| ID | 原文 | 译文 |
| 57418 | 用北京市轨迹交通数据对该模型进行验证，CNN-ＲesNet-LSTM 模型不仅在准确率方面比传统模型高，而且在保证预测准确率的情况下，模型使用的参数也少 | Through the verification of the CNN-ＲesNet-LSTM model by Beijing data，the model is not only higher in accuracy than the traditional model，but also has fewer parameters in the case of ensuring the accuracy of prediction. |
| 57419 | 在机坪感知网络场景下，针对不连通网络消息机会传输过程中投递率低和网络开销大的问题，提出一种基于博弈的机坪感知机会传输控制方法( OTCM) . | The low delivery rate and large network overhead is of great challenge in the apron-aware net- work scenario. To solve the problem，an opportunistic transmission control method ( OTCM) based on game theory is proposed. |
| 57420 | 首先结合场景特性建立首传节点博弈模型，实现消息传输排序，解决传输优先级的问题; | First，combining the characteristics of the scene to establish the initial-pass node game model to achieve message transmission sequencing and the problem of transmission priority is solved. |
| 57421 | 而后提出了一种融合多维拓扑节点属性的博弈规则体系和函数，实现消息传输环境的优化及传输过程的可靠性; | Then a game rule system and function is planned that integrates multi-dimensional topology node attributes to achieve the optimization of the message transmission environment and the reliability of the transmission process. |
| 57422 | 同时根据博弈体系中的效用函数保证拓扑在新机会节点融入后的自适应更新，维持其传输性能的最优状态. | At the same time，according to the utility function in the game system，the topology can be adaptively updated after adding the new opportunity node. Hence the topology maintains its opti- mal state. |
| 57423 | 利用机会网络仿真器建立国内某机坪场景，仿真结果表明，OTCM 算法相较于其他机会路由策略，平均投递率可达 52.50% ，平均传输时延降低至 1 773 s，基本达到了研究目标的要求 | Using opportunistic network environment to establish a domestic apron scene simulation. Veri- fication shows that the OTCM algorithm has an average delivery rate of 52. 50% and an average transmis- sion delay reduced to 1 773 s compared with other opportunistic routing strategies，which basically meets the research goals. |
| 57424 | 传统移动机械臂路径规划算法没有根据抓取点分布情况对工位点坐标进行优化，效率低，对此，提出了一种基于改进遗传算法的移动机械臂拣选路径优化方法. | Path planning is the core technology of mobile manipulators. Aiming at the problem of the tra- ditional fixed-station mobile manipulator planning algorithms，a method for optimizing the picking path of mobile manipulators based on improved genetic algorithm is proposed. |
| 57425 | 通过对拣选物品位置的分析，建立单个工位点上移动机械臂分拣路径模型和多工位点的旅行商( TSP) 问题模型，运用改进的遗传算法，在工作空间内对各个工位点的位置坐标寻优，规划出移动机械臂抓取的最短路径和多工位点间移动的最短路径. | By analyzing the position of items to be picked，a sorting path model of mobile manipulators at a single station and a traveling salesman problem( TSP) model for multiple stations are established. An improved genetic algorithm is used to opti- mize the station coordinates in the workspace，which planned the shortest path grasped by the mobile ro- bot arm and moved between multi-station points. |
| 57426 | 实验结果表明，与传统遗传算法可能，运用改进的等级进化选择算子和最优近邻交叉算子，遗传算法的收敛速度提高了 46.15% ，路径缩短了 45.99% ，系统运行时间减少了 25.80% ，提高了系统效率. | Experiments show that，by using the improved hierar- chical evolution selection operator and the optimal nearest neighbor crossover operator，compared with the traditional genetic algorithm，the convergence speed is increased by 46. 15% ，the path is shortened by 45. 99% ，and the system running time is reduced by 25. 80% . That improved system efficiency. |
| 57427 | 远监督作为一种能够快速大量产生标注数据的技术，在关系抽取任务中的应用愈加广泛，但仍存在文本特征提取不足、包内噪声过多等问题. | As a technology that can quickly generate large amounts of labeled data，the distant supervi- sion is increasingly used in relation extraction. However，there are still problems such as insufficient text feature extraction and noise in the bag. |