Guest Editorial Special Issue on AIoMT-Enabled Federated Learning-Based Computing for Socially Implemented IoMT Systems: How Will Healthcare Systems Change?

The current advances in wearable sensors show the shining future of socially implemented Internet-of-Medical- Things (IoMT) devices (e.g., smartwatches). However, the recent machine learning approaches cannot be applied well in these devices, because almost all the processing in the IoMT devices is now being performed in classic forms (mainly as centralized computing) or based on cloud services. This topical collection has tried to extend our knowledge about how to apply collaborative learning to IoMT considering social edge/fog nodes’ facilities. Federated learning, also known as collaborative learning, with supervised and unsupervised solutions has become a hot subject area of distributed computing and can be used in various real-world problems for sustainable societies and cities, particularly when a centralized learning technology with cloud-based training procedures cannot respond to practical requirements. Although the recent developments of federated learning have contributed to the operation of systems with distributed sensors, actuators, processors, and communication devices, they have made new challenges concerning communications across social networks, management of heterogeneous systems in networked computing, and privacy concerns. One of the applications that has largely benefited from federated learning recently is artificial intelligence (AI) deployments for remote healthcare systems. It is anticipated that medical services will be provided remotely, for instance, remote surgery, wearable sensing to predict illnesses, and intelligent pervasive medical helps based on AI and social computing, all of which will require a fusion of distributed healthcare systems with high-performance computing, and computational intelligence.