Soft Computing Techniques for Minimizing and Predicting Average Localization Error in Wireless Sensor Networks DOI Open Access

Srivani Reddy,

A. Kamala Kumari,

B. Satish Kumar

et al.

International Journal of Computational and Experimental Science and Engineering, Journal Year: 2025, Volume and Issue: 11(2)

Published: March 29, 2025

Localization methods are used to approximate the position of unknown nodes in a network. errors calculated by comparing estimated and true positions at each time step. Finding best network parameters minimize localization error during setup process while maintaining requisite accuracy short period remains difficult task. Both anchor strategically placed reduce problems, which addresses series issue. Soft computing approaches such as Fuzzy Logic Adaptive Neuro-Fuzzy Inference System (ANFIS) address this In study, number simulation area de facto for Average Error(ALE) training prediction. These feature values were obtained from simulations using modified centroid technique with Kalman filter. This work tries adjusting these soft techniques. The experimentation is carried out MATLAB, demonstrating suggested method's ability improve reliability wireless sensor networks.

Language: Английский

Improved DV-HOP Localization Algorithm Based on Grey Wolf Optimization DOI Creative Commons

Siqi Yang,

Xiao Hua Wang

Research Square (Research Square), Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 16, 2025

Abstract DV-HOP is a widely used localization algorithm, commonly applied in areas such as node Wireless Sensor Networks (WSN), deployment of Internet Things (IoT) devices, and navigation for mobile robots. However, the algorithm faces challenges practical applications, including cumulative hop count errors between nodes, inaccuracies estimated distances, computational bias introduced by least squares method when dealing with nonlinear problems. To address these issues, this paper proposes an improved based on Grey Wolf Optimization (GWO). By incorporating dual communication radii, weighted distance correction, (IGWO), proposed approach enhances accuracy nodes WSN. First, radii strategy utilized to refine improving estimations. Second, adjustment factor further correct minimum anchor resulting more precise average distances. Weighted optimization distances from unknown achieved using mean square error criterion. Finally, replaces solving coordinates nodes. Simulation results demonstrate that consistently achieves lower under various experimental conditions. Compared other methods, it provides higher accuracy, verifying its effectiveness advantages.

Language: Английский

Citations

1
Soft Computing Techniques for Minimizing and Predicting Average Localization Error in Wireless Sensor Networks DOI Open Access

Srivani Reddy,

A. Kamala Kumari,

B. Satish Kumar

et al.

International Journal of Computational and Experimental Science and Engineering, Journal Year: 2025, Volume and Issue: 11(2)

Published: March 29, 2025

Localization methods are used to approximate the position of unknown nodes in a network. errors calculated by comparing estimated and true positions at each time step. Finding best network parameters minimize localization error during setup process while maintaining requisite accuracy short period remains difficult task. Both anchor strategically placed reduce problems, which addresses series issue. Soft computing approaches such as Fuzzy Logic Adaptive Neuro-Fuzzy Inference System (ANFIS) address this In study, number simulation area de facto for Average Error(ALE) training prediction. These feature values were obtained from simulations using modified centroid technique with Kalman filter. This work tries adjusting these soft techniques. The experimentation is carried out MATLAB, demonstrating suggested method's ability improve reliability wireless sensor networks.

Language: Английский

Citations

1