Muhammad Mazhar@mazhar
2
Events attended
2
Submissions made
3+ years of experience
About me
Data Analyst/Machine Learning Engineer with strong analytical skills and proficiency in Python, TensorFlow, and PyTorch. Successfully applied these skills in impactful projects. Holds an MBA and a Bachelor's in Electronics Engineering. Eager to leverage technical expertise to drive innovation and insights as a Python developer or Machine Learning Engineer or Data Analyst.
🤝 Top Collaborators
🤓 Latest Submissions
BreathGuard AI- Agentic AI System for COPD Care
Long Description: BreathGuard AI addresses one of the world’s most urgent health challenges: Chronic Obstructive Pulmonary Disease (COPD), the third leading cause of death globally. Current care models often fail because they are reactive — patients only receive help once symptoms worsen. Our solution shifts the paradigm to proactive and preventive care. Using multi-agent intelligence, BreathGuard AI integrates continuous monitoring of patient vitals with environmental risk data to predict potential exacerbations before they become emergencies. Patients interact naturally with the system using voice-based symptom logging, while a personalized coaching agent guides them on daily routines such as inhaler use, breathing exercises, and activity management. In critical situations, automated alerts instantly notify caregivers or clinicians, ensuring timely response. Beyond patient care, the platform’s design supports hospitals, insurance providers, and healthcare networks with scalable AI-driven tools. By combining predictive analytics, intelligent coaching, and seamless emergency escalation, BreathGuard AI empowers patients to live more confidently while reducing hospitalizations and healthcare costs.
21 Sep 2025
SightGuide
Vision & Mission Empowering visually impaired individuals through a free intelligent navigation assistant using offline multimodal AI as "intelligent eyes." Born at co-creating-with-gpt-5, we enhance safety and autonomy with real-time descriptive audio feedback. Problem Statement Navigating spaces presents challenges for visually impaired people. Unexpected obstacles like benches, signs, and barriers pose safety risks. Traditional aids may miss head-height obstacles or optimal navigation paths. Solution Overview Combining smartphone camera with two-tiered AI architecture: Constant Scanning: MediaPipe continuously monitors video feed Intelligent Analysis: ChatGPT-5 triggers when objects detected Actionable Advice: Natural language descriptions with safe navigation suggestions Audio Feedback: Text-to-speech alerts Key Features Real-time obstacle detection and contextual scene analysis Natural language audio alerts with navigation guidance Efficient two-tiered architecture optimizing battery life Accessible technology with TalkBack, haptic feedback, high-contrast mode Fall Detection & Alert Management: Real-time fall detection with auto-alert emergency contacts via call/email Agentic Workflow: Autonomous operation from video to insights with multi-stage AI agents Live Monitoring Dashboard: Real-time video streams with timeline playback Intelligent Analysis Reports: JSON reports with timestamps, frame analysis, confidence metrics CCTV Integration: AI-powered event detection transforming standard cameras into proactive monitoring systems Technical Architecture CameraX captures continuous video. MediaPipe provides fast object detection. ChatGPT-5 analyzes critical events, generating descriptive guidance converted to speech with cooldown logic preventing user overwhelm.
24 Aug 2025
