Xiaotong Wang

Mr. Xiaotong Wang

orcid

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

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

Representative Publications

View All Publications
22 February 2023 in IEEE Sensors Journal
Verified
Journal Article
Closed access
HJHaonan Jiang
Haonan Jiang
XWXiaotong Wang
Xiaotong Wang
YDYifan Deng
Yifan Deng
YZYINGJIE ZHANG
YINGJIE ZHANG
This paper deals with the problem of multi-sensor bearings-only tracking under measurement uncertainty. In order to effectively track the target whilst reducing the communication times and keeping the estimation accuracy, a novel distributed bias-compensated pseudolinear information filter with event-triggered communication mechanism and hybrid-consensus-based fusion strategy is proposed. Each sensor transmits the local information to its neighbors only when it is considered to be valuable for the fusion of its neighboring sensors based on the normalized innovation. Besides, the weight of the transmitted information, which represents the importance degree of the local estimation result, is also taken into account. The stability of the proposed algorithm is proved. Simulation results verify the effectiveness and robustness of the proposed algorithm.

8 November 2024 in Remote Sensing
Verified
Journal Article
Open access
PDF file
HJHaonan Jiang
Haonan Jiang
YZYINGJIE ZHANG
YINGJIE ZHANG
XWXiaotong Wang
Xiaotong Wang
Yuanli CaiYuanli Cai
Yuanli Cai
This paper considers the problem of tracking a three-dimensional target under the condition that only a single two-dimensional radar is available. Since a two-dimensional radar can only measure the slant range and azimuth information relative to the target, an unobservability issue arises in this tracking application. Therefore, we first investigate the observability issue of tracking a three-dimensional target with a single two-dimensional radar from two perspectives, including intuitive illustration and quantitative analysis. From the perspective of intuitive illustration, we demonstrate “What is the unobservability issue” and “How does the relative target-radar geometry influence the observability of the tracking system”. From the perspective of quantitative analysis, we construct a novel observability metric for this special tracking problem. Second, aiming at improving tracking performance under the unobservability of target height, we propose an observability-based Gaussian sum cubature Kalman filter. Built within the Gaussian sum framework and based on the height-parameterized strategy, this novel algorithm uses a set of independent fifth-degree cubature Kalman filters, each of which can detect the system observability variation and enhance the tracking accuracy by using a Gaussian splitting scheme under low-degree observability. Finally, the effectiveness of the presented filtering algorithm is validated through lots of simulation experiments.

24 December 2025 in IEEE Transactions on Instrumentation and Measurement
Verified
Journal Article
Closed access
XWXiaotong Wang
Xiaotong Wang
HJHaonan Jiang
Haonan Jiang
Yuanli CaiYuanli Cai
Yuanli Cai
YDYifan Deng
Yifan Deng
Global navigation satellite system (GNSS) outages present a significant challenge for the global positioning of autonomous vehicles. In this paper, we propose a data-driven position error compensation method to enhance the positioning accuracy of GNSS-visual-inertial navigation system (GVINS) during GNSS outages. First, we introduce the equivalent inertial navigation system (E-INS), which is an abstraction of sensors such as cameras and inertial measurement units (IMUs) that only have localization capabilities, along with their measurement processing workflows. E-INS is employed to address the challenges posed by the differences in data modalities and measurement frequencies between cameras and IMUs. These differences complicate the design of the neural network. Subsequently, we design an error compensation network (EC-Net). It constructs a mapping between vehicle states and navigation data, enabling compensation of positioning solutions based on historical data when the GNSS signal is unavailable. EC-Net is built using stacked convolutional neural networks (CNNs) and gated recurrent units (GRUs) to effectively capture the spatiotemporal information in vehicle navigation sequences and suppress noise interference from low-cost sensors. Additionally, we utilize a trigonometric function-based Euler angle representation method to process the input features of EC-Net. It avoids the discontinuities at boundaries inherent in radian representations. The experimental results based on public datasets and real-world scenarios demonstrate that, compared to five other widely used methods, our proposed method achieves the highest accuracy during GNSS outages of up to five minutes. This effectively validates the performance of our approach.

17 November 2023
Verified
Conference Paper
Closed access
XWXiaotong Wang
Xiaotong Wang
Yuanli CaiYuanli Cai
Yuanli Cai
HJHaonan Jiang
Haonan Jiang
This paper investigates the problem of mobile robot positional estimation with robot localization under measurement abnormality. In order to improve the accuracy of position estimation without increasing the computational complexity, multiple fading factors extended Kalman filter based on Mahalanobis distance is proposed. The criterion of measurement abnormality is constructed based on the Mahalanobis distance of the innovation vector and the hypothesis testing method. A multiple fading factors matrix is constructed to provide different fading rates for different measurement data channels by combining the scalar fading factor and the innovation covariance, which realizes the adaptive adjustment of the statistical characteristics of measurement noise. Simulation results under two typical measurement abnormality scenarios verify the effectiveness and robustness of the proposed algorithm.

30 September 2020 in Web Intelligence
Verified
Journal Article
Closed access
HJHongxun Jiang
Hongxun Jiang
XWXiaotong Wang
Xiaotong Wang
MZMengjun Zhu
Mengjun Zhu
Weibo, the most widely-used social media in China, makes researchers highly regard its profound impact in public and gather moods for social computing and analysis, such as financial prediction. Most existing literatures concern excessively on text semantic or sentiment mining techniques, but neglect the procedure of moods dissemination and its factors. This paper proposes an integrated framework of social media moods mining, which creatively focuses on information transmission and propagating factors analysis, to predict stock prices more accurately. For the part of propagating factors on social media, several essential factors are distinguished in the dissemination process, such as emotional absorption of forwarding, influence of content and poster, user categories, release time, etc. to optimize the fitting effect of original model. And the count of forwarding also matters on predicting stock prices. Searching a given finance-related keyword, from Weibo we collected over 500,000 micro-blogs and their user information. Then we adopt the proposed integrated framework to predict stock price fluctuation, as well as the simple neural network method. Experiments demonstrate that the former outperformed the latter. The results also show that user categories and the count of forwarding differ on the lag phase of influence. And more, this paper studies the fitting effect of prediction models for different periods of the stock curve. The results indicate that the model works the best in the rising periods of stock prices curves, relatively well in the declining and the worst in the random fluctuating.

1 January 2026 in IEEE Sensors Journal
Verified
Journal Article
Closed access
XWXiaotong Wang
Xiaotong Wang
HJHaonan Jiang
Haonan Jiang
YDYifan Deng
Yifan Deng
Yuanli CaiYuanli Cai
Yuanli Cai