ID	原文	译文
24305	为了提高手机位置不固定时的动作识别率，该文提出一种基于层次分类的动作识别方法。	To improve the recognition rate when the phone's displacement is unfixed, a hierarchical classification-based activity recognition method is proposed.
24306	该方法将动作识别分为多层，每一层包含一个分类器。	The activity recognition process is divided into multiple layers in this method, and each layer contains a classifier.
24307	在训练某一层分类器时，首先根据本层训练样本集进行特征选择并训练分类器。	For training each layer's classifier, it runs the feature selection algorithm first, and the classifier is trained based on the selected features.
24308	然后使用训练得到的分类器对训练样本分类，并计算分类结果的可信度。	Then, the trained classifier is used to classify the training set, and each sample's classification confidence is calculated.
24309	最后通过对低可信度的样本进行剪枝得到下层分类器的训练样本。	Finally, samples whose confidence is lower than the hierarchical threshold are selected as the next layer's training set.
24310	对未知类别的样本分类时，首先使用第 1 层分类器分类。	When an unlabeled sample comes, the first layer is used to classify this sample.
24311	如果分类结果可信度较高，则分类结束；	If the classification confidence is higher than the hierarchical threshold, the recognition is over.
24312	否则使用下层分类器分类，直至所有分类器遍历完。	Otherwise, the next layer will repeat this process until all the layers are traversed.
24313	实验部分通过对采集的动作数据进行仿真，验证了该文方法的有效性。	The experiment collects activity data, and simulates the activity recognition.
24314	结果表明，与单层分类器相比，该方法可以将动作识别率由 85.2%提高至 89.2%。	The simulation show that compared with the current methods, this method may improve the recognition rate from 85.2% to 89.2%.