英语原文共 8 页,剩余内容已隐藏,支付完成后下载完整资料
Deep Multi-View Spatial-Temporal Network for Taxi Demand Prediction
Abstract
Taxi demand prediction is an important building block to enabling intelligent transportation systems in a smart city. An accurate prediction model can help the city pre-allocate resources to meet travel demand and to reduce empty taxis on streets which waste energy and worsen the traffic congestion. With the increasing popularity of taxi requesting services such as Uber and Didi Chuxing (in China), we are able to collect large-scale taxi demand data continuously. How to utilize such big data to improve the demand prediction is an interesting and critical real-world problem. Traditional demand prediction methods mostly rely on time series forecasting techniques, which fail to model the complex non-linear spatial and temporal relations. Recent advances in deep learning have shown superior performance on traditionally challenging tasks such as image classification by learning the complex features and correlations from largescale data. This breakthrough has inspired researchers to explore deep learning techniques on traffic prediction problems. However, existing methods on traffic prediction have only considered spatial relation (e.g., using CNN) or temporal relation (e.g., using LSTM) independently. We propose a Deep Multi-View Spatial-Temporal Network(DMVST-Net)framework to model both spatial and temporal relations. Specifically, our proposed model consists of three views: temporal view (modeling correlations between future demand values with near time points via LSTM), spatial view (modeling local spatial correlation via local CNN), and semantic view (modeling correlations among regions sharing similar temporal patterns). Experiments on large-scale real taxi demand data demonstrate effectiveness of our approach over state-of-the-art methods.
Introduction
Traffic is the pulse of a city that impacts the daily life of millions of people. One of the most fundamental questions for future smart cities is how to build an efficient transportation system. To address this question, a critical component is an accurate demand prediction model. The better we can predict demand on travel, the better we can pre-allocate resources to meet the demand and avoid unnecessary energy consumption. Currently, with the increasing popularity of taxi requesting services such as Uber and Didi Chuxing, we are able to collect massive demand data at an unprecedented scale. The question of how to utilize big data to better predict traffic demand has drawn increasing attention in AI research communities.
In this paper, we study the taxi demand prediction problem; that problem being how to predict the number of taxi requests for a region in a future timestamp by using historical taxi requesting data. In literature, there has been a long line of studies in traffic data prediction, including traffic volume, taxi pick-ups, and traffic in/out flow volume. To predict traffic, time series prediction methods have frequently been used. Representatively, autoregressive integrated moving average (ARIMA) and its variants have been widely applied for traffic prediction (Li et al. 2012; Moreira-Matias et al. 2013; Shekhar and Williams 2008). Based on the time series prediction method, recent studies further consider spatial relations (Deng et al. 2016; Tong et al. 2017) and external context data (e.g., venue, weather, and events) (Pan, Demiryurek, and Shahabi 2012; Wu, Wang, and Li 2016). While these studies show that prediction can be improved by considering various additional factors ,they still fail to capture the complex nonlinear spatial-temporal correlations.
Recent advances in deep learning have enabled re-searchers to model the complex nonlinear relationships and have shown promising results in computer vision and natural language processing fields (Lecun, Bengio, and Hin-ton 2015). This success has inspired several attempts to use deep learning techniques on traffic prediction problems. Recent studies(Zhang, Zheng, and Qi 2017; Zhang et al. 2016)propose to treat the traffic in a city as an image and the traffic volume for a time period as pixel values. Given a set of historical traffic images, the model predicts the traffic image for the next timestamp Convolutional neural network(CNN)is applied to model the complex spatial correlation. Yu et al. (2017) proposes to use Long Short Term Memory networks (LSTM) to predict loop sensor readings. They show the proposed LSTM model is capable of modeling complex sequential interactions. These pioneering attempts show superior performance compared with previous methods based on traditional time series prediction methods. However, none of them consider spatial relation and temporal sequential relation simultaneously.
In this paper, we harness the power of CNN and LSTM in a joint model that captures the complex nonlinear relations of both space and time. However, we cannot simply apply CNN and LSTM on demand prediction problem. If treating the demand over an entire city as an image and applying CNN on this image, we fail to achieve the best result. We realize including regions with weak correlations to predict a target region actually hurts the performance. To address this issue, we propose a novel local CNN method which only considers spatially nearby regions. This local CNN method is motivated by the First Law of Geography: “near things are more related than dis
剩余内容已隐藏,支付完成后下载完整资料
资料编号:[236807],资料为PDF文档或Word文档,PDF文档可免费转换为Word
以上是毕业论文外文翻译,课题毕业论文、任务书、文献综述、开题报告、程序设计、图纸设计等资料可联系客服协助查找。