Activity-based model based on long short-term memory network and mobile phone signalling data
Activity-based model based on long short-term memory network and mobile phone signalling data
复制标题
DOI：
10.1080/23249935.2023.2217283
复制
发表时间：
2023-05
期刊：
影响因子：
--
通讯作者：
Yudong Guo;Fei Yang;Siyuan Xie;Zhenxing Yao
中科院分区：
文献类型：
--
作者：
Yudong Guo;Fei Yang;Siyuan Xie;Zhenxing Yao
随着大数据时代的到来，基于活动的交通规划模型（activity-based model， ABM）再次成为交通规划研究的热点。交通大数据可以反映个人出行模式，为建立ABMs提供可能。然而，目前基于大数据的ABMs还不成熟，尤其是在个人出行预测方面。因此，本文提出了一种利用长短期记忆（LSTM）网络和移动电话信令数据的高级ABM。该模型是包含主活动链和次活动嵌套的骨架调度。在此基础上，提出了一种时间动态调整模型来调整连续活动之间的时间冲突。在成都进行了现场试验。工作离场时间和休闲离场时间的KS分别为35.20 × 10−2和41.02 × 10−2，活动离场时间的KS分别为44.91 × 10−2和54.65 × 10−2。结果表明，该模型能够有效地预测活动，并且比现有的BN、DT、GRNN、RF和GRU具有更好的精度和稳定性。
With the advent of big data era, activity-based model (ABM) has once again become hot topics in the traffic planning. Traffic big data can reflect individual travel patterns, making it possible to establish ABMs. However, current ABMs based on big data are not mature, especially in the individual trip forecasting. Therefore, this paper proposes an advanced ABM using Long Short-Term Memory (LSTM) networks and mobile phone signalling data. The model is skeleton scheduling which contains primary activity chaining and secondary activity nesting. Then a time-dynamic adjustment model is proposed to adjust time conflicts among consecutive activities. A field test is conducted in Chengdu. The KS values of work and leisure departure time reach 35.20 × 10−2 and 41.02 × 10−2 separately, and that for activity duration reach 44.91 × 10−2 and 54.65 × 10−2. The results show our model can effectively predict activities, and has better accuracy and stability than existing BN, DT, GRNN, RF and GRU.