An Improved SVM based Machine Learning Model for Efficient Energy Optimization in Wireless Sensor Networks

  • Sarita Simaiya, Umesh Kumar Lilhore, Shikha Maheshwari, Sanjeev Kumar Sharma

Abstract

There have been rising concerns well into the Wireless Sensor Networks during recent decades. Sensor nodes are power restricted within Wireless Sensor Networks. Furthermore, some of the significant development hurdles in WSNs seems to be to reduce the energy expended at either the sensor nodes. Machine learning encourages several pragmatic solutions that optimize resource usage as well as enhance network broadcaster's lifespan. Due to the extreme sensor's restricted resources as well as bandwidth limitations, sending almost all of the data directly to an access point further analysis including forming inferences becomes practically impractical.
Therefore the implementation of Machine learning strategies within WSNs seems to be important. These strategies will greatly reduce the level of transmission of data and also use the progressive taxation attribute of WSNs in just a trustworthy direction. The whole research article demonstrates an improved way of supporting vector machines for wireless sensor networks toward effective energy optimization. Get an efficient approach towards enhancing cross-voting validity using the K-NN framework will strengthen the SVM framework. Experimental analyses were carried out utilizing established approaches such as logistical regression as well as SVM and use the proposed I-SVM method, using numerous efficiency measurement factors.

Published
2020-05-17
How to Cite
Sarita Simaiya, Umesh Kumar Lilhore, Shikha Maheshwari, Sanjeev Kumar Sharma. (2020). An Improved SVM based Machine Learning Model for Efficient Energy Optimization in Wireless Sensor Networks . International Journal of Control and Automation, 13(4), 117 - 127. Retrieved from https://sersc.org/journals/index.php/IJCA/article/view/16057
Section
Articles