Spatio-Temporal Recursive Method for Traffic Flow Interpolation

Kaydedildi:
Detaylı Bibliyografya
Yayımlandı:Symmetry vol. 17, no. 9 (2025), p. 1577-1594
Yazar: Wang, Gang
Diğer Yazarlar: Mao Yuhao, Liu, Xu, Liang Haohan, Li, Keqiang
Baskı/Yayın Bilgisi:
MDPI AG
Konular:
Online Erişim:Citation/Abstract
Full Text + Graphics
Full Text - PDF
Etiketler: Etiketle
Etiket eklenmemiş, İlk siz ekleyin!

MARC

LEADER 00000nab a2200000uu 4500
001 3254653026
003 UK-CbPIL
022 |a 2073-8994 
024 7 |a 10.3390/sym17091577  |2 doi 
035 |a 3254653026 
045 2 |b d20250101  |b d20251231 
084 |a 231635  |2 nlm 
100 1 |a Wang, Gang  |u Highway Monitoring and Emergency Response Center, Ministry of Transport of the P.R.C., Beijing 100029, China; wang.gang@hmrc.net.cn (G.W.); liuxu2023@buaa.edu.cn (X.L.) 
245 1 |a Spatio-Temporal Recursive Method for Traffic Flow Interpolation 
260 |b MDPI AG  |c 2025 
513 |a Journal Article 
520 3 |a Traffic data sequence imputation plays a crucial role in maintaining the integrity and reliability of transportation analytics and decision-making systems. With the proliferation of sensor technologies and IoT devices, traffic data often contain missing values due to sensor failures, communication issues, or data processing errors. It is necessary to effectively interpolate these missing parts to ensure the correctness of downstream work. Compared with other data, the monitoring data of traffic flow shows significant temporal and spatial correlations. However, most methods have not fully integrated the correlations of these types. In this work, we introduce the Temporal–Spatial Fusion Neural Network (TSFNN), a framework designed to address missing data recovery in transportation monitoring by jointly modeling spatial and temporal patterns. The architecture incorporates a temporal component, implemented with a Recurrent Neural Network (RNN), to learn sequential dependencies, alongside a spatial component, implemented with a Multilayer Perceptron (MLP), to learn spatial correlations. For performance validation, the model was benchmarked against several established methods. Using real-world datasets with varying missing-data ratios, TSFNN consistently delivered more accurate interpolations than all baseline approaches, highlighting the advantage of combining temporal and spatial learning within a single framework. 
653 |a Recurrent neural networks 
653 |a Traffic flow 
653 |a Data processing 
653 |a Missing data 
653 |a Monitoring 
653 |a Trends 
653 |a Correlation 
653 |a Multilayer perceptrons 
653 |a Sensors 
653 |a Neural networks 
653 |a Data recovery 
653 |a Support vector machines 
653 |a Recursive methods 
700 1 |a Mao Yuhao  |u CCSE Lab, Beihang University, Beijing 100083, China; haohanliang@buaa.edu.cn 
700 1 |a Liu, Xu  |u Highway Monitoring and Emergency Response Center, Ministry of Transport of the P.R.C., Beijing 100029, China; wang.gang@hmrc.net.cn (G.W.); liuxu2023@buaa.edu.cn (X.L.) 
700 1 |a Liang Haohan  |u CCSE Lab, Beihang University, Beijing 100083, China; haohanliang@buaa.edu.cn 
700 1 |a Li, Keqiang  |u School of Vehicle and Mobility, Tsinghua University, Beijing 100084, China; likq@tsinghua.edu.cn 
773 0 |t Symmetry  |g vol. 17, no. 9 (2025), p. 1577-1594 
786 0 |d ProQuest  |t Engineering Database 
856 4 1 |3 Citation/Abstract  |u https://www.proquest.com/docview/3254653026/abstract/embedded/J7RWLIQ9I3C9JK51?source=fedsrch 
856 4 0 |3 Full Text + Graphics  |u https://www.proquest.com/docview/3254653026/fulltextwithgraphics/embedded/J7RWLIQ9I3C9JK51?source=fedsrch 
856 4 0 |3 Full Text - PDF  |u https://www.proquest.com/docview/3254653026/fulltextPDF/embedded/J7RWLIQ9I3C9JK51?source=fedsrch