An explainable and efficient deep learning framework for video anomaly detection.

Deep learning-based video anomaly detection methods have drawn significant attention in the past few years due to their superior performance. However, almost all the leading methods for video anomaly detection rely on large-scale training datasets with long training times. As a result, many real-world video analysis tasks are still not applicable for fast deployment. On the other hand, the leading methods cannot provide interpretability due to the uninterpretable feature representations hiding the decision-making process when anomaly detection models are considered as a black box. However, the interpretability for anomaly detection is crucial since the corresponding response to the anomalies in the video is determined by their severity and nature. To tackle these problems, this paper proposes an efficient deep learning framework for video anomaly detection and provides explanations. The proposed framework uses pre-trained deep models to extract high-level concept and context features for training denoising autoencoder (DAE), requiring little training time (i.e., within 10 s on UCSD Pedestrian datasets) while achieving comparable detection performance to the leading methods. Furthermore, this framework presents the first video anomaly detection use of combing autoencoder and SHapley Additive exPlanations (SHAP) for model interpretability. The framework can explain each anomaly detection result in surveillance videos. In the experiments, we evaluate the proposed framework's effectiveness and efficiency while also explaining anomalies behind the autoencoder's prediction. On the USCD Pedestrian datasets, the DAE achieved 85.9% AUC with a training time of 5 s on the USCD Ped1 and 92.4% AUC with a training time of 2.9 s on the UCSD Ped2.

A Comprehensive Evaluation System for Military Hospitals' Response Capability to Bio-terrorism.

The objective of this study is to establish a comprehensive evaluation system for military hospitals' response capacity to bio-terrorism. Literature research and Delphi method were utilized to establish the comprehensive evaluation system for military hospitals' response capacity to bio-terrorism. Questionnaires were designed and used to survey the status quo of 134 military hospitals' response capability to bio-terrorism. Survey indicated that factor analysis method was suitable to for analyzing the comprehensive evaluation system for military hospitals' response capacity to bio-terrorism. The constructed evaluation system was consisted of five first-class and 16 second-class indexes. Among them, medical response factor was considered as the most important factor with weight coefficient of 0.660, followed in turn by the emergency management factor with weight coefficient of 0.109, emergency management consciousness factor with weight coefficient of 0.093, hardware support factor with weight coefficient of 0.078, and improvement factor with weight coefficient of 0.059. The constructed comprehensive assessment model and system are scientific and practical.