The pervasiveness of wireless sensor networks has made them appropriate for a wide range of critical applications, including environmental surveillance, health monitoring via implantable sensors, weather forecasting, and a variety of other scenarios. Because of the hundreds of thousands of tiny sensor nodes that exist in the networks, crucial challenges such as computation time, limited memory, and energy are more widespread. In this case, the network's lifespan is entirely dependent on how well available resources are utilised. The technique of grouping sensor nodes that are close together into clusters is useful for cluster administration and network longevity. At this point, swarm intelligent and evolutionary algorithms related to the NP-complete problem are being investigated in order to find a better optimal solution. A Hybrid Artificial Bee Colony and Bacterial Foraging Algorithm-based Optimized Clustering (HABC-BFA-OC) is proposed in this paper for improving sensor network lifetime. The benefits of Bacterial Foraging Optimization are integrated in this suggested HABC-BFA-OC technique in order to improve the local search potential of the ABC algorithm and achieve maximum exploitation and exploration over the parameters evaluated for cluster head selection. During its research with a varying number of sensor nodes, simulation trials of the suggested HABC-BFA-OC technique confirmed an increased network lifetime with reduced energy usage. As a result, depression and anxiety symptoms are reduced. To ensure that the breathing patterns are correct, the KNN, SVM, Random Forest, and Decision Tree algorithms are used.
Author (S) Details
Bandi Rambabu
CSE, CVR College of Engineering, India.
View Book :- https://stm.bookpi.org/NAER-V12/article/view/3842
No comments:
Post a Comment