Browsing by Author "Rahman, Mahmudur"

Now showing 1 - 20 of 22

A Simple Recommendation System Using Bayesian Theory and Expectation Maximization
(East West University, 9/16/2015) Rahman, Mahmudur; Foysal, Noman Ibn
From ancient time, service of any shop or business or the quality of any product got reputation by the users. When a user praised highly or badly about any product or service it created a butterfly effect of individual advertisement that reached far beyond the limit that the service/product provider could reach themselves . In classical period Books and newspapers have done this reviewing job and now this is again done by the individual user using various sites on the internet .By using this reputation new or undecided user of a particular product/service were able to choose properly We have tried to create an online service that helps to review a restaurant by an individual user which will not only able to create an online reputation for the users but also help the individual /a group of users to find a better choice of places for them.
An Approach to Arduino Uno-Based Smart Car Parking System
(Elsevier, 2023-08-15) Zumma, Md. Thoufiq; Khan, Raihan; Suhaeel, Abdullah Aas; Tahmiduzzaman, K. B. M.; Rahman, Mahmudur; Ahmed, Md. Firoj
Since both the population and the number of cars in Bangladesh are growing quickly, a modern parking infrastructure is crucial. Since there aren't enough places for people to park their cars efficiently, more and more drivers are having to leave their cars parked on the road, contributing to congestion and a halt in the flow of traffic. Only approved users are able to park their vehicles in our automated parking, making it a secure and convenient option for car storage. When there is less traffic on the road, there is less pollution from the cars and trucks on that route. There is no possibility of paying a bribe to park a car since the whole system is computerized. Better infrastructure can be built since all the money will go to the government.
Artificial Intelligence to Ensure Proper Justice & Speedy Disposal of Judicial proceeding: An Analytical Overview in Respect of Bangladesh
(East West University, 2023-01-18) Rahman, Mahmudur
Every person is dependent on technology in one way or another in their daily life. People use science and technology to make their lives happy and prosperous. Life has been fast. Humans have conquered the seas from space using the technology of science. One such exciting invention of science is artificial intelligence. This discovery of science continues to help people in every aspect of their lives. This technology is used in every field, from household work to space research. Similarly, Artificial Intelligence is playing a role in the development of law. Developed countries like America, Canada, and England are benefiting from using artificial intelligence in the field of law. By harnessing this artificial intelligence, we can bring about unimaginable changes in our laws. We can speed up our justice system. This research paper will focus on how we can leverage artificial intelligence in our justice system.
Automated Electricity Billing System for Bangladesh
(Department of Computer Science and Engineering, Military Institute of Science and Technology, 2013-12) Hasan Ibne Obayed, Chowdhury; Mahmood, Tropa; Rahman, Mahmudur
TherearemainlythreeutilityservicesavailableinBangladesh. TheyareElectricity,Natural Gas and Water. The procedures of these services are mainly manual. We tried to give an automated solution for these utility services, starting from applying for the service to the billing system along with all other facilities required. We mainly focused on electricity utility service for the proposed solution. But this solution can be equally applicable to any other utility services with certain modiﬁcation. Since the bill payment can be done through online banking and application for new connection can be done online, we emphasized on meter reading and its processing to generate bill. We proposed a GSM based meter reading service and tried to make a prototype with present electric meter available in Bangladesh. We believe this solution can upgrade the utility service of Bangladesh. It will be helpful to monitor the usage of the services, to control the services remotely, to stop corruption in this sector and also to make efﬁcient consumption of valuable energy of Bangladesh.
COVID-19-Related Stigma Among Older Adults Residing in the Rohingya Refugee Camps in Bangladesh
(American Psychological Association, 2023-07-16) Anwar, Afsana; Yadav, Uday Narayan; Huda, Md. Nazmul; Ghimire, Saruna; Rahman, Mahmudur; Ali, A. R. M. Mehrab; Mahumud, Rashidul Alam; Shuvo, Suvasish Das; Nowar, Abira; Mondal, Probal Kumar; Rizwan, Abu Ansar Md.; Mistry, Sabuj Kanti
The onset of the COVID-19 pandemic and its overwhelming physical and mental health burden can stigmatize those affected. This study aimed to assess the prevalence of COVID-19-related stigma and its associated factors among the older people residing in the Rohingya refugee camps of Bangladesh. This cross-sectional study was conducted among 864 older adults aged 60 years and above residing in selected Rohingya refugee camps in Bangladesh. The data were collected using face-to-face interviews conducted between November and December 2021. COVID-19-related stigma was measured using the eight-item Stigma Scale adapted to the Rakhine language. A linear regression model was used to identify the factors associated with COVID-19-related stigma among the participants. Participants, on average, had stigmas on three items and 52.8% had a high COVID-19-related stigma score. The average stigma score was higher among the participants who had formal schooling (β = 0.58, 95% CI [0.21, 0.94]), was dependent on family for a living (β = 0.41, 95% CI [0.12, 0.74]), resided away from health center (β = 0.25, 95% CI [0.01, 0.50]), whose family income decreased during the pandemic (β = 0.27, 95% CI [0.03, 0.51]), had close friends or family members previously diagnosed with COVID-19 (β = 1.64, 95% CI [1.08, 2.20]), and had less communication during the pandemic (β = 1.80, 95% CI [1.24, 2.34]). The study findings suggest raising awareness among the older population on COVID-19 and the mitigating strategies to deal with physical and mental well-being through appropriate health literacy interventions and mass media campaigns in Rohingya camps. (PsycInfo Database Record (c) 2023 APA, all rights reserved)
Design & Developing of a Microcontroller Based Intelligent Traffic Control System
(East West University, 4/12/2016) Islam, Salim Bin; Rahman, Mahmudur
The number of vehicles is gradually increasing day by day all over the world. Vehicles are also increasing in the metropolitan cities of Bangladesh. As a result huge traffic congestions and traffic jam is increasing day by day. For traffic congestions a huge amount of time is being wasted by the citizen of metropolitan area. In this project an intelligent traffic control system is developed by us to minimize the congestions of traffic system. Here the traffic signal will be automatically control by the system. The road will be open for moving forward or close for moving forward is controlled by the system in real time and as necessary. When a certain number of vehicle is stuck in the traffic signal then the other part of the path will be show red signal and the congested path’s signal will be Green. After a few time when the first path will reach a certain number of vehicle then the second path’s signal will turn into red and the first path’s signal will turn into green. Our intelligent traffic control system can detect temperature of the environment also. And the information about signal and temperature will send to the certain vehicle holder by Short Message Service (SMS).
Economic burden of influenza-associated hospitalizations and outpatient visits in Bangladesh during 2010
(© 2014 Blackwell Publishing Ltd., 2014) Bhuiyan, Mejbah U.; Luby, Stephen P.; Alamgir, Nadia I.; Homaira, Nusrat; Mamun, Abdullah A.; Khan, Jahangir A. M.; Abedin, Jaynal; Sturm-Ramirez, Katharine; Gurley, Emily S.; Zaman, Rashid U.; Alamgir, ASM; Rahman, Mahmudur; Widdowson, Marc-Alain; Azziz-Baumgartner, Eduardo
Objective: Understanding the costs of influenza-associated illness in Bangladesh may help health authorities assess the cost-effectiveness of influenza prevention programs. We estimated the annual economic burden of influenza-associated hospitalizations and outpatient visits in Bangladesh. Design: From May through October 2010, investigators identified both outpatients and inpatients at four tertiary hospitals with laboratory-confirmed influenza infection through rRT-PCR. Research assistants visited case-patients' homes within 30 days of hospital visit/discharge and administered a structured questionnaire to capture direct medical costs (physician consultation, hospital bed, medicines and diagnostic tests), direct non-medical costs (food, lodging and travel) and indirect costs (case-patients' and caregivers' lost income). We used WHO-Choice estimates for routine healthcare service costs. We added direct, indirect and healthcare service costs to calculate cost-per-episode. We used median cost-per-episode, published influenza-associated outpatient and hospitalization rates and Bangladesh census data to estimate the annual economic burden of influenza-associated illnesses in 2010. Results: We interviewed 132 outpatients and 41 hospitalized patients. The median cost of an influenza-associated outpatient visit was US$4.80 (IQR = 2.93-8.11) and an influenza-associated hospitalization was US$82.20 (IQR = 59.96-121.56). We estimated that influenza-associated outpatient visits resulted in US$108 million (95% CI: 76-147) in direct costs and US$59 million (95% CI: 37-91) in indirect costs; influenza-associated hospitalizations resulted in US$1.4 million (95% CI: 0.4-2.6) in direct costs and US$0.4 million (95% CI: 0.1-0.8) in indirect costs in 2010. Conclusions: In Bangladesh, influenza-associated illnesses caused an estimated US$169 million in economic loss in 2010, largely driven by frequent but low-cost outpatient visits.
Economic burden of influenza-associated hospitalizations and outpatient visits in Bangladesh during 2010
(© 2014 Blackwell Publishing Ltd., 2014) Bhuiyan, Mejbah U.; Luby, Stephen P.; Alamgir, Nadia I.; Homaira, Nusrat; Mamun, Abdullah A.; Khan, Jahangir A. M.; Abedin, Jaynal; Sturm-Ramirez, Katharine; Gurley, Emily S.; Zaman, Rashid U.; Alamgir, ASM; Rahman, Mahmudur; Widdowson, Marc-Alain; Azziz-Baumgartner, Eduardo
Objective: Understanding the costs of influenza-associated illness in Bangladesh may help health authorities assess the cost-effectiveness of influenza prevention programs. We estimated the annual economic burden of influenza-associated hospitalizations and outpatient visits in Bangladesh. Design: From May through October 2010, investigators identified both outpatients and inpatients at four tertiary hospitals with laboratory-confirmed influenza infection through rRT-PCR. Research assistants visited case-patients' homes within 30 days of hospital visit/discharge and administered a structured questionnaire to capture direct medical costs (physician consultation, hospital bed, medicines and diagnostic tests), direct non-medical costs (food, lodging and travel) and indirect costs (case-patients' and caregivers' lost income). We used WHO-Choice estimates for routine healthcare service costs. We added direct, indirect and healthcare service costs to calculate cost-per-episode. We used median cost-per-episode, published influenza-associated outpatient and hospitalization rates and Bangladesh census data to estimate the annual economic burden of influenza-associated illnesses in 2010. Results: We interviewed 132 outpatients and 41 hospitalized patients. The median cost of an influenza-associated outpatient visit was US$4.80 (IQR = 2.93-8.11) and an influenza-associated hospitalization was US$82.20 (IQR = 59.96-121.56). We estimated that influenza-associated outpatient visits resulted in US$108 million (95% CI: 76-147) in direct costs and US$59 million (95% CI: 37-91) in indirect costs; influenza-associated hospitalizations resulted in US$1.4 million (95% CI: 0.4-2.6) in direct costs and US$0.4 million (95% CI: 0.1-0.8) in indirect costs in 2010. Conclusions: In Bangladesh, influenza-associated illnesses caused an estimated US$169 million in economic loss in 2010, largely driven by frequent but low-cost outpatient visits.
Exploratory Analysis of Developer Sentiment On Open Source Projects
(Department of Computer Science and Engineering(CSE), Islamic University of Technology(IUT), Board Bazar, Gazipur-1704, Bangladesh, 2024-09-17) Siam, Md. Kawsar Ahamed; Rahman, Mahmudur; Hassan, Moudud
Issue-tracking platforms such as Jira and Bugzilla have become essential in large- scale software development. Prominent organizations in the Open Source Software (OSS) landscape, such as Apache and Mozilla, make heavy use of these platforms and document their software development process through online repositories that utilize version control systems (VCS) like Git. Artifacts gathered from these sources contain natural language data that can be used to answer important questions relating to the nature of the software produced and the sentiment of the developers. The commit fre- quency and working time of the developers can be correlated to the sentiment shown through the commit messages. Moreover, the sentiment of issue comments might differ significantly based on the type (i.e., bug or non-bug) or severity. In this regard, we utilized a modern machine learning-based approach through fine-tuning seBERT, a BERT model pre-trained on software development data, to classify sentiment and provide answers to these questions. We used an existing data set, 20-MAD, to test these hypotheses and provide the results. We found that high committer frequency is associated with a higher proportion of negative sentiments compared to low and medium frequencies, while the part of the day developers work in has minimal effect on measured sentiment. We also observed that the severity of an issue significantly influences the sentiment expressed in issue comments and issues classified as bugs have a higher negative sentiment frequency compared to other issue types combined.
Eye Cataract Disease Classification: A Comparative Model Performance Analysis Under Data Constraints
(2025-06-10) Rahman, Mahmudur; Sakib, K. M. Sadman; Tahmiduzzaman, KBM; Anikur Rahman, Md; Munia, Jerin Akther; Akash, Abdul Hady
Blindness frequently arises from cataracts, which often require to be detected early for optimal treatment. Timely diagnosis is crucial since severe cases might require surgery. In such instances, computer-aided diagnosis can help the doctor detect the patient immediately by assisting in distinguishing the cataract condition from a normal eye. Finding enough cataract imaging data to train a custom Convolutional Neural Network(CNN) model can be challenging. Even with proper augmentation, a custom CNN model will still perform badly on testing data because it is unable to comprehend the extensive features offered by the enhanced data. However, with small as well as augmented data, the pre-trained model can still give better results than the custom CNN. Pre-trained models are trained to utilize augmented data to extract a wide range of features while boosting accuracy. Recall and accuracy are crucial factors in any disease screening process. In this study, we aimed to augment the data to mitigate the imbalance and scarcity of data, giving our pre-trained model more features to train efficiently. Later, to improve the model’s performance, we ensembled the models and assessed the ensemble models with optimal weights to find the best result on the test data, yielding an accuracy of 98.62% and Recall, Precision, F1 Score of 99% respectively.
Livestock Meat Demand in Chattogram City Corporation Area of Bangladesh.
(Faculty of Veterinary Medicine, Chattogram Veterinary and Animal Sciences University, Khulshi, Chattogram-4225, Bangladesh, 2024-10) Rahman, Mahmudur
This study explores the key factors influencing meat consumption in Chattogram City Corporation (CCC), Bangladesh, a region experiencing rapid urbanization and a growing demand for protein-rich foods. Using structured interviews, data were gathered from 100 participants across five thanas to assess the impact of economic status, nutritional awareness, and price fluctuations on meat consumption habits. The findings show that higher-income households (14%) consumed a greater variety of meats, such as beef, chicken, and chevon, several times a week, whereas middle-income households (55%) consumed meat 1-4 times weekly, mainly choosing affordable options like chicken. In contrast, low-income households (31%) reported less frequent meat consumption, relying primarily on cheaper meats like chicken due to financial constraints. Price increases over the past year were reported by 88% of respondents, with 60% reducing their meat intake and 10% switching to more affordable meat options. Additionally, only 23% of participants were aware of the health risks associated with meat consumption, with lower-income groups having less nutritional knowledge overall. The study highlights the need for targeted public education programs on nutrition and health, particularly for economically disadvantaged populations, and recommends policy interventions to improve access to affordable and diverse sources of protein. Limitations of the study include its geographical scope and a gender imbalance, with 81% of respondents being male. Future research should aim to address these gaps and promote collaboration across the food supply chain to enhance sustainable meat consumption and food security in CCC.
Operation of Grid-Substation of Dhaka Power Distribution Company Limited (DPDC)
(Daffodil International University, 2021-09) Rahman, Mahmudur
It was an extraordinary chance of entry level position in DPDC. DPDC represents dhaka power dispersion organization. It is one of the biggest force dissemination organization in Bangladesh. During my entry level position I worked in different division, for example, – substation activity and support , power and dissemination, load the executives, control room actuate, link division, sunlight based energy and NOCS.
Reducing the health effect of natural hazards in Bangladesh
(© 2013 Published by Elsevier Inc., 2013-11) Rahman, Mohammad Aminur; Mallick, Fuad Hassan; Cash, Richard A; Halder, Shantana R; Husain, Mushtuq; Islam, Md Sirajul; May, Maria A; Rahman, Mahmudur
Bangladesh, with a population of 151 million people, is a country that is particularly prone to natural disasters: 26% of the population are affected by cyclones and 70% live in flood-prone regions. Mortality and morbidity from these events have fallen substantially in the past 50 years, partly because of improvements in disaster management. Thousands of cyclone shelters have been built and government and civil society have mobilised strategies to provide early warning and respond quickly. Increasingly, flood and cyclone interventions have leveraged community resilience, and general activities for poverty reduction have integrated disaster management. Furthermore, overall population health has improved greatly on the basis of successful public health activities, which has helped to mitigate the effect of natural disasters. Challenges to the maintenance and reduction of the effect of cyclones and floods include rapid urbanisation and the growing effect of global warming. Although the effects of earthquakes are unknown, some efforts to prepare for this type of event are underway. This is the fifth in a Series of six papers about innovation for universal health coverage in Bangladesh
Reducing the health effect of natural hazards in Bangladesh
(© 2013 Published by Elsevier Inc., 2013-11) Mallick, Fuad Hassan; Cash, Richard A; Halder, Shantana R; Husain, Mushtuq; Islam, Md Sirajul; May, Maria A; Rahman, Mahmudur; Rahman, M Aminur
Bangladesh, with a population of 151 million people, is a country that is particularly prone to natural disasters: 26% of the population are affected by cyclones and 70% live in flood-prone regions. Mortality and morbidity from these events have fallen substantially in the past 50 years, partly because of improvements in disaster management. Thousands of cyclone shelters have been built and government and civil society have mobilised strategies to provide early warning and respond quickly. Increasingly, flood and cyclone interventions have leveraged community resilience, and general activities for poverty reduction have integrated disaster management. Furthermore, overall population health has improved greatly on the basis of successful public health activities, which has helped to mitigate the effect of natural disasters. Challenges to the maintenance and reduction of the effect of cyclones and floods include rapid urbanisation and the growing effect of global warming. Although the effects of earthquakes are unknown, some efforts to prepare for this type of event are underway. This is the fifth in a Series of six papers about innovation for universal health coverage in Bangladesh
Reducing the health effect of natural hazards in Bangladesh
(© 2013 Published by Elsevier Inc., 2013-11) Rahman, Mohammad Aminur; Mallick, Fuad Hassan; Cash, Richard A; Halder, Shantana R; Husain, Mushtuq; Islam, Md Sirajul; May, Maria A; Rahman, Mahmudur
Bangladesh, with a population of 151 million people, is a country that is particularly prone to natural disasters: 26% of the population are affected by cyclones and 70% live in flood-prone regions. Mortality and morbidity from these events have fallen substantially in the past 50 years, partly because of improvements in disaster management. Thousands of cyclone shelters have been built and government and civil society have mobilised strategies to provide early warning and respond quickly. Increasingly, flood and cyclone interventions have leveraged community resilience, and general activities for poverty reduction have integrated disaster management. Furthermore, overall population health has improved greatly on the basis of successful public health activities, which has helped to mitigate the effect of natural disasters. Challenges to the maintenance and reduction of the effect of cyclones and floods include rapid urbanisation and the growing effect of global warming. Although the effects of earthquakes are unknown, some efforts to prepare for this type of event are underway. This is the fifth in a Series of six papers about innovation for universal health coverage in Bangladesh
Reducing the health effect of natural hazards in Bangladesh
(© 2013 Published by Elsevier Inc., 2013-11) Mallick, Fuad Hassan; Cash, Richard A; Halder, Shantana R; Husain, Mushtuq; Islam, Md Sirajul; May, Maria A; Rahman, Mahmudur; Rahman, M Aminur
Bangladesh, with a population of 151 million people, is a country that is particularly prone to natural disasters: 26% of the population are affected by cyclones and 70% live in flood-prone regions. Mortality and morbidity from these events have fallen substantially in the past 50 years, partly because of improvements in disaster management. Thousands of cyclone shelters have been built and government and civil society have mobilised strategies to provide early warning and respond quickly. Increasingly, flood and cyclone interventions have leveraged community resilience, and general activities for poverty reduction have integrated disaster management. Furthermore, overall population health has improved greatly on the basis of successful public health activities, which has helped to mitigate the effect of natural disasters. Challenges to the maintenance and reduction of the effect of cyclones and floods include rapid urbanisation and the growing effect of global warming. Although the effects of earthquakes are unknown, some efforts to prepare for this type of event are underway. This is the fifth in a Series of six papers about innovation for universal health coverage in Bangladesh
RNN-Based Weather Forecast Prediction: A Modern Approach
(Daffodil International University, 2025-01-13) Rahman, Mahmudur
Accurate weather forecasting is vital for resource planning, disaster management, and informed decision-making. This study leverages deep learning techniques, including Long Short-Term Memory (LSTM), Gated Recurrent Units (GRU), and 1D Convolutional Neural Networks (1D CNN), to predict weather trends from sequential data. Extensive preprocessing was conducted to ensure data integrity and compatibility with the models. Among the evaluated models, the 1D CNN and LSTM demonstrated superior performance, achieving regression accuracies of 83.09% and 83.44%, respectively. The GRU model also performed reliably, with a regression accuracy of 81.72%. A Hybrid CNN-LSTM model was tested but exhibited significantly lower performance, highlighting the robustness of standalone LSTM and CNN models for weather prediction tasks. Future work will focus on incorporating larger datasets, enhancing interpretability through explainable AI, and exploring more advanced architectures. This research underscores the effectiveness of deep learning models for time-series forecasting and provides valuable insights into their comparative performance.
Sentiment analysis of AR and VR in multiple sectors using user experience from social media
(Daffodil International University, 2024-07-24) Rahman, Mahmudur
Augmented Reality (AR) and Virtual Reality (VR) technologies are revolutionizing how we engage with digital content, providing new experiences in gaming, entertainment, and beyond. Understanding users' opinions and attitudes around these developing technologies is critical for increasing adoption and user happiness. This study uses sentiment analysis approaches to analyze user experiences with AR and VR applications in the gaming and entertainment industries, utilizing data from social media platforms. The researchers used a combination of machine learning models, such as Naive Bayes, Support vector machine (SVM), and Random Forest, to determine whether user reviews and comments expressed positive or negative sentiment. The data show that people have a higher positive opinion of VR in gaming, with 46% expressing positive sentiments compared to 42% for AR gaming. In contrast, the entertainment sector reported a larger percentage of positive attitudes for AR (53.7%) than for VR (34.3%), implying that AR is better suited for immersive entertainment experiences. The study also identified critical aspects that influence user experiences, such as visual quality, comfort, and navigational challenges for VR and design, battery life, and confusing controls for AR. These insights can help developers and stakeholders improve the design and implementation of AR and VR technologies in order to better fulfill user needs and foster widespread adoption. The study helps to a better understanding of user impressions of AR and VR by conducting a complete sentiment analysis across many domains. The findings and conclusions addressed in this study can help to shape future research and development efforts in the AR and VR fields, ultimately boosting the quality and accessibility of these disruptive technologies.
Short Term Weather Forecasting Comparison Based on Machine Learning Algorithms
(IEEE, 2023-08-24) Era, Chowdhury Abida Anjum; Rahman, Mahmudur; Alvi, Syada Tasmia
Forecasting is the term used to describe the attempt to predict outcomes in unknown or uncertain situations. The most vital factor in many applications of weather forecasting is air temperature. The air temperature alone can’t be the effecting point of forecasting weather. Moreover, with the advancement of computer technologies, forecasting models have been transformed widely. This paper approached a system that forecasts air temperature using machine learning algorithms. Several regression methods were employed to attempt to predict temperatures. This research evaluated four algorithms (Decision Tree, AdaBoost, Random Forest, and Gradient Boosting) on some meteorological data over three years (2015-2019), where 80 percent of the total data set was utilized for training and tested on 20 percent. The variables used include Wind speed, Relative Humidity, Dew point, and Air pressure. The objective was to determine which regressor achieves better outcomes for forecasting air temperature with the lowest error rate. This research concluded that the Random Forest Regressor is the most accurate in prediction. Here, MAE is used to determine the accuracy. On average, the Random forest had the lowest MAE value of 0.102, which was lower than the outcomes of the other three algorithms.
Smart Presence System by Using Machine Learning
(Daffodil International University, 2022-01-04) Rahman, Mahmudur; Sultana, Boby Nasrin; Asif, Md. Mahmudul Hasan
If the task of ensuring the presence of an employee is completed by hand, it may be a significant load on the organization. An efficient and automatic presence system is being used to address this problem. However, with this system, verification is a critical topic to consider. In most cases, the Smart Presence System is implemented with the assistance of real-time facial detection and identification technology. The Haar Cascade Classifier method has been employed in the creation of this feature. Following face recognition, the system will create a spreadsheet for each day of the week in question. This real-time face detection and identification system are only available to firm personnel who have registered with the business. A QR code mechanism has been implemented for the benefit of those who have not registered. Some information about the user will be utilized in this system, but not all of it. This system will properly handle the presence of both registered and unregistered individuals.