Shaodan LIN

Prof. Shaodan LIN

orcid

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

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

Representative Publications

View All Publications
1 January 2019 in International Journal of Computational Intelligence Systems
Verified
Journal Article
Open access
PDF file
SLShaodan LIN
Shaodan LIN
FCFeng Chen
Feng Chen
CZChen Zhide
Chen Zhide
Ship detection is a canonical problem in computer vision. Motivated by the observation that the major bottleneck of ship detection lies on the different scales of ship instances in images, we focus on improving the detection rate, especially for the small-sized ships which are relatively far from the camera. We use the Smooth function combined with L1 and L2 norm to optimize the region proposal network (RPN) loss function and reduce the deviation between the prediction frame and the actual target to ensure the accurate location of the ship target. With the Two-Way sampling combined with the shared weight to generate the mask, we solve the problems of inaccurate segmentation, target loss and small interference when Mask Region Convolution Neural Network (RCNN) is used to segment an instance. We create the experimental data sets from the deep learning annotation tool—Labelme. Experiments show that the improved Mask-RCNN model has a confidence rate of 82.17%. Serving as the basic network, the test accuracy rate of ResNetXt-101 is 3.3% higher than that of the original ResNet-101, which can better realize the function of ship target location and mask generation.

25 October 2023 in Plants
Verified
Journal Article
Open access
PDF file
SLShaodan LIN
Shaodan LIN
JLJiayi Li
Jiayi Li
DHDeyao Huang
Deyao Huang
ZCZuxin Cheng
Zuxin Cheng
Lirong XiangLirong Xiang
Lirong Xiang
HWhaiyong Weng
haiyong Weng
Rice blast has caused major production losses in rice, and thus the early detection of rice blast plays a crucial role in global food security. In this study, a semi-supervised contrastive unpaired translation iterative network is specifically designed based on unmanned aerial vehicle (UAV) images for rice blast detection. It incorporates multiple critic contrastive unpaired translation networks to generate fake images with different disease levels through an iterative process of data augmentation. These generated fake images, along with real images, are then used to establish a detection network called RiceBlastYolo. Notably, the RiceBlastYolo model integrates an improved fpn and a general soft labeling approach. The results show that the detection precision of RiceBlastYolo is 99.51% under intersection over union (IOU0.5) conditions and the average precision is 98.75% under IOU0.5–0.9 conditions. The precision and recall rates are respectively 98.23% and 99.99%, which are higher than those of common detection models (YOLO, YOLACT, YOLACT++, Mask R-CNN, and Faster R-CNN). Additionally, external data also verified the ability of the model. The findings demonstrate that our proposed model can accurately identify rice blast under field-scale conditions.

14 November 2023 in IEEE Access
Verified
Journal Article
Open access
SLShaodan LIN
Shaodan LIN
CFChen Feng
Chen Feng
TJTao Jiang
Tao Jiang
HJHuasong Jing
Huasong Jing
Using deep learning models, we predict information system security indicators and obtain corresponding security evaluation scores. The scores of these predicted security evaluation are used as the input data of regression tree model, and the security grade protection evaluation system is constructed. The model training process involves four different models: VGG19, ResNet-50, XceptionNet, and EfficientNet. Based on the training results, we find that the EfficientNet model consumes fewer computational resources in single detection while achieves a detection accuracy of 99.93%.Subsequently, we apply the CART regression tree to assess the network security posture of 14 commercial systems. The test results of the model show that the mean absolute percentage error(MAPE) is 0.029 and the correlation coefficient is 0.9. These empirical results strongly support the performance of the proposed model and show its significant potential in improving security assessments. With these training results, we gain preliminary insights into the performance of each model and select the EfficientNet model with the best performance for the generation of subsequent security posture evaluation data.Ultimately, the developed security grade protection assessment system provides a reliable and efficient evaluation means for the network security.

20 December 2023 in Scientific Reports
Verified
Journal Article
Open access
PDF file
MWMengwei Wu
Mengwei Wu
SLShaodan LIN
Shaodan LIN
CXChenhan Xiao
Chenhan Xiao
XXXiulin Xiao
Xiulin Xiao
SXSiwei Xu
Siwei Xu
SYShuhan Yu
Shuhan Yu
During the COVID19 pandemic, there is a pronounced collective mental health issue among college students. Forecasting the trend of emotional changes in on-campus students is crucial to effectively address this issue. This study proposes an Attention-LSTM neural network model that performs deep learning on key input sequence information, so as to predict the distribution of emotional states in college students. By testing 60 consecutive days of emotional data, the model successfully predicts students' emotional distribution, triggers and resolution strategies, with an accuracy rate of no less than 99%. Compared with models such as ARIMA, SARIMA and VAR, this model shows significant advantages in accuracy, operational efficiency, and data collection requirements. The integration of deep learning technology with student management in this study offers a novel approach to address emotional issues among students under exceptional circumstances.

19 June 2021 in Journal of Ambient Intelligence and Humanized Computing
Verified
Journal Article
Closed access
PDF file
SLShaodan LIN
Shaodan LIN
KZKexin Zhu
Kexin Zhu
CFChen Feng
Chen Feng
ZCZhide Chen
Zhide Chen