Retraction Notice: Exploring Autoregressive Moving Average Models in Wireless Sensor Network Time Series Analysis
Swati B. Gupta, N Gobi, Vaishali Singh · 2024
This paper gives an exploration of Autoregressive shifting average (ARMA) fashions in Time collection analysis (TSA) of wireless Sensor Networks (WSNs). ARMA models are mathematical equipment that captures temporal relationships in time series information. The software of ARMA models in WSNs TSA is generally carried out by thinking about various stages of noise, extraordinary spatial orientations, and interference sorts that sensor nodes address. Via an extensive simulation platform, this takes a look at explores the significance of the combination of different ARMA models on the performance of various WSNs applications. The results display that a suitable choice of ARMA fashions can beautify the accuracy and balance of facts acquisition and analysis, especially in dynamic wi-fi environments. In the end, the effectiveness of ARMA models in WSNs TSA is confirmed thru reliable and precise effects. This paper explores using autoregressive moving every day (ARMA) fashions to examine temporal houses of wireless sensor community (WSN) time series statistics. The authors propose a -step evaluation of regressing ARMA-like models onto the found time collection statistics to extract the temporal behavior gift and then performing correlation analysis on the derived time collection parameters to discover correlations in the context of the WSN. A contrast of an easy Exponential Autoregressive (EAR) version with a more complex autoregressive moving average with exogenous inputs (ARMAX) model is offered. Results imply that Autoregressive shifting everyday fashions are beneficial for WSN time series analysis and highlight the significance of accounting for exogenous elements in these models.