Table 1 Features and challenges of state-of-the-art Sdn-based edge computing in Iot-enabled healthcare system.
Author [citation] | Methodology | Features | Challenges |
|---|---|---|---|
Li et al.25 | AI | It results in low latency, packet delivery ratio, and average response time | It protects the privacy of patients along with their data |
It offers better intelligent decisions | |||
Wang and Cai26 | NDN | It returns less complexity | It does not use the cluster head reelection mechanism |
It helps the security of medical data delivery | |||
Rahman et al.27 | Blockchain | It avoids the limitations of the high bandwidth | It does not minimize the off-chain storage time |
The leveraging of immutabilities of metadata is permitted | |||
Alabdulatif et al.28 | FHE | It analyses and stores the data in an encrypted format | It cannot be used for the advanced data mining models |
It preserves a high level of data privacy as well as analysis accuracy | |||
Elmisery et al.29 | Fog-based middleware | It enhances the privacy | The experiments are not performed on several real datasets from the UCI repository |
It minimizes the mean absolute error | |||
Jayaram and Prabakaran30 | SECHS | The cost of resource provisioning is reduced at the cloud layer | It does not deal with the transmission protocol and edge-to-edge secure object tracking |
It reduces the network capacity as well as the response time | |||
Chen et al.31 | ECC | It provides a better user QoE | It does not construct an emotional recognition system |
It reasonably optimizes the computing resources | |||
Umar and Hossain32 | AI | The edge computing services are enhanced for the healthcare | It does not address the information processing management as well as the local storage |
It identifies the challenges and demands of distinct application scenarios |
