SVM+KF Target Tracking Strategy Using the Signal Strength in Wireless Sensor Networks

Wang, Xing; Liu, Xuejun; Wang, Ziran; Li, Ruichao; Wu, Yiguang

doi:10.3390/s20143832

Cited by 14 publications

(5 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To address this issue, many approaches often necessitate extensive computational resources and a substantial volume of training data samples [27][28][29]. Several studies using noise-filtering methods have been undertaken to address the challenges posed by environmental dynamics impacting RSSI-based localization [18][19][20][21].…”

Section: Related Workmentioning

confidence: 99%

Improving LoRaWAN Localization in Industrial Environments Using Merging Path-Loss Modeling with Extended Kalman Filtering and adopting Map-Matching

Moradbeikie,

Keshavarz,

lopes

2024

Preprint

View full text Add to dashboard Cite

In industrial environments, accurate location information is crucial in enabling the seamless operation of technologies. Localization based on the signal features of the implemented network (such as RSSI) is becoming an appropriate substitute to solve its problems, such as low power consumption and cost. LoRaWAN, a contemporary LPWAN technology, can provide long-range coverage, an important requirement for several industrial application domains. RSSI-based localization in LoRaWAN is a widely used low-cost method, but it is susceptible to environmental changes and noise, leading to low performance and accuracy especially in industrial environments. So, applying an adoptable noise-filtering method based on the environment, to make measured RSSI usable in industrial applications such as asset management localization and tracking, is essential. This paper proposes a novel method that merges an Extended Kalman Filter (EKF) with Path-Loss modeling (PLM) for noise filtering in LoRaWAN system. Additionally, we incorporate map considerations to further improve the accuracy of location estimation. For the evaluation step, the proposed method is implemented and tested in a harbor in a highly dynamic and harsh industrial environment. The detailed evaluation demonstrates that the proposed approach leads to an improvement between 15% and 46% compared to normal PLM. In addition, adding map-matching leads to a 36% improvement in location estimation.

show abstract

Section: Related Workmentioning

confidence: 99%

Improving LoRaWAN Localization in Industrial Environments Using Merging Path-Loss Modeling with Extended Kalman Filtering and adopting Map-Matching

Moradbeikie,

Keshavarz,

lopes

2024

Preprint

View full text Add to dashboard Cite

show abstract

“…The authors adopted two-stage fusion structure and policy of dynamic cluster selection to achieve accurate location estimates. The authors in [23] presented an algorithm to locate target in indoor environments. The indoor environment is divided the targeted area into several sectors, and then, RSS measurements are used for target location estimation.…”

Section: Related Workmentioning

confidence: 99%

Energy-Constrained Target Localization Scheme for Wireless Sensor Networks Using Radial Basis Function Neural Network

K¹,

Nandini

Jondhale

et al. 2023

International Journal of Distributed Sensor Networks

View full text Add to dashboard Cite

The indoor object tracking by utilizing received signal strength indicator (RSSI) measurements with the help of wireless sensor network (WSN) is an interesting and important topic in the domain of location-based applications. Without the knowledge of location, the measurements obtained with WSN are of no use. The trilateration is a widely used technique to get location updates of target based on RSSI measurements from WSN. However, it suffers with high location estimation errors arising due to random variations in RSSI measurements. This paper presents a range-free radial basis function neural network (RBFN) and Kalman filtering- (KF-) based algorithm named RBFN+KF. The performance of the RBFN+KF algorithm is evaluated using simulated RSSIs and is compared against trilateration, multilayer perceptron (MLP), and RBFN-based estimations. The simulation results reveal that the proposed RBFN+KF algorithm shows very low location estimation errors compared to the rest of the three approaches. Additionally, it is also seen that RBFN-based approach is more energy efficient than trilateration and MLP-based localization approaches.

show abstract

“…In the second phase, the appropriate RSSI are selected by the k-NN algorithm, taking into account the characterization of the location. In [23], a target tracking algorithm using SVM and Kalman Filter (KF) is presented. The SVM is used to estimate the initial position of the target based on the received RSSI values.…”

Section: Related Workmentioning

confidence: 99%

Online sequential DV-Hop Localization Algorithm Based on Machine Learning for Wireless Sensors Network

Liouane

Femmam

Bakir

2023

Preprint

View full text Add to dashboard Cite

In many applications of Wireless Sensor Network (WSN), the transmitted data collected from the connected wireless sensor nodes has not great significance without knowing its geographical location. In this paper, firstly, we propose an analytical probabilistic model for multi-hops distance estimation between anchor nodes positions and unknown nodes positions. Moreover, we use the Machine Learning Technique (MLT) to optimize the accuracy of node localization in WSN. A range-free technique, based on the multi-hop localization method, is used with the proposed MLT. The proposed method consists of probabilistic expected hop-size and the On-line Sequential Extreme Learning Machine. The localization performance of the proposed techniques is proved through simulation tests when compared with the other soft-computing algorithms in term of Average Localization Errors (ALE).

show abstract

SVM+KF Target Tracking Strategy Using the Signal Strength in Wireless Sensor Networks

Cited by 14 publications

References 49 publications

Improving LoRaWAN Localization in Industrial Environments Using Merging Path-Loss Modeling with Extended Kalman Filtering and adopting Map-Matching

Improving LoRaWAN Localization in Industrial Environments Using Merging Path-Loss Modeling with Extended Kalman Filtering and adopting Map-Matching

Energy-Constrained Target Localization Scheme for Wireless Sensor Networks Using Radial Basis Function Neural Network

Online sequential DV-Hop Localization Algorithm Based on Machine Learning for Wireless Sensors Network

Contact Info

Product

Resources

About