https://ar.iub.edu.bd/handle/123456789/619 2026-04-15T22:36:23Z https://ar.iub.edu.bd/handle/11348/703 An Undergraduate Internship/Project on Book Recommendation System at ADN DigiNet Kabir, Ashraful As an intern in the artificial intelligence division of ADN DigiNet, I had the opportunity of developing prototypes and proof of concept projects utilizing Machine Learning (ML) and Artificial Intelligence (AI) techniques. The internship commenced with an intensive two- month training phase, immersing us in ML concepts, tools, and available libraries. Subsequently, the final month was dedicated to applying our newly acquired knowledge and skills to work on individual projects. The development of an intelligent book recommendation system was the main goal of my project, that utilizes AI techniques to suggest popular books to users and recommend books based on similarity. The primary objective of the system is to address the growing challenge of information overload in the digital age, where countless books are published regularly, making it increasingly difficult for users to discover relevant and interesting reads. As part of this project, I played a key role in developing the system's AI model. I was specifically in charge of putting the essential features into place, such as the collaborative and popularity-based filtering methods. Throughout the development process, various challenges were addressed, including data preprocessing and model optimization. By employing suitable AI techniques, the model successfully overcomes these challenges, resulting in an effective book recommendation system. 2023-10-19T00:00:00Z https://ar.iub.edu.bd/handle/11348/702 An Undergraduate Internship/Project on Topic “FamiPlasma Mobile App” Morshed, Md.Yeard The FamiPlasma Mobile Application is an all-inclusive platform that revolutionizes blood donation within families. This innovative app intends to simplify organizing blood donation events among family members, ensuring the timely availability of blood and fostering a sense of unity and support among family members. Essential features of the FamiPlasma Mobile Application include user registration, a QR code scanner, and the capacity to invite family members via email or QR code scanning. Once registered, users can quickly search for compatible blood groups within their family network, providing an essential resource during emergencies. Additionally, the app offers insights into any diseases or medical conditions within the family, facilitating determining eligibility for blood donation. Only authorized family members can access individual data to uphold privacy and confidentiality, ensuring that personal information remains secure and accessible only to those who genuinely need it. Additionally, the app encourages regular blood donation by taking account of each user's contributions and recognizing their altruistic efforts. In addition, FamiPlasma provides users with essential information about nearby blood banks, including their locations and contact information. This feature facilitates communication with blood banks, fostering a strong relationship between families and donation centers. The FamiPlasma Mobile Application is poised to have a significant impact by increasing the efficacy and accessibility of blood donation within families. Utilizing technology, it seeks to save lives, promote health awareness, and strengthen familial bonds by fostering a sense of shared responsibility. 2023-10-18T00:00:00Z https://ar.iub.edu.bd/handle/11348/700 An Undergraduate Internship on Potato Plant Disease Detection and Edu Chatbot Raihan, Akib At ADN DIGINET, I am currently undertaking an enriching internship as an Artificial Intelligence Trainee, working collaboratively with a team of four members. The internship's primary goal is to develop and submit two or more AI-related projects. In this abstract, I present the details of the ongoing projects, "EDU Chatbot'' and "Potato Plant Disease Detection." The "EDU Chatbot" project aims to create an intelligent chatbot tailored for university-related inquiries. The chatbot's functionalities include answering student queries about university facilities, financial aid, and other relevant information. To develop this innovative solution, I am utilizing TensorFlow and Nltk libraries to build the underlying model. For deployment, we plan to implement a Flask API, coupled with a front-end design using React. The chatbot's capabilities will empower students to access accurate and timely information about their respective universities. In the "Potato Plant Disease Detection" project, our focus is on creating an AI-based system capable of accurately identifying diseases affecting potato plants. By submitting an image of the plant, the model will predict whether it is suffering from early blight, late blight, or if it remains healthy. Utilizing Convolutional Neural Networks (CNN) and TensorFlow, I am actively constructing the disease detection model. The API framework we intend to implement is FastAPI, with the frontend to be developed using HTML and CSS. This project's successful completion will provide farmers with a valuable tool for crop health management. Throughout the initial stages of the internship, I have dedicated time to enhance my knowledge of various machine learning and deep learning libraries. This period has allowed me to become proficient in utilizing essential tools and methodologies for successful AI projects. As the internship progresses, I am actively engaged in hands-on learning, gaining valuable experience in team collaboration, and honing my skills in Artificial Intelligence technologies, 8 | Page including TensorFlow, CNN, FastAPI, NLP and ReactJS . I look forward to presenting the final outcomes of these projects, which will demonstrate my ability to address real-world challenges through innovative AI solutions. 2023-08-24T00:00:00Z https://ar.iub.edu.bd/handle/11348/699 An Undergraduate Internship on InfiltraWatch Hasan, Azwad Fawad This project develops a web application that makes use of modern computer vision and existing CCTV infrastructure to solve the growing security issues in industrial buildings. The main goal is to effectively and instantly hinder potential attackers and prevent unlawful entry. The solution makes use of a state-of-the-art AI model to intelligently evaluate the CCTV cameras’ video stream to recognize and categorize any individuals in the picture. To enable thorough surveillance of the premises, the model is particularly trained to recognize human figures, count the number of people, and mark off forbidden zones. When it detects any human presence in the designated areas after hours. The MySQL database is populated with the combined date, time, human count, and camera position by a Python script. A simultaneous alarm is sent off inside the designated region with the intention of frightening and discouraging the intruder. It is anticipated that the implementation of this web application would dramatically improve security controls, decrease potential weaknesses, and significantly lower the danger of property damage and loss in industrial settings. The project not only seeks to secure the factory property but also contributes to the investigation of the use of AI in surveillance for more extensive applications 2023-10-04T00:00:00Z