Exposure to air pollution has been suggested to be associated with an increased risk of women’s health disorders. However, it remains unknown to what extent changes in ambient air pollution affect gynecological cancer. In our case–control study, the logistic regression model was combined with the restricted cubic spline to examine the association of short-term exposure to air pollution with gynecological cancer events using the clinical data of 35,989 women in Beijing from December 2008 to December 2017. We assessed the women’s exposure to air pollutants using the monitor located nearest to each woman’s residence and working places, adjusting for age, occupation, ambient temperature, and ambient humidity. The adjusted odds ratios (ORs) were examined to evaluate gynecologic cancer risk in six time windows (Phase 1–Phase 6) of women’s exposure to air pollutants (PM2.5, CO, O3, and SO2) and the highest ORs were found in Phase 4 (240 days). Then, the higher adjusted ORs were found associated with the increased concentrations of each pollutant (PM2.5, CO, O3, and SO2) in Phase 4. For instance, the adjusted OR of gynecological cancer risk for a 1.0-mg m−3 increase in CO exposures was 1.010 (95% CI: 0.881–1.139) below 0.8 mg m−3, 1.032 (95% CI: 0.871–1.194) at 0.8–1.0 mg m−3, 1.059 (95% CI: 0.973–1.145) at 1.0–1.4 mg m−3, and 1.120 (95% CI: 0.993–1.246) above 1.4 mg m−3. The ORs calculated in different air pollution levels accessed us to identify the nonlinear association between women’s exposure to air pollutants (PM2.5, CO, O3, and SO2) and the gynecological cancer risk. This study supports that the gynecologic risks associated with air pollution should be considered in improved public health preventive measures and policymaking to minimize the dangerous effects of air pollution.
Multiple-object tracking (MOT) is a fundamental task in computer vision and is widely applied across various domains. However, its algorithms remain somewhat immature in practical applications. To address the challenges presented by complex scenarios featuring instances of missed detections, false alarms, and frequent target switching leading to tracking failures, we propose an approach to multi-object tracking utilizing KC-YOLO detection and an identity validity discrimination module. We have constructed the KC-YOLO detection model as the detector for the tracking task, optimized the selection of detection frames, and implemented adaptive feature refinement to effectively address issues such as incomplete pedestrian features caused by occlusion. Furthermore, we have introduced an identity validity discrimination module in the data association component of the tracker. This module leverages the occlusion ratio coefficient, denoted by “k”, to assess the validity of pedestrian identities in low-scoring detection frames following cascade matching. This approach not only enhances pedestrian tracking accuracy but also ensures the integrity of pedestrian identities. In experiments on the MOT16, MOT17, and MOT20 datasets, MOTA reached 75.9%, 78.5%, and 70.1%, and IDF1 reached 74.8%, 77.8%, and 72.4%. The experimental results demonstrate the superiority of the methodology. This research outcome has potential applications in security monitoring, including public safety and fire prevention, for tracking critical targets.
The effective association of multimodal data is the basis of massive multi-source heterogeneous data sharing in the era of big data. How to realize data autonomous association between massive multimodal databases and the automatic intelligent screening of valuable information from associated data, so as to provide a reliable data source for artificial intelligence (AI), is an urgent problem to be solved. In this paper, a data autonomous association method based on the organizational structure of data cells is proposed, including transaction abstraction based on information nucleuses, symmetric and asymmetric data association based on strategies and data pipes, and information generation based on big data. To screen meaningful data associations, an information-driven intelligent information discovery method and a task-driven intelligent information discovery method are proposed. The former screens meaningful data associations by training the reward and punishment model to simulate the manual scoring of data associations. The latter is task-oriented and screens meaningful data associations by training the reward and punishment model to simulate the manual ranking of data associations related to the task requests. Through the above work, autonomous data association and intelligent information discovery are effectively realized based on multimodal fusion technology, which provides a novel data source mining approach using multimodal data sharing and intelligent information discovery.
Focusing on the Lingshan section of Guangxi’s Pinglu Canal, this study addresses frequent waterlogging during construction under subtropical monsoon rainfall. Human disturbances alter hydrological processes, causing project delays and economic losses. We developed a coupled Storm Water Management Model (SWMM 1D hydrological) and Hydrologic Engineering Center—River Analysis System 2D (HEC-RAS 2D hydrodynamic) model. High-resolution Unmanned Aerial Vehicle—Light Detection and Ranging (UAV-LiDAR) Digital Elevation Model (DEM) delineated sub-catchments, while the Green-Ampt model quantified soil conductivity decay. Synchronized runoff data drove high-resolution HEC-RAS 2D simulations of waterlogging evolution under design storms (1–100-year return periods) and a real event (10 May 2025). Key results: Water depth exhibits nonlinear growth with return period—slow at low intensities but accelerating beyond 50-year events, particularly at temporary road junctions where embankments impede flow. Additionally, intensive intermittent rainfall causes significant ponding at excavation pit-road intersections, and optimized drainage drastically shortens recession time. The study reveals a “rapid runoff generation–restricted convergence–prolonged ponding” mechanism under construction disturbance, validates the model’s capability for complex scenarios, and provides critical data for real-time waterlogging risk prediction and drainage optimization during the canal’s construction.
With the increasing demand for remote sensing image applications, extracting the required images from a huge set of remote sensing images has become a hot topic. The previous retrieval methods cannot guarantee the efficiency, accuracy, and interpretability in the retrieval process. Therefore, we propose a bag-of-words association mapping method that can explain the semantic derivation process of remote sensing images. The method constructs associations between low-level features and high-level semantics through visual feature word packets. An improved FP-Growth method is proposed to achieve the construction of strong association rules to semantics. A feedback mechanism is established to improve the accuracy of subsequent retrievals by reducing the semantic probability of incorrect retrieval results. The public datasets AID and NWPU-RESISC45 were used to validate these experiments. The experimental results show that the average accuracies of the two datasets reach 87.5% and 90.8%, which are 22.5% and 20.3% higher than VGG16, and 17.6% and 15.6% higher than ResNet18, respectively. The experimental results were able to validate the effectiveness of our proposed method.
With the development of various location-based social networks (LSBNs), personalized point-of-interest (POI) recommendations have become a recent research hotspot. Current recommendation methods tend to mine user preferences from their historical check-in records but overlook interest deviations caused by real-time geographic environments and immediate interests present in the records, failing to meet users’ real-time and accurate needs. Therefore, this paper proposes a composite preference-based recommendation model (CPRM) for personalized POI recommendation. This method first extracts multi-factor contextual features, constructs a dual-layer attention network (DLAN) to capture long and short-term preferences, combines real-time geographic scenarios to uncover user immediate preferences, and then weights and fuses these three types of preferences to generate user composite preferences. Finally, a prediction function is employed to obtain the Top-N recommendation list. The experiments on two classic datasets, Foursquare and Gowalla, affirm the effectiveness of the model presented in this paper and offer a novel approach for providing personalized POI recommendations to users.