Browsing by Author "Rahman, Abdur"

Now showing 1 - 20 of 22

A microbial investigation of neonatal calf diarrhoea in Bangladesh
(1987-10) Debnath, Nitish Chandra; Huq, Mohammad Indadul; Rahman, Abdur
Ai-Powered Crop Disease Detection And Solution System To Empower Rural Entrepreneurs With Limited Education
(DAFFODIL INTERNATIONAL UNIVERSITY, 2024-08-03) Rahman, Abdur
The whole outcomes of my proposal, " AI-POWERED CROP DISEASE DETECTION AND SOLUTION SYSTEM TO EMPOWER RURAL ENTREPRENEURS WITH LIMITED EDUCATION", may be seen here. This essay goes into great detail about how the idea was transformed into a working website. The user dashboard is one element that system users notice. The project's objective was to develop a web application with image classification and GPT OpenAI integration for Fast API, AI-powered crop disease detection and assistance. intends to create a web application that uses picture recognition to classify agricultural diseases. Users will be able to snap a picture, submit it, and use the app to identify illnesses. An GPT OpenAI integration will also be incorporated to respond to user inquiries and offer answers about ailments that have been identified. An alternative is to establish specified wording for illness information and prevention. There is also an online version that requires uploading images before processing. The goal of this research is to create a picture web categorization system for crop disease identification. Users may take pictures of afflicted crops or submit them, and the system will accurately identify the illnesses. Four crops, each with three to four illnesses, will be supported by the system for categorization. An integrated Fast API GPT OpenAI integration will also give answers to user questions, solutions, or predetermined data on the specifics of the illness, prevention, and therapy. There will also be an online version that requires image submissions in order to diagnose diseases. This system gives farmers immediate, AI-driven information to improve agricultural decision-making. Every aspect of the system development process, from idea to execution, is covered in the research, including the technologies used, architecture, and user interface design. Python was used for the backend and Frontend use stream lit. All you need is a standard desktop computer and internet access to set up our system application; expensive software or computer components are not required.
Ai-Powered Crop Disease Detection and Solution System to Empower Rural Entrepreneurs With Limited Education.
(Daffodil International University, 2025-08-02) Rahman, Abdur
The whole outcomes of my proposal, " AI-POWERED CROP DISEASE DETECTION AND SOLUTION SYSTEM TO EMPOWER RURAL ENTREPRENEURS WITH LIMITED EDUCATION", may be seen here. This essay goes into great detail about how the idea was transformed into a working website. The user dashboard is one element that system users notice. The project's objective was to develop a web application with image classification and GPT OpenAI integration for Fast API, AI-powered crop disease detection and assistance. intends to create a web application that uses picture recognition to classify agricultural diseases. Users will be able to snap a picture, submit it, and use the app to identify illnesses. An GPT OpenAI integration will also be incorporated to respond to user inquiries and offer answers about ailments that have been identified. An alternative is to establish specified wording for illness information and prevention. There is also an online version that requires uploading images before processing. The goal of this research is to create a picture web categorization system for crop disease identification. Users may take pictures of afflicted crops or submit them, and the system will accurately identify the illnesses. Four crops, each with three to four illnesses, will be supported by the system for categorization. An integrated Fast API GPT OpenAI integration will also giveanswers to user questions, solutions, or predetermined data on the specifics of the illness, prevention, and therapy. There will also be an online version that requires image submissions in order to diagnose diseases. This system gives farmers immediate, AI-driven information to improve agricultural decision-making. Every aspect of the system development process, from idea to execution, is covered in the research, including the technologies used, architecture, and user interface design. Python was used for the backend and Frontend use stream lit. All you need is a standard desktop computer and internet access to set up our system application; expensive software or computer components are not required.
Customer satisfaction level of prepaid subscribers of Airtel Bangladesh Limited
(BRAC University, 7/5/2012) Rahman, Abdur
Airtel is the sixth telecom operators in Bangladesh. As an emerging company Airtel is doing extremely well. After the launch of Airtel in Bangladesh, the competition has become more strengthen among the telecom operators. Each of them is fighting to boost up its market share by offering new promotion and benefits to the customers. Since, all of the operators are offering almost same categories of products it has become a big challenge to retain the existing subscribers and acquisition of new customers. At this moment Airtel is trying to reach the customers with various promotional activities and is attempting to make their brand presence felt. Through their significant advances in Bangladesh, Airtel is moving ahead on the track to achieve their goals. As a student BBA program, I got the opportunity to complete my internship program in such a multinational telecom company. The internship program is the partial requirement of my BBA program and the duration of the internship session was 3 months. I worked in the central communication domain of Service Experience of Airtel Bangladesh. The report has been prepared in align with my job responsibilities and experiences at Airtel. I have conducted a research survey among Airtel prepaid among the prepaid customers. After that I have designed the research in a descriptive way and collected data are analyzed quantitatively. The research findings show that there are several factors that make the customers dissatisfied regarding Airtel. Poor network quality, excessively messaging communication from Airtel, poor call quality and bad internet service etc. are the areas for customer dissatisfaction. On the other hand, the customers are satisfied for the price of new prepaid connection, availability of the prepaid recharge cards/Ezee load, tariffs of the prepaid packages, lives enriching value added service, and for customer supports after sales. However, the overall analysis describes that the most of the airtel prepaid subscribers are moderate subscribers. At the end of the project, some recommendations are given to help the Airtel management so that they can deploy appropriate decisions to reduce the customer dissatisfaction.
Deep Learning for Bone Health-A Transformer Based Framework for Osteoporosis Screening
(Daffodil International University, 2025-09-16) Rahman, Abdur; Mim, Sarmin Rahman
Osteoporosis is a progressive bone disease that leads to a higher risk of fractures, and early diagnosis continues to be a significant problem because current diagnostic tools are not comprehensive. In this work, we tested deep learning models, such as VGG16, VGG19, ResNet, DenseNet, UNet, Vision Transformer (ViT), and Swin Transformer, on 853 X-ray images to detect osteoporosis automatically. To overcome the issue of class imbalance and enhance the robustness of the model, data preprocessing was carried out through standardization, normalization and augmentation. It was experimentally demonstrated that VGG19 had the best classification accuracy of 97%, and UNet performed better in a segmentation task with a Dice score of 0.936. In comparison with the available literature, our method shows a competitive level of performance and proves the possibility of CNN-based and transformer models in medical image processing. The present work helps to build trustworthy, inexpensive, and affordable AI-aided diagnostic systems to monitor osteoporosis and establishes the future trends towards larger datasets, multimodal systems, and real-time clinical use.
Development of Job Sharing Platform
(Daffodil International University, 2020-12) Hossain, Md. Shafayet Hossain; Biswas, Nahid; Rahman, Abdur
“DEVELOPMENT OF JOB SHARING PLATFORM” is a web application where people can share their jobs and job seekers can find jobs.And for completing jobs job seekers will be paid by the job sharers.Its a efficient ,convenient application where job seekers and job sharers will be connected. This application has admin panel,job sharer panel,job seeker panel.There will be job’s category based on job type. Job sharers will have to register to the system by verifying their email.Without verifying email they cant get access to their profile. They can update their profile ,share their job.While sharing jobs job sharers can select job’s category,add their location.They can add,update,edit,delete their shared job post.They can view the applicants(job seekers) profile’s informations.And based on applicant’s (job seekers)profile details they will decide to sent job approval confirmation mail to the selected one’s(job seeker) mailbox and job seekers will be notified .Jobs seekers can login to their dashboard by registering and verifying email.They can search jobs based on their skill,job’s type,their location.But for applying the jobs they must login.They can add,edit,update their profile too.They can check job sharer’s information too.They can save their favourite jobs.After applying for jobs if job seekers get any approval confirmation mail from the job sharer then he/she will communicate with the job sharer via cell or mail. There will be job recommendations in our system for the users.One unique feature of our application is that any user can recommend jobs to other user by mailing.In admin panel admin will view all the jobs,users.Admin can delete jobs,users.He/she can add job category,testimonial, blog post related with jobs in our application
Dialysisbook, an E-Commerce Website for Dialysis Patients
(Daffodil International University, 23-02-13) Atiq, Abdullah Ibn; Rahman, Abdur
Our project named “Dialysisbook, An E-commerce Website For Dialysis Patients” is a website that includes features like buying peritoneal dialysis products and also booking hemodialysis appointments at the listed hospital in our website. The webpage includes registration and log in for the users and after that they can explore the pages where they can browse peritoneal dialysis related products and add them to cart to purchase and they can also browse listed hospitals for hemodialysis appointments at the location of their need. There will also be an admin panel, only admin will be able to add hospitals or products to the list. We have created this project using HTML, CSS, PHP, SQL java script and bootstrap for front end and back-end work. The tools we have used are software such as visual studio code, XAMPP, PhpMyAdmin. This project includes a very attractive front end which will create a user-friendly environment. The back end and the database will provide the support it needs to be a proper website. In conclusion, the purpose of this project was to help dialysis patients with their regular needs and it will do so.
Effect of supplementation of neem (Azadirachta indica) leaves to lactating cows for improving milk production in traditional farming system
(Faculty of Animal Science and Veterinary Medicine, Sher-e-Bangla Agricultural University, 2022-07) Moniruzzaman, M; Khan, MAS; Akter, M; Rahman, Ashikur; Rahman, Abdur; Asaduzzaman, M
ABSTRACT The present experiment was carried out to evaluate the efficacy of neem leaves on the performance of early lactating cows feeding with straw-based traditional diet (rice straw, wheat straw and roadside grass etc.). For this purpose, six lactating cows were selected based on early lactation and severity of infection in terms of gastrointestinal nematode. In each cow, neem leaves were supplemented at the rate of 200 mg/kg live weight of the animal along with the straw-based traditional diet. The selected animals were observed and data were collected 4 weeks before and 4 weeks after treating with neem leaves. Feces were collected from the cows weekly for the observation of parasites. From the findings, it was observed that the average egg per gram of feces (EPG) was significantly (p<0.05) lowered after supplemented with neem leaves. The average body weight and milk production of the lactating cows were significantly increased after treatment. The results indicate that supplementation of neem leaves had a positive effect on the performance of lactating cows and it can be used for better performance of lactating cows under village conditions where cows are reared on straw-based traditional diet.
EST: A Semi-supervised ensemble approach for Explainable AI-driven stress detection in social media
(Department of Computer Science and Engineering, 2022-12) Rahman, Abdur; Symon, Nurul Karim; Zaman, Akther Uz
Social networking websites have become a vast ‘archive’ of human expression, containing hu man emotions from across the globe. Recognizing stress signals within this dynamic landscape is crucial for mental health monitoring, offering opportunities for timely intervention and sup port. This paper introduces a methodology integrating advanced machine learning techniques, notably Ensemble Learning and Self-Training, with Explainable Artificial Intelligence (XAI) to enhance stress detection capabilities. Our research follows a methodical approach, begin ning with foundational steps of data collection and exploratory data analysis, providing insight into sentiments within social media interactions. Prioritizing the interpretability of model pre dictions, our methodology aims to build trust and offer meaningful insights for end-users and mental health professionals. Subsequent phases involve data preprocessing, and refining textual data to extract subtle indicators of stress. The core of our methodology is the fusion of En semble Learning and Self-Training, strategically combining diverse learners to iteratively refine the model using labeled and unlabeled data. With the help of XAI, we seek to deliver clearly and straightforwardly noticeable insights relating to decision-making produced by our stress de tection model. Summing up the presented approach significantly contributes to mental health analytics taking a step forward toward better stress detection by a technical framework with an enhanced accuracy of 91.67%.
Fake Hilsa Detection Using Machine Learning Algorithm
(Daffodil International University, 2021-06-01) Islam, Merajul; Rahman, Abdur; Ani, Jannatul Ferdous
Hilsa is the national fish of Bangladesh. Bangladesh is earning a lot of foreign currency by exporting this fish. Unfortunately, in recent days some unscrupulous businessmen are selling fake Hilsa fishes to gain profit. The Sardines and Sardinella are the most sold in the market as Hilsa. The government agency of Bangladesh, namely the Bangladesh Food Safety Authority said that these fake Hilsa fish contain high levels of cadmium and lead which are detrimental for humans. In this research, We have proposed a method that can readily identify original Hilsa fish and fake Hilsa fish. Based on the research available on online literature, we are the first to do research on identifying original Hilsa fish. We have collected more than 16,000 images of original and counterfeit Hilsa fish. To classify these images, we have used several deep learning based models. Then the performance has been compared between them. Among those models, DenseNet201 achieved the highest accuracy of 97.02%.
Impact Analysis of Rooftop Solar Photovoltaic Systems in Academic Buildings
(Springer Nature, 2023-12-19) Nayan, Pranta Nath; Ahammed, Amir Khabbab; Rahman, Abdur; Johora, Fatema Tuj; Reza, Ahmed Wasif; Arefin, Mohammad Shamsul
Solar energy is a non-depleting and eco-friendly source of renewable energy that is generated through the use of solar panels, which convert the energy from the sun into electricity. In the current world, we need electricity supply constantly but produced electricity cannot meet the world’s demand. Even in our country, the situation is much more crucial. The government attempts to handle this situation by shedding loads, which has a detrimental impact on industrial, commercial, and educational institutions. In this paper, we provided a solution to produce renewable energy through photovoltaic solar panels that are environmentally friendly. The paper also provides the working process of solar panels, how solar panels meet load demand and reduce the cost of electricity bills, and future trends and aspects of solar energy.
IoT Based Air Quality Monitoring System
(East West University, 9/27/2018) Nur, Muktasib Un; Rahman, Abdur
Air pollution is one of the most concerning fact of today’s world. Among all the man-made pollution, air pollution poses a serious threat for health. It affects human body through breathing and since this pollution is barely visible in eye, a monitoring system is necessary to stay cautious. This is the motivation behind our work so that government and citizens can stay aware of the air they are breathing. Our objective is to provide a system to measure Air Quality and AQI level using gas sensors. We proposed a city model where the monitoring devices are connected through IoT technology. In the central based station, all the city data is stored and analyzed using classifier algorithm to predict future pollution of a city. From previous dataset we got high accuracy. Our work is significant for a city modeling where the authority wants a full monitoring on pollution and also the citizens want to stay concerned about the air quality. The potential application of our work is for modern cities where pollution level is relatively higher. This system can directly impact on the city pollution control because when it is possible to monitor precisely, it is also possible to prevent pollution.
Kajkormobd: Discover Jobs & Workers (An Android Application)
(Daffodil International University, 2019-12) Rahman, Abdur; Shohag, Mehedi Hasan
Demand for work is increasing day by day. On the other hand, people's unemployment is also increasing. the unemployment rate in Bangladesh is at approximately 4.4 percent[1]. where unemployment is to be reduced. Our applications will reduce unemployment to some extent through creating a useful bond between work and worker. In our application for any kind of work can be applied. The person who will work should be someone who is skilled in the work or is not skilled in any work, but he wants to work in a home, shop or institution. Those who need a worker, can hire him or her from a position near to the workplace or from anywhere as per his requirement. In this, anyone who needs his work to be done will get the worker very fast. In this, anyone who needs to work will get a very fast working person. On the other hand, those who want to work or lose unemployment will be able to earn a good living in exchange for work.
Modes of Investment of Islami Bank Bangladesh Limited
(Daffodil International University, 2018-11-25) Rahman, Abdur
Islami Bank Bangladesh Limited (IBBL) is attempting to build up the greatest welfare of the general public by keeping up the standards of Islamic Shari'ah which depends on "Quran" and "Sunnah". Since 1983, IBBL is the pioneer in welfare saving money in this subcontinent and it is attempting to do every one of its exercises for the advancement of its investors. For the more prominent enthusiasm of the investors the venture approach of IBBL is to contribute based on benefit and misfortune partaking as per the tents and standards of Islamic Shari'ah. To finish my report I have utilized both subjective and quantitative information. In the primary part I have endeavored to examine about the destinations, strategy, extension and restrictions of the examination. The primary goal of the report is to familiarize with the distinctive methods of speculation of Islami Bank Bangladesh Limited and to assess its viability. In the second part I have attempted to examine about the modern and hypothetical foundation of managing an account area in Bangladesh. In the third part I have attempted to appear about the idea of Islami saving money and its experience in banking area in Bangladesh. In the fourth part I have endeavored to talk about Different Modes of Investment. In the fifth section I have endeavored to talk about Investment Performance of IBBL. In the 6th part I have given discoveries, some proposal and end.
Performance analysis of a space time block coded MIMO system over faded channel
(BRAC University, 4/20/2011) Rahman, Md. Asiqur; Rahman, Abdur; Majumder, Satya Prasad
Performance analysis will be carried out for a MIMO wireless link with space time block coding to find the performance over a Raleigh fading channel. The expression for the signal and SNR at the receiver output will be derived. The bit error rate (BER) will be found for maximal ratio combining technique and the performance results will be numerically evaluated for different system parameters. Performance improvement to space time block code will be determined at a given BER and to find the effect of carrier offset frequency on the link performance.
Performance analysis of dye sensitized solar cell based on ZnO compact layer and TiO2 Photoanode
(BRAC University, 2018-09) Rahman, Abdur; Mahmud, Md. Ashik; Haque, Md. Injamamul; Bhuian, Md. Belal Hossain
Harnessing solar energy as an alternative solution to power production. Power can be produced through burning fossil fuels. To gain optimum benefit through solar energy is an extreme challenge for scientists and researchers nowadays. Solar power generation is consistently improving through the decades and third generation dye sensitized solar cell can play an important role as a solution. Dye sensitized solar cell approaches to high efficient thin film technology. Efficiency can be increased by adding more cells of different band gap to a cell stack in Tandem cell. In this ongoing study, a double layer structured dye sensitized solar cell has analyzed where ZnO and TiO2 composited photoanode were prepared on FTO. The Photovoltaic characteristics, I-V & J-V curve were evaluated for different thickness, absorption coefficient and wavelength. DSSC solar cell characterization techniques such as current-voltage and spectral response measurements were analyzed to evaluate the cell performance.
Performance analysis of dye sensitized solar cell based on ZnO compact layer and TiO2 photoanode
(BRAC University, 2018-08) Rahman, Abdur; Mahmud, Md. Ashik; Haque, Md. Injamamul; Bhuian, Mohammad Belal Hossain
Harnessing solar energy as an alternative solution to power production. Power can be produced through burning fossil fuels. To gain optimum benefit through solar energy is an extreme challenge for scientists and researchers nowadays. Solar power generation is consistently improving through the decades and third generation dye sensitized solar cell can play an important role as a solution. Dye sensitized solar cell approaches to high efficient thin film technology. Efficiency can be increased by adding more cells of different band gap to a cell stack in Tandem cell. In this ongoing study, a double layer structured dye sensitized solar cell has analyzed where ZnO and TiO2 composited photoanode were prepared on FTO. The Photovoltaic characteristics, I-V & J-V curve were evaluated for different thickness, absorption coefficient and wavelength. DSSC solar cell characterization techniques such as current-voltage and spectral response measurements were analyzed to evaluate the cell performance.
Prevalence of selected reproductive tract infections among pregnant women attending an urban maternal and childcare unit in Dhaka, Bangladesh
(2003) Begum, Afroza; Nilufar, Sofia; Akter, Khaleda; Rahman, Abdur; Khatoon, Fatema; Rahman, Motiur
Promoting social and emotional learning in BRAC primary schools
(BRAC Research and Evaluation Division (RED), 2012-01) Afroze, Rifat; Nahid, Durdana; Rahman, Abdur
BRAC Education Programme took a scheme on a pilot basis to improve social and emotional skills among the students of BRAC primary schools. The aim was to make the learners more social and shaping their behaviour and thoughts in a positive way. After 10 months of programme implementation, this study was undertaken to see the classroom situation level. Several aspects of Social and Emotional Learning (SEL) was already included in regular BRAC curriculum. However, six more activities were introduced in the pilot schools. Three SEL implemented and three non-SEL schools were taken for investigation using qualitative research techniques. Findings reveal that the learners could describe their emotions, sometimes showed their confidence, and cooperated effectively with their peers. However, they did not show much interest in participating in the newly added components. There was also lack of follow-up and supervision of the activities. The SEL core team was supposed to be more active in this regard. It might be better to engage parents to gain a greater success of the initiative. The study recommends rethinking of the whole process–from curriculum development to implement in classroom considering student’s age, teachers’ quality, and local context.
Study of the Solar Irradiation Pattern of Bangladesh for Electricity Generation
(Daffodil International University, 2019-01) Hossin, Iftekhar; Rahman, Abdur
Now a days, the increasing demand of electric power and shortage of present energy resources lead today’s engineers and scientists to think about the alternative sources of energy. The sunlight is a potential source for producing electric power. In recent years, this solar system gains its popularity more and more. In home system applications, the use of solar energy is also attractive. Moreover, solar home systems require very little maintenance and need no fuel. Other advantages of a PV system are reliable power, free source of power, flexibility and quick installation. For socio-economic development a reliable, affordable and secure supply of energy is significant. The following research paper is based on analyzing the solar irradiation pattern of Bangladesh for electricity generation. Irradiation and power are discussed with their optimum capacity. Power is one of the most important factors in developing country and for sustainable economy. Like the rest of the countries of the planet, in Bangladesh the demand for power is increasing day by day. The main aim of our research is to find out the irradiation of sun in Dhaka city in the month of May and June so that the power production by the solar panel can be estimated and, we collect the solar irradiation and the maximum power data in Dhaka for (May & June) two months and analyze the data to get average irradiation and find the relationship between solar irradiation and power and by using this data we can easily understand the electricity production by solar home system and create a standard form of power production of solar home system in 2018.