ID 原文 译文
57278 为了解决疲劳驾驶易造成交通事故的问题，提出了基于密集连接网络的驾驶疲劳状态检测方法. In order to solve the problem of traffic accidents caused by fatigue driving，a driving fatigue state detection method based on densely connected convolutional networks is proposed.
57279 首先，借助摄像机采集驾驶状态视频，获取视频帧图像后利用图像处理技术进行图像预处理; Firstly，a camera is used to collect driving state video，the video frame image is obtained. The image processing technology is used to process images.
57280 利用自适应提升算法检测人脸，再用灰度积分投影和径向对称变换算法定位驾驶员的眼部区域; Then the adaptive Boosting algorithm is used to detect the face，and then the gray integral projection and radial symmetry transformation algorithm are used to locate the driver’s eye area.
57281 然后，通过密集连接网络精确判别眼睛状态，在网络中设置了 3 个密集连接块以减少特征参数和加快训练速度，且采用稀疏化结构以减少存储量和增强特征传播; Moreover，the eye state is accurately distinguished through the densely connected network. Three densely connected blocks are set in the network to reduce feature parameters and speed up training. The sparse structure is used to reduce storage and enhance feature propagation.
57282 最后，借助 2 个疲劳参数综合判断驾驶员的疲劳状态，使检测结果更为准确. Finally，with the help of two fatigue parameters comprehensively judge the fatigue state of the driver，making the detection result more accurate.
57283 定性和定量实验结果证明，该方法在准确率等方面优于现有技术. It is proved by a large number of qualitative and quantitative experiments that this method is better than the existing technology in terms of accuracy.
57284 在密集部署的小小区网络中，考虑到小小区基站( SBS) 的计算资源有限，提出了基于任务间串并依赖关系的协作卸载策略，以降低计算卸载任务的整体完成时延. In dense small cell networks，a task-dependency-based collaborative offloading scheme is pro- posed to cope with the limited computational resources in small cell base station ( SBS) ，which can fur- ther reduce the total execution delay.
57285 首先，考虑将可以同时执行的并行任务卸载至不同的 SBS，利用计算资源的分布式特点来降低整体时延，同时最大化单个 SBS 上的串行任务数量，以减小所需 SBS 的数目;然 后，根据网络的负载均衡情况对 2 种场景进行讨论，联合考虑任务间的依赖关系、不同 SBS 的可用计算资源量和SBS 与用户间的信道质量，分别引入最长路径理论和图着色算法以确定最佳任务卸载方案. Firstly，the parallel tasks are offloaded to different SBSs to reduce computing delay，while sequential tasks are offloaded to the same SBSs to reduce the number of required SBS. Then，based on whether different SBSs have the same load pressure or not，the optimal offloading strategies are proposed in two different scenarios by introducing the longest path theory and the graph col- oring theory，respectively. The strategies jointly considerate the user energy constraint，dependencies a- mong tasks，the amount of available computational resources and channel conditions of different SBSs.
57286 仿真结果表明，与已有策略相比，所提策略可降低计算卸载任务的整体完成时延. Simulation shows that the proposed strategies can reduce total execution delay compared with existing strategies in both scenarios.
57287 无线上网( Wi-Fi) 定位是目前室内定位中的主流方法，指纹数据库的构建是 Wi-Fi 定位系统的关键. Wireless-fidelity( Wi-Fi) positioning is currently the mainstream method in indoor positioning， and the construction of fingerprint database is the key to Wi-Fi positioning system.