Prediction, Expectation, and Surprise: Methods, Designs, and Study of a Deployed Traffic Forecasting Service

Horvitz, Eric; Apacible, Johnson; Sarin, Raman; Liao, Lin

doi:10.48550/arxiv.1207.1352

Cited by 22 publications

(6 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The availability of people's locations and movements supports progress in "mobility analytics" -e.g., applications geared to improve urban planning [4], study the effect of "shocks" on transport [44], predict events [22], detect traffic anomalies [32], generate real-time traffic statistics [1], etc. At the same time, however, large-scale collection of individuals' whereabouts prompts serious privacy concerns, as location data may reveal one's occupation, lifestyle, as well as political and religious beliefs [25,33].…”

Section: Introductionmentioning

confidence: 99%

What Does The Crowd Say About You? Evaluating Aggregation-based Location Privacy

Pyrgelis

Troncoso

Cristofaro

2017

Proceedings on Privacy Enhancing Technologies

View full text Add to dashboard Cite

Information about people's movements and the locations they visit enables an increasing number of mobility analytics applications, e.g., in the context of urban and transportation planning, In this setting, rather than collecting or sharing raw data, entities often use aggregation as a privacy protection mechanism, aiming to hide individual users' location traces. Furthermore, to bound information leakage from the aggregates, they can perturb the input of the aggregation or its output to ensure that these are differentially private. In this paper, we set to evaluate the impact of releasing aggregate location time-series on the privacy of individuals contributing to the aggregation. We introduce a framework allowing us to reason about privacy against an adversary attempting to predict users' locations or recover their mobility patterns. We formalize these attacks as inference problems, and discuss a few strategies to model the adversary's prior knowledge based on the information she may have access to. We then use the framework to quantify the privacy loss stemming from aggregate location data, with and without the protection of differential privacy, using two real-world mobility datasets. We find that aggregates do leak information about individuals' punctual locations and mobility profiles. The density of the observations, as well as timing, play important roles, e.g., regular patterns during peak hours are better protected than sporadic movements. Finally, our evaluation shows that both output and input perturbation offer little additional protection, unless they introduce large amounts of noise ultimately destroying the utility of the data.

show abstract

Section: Introductionmentioning

confidence: 99%

What Does The Crowd Say About You? Evaluating Aggregation-based Location Privacy

Pyrgelis

Troncoso

Cristofaro

2017

Proceedings on Privacy Enhancing Technologies

View full text Add to dashboard Cite

show abstract

“…However, a similar phenomena can be observed not only between downstream and upstream locations on a highway. A similar relationship can be established between locations on city streets and highways (Horvitz, Apacible, Sarin, & Liao, 2012).…”

Section: Traffic Flow On Chicago's Interstate I-55mentioning

confidence: 63%

Deep learning for spatio‐temporal modeling: Dynamic traffic flows and high frequency trading

Dixon

Polson

Sokolov

2018

Appl Stoch Models Bus & Ind

View full text Add to dashboard Cite

Deep learning applies hierarchical layers of hidden variables to construct nonlinear high dimensional predictors. Our goal is to develop and train deep learning architectures for spatio-temporal modeling. Training a deep architecture is achieved by stochastic gradient descent and dropout for parameter regularization with a goal of minimizing out-of-sample predictive mean squared error. To illustrate our methodology, we first predict the sharp discontinuities in traffic flow data, and secondly, we develop a classification rule to predict short-term futures market prices using order book depth. Finally, we conclude with directions for future research.

show abstract

“…This is why research done in this area is scarce [35], [41]. However, in the particular context of traffic forecasting, the advantages of adopting a stream learning approach reside in the need for dealing with possible concept drift [8], as well as in the implementation constraints derived from deploying the model [11]. Usually, after a traditional batch training phase using all initially available data, the traffic forecasting system is deployed.…”

Section: B Offline and Online Versions Of The Learning Methodsmentioning

confidence: 99%

“…The essential purpose of traffic management systems, for which the level of service is inferred from e.g. congestion levels, is to take active measures and provide information to road users [11]. Thus, while traffic flow forecasts need to be interpreted alongside other inputs, such as the road capacity or the typical flow profiles at different locations of the road network, variables like speed or travel time are more straightforward to be used, as it is easier for a practitioner to discriminate whether a certain speed implies free-flow circulation or a bottleneck.…”

Section: Introductionmentioning

confidence: 99%

New Perspectives on the Use of Online Learning for Congestion Level Prediction over Traffic Data

Manibardo¹,

Laña²,

Lobo³

et al. 2020

Preprint

View full text Add to dashboard Cite

This work focuses on classification over time series data. When a time series is generated by non-stationary phenomena, the pattern relating the series with the class to be predicted may evolve over time (concept drift). Consequently, predictive models aimed to learn this pattern may become eventually obsolete, hence failing to sustain performance levels of practical use. To overcome this model degradation, online learning methods incrementally learn from new data samples arriving over time, and accommodate eventual changes along the data stream by implementing assorted concept drift strategies.In this manuscript we elaborate on the suitability of online learning methods to predict the road congestion level based on traffic speed time series data. We draw interesting insights on the performance degradation when the forecasting horizon is increased. As opposed to what is done in most literature, we provide evidence of the importance of assessing the distribution of classes over time before designing and tuning the learning model. This previous exercise may give a hint of the predictability of the different congestion levels under target. Experimental results are discussed over real traffic speed data captured by inductive loops deployed over Seattle (USA). Several online learning methods are analyzed, from traditional incremental learning algorithms to more elaborated deep learning models. As shown by the reported results, when increasing the prediction horizon, the performance of all models degrade severely due to the distribution of classes along time, which supports our claim about the importance of analyzing this distribution prior to the design of the model.

show abstract

Prediction, Expectation, and Surprise: Methods, Designs, and Study of a Deployed Traffic Forecasting Service

Cited by 22 publications

References 4 publications

What Does The Crowd Say About You? Evaluating Aggregation-based Location Privacy

What Does The Crowd Say About You? Evaluating Aggregation-based Location Privacy

Deep learning for spatio‐temporal modeling: Dynamic traffic flows and high frequency trading

New Perspectives on the Use of Online Learning for Congestion Level Prediction over Traffic Data

Contact Info

Product

Resources

About