Nature-Inspired Algorithms for Reliable, Low-Latency Communication in Wireless Sensor Networks for Pervasive Healthcare Applications

Abstract

With the growing popularity of IoT paradigms, the number of connected medical equipment is on the rise and includes a variety of products ranging from simple devices such as thermometers to more complex machinery like smart infusion pumps, patient monitoring systems, and MRI scanners, to name a few. The advantages of such interconnected architectures are manifold, enabling better access to patients’ electronic health records, and improving the quality of care through real-time monitoring systems. However, a healthcare facility packed with medical appliances could face issues such as dropped network connections, power loss, and failure in the transmission of critical alarms. In pervasive healthcare applications, such incidents could result in disastrous consequences and are non-negotiable. Wireless sensor networks for healthcare have emerged in the recent years due to advances in sensor technology and the pressing need for the design of reliable, low-power networks. The most important key in WSN design is the task of finding the optimal path for transmission of sensor data to achieve energy efficiency and reduce costs, while catering to the needs of the application. Nature is arguably the best coach and extracting eccentric elements of biological network design proves useful in solving complex problems. Computations using nature-inspired algorithms have emerged as a new epoch in computing, serving a varied range of applications. This paper explores the need of optimization in WSN design for pervasive healthcare systems, while studying the existing class of bio-inspired algorithms and routing protocols for reliable communication in such architectures. Further, a detailed study is conducted to identify the challenges in routing sensitive data over a cluster of light, portable sensing motes, and application-specific nature-inspired models are suggested based on the observations.