Yunchao Gu

Dr. Yunchao Gu


Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
23 February 2022 in Frontiers in Education
Verified
Journal Article
Open access
YSYang Shen
Yang Shen
ZWZhaoxue Wang
Zhaoxue Wang
MLMing Li
Ming Li
JYJing Yuan
Jing Yuan
YGYunchao Gu
Yunchao Gu
This paper assesses the impact of emotional arousal on learning through a virtual reality video of geography immersion learning. Validity was measured with traditional questionnaire data and using electroencephalography (EEG). Twenty-four human subjects were recruited and presented with eight geography immersive learning videos with different affective tendencies. EEG data of the subjects were collected while they were watching the videos. After the video watching, subjects were requested to fill in an emotion scale, a learning motivation scale, and a mind flow experience. The results of the study show that VR video learning materials can well induce the positive and negative emotions of the subjects. Compared with negative emotions, the alpha band power in the frontal lobe of the brain, beta and gamma bands in the temporal lobe region is significantly higher under positive emotions. In addition, the results of the subjective scales indicate that subjects have stronger intrinsic motivations and better flow experiences under positive emotions. However, there was no significant difference for the immersion under positive and negative emotions. Our findings demonstrate the usability of teaching virtual reality situational geography stories and the broad value of using this teaching method for future instruction.

16 August 2023 in Bioengineering
Verified
Journal Article
Open access
PDF file
YGYunchao Gu
Yunchao Gu
RLRenyu Li
Renyu Li
XWXinliang Wang
Xinliang Wang
ZZZhong Zhou
Zhong Zhou
Automatic medical report generation based on deep learning can improve the efficiency of diagnosis and reduce costs. Although several automatic report generation algorithms have been proposed, there are still two main challenges in generating more detailed and accurate diagnostic reports: using multi-view images reasonably and integrating visual and semantic features of key lesions effectively. To overcome these challenges, we propose a novel automatic report generation approach. We first propose the Cross-View Attention Module to process and strengthen the multi-perspective features of medical images, using mean square error loss to unify the learning effect of fusing single-view and multi-view images. Then, we design the module Medical Visual-Semantic Long Short Term Memorys to integrate and record the visual and semantic temporal information of each diagnostic sentence, which enhances the multi-modal features to generate more accurate diagnostic sentences. Applied to the open-source Indiana University X-ray dataset, our model achieved an average improvement of 0.8% over the state-of-the-art (SOTA) model on six evaluation metrics. This demonstrates that our model is capable of generating more detailed and accurate diagnostic reports.


20 September 2023 in Bioengineering
Verified
Journal Article
Open access
PDF file
RLRenyu Li
Renyu Li
YGYunchao Gu
Yunchao Gu
XWXinliang Wang
Xinliang Wang
Pan junjunPan junjun
Pan junjun
Accurate identification of lesions and their use across different medical institutions are the foundation and key to the clinical application of automatic diabetic retinopathy (DR) detection. Existing detection or segmentation methods can achieve acceptable results in DR lesion identification, but they strongly rely on a large number of fine-grained annotations that are not easily accessible and suffer severe performance degradation in the cross-domain application. In this paper, we propose a cross-domain weakly supervised DR lesion identification method using only easily accessible coarse-grained lesion attribute labels. We first propose the novel lesion-patch multiple instance learning method (LpMIL), which leverages the lesion attribute label for patch-level supervision to complete weakly supervised lesion identification. Then, we design a semantic constraint adaptation method (LpSCA) that improves the lesion identification performance of our model in different domains with semantic constraint loss. Finally, we perform secondary annotation on the open-source dataset EyePACS, to obtain the largest fine-grained annotated dataset EyePACS-pixel, and validate the performance of our model on it. Extensive experimental results on the public dataset FGADR and our EyePACS-pixel demonstrate that compared with the existing detection and segmentation methods, the proposed method can identify lesions accurately and comprehensively, and obtain competitive results using only coarse-grained annotations.

3 August 2023 in Remote Sensing
Verified
Journal Article
Open access
PDF file
MWminghui wang
minghui wang
QLQingpeng Li
Qingpeng Li
YGYunchao Gu
Yunchao Gu
Pan junjunPan junjun
Pan junjun
With the continuous progress of remote sensing image object detection tasks in recent years, researchers in this field have gradually shifted the focus of their research from horizontal object detection to the study of object detection in arbitrary directions. It is worth noting that some properties are different from horizontal object detection during oriented object detection that researchers have yet to notice much. This article presents the design of a straightforward and efficient arbitrary-oriented detection system, leveraging the inherent properties of the orientation task, including the rotation angle and box aspect ratio. In the detection of low aspect ratio objects, the angle is of little importance to the orientation bounding box, and it is even difficult to define the angle information in extreme categories. Conversely, in the detection of objects with high aspect ratios, the angle information plays a crucial role and can have a decisive impact on the quality of the detection results. By exploiting the aspect ratio of different targets, this letter proposes a ratio-balanced angle loss that allows the model to make a better trade-off between low-aspect ratio objects and high-aspect ratio objects. The rotation angle of each oriented object, which we naturally embed into a two-dimensional Euclidean space for regression, thus avoids an overly redundant design and preserving the topological properties of the circular space. The performance of the UCAS-AOD, HRSC2016, and DLR-3K datasets show that the proposed model in this paper achieves a leading level in terms of both accuracy and speed.

21 September 2021
Verified
Book Chapter
Closed access
PDF file
XWXinliang Wang
Xinliang Wang
YGYunchao Gu
Yunchao Gu
JPJunjun Pan
Junjun Pan
LJLiyun Jia
Liyun Jia