Debottam

Mood Tracker

nice work, really different and unique execution.

15 Puzzle Solver

Nice work!

Scam Detector

nice project! try adding a summary feature

Mood Tracker

A simple Python program that detects the sentiment of a short text and returns a matching emoji

15 Puzzle Solver

Welcome to 15-Puzzle GUI Solver, an interactive application designed to solve the classic 15-puzzle using advanced AI search algorithms with a graphical interface. Goal: Rearrange the 15 numbered tiles on a 4x4 grid to reach the ordered configuration (1-15 with empty space in the bottom-right corner). Features Interactive GUI User-friendly graphical interface built with Tkinter. Drag-and-click or keyboard navigation to move tiles. Real-time visualization of puzzle state. Advanced Solvers A* Search with multiple heuristics: Manhattan Distance Linear Conflict Misplaced Tiles IDA* (Iterative Deepening A*) for memory-efficient search. Step-by-step solution visualization. Real-Time Statistics Moves count Time taken to solve Heuristic cost display Customization Shuffle puzzle randomly Input custom puzzle configurations Choose different heuristics for AI solving How It Works Puzzle Representation: Internal 2D array represents the board state. Move Generation: Generates all valid moves from the current state. Heuristic Evaluation: Calculates cost using selected heuristic. Search Algorithm: AI searches for optimal solution using A* or IDA*. Visualization: Updates GUI for each move until the puzzle is solved.

Debottam's Personal Website

On the Achievements page, your certificates are PDF files, but you tried to include them as images. That causes the certificates to not load.

Dream Insights

💤 Dream Analyzer + Future Predictor Welcome to Dream Analyzer + Future Predictor — An intelligent Python-based tool that analyzes your dreams and predicts your future moods, challenges, or opportunities based on dream psychology and AI! ✨ Features Dream Analysis Predicts 10 key psychological factors from your dream description: Lucidity Emotional Intensity Realism Fear Level Joy Level Control Over Dream Symbolism Strength Memory Recall After Waking Strangeness Vividness Smart Mental Interpretation Provides detailed, human-style explanations for each predicted factor. PCA Visualization Projects your dream onto a 2D space alongside previous dreams, helping you see dream patterns visually. Dream Factor Bar Chart Displays a beautiful bar chart showing how strongly each factor appeared in your dream. 🔮 Real Life Prediction Based on your dream’s emotional profile, the analyzer predicts a possible upcoming event or advice for your waking life! 🛠️ How It Works Data Preparation A CSV file (dream_dataset.csv) containing past dream descriptions and their annotated psychological factors is used to train the model. Model Training Texts are vectorized using TF-IDF. A Random Forest Regressor (wrapped in MultiOutputRegressor) is trained to predict the dream factors. Input Your Dream When you input a new dream description, the model analyzes it and predicts the values for each psychological factor. Interpretation and Visualization The system explains what each factor means. It projects your dream in a PCA graph and shows a factor bar plot. Bonus Prediction The analyzer generates a random but smart "fortune" about your near future based on your dream factors!

Scam Detector

🛡️ AI-Powered Scam Message Detector An intelligent Python-based tool that identifies scam messages using a custom rule-based and machine learning model. Designed to analyze message patterns, assign scores to multiple scam indicators, and classify input as SCAM or REAL — all while explaining why. 📦 Features ✅ Classifies input messages as SCAM or REAL 🧠 Uses a custom-built feature extractor for: Money requests Urgency Grammar issues Suspicious links Upfront payments Celebrity references Reward offers Pressure tactics Unusual contact methods Official appearance fakes Unsecured sources Threats or blackmail 📊 Machine Learning classifier (Random Forest) 📈 Accuracy report with precision, recall, and F1-score

Plant Doctor

Nice idea, really impressive problem solving. keep it up.

Debottam's Personal Website

Overview My_Website is a clean and modern personal portfolio showcasing my skills, projects, achievements, and goals. It serves as a professional space to introduce myself and share my work with the world. Features Home Page: Introduction and personal overview. Achievements: Highlights of key accomplishments. Goals: A section outlining personal and professional objectives. Blog: A collection of articles, tutorials, or personal insights. Support: Contact information and ways to connect. Tech Stack Frontend: HTML, CSS, JavaScript

Plant Doctor

Plant Doctor: AI-Powered Plant Disease Detector Inspiration Over 50% of India’s population relies on agriculture for their livelihood. Yet, according to FAO estimates, plant diseases cause 20–40% yield losses worldwide, with some regions in India facing even higher rates. Early detection is critical, but access to expert plant pathologists is limited—especially in rural areas. I wanted to create an accessible, AI-powered tool to help farmers, gardeners, and students identify plant diseases quickly and accurately. What it Does Plant Doctor is an AI-based plant disease detection system capable of identifying over 38 plant diseases from leaf images with 99% accuracy, trained on a dataset of 60,000+ images. Users can simply upload a photo or use their device camera to get instant diagnosis results, along with brief treatment suggestions. Features include: Real-time plant disease detection and diagnosis Treatment recommendations and prevention tips Interactive plant health quizzes for agricultural education Disease encyclopedia for learning about plant illnesses How I Built It Collected and cleaned a large-scale dataset of plant leaf images, creating consistent metadata and captions for each class. Trained a deep learning model using PyTorch and ResNet18, optimized with transfer learning for high accuracy. Built the UI using Streamlit, combining image/camera inputs, instant predictions, educational tools, and chatbot support. Challenges We Ran Into Handling a massive dataset within limited computing resources. Managing time for metadata creation, training, and feature integration within the hackathon deadline. Fixing UI while the backend training was still in progress. Accomplishments That We're Proud Of Successfully trained a deep learning model on several classes of plant diseases. Designed a feature-rich, educational, and interactive platform. Created a tool that has real-world impact potential for both farmers and hobbyists. What We Learned Large datasets require not only computing power but also careful data labeling and cleaning. Balancing model accuracy with speed is essential for real-time applications. Hackathon timelines demand prioritizing critical features over perfection. What's Next for Plant Doctor Deploy the model to a mobile app for offline usage in rural areas. Expand dataset to include more crops and environmental conditions. Chatbot Integration UI Enhancing

This was widely regarded as a great move by everyone.