Hotel Management System
· Developed a user-friendly website for hotel bookings across different locations.
· Developed a comprehensive hotel management system using Java, NetBeans showcasing proficiency in software development.
· Implemented core functionalities including guest management, room reservations, billing, and inventory control, demonstrating strong programming skills and attention to detail.
· Enabled users to select accommodations based on the best deals available.
· Leveraged NetBeans IDE for Java development and utilized Swing framework to design an intuitive graphical user interface, highlighting expertise in Java development tools and GUI design principles.
· Successfully integrated MySQL database using JDBC to ensure efficient data storage, retrieval, and management, showcasing proficiency in database integration and connectivity.
· Collaborated with a team of two to create the hotel management database system.
Cake shop Management System
· Designed and developed an application allowing users to order customized cakes with various flavors and shapes for home delivery.
· Utilized HTML and CSS for front-end design, SQL for database management, and PHP for server-side scripting.
· Collaborated with a team of two to create a seamless ordering experience for customers of the cake shop.
Prediction of terrorism activities using machine learning algorithms
· Implemented a project focused on applying machine learning techniques to analyze the characteristics of terrorist attacks, perform quantitative analysis, and make predictions.
· Developed a classification framework utilizing ensemble learning to classify and predict terrorist organizations.
· The framework comprised four key steps: data preprocessing, data splitting, construction and training of multiple ensemble learning classifier models, and testing of classifier models.
Object detection
· Developed a flower classification system using TensorFlow's convolutional neural network (CNN) to accurately classify 3,670 flower images.
· Implemented data preprocessing techniques to prepare the diverse dataset, followed by the design of a CNN architecture comprising convolutional layers, pooling, and dense layers.
· Employed methods like data augmentation and dropout to enhance model generalization and mitigate overfitting, achieving commendable accuracy.
· Identified opportunities for improvement including addressing class imbalances, refining network architecture, and potentially incorporating transfer learning to optimize model performance.
