arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2105.12433cs.LG
收藏

基于网络搜索活动的流感流行神经网络预测的不确定性评估

Estimating the Uncertainty of Neural Network Forecasts for Influenza Prevalence Using Web Search Activity

University College London(伦敦大学学院);University of Copenhagen(哥本哈根大学)

Michael Morris, Peter Hayes, Ingemar J. Cox, Vasileios Lampos

摘要:

流感是一种有可能成为大流行病的传染病,因此,预测其流行程度是规划有效应对措施的一项重要工作。研究发现,网络搜索活动可用于改进流感模型。神经网络(NN)可以提供最先进的预测精度,但通常不会将不确定性纳入其估计,这对于在决策过程中有效使用它们至关重要。在本文中,我们演示了如何贝叶斯神经网络(BNN)可以用来提供一个预测和相应的不确定性没有显着损失的预测精度相比,传统的NN。我们的方法占两个来源的不确定性:数据和模型的不确定性,分别由于测量噪声和模型规格。使用英格兰14年的数据进行实验,评估该数据集中过去4个流感季节模型的准确性。我们评估了不同模型的性能,包括具有竞争力的基线与传统的度量以及误差函数,将不确定性估计。我们的实证分析表明,同时考虑这两个来源的不确定性是优于单独考虑其中之一。我们还表明,一个BNN与循环层模型的不确定性来源产生优越的准确性,这些指标的预测范围大于7天。

英文摘要:

Influenza is an infectious disease with the potential to become a pandemic, and hence, forecasting its prevalence is an important undertaking for planning an effective response. Research has found that web search activity can be used to improve influenza models. Neural networks (NN) can provide state-of-the-art forecasting accuracy but do not commonly incorporate uncertainty in their estimates, something essential for using them effectively during decision making. In this paper, we demonstrate how Bayesian Neural Networks (BNNs) can be used to both provide a forecast and a corresponding uncertainty without significant loss in forecasting accuracy compared to traditional NNs. Our method accounts for two sources of uncertainty: data and model uncertainty, arising due to measurement noise and model specification, respectively. Experiments are conducted using 14 years of data for England, assessing the model's accuracy over the last 4 flu seasons in this dataset. We evaluate the performance of different models including competitive baselines with conventional metrics as well as error functions that incorporate uncertainty estimates. Our empirical analysis indicates that considering both sources of uncertainty simultaneously is superior to considering either one separately. We also show that a BNN with recurrent layers that models both sources of uncertainty yields superior accuracy for these metrics for forecasting horizons greater than 7 days.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑