Blockage of pedestrians will cause inaccurate people counting, and people’s heads are easily blocked by each other in crowded occasions. To reduce missed detections as much as possible and improve the capability of the detection model, this paper proposes a new people counting method, named Soft-YoloV4, by attenuating the score of adjacent detection frames to prevent the occurrence of missed detection. The proposed Soft-YoloV4 improves the accuracy of people counting and reduces the incorrect elimination of the detection frames when heads are blocked by each other. Compared with the state-of-the-art YoloV4, the AP value of the proposed head detection method is increased from 88.52 to 90.54%. The Soft-YoloV4 model has much higher robustness and a lower missed detection rate for head detection, and therefore it dramatically improves the accuracy of people counting.

Urban waterlogging is mainly caused by garbage clogging the sewer manhole covers. If the amount of garbage at a sewer manhole cover can be detected, together with an early warning signal when the amount is large enough, it will be of great significance in preventing urban waterlogging from occurring. Based on the YOLOX algorithm, this paper accomplishes identifying manhole covers and garbage and building a flood control system that can automatically recognize and monitor the accumulation of garbage. This system can also display the statistical results and send early warning information. During garbage identification, it can lead to inaccurate counting and a missed detection if the garbage is occluded. To reduce the occurrence of missed detections as much as possible and improve the performance of detection models, Soft-YOLOX, a method using a new detection model for counting, was used as it can prevent the occurrence of missed detections by reducing the scores of adjacent detection frames reasonably. The Soft-YOLOX improves the accuracy of garbage counting. Compared with the traditional YOLOX, the mAP value of Soft-YOLOX for garbage identification increased from 89.72% to 91.89%.

This study addresses a gap in research on predictive models for postpartum dyslipidemia in women with gestational diabetes mellitus (GDM). The goal was to develop a machine learning-based model to predict postpartum dyslipidemia using early pregnancy clinical data, and the model’s robustness was evaluated through both internal and temporal validation. Clinical data from 15,946 pregnant women were utilized. After cleaning, the data were divided into two sets: Dataset A (n = 1,116), used for training and evaluating the model, and Dataset B (n = 707), used for temporal validation. Several machine learning algorithms were applied, and the performance of the model was assessed with Dataset A, while Dataset B was used to validate the model across a different time period. Feature significance was evaluated through Information Value (IV), model importance analysis, and SHAP (SHapley Additive exPlanations) analysis. The results showed that among the five machine learning algorithms tested, tree-based ensemble models, such as XGBoost, LightGBM, and Random Forest, outperformed others in predicting postpartum dyslipidemia. In Dataset A, these models achieved accuracies of 70.54%, 70.54%, and 69.64%, respectively, with AUC-ROC values of 73.10%, 71.94%, and 76.14%. Temporal validation with Dataset B indicated that XGBoost performed best, achieving an accuracy of 81.05% and an AUC-ROC of 87.92%. The predictive power of the model was strengthened by key variables such as total cholesterol, fasting glucose, triglycerides, and BMI, with total cholesterol being identified as the most important feature. Further IV and SHAP analyses confirmed the pivotal role of these variables in predicting dyslipidemia. The study concluded that the XGBoost-based predictive model for postpartum dyslipidemia in GDM showed strong and consistent performance in both internal and temporal validations. By introducing new variables, the model can identify high-risk groups during early pregnancy, supporting early intervention and potentially improving pregnancy outcomes and reducing complications.

The 3D reconstruction experiment can be performed accurately in most cases based on the structure from motion (SfM) algorithm with the combination of the multi-view stereo (MVS) framework through a video recorded around the object. However, we need to artificially hold the camera and stabilize the recording process as much as possible to obtain better accuracy. To eliminate the inaccurate recording caused by shaking during the recording process, we tried to fix the camera on a camera stand and placed the object on a motorized turntable to record. However, in this case, the background did not change when the camera position was kept still, and the large number of feature points from the background were not useful for 3D reconstruction, resulting in the failure of reconstructing the targeted object. To solve this problem, we performed video segmentation based on background matting to segment the object from the background, so that the original background would not affect the 3D reconstruction experiment. By intercepting the frames in the video, which eliminates the background as the input of the 3D reconstruction system, we could obtain an accurate 3D reconstruction result of an object that could not be reconstructed originally when the PSNR and SSIM increased to 11.51 and 0.26, respectively. It was proved that this algorithm can be applied to the display of online merchandise, providing an easy way for merchants to obtain an accurate model.

Given the advancements in machine vision, deep learning, convolutional neural networks, and other technologies, various artificial intelligence techniques have been used in placental pathology examinations. However, there are limitations in achieving real-time recognition and precise localization. This study aims to enhance and validate the YOLOv8 model while investigating its significance in the pathological detection of placental tissues. Embedding GAM attention into the YOLOv8 backbone network and incorporating critical preprocessing steps like image enhancement and normalization enable the model's middle layer to focus more effectively on essential image features, improving computational efficiency and accuracy. This study developed a new model,GAMatrix-YOLOv8,which enhances object detection accuracy and efficiency while offering superior generalization capabilities. Both the training and validation accuracy are close to 100 %. Compared with GoogleNet, ResNet18,YOLOv8 and other models,GAMatrix-YOLOv8 had an Accuracy of 0.997,Precision of 0.975,Recall of 0.970,and F1-Score of 0.972,which were significantly higher than those of other models. Based on the Gamatrix-YOLOV8 model, we developed an intuitive and easy-to-use graphical user interface, which enables users to easily upload pictures, view the prediction results of the model in real time, analyze and verify the detection results. GAMatrix-YOLOv8 achieves unprecedented prediction accuracy in detecting delayed villous maturation in placental pathological tissues through algorithmic innovation. The graphical user interface allows users to upload images, view model prediction results in real time, and analyze and verify test outcomes. This provides a theoretical and technical foundation for further research into artificial intelligence-based pathological auxiliary diagnostic systems.