通过多组实验可以看出，新算法能够满足不同监控场景下的异常行为识别需求，运算速度快、满足实时性要求。
Through experiments, the new algorithm satisfies the abnormal behavior recognition demand under different monitoring scene and the processing speed is quick under practice request.
本文中的实例是一个应用程序，该应用程序帮助一家银行的雇员识别行为异常的客户。
The running example in this article is an application that helps employees of a bank identify customers that show unusual behavior.
如果您的BPM解决方案涉及大量组件和模块，跟踪并识别异常行为发生将有所帮助。
When there are numerous components and modules involved in your BPM solution, it is helpful to trace and identify where the unexpected behavior occurred.
不当的配置可能会导致性能问题，这些问题并不总是能通过前面介绍过的方法识别，它们会导致异常的应用程序行为并危害服务能力。
Poor configuration can cause performance problems that can't always be identified using the techniques already described, cause unexpected application behavior, and jeopardize serviceability.
经过训练学习后，该算法可以识别新视频在相应场景下行为的异常或正常。
The algorithm can categorize the human anomalous or normal action contained in the special occasion to a novel video sequence after being trained.
经过训练学习后，该算法可以识别新视频在相应场景下行为的异常或正常。
The algorithm can categorize the human anomalous or normal action contained in the special occasion to a novel video sequence after being trained.
应用推荐