基于CNN和LSTM的移动对象目的地预测

Destination Prediction of Moving Objects Based on Convolutional Neural Networks and Long-Short Term Memory

移动对象目的地预测是基于位置的服务的重要组成部分。该领域一直存在数据稀疏、长期依赖等难以解决的问题。为了有效解决这些问题,首先引入了一种基于最小描述长度策略(Minimum Description Length,MDL)的轨迹分段方法,以获得轨迹的最佳分段,提高轨迹之间的相似度,实现对轨迹的简化。随后将分段后的数据进行图像化处理和局部特征提取,并对轨迹目的地进行聚类,从而为轨迹数据增加标签。最后提出了一种基于卷积和长短期记忆循环单元的深度学习算法CNN-LSTM,该算法先将局部图像数据和标签作为卷积神经网络(Convolutional Neural Network,CNN)模型的输入,通过空间特征的深度提取来保留有效信息,再利用长短期记忆网络(Long-Short Term Memory,LSTM)算法进行训练和目的地预测。在移动对象的真实轨迹数据集上进行了大量实验,结果表明,所提CNN-LSTM方法具有较强的学习能力,能更好地捕捉轨迹时空相关性。与现有的最新相关算法相比,该方法具有很高的目的地预测准确度。

Destination prediction of moving objects is an important part of location-based service.There are always some difficult problems in this field,such as sparse data and long-term dependence.In order to solve these problems effectively,firstly,a trajectory segmentation method based on the minimum description length strategy(MDL)is introduced,which can obtain the best tra-jectory segmentation,improve the similarity between tracks and realize the simplification of trajectories.Then,the segmented data are processed by image processing and local extraction,and the trajectory destination is clustered to add labels to the trajectory data.Finally,this paper proposes a deep learning framework CNN-LSTM based on convolution and long-short term memory.In this framework,local image data and labels firstly are taken as the input of the CNN model,and the effective information is preserved through the depth extraction of spatial features.Then,the LSTM algorithm is used for training and destination prediction.Extensive experiments are carried out on real trajectory dataset of moving objects.The results demonstrate that the CNN-LSTM method proposed in this paper has a strong learning ability and can better capture the spatiotemporal correlation of trajectories.In comparison to state-of-the-art and latest prediction algorithms,this method has high accuracy of destination prediction.