In recent years, advances in artificial intelligence, machine vision, and the Internet of Things have significantly impacted sports analytics, particularly basketball, where accurate measurement and analysis of player performance have become increasingly important. This study proposes a real-time goal state recognition system based on inertial measurement unit (IMU) sensors, focusing on four shooting scenarios: rebounds, swishes, other shots, and misses. By installing IMU sensors around the basketball net, the system captures real-time data on acceleration, angular velocity, and angular changes to comprehensively analyze the fluency and success rate of shooting execution, utilizing five deep learning models—convolutional neural network (CNN), recurrent neural network (RNN), long short-term memory (LSTM), CNN-LSTM, and CNN-LSTM-Attention—to classify shot types. Experimental results indicate that the CNN-LSTM-Attention model outperformed other models with an accuracy of 87.79% in identifying goal states. This result represents a commanding level of real-time goal state recognition, demonstrating the robustness and efficiency of the model in complex sports environments. This high accuracy not only supports the application of the system in skill analysis and sports performance evaluation but also lays a solid foundation for the development of intelligent basketball training equipment, providing an efficient and practical solution for athletes and coaches.

With the rapid development of society and technology, the physical health of university students has become a critical concern, influencing both individual well-being and the national talent pool. This study employs an improved K-means algorithm integrated with machine learning models to analyze university students’ fitness data and develop personalized health intervention strategies. The enhanced K-means algorithm overcomes the limitations of traditional clustering approaches, leading to improved clustering accuracy and stability. Machine learning models—including Random Forest, decision trees, Gradient Boosting Trees, and logistic regression—were utilized to validate the clustering outcomes and to identify key health indicators associated with different student groups. Based on the clustering and model analysis, targeted intervention programs are proposed, such as strength training for groups with low muscular explosiveness, endurance training for those with stamina deficiencies, and flexibility exercises for groups exhibiting limited mobility. This integrated analytical framework provides a scientifically grounded tool for comprehensive health assessments and offers actionable, data-driven recommendations for student health management. Future research will focus on optimizing algorithmic performance, enhancing data diversity, and broadening the application scope to further improve the effectiveness and feasibility of health interventions.

Recent developments in computer vision have significantly enhanced the automation and objectivity of sports analytics. This paper proposes a novel deep learning-based framework for estimating football possession directly from broadcast video, eliminating the reliance on manual annotations or event-based data that are often labor-intensive, subjective, and temporally coarse. The framework incorporates two structurally improved object detection models: YOLOv8-P2S3A for football detection and YOLOv8-HWD3A for player detection. These models demonstrate superior accuracy compared to baseline detectors, achieving 79.4% and 71.1% validation average precision, respectively, while maintaining low computational latency. Team identification is accomplished through unsupervised DBSCAN clustering on jersey color features, enabling robust and label-free team assignment across diverse match scenarios. Object trajectories are maintained via the Norfair multi-object tracking algorithm, and a temporally aware refinement module ensures accurate estimation of ball possession durations. Extensive experiments were conducted on a dataset comprising 20 full-match Video clips. The proposed system achieved a root mean square error (RMSE) of 4.87 in possession estimation, outperforming all evaluated baselines, including YOLOv10n (RMSE: 5.12) and YOLOv11 (RMSE: 5.17), with a substantial improvement over YOLOv6n (RMSE: 12.73). These results substantiate the effectiveness of the proposed framework in enhancing the precision, efficiency, and automation of football analytics, offering practical value for coaches, analysts, and sports scientists in professional settings.

Perception-level interference patterns, such as abutting gratings that induce illusory contours and pseudoisochromatic dot camouflage, can trigger failures that are not well captured by conventional corruption benchmarks. We construct an illusion-driven evaluation suite based on MNIST variants, including AG-MNIST and Ishihara-MNIST, under a unified $224\times 224\times 3$ pipeline with fixed train/validation/test splits. Building on a multi-domain empirical risk minimization (ERM) baseline, we present AugMix–DeepAugment Consistency Training (ADCT), a training-time recipe that combines mixed augmentations, DeepAugment-style image distortions, and Jensen–Shannon consistency regularization. Across multiple ImageNet-pretrained backbones and multiple random seeds, ADCT improves robustness on the five-set illusion OOD suite (OOD5) on average while simultaneously improving probabilistic calibration, as measured by ECE together with proper scoring rules (NLL and Brier score). For ResNet-50, ADCT yields a substantial gain on OOD5 relative to the Ishihara-only baseline (S0), increasing accuracy from 29.0% to 59.7% and reducing NLL from 7.44 to 1.11. To assess external validity, we additionally report results on CIFAR-10 and CIFAR-10-C and compare against representative augmentation-based baselines (including PixMix), contextualizing the robustness–calibration trade-off on a widely used natural-image robustness benchmark. These results suggest that consistency-based augmentation recipes can improve both robustness and confidence reliability under structured, illusion-like shifts without changing inference-time architectures.