ID 原文 译文
17595 首先对低采样密度的信令数据进行预处理，消除轨迹震荡现象； Firstly, the low sampling density signaling data are pre-processed to eliminate the trajectory oscillationphenomenon in the data.
17596 然后基于密度峰值快速聚类(CFSFDP)算法显式地增加时间维度限制，将局部密度由2维扩展到3维，并提出高密度时间间隔以表征簇中心在时间维度上的数据特征； Then, based on the Clustering by Fast Search and Find of Density Peaks(CFSFDP)algorithm, the time dimension limitation is explicitly increased, and the local density is extended from two-dimension to three-dimension. Moreover, in order to characterize the cluster center point in the time dimension,the concept of high-density time interval is defined.
17597 接着设计筛选策略以选取聚类中心； Secondly, the suitable cluster center screening strategy is developed to select automatically the appropriate cluster center.
17598 最后识别用户出行轨迹中的驻留点，完成出行链的划分。 Finally, the resident points are identified inthe travel trajectory of individual users over a period of time and the division of the travel chains is completed.
17599 实验结果表明，所提算法适用于采样密度低且定位精度差的信令数据，相比CFSFDP算法更适用于时空数据，相比基于密度的时空聚类算法(ST-DBSCAN)召回率提升14%，准确率提升8%，同时降低计算复杂度。 The experimental results show that the algorithm is suitable for signaling data with low sampling density andpoor positioning accuracy. It is more suitable for spatio-temporal data than CFSFDP algorithm. Compared with Density-Based Spatial Clustering of Applications with Noise based on Spatio-Temporal data (ST-DBSCAN) algorithm, the recall rate is improved by 14%, the accuracy rate is increased by 8%, and the computational complexity is also reduced.
17600 小麦多生理生化指标变化趋势反映了储藏品质的劣变状态，预测多指标时序数据会因关联性及相互作用而产生较大误差， The change trend of multi-index of wheat reflects the deterioration state of storage quality, while the predicted multi-index data will produce large errors due to its correlation and interaction.
17601 为此该文基于长短期记忆网络(LSTM)和生成式对抗网络(GAN)提出一种改进拓扑结构的长短期记忆生成对抗网络(LSTM-GAN)模型。 For this reason, an improved Long Short-Term Memory and Generative Adversarial Network(LSTM-GAN) model is proposed.
17602 首先，由LSTM预测多指标不同时序数据的劣变趋势；其次，根据多指标的关联性并结合GAN的对抗学习方法来降低综合预测误差； The deterioration trend of different time series data of multi-index is predicted by Long Short-TermMemory(LSTM) network, and the improved model may reduce comprehensive prediction error by usingGenerative Adversarial Network(GAN) according to the correlation of multi-index.
17603 最后通过优化目标函数及训练模型得出多指标预测结果。 Finally, the prediction results obtained by optimizing the objective function and model structure.
17604 经实验分析发现：小麦多指标的长短期时序数据的变化趋势不同，进一步优化模型结构及训练时序长度可有效降低预测结果的误差； The experimental analysis showsthat the training sequence length and structural parameters of the optimization model can effectively reducethe error of the prediction result.