Xiaodong Ren
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Xiaodong Ren has a total of 31 co-authors. Here are the top co-authors by number of shared publications:
- Pinghui Wang
Xi'an Jiaotong University, Xi'an, China
2 shared publications - Yanxiang Feng
School of Automation Science and Engineering, Xian Jiaotong University, Xian, China
2 shared publications - Yikang Yang
School of Automation Science and Engineering, Xian Jiaotong University, Xian, China
2 shared publications - Anish Jindal
Department of Computer Science, Durham University, Durham, U.K.
1 shared publication - Bin Wang
Xi’an Jiaotong University
1 shared publication - Gagangeet Singh Aujla
Department of Computer Science, Durham University, Durham, U.K.
1 shared publication
Latest Publications
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 15079-15088
PrismDM: An Accurate and Efficient Framework for Privacy-Preserving Diffusion Model Sampling
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 15079-15088
Open AccessPrismDM: An Accurate and Efficient Framework for Privacy-Preserving Diffusion Model Sampling
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Robotics
- Vol. 42, 3408-3428
Unified Framework for Robot Calibration via Product Manifold Optimization and Riemannian Bayesian Optimization
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Robotics
- Vol. 42, 3408-3428
Unified Framework for Robot Calibration via Product Manifold Optimization and Riemannian Bayesian Optimization
- 29 November 2024
- Published by Elsevier in Knowledge-Based Systems
- Vol. 309
FedSR: Federated Learning for Image Super-Resolution via detail-assisted contrastive learning
- 29 November 2024
- Published by Elsevier in Knowledge-Based Systems
- Vol. 309
FedSR: Federated Learning for Image Super-Resolution via detail-assisted contrastive learning
- 14 October 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Systems, Man, and Cybernetics: Systems
- Vol. 53 (4) , 2222-2235
Small-Size Liveness-Enforcing Supervisor for Automated Manufacturing Systems Using the Theory of Transition Cover
The supervisor simplification problem for automated manufacturing systems (AMSs) has been receiving increasing attention in recent years. This article uses a well-known class of Petri nets, namely, systems of sequential systems with shared resources (S4Rs) to model general AMSs. We aim to simplify the liveness-enforcing supervisor for S4R by using the concept of transition cover (TC). Deadlocks in S4R can be characterized by a kind of special structural object called perfect activity circuits (PACs). First, a set of special PACs are defined as a TC and its effectness is also verified. Then, by adding a monitor with a control variable to each PAC in an effective TC (ETC), we establish a liveness-enforcing supervisor for S4R. The control variables are determined by solving an integer linear programming problem so as to increase the supervisor’s permissiveness as much as possible. Under the proposed control methodology, it is analyzed that the upper bound of the number of monitors equates to that of transitions in S4R. Especially for the system with a few transitions, since not many monitors are added, the proposed supervisor has relatively small-scaled structures or a small number of control places. In addition, we present algorithms to get an ETC from any nonlive S4R. Based on this ETC, we can design one liveness-enforcing supervisor of small size for the underlying S4R. Finally, some examples are used to illustrate the proposed approach.
- 14 October 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Systems, Man, and Cybernetics: Systems
- Vol. 53 (4) , 2222-2235
Small-Size Liveness-Enforcing Supervisor for Automated Manufacturing Systems Using the Theory of Transition Cover
The supervisor simplification problem for automated manufacturing systems (AMSs) has been receiving increasing attention in recent years. This article uses a well-known class of Petri nets, namely, systems of sequential systems with shared resources (S4Rs) to model general AMSs. We aim to simplify the liveness-enforcing supervisor for S4R by using the concept of transition cover (TC). Deadlocks in S4R can be characterized by a kind of special structural object called perfect activity circuits (PACs). First, a set of special PACs are defined as a TC and its effectness is also verified. Then, by adding a monitor with a control variable to each PAC in an effective TC (ETC), we establish a liveness-enforcing supervisor for S4R. The control variables are determined by solving an integer linear programming problem so as to increase the supervisor’s permissiveness as much as possible. Under the proposed control methodology, it is analyzed that the upper bound of the number of monitors equates to that of transitions in S4R. Especially for the system with a few transitions, since not many monitors are added, the proposed supervisor has relatively small-scaled structures or a small number of control places. In addition, we present algorithms to get an ETC from any nonlive S4R. Based on this ETC, we can design one liveness-enforcing supervisor of small size for the underlying S4R. Finally, some examples are used to illustrate the proposed approach.
- Open Access
- 9 June 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 9, 84490-84500
Learning Target Template for Acoustic Event Detection From Low-SNR Training Data
Acoustic events of interest sometimes are inherently intermixed with strong background noise, like underwater sounds or mechanical fault signals. The noise usually creates a low-SNR scenario, making it more difficult to detect the events of interest. Suffering from lack of prior knowledge, it is a difficult job to extract “correct” features from noisy acoustic mixtures for the target events. This paper addresses the detection problem for acoustic events based on low-SNR training data. A novel learning algorithm is proposed to extract the target’s template from noisy training data. Based on a target-guided band-pass filter using wavelet packets, which has been proposed in our previous work for low-SNR event detection, the template of a specific event is represented in the context of the wavelet packet energy spectrum. Template learning is then formulated as an optimization problem maximizing the detection performance which is quantified as the output SNR of the filtered signal. It is further proved that the original complex optimization problem is equivalent to a linear program which is easy to solve. A relatively sufficient database was built to simulate the noise-polluted training signals and the low-SNR detection task. Results show that the learning method can work at −15 dB and above, and the trained templates exhibit excellent detection performance comparable to the templates extracted from clean samples.
- 9 June 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 9, 84490-84500
Open AccessLearning Target Template for Acoustic Event Detection From Low-SNR Training Data
Acoustic events of interest sometimes are inherently intermixed with strong background noise, like underwater sounds or mechanical fault signals. The noise usually creates a low-SNR scenario, making it more difficult to detect the events of interest. Suffering from lack of prior knowledge, it is a difficult job to extract “correct” features from noisy acoustic mixtures for the target events. This paper addresses the detection problem for acoustic events based on low-SNR training data. A novel learning algorithm is proposed to extract the target’s template from noisy training data. Based on a target-guided band-pass filter using wavelet packets, which has been proposed in our previous work for low-SNR event detection, the template of a specific event is represented in the context of the wavelet packet energy spectrum. Template learning is then formulated as an optimization problem maximizing the detection performance which is quantified as the output SNR of the filtered signal. It is further proved that the original complex optimization problem is equivalent to a linear program which is easy to solve. A relatively sufficient database was built to simulate the noise-polluted training signals and the low-SNR detection task. Results show that the learning method can work at −15 dB and above, and the trained templates exhibit excellent detection performance comparable to the templates extracted from clean samples.
- 8 March 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 10 (3) , 2112-2120
Adaptive Recovery Mechanism for SDN Controllers in Edge-Cloud Supported FinTech Applications
Financial Technology have revolutionized the delivery and usage of the autonomous operations and processes to improve the financial services. However, the massive amount of data (often called as big data) generated seamlessly across different geographic locations can end up as a bottleneck for the underlying network infrastructure. To mitigate this challenge, software-defined network (SDN) has been leveraged in the proposed approach to provide scalability and resilience in multicontroller environment. However, in case if one of these controllers fail or cannot work as per desired requirements, then either the network load of that controller has to be migrated to another suitable controller or it has to be divided or balanced among other available controllers. For this purpose, the proposed approach provides an adaptive recovery mechanism in a multicontroller SDN setup using support vector machine-based classification approach. The proposed work defines a recovery pool based on the three vital parameters, reliability, energy, and latency. A utility matrix is then computed based on these parameters, on the basis of which the recovery controllers are selected. The results obtained prove that it is able to perform well in terms of considered evaluation parameters.
- 8 March 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 10 (3) , 2112-2120
Adaptive Recovery Mechanism for SDN Controllers in Edge-Cloud Supported FinTech Applications
Financial Technology have revolutionized the delivery and usage of the autonomous operations and processes to improve the financial services. However, the massive amount of data (often called as big data) generated seamlessly across different geographic locations can end up as a bottleneck for the underlying network infrastructure. To mitigate this challenge, software-defined network (SDN) has been leveraged in the proposed approach to provide scalability and resilience in multicontroller environment. However, in case if one of these controllers fail or cannot work as per desired requirements, then either the network load of that controller has to be migrated to another suitable controller or it has to be divided or balanced among other available controllers. For this purpose, the proposed approach provides an adaptive recovery mechanism in a multicontroller SDN setup using support vector machine-based classification approach. The proposed work defines a recovery pool based on the three vital parameters, reliability, energy, and latency. A utility matrix is then computed based on these parameters, on the basis of which the recovery controllers are selected. The results obtained prove that it is able to perform well in terms of considered evaluation parameters.
- 1 August 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 29, 801-806
Visual guided deep learning scheme for fall detection
Fall detection is an important problem in the field of public health care, which is especially crucial for instant medical service delivery to the injured elderly due to falls. Ambient camera based fall detection has been a recognized non-intrusive and publicly acceptable method, where video data is employed to discriminate fall event from daily activities. Fall detection with videos usually requires a large dataset to extract features and train the classifier. However, it is hard to collect free-living environment fall data and instead simulated falls by young people have been collected to construct the training dataset, which is controlled intentional behavior and restricted to limited quantity of samples. In addition, the existing video based fall detection methods need segment the subject first, which is inclined to be influenced by image noise, illumination variation and occlusion. To address these problems, a three dimensional convolutional neural network (3D CNN) based method for fall detection is developed which only uses kinetic data to train an automatic feature extractor. Besides the spatial feature in 2D image, the motion information from the video could also be encoded by the three dimensional convolutions over the frames. A LSTM based spatial visual attention scheme is then incorporated, which could enable the network to focus on the key regions. Sports dataset Sports-1M with no fall examples is employed to train the 3D CNN and the visual attention model is trained on the small Multiple Cameras Fall Dataset. Then the visual attention based 3D CNN is employed to extract the features from the videos with fall event and implement fall detection. Experiments have shown the superior performance of the proposed scheme on fall dataset with high detection accuracy of 100%.
- 1 August 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 29, 801-806
Visual guided deep learning scheme for fall detection
Fall detection is an important problem in the field of public health care, which is especially crucial for instant medical service delivery to the injured elderly due to falls. Ambient camera based fall detection has been a recognized non-intrusive and publicly acceptable method, where video data is employed to discriminate fall event from daily activities. Fall detection with videos usually requires a large dataset to extract features and train the classifier. However, it is hard to collect free-living environment fall data and instead simulated falls by young people have been collected to construct the training dataset, which is controlled intentional behavior and restricted to limited quantity of samples. In addition, the existing video based fall detection methods need segment the subject first, which is inclined to be influenced by image noise, illumination variation and occlusion. To address these problems, a three dimensional convolutional neural network (3D CNN) based method for fall detection is developed which only uses kinetic data to train an automatic feature extractor. Besides the spatial feature in 2D image, the motion information from the video could also be encoded by the three dimensional convolutions over the frames. A LSTM based spatial visual attention scheme is then incorporated, which could enable the network to focus on the key regions. Sports dataset Sports-1M with no fall examples is employed to train the 3D CNN and the visual attention model is trained on the small Multiple Cameras Fall Dataset. Then the visual attention based 3D CNN is employed to extract the features from the videos with fall event and implement fall detection. Experiments have shown the superior performance of the proposed scheme on fall dataset with high detection accuracy of 100%.