Browsing by Author "Ahmed, Fahim"

Now showing 1 - 7 of 7

ARC 401_Design VII_17108037
(2021-06-20) Ahmed, Fahim
Bangla text classification using machine learning and deep learning techniques
(BRAC University, 2021-09) Salehin, Kamrus; Ahmed, Fahim; Nabi, Md. Ashifun; Alam, M. Kaosar; Ashraf, Faisal Bin
At present, we have seen everything is getting digitized where technology almost takes full control over our life. As a result, a massive number of textual documents are generated on online platforms and news articles are no exception. People prefer to get connected with online news portals as they are updated every single hour. Newspaper articles have so many categories such as politics, sports, business, entertainment, etc. Recently, we have noticed the rapid growth and increase of Bangla online news portals on the internet. It will be helpful for the online readers to get recommended the preferable news category which assists them in locating desired articles. Manually categorizing news articles takes a huge time and e ort. So, text categorization is necessary for the modern day, as enormous amounts of uncategorized data are an issue here. Although the study has improved in categorizing news articles greatly for languages such as English, Arabic, Chinese, Urdu, and Hindi. Among others, the Bangla language has shown little development. However, some approaches applied to categorize Bangla news articles, using some machine learning algorithms where resources were minimum. We have applied ve machine learning classi ers and two neural networks to categorize Bangla news articles. To show the comparison between applied algorithms, which one is performing better, we have used four metrics that measure performance.
Ethoreal Shift: A role playing game for the PC platform
(Daffodil International University, 2018-11-11) Kundu, Swarna; Ahmed, Fahim
For this project, we wanted to design a computer game in Unity. So we decided to design a Role-Playing game (RPG) where the objective is to collect three elemental stones, save the planet using the stones and get out of the game by finishing it. The player, who is a magician, has to collect three stones by defeating enemies in different levels and save the planet from being destroyed. The game is designed & developed in Microsoft Windows and written in C# using Unity Game Engine, Monodevelop and Microsoft Visual Studio. We have implemented many advanced programming functions in this project as taught in our Multimedia Authoring & Game Development course. As a result, we have created a 3D RPG game that we hope would be fun to play and enjoyable.
Feasibility analysis of CSP Technology coupled with TES system for power generation in industrial plants of Bangladesh
(Department of Mechanical and Production Engineering(MPE), Islamic University of Technology(IUT), Board Bazar, Gazipur-1704, Bangladesh., 2022-05-30) Ahmed, Fahim; Mubarrat, Mitin
Different technologies and approaches to diverse methodology may be used to convert solar energy into electrical power, making it an important renewable energy source across the world. Photovoltaic (PV) conversion and Concentrating Solar Power (CSP) are two separate technologies for converting solar energy into electricity. In the realm of solar energy harvesting, Concentrating Solar Power (CSP) is seen as a key future option. It is more efficient and lasts longer than PV cells. CSP plants with integrated thermal energy storage (TES) technology can provide up to 12 hours of power reserve under optimal circumstances. We sought to find the optimum place in Bangladesh for a feasibility study based on the place's high average temperature and the amount of flat land that was available. Following our comparisons, we believe Kushtia may be the location we've been seeking. As part of this project, we built and optimized a 10 MW Power Tower Molten Salt-based stand-alone CSP power plant with 12 hours of thermal storage for Kushtia in System Advisory Model (SAM). It was decided that the stated site should have a DNI design point value of 950 W/m2. With a power cycle efficiency of 40.58 percent, the optimized plant's gross power cycle output is determined. There are two key obstacles for developing any CSP-based power plant: cost and the overall area it covers. The break-even threshold for this specific plant against conventional unit cost has been calculated in this study using extensive numerical analysis. The proposed power station is compared to a standard 10 MW steam power plant to evaluate its environmental and economic benefits and drawbacks. Future CSP researchers will benefit from this paper's thorough overview of the technology and research in this area. Additionally, Bangladesh's solar thermal power plant development and innovation is encouraged by this plant's feasibility study.
Project Management Software - A Project by United Commercial Bank Ltd.
(BRAC University, 2021-09) Ahmed, Fahim; Afzal, Mr. Syed Hasan; Alam, Dr. Md. Golam Rabiul
Thousands of Apps are created each day, globally. A prominent software firm works on 10+ projects simultaneously at any given moment. The versatility of web appli cation, from ecommerce site to blog sites to browser games, is unparalleled in the field of software development. In this plethora of projects, it is important to keep track of the phases, documents, and developers working on each project. This is where project management systems come in. In this report the goal is to introduce readers to United Commercial Bank, elaborate on the development tools available today, and debut the project management system ‘Protracker’. A very powerful pro gramming language, C#, some very popular frameworks, like ASP.NET, ASP.NET Core, EntityFrameworkCore, and MVC, are used in the development of this webapp, and are elaborated in this report. Moreover, a detailed SDLC of Protracker is also included. Finally, the benefits of doing an internship, what can we expect to learn during this period, the challenges that are faced, and how we grow as we overcome the challenges are worthwhile sections to read.
Retinal Diseases Detection using Deep Learning
(BRAC University, 2022-09) Mashfi, Shahriar; Roy, Amit; Abdullah, Riasat; Ahmed, Fahim; Khan, Sazid Hayat; Karim, Dewan Ziaul
Retina is an important aspect of human vision because it converts light rays into images and sends messages to the brain. We run the danger of suffering long-term harm to the eyesight if we have a problem with our retina that might lead to vi sion loss or blindness which can be caused by eye illness, ocular trauma, or other problems. Retinal based diseases such as diabetic retinopathy, age-related macular degeneration (AMD) and retinal detachment . However, if someone can take care of his/her retinal health by eye-checkup annually it might help. Moreover, human civ ilization is now way advanced by the blessings of modern technology. Furthermore, we came up with an idea which will lead us to the success door of retinal disease detection in a very easy and cheap way. In this modern world, a large amount of people use smartphones and high resolution cameras and that is the main fact. De tecting retinal diseases with computer vision based image processing will help a lot of people in the world to be healthy in terms of their eyesight. We are planning to apply Convolutional Neural Network (CNN) to identify and classify retinal diseases with high accuracy. However,we will go through some methodologies such as data pre-processing, segmentation, analyzing etc. For Large-Scale Image Recognition we are using our customized Convolutional Network that we have proposed in this pa per. Here, we started our data segmentation from Kaggle. We have used 28972 images from Kaggle as our data-set. Then we segmented it in three parts: Test, training and validation. And here we will detect a total of four different retinal pictures.. They are: CNV, DME, DRUSEN and NORMAL. We have trained our proposed CNN model with these dataset and gained 98.97% validation accuracy. Moreover, we also run some pre-trained models. They are: Resnet50, Inceptionv3, EfficientNet B0, Xception and VGG16. We gained 79.34%, 91.32%, 28%, 87.94% and 94.01% accuracy respectively from them. Hence, we can see that our proposed CNN model outperformed them in these experimental results.
Share Market Solution
(Department of Computer Science and Engineering, Islamic University of Technology, Gazipur, Bangladesh, 2015-11-15) Ahmed, Fahim; Islam, Tausiful
Stock market of Bangladesh covered 33 per cent of Bangladesh's gross domestic products (GDP) in 2011. ‘Stock Market’ is the reflector of a country and ‘Brokerage House’ is the reflector of share market ‘Share Market Solution’ is a website, which provides a complete, high-quality trading experience in various markets by ensuring quick, easy, accurate transactions that are easily accessible to respective user and ensured by administration from the perspective of a brokerage house. Thus this project has five major parts, the admin part for managing the all system, the hospital part for managing all the doctors of the system, the doctor part to give consultation and advice to patients, the patient part for getting consultation and advices, and at last the pharmacy part for managing all the medicines and deliver the prescriptions to patients.