ID 原文 译文
57448 实验结果表明，该方法对剑桥大学和美国西北大学数据集中动态手势的平均识别率分别达到 94.22% 和 94.48% ，并且与 CNN 结合长短期记忆网络的识别方法相比，手势识别时间减少了 85% . The experiment shows that the proposed method has an average recognition rate of 94. 22% and 94. 48% respective for university of Cambridge and Northwestern University hand gesture data sets. Compared with the scheme combine of CNN and long short-term memory，the gesture recognition time is reduced by 85% .
57449 在背景图像复杂且光照条件不足时，该方法仍然能够维持较高的识别率，表现出较好的鲁棒性. It can still maintain a higher recognition rate for the complex background with insufficient illumination，re- presents a higher robustness.
57450 由于缺乏大量已标注数据，在中文医疗命名实体识别中，主要利用外部资源来改善医疗实体识别的性能，这需要大量的时间和有效的规则加入外部资源. Chinese clinical named entity recognition plays an important role in recognizing medical enti- ties contained in Chinese electronic medical records. Limited to lack of large annotated data，most of ex- isting methods concentrate on employing external resources to improve the performance of clinical named entity recognition，which require lots of time and efficient rules.
57451 为了解决标注数据不足的问题，提出了一种基于生成对抗网络的数据增强算法，自动生成大量标注数据，提高医疗实体识别的性能. To solve the problem of lack of large an- notated data，data augmentation using sequence adversarial generative network is used to generate more various data depending on entities and non-entities in the training set.
57452 实验结果表明，该算法在性能方面优于实验中的基准模型，证明了该算法在医疗实体识别上的有效性. Experiments show that when using generated data to expand training set，the proposed named entity recognition system has achieved compet- itive performance compared with state-of-art methods，which shows the effectiveness of our data augmen- tation method.
57453 针对多维定标( MDS-MAP) 算法计算效率低且定位精度不高的问题，提出了一种基于映射曲线的自适应莱维鲸鱼无线定位( AWL-MC) 算法. Aiming at the problems of low calculation efficiency and low positioning accuracy of the multi- dimensional scaling map ( MDS-MAP) algorithm，a wireless localization algorithm of adaptive Levy whale based on mapping curve ( AWL-MC) is proposed.
57454 采用映射曲线距离分析方法对待定位节点进行粗略相对定位，以提高节点的计算效率; The mapping curve distance analysis method is used to make rough relative positioning of the localization nodes，so as to improve the calculation efficiency of nodes.
57455 再通过线性变换将相对坐标转换成绝对坐标; Then the relative coordinates are converted into absolute coordinates by linear transformation.
57456 最后采用自适应莱维飞行鲸鱼优化算法对待定位节点坐标进行全局和局部搜索寻优处理，避免产生局部最优解，提高了定位精度. Finally，the adaptive Levy flight whale optimization algorithm is adopted to perform global and local search optimization processing for the coordinates of positioning nodes，so as to avoid local optimal solution and improve positioning accuracy.
57457 仿真结果表明，AWL-MC 算法相比 MDS-MAP算法的定位精度改进率为 66.42% ，计算效率提高了 52.57% ，相比多维定标扩展卡尔曼滤波的定位精度改进率为57.80% ，计算效率提高了 66.01% . Simulations show that compared with MDS-MAP，AWL-MC algorithm has a 66. 42% improvement rate in positioning accuracy and a 52. 57% improvement in calculation efficiency. Compared with the multidimensional scaling extended Kalman filter，AWL-MC algorithm has a 57. 80% improvement rate in positioning accuracy and a 66. 01% improvement in calculation efficiency.