RSSI based Localization and Evaluation using Support Vector Machine

The wireless sensor network consists of several sensor nodes and anchor nodes with a sink node which stores and send the values to the user. The sensor nodes can place randomly or in a fixed positions in a network. The sensors are placed randomly then to know the environment the location or position...

Full description

Saved in:
Bibliographic Details
Published in2022 4th International Conference on Inventive Research in Computing Applications (ICIRCA) pp. 509 - 515
Main Authors Madhav, Ajay, K M, Akhil
Format Conference Proceeding
LanguageEnglish
Published IEEE 21.09.2022
Subjects
Confusion matrix
Estimation
F1-score
Localization
Location awareness
Machine learning algorithms
Precision
Recall
Received signal strength indication
Support
Support vector machine
Support vector machines
Training
Wireless communication
Wireless sensor networks
Online AccessGet full text

Cover

More Information
Summary:The wireless sensor network consists of several sensor nodes and anchor nodes with a sink node which stores and send the values to the user. The sensor nodes can place randomly or in a fixed positions in a network. The sensors are placed randomly then to know the environment the location or position of the sensor node should be known. Accurate positioning in sensor networks is the major concern in the current era. There are two types of techniques to localization: range-based and range-free. We present an RSSI-based localization approach based on Support Vector Machines in this study (SVM).We have collected RSSI values using the COOJA simulator. Here by implementing the anchor nodes and by using a machine learning approach to predict the position of the sensor nodes using the help of categorized RSSI values. Combining both technologies like localization and Machine Learning result an Accurate Output.
DOI:10.1109/ICIRCA54612.2022.9985716