Читать книгу Smart Systems for Industrial Applications - Группа авторов - Страница 33

Patients to rehabilitate at home are a common condition post-treatments or part of a few during which there is a possibility of relapse due to inadequate care. In today’s scenario, patients are provided with AI-powered wearable technology that enables remote monitoring once they have been discharged or in cases where equipment supports is required for treating them. It brings about significant benefits like early warnings of deterioration in patients to allow targeted interventions, also minimize administrative ordeal of hospitalization and readmission. A quick response to any fluctuation in health conditions is made feasible with IoT. Therefore, remote monitoring services become dependable round the clock.

Sensors used in IoT devices are linked together yet separately identified over a communication infrastructure [27]. IoT has three layers of communication: sensors that have the physical interface. This system provides connectivity and server where all the sensory data is stored and processed, as shown in Figure 1.8. The first two layers are simple and can be very cost-effective and predominately setup at the patient’s end. The third layer is traditionally a cloud where an array of services is provided with the help of AI algorithms performance big data analytics. The cloud layer is interconnected with local layers through the multi-hop network, making it susceptible to challenges of reliability, availability, and soundness. With varying latency and bandwidth, traditional cloud computing architecture needs to be reviewed as the patient is the end-user, and in emergencies, establishing connections could have adverse effects. In remote healthcare monitoring, there is always an increase in the number of connected devices, and with it comes the sensory data, which could cause potential overload on the communication infrastructure. Currently, many types of research are underway to make this architecture effective, enabling layer two to pre-process using computational capabilities and close loop architecture. Allowing this layer creates a system where essential and critical services can be locally controlled and, in turn, reducing the load on IoT communication infrastructure through effective task and resource management.

Figure 1.8 IoT architecture for healthcare.

The overall objective was to minimize the effects of varying latency and bandwidth between gateways and servers here; it is the traditional cloud computing. It is tested with hierarchical computing architecture where existing machine learning methods can help in a fog-enabled IoT system. At a local level, it explores the feasibility of delivering adaptive transmission of data inside a closed-loop environment [27].