Yunhong Ding

Major depressive disorder (MDD) is a common disabling psychiatric disorder mainly diagnosed through clinical interviews and rating-scale assessments. Magnetic resonance imaging (MRI) provides a promising basis for computer-aided MDD identification, particularly through multimodal models that can integrate structural and functional brain information. However, existing multimodal MRI fusion models often use data-level fusion or post hoc feature concatenation, potentially overlooking differences in spatial resolution, voxel organization, and region of interest (ROI)-level semantic correspondence. To address this issue, this study proposes MUSA, a unified ROI semantic space model for multimodal MRI-based MDD classification. An Automated Anatomical Labeling (AAL) atlas-guided ROI semantic space establishes consistent brain-region correspondence across heterogeneous MRI features. An ROI-level 3D Vision Transformer (3D ViT) encodes ROI voxel information into fixed-dimensional representations, allowing structural, local functional, and connectivity information to be organized and integrated within a consistent brain-region semantic space. Experiments on 2380 participants from REST-meta-MDD validated MUSA for MDD and normal controls (NCs) classification. The feature combination of white matter (WM), functional connectivity (FC), regional homogeneity (ReHo), and degree centrality (DC) achieved 79.20% ± 0.65% accuracy and an AUC of 87.08% ± 0.51%. Brain-region importance analysis identified classifier-derived discriminative patterns across frontoparietal, sensorimotor, visual, temporal, and limbic-related regions.

Predicting academic performance in face-to-face computing and software engineering courses is hindered by the limited availability of fine-grained process data. This study proposes STEAP, a camera-based static–temporal fusion framework that integrates longitudinal classroom behavior sensing with conventional educational records. Classroom videos from 375 undergraduates enrolled in four computing-related courses were collected over nine teaching weeks. Camera-derived observable behaviors were organized into student-level weekly sequences and transformed into outcome-independent longitudinal representations. Multiple machine-learning classifiers were subsequently applied to predict students’ academic performance. Checkpoint-specific predictions were conducted at Weeks 3, 6, and 9, with each prediction using only the classroom behavioral information available up to the corresponding time point. Using the complete nine-week Temporal representation together with the pre-course Background variables, XGBoost achieved the strongest classification performance among the evaluated models, with an Accuracy of 0.867, a Macro F1 of 0.862, and an At-risk Recall of 0.924. The checkpoint analyses further indicated that classroom behavioral information collected during the early course stage already provided useful predictive information without incorporating behavioral observations from subsequent weeks. After further integrating pre-course background variables and regular assessment information, the final fusion model achieved an Accuracy of 0.896 and a Macro F1 of 0.895. Overall, longitudinal camera-derived classroom behavior provides complementary predictive information beyond conventional educational information and supports the feasibility of earlier academic-risk identification at different course checkpoints.

With the continuous advancement of education informatization, classroom behavior analysis has become an important tool to improve teaching quality and student learning outcomes. However, student classroom behavior recognition methods still face challenges such as occlusion, small objects, and environmental interference, resulting in low recognition accuracy and lightweight performance. To address the above problems, this study proposes a lightweight student behavior recognition model based on Inverted Residual Mobile Block (IMRMB-Net). Specifically, this study designs a lightweight feature extraction module, IMRMB, from the images of the backbone network to be able to better capture contextual information and improve the recognition of occluded objects while saving computational resources. Using DySample, the neck network reconsiders the initial sampling position and the moving range of the offset from the point sampling perspective to accurately recognize small object behaviors in course scenes. Meanwhile, a new loss function, Focaler-ShapeIoU, is designed in this study, aiming to improve the learning ability and robustness of the model to different samples thus further solving the occlusion problem. Experiments in UK_Dataset show that IMRMB-Net has high accuracy (mAP@50 = 93.3%, mAP@50:95 = 78.7%) and lightweight performance (FPS = 60.37, Params = 7.32MB, GFLOPs = 23.8G). Meanwhile, this study verifies that IMRMB-Net can effectively solve the occlusion problem in classroom scenarios through experiments on the UK_Dataset and SCB_Dataset occlusion subsets. In addition, this study verifies the generalization ability and the ability to recognize small targets of IMRMB-Net on the VisDrone2021 dataset.

Unmanned aerial vehicles (UAVs) are widely used for small target detection of forest fires due to its low-risk rate, low cost and high ground coverage. However, the detection accuracy of small target forest fires is still not ideal due to its irregular shape, different scale and how easy it can be blocked by obstacles. This paper proposes a multi-scale feature extraction model (MS-FRCNN) for small target forest fire detection by improving the classic Faster RCNN target detection model. In the MS-FRCNN model, ResNet50 is used to replace VGG-16 as the backbone network of Faster RCNN to alleviate the gradient explosion or gradient dispersion phenomenon of VGG-16 when extracting the features. Then, the feature map output by ResNet50 is input into the Feature Pyramid Network (FPN). The advantage of multi-scale feature extraction for FPN will help to improve the ability of the MS-FRCNN to obtain detailed feature information. At the same time, the MS-FRCNN uses a new attention module PAM in the Regional Proposal Network (RPN), which can help reduce the influence of complex backgrounds in the images through the parallel operation of channel attention and space attention, so that the RPN can pay more attention to the semantic and location information of small target forest fires. In addition, the MS-FRCNN model uses a soft-NMS algorithm instead of an NMS algorithm to reduce the error deletion of the detected frames. The experimental results show that, compared to the baseline model, the proposed MS-FRCNN in this paper achieved a better detection performance of small target forest fires, and its detection accuracy was 5.7% higher than that of the baseline models. It shows that the strategy of multi-scale image feature extraction and the parallel attention mechanism to suppress the interference information adopted in the MS-FRCNN model can really improve the performance of small target forest fire detection.

Satellite remote sensing plays an important role in wildfire detection. Methods using the brightness and temperature difference of remote sensing images to determine if a wildfire has occurred are one of the main research directions of forest fire monitoring. However, common wildfire detection algorithms are mainly based on a fixed brightness temperature threshold to distinguish wildfire pixels and non-wildfire pixels, which reduces the applicability of the algorithm in different space–time regions. This paper presents an adaptive wildfire detection algorithm, DBTDW, based on a dynamic brightness temperature threshold. First, a regression dataset, MODIS_DT_Fire, was constructed based on moderate resolution imaging spectroradiometry (MODIS) to determine the wildfire brightness temperature threshold. Then, based on the meteorological information, normalized difference vegetation index (NDVI) information, and elevation information provided by the dataset, the DBTDW algorithm was used to calculate and obtain the minimum brightness temperature threshold of the burning area by using the Planck algorithm and Otsu algorithm. Finally, six regression models were trained to establish the correlation between factors and the dynamic brightness temperature threshold of wildfire. The root-mean-square error (RMSE) and mean absolute error (MAE) were used to evaluate the regression performance. The results show that under the XGBoost model, the DBTDW algorithm has the best prediction effect on the dynamic brightness temperature threshold of wildfire (leave-one-out method: RMSE/MAE = 0.0730). Compared with the method based on a fixed brightness temperature threshold, the method proposed in this paper to adaptively determine the brightness temperature threshold of wildfire has higher universality, which will help improve the effectiveness of satellite remote fire detection.

Wildfires influence the global carbon cycle, and the regularity of wildfires is mostly determined by elements such as meteorological conditions, combustible material states, and human activities. The time series and spatial dispersion of wildfires have been studied by some scholars. Wildfire samples were acquired in a monthly series for the Montesinho Natural Park historical fire site dataset (January 2000 to December 2003), which can be used to assess the possible effects of geographical and temporal variations on forest fires. Based on the above dataset, dynamic wildfire distribution thresholds were examined using a K-means++ clustering technique for each subgroup, and monthly series data were categorized as flammable or non-flammable depending on the thresholds. A five-fold hierarchical cross-validation strategy was used to train four machine learning models: extreme gradient boosting (XGBoost), random forest (RF), support vector machine (SVM), and decision tree (DT). Finally, to explore the performance of those we have mentioned, we used accuracy (ACC), F1 score (F1), and the values for the area under the curve (AUC) of the receiver operating characteristics (ROCs). The results depicted that the XGBoost model works best under the evaluation of the three metrics (ACC = 0.8132, F1 = 0.7862, and AUC = 0.8052). The model performance is significantly improved when compared to the approach of classifying wildfires by burned area size (ACC = 72.3%), demonstrating that spatiotemporal heterogeneity has a broad influence on wildfire occurrence. The law of a spatiotemporal distribution connection in wildfires could aid in the prediction and management of wildfires and fire disasters.

Timely detection of forest wildfires is of great significance to the early prevention and control of large-scale forest fires. Unmanned Aerial Vehicle(UAV) with cameras has the characteristics of wide monitoring range and strong flexibility, making it very suitable for early detection of forest fire. However, the visual angle/distance of UAV in the process of image sampling and the limited sample size of UAV labeled images limit the accuracy of forest fire recognition based on UAV images. This paper proposes a FT-ResNet50 model based on transfer learning. The model migrates the ResNet network trained on an ImageNet dataset and its initialization parameters into the target dataset of forest fire identification based on UAV images. Combined with the characteristics of the target data set, Adam and Mish functions are used to fine tune the three convolution blocks of ResNet, and focal loss function and network structure parameters are added to optimize the ResNet network, to extract more effectively deep semantic information from fire images. The experimental results show that compared with baseline models, FT-ResNet50 achieved better accuracy in forest fire identification. The recognition accuracy of the FT-ResNet50 model was 79.48%; 3.87% higher than ResNet50 and 6.22% higher than VGG16.