Pampa Debnath, Diptadip Barai, Rajorshi Mandal, Ayeshee Sinha, Jeet Saha, Arpan Deyasi,
Volume 20, Issue 2 (June 2024)
Abstract
A novel architecture is proposed in the present paper for detection and monitoring of air pollution at real-time condition following industrial standard, embedded with gas sensors which are able to identify both organic as well as inorganic hazardous contents. A vis-à-vis comparative analysis is carried out with existing literature highlighting cons of most referred circuits, both in component, system and power consumption levels, and a generalized drawback is reported citing their inefficacy for real-time data collection and accuracy level. Detailed review is reported based on qualitative assessments also, and henceforth, justifies the significance of the proposed design; where not only higher ranges of detection are possible, however is also associated with lower power consumption (26.41% and 10.71% respectively compared to the two latest circuits) and finer detection of dust particles even at extremely low concentration. The architecture will help to implicate precautionary steps at real-time condition for controlling the harmful effect in Society.
Arpan Deyasi, Diptadip Barai, Pampa Debnath,
Volume 22, Issue 0 (In Press 2026)
Abstract
The present paper introduces a real-time intelligent assistive system that uses a pre-trained Artificial Intelligence (AI) model to estimate relative distance and detect common items/living beings and known people to help visually impaired people. A lightweight and accurate object identification framework based on YOLOv8 algorithm is used in the proposed system and tailored for embedded and portable devices for facilitating real-time detection. The system continually analyses live video data, recognizes objects and people within its range of vision, even moving towards the impaired with a significant relative velocity; and uses depth mapping or stereo vision algorithms to determine their relative distances. Relative distance is measured with accuracy varying from 98.66% to 99.8% for static objects and 98.67% to 99.47% for dynamic objects and both indoor and outdoor environments, with maximum variance of 1.21 and 5.76 respectively for static and moving objects, far superior compared to earlier results for more than 200 cm distance. With approximate 30% improvement in confidence score for static objects with 2.5% enhancement in mean average precision and 15% improvement in FPS, the proposed study presents a practical and scalable assistive solution that integrates AI perception and distance awareness to support independent navigation for visually impaired users.
