Abstract
•This research explores machine learning techniques in providing quality-aware data acquisition with reliable computing devices.•Extracted the devices' information in terms of their updated factors and offer an intelligent learning strategy with low-cost processing.•Used simple cryptographic techniques for secure collaboration of all devices with dual authentication to protect data retrieval.•Finally, simulations are verified to validate the proposed system under dynamic and unpredictable situations.
Wireless communication systems offer a dynamic infrastructure with efficient data sensing and forwarding services using digital networks and the Internet of Things (IoT). Many schemes have been proposed to cope with a smart communication system by integrating medical devices. However, lowering the processing overheads with efficient utilization of network services are challenging tasks. Thus, this paper presents a smart health analysis system using machine learning techniques for IoT network, which aims to handle big data with balancing the communication load for green technologies. Firstly, using regression prediction, the proposed system offers quality-aware services, secondly, by exploring intelligent methods it provides a delay-tolerant scheme to give the least overhead communication paradigm using mobile agents. Finally, the big data is secured using cryptographic techniques and collaborative devices to maintain its trustworthiness with the cloud. The proposed system has revealed a noteworthy performance in terms of network parameters against existing studies.
[Display omitted]