CYChengyu Yang

Chengyu Yang

*This is an algorithmically generated author record based on publicly available information.

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


Chengyu Yang has a total of 14 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • DML-TSCRT Algorithm for Long-Tailed Distributed Anchor Damage Event Recognition in Submarine Cables

    by Chunying Xu, Ruixin Liang, Xinjie Wu, Taoyu Wen, Chengyu Yang, Yu Zhou, Chuliang Wei, Yi Shi

    In submarine cable safety monitoring, anchor damage events are rare, leading to a long-tailed distribution that challenges event identification. To address this issue, this study introduces the Deep Mutual Learning-Time Series Classifier Re-Training (DML-TSCRT) model, leveraging Fiber Bragg Grating (FBG) sensing technology., and proposes a deep mutual learning-time series classifier re-training (DML-TSCRT) model algorithm. This end-to-end, high-performance model features low computational cost and integrates time-series data augmentation, classifier re-training, and mutual learning. The effectiveness and superiority of the proposed method are validated through comprehensive experiments and comparative tests. In the training set with a head-tail sample quantity ratio of 12:1, the best accuracy reached 97.69$\%$, surpassing the baseline model, bidirectional gated recurrent unit (Bi-GRU), trained on the complete training set with an accuracy of 97.30$\%$. Its accuracy was also significantly improved compared to other models in the cases of 24:1 and an extremely small-sample head-tail ratio of 60:1. This study provides a new solution for accurately identifying submarine cable anchor damage events in small and extremely small-sample scenarios, thereby enriching the theory and methods of small-sample event identification.


  • Research on the Key Technology of Fishermen Safety Guarantee System

    by Chengyu Yang, Deshan Chen, Jie Man, Xinping Yan, Jinglong Zhao

    The safety of fishermen on fishing vessels is always at risk due to potential collisions with merchant vessels. The lack of timely information about incoming ships during fishing operations and sleeping can lead to disastrous consequences. This paper proposes a fishermen safety guarantee system that utilizes wearable devices to alert fishermen about the presence of incoming ships. The system involves three terminals: fishing vessel terminal, shore-based terminal, and fishermen terminal. The system utilizes sensor data from bracelets worn by fishermen and an algorithm to analyze the fishermen behavior and evaluate the fishermen defense ability, then combines the fishermen defense ability level and the collision risk level to evaluate fishermen comprehensive risk level. The system adopts the idea of modular design, constructs from the aspects of framework design, architecture, hardware design, software design and modeling methods. This system helps fishermen to be more aware of their surroundings, accurately assess the current encounter stage, and understand their corresponding duties, ultimately reducing the risk of collisions and ensuring the safety of fishermen.


  • A Hybrid Model Integrating CNN–BiLSTM and CBAM for Anchor Damage Events Recognition of Submarine Cables

    by Chunying Xu, Ruixin Liang, Xinjie Wu, Chen Cao, Jiawang Chen, Chengyu Yang, Yu Zhou, Taoyu Wen, Hongjian Lv, Chuliang Wei

    Strain and acceleration signals are essential for accurate event recognition along submarine cables. However, concise identification still poses challenges for the prompt recognition and classification of anchor smashing and hooking events with multiple types of sensors and multiple locations. For these reasons, this paper proposes a hybrid model that combines convolutional neural networks-bidirectional long short-term memory (CNN-BiLSTM) and a convolutional block attention module (CBAM) to instantaneously identify and organise anchor smashing and hooking events. Eight different categories of data were selected as data samples and collected from multiple Fiber Bragg Grating (FBG) strain sensors and accelerometers at four different locations. The results demonstrated that the recognition best accuracy of the method could reach 98.95%. This method has a better identification rate than the existing schemes used for the same purposes, confirming the validity and reliability of the proposed hybrid model.