Diabetes is a growing global health issue, and early prediction is key to preventing its effects. This thesis develops predictive models for diabetes using various machine learning methods, including Logistic Regression, Decision Trees, K-Nearest Neighbors (KNN), Random Forest, Support Vector Machine (SVM), and XGBoost, using the Diabetes Health Indicators dataset, which covers clinical, lifestyle, and demographic factors. Feature selection identifies the most important diabetic predictors, and model performance is evaluated using macro average and weighted average metrics, accuracy, precision, recall, F1-score, and error metrics (MSE and RMSE) to provide a thorough evaluation of model performance across the classes. Both SVM and Random Forest performed best overall, with an accuracy of 0.86. They also performed exceptionally well in weighted average and macro average measures, with overall recall and F1-scores of 0.86. SVM has the highest precision performance at 0.88, with Random Forest achieving the next best score of 0.87. These models are very dependable for diabetes prediction tasks because of their remarkable balance while handling both classes. SVM and Random Forest offer more dependable performance on a range of metrics, as evidenced by the weaker outcomes of Decision Tree, KNN, XGBoost, and Logistic Regression.

]]> Heart strokes remain one of the leading health risks in the world today. Timely prediction can significantly improve patient outcomes and healthcare resource allocation. This study aims to harness machine learning techniques to develop efficient predictive models for the early detection of heart strokes.
Research is based on a dataset created by combining different (five) datasets. The dataset encompasses patient demographics, clinical measurements, and historical medical records. The analysis focused on five machine learning models: Logistic Regression, Decision Tree, K-Nearest Neighbors, Random Forest, and Support Vector Machine.
The goal was not only to test different algorithms, but also to understand how data preparation, feature selection, and model choice impact the final results. The models were trained and tested on both the original dataset and an extended version, where new features were added by combining existing ones.
The results showed that models such as Logistic Regression, Decision Tree, and KNN performed better when applied to the original data. The Decision Tree model achieved an accuracy of 87.8% and an F1 score of 0.881, while Logistic Regression and K-Nearest Neighbors each attained F1 scores of 0.850 and 0.849, respectively. On the other hand, Random Forest and SVM showed significant improvements with the extended dataset. Random Forest performed the best overall, with an F1 score of 0.920 and an accuracy of 91.6% with enhanced results.
SVM also benefited from enhanced results, improving its F1 score from 0.892 to 0.879, which highlights how specific models can leverage additional features for improved generalization.
This tool could help detect risks earlier, allowing for timely interventions and prevention, thereby reducing the burden of strokes on healthcare systems and improving patient care. Limitations include data quality and availability, as well as potential bias in healthcare records.]]> Enterprise Resource Planning (ERP) systems are of immense importance in simplifying business operations. However, most ERP projects fail owing to the complexity and scope of the projects. The present research attempted to determine the outcomes of ERP projects by employing machine learning methods and addressing factors which determine whether projects fail or succeed. This dissertation obtained data from different aspects of the projects that included successful and unsuccessful ERP deployments in terms of within which industry, project magnitude, the level of budget and time exceeding, background of team experience as well as technical challenges faced amongst others.
The research includes machine learning methods such as logistic regression, decision trees, and random forests in order to assess the importance of the relevant predictors of any project. By training and testing these applications on a sample composed of both successful and non-successful ERP projects, the goal of the model is to seek for factors and patterns which could help in forecasting troubling tendencies. This research is aimed at devising a functional framework that can be used by project managers, enabling them to take action before issuing their project plans for ERP systems. Such a predictive model could significantly help in decreasing the rates of ERP failures and hence assist businesses in carrying out successful implementations and enhancing their returns on technology investment.]]> In this thesis, three generative models are compared for the task of weather based music generation; Conditional Variational Autoencoder (cVAE), a Conditional Generative Adversarial Network (cGAN) and Long Short-Term Memory (LSTM) network. Mentioned models are implemented and trained on combination of large MIDI corpus with historical weather information.
Performance of models in this paper are evaluated using metrics that capture musical diversity and quality, such as pitch range, unique pitches and pitch variance, and for fidelity to real data is measured by mean squared error and KL divergence. Results of the paper showed that the cVAE produced the most diverse music for music that is context sensitive. Building upon these findings, the thesis presents the architecture and functionality of a real time full stack application. This system acquires weather data, processes it through the cVAE and generates musical compositions. These compositions are then delivered and rendered through a web interface. This research shows the potential of combining environmental data with AI generated music and gives a framework for applications such as adaptive game soundtracks, mood-based music therapy, or dynamic background music systems that respond to the user's environment. Thesis also points out limitations of the models and gives future research directions in terms of hybrid architectures, richer environmental data representations, and user perception studies.]]> ]]> The system is designed as a full-stack application using React.js for the frontend, Node.js for the backend, and SQLite as the database. Core features include user authentication with role-based access, product and stock management, real-time transaction logging, sales tracking, and low-stock alerts. Backend logic is exposed via RESTful APIs, secured using JSON Web Tokens (JWT), and connected to a responsive user interface for efficient day-to-day usage.
The final version of the system is expected to provide full visibility into stock levels and sales performance, allowing admins and staff to carry out inventory tasks easily and securely. Features such as an analytics dashboard and a responsive design are planned to support future scalability and usability. The solution ultimately aims to reduce manual workload, minimize stock-related errors, and support data-driven decision-making in everyday business operations.
]]> ]]> ]]>
]]> Another key-point to the development of this app relates to the importance of marketing and social events on the effect of tourism. Many big cities today live off of the money created from tourism. Whether we like it or not, foreign people like to spend time in our cities and are more inclined to spend their money on as many events and traditions as they possibly can in the short amount of time they have. Sarajevo is no exception, as it has long stood as the “Jerusalem of Europe”, bringing in tourists from all over the world. Hence, It would be important to inform the tourists of the main attractions and places to spend their valuable time at.


Those two key-points make up the bulk of the idea behind this application: Create an online information system for tourists and locals to discover new events and places to spend their time at. Not only would it serve as a convenient tool to have at everyday disposal, but it would also allow for marketing and discovering lesser known events and places all in one place, along with many other useful features, ensuring everyone stays up to date with the current situation in Sarajevo.
]]> The platform was developed using React frontend with TypeScript, Laravel PHP backend with RESTful API, and PostgreSQL database. The system features a three-tier user system (Free, Premium, Premium+) balancing accessibility with sustainability. Key functionality includes advanced search and filtering by educational level, secure authentication, product management with image upload, shopping cart and wishlist features, order processing, and real-time notifications. Development followed test-driven principles using Playwright.
SchoolBooks demonstrates the viability of specialized C2C marketplaces using modern web development practices. The modular architecture supports future enhancements including mobile applications and recommendation systems, contributing to educational technology through accessible resource sharing.
]]> The development process was divided into several key phases: planning, design, implementation, and testing. The frontend of the application was built using standard web technologies such as HTML, CSS, and JavaScript to ensure responsiveness and clarity in design. On the back-end, PHP and MySQL were used to handle database interactions and user inputs, ensuring the dynamic functionality of the site. The initial phase involved a thorough analysis of user and business requirements, followed by the design of an efficient database structure to support product listings and user data. The completed application went through multiple testing iterations aimed at improving performance and optimizing usability.
The final outcome of the project was a fully functional, user-oriented web application that allows smooth interaction with the content. By centralizing the display of all available jewelry items, the platform helps maintain consistent data management while reducing operational costs and time. Moreover, the resulting digital storefront positions Blingho to enter broader markets with a polished and professional online image. Overall, the techniques and tools employed during the development proved effective in achieving the project’s objectives. Looking ahead, further enhancements could include the addition of advanced features and strengthened security protocols to support future scalability and user trust.
]]> ]]> The system is implemented using a standard web stack, with a PHP backend and a MySQL database. Frontend functionality is handled with HTML, CSS, and JavaScript. Key features include robust user authentication with email verification, secure payment processing via the Stripe API, and scalable image storage using Google Cloud Storage (GCS). A unique scam detection mechanism is integrated into the item posting process, which analyzes an item's attributes to suggest a fair market price, thereby safeguarding both buyers and sellers.
The results of the implementation demonstrate a fully functional e-commerce platform that successfully manages user accounts, item listings, and a secure checkout process.
In conclusion, "Fits 'n Finds" provides a dependable and user-friendly solution for the online apparel market. The project's success is attributed to its focus on security and transparency, creating a trustworthy environment for its users.
]]>