GLGuangsheng Luo

Guangsheng Luo

*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


Guangsheng Luo has a total of 37 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • A UMAP-driven framework for depression conversation audio separation

    by Guangsheng Luo, Lifeng Wang, Naixing Fu, Zhijun Fang

  • Audio multi‐feature fusion detection for depression based on graph convolutional networks

    by Guangsheng Luo, Xianda Ma, Jun Yea, Yang Liu, Yiwei Xia, Chengrun Li, Yifang Kuang, Ruyuan Zhang, Siyu Lou, Kai Yu, et al.

    Depression is a prevalent mental disorder, and early detection and diagnosis are crucial for its prevention and treatment. Speech‐based depression detection represents an efficient and convenient approach within the current landscape of computer‐aided detection methods. However, challenges remain in effectively and reliably extracting features and classifying speech patterns to distinguish individuals with depression from those without. This paper introduces an audio feature set for depression analysis, referred to as SJTU‐LWDLab DACD. Based on this feature set, we propose a novel method for identifying patients with depression using summed graph convolutional networks to mitigate inaccuracies that arise from the loss of spatial features, such as height and depth, during the structured fusion of multiple depression audio features. Experimental results demonstrate that the accuracy of depression recognition in speech can reach 92.4%. The method proposed in this paper provides objective indicators and a foundation for the auxiliary identification of depression.


  • Open Access

    Survey of Architectural Floor Plan Retrieval Technology Based on 3ST Features

    by Hongxing Ling, Guangsheng Luo, Nanrun Zhou, Xiaoyan Jiang

    Feature retrieval technology for building floor plans has garnered significant attention in recent years due to its critical role in the efficient management and execution of construction projects. This paper presents a comprehensive exploration of four primary features essential for the retrieval of building floor plans: semantic features, spatial features, shape features, and texture features (collectively referred to as 3ST features). The extraction algorithms and underlying principles associated with these features are thoroughly analyzed, with a focus on advanced methods such as wavelet transforms and Fourier shape descriptors. Furthermore, the performance of various retrieval algorithms is evaluated through rigorous experimental analysis, offering valuable insights into optimizing the retrieval of building floor plans. Finally, this study outlines prospective directions for the advancement of feature retrieval technology in the context of floor plans.


  • Open Access

    Survey of Architectural Floor Plan Retrieval Technology Based on 3ST Features

    by Xing Hong Ling, Sheng Guang Luo, Run Nan Zhou, Yan Xiao Jiang

    The feature retrieval technology for building floor plans has garnered significant attention in recent years. Efficient information retrieval is essential for the effective management and execution of construction projects. This paper presents a comprehensive exploration of four primary features in the retrieval of building floor plans: Semantic features, Spatial features, Shape features, and Texture features(3ST features). The extraction algorithms and principles associated with these features are analyzed, and relevant methods, such as wavelet transforms and Fourier shape descriptions, are discussed. Additionally, the performance of various retrieval algorithms is evaluated through experimental analysis, providing valuable insights for the retrieval of building floor plans. Finally, this study anticipates future directions for the development of feature retrieval technology in floor plans.

  • Top Cited Papers

    Novel multiple color images encryption and decryption scheme based on a bit-level extension algorithm

    by Nan-Run Zhou, Long-Long Hu, Zhi-Wen Huang, Meng-Meng Wang, Guang-Sheng Luo


  • Open Access

    A Survey of Graph Federation Learning for Data Privacy Security Scenarios

    by Guangsheng Luo, ZhiJun Fang, Xiaoli Zhao, Mingxuan Chen

    In recent years, the research on Graph Neural Networks(GNNs) and Federated Learning(FL) has become more and more mature. However, these studies rely heavily on training data. With the improvement of user data privacy awareness and the emphasis on data security at the national level, the training data has become relatively large. difficulty. Moreover, in practical application scenarios, most of the data is unstructured, making it very important to adopt GNNs to learn representations. This paper will give a comprehensive overview of the fusion learning algorithm of GNNs and FL under the framework of distributed machine learning from the perspective of data privacy and security. First, an overview of the current challenges of graph federated learning(GFL); then, an in-depth analysis of GFL methods, and an extended exploration of the topology of graphs; then, focus on several graph-structured federated learning privacy calculations, communication mechanisms, etc. Secondly, it makes a comparative analysis of the common methods of GFL, experimental data sets and experimental evaluations; finally, this paper looks forward to the research hotspots of GFL in combination with privacy and security.


  • Open Access

    MetaGNN-Based Medical Records Unstructured Specialized Vocabulary Few-Shot Representation Learning

    by Hongxing Ling, Guangsheng Luo, Yu Yang

    With the continuous breakthroughs in artificial intelligence technology, it has become easier to extract general-purpose knowledge using machine learning, but it is a challenging task to extract and learn small samples of knowledge in medical expertise. On the one hand, it is difficult to represent medical expertise entities, and on the other hand, the training samples of such expertise are small, and deep learning methods often require a large number of samples to complete the learning task. To this end, we proposes a graph network learning method for specialized vocabulary representation. Specifically, a contextual knowledge representation model based on graph meta-learning is proposed, which combines text, phrase, vocabulary, and other information to solve the problem of sparse data of medical electronic medical record entities that cannot be extracted and learned. In this method, a text-independent lexical representation learning method, a context-aware graph neural network, and a combined LSTM language model are used to model information from different perspectives as a way to learn semantic representations of professional discourse entities. The experimental results show that the accuracy of the method outperforms other similar methods and proves its effectiveness.


  • Open Access

    Analysis and Research Based on Instrument Drift Data

    by Guangsheng Luo, Chunyang Ruan, Yu Yang, Wenwei Li

    Instruments and meters are used to inspect, measure, control, analyze, calculate and display the physical quantity, chemical quantity, biomass, electrical parameters, geometric quantity, and movement status of the object under test. Its applications cover a wide range of industries, agriculture, transportation, science, and technology, etc., and can be divided into electrical instruments, optical instruments, laboratory instruments, analytical instruments, testing machines, industrial instruments, etc. It assumes the task of gatekeeper and guide in the construction of the national economy. The analysis and research techniques of this article are based on the professional data of power plant industrial instrumentation. This paper presents an overview of various analysis methods of instrument data, and in-depth analysis of time correlation and coverage analysis, outlier analysis, etc. We give the statistical analysis process of drift data, focusing on the process of the AFAL method; We also described the drift algorithm of random behavior and deviation behavior and explored and discussed the analysis tools and data analysis results of the power plant industry professional data. We have designed a set of application systems for instrument data import, export, storage, and analysis, which can store instrument calibration data onto a Hadoop database in a prescribed format. Which provides great reference values for the calibration of instrument data. Finally, it looks forward to the analysis and research direction and development trend of industrial big data.


  • Open Access

    Semantic-Aware Graph Convolutional Networks for Clinical Auxiliary Diagnosis and Treatment of Traditional Chinese Medicine

    by Chunyang Ruan, Yingpei Wu, Yun Yang, Guangsheng Luo

    Traditional Chinese Medicine (TCM) clinical informatization focuses on serving user-oriented health knowledge and facilitating online diagnosis. Regularities are hidden in clinical knowledge play a significant role in the improvement of the TCM informatization service. However, many regularities can hardly be discovered because of specific data-challenges in TCM prescriptions at present. Therefore, in this article, we propose an end-to-end model, called Semantic-aware Graph Convolutional Networks (SaGCN) model, to learn the latent regularities in three steps: (1) We first construct a heterogeneous graph based on prescriptions; (2) We stack Semantic-aware graph convolution to learn effective low-dimensional representations of nodes by meta-graphs and self-attention; (3) With the learned representations, we can detect regularities accurately by clustering and linked prediction. To the best of our knowledge, this is the first study to use metagraph and graph convolutional networks for modeling TCM clinical data and diagnosis prediction. Experimental results on three real datasets demonstrate SaGCN outperforms the state-of-the-art models for clinical auxiliary diagnosis and treatment.


  • Open Access

    Relation Extraction for Chinese Clinical Records Using Multi-View Graph Learning

    by Chunyang Ruan, Yingpei Wu, Guang Sheng Luo, Yun Yang, Pingchuan Ma.

    Relation extraction is a necessary step in obtaining information from clinical medical records. In the medical domain, there have been several studies on relation extraction in modern medicine clinical notes written in English. However, very limited relation extraction research has been conducted on clinical notes written in Chinese, especially traditional Chinese medicine (TCM) clinical records (e.g., herb-symptom, herb-disease). Instead of independently extracting each relation from a single sentence or text, we propose to globally and reasonably extract multiple types of relations from the Chines clinical records with a novel heterogeneous graph representation learning method. Specifically, we first construct multiple view medical entity graphs based on the co-occurring relations, knowledge obtained from the clinic, and domain texts with the corresponding information of two medical entities from the Chinese clinical records, in which each edge is a candidate relation; we then build a Graph Convolutional Network (GCN)-based representation learning with the attention mechanism to simultaneously infer the existence of all the edges via classification. The experimental data were obtained from the Chinese medical records and literature provided by previous work. The main experimental results on Chinese clinical records show that our proposed model’s precision, recall, and F1-score reach 10.2%, 13.5%, 12.6%, demonstrating significant improvements over state-of-the-art.