ID 原文 译文
57848 首先提取作品的 Block 使用特征、计算思维技能特征和复杂度特征 3 类特征作为分类特征; Firstly，the block usage features，the computa- tional thinking skill features and the Halstead features of projects are extracted as classification features.
57849 然后针对 ＲAKEL 算法随机选择标签子集，忽略了标签间的关联性，提出了改进的 MLLＲ 算法，该方法根据多标签之间的关联性来划分标签子集，再训练相应的标签幂集子分类器. Then，the ＲAKEL algorithm randomly chooses label subsets，ignoring the relevance between labels， thereafter an improved MLLＲ algorithm was proposed. This method divides label subsets according to the relevance between multiple labels，and then trains the corresponding label power set sub-classifiers.
57850 实验结果表明，MLLＲ 算法在分类性能和时间性能上优于 ＲAKEL 等多标签分类算法，构建的分类模型对于 Scratch 作品具有较强的适用性，分类的准确率达到 81. Ex- periments show that MLLＲ algorithm is superior to ＲAKEL and other multi-label classification algorithms in classification performance and time performance，The classification model constructed has a strong ap- plicability for Scratch projects，and the accuracy of classification reaches 81.
57851 3% . 3% .
57852 针对现有智能手机隐式认证方法难以被实际应用的情况，提出了一种基于上下文感知的隐式身份认证机制. Considering that the existing implicit authentication method for smartphone is difficult to be ap- plied in practice，an implicit authentication mechanism based on context awareness was proposed.
57853 首先，由智能手机内置传感器( 加速计、陀螺仪、磁力计) 获取点击行为数据;然后从这些数据中提取上下文特征以识别上下文信息 ( 用户的身体姿势状态) ，同时提取点击特征为每个上下文训练相应的认证子模型用于认证; First- ly，the tapping behavior data acquired by embedded sensors ( i. e. accelerometer，gyroscope，and mag- netometer) of the smartphone is used to identify the context information ( that is，the user's body posture state) .
57854 最后利用所收集的 7000 + 数据进行实验评估. Then，the context feature and tapping feature is extracted from the data after noise elimination which is employed to train the corresponding authentication sub-model for each context. Experiment eval- uation is performed using the collected 7000 + data.
57855 结果表明，该方案对不同用户进行认证所得的平均错误接受率和错误拒绝率分别为 1.29% 和 1.03% ，与无上下文感知的认证方法相比，平均错误接受率和错误拒绝率分别降低了 1.72% 和 2.59% . It is shown that the average false acceptance rate ( FAＲ) and false rejection rate ( FＲＲ) of the proposed scheme for different users is 1. 29% and 1. 03% respectively. Compared with the authentication method without context awareness，FAＲ and FＲＲ is re- duced by 1. 72% and 2. 59% respectively.
57856 所提的机制可有效提高身份认证的准确性 The proposed mechanism can effectively improve the accuracy of authentication.
57857 针对光分路器( OBD) 端口占用状态不能自动采集的问题，提出了一种改进型 YOLOv3 算法. Because that optical branching device ( OBD) port occupancy state can not be automatically acquired，an improved YOLOv3 algorithm was proposed.