YBYun Bu

Yun Bu

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

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Yun Bu has a total of 7 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Mitigating the Vanishing Gradient Problem Using a Pseudo-Normalizing Method

    by Yun Bu, Wenbo Jiang, Gang Lu, Qiang Zhang

    When training a neural network, the choice of activation function can greatly impact its performance. A function with a larger derivative may cause the coefficients of the latter layers to deviate further from the calculated direction, making deep learning more difficult to train. However, an activation function with a derivative amplitude of less than one can result in the problem of a vanishing gradient. To overcome this drawback, we propose the application of pseudo-normalization to enlarge some gradients by dividing them by the root mean square. This amplification is performed every few layers to ensure that the amplitudes are larger than one, thus avoiding the condition of vanishing gradient and preventing gradient explosion. We successfully applied this approach to several deep learning networks with hyperbolic tangent activation for image classifications. To gain a deeper understanding of the algorithm, we employed interpretability techniques to examine the network’s prediction outcomes. We discovered that, in contrast to popular networks that learn picture characteristics, the networks primarily employ the contour information of images for categorization. This suggests that our technique can be utilized in addition to other widely used algorithms.


  • Top Cited Papers
    Open Access

    Application of Deep Learning in the Phase Processing of Digital Holographic Microscopy

    by Wenbo Jiang, Lirui Liu, Yun Bu

    Digital holographic microscopy (DHM) provides numerous advantages, such as noninvasive sample analysis, real-time dynamic detection, and three-dimensional (3D) reconstruction, making it a valuable tool in fields such as biomedical research, cell mechanics, and environmental monitoring. To achieve more accurate and comprehensive imaging, it is crucial to capture detailed information on the microstructure and 3D morphology of samples. Phase processing of holograms is essential for recovering phase information, thus making it a core component of DHM. Traditional phase processing techniques often face challenges, such as low accuracy, limited robustness, and poor generalization. Recently, with the ongoing advancements in deep learning, addressing phase processing challenges in DHM has become a key research focus. This paper provides an overview of the principles behind DHM and the characteristics of each phase processing step. It offers a thorough analysis of the progress and challenges of deep learning methods in areas such as phase retrieval, filtering, phase unwrapping, and distortion compensation. The paper concludes by exploring trends, such as ultrafast 3D holographic reconstruction, high-throughput holographic data analysis, multimodal data fusion, and precise quantitative phase analysis.


  • Open Access

    Research on the Identification and Classification of Marine Debris Based on Improved YOLOv8

    by Wenbo Jiang, Lusong Yang, Yun Bu

    Autonomous underwater vehicles equipped with target recognition algorithms are a primary means of removing marine debris. However, due to poor underwater visibility, light scattering by suspended particles, and the coexistence of organisms and debris, current methods have problems such as poor recognition and classification effects, slow recognition speed, and weak generalization ability. In response to these problems, this article proposes a marine debris identification and classification algorithm based on improved YOLOv8. The algorithm incorporates the CloFormer module, a context-aware local enhancement mechanism, into the backbone network, fully utilizing shared and context-aware weights. Consequently, it enhances high- and low-frequency feature extraction from underwater debris images. The proposed C2f-spatial and channel reconstruction (C2f-SCConv) module combines the SCConv module with the neck C2f module to reduce spatial and channel redundancy in standard convolutions and enhance feature representation. WIoU v3 is employed as the bounding box regression loss function, effectively managing low- and high-quality samples to improve overall model performance. The experimental results on the TrashCan-Instance dataset indicate that compared to the classical YOLOv8, the mAP@0.5 and F1 scores are increased by 5.7% and 6%, respectively. Meanwhile, on the TrashCan-Material dataset, the mAP@0.5 and F1 scores also improve, by 5.5% and 5%, respectively. Additionally, the model size has been reduced by 12.9%. These research results are conducive to maintaining marine life safety and ecosystem stability.


  • Mini-UAV Movement Classification Based on Sparse Decomposition of Micro-Doppler Signature

    by Gang Lu, Yun Bu

    It is necessary for radar sensors used in security and privacy surveillance systems to determine the movements of mini-unmanned aerial vehicles (UAVs) to evaluate and analyze their flight intent or purpose. For a typical quadrotor, its movement depends on the different rotation rates and directions of the four rotors individually positioned at the end of the cross frame. To extract the micro-Doppler signature of the multiple rotors, we define the exponential complex sinusoidal basis (ECSB) according to the modulation properties of the micro-Doppler echo. This allows us to convert the parameter estimation of the multidimensional signal into a sparse decomposition process in the 1-D space of the signal. Based on this, the micro-Doppler signal is decomposed using the proposed exponential orthogonal matching pursuit (EOMP). The approach decomposes the signal’s exponent into a series of complex sinusoidal components, and the sparse solution can accurately indicate the rotation status of the UAV rotors. To assess the performance of the proposed method, two machine learning (ML) classification models, support vector machine (SVM) and decision tree (DT), are investigated. The proposed approach has been validated using simulation and experimental data. The results indicate that the SVM model outperforms the DT model in terms of classification performance, achieving an accuracy of 97.3%. These findings suggest that the approach could be a promising tool for surveilling UAVs.


  • Open Access

    A Review of Microsphere Super-Resolution Imaging Techniques

    by Wenbo Jiang, Jingchun Wang, Yidi Yang, Yun Bu

    Conventional optical microscopes are only able to resolve objects down to a size of approximately 200 nm due to optical diffraction limits. The rapid development of nanotechnology has increased the demand for greater imaging resolution, with a need to break through those diffraction limits. Among super-resolution techniques, microsphere imaging has emerged as a strong contender, offering low cost, simple operation, and high resolution, especially in the fields of nanodevices, biomedicine, and semiconductors. However, this technology is still in its infancy, with an inadequate understanding of the underlying principles and the technology’s limited field of view. This paper comprehensively summarizes the status of current research, the advantages and disadvantages of the basic principles and methods of microsphere imaging, the materials and preparation processes, microsphere manipulation methods, and applications. The paper also summarizes future development trends.