SMART BILLING SYSTEM
The Queen Mall Billing System is a Python-based desktop application designed to optimize billing operations across multiple shops in a mall. It features a stylish, user-friendly interface integrated with MySQL, enabling itemized billing, speech-based item entry, QR code and manual code scanning, customer management with reward points, and seamless invoice generation. The system is built with advanced technologies like Tkinter, MySQL, and ReportLab, providing an efficient, streamlined solution for managing retail transactions.
Hotel Booking Cancellation Prediction System
The Hotel Booking Cancellation Prediction System uses machine learning (Logistic Regression) to predict the likelihood of hotel booking cancellations based on various features like lead time, number of guests, and booking date. It integrates a Streamlit dashboard for easy interaction, allowing users to input booking details and receive real-time predictions. Key features include data visualization of trends, cancellations by day, and feature importance analysis. This system helps hotel managers proactively manage bookings, reduce cancellations, and optimize occupancy rates.
Leave Management System with Face Recognition
This Leave Management System is a robust Streamlit application designed for educational institutions. It prioritizes security with an innovative face recognition feature for students to securely log in and submit leave requests. The platform offers tailored dashboards: students can easily apply for and track their leaves, while teachers (class in-charges and HODs) can efficiently manage and approve requests specific to their roles. The administrator has comprehensive control over user management, system-wide settings, attendance, and announcements, making it a complete solution for streamlined leave management..
ChildCare+ – AI-Powered Pediatric Health Companion
ChildCare+ is a smart pediatric healthcare web app built using Python and Streamlit, designed to assist parents and doctors in monitoring and managing a child’s health more effectively. It integrates AI-based predictions, smart alerts, and interactive dashboards to ensure holistic care for children.🔑 Key Features:✅ AI-Powered Growth Tracking – Predicts child’s height based on age, weight, BMI using Random Forest, and compares it with WHO standards.💉 Digital Vaccination Records – Personalized schedules with QR-coded immunization cards.💊 Medicine Safety & Reminders – Barcode/QR scanning for dosage and expiry tracking.😊 Mood & Behavior Analysis – Sentiment analysis on journal entries to track well-being.🚑 Emergency Location Alerts – One-tap SOS and nearby hospital locator simulation.This project demonstrates a fusion of machine learning, data visualization, and user-friendly UI/UX, aimed at making pediatric care more proactive and informed.
Symptom-to-Disease Prediction App
The Symptom-to-Disease Prediction App leverages machine learning to predict potential diseases based on the symptoms provided by the user. The app uses Logistic Regression for prediction, and it accepts symptoms through manual input or voice recognition. It includes a feature for generating word clouds to visualize the most common symptoms in the dataset. The app also showcases key metrics of model performance, such as accuracy and a detailed classification report. By offering an interactive, user-friendly interface, the app helps users quickly identify potential diseases based on symptom patterns.
DHIVYALAKSHMI M
"Where Curiosity Meets Code — Real Projects, Real Learning, Real Value."
Text