Browsing by Author "Hossain, Md Golam Sorwar"

Filter results by typing the first few letters
Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    AI stethoscope for heart murmur detection and classification
    (BRAC University, 2026-01) Fahi, Fariyan Shah; Ahmed, Muntasir Abdullah Bin; Datta, Abhishek; Husam Uz-Zaman, S.M; Hossain, Md Golam Sorwar; Kabir, Md. Saif; Jalal, Junaid
    Cardiovascular diseases remain a leading cause of mortality in Bangladesh, exacerbated by a critical shortage of pediatric cardiac specialists in rural regions. This project presents the design and implementation of a low-cost, Cloud-Connected AI Stethoscope aimed at democratizing cardiac screening. The system integrates a dual-microphone setup with Active Noise Cancellation (LMS algorithm) to capture high-fidelity heart sounds, achieving a Signal-to-Noise Ratio (SNR) improvement of +12.6 dB even in noisy clinical environments. Captured audio is digitized by an ESP32 microcontroller and transmitted via Wi-Fi to a cloud server, where a Fusion Convolutional Neural Network (CNN) detects and classifies heart murmurs with 91% accuracy. By offloading computation to the cloud, the device maintains a low unit cost of approximately 5,650 BDT while ensuring diagnostic reliability. This solution offers a scalable, affordable tool for frontline health workers to identify cardiac risks early, potentially reducing preventable deaths in underserved communities.
  • Thumbnail Image
    Item
    Smart gas leakage detection and management system
    (BRAC University, 2025-09) Jannat, Raiyan; Begum, Fatema; Khan, Mansia Samrana; Rahman, Fardeen; Hossain, Md Golam Sorwar; Kabir, Md. Saif; Jalal, Junaid
    Liquefied Petroleum Gas (LPG) is widely used in Bangladeshi households, but its high flammability makes LPG leakage a critical safety concern. Very few detection systems exist, and the conventional ones are often expensive, grid-dependent and limited to alarms. This project presents a solar-powered smart gas leakage detection and management system for residential kitchens. The prototype integrates dual gas sensors (MQ-2, MQ-6), Arduino Uno controllers, GSM-based remote alert, Bluetooth-enabled subsystem communication, automatic ventilation through an exhaust fan and linear actuator and a solenoid valve to cut off gas supply. The batteries of the entire system are solar-charged and ensure continued operation with no human intervention. Testing under simulated leakage conditions confirmed accurate detection at a 2000 ppm threshold, rapid activation of safety measures, and stable performance for up to three hours on solar backup. Therefore, the system demonstrates a cost-effective, sustainable solution to improve household gas safety.