A robust TDOA based solution for source location using mixed Huber loss

Mingyi, You; An-nan, LU

doi:10.23919/jsee.2021.000117

Cited by 4 publications

(2 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There are optimization variables both in the numerator and denominator as in (6). Therefore, problem ( 6) is non-convex and difficult to solve.…”

Section: Bivariate Rss Localization Modelmentioning

confidence: 99%

“…Large-scale network localization techniques in 5G and beyond 5G wireless networks are essential for many Internet-of-Things (IoT), smart city and military applications, including spectrum monitoring, intelligent transportation, asset tracking and battlefield monitoring [1], [2]. Compared with methods relying on time of arrival (TOA) [3], [4], time difference of arrival (TDOA) [5], [6], or angle of arrival (AOA) [7], [8] measurements, received signal strength (RSS) based localization method features low hardware cost and low network synchronization require-ment, making it suitable for large-scale IoT with resourceconstrained radio sensors [9][10][11][12][13].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Uncooperative Emitter Localization Based on Joint Sensor Selection and Semidefinite Programming

Cao¹,

Zhang²,

Liu³

et al. 2022

RADIOENGINEERING

View full text Add to dashboard Cite

Radio emitter localization based on Received Signal Strength (RSS) is promising in large-scale Internet of Things (IoT) and wireless sensor networks (WSNs) for its low hardware and computation costs. To improve its localization accuracy and reduce the system energy consumption, we propose an improved RSS localization algorithm based on the joint sensor selection and semidefinite programming (SDP). An initial position estimate is first obtained using RSSs available at a random set of sensors.A refined sensor set is then selected to complete the second estimation by analyzing the geometric structure of sensing network. Performance of the method is evaluated in terms of localization accuracy and execution time, and compared with existing methods. Extensive simulations demonstrate that the proposed approach achieves a localization accuracy of approximately 1.5 m with 8 to 10 sensors. The method outperforms the second-order cone programming (SOCP) and the least squared relative error (LSRE)-based SDP algorithms in terms of both the location and the transmit power estimation accuracy.

show abstract

“…There are optimization variables both in the numerator and denominator as in (6). Therefore, problem ( 6) is non-convex and difficult to solve.…”

Section: Bivariate Rss Localization Modelmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Uncooperative Emitter Localization Based on Joint Sensor Selection and Semidefinite Programming

Cao¹,

Zhang²,

Liu³

et al. 2022

RADIOENGINEERING

View full text Add to dashboard Cite

show abstract

Securing Fast and High-Precision Localization for Shallow Underground Explosive Source: A Curiosity-Driven Deep Reinforcement Learning Approach

Wu,

Wang,

et al. 2024

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

Shallow underground explosive source localization technology is a key technology in the field of underground space localization. The existing approaches mainly aim to improve the localization accuracy, but need to deploy enormous sensors in the monitoring area, and rely on a large number of back-end workstations to solve. These methods have the defects of considerable calculation and high time cost, and are hard to satisfy the precise and real-time requirements of onsite testing, ultimately resulting in slow localization speed and accurate localization failure. Fortunately, emerging deep reinforcement learning (DRL) can effectively solve the problem of slow search policy by modeling the source localication as a Markov decision process (MDP). Therefore, a Curiosity-Driven Deep Dueling Double Q-learning Network (C-D3QN) is subsequently proposed to solve the above MDP. The overestimation problem is solved by decoupling selection and evaluation of the bootstrap action, and the action difference is effectively increased by introducing the dueling network that separately represents state values and action advantages. Meanwhile, the exploration is jointly reinforced by an intrinsic reward outputted from the curiosity module and an extrinsic reward supplied by the environment, guaranteeing the convergence to global optimal. Finally, extensive simulation results based on the outfield experiment data show that compared with other algorithms, the proposed scheme can significantly improve exploration ability and learning speed as well as generalization and robustness. Additionally, compared to the baseline algorithm DQN, the C-D3QN algorithm can offer an improved localization accuracy as high as 99.62% and an increased localization speed of 66.23%.

show abstract

Improved-RSSI-based indoor localization by using pseudo-linear solution with machine learning algorithms

Maduranga,

Tilwari,

Abeysekera

2024

Journal of Electrical Systems and Inf Technol

View full text Add to dashboard Cite

With the rapid advancement of the Internet of Things and the popularization of mobile Internet-based applications, the location-based service (LBS) has attracted much attention from commercial developers and researchers. Received signal strength indicator (RSSI)-based indoor localization technology has irreplaceable advantages for many LBS applications. However, due to multipath fading, noise, and the limited dynamic range of the RSSI measurements, precise localization based on a path-loss model and multiliterate becomes highly challenging. Therefore, this study proposes a machine learning (ML)-based improved RSSI-based indoor localization approach in which RSSI data is first augmented and then classified using ML algorithms. In addition, we implement an experimental testbed to collect the RSSI value based on Wi-Fi using various reference and target nodes. The received RSSI measurements undergo pre-processing using pseudo-linear solution techniques for closed-form solutions, approximating the original system of nonlinear RSSI measurement equations with a system of linear equations. Finally, the RSSI measurement are trained using ML models such as linear regression, polynomial regression, support vector regression, random forest regression, and decision tree regression. Consequently, the experimental results express in terms of root mean square error and coefficient of determinant compared with various machine learning models with hyper-parameter tuning.

show abstract

A robust TDOA based solution for source location using mixed Huber loss

Cited by 4 publications

References 7 publications

Uncooperative Emitter Localization Based on Joint Sensor Selection and Semidefinite Programming

Uncooperative Emitter Localization Based on Joint Sensor Selection and Semidefinite Programming

Securing Fast and High-Precision Localization for Shallow Underground Explosive Source: A Curiosity-Driven Deep Reinforcement Learning Approach

Improved-RSSI-based indoor localization by using pseudo-linear solution with machine learning algorithms

Contact Info

Product

Resources

About