YWYushan Wu

Yushan Wu

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

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Yushan Wu has a total of 10 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    FNIRS‐Based Energy Landscape Analysis to Signify Brain Activity Dynamics of Individuals With Depression

    by Yushan Wu, Shi Qiao, Jitao Zhong, Lu Zhang, Juan Wang, Bin Hu, Hong Peng

    Background: Major depressive disorder (MDD) is one of the most common mental disorders, and the number of individuals with MDD (MDDs) continues to increase. Therefore, there is an urgent need for an objective characterization and real‐time detection method for depression. Functional near‐infrared spectroscopy (fNIRS) is a non‐invasive tool, which is widely used in depression research. However, the process of how the brain activity of MDDs changes in response to external stimuli based on fNIRS signals is not yet clear.Method: Energy landscape (EL) can describe the brain dynamics under task conditions by assigning energy values to each state. The higher the energy value, the lower the probability of the state occurring. This study compares the EL features of 60 MDDs with 60 healthy controls (HCs).Results: Compared to HCs, MDDs have more local minima, smaller energy differences, smaller variations in basin sizes, and longer duration in the basin of global minimum (GM). The classification results indicate that using the four features above for depression detection yields an accuracy of 86.53%. Simultaneously, there are significant differences between the two groups in the duration of the major states.Conclusion: The dynamic brain networks of MDDs exhibit more constraints and lower degrees of freedom, which might be associated with depressive symptoms such as negative emotional bias and rumination. In addition, we also demonstrate the strong depression detection capability of EL features, providing a possibility for their application in clinical diagnosis.


  • Top Cited Papers

    DepMSTAT: Multimodal Spatio-Temporal Attentional Transformer for Depression Detection

    by Yongfeng Tao, Minqiang Yang, Huiru Li, Yushan Wu, Bin Hu

    Depression is one of the most common mental illnesses, but few of the currently proposed in-depth models based on social media data take into account both temporal and spatial information in the data for the detection of depression. In this paper, we present an efficient, low-covariance multimodal integrated spatio-temporal converter framework called DepMSTAT, which aims to detect depression using acoustic and visual features in social media data. The framework consists of four modules: a data preprocessing module, a token generation module, a Spatial-Temporal Attentional Transformer (STAT) module, and a depression classifier module. To efficiently capture spatial and temporal correlations in multimodal social media depression data, a plug-and-play STAT module is proposed. The module is capable of extracting unimodal spatio-temporal features and fusing unimodal information, playing a key role in the analysis of acoustic and visual features in social media data. Through extensive experiments on a depression database (D-Vlog), the method in this paper shows high accuracy (71.53%) in depression detection, achieving a performance that exceeds most models. This work provides a scaffold for studies based on multimodal data that assists in the detection of depression.


  • Trial Selection Tensor Canonical Correlation Analysis (TSTCCA) for Depression Recognition With Facial Expression and Pupil Diameter

    by Minqiang Yang, Yushan Wu, Yongfeng Tao, Xiping Hu, Bin Hu

    Facial expressions have been widely used for depression recognition because it is intuitive and convenient to access. Pupil diameter contains rich emotional information that is already reflected in facial video streams. However, the spatiotemporal correlation between pupillary changes and facial behavior changes induced by emotional stimuli has not been explored in existing studies. This paper presents a novel multimodal fusion algorithm - Trial Selection Tensor Canonical Correlation Analysis (TSTCCA) to optimize the feature space and build a more robust depression recognition model, which innovatively combines the spatiotemporal relevance and complementarity between facial expression and pupil diameter features. TSTCCA explores the interaction between trials and obtains an effective fusion representation of two modalities from a trial subset related to depression. The experimental results show that TSTCCA achieves the highest accuracy of 78.81% with the subset of 25 trials.