AI Engineer building HealixAI 🧠 | Agentic AI & ML projects solving real-world problems

github

Zahed Shaikh  • Peerlist

HealixAI is an AI-powered healthcare assistant that predicts possible diseases based on user-provided symptoms. It supports both manual and voice input, providing intelligent, real-time analysis along with confidence scores.The system focuses on accessibility and usability with a clean, interactive UI and intent-aware chat system. It aims to assist users in early diagnosis while promoting awareness and informed decision-making.HealixAI is designed as a scalable solution with potential integration into telemedicine and healthcare platforms. Disclaimer: This system is not a substitute for professional medical advice. Always consult a qualified healthcare provider.

HealixAI – AI-Powered Healthcare Assistant

Developed a web-based AI application for preliminary health assessment using an SVM classifier trained on symptom–disease datasets. Supports manual and voice-based symptom input with real-time predictions. Enhanced predictions with structured outputs including descriptions, precautions, medications, diet, and workouts, delivered via a clean Flask + Bootstrap UI. Designed with a modular, extensible architecture for future model and API integrations.

MediAI – AI Health Assessment System

Built an end‑to‑end pipeline to group customers by behavior and demographics—engineering RFM features, selecting the optimal cluster count via the Elbow Method, and profiling segments like “High‑Value Loyalists” and “Occasional Bargain Shoppers.” Deployed an interactive Streamlit dashboard and Flask API so business teams can explore segments, export reports, and drive targeted marketing campaigns. 🚀

Customer Segmentation with K‑Means

The Fraud Message Detection System is a machine learning and NLP-based project designed to classify text messages as either Spam (fraudulent) or Ham (legitimate). The system uses a well-known labeled dataset (SMS Spam Collection) containing thousands of real-world text messages annotated for spam detection tasks. This project demonstrates a complete end-to-end pipeline for text classification, beginning with data preprocessing, including lowercasing, stopword removal, stemming, and vectorization (TF-IDF or CountVectorizer). The processed text is then fed into a machine learning model—commonly a Multinomial Naive Bayes or Support Vector Machine (SVM)—trained to distinguish spam messages from genuine ones. The model is evaluated using performance metrics such as accuracy, precision, recall, F1-score, and confusion matrix. Visualizations are created to show insights about data distribution, spam frequency, and word frequency patterns using matplotlib and seaborn. This system can be integrated into real-world messaging platforms to improve security, reduce fraudulent communication, and enhance user experience by automatically filtering spam. Built using Python, it leverages powerful libraries such as scikit-learn, nltk, pandas, and matplotlib. Whether used for academic purposes or real-time deployment, this project offers a solid foundation for text classification and NLP applications in fraud detection.

Fraud Message Detection System

<h3>MediAI — AI-powered preliminary health assessment platform</h3>MediAI is a modular web application that delivers fast, AI-driven preliminary health assessments from user-reported symptoms. The core prediction engine uses a supervised classifier (configurable; default: Support Vector Classifier) trained on symptom→disease mappings. Users submit comma-separated symptoms or dictate them via speech; inputs are normalized and encoded as a fixed-length binary feature vector before being scored by the preloaded model. Results include ranked diagnoses with probability/confidence scores and are augmented by five editable, CSV-driven content sections: Description, Precautions (four concise measures), Medications, Dietary Advice, and Workouts.Architecture &amp; responsibilities<ul><li>Model layer: model loading, prediction API, evaluation utilities (pluggable model support).</li><li>Content/data layer: editable CSV lookups for condition metadata and guidance content.</li><li>Input processing: text normalization, speech-to-text integration, vectorization into fixed-length binary arrays.</li><li>Presentation layer: Flask + Bootstrap front end with a modern glassmorphism UI (translucent cards, gradient accents, smooth fade-ins).</li><li>Deployment: production-ready under WSGI (Gunicorn) and containerizable with Docker.</li></ul>

MediAI

🧠 Shaikh Zahed – AI/ML Engineer Portfolio 🚀 Built a responsive, animated, and modern personal portfolio website using HTML, CSS, and JavaScript to showcase my skills in AI, Machine Learning, and Computer Vision. 💻 Designed with a futuristic glassmorphism + cyberpunk theme, the site highlights my academic background, core tech stack (Python, PyTorch, TensorFlow, OpenCV, etc.), and key AI/ML projects like: 🩺 MediAI – Health Diagnosis using ML ⚠️ Message Fraud Detection using NLP 🎯 Features include: AOS animations and particle.js effects Skill chips, smooth scroll, and interactive hover UI Fully mobile-responsive and ready for GitHub Pages/Netlify deployment 🔗 Visit my portfolio: [Add your live link here] 📌 Technologies: HTML, CSS, JS, AOS, Particle.js, Flask (backend projects)

My_Portfolio

This is a project for my college, designed to demonstrate an efficient and user-friendly online bus reservation system. The system allows customers to easily book bus tickets for various routes, select preferred seats, and view real-time schedules. The project focuses on streamlining the booking process, providing a simple, secure platform for travelers to plan their journeys. With features like instant booking confirmations, payment integration, and live updates, the system aims to enhance the convenience and experience of bus travel. Fast, reliable, and accessible, this project reflects modern solutions for everyday travel needs.

Online Bus Reservation System

This is a project for my college, showcasing an online clothing store concept—[Store Name]. The store aims to offer a wide range of trendy and versatile clothing, from casual wear to special occasion outfits, all curated to cater to different tastes, sizes, and budgets. The project focuses on creating a seamless online shopping experience, allowing customers to easily browse and shop for fashion-forward items from the comfort of their own homes. Fast delivery and excellent customer service are key features of this concept, designed to make online shopping convenient, fun, and accessible for everyone