Project Report

Browse

Subject: search.filters.subject.Artificial Intelligence (AI)

Search Results

Now showing 1 - 6 of 6
  • Thumbnail Image
    Item
    AI Studio :Revolutionizing Interior and Graphic Design
    (Daffodil International University, 2025-01-19) Pritom, Sondipon Paul
    AI Studio is an integrated work-environment, Learning Management System, as well as a Creative Cloud that has been developed to change the way people work, learn, and create with the help of AI. It showcases and combines systems like DALL-E for image generation and AI content creation for various users from content creators to educators and businesses to break down complicated creative processes. AI Studio engages its community members with post sharing, comments, and quiz functionalities besides providing differential subscription with a plan that provides obligatory access to the core AI Studio services. As a result, the heart of the platform is based on Laravel and MySQL with integrated modern frontend frameworks such as Bootstrap to provide a smooth interface to the users. The development process was done using an agile model where it is possible to test and integrate feedback in every loop, aimed at functionality and scalability. Therefore, key challenges, for example, the complexity of the integration of a set of high-demand AI tools, the platform scalability problem, and security threats or risks were either solved or reduced by the help of asynchronous processing techniques, cloud based infrastructure, and data encryption protocols. The straightforward design and architecture of the platform allow both engineers and laymen to leverage advanced AI tools, encouraging quick development. The concept of AI Studio is to promote and enhance the ability of individuals and organisations to capture, share, learn and create knowledge in the age of digital affiliation. This project not only shows that pair AI with good design and proper implementation, further innovation on using AI on various platforms can be created.
  • Thumbnail Image
    Item
    AI-Driven RFM E-Commerce
    (Daffodil International University, 2025-03-04) zaman, Rakibuz
    The findings that support my concept, "AI-Driven RFM E-Commerce," may be read in its entirety. In this article, the techniques utilized to transform the idea into a working website are discussed in depth. One module that sticks out among system users is the admin dashboard. I have been working on student project, which uses artificial intelligence to analyze dynamic customer, sales, and product data. The needs will be similar to what specifically mentioned. Three main areas & Dashboard are the emphasis of this project's development of AI-driven insights: Product Analysis (Dashboard-1): Predicting trends and performance by using forecasting models. Transaction/Sales Analysis (Dashboard-2): Finding trends and useful information in sales data. Customer Analysis (Dashboard-3): Recognizing consumer trends and segmenting them to improve decision-making. Technical Information Integration: To ensure smooth viewing and interaction, the dashboards will be integrated using frames. Data Handling: In order to enable real-time updates and more profound insights, I want to integrate the data with a dataset to make it static. For both the user interface and database backend, I have used Python, respectively. No costly software or computer components are required to set up my system application; all you need is your desktop machine and internet access. Almost any user with a regular internet connection may use my platform-neutral solution at any time and from any location. I may change my system to meet certain needs as well.
  • Thumbnail Image
    Item
    AI-Driven Job Recommendation System for Underprivileged Communities in Bangladesh
    (Daffodil International University, 2025-01-21) Sakib, Mottakin Ahmed
    The entire findings of my proposal, "AI-Driven Job Recommendation System for Underprivileged Communities in Bangladesh," may be read here. This article covers all of the procedures involved in turning the concept into a working website. In this project, there have one module: User modules. This project introduces a new smartphone application that uses artificial intelligence to deliver individualized career recommendations to Bangladesh's poor areas. The system, built in Java and powered by a large dataset, includes secure user authentication capabilities such as login, registration, and password recovery. Dataset contains almost 3761 data and features like: “experience_level, salary, company_size, age, company_name”, etc are columns. For user’s authentication use SQLite database. Users may utilize the thorough job search option to learn more about potential possibilities, while the AI-powered recommendation search engine examines user inputs to provide personalized job ideas. Furthermore, the program features a multilingual interface that enables for easy switching between English and Bangla, making it accessible to a wide range of users. Overall, this approach seeks to close the employment gap by linking disadvantaged job searchers with suitable work opportunities, promoting socioeconomic empowerment and progress in the region. From idea to execution, the research examines every aspect of mobile application development, including architecture, user interface design, and technologies used. The user interface was built with Java XML, while the backend was built with Python AI and Java. To set up our system application, no expensive software or computer components are required; all you need is a standard desktop computer and Internet access.
  • Thumbnail Image
    Item
    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.
  • Thumbnail Image
    Item
    "Food Detection, Classification and Nutrition Prediction Using Deep Feature Extraction with Convolutional Neural Networks
    (DAFFODIL INTERNATIONAL UNIVERSITY, 2024-02-03) Haider, S. M. Nesar
    This study investigates the application of Convolutional Neural Networks (CNNs) for food identification, categorization, and nutritional prediction, responding to the increasing need for automated dietary evaluation tools in healthcare and consumer sectors. The study employs extensive datasets, including Food-101 for food classification and a tailored nutrition dataset for estimating nutritional values, to establish a comprehensive system for food image analysis. The study utilizes four advanced CNN architectures—InceptionV3, VGG, ResNet, and EfficientNet—for feature extraction and model training, each selected for its distinctive capacity to grasp intricate visual patterns and nuances seen in food photos. The experimental framework entails a thorough assessment of different architectures utilizing standard performance criteria. In food classification, accuracy, precision, and recall are calculated to evaluate the models' effectiveness in identifying and categorizing a variety of food products. The study evaluates nutrition prediction performance using regression-based metrics, including mean absolute error (MAE) and root mean squared error (RMSE). Comprehensive testing and cross-validation reveal that, although all models exhibit effective performance, ResNet regularly surpasses its competitors in categorization and nutrition prediction tasks. In addition to the quantitative findings, the study offers insights into the practical ramifications of implementing deep learning models in real-world dietary monitoring systems. CNNs' capacity to autonomously extract pertinent elements from intricate food images presents a promising opportunity for creating intelligent, userfriendly applications that aid users in monitoring their nutritional intake and making informed dietary decisions. The findings highlight the capacity of deep learning to reconcile old manual dietary assessments with contemporary data-driven methodologies, thereby enhancing public health outcomes.
  • Thumbnail Image
    Item
    AI-Driven Job Recommendation System for Underprivileged Communities in Bangladesh
    (DAFFODIL INTERNATIONAL UNIVERSITY, 2024-06-24) Sakib, Mottakin Ahmed
    The entire findings of my proposal, "AI-Driven Job Recommendation System for Underprivileged Communities in Bangladesh," may be read here. This article covers all of the procedures involved in turning the concept into a working website. In this project, there have one module: User modules. This project introduces a new smartphone application that uses artificial intelligence to deliver individualized career recommendations to Bangladesh's poor areas. The system, built in Java and powered by a large dataset, includes secure user authentication capabilities such as login, registration, and password recovery. Dataset contains almost 3761 data and features like: “experience_level, salary, company_size, age, company_name”, etc are columns. For user’s authentication use SQLite database. Users may utilize the thorough job search option to learn more about potential possibilities, while the AI-powered recommendation search engine examines user inputs to provide personalized job ideas. Furthermore, the program features a multilingual interface that enables for easy switching between English and Bangla, making it accessible to a wide range of users. Overall, this approach seeks to close the employment gap by linking disadvantaged job searchers with suitable work opportunities, promoting socioeconomic empowerment and progress in the region. From idea to execution, the research examines every aspect of mobile application development, including architecture, user interface design, and technologies used. The user interface was built with Java XML, while the backend was built with Python AI and Java. To set up our system application, no expensive software or computer components are required; all you need is a standard desktop computer and Internet access.