Yong Li

Dr. Yong Li


Research Focus & Metrics

Academic Career Length

11Years (2016-Present)

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

Representative Publications

View All Publications
1 February 2016 in Computer Methods and Programs in Biomedicine
Verified
Journal Article
Closed access
Ji-Jiang YangJi-Jiang Yang
Ji-Jiang Yang
JLJianqiang Li
Jianqiang Li
RSRuifang Shen
Ruifang Shen
YZYang Zeng
Yang Zeng
JHJian He
Jian He
QWQing Wang
Qing Wang

Verified
Journal Article
Open access
PDF file
YLYong Li
Yong Li
ZLZhaoxuan Li
Zhaoxuan Li
QMQiang Mei
Qiang Mei
PWpeng wang
peng wang
WHWenlong Hu
Wenlong Hu
YCYuhaoran Chen
Yuhaoran Chen
The intelligent maritime transportation system has emerged as a pivotal component in port management, owing to the rapid advancements in artificial intelligence and big data technology. Its essence lies in the application of digital modeling techniques, which leverage extensive ship data to facilitate efficient operations. In this regard, effective modeling and accurate prediction of the fluctuation patterns of ship traffic in multiple port regions will provide data support for trade analysis, port construction planning, and traffic safety management. In order to better express the potential interdependencies between ports, inspired by graph neural networks, this paper proposes a data-driven approach to construct a multi-port network and designs a spatiotemporal graph neural network model. The model incorporates graph attention networks and a dilated causal convolutional architecture to capture the temporal and spatial dimensions of traffic variation patterns. It also employs a gated-mechanism-based spatiotemporal bi-dimensional feature fusion strategy to handle the potential unequal relationships between the two dimensions of features. Compared to existing methods for port traffic prediction, this model fully considers the network characteristics of the overall port and fills the research gap in multi-port scenarios. In the experiments, real port ship traffic datasets were constructed using data from the Automatic Identification System (AIS) and port geographical information data for model validation. The results demonstrate that the model exhibits outstanding robustness and performs well in predicting traffic in multiple sub-regional port clusters.

1 December 2023 in Frontiers in Marine Science
Verified
Journal Article
Open access
WXWenxin Xie
Wenxin Xie
YLYong Li
Yong Li
YYYang Yang
Yang Yang
PWPeng Wang
Peng Wang
ZWZhishan Wang
Zhishan Wang
YSYaqi Sun
Yaqi Sun
The escalating greenhouse gas (GHG) emissions from maritime trade present a serious environmental and biological threat. With increasing emission reduction initiatives, such as the European Union’s incorporation of the maritime sector into the emissions trading system, both challenges and opportunities emerge for maritime transport and associated industries. To address these concerns, this study presents a model specifically designed for estimating and projecting the spatiotemporal GHG emission inventory of ships, particularly when dealing with incomplete automatic identification system datasets. In the computational aspect of the model, various data processing techniques are employed to rectify inaccuracies arising from incomplete or erroneous AIS data, including big data cleaning, ship trajectory aggregation, multi-source spatiotemporal data fusion and missing data complementation. Utilizing a bottom-up ship dynamic approach, the model generates a high-resolution GHG emission inventory. This inventory contains key attributes such as the types of ships emitting GHGs, the locations of these emissions, the time periods during which emissions occur, and emissions. For predictive analytics, the model utilizes temporal fusion transformers equipped with the attention mechanism to accurately forecast the critical emission parameters, including emission locations, time frames, and quantities. Focusing on the sea area around Tianjin port—a region characterized by high shipping activity—this study achieves fine-grained emission source tracking via detailed emission inventory calculations. Moreover, the prediction model achieves a promising loss function of approximately 0.15 under the optimal parameter configuration, obtaining a better result than recurrent neural network (RNN) and long short-term memory network (LSTM) in the comparative experiments. The proposed method allows for a comprehensive understanding of emission patterns across diverse vessel types under various operational conditions. Coupled with the prediction results, the study offers valuable theoretical and data-driven support for formulating emission reduction strategies and optimizing resource allocation, thereby contributing to sustainable maritime transformation.

21 March 2025 in Complex & Intelligent Systems
Verified
Journal Article
Open access
PDF file
BYBin Yang
Bin Yang
LDLei Ding
Lei Ding
JLJianqiang Li
Jianqiang Li
YLYong Li
Yong Li
GQGuangzhi Qu
Guangzhi Qu
BLBo Liu
Bo Liu
Digital medical imaging, particularly pathology images, is essential for cancer diagnosis but faces challenges in direct model training due to its super-resolution nature. Although weakly supervised learning has reduced the need for manual annotations, many multiple instance learning (MIL) methods struggle to effectively capture crucial spatial relationships in histopathological images. Existing methods incorporating positional information often overlook nuanced spatial correlations or use positional encoding strategies that do not fully capture the unique spatial dynamics of pathology images. To address this issue, we propose a new framework named TMIL (Transformer-based Multiple Instance Learning Network with 2D positional encoding), which leverages multiple instance learning for weakly supervised classification of histopathological images. TMIL incorporates a 2D positional encoding module, based on the Transformer, to model positional information and explore correlations between instances. Furthermore, TMIL divides histopathological images into pseudo-bags and trains patch-level feature vectors with deep metric learning to enhance classification performance. Finally, the proposed approach is evaluated on a public colorectal adenoma dataset. The experimental results show that TMIL outperforms existing MIL methods, achieving an AUC of 97.28% and an ACC of 95.19%. These findings suggest that TMIL’s integration of deep metric learning and positional encoding offers a promising approach for improving the efficiency and accuracy of pathology image analysis in cancer diagnosis.

30 November 2023 in Sensors
Verified
Journal Article
Open access
PDF file
YLYong Li
Yong Li
ZZzhiguo zhao
zhiguo zhao
YCYunli Chen
Yunli Chen
XZXiaoting Zhang
Xiaoting Zhang
RTRui Tian
Rui Tian
Previous camera self-calibration methods have exhibited certain notable shortcomings. On the one hand, they either exclusively emphasized scene cues or solely focused on vehicle-related cues, resulting in a lack of adaptability to diverse scenarios and a limited number of effective features. Furthermore, these methods either solely utilized geometric features within traffic scenes or exclusively extracted semantic information, failing to comprehensively consider both aspects. This limited the comprehensive feature extraction from scenes, ultimately leading to a decrease in calibration accuracy. Additionally, conventional vanishing point-based self-calibration methods often required the design of additional edge-background models and manual parameter tuning, thereby increasing operational complexity and the potential for errors. Given these observed limitations, and in order to address these challenges, we propose an innovative roadside camera self-calibration model based on the Transformer architecture. This model possesses a unique capability to simultaneously learn scene features and vehicle features within traffic scenarios while considering both geometric and semantic information. Through this approach, our model can overcome the constraints of prior methods, enhancing calibration accuracy and robustness while reducing operational complexity and the potential for errors. Our method outperforms existing approaches on both real-world dataset scenarios and publicly available datasets, demonstrating the effectiveness of our approach.

Verified
Journal Article
Open access
PDF file
YLYong Li
Yong Li
WZWang Zhishan
Wang Zhishan
In the extensive monitoring of maritime traffic, maritime management frequently encounters incomplete automatic identification system (AIS) data. This deficiency poses significant challenges to safety management, requiring effective methods to infer corresponding ship information. We tackle this issue using a classification approach. Due to the absence of a fixed road network at sea unlike on land, raw trajectories are difficult to convert and cannot be directly fed into neural networks. We devised a latitude–longitude gridding encoding strategy capable of transforming continuous latitude–longitude data into discrete grid points. Simultaneously, we employed a compression algorithm to further extract significant grid points, thereby shortening the encoding sequence. Utilizing natural language processing techniques, we integrate the Word2vec word embedding approach with our novel biLSTM self-attention chunk-max pooling net (biSAMNet) model, enhancing the classification of vessel trajectories. This method classifies targets into ship types and ship lengths within static information. Employing the Taiwan Strait as a case study and benchmarking against CNN, RNN, and methods based on the attention mechanism, our findings underscore our model’s superiority. The biSAMNet achieves an impressive trajectory classification F1 score of 0.94 in the ship category dataset using only five-dimensional word embeddings. Additionally, through ablation experiments, the effectiveness of the Word2vec pre-trained embedding layer is highlighted. This study introduces a novel method for handling ship trajectory data, addressing the challenge of obtaining ship static information when AIS data are unreliable.