Machine Learning Engineering Projects in SuratMachine Learning Engineering Projects in Surat
Projects
People
Cover image for Antidote- Healthcare  ◆ Context & Challenge The
Antidote- Healthcare  ◆ Context & Challenge The client needed a scalable digital healthcare platform to provide affordable and accessible medical services through a virtual-first model. The challenge was to deliver reliable, real-time telehealth services while ensuring data security, clinical accuracy, and seamless patient-doctor interactions across web and mobile platforms. ◆ Approach & Solution We developed an AI-powered telehealth platform that enables patients to access medical care, connect with clinicians, and manage their health digitally through a unified and secure system. ◆ Key focus areas: ‣ AI-assisted patient screening and clinical decision support ‣ 24/7 access to virtual healthcare services ‣ Seamless video consultation and communication workflows ‣ Integrated system for appointments, prescriptions, and records ‣ Scalable and secure healthcare infrastructure ◆ Execution ‣ Built telehealth platform for real-time video consultations ‣ Developed AI-driven symptom screening and support systems ‣ Implemented patient management for appointments and records ‣ Created secure infrastructure compliant with healthcare standards ‣ Designed scalable architecture for continuous care and access ◆ Outcome & Impact The platform enables patients to access quality healthcare services anytime, anywhere, at an affordable cost. ‣ Improved access to primary and urgent care services ‣ Reduced healthcare costs through virtual-first approach ‣ Enhanced patient experience with seamless digital interactions ‣ Enabled continuous care for chronic and preventive health needs ‣ Scalable solution supporting growing patient demand
0
77
Cover image for FrostGuard AI – Cold Chain
FrostGuard AI – Cold Chain Monitoring & Predictive Rerouting Overview FrostGuard AI is a real-time cold-chain logistics platform built by Team Red Dragon during a hackathon. It monitors a simulated fleet of medical cargo trucks, predicts temperature breaches before they happen using trained ML models, and recommends the nearest cold-storage facility when a shipment is at risk — all rendered on a live geospatial dashboard. Core Capabilities Predictive Breach Detection: An Isolation Forest anomaly detector and a HistGradientBoosting-based forecaster (frost_ml.py (http://ml.py), trained via train_model.py (http://model.py)) flag abnormal temperature patterns and forecast breach risk 30 seconds ahead. The trained model is serialized once (frostguard_ml.joblib) and loaded at boot rather than retrained on every startup — keeping cold starts fast on resource-limited hosts. Nearest-Facility Rerouting: A K-Nearest Neighbors model (scikit-learn) matches an at-risk truck's GPS position to the nearest of 16 cold-storage nodes across India, so operators get an immediate reroute recommendation rather than raw coordinates. Cached Road Routing: Driving paths between cities are fetched from the OSRM routing engine and precomputed once (precompute_routes.py (http://routes.py) → routes_cache.json), removing a live external API dependency from the app's boot path. Interactive Dashboard: main_dashboard.py (http://dashboard.py), built with Streamlit, gives operators a live map, fleet metrics, alerts, and a manual failure-injection tool for demoing breach scenarios. Optional Standalone Services: api.py (http://api.py) (FastAPI) and Bridge.py (http://Bridge.py) (Flask) provide REST endpoints for telemetry ingestion, and Bridge.py (http://Bridge.py) includes a Discord webhook integration that posts an alert when a truck goes CRITICAL — opt-in via a DISCORD_WEBHOOK environment variable. These run independently of the main dashboard and aren't required for it to function. Technologies: Python, Streamlit, scikit-learn (Isolation Forest, HistGradientBoosting, KNN), Docker, REST APIs, OSRM, Discord Webhooks.
0
54
Cover image for Aagami AI - Fintech Platform https://app.agami.ai/login
Aagami AI - Fintech Platform https://app.agami.ai/login (https://app.agami.ai/login)◆ Short Description: AI-powered enterprise platform for automating workflows, document processing, and contextual decision-making securely. ◆ About Project: Agami AI is an enterprise-grade agentic AI platform designed to automate complex business workflows using secure and context-aware artificial intelligence. The platform enables organizations to process internal documents, analyze enterprise data, automate operations, and generate intelligent insights while maintaining complete control over sensitive information and infrastructure. Built with an intelligent agent-based architecture, Agami AI integrates seamlessly with enterprise systems and databases to deliver accurate, scalable, and production-ready automation. The platform combines private AI models, workflow automation, and contextual data analysis to help businesses improve operational efficiency, reduce manual processes, and accelerate AI adoption securely. ◆ Context & Challenge: The client needed a secure AI platform to automate complex workflows using internal data. The challenge was ensuring accuracy, privacy, and seamless integration with existing systems, without the common issues of unreliable outputs or data exposure. ◆ Approach & Solution: We designed an agent-based AI system where intelligent agents handle tasks like document analysis, data querying, and decision support. ◆ Key focus areas: ‣ Private AI models trained on enterprise data ‣ Context-aware pipelines to improve accuracy ‣ Structured workflows for automation ‣ Secure deployment within controlled environments ‣ Integration with existing tools and databases ◆ Execution: ‣ Built AI agents for multi-step workflows ‣ Developed document processing and data analysis pipelines ‣ Implemented secure infrastructure for private AI usage ‣ Created integration layers for enterprise systems ◆ Outcome & Impact The platform enables businesses to automate workflows, process documents, and generate insights securely. ‣ Improved accuracy with contextual responses ‣ Reduced manual effort through automation ‣ Maintains full data control and compliance ‣ Ready to scale across multiple use cases
1
102