]]>
The main intention of "My Wallet - AI-Based Personal Finance Manager" is to make personal finance management simpler, less time-consuming, and more insightful for every user.
"My Wallet" is a web-based system designed to empower users with an intuitive and intelligent platform for financial control. This system enables individuals to efficiently manage their transactions, track income and expenses, set and monitor saving goals, and maintain a clear overview of their financial health. Key functionalities include secure user authentication, comprehensive transaction management (both manual entry and automated parsing from uploaded bank statements), and dedicated sections for incomes, expenses, upcoming bills, and saving goals. A distinctive feature of this application is its integration of Artificial Intelligence, which intelligently categorizes transactions, detects beneficiaries from bank statement data, and generates personalized saving plans based on user-defined objectives. While designed for ease of use and intuitive navigation, the application
incorporates relatively complex AI algorithms and data processing logic beneath its user-friendly interface.
]]> ]]>
The main intention of "TripTidy: AI-Based Travel Planner" is to make personalized trip planning simpler, less time-consuming, and more insightful for every user.

TripTidy is a web-based application designed to empower users with an intuitive and intelligent platform for comprehensive travel organization. This system enables individuals to efficiently generate personalized itineraries based on their destination, dates, budget, and preferences. Key functionalities include robust user authentication, dynamic integration with external APIs for real-time hotel (Booking.com via RapidAPI) and flight (Amadeus API) searches, AI-powered content generation (via TogetherAI), image retrieval, and geolocation services (Foursquare API) [1][2][3][4]. Users can also customize generated itineraries, track and manage expenses, and browse pre-made itineraries on a dedicated Guide page. While designed for ease of use and intuitive navigation, the application incorporates sophisticated AI logic and data processing beneath its user-friendly interface, built with React for the front-end, Node.js with Express.js for the back-end, and MySQL as the database [5][6][7][8].
]]> ]]> ]]> This project aims to design and implement an automated antenna rotator system capable of tracking satellites and facilitating radio communication. The system integrates a custom-built hardware platform with a software interface to: (1) automatically adjust the antennas direction based on the position of the ground station and a chosen satellite, (2) set the appropriate radio frequency and configure other parameters based on selected satellite, and (3) provide a user-friendly interface for satellite selection and real-time control. The project targets Low Earth Orbit (LEO) satellites, such as weather satellites (e.g. NOAA, MetOp, etc.), with the potential to receive and decode signals like weather images. The system is intended to be modular; if certain features are not needed they do not break the rest of the system (e.g. for tracking celestial objects other than satellites, where decoding is not necessary).
The main purpose of this project is not to develop another universal weather satellite decoder with extra features, but a more specific and simplified system for amateur use.
]]> The system was implemented using a modular, role-based structure that enables patients to search for doctors, view profiles, book or cancel appointments, and make payments online. Doctors can manage their schedules and track appointments, while administrators are provided with tools to oversee users and system activity. Methods included designing user-centered interfaces, applying secure authentication mechanisms, and testing the system through automated end-to-end simulations.
]]> AND MACHINE LEARNING
]]> Several models were tested, including Logistic Regression, Support Vector Machines, GRUs, and transformer-based models like RoBERTa and DeBERTa. The best performance came from RoBERTa with label smoothing and DeBERTa-v3, both reaching 98% accuracy. While these advanced models were the most accurate, simpler models like GRU were still competitive and easier to interpret.
The thesis also examined linguistic differences between real and AI-generated reviews. Real reviews were shorter, used more personal and emotional language, while AI-generated ones were longer, more structured, and often overused formal or generic phrases.
A working browser extension was built as part of the project. It allows users to analyze reviews directly on websites and see predictions with basic explanations. Although the tool works well, there are still limitations, such as handling newer AI models and providing clearer feedback for non-technical users.
]]> ]]> ]]> The application addresses the problem of limited access to personalized, diverse, and engaging story content, especially for children from various cultural and linguistic backgrounds. By integrating advanced AI services, the platform generates unique stories based on user-provided inputs such as title, age group, genre, and illustration style. Using technologies like Google AI, Hugging Face’s text generation models, and custom text-to-speech tools, the system delivers cohesive narratives paired with AI-generated visuals and narration. The backend is developed using Node.js and Express.js, while the frontend is built with React.js, offering a responsive and user-friendly interface. Data is securely stored and managed using a Drizzle ORM with a PostgreSQL database.
Results show that the system can produce high-quality storybooks with consistent plots, age-appropriate language, and stylized imagery, enhancing the reading experience. The platform also includes features like story exploration, user account management, coin-based generation limits, and payment integration for purchasing additional credits.
In conclusion, the AI Storybook Generator showcases the potential of merging generative AI with interactive design to promote literacy and creativity in young users. Future work may involve mobile app development, multilingual support, story sharing features, and integration of educational objectives into story structure. The application serves as a scalable, customizable tool for families, educators, and storytellers worldwide.
]]> ]]> It implements a Retrieval-Augmented Generation (RAG) system designed to streamline information access at International Burch University. The system features a multi-layered architecture combining semantic search and generative AI. Vespa.ai serves as the vector database enabling high-performance similarity search, while OpenAI’s GPT models handle natural language understanding and generation. MongoDB is used for session tracking and user state management. Documents in PDF, TXT, and web-based formats are ingested through a pipeline that performs scraping, text extraction, and chunking using LangChain’s RecursiveCharacterTextSplitter. The system is accessible via a modern web interface built with React.js, Vite, and Tailwind CSS, and also exposes a FastAPI-based REST API for backend interaction. Secure access is enforced using JWT-based authentication and authorization. The chatbot component retrieves relevant context through semantic search and maintains coherent multi-turn conversations using conversation history tracking.
The developed system significantly improves the accessibility and efficiency of retrieving university information. It provides fast, context-aware responses to user queries by combining robust retrieval techniques with generative language models.

The web-based interface ensures ease of use for both technical and non-technical users, while the modular backend supports scalability and maintainability. Intelligent query rephrasing and optimized chunk retrieval contribute to improved precision and user satisfaction. Overall, this solution demonstrates how RAG-based systems can transform information access in academic environments by offering a centralized, intelligent platform tailored to users' needs.
]]> ]]> To achieve this, a publicly available dataset of labeled tweets was processed through a detailed pipeline involving data cleaning, normalization, and transformation. Text preprocessing steps such as removing URLs, mentions, hashtags, and punctuation, followed by tokenization, stopword removal, and lemmatization, were essential to reduce noise and standardize the input. The cleaned data was then vectorized using Term Frequency-Inverse Document Frequency (TF-IDF) to represent tweets numerically, enabling machine learning algorithms to extract meaningful patterns.
The preprocessed dataset was used to create and train a number of classification models, including Logistic Regression, Support Vector Machines, Random Forest, Naive Bayes, and many boosting methods like XGBoost, LightGBM, and CatBoost. The Synthetic Minority Over-sampling Technique (SMOTE) was used during training to address class imbalance and improve the model's detection of minority classes, including hate speech.

A broad range of metrics, such as accuracy, precision, recall, F1-score, and confusion matrices, were used to assess performance in order to provide an objective and fair assessment for each class. By demonstrating how NLP and ML techniques may be used to more efficiently detect hate speech, this research supports continuing attempts to automate content moderation. It also lays the foundation for future developments in the discipline by identifying important difficulties in managing complex language and contextual uncertainty.
]]>