Multi-hop Range-Free Localization Algorithm for Wireless Sensor Network Using Principal Component Regression

Summary Range‐free localization algorithms in wireless sensor networks have been an interesting field for researchers over the past few years. The combining of different requirements such as storage space, computational capacities, communication capabilities, and power efficiency is a challenging aspect of developing a localization algorithm. In this paper, a new range‐free localization algorithm, called PCAL, is proposed using soft computing techniques. The proposed method utilizes hop‐count distances as the data to train and build a neural network. Before feeding the data into the neural network for the purpose of training, the dimensionality of data is reduced by principal component analysis algorithm. The performance of the proposed algorithm is evaluated using simulation. The obtained results show that the proposed algorithm has a better performance in contrast to other algorithms based on storage space, communication overhead, and localization accuracy. Furthermore, the effect of various parameters on the PCAL algorithm is studied.

show abstract

“…Tian et al proposed a PCR‐based multihop range‐free positioning method. This algorithm uses PCR for obtaining a mapping model.…”

Section: Related Workmentioning

confidence: 99%

“…Next, a neural network is trained by the transformed data samples. Although some research works used the PCA in localization, the PCA algorithm is used for removing noise and harmful data or for mapping hop counts to Euclidean distances. We will describe these schemes in the related works in detail.…”

Section: Introductionmentioning

confidence: 99%