[20240701_LabSeminar_Huy]TelTrans: Applying Multi-Type Telecom Data to Transportation Evaluation and Prediction via Multifaceted Graph Modeling.pptx

TelTrans: Applying Multi-Type Telecom Data to Transportation Evaluation and Prediction via Multifaceted Graph Modeling

1. Quang-Huy Tran Network Science Lab Dept. of Artificial Intelligence The Catholic University of Korea E-mail: [email protected] 2024-07-01 TelTrans : Applying Multi-Type Telecom Data to Transportation Evaluation and Prediction via Multifaceted Graph Modeling ChungYi Lin et al. AAAI- 202 4: Proceedings of the Thirty-Eight h Conference on Artificial Intelligence

2. OUTLINE MOTIVATION METHODOLOGY EXPERIMENT & RESULT CONCLUSION

3. MOTIVATION Accurate traffic prediction can alleviate congestion and enhance traffic signal o ptimization in many application fields for intelligent transportation systems. But they rely on dedicated sensors – cost and maintenance issue. Overview Leveraging the extensive mobile network coverage. Geographically inherent cellular traffic offers a unique insight into transportation dynamics.

4. INTRODUCTION Present the Geographical Cellular Traffic (GCT) Flows : Define the GCT flow as the accumulation of GCTs over specific time intervals in road segments. Categorize into three distinct types: Vehicle (V-GCT) , Pedestrian(P-GCT), and Stationary (S-GCT) . Contribution Propose a novel model with three facets for predicting V-GCT : Multivariate : discerning the interplay among multi-type GCT flows to uncover hidden regional functionality. Temporal: separating short-term and long-term dynamics to avoid entangled dependencies. Spatial : capturing bidirectional user mobility to understand the spatial dependencies.

5. METHODOLOGY Problem Definition Given a dataset: road segments, D observations. Feature matrix from historical steps of multi-type GCT flow. stands for V-GCT, S-GCT, or P-GCT.   Problem: forecast V-GCT in the upcoming steps  

6. METHODOLOGY Main Architecture Three facets from CGAT: Channel-Specific Graph Attention (CGAT). Multivariate Facet: Capturing interactions among multitype GCT flows reveals implicit regional functionality. Temporal Facet: Extracts short-term and long-term patterns to discern sudden and regular patterns separately. Spatial Facet: Captures bidirectional spatial dependencies among road segments due to user mobility. Overall: Begins with a 32-channel CNN layer to encode all GCT flow types. Vehicle (V-GCT) , Pedestrian(P-GCT), and Stationary (S-GCT) . Output Layer: use 64-channel CNN layer as skip connections at every Temporal Facet Modeling.

7. METHODOLOGY Channel-Specific Graph Attention Layer (CGATL) For multi-channel representation H (size [C × N × D]), employ C independent GATs. Examine distinct correlations among N nodes of each channel c. where , is the neighbors of node , and is a nonlinear function.   Where H with dimension [C × N × D] and G is a graph structure indicating connections among nodes in H. A dopt 1×1 convolution layers for Encoder and Decoder to compute efficiently: R educes the channel count from C to C′ (C′< C) in encoder and restore to C in decoder.

8. METHODOLOGY Multivariate Facet Modeling Insight: M odeling with subtracted type flows to emphasize differences between V-GCT and P-GCT, hence revealing regional attributes. E ach time step t , concatenate with along third dimension Then, reshape into [C × 3 × N] from [C × N × 3] and apply CGATL.   Where ‘Extract’ function retrieves the enhanced representation of , the first element of from CGATL’s output.   Concatenate the output of all time step along second dimension [C × T × N]: : multi-channel representations of VGCT flow and either P-GCT or S-GCT flow. : either be P-GCT or S-GCT flow.   : complete graph that reveals the connections among various GCT flow types.  

9. METHODOLOGY Temporal Facet Modeling Insight: emphasize short-term and long-term from heightened fluctuations in V-GCT flow. Use two CNNs with kernel sizes (2 × 1) and (5 × 1) to extract short- and long-term temporal patterns from multichannel representation H( H 2 and H 5 ) . A pply CGATL separate and concatenate: Reshape H 2 from [C × (T − 1) × S] to [C × (T − 4) × S] to align of H 5 . Implement the Gating Mechanism to manage ratio of information passed to the next module Where ‘ Concat ’ function merges two outputs along the second dimension of [C × T × N]. where and are generated from CGATL. denotes the tangent hyperbolic function, and represents the Hadamard product.  

10. METHODOLOGY Spatial Facet Modeling Insight: GCT flow of an upstream segment influences the downstream GCT flow. Users’ mobility may cause them to move back and forth due to their activity behaviors. Accounting for bidirectional variations among road segments can lead to a comprehensive understanding of user mobility. Assign specific directional graphs, and , to each CGATL and then combine:   where H is multi-channel representation reshaped to [C × S ×T], regarded as S road segment with T observations. Forward and backward graph structure, created by threshold of Gaussian Kernel and .  

11. EXPERIMENT AND RESULT EXPERIMENT SETTINGs Dataset: Geographical Cellular Traffic in Hsinchu, Taiwan. Baselines: Deep Learning: Temporal Convolution (TCN). STGNN: Graph WaveNet ( GWNet )[1], MTGNN [2], Gman [3], MPNet [4], DMGCN [5] and ESG[6]. [1] Wu, Z., Pan, S., Long, G., Jiang, J., & Zhang, C. (2019). Graph wavenet for deep spatial-temporal graph modeling. arXiv preprint arXiv:1906.00121. [2] Wu, Z., Pan, S., Long, G., Jiang, J., Chang, X., & Zhang, C. (2020, August). Connecting the dots: Multivariate time series forecasting with graph neural networks. In Proceedings of the 26th ACM SIGKDD international conference on knowledge discovery & data mining (pp. 753-763). [3] Zheng, C., Fan, X., Wang, C., & Qi, J. (2020, April). Gman : A graph multi-attention network for traffic prediction. In Proceedings of the AAAI conference on artificial intelligence (Vol. 34, No. 01, pp. 1234-1241). [4] Lin, C. Y., Su, H. T., Tung, S. L., & Hsu, W. H. (2021, October). Multivariate and propagation graph attention network for spatial-temporal prediction with outdoor cellular traffic. In Proceedings of the 30th ACM International Conference on Information & Knowledge Management (pp. 3248-3252). [5] Han, L., Du, B., Sun, L., Fu, Y., Lv , Y., & Xiong, H. (2021, August). Dynamic and multi-faceted spatio -temporal deep learning for traffic speed forecasting. In Proceedings of the 27th ACM SIGKDD conference on knowledge discovery & data mining (pp. 547-555). [6] Ye, J., Liu, Z., Du, B., Sun, L., Li, W., Fu, Y., & Xiong, H. (2022, August). Learning the evolutionary and multi-scale graph structure for multivariate time series forecasting. In Proceedings of the 28th ACM SIGKDD conference on knowledge discovery and data mining (pp. 2296-2306). Measurement : Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), and Mean Absolute Percentage Error (MAPE).

12. EXPERIMENT AND RESULT RESULT – Overall Perfor mance

13. EXPERIMENT AND RESULT RESULT – Sensitivity Analysis of Multi-Type GCT Flows

14. CONCLUSION Presented multi-type GCT flows as a novel data source for transportation and proposed MFGM to predict V-GCT flows. Integrating multi-type GCT flows. Accuracy is improved. Integrated V-GCT into transportation systems, presenting new applications for telecom data in transportation. Summarization