Ning Xu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Ning Xu has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
- Fuyang Chen
College of Automation Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing, China
2 shared publications - Hongtian Chen
Shanghai Jiao Tong University
1 shared publication - Ruihang Xu
Institute of Applied Mathematics, Academy of Mathematics and Systems Science, Chinese Academy of Sciences, Beijing, China
1 shared publication - Sudao He
College of Automation Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing, China
1 shared publication - Tao Chen
Center for Language and Speech Processing, Johns Hopkins University, Baltimore, MD, United States
1 shared publication - Yiwei Li
College of Automation Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing, China
1 shared publication
Latest Publications
- 3 March 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 74 (00189456) , 1-12
A Human Intrusion Monitoring Strategy Based on Distributed Sensor Networks to Tackle Label Noise
This article proposes a Human Intrusion monitoring strategy based on Distributed Fiber Optic Sensor (DFOS) systems, specifically designed to address the label noise challenges caused by the non-linear spatial attenuation from varying external environments and uncertainties from human intrusions. Utilized for dynamic measurements of the physical environment, DFOS systems comprise various sensor nodes that capture anomalous vibration signals. Due to the distributed nature of DFOS systems, adjacent nodes frequently detect overlapping vibration signals. This, coupled with unknown interference events and variable delays in data acquisition, poses significant challenges to the accurate labeling of data. A Dual-Enhanced Convolutional Neural Networks (CNNs)-Transformer Co-teaching (DCTC) Strategy is proposed which integrates the robust features of CNNs and Transformers to effectively handle the multi-scale dependencies and uncertainties. By using CNN to capture spatial features and Transformers to model long-range temporal dependencies, the DCTC method enhances the capability to discern and isolate true anomalies from noisy data. The DCTC employs a Co-teaching strategy between two neural networks which facilitates mutual learning and improves resistance to label noise. This is further augmented by Bootstrapping Loss, which adjusts the training loss to prioritize reliable labels, thereby enhancing the overall robustness of the model. The practicality of the DCTC strategy is demonstrated through real-field experiments using DFOS in high-speed train human intrusion monitoring system. These experiments validate the method’s ability to significantly enhance monitoring accuracy in environments with label noise.
- 3 March 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 74 (00189456) , 1-12
A Human Intrusion Monitoring Strategy Based on Distributed Sensor Networks to Tackle Label Noise
This article proposes a Human Intrusion monitoring strategy based on Distributed Fiber Optic Sensor (DFOS) systems, specifically designed to address the label noise challenges caused by the non-linear spatial attenuation from varying external environments and uncertainties from human intrusions. Utilized for dynamic measurements of the physical environment, DFOS systems comprise various sensor nodes that capture anomalous vibration signals. Due to the distributed nature of DFOS systems, adjacent nodes frequently detect overlapping vibration signals. This, coupled with unknown interference events and variable delays in data acquisition, poses significant challenges to the accurate labeling of data. A Dual-Enhanced Convolutional Neural Networks (CNNs)-Transformer Co-teaching (DCTC) Strategy is proposed which integrates the robust features of CNNs and Transformers to effectively handle the multi-scale dependencies and uncertainties. By using CNN to capture spatial features and Transformers to model long-range temporal dependencies, the DCTC method enhances the capability to discern and isolate true anomalies from noisy data. The DCTC employs a Co-teaching strategy between two neural networks which facilitates mutual learning and improves resistance to label noise. This is further augmented by Bootstrapping Loss, which adjusts the training loss to prioritize reliable labels, thereby enhancing the overall robustness of the model. The practicality of the DCTC strategy is demonstrated through real-field experiments using DFOS in high-speed train human intrusion monitoring system. These experiments validate the method’s ability to significantly enhance monitoring accuracy in environments with label noise.
- 1 January 2023
- Published by Society of Motion Picture and Television Engineers (SMPTE)
- p. 8-10
Real-time Personalized Ranking and Recommendation System for Linear TV: A Dual Dynamic Queue Approach
The increasing number of channels on linear TV has amplified the challenge of efficient content discovery for viewers. This paper presents an innovative, real-time personalized ranking and recommendation system designed to address this problem. The objective was to enhance viewer satisfaction and interaction through a personalized, dynamic channel surfing experience. Our approach uses a dual dynamic queue system - the Dynamic History Channel Queue (DHCQ) and the Dynamic Future Channel Queue (DFCQ), each serving a unique purpose in managing the viewer's channel interaction. — Advanced deep learning models reinforce these queues’ dynamism by generating ‘global’ and ‘local’ content embeddings and ‘user’ embeddings. These embeddings are used to provide real-time updates, considering both timestamps and the time-sensitivities of the content and viewer. A ‘look- ahead’ feature was integrated to account for future content on each channel, adding another layer of personalization. — Preliminary user feedback highlighted a strong interest in this new form of personalized channel surfing, with a majority of respondents indicating a preference for our system over traditional channel navigation methods. The results show that our proposed solution could potentially change the way users interact with the ever-growing number of channels on linear TV.
- 1 January 2023
- Published by Society of Motion Picture and Television Engineers (SMPTE)
- p. 8-10
Real-time Personalized Ranking and Recommendation System for Linear TV: A Dual Dynamic Queue Approach
The increasing number of channels on linear TV has amplified the challenge of efficient content discovery for viewers. This paper presents an innovative, real-time personalized ranking and recommendation system designed to address this problem. The objective was to enhance viewer satisfaction and interaction through a personalized, dynamic channel surfing experience. Our approach uses a dual dynamic queue system - the Dynamic History Channel Queue (DHCQ) and the Dynamic Future Channel Queue (DFCQ), each serving a unique purpose in managing the viewer's channel interaction. — Advanced deep learning models reinforce these queues’ dynamism by generating ‘global’ and ‘local’ content embeddings and ‘user’ embeddings. These embeddings are used to provide real-time updates, considering both timestamps and the time-sensitivities of the content and viewer. A ‘look- ahead’ feature was integrated to account for future content on each channel, adding another layer of personalization. — Preliminary user feedback highlighted a strong interest in this new form of personalized channel surfing, with a majority of respondents indicating a preference for our system over traditional channel navigation methods. The results show that our proposed solution could potentially change the way users interact with the ever-growing number of channels on linear TV.
- 12 April 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 71 (00189456) , 1-12
Online Monitoring for Non-Stationary Operation via a Collaborative Neural Network
Online monitoring has become a challenging issue because of the changing knowledge in non-stationary operation. It requires an appropriate monitoring algorithm to timely self-adjust based on a finite number of online data. This study proposes a collaborative neural network (CoNN) is proposed for detecting physical intrusions in perimeter security monitoring through real-time adaptation. The proposed CoNN method consists of two half-shared neural networks for online learning with finite measurements through preserving previous knowledge and absorbing the new knowledge. Specifically, the shared feature layers can learn latent domain-invariant representations through weights sharing and adapt CoNN to prior knowledge changes. On this basis, the classification layers utilize concept-exclusive parameters to model the changes of posterior knowledge. Furthermore, the objective of CoNN is formulated as a linearly constrained non-convex minimization problem with coupled functions, and an alternating direction method is employed to solve it with theoretically guaranteed convergence. The feasibility and effectiveness of the proposed method are validated through a real-field experiment of a perimeter security system.
- 12 April 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 71 (00189456) , 1-12
Online Monitoring for Non-Stationary Operation via a Collaborative Neural Network
Online monitoring has become a challenging issue because of the changing knowledge in non-stationary operation. It requires an appropriate monitoring algorithm to timely self-adjust based on a finite number of online data. This study proposes a collaborative neural network (CoNN) is proposed for detecting physical intrusions in perimeter security monitoring through real-time adaptation. The proposed CoNN method consists of two half-shared neural networks for online learning with finite measurements through preserving previous knowledge and absorbing the new knowledge. Specifically, the shared feature layers can learn latent domain-invariant representations through weights sharing and adapt CoNN to prior knowledge changes. On this basis, the classification layers utilize concept-exclusive parameters to model the changes of posterior knowledge. Furthermore, the objective of CoNN is formulated as a linearly constrained non-convex minimization problem with coupled functions, and an alternating direction method is employed to solve it with theoretically guaranteed convergence. The feasibility and effectiveness of the proposed method are validated through a real-field experiment of a perimeter security system.