Portfolio

Introducing the 1D Music App - a sleek and intuitive music player designed with Material Design principles. Embracing simplicity and elegance, this app redefines your music listening experience with its seamless interface and robust functionality.

Key Features:

• Material Design Aesthetics: Immerse yourself in a visually stunning environment crafted with Google’s Material Design guidelines. The app’s clean and intuitive layout ensures effortless navigation, allowing you to focus solely on enjoying your favorite tunes.
• Dynamic Playback Controls: Take full control of your music with a comprehensive set of playback options. Play, pause, skip tracks, shuffle, and repeat effortlessly with intuitive gestures and touch controls, providing a seamless and enjoyable user experience.
• Personalized Library Management: Organize your music library exactly how you want it. Easily browse through your collection by artists, albums, genres, or playlists, ensuring that you can quickly find the perfect soundtrack for any moment.
• Smart Queue Management: Tailor your listening experience on-the-go with a customizable queue system. Easily add, remove, and rearrange tracks in the queue to create the perfect playlist for any occasion, whether it’s a relaxed evening at home or an energetic workout session.
• Beautiful Now Playing Screen: Immerse yourself in the music with a stunning Now Playing screen that showcases album artwork, track information, and playback controls in a visually captivating manner. Experience your music like never before, with smooth transitions and elegant animations.
• Customization Options: Make the app your own with a variety of customization options. Choose from different themes, color schemes, and accent colors to personalize the app’s appearance to suit your style.
• Experience the future of music playback with the 1D Music App - where simplicity meets sophistication, and every beat comes to life in stunning detail. Download now and embark on a journey of musical discovery like never before.

This project focuses on disease prediction, including liver disease, diabetes, and heart disease, through machine learning models implemented with XGBoost. Additionally, a healthcare chatbot is integrated to provide personalized health recommendations. The entire system is containerized using Docker and deployed on Google Cloud Run for seamless scalability. Users also have the option to run the system locally.

Key Features:

• Disease Prediction: Utilizes XGBoost and Python ML libraries to predict prevalent diseases, addressing health challenges in the Indian population.
• Healthcare Chatbot: Integrates NLP and OpenAI API techniques for interactive and personalized health recommendations.
• Dockerized: The system is containerized for easy deployment and management.
• Cloud Deployment: Utilizes Google Cloud Run for scalable and available healthcare services.
• Local Deployment: Users can run the system locally for testing and development purposes.

Cutting-edge dating platform designed to revolutionize your online dating experience. This app incorporates the latest technologies and best practices to ensure seamless interactions, enhanced security, and personalized connections.

Key Features:

• Identity and Role Management implemented.
• Data persistence with Entity Framework Core.
• Repository Pattern for abstraction over Entity Framework.
• Common error handling in Angular and .NET Core using Http Interceptors.
• AutoMapper integration in .NET Core WebAPI.
• Integration of third-party components like Alertify.js in Angular.
• Authentication secured with JWT tokens for WebAPIs.
• Lazy loading for efficient loading of related navigation properties.
• Filtering, sorting, and paging of data.
• Integration of drag-and-drop photo upload with Cloudinary.
• Implementation of a private messaging chat system.
• User profile liking functionality with Many-To-Many relationships.
• Global error handling in both API and SPA.
• Usage of ngx-loader for displaying loaders during HTTP requests.
• Routing secured with CanActivate and CanDeactivate guards.
• Resolvers used for passing data in routes.
• Utilization of Angular Reactive forms for form handling.
• Deployment to Azure platform.
• HTTPS certificate applied for secure communication.

In today’s fast-paced business environment, organizations face a significant challenge of retaining their employees. Employee Attrition, which refers to the loss of employees over time, is a critical issue that can have a significant impact on an organization’s productivity, profitability, and overall success. To ensure optimal employee productivity and quality of delivery, it is essential to have an effective employee performance management system in place. With the advent of Data Science and analytics, organizations can now leverage their vast amounts of data to gain insights into employee attrition and take corrective action. In this context, this background highlights the importance of employee performance management and the role of Data Science and analytics in analyzing relevant datasets to gain insights into employee attrition.

Key Features:

• The workflow for analyzing datasets involves identifying driving factors, visualizing data using tools like Power BI, and designing dynamic dashboards.
• Identification of relevant factors contributing to employee attrition is a key step in understanding retention issues.
• Data visualization aids in better understanding trends and patterns related to employee attrition.
• Dynamic dashboard design provides real-time insights into factors driving employee attrition.
• Actionable insights from data analytics help organizations implement targeted strategies to optimize employee productivity and retention.

A Recommendation System is a filtering program whose primary goal is to predict the “rating” or “preference” of a user towards a domain-specific element. In our project, this domain-specific element is a movie. Hence the main focus of our recommendation system is to provide a total of ten movie recommendations to users who searched for a movie that they like. These results are based on tags of the movie that has been searched. Content based filtering is a technique that is used to recommend movies. Apart from providing recommendations the system also provides posters, trailers/relevant videos of the Movies along with Release Date, Budget, Collection, Popularity, Similarity between selected Movie, Overview of Movie and More. The System uses the concept of vectorization based on common features and uses Cosine Similarity with respect to each other vectors to determine the most similar movies.

Key Features:

• Content-Based Filtering: Utilizes movie tags to recommend similar movies.
• Personalized Recommendations: Provides ten movie recommendations based on user preferences.
• Comprehensive Movie Information: Includes posters, trailers, release date, budget, collection, popularity, and overview for each * recommended movie.
• Vectorization and Cosine Similarity: Implements vectorization based on common features and calculates cosine similarity to determine movie similarities.
• User-Friendly Interface: Offers a seamless and intuitive interface for users to explore recommendations and movie details.
• Dynamic and Real-Time Recommendations: Recommends movies dynamically based on user searches and preferences.
• Multimedia Integration: Incorporates trailers and relevant videos to enhance the movie browsing experience.
• Additional Insights: Provides additional insights such as similarity scores between selected movies to aid decision-making.
• Scalability and Performance: Ensures scalability and performance optimization for handling large datasets and user traffic.
• Continuous Improvement: Incorporates feedback mechanisms to continuously enhance recommendation accuracy and user satisfaction.

Breast cancer is the most common form of cancer in women, accounting for 14% of all cancers in Indian women. About 90% of breast cancer patients live for at least 5 years after the cancer is diagnosed. When the breast cancer is detected early, the chance of survival is much higher. So, we are developing a tool for Calculating the Risk of Attaining Breast Cancer. The tool is supposedly going to help women understand their Risk of Attaining Breast Cancer and leading to understanding the special need of care.

Key Features:

• The tool utilizes advanced data insights derived from BRCA data and machine learning techniques, employing a random forest model as a classifier.
• Performance evaluation involves fine-tuning precision and recall metrics.
• Informatic applications will be available for mobile phones, Windows, and MacOS systems, facilitating accessibility to risk assessment.
• Ongoing efforts extend beyond risk assessment to include daily lifestyle changes for breast cancer prevention.
• Long-term aspirations include leveraging data imaging for enhanced diagnostics and analysis, with the ultimate goal of eradicating breast cancer fatalities.