Yujing Wu
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
Yujing Wu has a total of 58 co-authors. Here are the top co-authors by number of shared publications:
- Yinan Xu
Department of Electronic & Communication Engineering, Yanbian University, Yanji 133002, China
19 shared publications - Yihu Xu
Department of Electronic & Communication Engineering, Yanbian University, Yanji 133002, China
11 shared publications - Kaihang Zhang
College of Engineering, YanBian University, Yanji 133002, China
4 shared publications - Jiaoyue Chen
Department of Electronic & Communication Engineering, Yanbian University, Yanji 133002, China
3 shared publications - Suya Liu
College of Engineering, YanBian University, Yanji 133002, China
3 shared publications Yihu Xu
3 shared publications
Latest Publications
- Open Access
- 21 October 2026
- Published by MDPI AG in Journal of Marine Science and Engineering
- Vol. 14 (20) , 1974
A Physics-Guided Adaptive Bayesian Optimization Framework for Training-Free Underwater Image Enhancement
Reliable underwater visual perception plays a critical role in marine exploration, autonomous underwater vehicles, and subsea inspection. Nevertheless, underwater images are frequently degraded by severe color distortion, contrast reduction, and structural information loss due to wavelength-dependent light attenuation and scattering. Existing enhancement approaches either depend on fixed physical assumptions or require data-driven models, which often limits their adaptability across diverse underwater environments. To address these challenges, this paper presents a Physics-Guided Adaptive Bayesian Optimization (PG-ABO) framework for training-free underwater image enhancement. By combining physical degradation priors with image-specific parameter optimization, the proposed approach enables enhancement strategies to adapt dynamically to varying underwater conditions without relying on paired training data. The proposed framework incorporates an improved underwater dark channel prior with structure-aware transmission refinement to establish a physically consistent initial representation. Subsequently, a dual-path optimization strategy is constructed to generate complementary enhancement candidates by separately targeting color fidelity and structural perception. Bayesian optimization is employed to adaptively search enhancement parameters under the guidance of UCIQE and UIQM objectives. Furthermore, a robust multi-scale fusion strategy with anti-hotspot weight regulation is introduced, while a metric-aware refinement module is applied to enhance perceptual consistency and reduce enhancement artifacts. Experiments conducted on three underwater image datasets, including U45, UIEB, and LSUI, verify the effectiveness and robustness of the proposed framework across diverse underwater conditions. Consequently, the proposed method provides an adaptive, training-free, and physically motivated solution for underwater image enhancement under complex degradation conditions.
- 21 October 2026
- Published by MDPI AG in Journal of Marine Science and Engineering
- Vol. 14 (20) , 1974
Open AccessA Physics-Guided Adaptive Bayesian Optimization Framework for Training-Free Underwater Image Enhancement
Reliable underwater visual perception plays a critical role in marine exploration, autonomous underwater vehicles, and subsea inspection. Nevertheless, underwater images are frequently degraded by severe color distortion, contrast reduction, and structural information loss due to wavelength-dependent light attenuation and scattering. Existing enhancement approaches either depend on fixed physical assumptions or require data-driven models, which often limits their adaptability across diverse underwater environments. To address these challenges, this paper presents a Physics-Guided Adaptive Bayesian Optimization (PG-ABO) framework for training-free underwater image enhancement. By combining physical degradation priors with image-specific parameter optimization, the proposed approach enables enhancement strategies to adapt dynamically to varying underwater conditions without relying on paired training data. The proposed framework incorporates an improved underwater dark channel prior with structure-aware transmission refinement to establish a physically consistent initial representation. Subsequently, a dual-path optimization strategy is constructed to generate complementary enhancement candidates by separately targeting color fidelity and structural perception. Bayesian optimization is employed to adaptively search enhancement parameters under the guidance of UCIQE and UIQM objectives. Furthermore, a robust multi-scale fusion strategy with anti-hotspot weight regulation is introduced, while a metric-aware refinement module is applied to enhance perceptual consistency and reduce enhancement artifacts. Experiments conducted on three underwater image datasets, including U45, UIEB, and LSUI, verify the effectiveness and robustness of the proposed framework across diverse underwater conditions. Consequently, the proposed method provides an adaptive, training-free, and physically motivated solution for underwater image enhancement under complex degradation conditions.
- Open Access
In-Vehicle Ethernet Network Intrusion Detection Using a Feature Masking Algorithm
With the fast-paced advancement of intelligent connected vehicles (ICVs), In-Vehicle Ethernet has gradually become the core of in-vehicle network communication systems, thanks to its superior high-bandwidth data transmission performance. However, the open nature of In-Vehicle Ethernet and the intricacy of its communication protocols have brought significant challenges to the practice of network intrusion detection for this technology. To tackle the problem of network intrusion detection in In-Vehicle Ethernet, this study takes into account the data characteristics of the AVTP protocol as well as common network attack approaches. We put forward a novel intrusion detection method based on a feature mask algorithm, which is designed to enhance the overall security level of In-Vehicle Ethernet. Experimental results show that the proposed algorithm can detect 99.5% of abnormal data in In-Vehicle Ethernet. Compared with traditional anomaly detection algorithms such as the Bayesian algorithm and decision tree method, the proposed method achieves detection rate increases of 12.4% and 7.8% respectively. Compared with the state-of-the-art CNN and XGBoost algorithms, the proposed method yields a relatively modest improvement in detection rate, while reducing inference latency by 81.6% and 21.8% respectively. These findings effectively boost the network security performance of In-Vehicle Ethernet and provide a reliable foundation for safeguarding the network security of intelligent connected vehicles.
Open AccessIn-Vehicle Ethernet Network Intrusion Detection Using a Feature Masking Algorithm
With the fast-paced advancement of intelligent connected vehicles (ICVs), In-Vehicle Ethernet has gradually become the core of in-vehicle network communication systems, thanks to its superior high-bandwidth data transmission performance. However, the open nature of In-Vehicle Ethernet and the intricacy of its communication protocols have brought significant challenges to the practice of network intrusion detection for this technology. To tackle the problem of network intrusion detection in In-Vehicle Ethernet, this study takes into account the data characteristics of the AVTP protocol as well as common network attack approaches. We put forward a novel intrusion detection method based on a feature mask algorithm, which is designed to enhance the overall security level of In-Vehicle Ethernet. Experimental results show that the proposed algorithm can detect 99.5% of abnormal data in In-Vehicle Ethernet. Compared with traditional anomaly detection algorithms such as the Bayesian algorithm and decision tree method, the proposed method achieves detection rate increases of 12.4% and 7.8% respectively. Compared with the state-of-the-art CNN and XGBoost algorithms, the proposed method yields a relatively modest improvement in detection rate, while reducing inference latency by 81.6% and 21.8% respectively. These findings effectively boost the network security performance of In-Vehicle Ethernet and provide a reliable foundation for safeguarding the network security of intelligent connected vehicles.
- 25 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 26 (9) , 13145-13152
All-Fiber Multimodal Sensor for Dual-Gas and Spectral Co-Detection Based on Hollow-Core Photonic Bandgap Fiber
Accurate, non-invasive measurement of greenhouse gases is crucial for environmental monitoring and sensor networks. Traditional gas sensors are limited in terms of sensitivity and spatial resolution, and thus accurate spatiotemporal mapping of gas concentrations is difficult. In this work, we present a fully fiber-integrated multimodal sensing system combining a HC-PBF gas detection module with a UV-excited spectral analysis module. This arrangement allows for simultaneous spatially resolved monitoring of vegetation spectral signals and greenhouse gases. The HC-PBF sensor with side-hole diffusion structure provides non-invasive gas sampling, and time-division multiplexed dual-wavelength detection measures methane and carbon dioxide with 1 s integration detection limits of 0.15 ppm and 14 ppm, respectively. The system provides high sensitivity, low interference, and spatial resolution, allowing real-time integration of gas concentration and spatial data. Rice paddy field experiments demonstrate the robustness and stability of the system under complex environmental conditions and indicate a potential correlation between vegetation fluorescence ratio parameters (F735/480 and F780/480) and gas emissions. These results demonstrate that the fully fiber-integrated approach is suitable for high-precision multimodal environmental sensing and can be applied to ecological monitoring and distributed fiber-optic sensor networks.
- 25 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 26 (9) , 13145-13152
All-Fiber Multimodal Sensor for Dual-Gas and Spectral Co-Detection Based on Hollow-Core Photonic Bandgap Fiber
Accurate, non-invasive measurement of greenhouse gases is crucial for environmental monitoring and sensor networks. Traditional gas sensors are limited in terms of sensitivity and spatial resolution, and thus accurate spatiotemporal mapping of gas concentrations is difficult. In this work, we present a fully fiber-integrated multimodal sensing system combining a HC-PBF gas detection module with a UV-excited spectral analysis module. This arrangement allows for simultaneous spatially resolved monitoring of vegetation spectral signals and greenhouse gases. The HC-PBF sensor with side-hole diffusion structure provides non-invasive gas sampling, and time-division multiplexed dual-wavelength detection measures methane and carbon dioxide with 1 s integration detection limits of 0.15 ppm and 14 ppm, respectively. The system provides high sensitivity, low interference, and spatial resolution, allowing real-time integration of gas concentration and spatial data. Rice paddy field experiments demonstrate the robustness and stability of the system under complex environmental conditions and indicate a potential correlation between vegetation fluorescence ratio parameters (F735/480 and F780/480) and gas emissions. These results demonstrate that the fully fiber-integrated approach is suitable for high-precision multimodal environmental sensing and can be applied to ecological monitoring and distributed fiber-optic sensor networks.
- Open Access
- 10 February 2026
- Published by MDPI AG in Electronics
- Vol. 15 (4) , 754
Study of Network Anomaly Detection for In-Vehicle Ethernet Using Fuzzy Clustering
Along with the swift evolution of autonomous driving and internet technologies, In-Vehicle Ethernet has evolved into the core backbone network underpinning the new generation of in-vehicle networks (IVNs). Since In-Vehicle Ethernet is susceptible to a host of cybersecurity threats—such as data pilferage, data falsification, and malicious unauthorized access—it is imperative to enhance its defense capabilities. This research focuses on anomaly identification for In-Vehicle Ethernet communication networks, with a specific focus on the intrinsic data features of the AVTP protocol and potential cyber-attack vectors targeting the network. This work develops a novel network anomaly detection approach rooted in the Fuzzy clustering algorithm. This effectively enhances the cybersecurity performance of In-Vehicle Ethernet. Experimental results demonstrate that the Fuzzy clustering algorithm proposed in this study achieves 97.4% accuracy in detecting anomalous data, outperforming the traditional K-Means and OPTICS clustering algorithms by 6.4% and 14.5% respectively in anomaly detection rate. This further elevates the cybersecurity performance of In-Vehicle Ethernet and forges a robust foundation for the stable operation and iterative advancement of intelligent connected vehicles (ICVs).
- 10 February 2026
- Published by MDPI AG in Electronics
- Vol. 15 (4) , 754
Open AccessStudy of Network Anomaly Detection for In-Vehicle Ethernet Using Fuzzy Clustering
Along with the swift evolution of autonomous driving and internet technologies, In-Vehicle Ethernet has evolved into the core backbone network underpinning the new generation of in-vehicle networks (IVNs). Since In-Vehicle Ethernet is susceptible to a host of cybersecurity threats—such as data pilferage, data falsification, and malicious unauthorized access—it is imperative to enhance its defense capabilities. This research focuses on anomaly identification for In-Vehicle Ethernet communication networks, with a specific focus on the intrinsic data features of the AVTP protocol and potential cyber-attack vectors targeting the network. This work develops a novel network anomaly detection approach rooted in the Fuzzy clustering algorithm. This effectively enhances the cybersecurity performance of In-Vehicle Ethernet. Experimental results demonstrate that the Fuzzy clustering algorithm proposed in this study achieves 97.4% accuracy in detecting anomalous data, outperforming the traditional K-Means and OPTICS clustering algorithms by 6.4% and 14.5% respectively in anomaly detection rate. This further elevates the cybersecurity performance of In-Vehicle Ethernet and forges a robust foundation for the stable operation and iterative advancement of intelligent connected vehicles (ICVs).
- 5 December 2025
- Published by Elsevier in Ad Hoc Networks
- Vol. 183
A dual layer LSTM-CNN framework for real time and precise per-message intrusion detection in In-vehicle networks
- 5 December 2025
- Published by Elsevier in Ad Hoc Networks
- Vol. 183
A dual layer LSTM-CNN framework for real time and precise per-message intrusion detection in In-vehicle networks
- Open Access
Research on Network Intrusion Detection Based on Weighted Histogram Algorithm for In-Vehicle Ethernet
The Internet of Vehicles plays a crucial role in advancing intelligent transportation systems, with In-Vehicle Ethernet serving as the fundamental backbone network of the new generation of in-vehicle communication. However, In-Vehicle Ethernet faces various network security threats, including data theft, data tampering, and malicious attacks. This study focuses on network intrusion and security issues in In-Vehicle Ethernet, by analyzing the data characteristics of Audio Video Transport Protocol and potential network attack means. We innovatively propose a network intrusion detection method based on a weighted histogram algorithm. This method aims to enhance the security of In-Vehicle Ethernet. Experimental results show that the anomaly detection rate of the proposed weighted histogram algorithm in this study is 99.7%, which shows an improvement of 15.8% compared with the traditional Bayesian algorithm, and 6.9% higher than the decision tree algorithm. Thus, our approach enhances the stability and anti-attack ability of In-Vehicle Ethernet, providing a solid network security for In-Vehicle Networks.
Open AccessResearch on Network Intrusion Detection Based on Weighted Histogram Algorithm for In-Vehicle Ethernet
The Internet of Vehicles plays a crucial role in advancing intelligent transportation systems, with In-Vehicle Ethernet serving as the fundamental backbone network of the new generation of in-vehicle communication. However, In-Vehicle Ethernet faces various network security threats, including data theft, data tampering, and malicious attacks. This study focuses on network intrusion and security issues in In-Vehicle Ethernet, by analyzing the data characteristics of Audio Video Transport Protocol and potential network attack means. We innovatively propose a network intrusion detection method based on a weighted histogram algorithm. This method aims to enhance the security of In-Vehicle Ethernet. Experimental results show that the anomaly detection rate of the proposed weighted histogram algorithm in this study is 99.7%, which shows an improvement of 15.8% compared with the traditional Bayesian algorithm, and 6.9% higher than the decision tree algorithm. Thus, our approach enhances the stability and anti-attack ability of In-Vehicle Ethernet, providing a solid network security for In-Vehicle Networks.
- Open Access
A Stacked Machine Learning-Based Intrusion Detection System for Internal and External Networks in Smart Connected Vehicles
In response to the escalating threat of cyberattacks on smart connected vehicles, numerous Intrusion Detection Systems (IDSs) have emerged. However, existing IDSs often prioritize enhancing detection accuracy while overlooking the time needed for training and detection. Moreover, they may not fully leverage the combined utilization of CAN bus IDs and the data field with external network data. Consequently, these systems frequently struggle to meet the real-time demands and broader attack scenarios inherent in in-vehicle systems. To overcome these challenges, we propose a stacked-model IDS architecture deployed across the CAN bus and central gateway, capable of detecting both internal and external vehicular network attacks. The system extracts key features from in-vehicle and external network data, builds base learners (CART, LightGBM, XGBoost), and integrates them through stacking with a meta-learner. Feature selection and training efficiency are enhanced using information gain and maximal information coefficient algorithms. Experiments show that the proposed IDS achieves an average detection accuracy of 99.99% for internal CAN bus attacks and 99.81% for external network attacks, with fast detection times of 0.018 ms and 0.088 ms, respectively. These results highlight the system’s real-time capability, high accuracy, and adaptability to complex attack scenarios.
Open AccessA Stacked Machine Learning-Based Intrusion Detection System for Internal and External Networks in Smart Connected Vehicles
In response to the escalating threat of cyberattacks on smart connected vehicles, numerous Intrusion Detection Systems (IDSs) have emerged. However, existing IDSs often prioritize enhancing detection accuracy while overlooking the time needed for training and detection. Moreover, they may not fully leverage the combined utilization of CAN bus IDs and the data field with external network data. Consequently, these systems frequently struggle to meet the real-time demands and broader attack scenarios inherent in in-vehicle systems. To overcome these challenges, we propose a stacked-model IDS architecture deployed across the CAN bus and central gateway, capable of detecting both internal and external vehicular network attacks. The system extracts key features from in-vehicle and external network data, builds base learners (CART, LightGBM, XGBoost), and integrates them through stacking with a meta-learner. Feature selection and training efficiency are enhanced using information gain and maximal information coefficient algorithms. Experiments show that the proposed IDS achieves an average detection accuracy of 99.99% for internal CAN bus attacks and 99.81% for external network attacks, with fast detection times of 0.018 ms and 0.088 ms, respectively. These results highlight the system’s real-time capability, high accuracy, and adaptability to complex attack scenarios.
- Open Access
- 30 May 2025
- Published by MDPI AG in Journal of Marine Science and Engineering
- Vol. 13 (6) , 1101
A Multi-Time-Frequency Feature Fusion Approach for Marine Mammal Sound Recognition
Accurate acoustic identification of marine mammals is vital for monitoring ocean health and human impacts. Existing methods often struggle with limited single-feature representations or suboptimal fusion of multiple features. This paper proposes an Evaluation-Adaptive Weighted Multi-Head Fusion Network that integrates CQT and STFT features via a dual-branch ResNet architecture. The model enhances intra-branch features using channel attention and adaptive weighting of each branch based on its validation accuracy during training. Experiments on the Watkins Marine Mammal Sound Database show that the proposed method achieves superior performance, reaching 96.05% accuracy and outperforming baseline and attention-based fusion models. This approach offers an effective solution for multi-feature acoustic recognition in complex underwater environments.
- 30 May 2025
- Published by MDPI AG in Journal of Marine Science and Engineering
- Vol. 13 (6) , 1101
Open AccessA Multi-Time-Frequency Feature Fusion Approach for Marine Mammal Sound Recognition
Accurate acoustic identification of marine mammals is vital for monitoring ocean health and human impacts. Existing methods often struggle with limited single-feature representations or suboptimal fusion of multiple features. This paper proposes an Evaluation-Adaptive Weighted Multi-Head Fusion Network that integrates CQT and STFT features via a dual-branch ResNet architecture. The model enhances intra-branch features using channel attention and adaptive weighting of each branch based on its validation accuracy during training. Experiments on the Watkins Marine Mammal Sound Database show that the proposed method achieves superior performance, reaching 96.05% accuracy and outperforming baseline and attention-based fusion models. This approach offers an effective solution for multi-feature acoustic recognition in complex underwater environments.
- Open Access
Research on Lightweight Dynamic Security Protocol for Intelligent In-Vehicle CAN Bus
With the integration of an increasing number of outward-facing components in intelligent and connected vehicles, the open controller area network (CAN) bus environment faces increasingly severe security threats. However, existing security measures remain inadequate, and CAN bus messages lack effective security mechanisms and are vulnerable to malicious attacks. Although encryption algorithms can enhance system security, their high bandwidth consumption negatively impacts the real-time performance of intelligent and connected vehicles. Moreover, the message authentication mechanism of the CAN bus requires lengthy authentication codes, further exacerbating the bandwidth burden. To address these issues, we propose an improved dynamic compression algorithm that achieves higher compression rates and efficiency by optimizing header information processing during data reorganization. Additionally, we have proposed a novel dynamic key management approach, incorporating a dynamic key distribution mechanism, which effectively resolves the challenges associated with key management. Each Electronic Control Unit (ECU) node independently performs compression, encryption, and authentication while periodically updating its keys to enhance system security and strengthen defense capabilities. Experimental results show that the proposed dynamic compression algorithm improves the average compression rate by 2.24% and enhances compression time efficiency by 10% compared to existing solutions. The proposed security protocol effectively defends against four different types of attacks. In hardware tests, using an ECU operating at a frequency of 30 MHz, the computation time for the security algorithm on a single message was 0.85 ms, while at 400 MHz, the computation time was reduced to 0.064 ms. Additionally, for different vehicle models, the average CAN bus load rate was reduced by 8.28%. The proposed security mechanism ensures the security, real-time performance, and freshness of CAN bus messages while reducing bus load, providing a more efficient and reliable solution for the cybersecurity of intelligent and connected vehicles.
Open AccessResearch on Lightweight Dynamic Security Protocol for Intelligent In-Vehicle CAN Bus
With the integration of an increasing number of outward-facing components in intelligent and connected vehicles, the open controller area network (CAN) bus environment faces increasingly severe security threats. However, existing security measures remain inadequate, and CAN bus messages lack effective security mechanisms and are vulnerable to malicious attacks. Although encryption algorithms can enhance system security, their high bandwidth consumption negatively impacts the real-time performance of intelligent and connected vehicles. Moreover, the message authentication mechanism of the CAN bus requires lengthy authentication codes, further exacerbating the bandwidth burden. To address these issues, we propose an improved dynamic compression algorithm that achieves higher compression rates and efficiency by optimizing header information processing during data reorganization. Additionally, we have proposed a novel dynamic key management approach, incorporating a dynamic key distribution mechanism, which effectively resolves the challenges associated with key management. Each Electronic Control Unit (ECU) node independently performs compression, encryption, and authentication while periodically updating its keys to enhance system security and strengthen defense capabilities. Experimental results show that the proposed dynamic compression algorithm improves the average compression rate by 2.24% and enhances compression time efficiency by 10% compared to existing solutions. The proposed security protocol effectively defends against four different types of attacks. In hardware tests, using an ECU operating at a frequency of 30 MHz, the computation time for the security algorithm on a single message was 0.85 ms, while at 400 MHz, the computation time was reduced to 0.064 ms. Additionally, for different vehicle models, the average CAN bus load rate was reduced by 8.28%. The proposed security mechanism ensures the security, real-time performance, and freshness of CAN bus messages while reducing bus load, providing a more efficient and reliable solution for the cybersecurity of intelligent and connected vehicles.
- 23 May 2025
- Published by Springer Nature
- p. 3-11
Design of Vehicle Flow Recognition and Speed Detection System Based on Raspberry PI
- 23 May 2025
- Published by Springer Nature
- p. 3-11
Design of Vehicle Flow Recognition and Speed Detection System Based on Raspberry PI