ABSTRACT
Routing has become a predominant constraint in wireless networks because of no sufficient power supply in the sensor node. Low transmission bandwidth requires less memory and reduced data limit. These sensors are distributed randomly in nature and each sensor node gathers data for further analysis and hence additional processing is required for transmitting the information to the base station. The objective of the chapter is to develop the optimization algorithms for smart healthcare devices which address the issues like energy consumption, malfunction capacity, and scalability. Using the on-hand graph edges, the current analytical model routing issue could be described as a method to decide the lowest cost route beginning at the origin vertex and covering all target verticals. This chapter discusses about the various algorithms to be developed for routing protocols in WSNs for developing smart healthcare devices. Wide selection of features in wireless sensor nodes, like optimal routing, has minimized the cost and delay-aware communication. The technologies are developed using learning to take the appropriate routing decisions to the changes in the sensing environment. A wide range of machine learning (ML)-based routing protocols with distributed regression (DR), self-organizing map (SOM), and routing have been there using reinforcement learning (RL). This chapter is structured in a way that suggests network characteristics and evaluation gradually viewed over time.
