ARCHIVES
VOL. 8, ISSUE 1 (2024)
Adaptive neuro-fuzzy Inference System(ANFIS) localization model for enhanced position estimation in Wireless Sensor Networks
Authors
Amrin R Sheikh, Dr. Priya Vij, Dr. Sandeep Kadam
Abstract
Accurate localization plays a key role in the performance of Wireless
Sensor Networks (WSNs), especially when deployed in anisotropic environments
where irregular signal propagation leads to large positioning errors. In this
study, an Adaptive Neuro-Fuzzy Inference System
(ANFIS) based localization model is developed using Received Signal Strength
Indicator (RSSI) values as input and estimated node distances as output. The
proposed system integrates the learning ability of neural networks with the
linguistic reasoning of fuzzy logic and is implemented using a Sugeno-type
fuzzy inference structure. The model is trained using 100 RSSI samples, and
performance is evaluated using Root Mean Square Error (RMSE) and Relative
Localization Error (RLE). Simulation results demonstrate that the proposed
ANFIS model significantly improves localization accuracy compared to
traditional fuzzy and ANN methods. The RLE results show a decreasing trend as
the number of anchor nodes increases, and the bell-shaped membership function
delivers the lowest RMSE value among all tested configurations. The findings
confirm that the proposed ANFIS-based model provides an effective and scalable
solution for accurate localization in anisotropic WSN environments.
Download
Pages:36-39
How to cite this article:
Amrin R Sheikh, Dr. Priya Vij, Dr. Sandeep Kadam "Adaptive neuro-fuzzy Inference System(ANFIS) localization model for enhanced position estimation in Wireless Sensor Networks". International Journal of Advanced Engineering and Technology, Vol 8, Issue 1, 2024, Pages 36-39
Download Author Certificate
Please enter the email address corresponding to this article submission to download your certificate.