Xiaozhu Lin

Xiaozhu Lin

Auto-generated profile, based on publicly available information

Xiaozhu Lin

School of Information Science and Technology, ShanghaiTech University, Shanghai, China

Research Focus & Metrics

Academic Career Length

19Years (2008-Present)

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

Representative Publications

View All Publications
22 November 2008 in Abdominal Radiology
Verified
Journal Article
Closed access
PDF file
HZHui Zhu
Hui Zhu
BSBei Shi
Bei Shi
MUManavendra Upadhyaya
Manavendra Upadhyaya
ZWZhiyuan Wu
Zhiyuan Wu
XLXiaozhu Lin
Xiaozhu Lin
KCKe-min Chen
Ke-min Chen

28 June 2012 in La radiologia medica
Verified
Journal Article
Closed access
PDF file
SHS. Hu
S. Hu
XLX. Lin
X. Lin
QSQ. Song
Q. Song
KCK. Chen
K. Chen

9 January 2025 in IEEE Robotics and Automation Letters
Verified
Journal Article
Closed access
XLXiaozhu Lin
Xiaozhu Lin
XLXiaopei Liu
Xiaopei Liu
YWYang Wang
Yang Wang
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
Verified
Conference Paper
Closed access
HSHuijia Song
Huijia Song
JWJiacheng Wei
Jiacheng Wei
XLXiaozhu Lin
Xiaozhu Lin
HZHuainian Zhang
Huainian Zhang
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
Verified
Conference Paper
Closed access
JWJiacheng Wei
Jiacheng Wei
HSHuijia Song
Huijia Song
XLXiaozhu Lin
Xiaozhu Lin
SJShaoning Jin
Shaoning Jin
SCSenliu Chen
Senliu Chen
TZTianqian Zhou
Tianqian Zhou
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.