Abstract
— The rapid evolution of Internet of Things (IoT) technology has transformed traditional
healthcare systems by enabling intelligent, connected, and patient-centric healthcare solutions. Conventional healthcare monitoring relies heavily on hospital-centric infrastructure and periodic manual
observation, which leads to delayed diagnosis, increased operational cost, and limited accessibility, especially for elderly and chronically ill patients. The convergence of Internet of Things (IoT) and deep
learning technologies is reshaping modern healthcare by enabling intelligent, real-time, and remote
patient monitoring systems. Traditional healthcare monitoring methods rely heavily on hospital-based
equipment and manual observation, which are expensive, bulky, and unsuitable for continuous monitoring. These limitations hinder early disease detection and personalized treatment, particularly for
patients with chronic illnesses and elderly individuals.
This paper presents an IoT-enabled healthcare system and a medical remote monitoring framework capable of continuously monitoring multiple physiological parameters, including heart rate,
blood pressure, blood oxygen saturation (SpO2), and body temperature. The proposed system employs
wearable medical sensors interfaced with an ARM-based embedded platform for data acquisition and
preprocessing. Sensor data is transmitted remotely using a GPRS-based wireless communication module to a cloud infrastructure, where deep learning models such as CNN, RNN, and LSTM are used
for predictive analytics and anomaly detection. The system enables real-time alerts, predictive health
assessment, and remote medical intervention. Experimental results demonstrate improved accuracy,
reliability, and scalability compared to conventional monitoring systems. The proposed solution is
well suited for smart healthcare environments, chronic disease management, emergency response, and
personalized healthcare services.