Summary of Incorporating Uncertainty Quantification Into Travel Mode Choice Modeling: a Bayesian Neural Network (bnn) Approach and An Uncertainty-guided Active Survey Framework, by Shuwen Zheng et al.
Incorporating uncertainty quantification into travel mode choice modeling: a Bayesian neural network (BNN) approach and an uncertainty-guided active survey framework
by Shuwen Zheng, Zhou Fang, Liang Zhao
First submitted to arxiv on: 16 Jun 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This paper proposes a novel approach to travel mode choice modeling by incorporating uncertainty quantification using Bayesian neural networks. The authors develop a Bayesian Travel Mode Prediction (BTMP) model that can identify and quantify its own prediction uncertainty, allowing it to “know” what it doesn’t know. This is achieved through an uncertainty-guided active survey framework that dynamically formulates survey questions based on the model’s predicted uncertainty. Experimental results show that the BTMP model requires 20-50% fewer survey responses to match the performance of traditional models trained on randomly collected data, while also providing valuable insights into prediction reliability. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper introduces a new approach for travel mode choice modeling by combining Bayesian neural networks and explainable AI techniques. The authors develop a model that can predict travel modes and quantify its own uncertainty, which is useful in scenarios where the input data is out of the training distribution. This is achieved through an active survey framework that dynamically generates questions based on the model’s predicted uncertainty. The experimental results show that the proposed approach requires fewer survey responses while still achieving high accuracy. |
