A Comparative Study of Loss Functions: Traffic Predictions in Regular and Congestion Scenarios

• URL: http://arxiv.org/abs/2308.15464v1
• Date: Tue, 29 Aug 2023 17:44:02 GMT
• Title: A Comparative Study of Loss Functions: Traffic Predictions in Regular and Congestion Scenarios
• Authors: Yangxinyu Xie, Tanwi Mallick
• Abstract summary: We explore various loss functions inspired by heavy tail analysis and imbalanced classification problems to address this issue. We discover that when optimizing for Mean Absolute Error (MAE), the MAE-Focal Loss function stands out as the most effective. This research enhances deep learning models' capabilities in forecasting sudden speed changes due to congestion.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Spatiotemporal graph neural networks have achieved state-of-the-art performance in traffic forecasting. However, they often struggle to forecast congestion accurately due to the limitations of traditional loss functions. While accurate forecasting of regular traffic conditions is crucial, a reliable AI system must also accurately forecast congestion scenarios to maintain safe and efficient transportation. In this paper, we explore various loss functions inspired by heavy tail analysis and imbalanced classification problems to address this issue. We evaluate the efficacy of these loss functions in forecasting traffic speed, with an emphasis on congestion scenarios. Through extensive experiments on real-world traffic datasets, we discovered that when optimizing for Mean Absolute Error (MAE), the MAE-Focal Loss function stands out as the most effective. When optimizing Mean Squared Error (MSE), Gumbel Loss proves to be the superior choice. These choices effectively forecast traffic congestion events without compromising the accuracy of regular traffic speed forecasts. This research enhances deep learning models' capabilities in forecasting sudden speed changes due to congestion and underscores the need for more research in this direction. By elevating the accuracy of congestion forecasting, we advocate for AI systems that are reliable, secure, and resilient in practical traffic management scenarios.

Related papers

• Physics-guided Active Sample Reweighting for Urban Flow Prediction [75.24539704456791]
  Urban flow prediction is a nuanced-temporal modeling that estimates the throughput of transportation services like buses, taxis and ride-driven models. Some recent prediction solutions bring remedies with the notion of physics-guided machine learning (PGML) We develop a atized physics-guided network (PN), and propose a data-aware framework Physics-guided Active Sample Reweighting (P-GASR)
  arXiv  Detail & Related papers  (2024-07-18T15:44:23Z)
• Interpretable Cascading Mixture-of-Experts for Urban Traffic Congestion Prediction [24.26429523848735]
  Rapid urbanization has significantly escalated traffic congestion, underscoring the need for advanced congestion prediction services. We introduce a Congestion Prediction Mixture-of-Experts, CP-MoE, to address the challenges. CP-MoE has been deployed in DiDi to improve the accuracy and reliability of the travel time estimation system.
  arXiv  Detail & Related papers  (2024-06-14T12:57:17Z)
• Enhancing Traffic Flow Prediction using Outlier-Weighted AutoEncoders: Handling Real-Time Changes [0.7614628596146602]
  We introduce the Outlier Weighted Autoencoder Modeling (OWAM) framework. OWAM employs autoencoders for local outlier detection and generates correlation scores to assess neighboring traffic's influence. This information enhances the traffic model's performance and supports effective real-time updates.
  arXiv  Detail & Related papers  (2023-12-27T14:44:58Z)
• An Application of Vector Autoregressive Model for Analyzing the Impact of Weather And Nearby Traffic Flow On The Traffic Volume [0.0]
  This paper aims to predict the traffic flow at one road segment based on nearby traffic volume and weather conditions. Our team also discover the impact of weather conditions and nearby traffic volume on the traffic flow at a target point.
  arXiv  Detail & Related papers  (2023-11-12T16:45:29Z)
• Networkwide Traffic State Forecasting Using Exogenous Information: A Multi-Dimensional Graph Attention-Based Approach [0.0]
  This paper proposes a graph-based traffic prediction approach (M-STGAT) It predicts traffic based on past observations of speed, along with lane closure events, temperature, and visibility across the transportation network. It is shown to outperform three alternative models when performing tests with a 30-, 45-, and 60-minute prediction horizon.
  arXiv  Detail & Related papers  (2023-10-18T21:57:20Z)
• Streaming Motion Forecasting for Autonomous Driving [71.7468645504988]
  We introduce a benchmark that queries future trajectories on streaming data and we refer to it as "streaming forecasting" Our benchmark inherently captures the disappearance and re-appearance of agents, which is a safety-critical problem yet overlooked by snapshot-based benchmarks. We propose a plug-and-play meta-algorithm called "Predictive Streamer" that can adapt any snapshot-based forecaster into a streaming forecaster.
  arXiv  Detail & Related papers  (2023-10-02T17:13:16Z)
• Uncertainty Quantification for Image-based Traffic Prediction across Cities [63.136794104678025]
  Uncertainty quantification (UQ) methods provide an approach to induce probabilistic reasoning. We investigate their application to a large-scale image-based traffic dataset spanning multiple cities. We find that our approach can capture both temporal and spatial effects on traffic behaviour in a representative case study for the city of Moscow.
  arXiv  Detail & Related papers  (2023-08-11T13:35:52Z)
• Multi-graph Spatio-temporal Graph Convolutional Network for Traffic Flow Prediction [0.5551832942032954]
  Daily traffic flow prediction still faces challenges at network-wide toll stations. In this paper, a correlative prediction method is proposed for daily traffic flow highway domain through flow-temporal deep learning. Our method shows clear improvement in predictive accuracy than baselines and practical benefits in business.
  arXiv  Detail & Related papers  (2023-08-10T14:20:43Z)
• Implicit Occupancy Flow Fields for Perception and Prediction in Self-Driving [68.95178518732965]
  A self-driving vehicle (SDV) must be able to perceive its surroundings and predict the future behavior of other traffic participants. Existing works either perform object detection followed by trajectory of the detected objects, or predict dense occupancy and flow grids for the whole scene. This motivates our unified approach to perception and future prediction that implicitly represents occupancy and flow over time with a single neural network.
  arXiv  Detail & Related papers  (2023-08-02T23:39:24Z)
• A Graph Convolutional Network with Signal Phasing Information for Arterial Traffic Prediction [63.470149585093665]
  arterial traffic prediction plays a crucial role in the development of modern intelligent transportation systems. Many existing studies on arterial traffic prediction only consider temporal measurements of flow and occupancy from loop sensors and neglect the rich spatial relationships between upstream and downstream detectors. We fill this gap by enhancing a deep learning approach, Diffusion Convolutional Recurrent Neural Network, with spatial information generated from signal timing plans at targeted intersections.
  arXiv  Detail & Related papers  (2020-12-25T01:40:29Z)
• The Importance of Prior Knowledge in Precise Multimodal Prediction [71.74884391209955]
  Roads have well defined geometries, topologies, and traffic rules. In this paper we propose to incorporate structured priors as a loss function. We demonstrate the effectiveness of our approach on real-world self-driving datasets.
  arXiv  Detail & Related papers  (2020-06-04T03:56:11Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.