Zhu Li

Prof. Dr. Zhu Li

Hangzhou Dianzi University
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
21 October 2020 in Sensors
Verified
Journal Article
Open access
PDF file
Zhu LiZhu Li
Zhu Li
Yisha ZhouYisha Zhou
Yisha Zhou
Qinghua ShengQinghua Sheng
Qinghua Sheng
Kunjian ChenKunjian Chen
Kunjian Chen
JHJian Huang
Jian Huang
Automatic reading of pointer meters is of great significance for efficient measurement of industrial meters. However, existing algorithms are defective in the accuracy and robustness to illumination shooting angle when detecting various pointer meters. Hence, a novel algorithm for adaptive detection of different pointer meters was presented. Above all, deep learning was introduced to detect and recognize scale value text in the meter dial. Then, the image was rectified and meter center was determined based on text coordinate. Next, the circular arc scale region was transformed into a linear scale region by polar transform, and the horizontal positions of pointer and scale line were obtained based on secondary search in the expanded graph. Finally, the distance method was used to read the scale region where the pointer is located. Test results showed that the algorithm proposed in this paper has higher accuracy and robustness in detecting different types of meters.

21 June 2023 in Sensors
Verified
Journal Article
Open access
PDF file
XJXiao Jiang
Xiao Jiang
HYHaibin Yu
Haibin Yu
yaxin zhangyaxin zhang
yaxin zhang
MPMian Pan
Mian Pan
Zhu LiZhu Li
Zhu Li
SLShuaishuai Lv
Shuaishuai Lv
This paper presents an efficient underwater image enhancement method, named ECO-GAN, to address the challenges of color distortion, low contrast, and motion blur in underwater robot photography. The proposed method is built upon a preprocessing framework using a generative adversarial network. ECO-GAN incorporates a convolutional neural network that specifically targets three underwater issues: motion blur, low brightness, and color deviation. To optimize computation and inference speed, an encoder is employed to extract features, whereas different enhancement tasks are handled by dedicated decoders. Moreover, ECO-GAN employs cross-stage fusion modules between the decoders to strengthen the connection and enhance the quality of output images. The model is trained using supervised learning with paired datasets, enabling blind image enhancement without additional physical knowledge or prior information. Experimental results demonstrate that ECO-GAN effectively achieves denoising, deblurring, and color deviation removal simultaneously. Compared with methods relying on individual modules or simple combinations of multiple modules, our proposed method achieves superior underwater image enhancement and offers the flexibility for expansion into multiple underwater image enhancement functions.

23 February 2023 in Medical Engineering & Physics
Verified
Journal Article
Closed access
YWYanwen Wang
Yanwen Wang
JYJiayu Yang
Jiayu Yang
MCMiao Cai
Miao Cai
XLXiaoli Liu
Xiaoli Liu
KLKang Lu
Kang Lu
Zhu LiZhu Li
Zhu Li
Essential tremor (ET) is one of the most common neurological disorders, and its mainly clinical symptoms, including patient hand's kinetic tremor, dystonia, ataxia, etc., would influence the daily life of patients inordinately. Current ET diagnosis highly replies on the clinical evaluation and neurological examination, so the objective measurement indicators are particularly important in the auxiliary diagnosis of ET. In this research, the Archimedes spiral line freehand sketching samples without template assistance is collected and the Convolutional Neural Network (CNN) model of optimized structure is adopted to fully analyze the tremor, spacing of turns, shape, etc. shown in the handwriting samples of patients with ET, including the following main process: characteristics extraction, model visualization and subregional relevance evaluation. Dropout is used as a regularization technique in the network structure. The test group consisted of 50 patients with confirmed ET and the control group consisted of 40 healthy individuals. The main research objectives of this paper comprise two points: on the one hand, to achieve effective automatic classification of patients with ET and healthy controls using a scheme combining deep learning and simple hand mapping for the purpose of primary disease screening; on the other hand, to design sub-regional automatic classification experiments to demonstrate that Archimedean spiral hand drawings of patients with ET do have distinct local features, and to lay the experimental foundation for future hand drawing-based automatic aid for the identification of a variety of neurodegenerative diseases. Our model's average accuracy rate in test set reaches 89.3%, and average AUC is 0.972, with favorable stability and generalization performance. Besides, subregional characteristics recognition proofs that the spiral line samples of most of the patients with ET show more category-related characteristics in the local area of upper right, which provides evidences and theory update for predecessors' medical research.

6 April 2022 in Surgical and Radiologic Anatomy
Verified
Journal Article
Closed access
PDF file
LPLei Pan
Lei Pan
KCKunjian Chen
Kunjian Chen
ZZZepei Zheng
Zepei Zheng
YZYe Zhao
Ye Zhao
PYPanfeng Yang
Panfeng Yang
SWSufan Wu
Sufan Wu

17 September 2021 in Sensors
Verified
Journal Article
Open access
PDF file
WCWenyu Cai
Wenyu Cai
DZDongyang Zhao
Dongyang Zhao
MZMeiyan Zhang
Meiyan Zhang
YXYinan Xu
Yinan Xu
Zhu LiZhu Li
Zhu Li
As the intensity of work increases, many of us sit for long hours while working in the office. It is not easy to sit properly at work all the time and sitting for a long time with wrong postures may cause a series of health problems as time goes by. In addition, monitoring the sitting posture of patients with spinal disease would be beneficial for their recovery. Accordingly, this paper designs and implements a sitting posture recognition system from a flexible array pressure sensor, which is used to acquire pressure distribution map of sitting hips in a real-time manner. Moreover, an improved self-organizing map-based classification algorithm for six kinds of sitting posture recognition is proposed to identify whether the current sitting posture is appropriate. The extensive experimental results verify that the performance of ISOM-based sitting posture recognition algorithm (ISOM-SPR) in short outperforms that of four kinds of traditional algorithms including decision tree-based (DT), K-means-based (KM), back propagation neural network-based (BP), self-organizing map-based (SOM) sitting posture recognition algorithms. Finally, it is proven that the proposed system based on ISOM-SPR algorithm has good robustness and high accuracy.

9 April 2025 in Medical Engineering & Physics
Verified
Journal Article
Closed access
XJXiao Jiang
Xiao Jiang
HYHaibin Yu
Haibin Yu
JYJiayu Yang
Jiayu Yang
XLXiaoli Liu
Xiaoli Liu
Zhu LiZhu Li
Zhu Li
Parkinson's disease (PD) remains a condition without a cure, though its early manifestations can be managed effectively by medical professionals. This underscores the significance of early detection of PD. It has been widely demonstrated that handwriting analysis is a promising avenue for early PD diagnosis. In recent research, there has been a pivot towards leveraging artificial intelligence (AI) technologies for analyzing handwriting images to aid in diagnosing the disease. This study introduces an innovative network architecture specifically designed to capture the nuances of tremor and irregular spacing characteristic of PD patients' handwriting. By incorporating an attention mechanism, this network is capable of prioritizing different areas within the handwriting feature map, according to their diagnostic relevance. This approach significantly enhances the accuracy of detecting PD through handwriting analysis, with our model achieving an impressive mean accuracy rate of 96.5 %. When compared to traditional convolutional neural networks, our attention-based continuous convolutional network model demonstrates a substantial increase in diagnostic precision.