Retinopathy Prediction Using Machine Learning Models
(2021 6th International Conference on Inventive Computation Technologies (ICICT), IEEE, 2021-02-26) Emon, Minhaz Uddin; Zannat, Raihana; Khatun, Tania; Rahman, Mahfujur; Keya, Maria Sultana
Diabetic Retinopathy (DR) is a symptom of diabetes that affects the eyes. The blood vessels of the light tissue behind the eyes are damaged (retina). Machine Learning (ML) techniques play a vital role in computer aid diagnosis and discover successful systems for detecting life-threatening diseases. This research aimed to predict diabetic retinopathy and also implement feature extraction to figure out some features. In this research, the data is collected from the UCI machine learning repository. Several Machine Learning (ML) techniques are used for analysis this dataset and find out the best performance and sensitivity, selectivity, true positive (tp) rate, false negative (fn) rate and receiver operating characteristic (roc) curve. In this study, some machine learning algorithms are used such as Naive Bayes, Sequential Minimal Optimization (SMO), logistic regression, Stochastic Gradient Descent (SGD), bagging classifier, J48 classifier, decision tree classifier, and random forest classifier. The overall performance of logistic regression shows the best result.
Sylhet Divisional Museum
(BRAC University, 2019-08) Rahman, Mahfujur; Mallick, Fuad H.
In broder perspective, we know Sylhet for its natural beauty and geographical features, for instance, tilas, tea estates, haor, natural fountains, etc. The history, culture and living patterns are highly influenced by the natural aspect of this Division. A divisional museum collects and preserve significant historical and cultural element and information and exhibit it to the public so that the public could get aware of then significant division. It is also very important to keep the culture and history live through public collaboration. In this project the museum work as a platform for knowing Sylhet as well as to preserve the culture with the public collaboration. Form and landscape derived from the natural significant elements and the waterbody represent the life in haor and swamp. A plaza connects the adjacent neighborhood and the city, it also includes an existing playground which could be used as a community activity such as mela, folk music festivals. Inside the museum, there are 6 different galleries. The division of galleries is created according to the history, influential people, liberation war, folk music, and cultural aspect of the division.
The Effect of Foreign Direct Investment on Public Health
(Scopus, 2021) Siddique, Fahimul Kader; Hasan, K.B.M. Rajibul; Chowdhury, Shanjida; Rahman, Mahfujur; Raisa, Tahsin Sharmila; Zayed, Nurul Mohammad
Health is an outset of psychological, social, financial, and physical state. Several macroeconomic factors are entangled with health and mortality. Infant mortality and life expectancy are two key guard on demographic research context on last few decades. On the other hand, foreign inflows play an unprecedent role for raising economic circulation and providing more opportunities to build a better society. The study aims to investigate the relationship between foreign direct investment (FDI), economic growth, and Bangladesh's health. This study employs time-series data from 1980 to 2018. Results show, with Auto-regressive Distribute Lag (ARDL) model, that there is significant cointegration among variables. Foreign investment and economic output relate significantly and positively to health. On the contrary, education is quasi-linked with a different sign-on different model. For model validation, pitfalls of time-series multicollinearity, heteroscedasiticy, and autocorrelation are not present. Also, CUSUM and CUSUMSQ tests are validating the model as stable and fit for future prediction. Medical assessment and education need more attention from the government as well as the private sector. FDI can play a catalyst role for improving the health sector, raising opportunity in educating and creating a better lifestyle. In order to optimize foreign investment, the government should implement necessary reforms and policies.