Xiaozhu Lin
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Research Interests
Xiaozhu Lin has a total of 17 co-authors. Here are the top co-authors by number of shared publications:
- Huijia Song
College of Information Engineering, Beijing Institute of Petrochemical Technology, Beijing, China
2 shared publications - Jiacheng Wei
Nanyang technological university, Singapore, Singapore
2 shared publications - Bei Shi
Center of Reproductive Medicine, Shengjing Hospital of China Medical University, Shenyang, China
1 shared publication Huainian Zhang
Beijing Institute of Petrochemical Technology,School of Information Engineering,Beijing,China,102617
1 shared publication- Hui Zhu
Shanghai Jiao Tong University, Shanghai, China
1 shared publication - K. Chen
Shanghai Jiao Tong University, School of Medicine
1 shared publication
Latest Publications
- 9 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 10 (2) , 1992-1999
Learning Agile Swimming: An End-to-End Approach Without CPGs
The pursuit of agile and efficient underwater robots, especially bio-mimetic robotic fish, has been impeded by challenges in creating motion controllers that are able to fully exploit their hydrodynamic capabilities. This letter addresses these challenges by introducing a novel, model-free, end-to-end control framework that leverages Deep Reinforcement Learning (DRL) to enable agile and energy-efficient swimming of robotic fish. Unlike existing methods that rely on predefined trigonometric swimming patterns like Central Pattern Generators (CPG), our approach directly outputs low-level actuator commands without strong constraints, enabling the robotic fish to learn agile swimming behaviors. In addition, by integrating a high-performance Computational Fluid Dynamics (CFD) simulator with innovative sim-to-real strategies, such as normalized density calibration and servo response calibration, the proposed framework significantly mitigates the sim-to-real gap, facilitating direct transfer of control policies to real-world environments without fine-tuning. Comparative experiments demonstrate that our method achieves faster swimming speeds, smaller turn-around radii, and reduced energy consumption compared to the state-of-the-art swimming controllers. Furthermore, the proposed framework shows promise in addressing complex tasks, paving the way for more effective deployment of robotic fish in real aquatic environments.
- 9 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 10 (2) , 1992-1999
Learning Agile Swimming: An End-to-End Approach Without CPGs
The pursuit of agile and efficient underwater robots, especially bio-mimetic robotic fish, has been impeded by challenges in creating motion controllers that are able to fully exploit their hydrodynamic capabilities. This letter addresses these challenges by introducing a novel, model-free, end-to-end control framework that leverages Deep Reinforcement Learning (DRL) to enable agile and energy-efficient swimming of robotic fish. Unlike existing methods that rely on predefined trigonometric swimming patterns like Central Pattern Generators (CPG), our approach directly outputs low-level actuator commands without strong constraints, enabling the robotic fish to learn agile swimming behaviors. In addition, by integrating a high-performance Computational Fluid Dynamics (CFD) simulator with innovative sim-to-real strategies, such as normalized density calibration and servo response calibration, the proposed framework significantly mitigates the sim-to-real gap, facilitating direct transfer of control policies to real-world environments without fine-tuning. Comparative experiments demonstrate that our method achieves faster swimming speeds, smaller turn-around radii, and reduced energy consumption compared to the state-of-the-art swimming controllers. Furthermore, the proposed framework shows promise in addressing complex tasks, paving the way for more effective deployment of robotic fish in real aquatic environments.
- 18 August 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 30, 515-518
‘Pre-training+Fine-tuning’ Model-based 1/2 Folded Image Restoration
The 1/2 folded image refers to folding the original image at the halfway point along the horizontal or vertical direction, creating an image with partial overlap. The purpose of restoring 1/2 folded images is to repair folded, damaged, or partially hidden images in order to restore image integrity, recover data, analyze and process images, and perform reverse hiding and steganography analysis. In response to the restoration problem of 1/2 folded images, a model called ‘pre-training + fine-tuning’ was applied to restore folded images using unsupervised pre-training and supervised fine-tuning modes. The WGAN-GP model with gradient penalty is used for the pre-training model. A four-layer non-linear fully connected network is selected for the fine-tuning model. The experimental process consists of two stages. Firstly, the WGAN-GP network is subjected to unsupervised pre-training to obtain a generator capable of generating clear images. Then, in the fine-tuning stage, the output of the generator is used as the input for a fully connected network, and the target results of the fully connected network model are fixed for fine-tuning, aiming to restore the folded images to be close to the original ones. The applied method is validated on the MNIST and Fashion-MNIST datasets in this paper. The experimental result shows that the “pre-training + fine-tuning” mode achieves good restoration performance on 1/2 folded handwritten digit images and Fashion-MNIST images, with the maximum similarity score between the restored images and the original images is around 0.98. Moreover, this technique can enhance image quality and information integrity, expand the application areas of image processing and computer vision.
- 18 August 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 30, 515-518
‘Pre-training+Fine-tuning’ Model-based 1/2 Folded Image Restoration
The 1/2 folded image refers to folding the original image at the halfway point along the horizontal or vertical direction, creating an image with partial overlap. The purpose of restoring 1/2 folded images is to repair folded, damaged, or partially hidden images in order to restore image integrity, recover data, analyze and process images, and perform reverse hiding and steganography analysis. In response to the restoration problem of 1/2 folded images, a model called ‘pre-training + fine-tuning’ was applied to restore folded images using unsupervised pre-training and supervised fine-tuning modes. The WGAN-GP model with gradient penalty is used for the pre-training model. A four-layer non-linear fully connected network is selected for the fine-tuning model. The experimental process consists of two stages. Firstly, the WGAN-GP network is subjected to unsupervised pre-training to obtain a generator capable of generating clear images. Then, in the fine-tuning stage, the output of the generator is used as the input for a fully connected network, and the target results of the fully connected network model are fixed for fine-tuning, aiming to restore the folded images to be close to the original ones. The applied method is validated on the MNIST and Fashion-MNIST datasets in this paper. The experimental result shows that the “pre-training + fine-tuning” mode achieves good restoration performance on 1/2 folded handwritten digit images and Fashion-MNIST images, with the maximum similarity score between the restored images and the original images is around 0.98. Moreover, this technique can enhance image quality and information integrity, expand the application areas of image processing and computer vision.
- 4 August 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 01-04
Folded Handwritten Digit Recognition Based on WGAN-GP Model
The study of overlapped handwritten digit recognition algorithms is critical for improving automated recognition accuracy, improving document processing, and automating recognition systems. The majority of current research in this field is focused on detecting two overlapped handwritten numbers. However, when one handwritten digit is folded onto another, recognition becomes more difficult, and there is currently no well-established recognition algorithm for this circumstance. To solve the issue of folded digit recognition, a method is provided that reconstructs the folded handwritten digit images using Generative Adversarial Networks (GANs) and transformation optimization algorithm, followed by recognition using a recognition network. The MNIST dataset is used to validate the suggested approach. The experimental findings demonstrate that the recognition accuracy reaches 97.22%, proving the suggested approach's considerable promise in solving the recognition of folded handwritten digit images.
- 4 August 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 01-04
Folded Handwritten Digit Recognition Based on WGAN-GP Model
The study of overlapped handwritten digit recognition algorithms is critical for improving automated recognition accuracy, improving document processing, and automating recognition systems. The majority of current research in this field is focused on detecting two overlapped handwritten numbers. However, when one handwritten digit is folded onto another, recognition becomes more difficult, and there is currently no well-established recognition algorithm for this circumstance. To solve the issue of folded digit recognition, a method is provided that reconstructs the folded handwritten digit images using Generative Adversarial Networks (GANs) and transformation optimization algorithm, followed by recognition using a recognition network. The MNIST dataset is used to validate the suggested approach. The experimental findings demonstrate that the recognition accuracy reaches 97.22%, proving the suggested approach's considerable promise in solving the recognition of folded handwritten digit images.
- 28 June 2012
- Published by Springer Nature in La radiologia medica
- Vol. 117 (7) , 1242-1249
Solid pseudopapillary tumour of the pancreas in children: clinical and computed tomography manifestation
The purpose of our study was to retrospectively assess imaging features of computed tomography (CT) and clinical characteristics of children with solid pseudopapillary tumours (SPTs) of the pancreas in comparison with those of SPTs in adults.
- 28 June 2012
- Published by Springer Nature in La radiologia medica
- Vol. 117 (7) , 1242-1249
Solid pseudopapillary tumour of the pancreas in children: clinical and computed tomography manifestation
The purpose of our study was to retrospectively assess imaging features of computed tomography (CT) and clinical characteristics of children with solid pseudopapillary tumours (SPTs) of the pancreas in comparison with those of SPTs in adults.
- 22 November 2008
- Published by Springer Nature in Abdominal Radiology
- Vol. 35 (1) , 15-22
Therapeutic endoscopy of localized gastric varices: pretherapy screening and posttreatment evaluation with MDCT portography
Gastric varices are a major cause of gastrointestinal bleeding in patients with portal hypertension. Whatever therapeutic method is used, hemodynamic changes in the portal systemic shunt should be assessed. In this study, we used multi-detector row CT portography as a screening and assessment tool. A total of 85 patients with gastroscopy-confirmed gastroesophageal varices underwent multi-detector row CT portography. Patients through multi-detector row CT portography screening were recommended to therapeutic endoscopy. Multi-detector row CT portography was carried out in these patients one week before treatment and one month after treatment. The cross-sectional areas of the left gastric vein, main portal vein, superior mesenteric vein and splenic vein were measured by advanced vessel analysis software before and after treatment. Data was subjected to statistical test. Of the 85 patients who underwent multi-detector row CT portography screening, 17 had localized gastric varices with a solitary afferent vein and were recommended for therapeutic endoscopy. The changes in cross-sectional areas of the left gastric vein, main portal vein, superior mesenteric vein, and splenic vein before and after the treatment were of significant statistical difference. Multi-detector row CT portography is an effective screening and evaluating tool for therapeutic endoscopy.
- 22 November 2008
- Published by Springer Nature in Abdominal Radiology
- Vol. 35 (1) , 15-22
Therapeutic endoscopy of localized gastric varices: pretherapy screening and posttreatment evaluation with MDCT portography
Gastric varices are a major cause of gastrointestinal bleeding in patients with portal hypertension. Whatever therapeutic method is used, hemodynamic changes in the portal systemic shunt should be assessed. In this study, we used multi-detector row CT portography as a screening and assessment tool. A total of 85 patients with gastroscopy-confirmed gastroesophageal varices underwent multi-detector row CT portography. Patients through multi-detector row CT portography screening were recommended to therapeutic endoscopy. Multi-detector row CT portography was carried out in these patients one week before treatment and one month after treatment. The cross-sectional areas of the left gastric vein, main portal vein, superior mesenteric vein and splenic vein were measured by advanced vessel analysis software before and after treatment. Data was subjected to statistical test. Of the 85 patients who underwent multi-detector row CT portography screening, 17 had localized gastric varices with a solitary afferent vein and were recommended for therapeutic endoscopy. The changes in cross-sectional areas of the left gastric vein, main portal vein, superior mesenteric vein, and splenic vein before and after the treatment were of significant statistical difference. Multi-detector row CT portography is an effective screening and evaluating tool for therapeutic endoscopy.