The Internet has rapidly led to the development of Internet of Things (IoT) based health monitoring systems, such as advances in sensor technologies and the emerging thought applications of behavioral and physical monitoring systems. Nowadays, many patient lives are scattered over wide geographical areas alone, and it is necessary to monitor the status of their health function. This work proposes an IoT-based health monitoring model that monitors key symptoms and detects biological, behavioral changes through smart health technologies. In this model, sensitive data are collected via IoT devices. Data analysis is carried out using the Dynamic Rule Soft Signaling (DRSS) method, which detects the possible risks of patient physiology and behavior changes. The experimental results suggest that the proposed model meets efficiency and reasonable accuracy for detecting the patient condition. This research work also mainly focuses on the Electronic Health Record (EHRs) security requirements for storage discovery, accessing, sharing and audit monitoring in Cloud Healthcare System (CHMS) using Dynamic Attribute-Based Encryption (DABE) system. After evaluating the proposed model, the dynamic rule soft signaling method and dynamic attribute-based encryption (DABE) system have achieved the best accuracy of 97%, which is a promising result for the proposed method’s objective. Proposed methods' results outperformed fuzzy, adaptive neuro-fuzzy and Artificial Neural networks.