Showing 3 results for Internet of Things
Eisa Zarepour, Mohammad Reza Mohammadi, Morteza Zakeri-Nasrabadi, Sara Aein, Razieh Sangsari, Leila Taheri, Mojtaba Akbari, Ali Zabihallahpour,
Volume 20, Issue 3 (9-2024)
Abstract
Using mobile phones for medical applications are proliferating due to high-quality embedded sensors. Jaundice, a yellow discoloration of the skin caused by excess bilirubin, is a prevalent physiological problem in newborns. While moderate amounts of bilirubin are safe in healthy newborns, extreme levels are fatal and cause devastating and irreversible brain damage. Accurate tests to measure jaundice require a blood draw or dedicated clinical devices facing difficulty where clinical technology is unavailable. This paper presents a smartphone-based screening tool to detect neonatal hyperbilirubinemia caused by the high bilirubin production rate. A machine learning regression model is trained on a pretty large dataset of images, including 446 samples, taken from newborns' sternum skin in four medical centers in Iran. The learned model is then used to estimate the level of bilirubin. Experimental results show a mean absolute error of 1.807 mg/dl and a correlation of 0.701 between predicted bilirubin by the proposed method and the TSB values as ground truth.
Nasibeh Heshmati Moulaei, Seyed Ali Seyedalian, Alireza Sinaee Oskouie, Eisa Zarepour,
Volume 21, Issue 3 (8-2025)
Abstract
As the demand for continuous online remote monitoring of patients grows, the energy consumption of wearable home-care monitoring systems (WHMSs) requires careful evaluation. Selecting the right communication protocol therefore is crucial to minimize energy usage and extend device lifecycles. Recent versions of Bluetooth Smart (IEEE 802.15.1 are promising for WHMSs, offering low energy consumption and extended coverage range. However, their energy consumption in WHMSs remains underexplored. This paper investigates the energy consumption and maximum coverage range of Bluetooth V4.2, V5/1MB and V5/2MB in various home-care environments. We propose a software and hardware-based energy monitoring framework to practically measure the energy consumption of the protocols, conducting extensive experiments in typical home scenarios with obstacles like kitchen cabinets, brick walls, and the human body. Our results show similar power consumption for BLE v4.2 and BLE v5 modules, but the BLE v5/2MB has lower energy usage than BLE v5/1MB due to faster transmission. Additionally, obstacles significantly impact energy consumption and range, with BLE v5/1MB achieving a maximum range of 108m in line-of-sight conditions, which drops to 45m and 29m with brick walls and human bodies, respectively. Finally, the BLE v5/2MB effective range in all experimental scenarios is about 80% of BLE v5/1MB.
Kausar Ahmed, Bibhor Regan Gomes, S.m. Jobair Hossain, Emran Khan Musa, Fuyad Hasan Bhoyan, Md Humaion Kabir Mehedi, Jia Uddin,
Volume 22, Issue 3 (9-2026)
Abstract
Fires in indoor spaces such as residential and office buildings pose significant threats to human lives and property, causing substantial damage each year. Early and accurate fire detection plays a critical role in mitigating these risks and ensuring timely responses. However, conventional methods such as smoke sensors, temperature indicators, and standalone computer vision models suffer from limitations like false alarms, delayed detection, and high hardware demands. To address these challenges, we propose a novel three-layer verification framework for indoor fire detection to reduce false alarms, integrating smoke sensors, computer vision, and temperature monitoring into a multi-modal validation framework. The process begins with smoke sensors detecting potential fire incidents. The custom-trained YOLOv11n computer vision model verifies the detection using predefined thresholds, allowing immediate response without waiting for temperature escalation. If the computer vision model does not confirm the fire, the system initiates a temperature check as a final validation layer. Experimental evaluation of our model demonstrates a significantly high precision of 0.979 and a recall of 0.971. This layered approach ensures comprehensive detection, balancing reliability and resource efficiency. Our proposed hybrid AI-physical systematic framework demonstrates significant potential in reducing false alarms, improving detection accuracy, and prioritizing methodological scalability over industrial hardware. It lays the foundation for more reliable and energy-efficient fire safety solutions in smart buildings and industrial safety applications.
