Hotspot Forecast of Taxi Demand Based on WCGAN

doi:10.3778/j.issn.1002-8331.2203-0274

Abstract

Abstract: Empty taxis affect the allocation of traffic resources and the income of taxi drivers. Accurate taxi demand hot spot prediction can effectively guide taxi drivers to optimize the route for passengers. Aiming at this problem, a taxi based on conditional generative adversarial network is proposed. Demand hot spot prediction method, which is based on the wasserstein conditional generative adversarial network（WCGAN）, uses the convolutional long short-term memory neural network（ConvLSTM） in the generator to capture the long-term dependencies of the time series, and uses the temporal discriminator and spatial discriminator respectively. The discriminator extracts the spatio-temporal characteristics of passenger historical demand distribution. Using Lanzhou taxi trajectory data, the method proposed in this paper is compared with three algorithms：long short-term memory neural network（LSTM） algorithm, spatio-temporal residual network（ST-ResNet） and BP neural network（BPNN）. The average absolute error is reduced by 17.3%, 8.4% and 10.3% respectively.

Key words: hot spots prediction, generative adversarial networks（GAN）, convolutional long short-term memory neural network（ConvLSTM）

摘要： 出租车空驶影响交通资源分配，同时影响出租车司机收益，准确的出租车需求热点预测可以有效地指导出租车驾驶员对寻客路线进行优化，针对该问题提出了基于条件生成对抗网络的出租车需求热点预测方法。该方法在Wasserstein条件生成对抗网络（WCGAN）的基础上，利用生成器中的卷积长短时记忆神经网络（ConvLSTM）捕捉时间序列的长期依赖关系，分别利用时间判别器和空间判别器提取乘客历史需求分布时空特性。利用兰州市出租车轨迹数据，将提出的方法与长短时记忆神经网络（LSTM）算法、时空残差网络（ST-ResNet））和BP神经网络（BPNN）三种算法进行对比，平均绝对误差分别降低了17.3%、8.4%和10.3%。

关键词: 需求热点预测, 生成对抗网络, 卷积长短时记忆神经网络（ConvLSTM）

WANG Bowei, DENG Jun, LYU Bin. Hotspot Forecast of Taxi Demand Based on WCGAN[J]. Computer Engineering and Applications, 2023, 59(12): 293-300.

王博伟, 邓君, 吕斌. 基于WCGAN的出租车需求热点预测[J]. 计算机工程与应用, 2023, 59(12): 293-300.

References

[1] 倪杰，于莉，靳笑楠.基于ARIMA模型的城市轨道交通客流预测及研究[J].智能计算机与应用，2021，11（4）：135-138.
NI J，YU L，JIN X N.Forecast and research of urban rail transit passenger flow based on ARIMA model[J].Intelligent Computer and Applications，2021，11（4）：135-138.
[2] 宋龙泽，万怀宇，郭晟楠，等.面向出租车空载时间预测的多任务时空图卷积网络[J].计算机科学，2021，48（7）：112-117.
SONG L Z，WAN H Y，GUO S N，et al.Multi-task spatio-temporal graph convolutional network for taxi idle time prediction[J].Computer Science，2021，48（7）：112-117.
[3] 曲昭伟，王鑫，宋现敏，等.基于出租车GPS大数据的城市热点出行路段识别方法[J].交通运输系统工程与信息，2019，19（2）：238-246.
QU Z W，WANG X，SONG X M，et al.Urban hotspot travel section identification method based on taxi GPS large data[J].Journal of Transportation Systems Engineering and Information Technology，2019，19（2）：238-246.
[4] KONG X，XIAN F，WANG J，et al.Time-location-relationship combined service recommendation based on taxi trajectory data[J].IEEE Transportation on Industral Informatics，2017，6（3）.
[5] 冯然，张力仁，王立辉.基于二阶马尔可夫链的不确定性轨迹预测[J].测绘与空间地理信息，2020，43（S1）：207-211.
FENG R，ZHANG L R，WANG L H.Uncertainty trajectory prediction based on second-order Markov chain[J].Geomatics & Spatial Information Technology，2020，43（S1）：207-211.
[6] LIU X，SUN L，SUN Q，et al.Spatial variation of taxi demand using GPS trajectories and POI data[J].Journal of Advanced Transportation，2020（12）：1-20.
[7] 张政，陈艳艳，梁天闻.基于网约车数据的城市区域出行时空特征识别与预测研究[J].交通运输系统工程与信息，2020，20（3）：89-94.
ZHANG Z，CHEN Y Y，LIANG T W.Regional travel demand mining and forecasting using car-hailing order records[J].Journal of Transportation Systems Engineering and Information Technology，2020，20（3）：89-94.
[8] CHAN K Y，DILLON T，CHANG E，et al.Prediction of short-term traffic variables using intelligent swarm-based neural networks[J].IEEE Transactions on Control Systems Technology，2013，21（1）：263-274.
[9] LIU T，WU W，ZHU Y，et al.Predicting taxi demands via an attention-based convolutional recurrent neural network[J].Knowledge-Based Systems，2020，206（1）：106294.
[10] 张国兴，李亚东，张磊，等.基于SDZ-RNN的出租车出行目的地预测方法[J].计算机工程与应用，2018，54（6）：143-149.
ZHANG G X，LI Y D，ZHANG L，et al.Taxi travel destination prediction based on SDZ-RNN[J].Computer Engineering and Applications，2018，54（6）：143-149.
[11] 安磊，赵书良，武永亮，等.基于recurrent neural networks的网约车供需预测方法[J].计算机应用研究，2019，36（3）：756-761.
AN L，ZHAO S L，WU Y L，et al.Prediction method of supply and demand for online car based on recurrent neural networks[J].Computer Application Research，2019，36（3）：756-761.
[12] GOODFELLOW I，POUGET-ABADIE J，MIRZA M，et al.Generative adversarial nets[C]//Proceedings of the 27th International Conference on Neural Information Processing Systems.Lake Tahoe：ACM，2014：2672-2680.
[13] 代亮，梅洋，钱超，等.基于生成对抗网络的大规模路网交通流预测算法[J].控制与决策，2021，36（12）：2937-2945.
DAI L，MEI Y，QIAN C，et al.Traffic flow forecasting algorithm for large-scale road network based on GAN[J].Control and Decision，2021，36（12）：2937-2945.
[14] SAXENA D，CAO?J.D-GAN：deep generative adversarial nets for spatio-temporal prediction[J].arXiv：1907.08556，2019.
[15] YU H，LI Z，ZHANG G，et al.Extracting and predicting taxi hotspots in spatiotemporal dimensions using conditional generative adversarial neural networks[J].IEEE Transactions on Vehicular Technology，2020，69（4）：3680-3692.
[16] MIRZA M，OSINDERO S.Conditional generative adversarial nets[J].arXiv：1411.1784，2014.
[17] ARJOVSKY M，CHINTALA S，BOTTOU L.Wasserstein generative adversarial networks[C]//Proceedings of the 34th International Conference on Machine Learning.Lake Tahoe：ACM，2017.
[18] BAI L，YAO L，KANHERE S S，et al.STG2Seq：Spatial-temporal graph to sequence model for multi-step passenger demand forecasting[J].arXiv：1905.10069，2019.
[19] KIPF T N，WELLING M.Semi-supervised classification with graph convolutional networks[J].arXiv：1609.02907，2016.
[20] SHI X J，CHEN Z R，WANG H，et al.Convolutional LSTM network：a machine learning approach for precipitation nowcasting[J].arXiv：1506.04214，2015.
[21] WANG Y，LONG M，WANG J，et al.PredRNN：recurrent neural networks for prediction learning using spatiotemporal LSTMs[C]//31st Conference on Neural Information Processing Systems（NIPS 2017），Long Beach，CA，USA，2017.
[22] LIU L，QIU Z，LI G Q，et al.Contextualized spatial-temporal network for taxi origin-destination demand prediction[J].IEEE Transactions on Intelligent Transportation Systems，2019，20（10）：3875-3887.
[23] 陈文强，吴群琪.城市交通拥堵背景下的出租车管制效应分析[J].华东交通大学学报，2012，29（5）：68-73.
CHEN W Q，WU Q Q.Effect analysis of taxicab industry regulation in the context of urban traffic congestion[J].Journal of East China Jiaotong University，2012，29（5）：68-73.