The exact localization of sensor nodes is one of the important issues in Wireless Sensor Networks (WSNs) for different applications. However, traditional methods of localization may suffer from several types of errors...
详细信息
The exact localization of sensor nodes is one of the important issues in Wireless Sensor Networks (WSNs) for different applications. However, traditional methods of localization may suffer from several types of errors. This research examines a machine learning (ML) approach for predicting average localization error (ALE) in WSNs. This study applies two powerful ML models: K-nearest neighbors Regression (KNNR) and Light Gradient Boosting Machine (LGBM). KNNR is light and easy to interpret, while LGBM has the capability to model complex relationships among features. Furthermore, an optimizer in the form of the Walrus Optimization Algorithm (WaOA) is utilized to boost the performance of the model. WaOA is a nature-inspired algorithm that is efficient in fine-tuning the parameters of ML models to improve their prediction accuracy. The LGWO model performed better on the test set, with an RMSE value of 0.066 and an R2 of 0.980, compared with other traditional models, such as KNN, at 0.131 and 0.915, respectively. During the testing phase, the LGWO model demonstrated the highest performance based on the Mean Squared error (MSE) metric, achieving a value of 0.004, while the KNWO model ranked third with an MSE value of 0.015. Similarly, in the validation phase, the LGWO model achieved the best performance in terms of the Relative Absolute error (RAE) metric, with a value of 2.799. The second-best performance in the validation phase was observed with the LGBM model, which recorded an RAE value of 3.931. In terms of the minimum prediction error and best accuracy within the entire training, validation, and testing processes, the LGWO model proves robust and reliable.
localization node is a core issue in Wireless Sensor Networks (WSNs). Accurate errorlocalization prediction presents several benefits, including enhanced network performance, optimized resource allocation, and reduce...
详细信息
localization node is a core issue in Wireless Sensor Networks (WSNs). Accurate errorlocalization prediction presents several benefits, including enhanced network performance, optimized resource allocation, and reduced expense. localization subsystems are indispensable in most vehicular ad hoc network applications (VANETs). Maintaining current and correct localization data ready to be obtained at any position and time is one of the key issues in vehicular networks. This study proposes a cost-efficient network parameter optimization technique to achieve low average localization error (ALE) through the use of Machine Learning (ML) techniques from the Adaptive Neuro-Fuzzy Inference System (ANFIS) and the Extra Tree Regression (ETR). For improved model performance, the study uses two optimizers: The Red Deer Algorithm (RDA) and the Sea Horse Optimizer (SHO). In the proposed localization scheme, at most, three beacon nodes collaborate to precisely determine any common node's location. The two base models are hybridized with the optimizers as follows: ANFIS model hybridized with RDA as ANRD;ANFIS model hybridized with SHO as ANSH;ETR model hybridized with RDA as ETRD;and ETR model hybridized with SHO as ETSH. During the Test phase, the ETSH model demonstrates the highest performance with an R2 value of 0.973, followed by the ETRD model, which achieves the second-best performance at 0.960. Regarding the RMSE metric during the Test phase, the ETSH model exhibits the best performance with a value of 0.079, while the ANFIS model shows the weakest performance with a value of 0.186.
In the realm of today's networking technologies, user localization has been a formidable challenge for recent applications. There are different approaches in pursuit of heightened position detection of an end-user...
详细信息
In the realm of today's networking technologies, user localization has been a formidable challenge for recent applications. There are different approaches in pursuit of heightened position detection of an end-user with the help of GPS, Wi-Fi fingerprint and 5G equipment. However, these approaches require both deployment and maintenance costs because of equipment establishment for position tracking. Moreover, they are not capable of minimizing the localizationerror, especially for indoor scenarios to track the indoor position of an end-user. Hence, there is an urgent need to delve deeper into innovative approaches to drive further advancements in user localization. In response, Machine Learning (ML) approaches have recently been widely adapted to predict the localization of end-users with minimum error. More specifically, average localization error (ALE) of an end-user can be predicted in a cost-effective way by using proper data and ML methods. For this purpose, we have investigated different ML approaches to get an accurate ALE prediction scheme for 5G networks with mobile end-users. Accordingly, an existing dataset is utilized to generate localization data of end-users in which the ALE is directly calculated by Received Signal Strength Indicator. Moreover, three different normalization approaches are applied for the overarching goal of increased data quality. Consequently, six different ML algorithms, including Linear regression, support vector machine with three different kernels, Gaussian process, and ensemble least-squares boosting (LSBoost) are evaluated with respect to a set of evaluation criteria including R, R2, RMSE, and MAE. The evaluation outcomes emphasize that ensemble LSBoost method, in the context of localization prediction, outperforms the other approaches and is sufficient to yield a viable learning strategy for ALE prediction.
localization is an apparent aspect of a wireless sensor network, which is the focus of much interesting research. One of the severe conditions that needs to be taken into consideration is localizing a mobile target th...
详细信息
localization is an apparent aspect of a wireless sensor network, which is the focus of much interesting research. One of the severe conditions that needs to be taken into consideration is localizing a mobile target through a dispersed sensor network in the presence of physical barrier attacks. These attacks confuse the localization process and cause location estimation errors. Range-based methods, like the received signal strength indication (RSSI), face the major influence of this kind of attack. This paper proposes a solution based on a combination of multi-frequency multi-power localization (C-MFMPL) and step function multi-frequency multi-power localization (SF-MFMPL), including the fingerprint matching technique and lateration, to provide a robust and accurate localization technique. In addition, this paper proposes a grid coloring algorithm to detect the signal hole map in the network, which refers to the attack-prone regions, in order to carry out corrective actions. The simulation results show the enhancement and robustness of RSS localization performance in the face of log normal shadow fading effects, besides the presence of physical barrier attacks, through detecting, filtering and eliminating the effect of these attacks.
Wireless Sensor Network (WSN) technology has been applied more and more widely and node localization is an important aspect of it. Bounding Box localization algorithm has been used in many cases. The purpose of this p...
详细信息
ISBN:
(数字)9781510623002
ISBN:
(纸本)9781510623002
Wireless Sensor Network (WSN) technology has been applied more and more widely and node localization is an important aspect of it. Bounding Box localization algorithm has been used in many cases. The purpose of this paper is to study the localization accuracy of the three different strategies based on Bounding Box localization algorithm and to explore the influence of the two parameters, the number of the anchor nodes and communication radius, on the localization accuracy. Firstly, the paper illustrates the principals of three strategies according to whether the unknown nodes that have been located will participate in locating other unknown nodes or not. Then the simulation condition is set, and the average localization error is gotten using three strategies respectively. The result shows the localization accuracy of Strategy C is the highest. Finally, the paper studies the influence of the number of the anchor nodes and the length of the communication radius on the localization accuracy and gives the optimal number of anchor nodes and communication radius when used in practice.
localization is an essential requirement in the increasing prevalence of wireless sensor network (WSN) applications. Reducing the computational complexity, communication overhead in WSN localization is of paramount im...
详细信息
localization is an essential requirement in the increasing prevalence of wireless sensor network (WSN) applications. Reducing the computational complexity, communication overhead in WSN localization is of paramount importance in order to prolong the lifetime of the energy-limited sensor nodes and improve localization performance. This paper proposes an effective Cuckoo Search (CS) algorithm for node localization. Based on the modification of step size, this approach enables the population to approach global optimal solution rapidly, and the fitness of each solution is employed to build mutation probability for avoiding local convergence. Further, the approach restricts the population in the certain range so that it can prevent the energy consumption caused by insignificant search. Extensive experiments were conducted to study the effects of parameters like anchor density, node density and communication range on the proposed algorithm with respect to average localization error and localization success ratio. In addition, a comparative study was conducted to realize the same localization task using the same network deployment. Experimental results prove that the proposed CS algorithm can not only increase convergence rate but also reduce average localization error compared with standard CS algorithm and Particle Swarm Optimization (PSO) algorithm.
暂无评论