Ruixin Niu

Ruixin Niu

Auto-generated profile, based on publicly available information

Ruixin Niu

Virginia Commonwealth University

Research Focus & Metrics

Academic Career Length

20Years (2007-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
5 June 2018 in Proceedings of the IEEE
Verified
Journal Article
Closed access
RNRuixin Niu
Ruixin Niu
AVAditya Vempaty
Aditya Vempaty
PVPramod K. Varshney
Pramod K. Varshney
In this paper, an overview of recent developments in received-signal-strength (RSS)-based localization in wireless sensor networks is presented. Several important practical issues and their solutions are discussed. To save communication bandwidth and sensor energy, a maximum-likelihood estimator based on quantized data is presented along with its corresponding Cramér.Rao lower bound (CRLB) and optimal quantizer design schemes. For further system resource savings, an iterative sensor selection approach is presented to activate only the most informative sensors, by maximizing the mutual information or minimizing the posterior CRLB at each iteration. For a resource constrained WSN with imperfect wireless channels, channel-aware target localization is described, where the channel model is incorporated into the localization scheme itself, thereby improving performance without increasing communication overhead. Another practical issue involving the presence of malicious sensors called Byzantines is discussed and mitigation schemes are provided. A recent coding-theory-based approach which is both computationally inexpensive and robust to such malicious attacks is also discussed.

12 February 2018 in IEEE Transactions on Aerospace and Electronic Systems
Verified
Journal Article
Closed access
XYXiaojun Yang
Xiaojun Yang
RNRuixin Niu
Ruixin Niu
In this paper, we propose a few sparsity-promoting approaches for sensor selection in wireless sensor networks (WSNs) to reach the optimal tradeoff between the tracking performance and the sensing-communication cost. The proposed framework is valid for general nonlinear target tracking without explicit linearization and not restricted to any specific estimator. We formulate the sensor selection problem as the design of a sparse selection vector. The cardinality of the selection vector is added as a sparsity-promoting penalty term to the cost function where the conditional posterior Cramér-Rao lower bound is used as the criterion for sensor selection. To cope with large-scale WSNs, by combining iterative reweighted ℓ 1 -norm minimization with the accelerated proximal gradient method and the alternating direction method of multipliers (ADMM), we develop two efficient sensor selection algorithms, respectively. We further develop a low-complexity distributed version of the ADMM where each sensor makes a local sensor selection decision. We test the proposed algorithms by simulations based on an extended Kalman filter using analog data and a particle filter using quantized data, respectively, which provide valuable insights and demonstrate the proposed algorithms' performance.

20 June 2024 in IEEE Transactions on Signal Processing
Verified
Journal Article
Closed access
LXLiang Xu
Liang Xu
RNRuixin Niu
Ruixin Niu
In this paper, to reduce the time and manpower to fine-tune an extended Kalman filter (EKF), we propose a new learning framework, EKFNet, for automatically estimating the best process and measurement noise covariance parameters for an EKF from real measurement data. The EKFNet is trained end-to-end by using backpropagation through time (BPTT) over the EKF. The forward operation of EKFNet is the same as the normal EKF operation which will be used during the tracking process. During the offline training, the EKFNet uses the BPTT for passing the gradient flow to each time step and optimizing the unknown noise statistic parameters. The proposed method can choose among several optimization criteria, such as maximizing the likelihood, minimizing the measurement residual error, or minimizing the posterior state estimation error either with or without the ground truth data. The proposed method’s performance is demonstrated using real GPS data, which outperforms an existing method and a manually tuned EKF.

1 August 2012
Verified
Conference Paper
Closed access
YZYujiao Zheng
Yujiao Zheng
RNRuixin Niu
Ruixin Niu
PVPramod K. Varshney
Pramod K. Varshney
In this paper, a new framework for sequential Bayesian estimation in a sensor network by using both the received data and the information conveyed by missing data due to per-sensor censoring is proposed. In this framework, each local sensor maintains a Kalman Filter (KF) and the Fusion Center (FC) runs a particle filter (PF) to track the system state. Informative measurements are selected by the per-sensor censoring process executed at the sensors at each time. Though the less informative measurements are not sent to the FC, their absence still conveys some information, and the proposed scheme exploits such information from the missing message to achieve better inference performance. Numerical examples are provided to support the theoretical results.

1 January 2007
Verified
Conference Paper
Closed access
PRPriyadip Ray
Priyadip Ray
PVPramod K. Varshney
Pramod K. Varshney
RNRuixin Niu
Ruixin Niu
This paper presents a new framework for distributed target detection in wireless sensor networks (WSNs). In our previous work, for multiple networked sensors collaboratively detecting the presence or absence of a target in the sensor field, every sensor uses an identical threshold for local decision-making. In this paper, we propose a framework where the sensors in the network collaboratively decide and select non-identical thresholds to improve network-wide detection performance in a dynamic manner. This threshold selection scheme is based on a new statistical metric called false discovery rate (FDR). Assuming a signal attenuation model, where the received signal power decays as the distance from the target increases, various performance indices like system level probability of detection and probability of false alarm are studied. Analytical and simulation results are provided for system level probability of false alarm and probability of detection. Performance comparison between the proposed approach and the classical identical local sensor threshold approach is provided to demonstrate the effectiveness of this scheme.

28 September 2017
Verified
Conference Paper
Closed access
PDF file
Erik BlaschErik Blasch
Erik Blasch
DSDan Shen
Dan Shen
RNRuixin Niu
Ruixin Niu
JLJingyang Lu
Jingyang Lu
ZWZhonghai Wang
Zhonghai Wang
MDMarcello Distasio
Marcello Distasio
The dynamic data-driven applications system (DDDAS) paradigm uses the controlled measurement data to update models. When big data streams are available, signal processing can be used for situation awareness. However, many times, the physical world prevents sensor measurements availability which provides an opportunity to use heterogeneous sensor information; but methods are needed for data normalization, sampling alignment, and data mining. In this paper, we highlight a joint nonlinear manifold learning approach to that incorporates advances in machine learning, data fusion, and model-based simulation propagators. The context of the situation monitoring includes a multiple moving targets, a video sensor, and distributed signal sensors. The challenge is to determine the moving emitter amongst a cluttered scene during an experiment with large data streams. Resolving the signature triangulation of the emitter with that of the video sensor is both a nonlinear tracking problem as well as data learning issue. The paper presents the joint nonlinear manifold learning approach that is theoretically developed such sensor models could not only be the tracking scenario; but that of structure health monitoring as well as internet of things (IoT) examples. The theoretical analysis, heterogeneous data set, machine learning, and results are presented to showcase the importance of real-time DDDAS modeling updates of kinematic models.