arXiv subjects

Francisco C. Pereira

Publications and source records attributed to Francisco C. Pereira.

At least 37 records · Page 2Linked to original sources

arXiv2021

Combining Discrete Choice Models and Neural Networks through Embeddings: Formulation, Interpretability and Performance

This study proposes a novel approach that combines theory and data-driven choice models using Artificial Neural Networks (ANNs). In particular, we use continuous vector representations, called embeddings, for encoding categorical or discrete explanatory variables with a special focus on interpretability and model transparency. Although embedding representations within the logit framework have been conceptualized by Pereira (2019), their dimensions do not have an absolute definitive meaning, hence offering limited behavioral insights in this earlier work. The novelty of our work lies in enforcing interpretability to the embedding vectors by formally associating each of their dimensions to a choice alternative. Thus, our approach brings benefits much beyond a simple parsimonious representation improvement over dummy encoding, as it provides behaviorally meaningful outputs that can be used in travel demand analysis and policy decisions. Additionally, in contrast to previously suggested ANN-based Discrete Choice Models (DCMs) that either sacrifice interpretability for performance or are only partially interpretable, our models preserve interpretability of the utility coefficients for all the input variables despite being based on ANN principles. The proposed models were tested on two real world datasets and evaluated against benchmark and baseline models that use dummy-encoding. The results of the experiments indicate that our models deliver state-of-the-art predictive performance, outperforming existing ANN-based models while drastically reducing the number of required network parameters.

stat.ML↗

arXiv2021

Graph Neural Network Reinforcement Learning for Autonomous Mobility-on-Demand Systems

Autonomous mobility-on-demand (AMoD) systems represent a rapidly developing mode of transportation wherein travel requests are dynamically handled by a coordinated fleet of robotic, self-driving vehicles. Given a graph representation of the transportation network - one where, for example, nodes represent areas of the city, and edges the connectivity between them - we argue that the AMoD control problem is naturally cast as a node-wise decision-making problem. In this paper, we propose a deep reinforcement learning framework to control the rebalancing of AMoD systems through graph neural networks. Crucially, we demonstrate that graph neural networks enable reinforcement learning agents to recover behavior policies that are significantly more transferable, generalizable, and scalable than policies learned through other approaches. Empirically, we show how the learned policies exhibit promising zero-shot transfer capabilities when faced with critical portability tasks such as inter-city generalization, service area expansion, and adaptation to potentially complex urban topologies.

eess.SY↗

arXiv2021

Deep Spatio-Temporal Forecasting of Electrical Vehicle Charging Demand

Electric vehicles can offer a low carbon emission solution to reverse rising emission trends. However, this requires that the energy used to meet the demand is green. To meet this requirement, accurate forecasting of the charging demand is vital. Short and long-term charging demand forecasting will allow for better optimisation of the power grid and future infrastructure expansions. In this paper, we propose to use publicly available data to forecast the electric vehicle charging demand. To model the complex spatial-temporal correlations between charging stations, we argue that Temporal Graph Convolution Models are the most suitable to capture the correlations. The proposed Temporal Graph Convolutional Networks provide the most accurate forecasts for short and long-term forecasting compared with other forecasting methods.

cs.LG↗

arXiv2021

Improving the Accuracy and Efficiency of Online Calibration for Simulation-based Dynamic Traffic Assignment

Simulation-based Dynamic Traffic Assignment models have important applications in real-time traffic management and control. The efficacy of these systems rests on the ability to generate accurate estimates and predictions of traffic states, which necessitates online calibration. A widely used solution approach for online calibration is the Extended Kalman Filter (EKF), which -- although appealing in its flexibility to incorporate any class of parameters and measurements -- poses several challenges with regard to calibration accuracy and scalability, especially in congested situations for large-scale networks. This paper addresses these issues in turn so as to improve the accuracy and efficiency of EKF-based online calibration approaches for large and congested networks. First, the concept of state augmentation is revisited to handle violations of the Markovian assumption typically implicit in online applications of the EKF. Second, a method based on graph-coloring is proposed to operationalize the partitioned finite-difference approach that enhances scalability of the gradient computations. Several synthetic experiments and a real world case study demonstrate that application of the proposed approaches yields improvements in terms of both prediction accuracy and computational performance. The work has applications in real-world deployments of simulation-based dynamic traffic assignment systems.

eess.SY↗

arXiv2021

Estimating Causal Effects with the Neural Autoregressive Density Estimator

Estimation of causal effects is fundamental in situations were the underlying system will be subject to active interventions. Part of building a causal inference engine is defining how variables relate to each other, that is, defining the functional relationship between variables given conditional dependencies. In this paper, we deviate from the common assumption of linear relationships in causal models by making use of neural autoregressive density estimators and use them to estimate causal effects within the Pearl's do-calculus framework. Using synthetic data, we show that the approach can retrieve causal effects from non-linear systems without explicitly modeling the interactions between the variables.

stat.ME↗

arXiv2020

Population synthesis for urban resident modeling using deep generative models

The impacts of new real estate developments are strongly associated to its population distribution (types and compositions of households, incomes, social demographics) conditioned on aspects such as dwelling typology, price, location, and floor level. This paper presents a Machine Learning based method to model the population distribution of upcoming developments of new buildings within larger neighborhood/condo settings. We use a real data set from Ecopark Township, a real estate development project in Hanoi, Vietnam, where we study two machine learning algorithms from the deep generative models literature to create a population of synthetic agents: Conditional Variational Auto-Encoder (CVAE) and Conditional Generative Adversarial Networks (CGAN). A large experimental study was performed, showing that the CVAE outperforms both the empirical distribution, a non-trivial baseline model, and the CGAN in estimating the population distribution of new real estate development projects.

cs.LG↗

arXiv2020

QTIP: Quick simulation-based adaptation of Traffic model per Incident Parameters

Current data-driven traffic prediction models are usually trained with large datasets, e.g. several months of speeds and flows. Such models provide very good fit for ordinary road conditions, but often fail just when they are most needed: when traffic suffers a sudden and significant disruption, such as a road incident. In this work, we describe QTIP: a simulation-based framework for quasi-instantaneous adaptation of prediction models upon traffic disruption. In a nutshell, QTIP performs real-time simulations of the affected road for multiple scenarios, analyzes the results, and suggests a change to an ordinary prediction model accordingly. QTIP constructs the simulated scenarios per properties of the incident, as conveyed by immediate distress signals from affected vehicles. Such real-time signals are provided by In-Vehicle Monitor Systems, which are becoming increasingly prevalent world-wide. We experiment QTIP in a case study of a Danish motorway, and the results show that QTIP can improve traffic prediction in the first critical minutes of road incidents.

stat.ML↗

arXiv2020

Estimating Latent Demand of Shared Mobility through Censored Gaussian Processes

Transport demand is highly dependent on supply, especially for shared transport services where availability is often limited. As observed demand cannot be higher than available supply, historical transport data typically represents a biased, or censored, version of the true underlying demand pattern. Without explicitly accounting for this inherent distinction, predictive models of demand would necessarily represent a biased version of true demand, thus less effectively predicting the needs of service users. To counter this problem, we propose a general method for censorship-aware demand modeling, for which we devise a censored likelihood function. We apply this method to the task of shared mobility demand prediction by incorporating the censored likelihood within a Gaussian Process model, which can flexibly approximate arbitrary functional forms. Experiments on artificial and real-world datasets show how taking into account the limiting effect of supply on demand is essential in the process of obtaining an unbiased predictive model of user demand behavior.

stat.ML↗

arXiv2020

Mining User Behaviour from Smartphone data: a literature review

To study users' travel behaviour and travel time between origin and destination, researchers employ travel surveys. Although there is consensus in the field about the potential, after over ten years of research and field experimentation, Smartphone-based travel surveys still did not take off to a large scale. Here, computer intelligence algorithms take the role that operators have in Traditional Travel Surveys; since we train each algorithm on data, performances rest on the data quality, thus on the ground truth. Inaccurate validations affect negatively: labels, algorithms' training, travel diaries precision, and therefore data validation, within a very critical loop. Interestingly, boundaries are proven burdensome to push even for Machine Learning methods. To support optimal investment decisions for practitioners, we expose the drivers they should consider when assessing what they need against what they get. This paper highlights and examines the critical aspects of the underlying research and provides some recommendations: (i) from the device perspective, on the main physical limitations; (ii) from the application perspective, the methodological framework deployed for the automatic generation of travel diaries; (iii)from the ground truth perspective, the relationship between user interaction, methods, and data.

cs.LG↗

arXiv2020

Uncovering life-course patterns with causal discovery and survival analysis

We provide a novel approach and an exploratory study for modelling life event choices and occurrence from a probabilistic perspective through causal discovery and survival analysis. Our approach is formulated as a bi-level problem. In the upper level, we build the life events graph, using causal discovery tools. In the lower level, for the pairs of life events, time-to-event modelling through survival analysis is applied to model time-dependent transition probabilities. Several life events were analysed, such as getting married, buying a new car, child birth, home relocation and divorce, together with the socio-demographic attributes for survival modelling, some of which are age, nationality, number of children, number of cars and home ownership. The data originates from a survey conducted in Dortmund, Germany, with the questionnaire containing a series of retrospective questions about residential and employment biography, travel behaviour and holiday trips, as well as socio-economic characteristic. Although survival analysis has been used in the past to analyse life-course data, this is the first time that a bi-level model has been formulated. The inclusion of a causal discovery algorithm in the upper-level allows us to first identify causal relationships between life-course events and then understand the factors that might influence transition rates between events. This is very different from more classic choice models where causal relationships are subject to expert interpretations based on model results.

stat.AP↗

arXiv2019

Prediction of rare feature combinations in population synthesis: Application of deep generative modelling

In population synthesis applications, when considering populations with many attributes, a fundamental problem is the estimation of rare combinations of feature attributes. Unsurprisingly, it is notably more difficult to reliably representthe sparser regions of such multivariate distributions and in particular combinations of attributes which are absent from the original sample. In the literature this is commonly known as sampling zeros for which no systematic solution has been proposed so far. In this paper, two machine learning algorithms, from the family of deep generative models,are proposed for the problem of population synthesis and with particular attention to the problem of sampling zeros. Specifically, we introduce the Wasserstein Generative Adversarial Network (WGAN) and the Variational Autoencoder(VAE), and adapt these algorithms for a large-scale population synthesis application. The models are implemented on a Danish travel survey with a feature-space of more than 60 variables. The models are validated in a cross-validation scheme and a set of new metrics for the evaluation of the sampling-zero problem is proposed. Results show how these models are able to recover sampling zeros while keeping the estimation of truly impossible combinations, the structural zeros, at a comparatively low level. Particularly, for a low dimensional experiment, the VAE, the marginal sampler and the fully random sampler generate 5%, 21% and 26%, respectively, more structural zeros per sampling zero generated by the WGAN, while for a high dimensional case, these figures escalate to 44%, 2217% and 170440%, respectively. This research directly supports the development of agent-based systems and in particular cases where detailed socio-economic or geographical representations are required.

stat.ML↗

arXiv2019

Rethinking travel behavior modeling representations through embeddings

This paper introduces the concept of travel behavior embeddings, a method for re-representing discrete variables that are typically used in travel demand modeling, such as mode, trip purpose, education level, family type or occupation. This re-representation process essentially maps those variables into a latent space called the \emph{embedding space}. The benefit of this is that such spaces allow for richer nuances than the typical transformations used in categorical variables (e.g. dummy encoding, contrasted encoding, principal components analysis). While the usage of latent variable representations is not new per se in travel demand modeling, the idea presented here brings several innovations: it is an entirely data driven algorithm; it is informative and consistent, since the latent space can be visualized and interpreted based on distances between different categories; it preserves interpretability of coefficients, despite being based on Neural Network principles; and it is transferrable, in that embeddings learned from one dataset can be reused for other ones, as long as travel behavior keeps consistent between the datasets. The idea is strongly inspired on natural language processing techniques, namely the word2vec algorithm. Such algorithm is behind recent developments such as in automatic translation or next word prediction. Our method is demonstrated using a model choice model, and shows improvements of up to 60\% with respect to initial likelihood, and up to 20% with respect to likelihood of the corresponding traditional model (i.e. using dummy variables) in out-of-sample evaluation. We provide a new Python package, called PyTre (PYthon TRavel Embeddings), that others can straightforwardly use to replicate our results or improve their own models. Our experiments are themselves based on an open dataset (swissmetro).

econ.EM↗

arXiv2019

Multi-Output Gaussian Processes for Crowdsourced Traffic Data Imputation

Traffic speed data imputation is a fundamental challenge for data-driven transport analysis. In recent years, with the ubiquity of GPS-enabled devices and the widespread use of crowdsourcing alternatives for the collection of traffic data, transportation professionals increasingly look to such user-generated data for many analysis, planning, and decision support applications. However, due to the mechanics of the data collection process, crowdsourced traffic data such as probe-vehicle data is highly prone to missing observations, making accurate imputation crucial for the success of any application that makes use of that type of data. In this article, we propose the use of multi-output Gaussian processes (GPs) to model the complex spatial and temporal patterns in crowdsourced traffic data. While the Bayesian nonparametric formalism of GPs allows us to model observation uncertainty, the multi-output extension based on convolution processes effectively enables us to capture complex spatial dependencies between nearby road segments. Using 6 months of crowdsourced traffic speed data or "probe vehicle data" for several locations in Copenhagen, the proposed approach is empirically shown to significantly outperform popular state-of-the-art imputation methods.

stat.ML↗

arXiv2019

Online Predictive Optimization Framework for Stochastic Demand-Responsive Transit Services

This study develops an online predictive optimization framework for dynamically operating a transit service in an area of crowd movements. The proposed framework integrates demand prediction and supply optimization to periodically redesign the service routes based on recently observed demand. To predict demand for the service, we use Quantile Regression to estimate the marginal distribution of movement counts between each pair of serviced locations. The framework then combines these marginals into a joint demand distribution by constructing a Gaussian copula, which captures the structure of correlation between the marginals. For supply optimization, we devise a linear programming model, which simultaneously determines the route structure and the service frequency according to the predicted demand. Importantly, our framework both preserves the uncertainty structure of future demand and leverages this for robust route optimization, while keeping both components decoupled. We evaluate our framework using a real-world case study of autonomous mobility in a university campus in Denmark. The results show that our framework often obtains the ground truth optimal solution, and can outperform conventional methods for route optimization, which do not leverage full predictive distributions.

stat.ML↗

arXiv2019

Scalable Population Synthesis with Deep Generative Modeling

Population synthesis is concerned with the generation of synthetic yet realistic representations of populations. It is a fundamental problem in the modeling of transport where the synthetic populations of micro-agents represent a key input to most agent-based models. In this paper, a new methodological framework for how to 'grow' pools of micro-agents is presented. The model framework adopts a deep generative modeling approach from machine learning based on a Variational Autoencoder (VAE). Compared to the previous population synthesis approaches, including Iterative Proportional Fitting (IPF), Gibbs sampling and traditional generative models such as Bayesian Networks or Hidden Markov Models, the proposed method allows fitting the full joint distribution for high dimensions. The proposed methodology is compared with a conventional Gibbs sampler and a Bayesian Network by using a large-scale Danish trip diary. It is shown that, while these two methods outperform the VAE in the low-dimensional case, they both suffer from scalability issues when the number of modeled attributes increases. It is also shown that the Gibbs sampler essentially replicates the agents from the original sample when the required conditional distributions are estimated as frequency tables. In contrast, the VAE allows addressing the problem of sampling zeros by generating agents that are virtually different from those in the original data but have similar statistical properties. The presented approach can support agent-based modeling at all levels by enabling richer synthetic populations with smaller zones and more detailed individual characteristics.

stat.ML↗

arXiv2018

Heteroscedastic Gaussian processes for uncertainty modeling in large-scale crowdsourced traffic data

Accurately modeling traffic speeds is a fundamental part of efficient intelligent transportation systems. Nowadays, with the widespread deployment of GPS-enabled devices, it has become possible to crowdsource the collection of speed information to road users (e.g. through mobile applications or dedicated in-vehicle devices). Despite its rather wide spatial coverage, crowdsourced speed data also brings very important challenges, such as the highly variable measurement noise in the data due to a variety of driving behaviors and sample sizes. When not properly accounted for, this noise can severely compromise any application that relies on accurate traffic data. In this article, we propose the use of heteroscedastic Gaussian processes (HGP) to model the time-varying uncertainty in large-scale crowdsourced traffic data. Furthermore, we develop a HGP conditioned on sample size and traffic regime (SRC-HGP), which makes use of sample size information (probe vehicles per minute) as well as previous observed speeds, in order to more accurately model the uncertainty in observed speeds. Using 6 months of crowdsourced traffic data from Copenhagen, we empirically show that the proposed heteroscedastic models produce significantly better predictive distributions when compared to current state-of-the-art methods for both speed imputation and short-term forecasting tasks.

stat.ML↗

arXiv2018

A Bayesian Additive Model for Understanding Public Transport Usage in Special Events

Public special events, like sports games, concerts and festivals are well known to create disruptions in transportation systems, often catching the operators by surprise. Although these are usually planned well in advance, their impact is difficult to predict, even when organisers and transportation operators coordinate. The problem highly increases when several events happen concurrently. To solve these problems, costly processes, heavily reliant on manual search and personal experience, are usual practice in large cities like Singapore, London or Tokyo. This paper presents a Bayesian additive model with Gaussian process components that combines smart card records from public transport with context information about events that is continuously mined from the Web. We develop an efficient approximate inference algorithm using expectation propagation, which allows us to predict the total number of public transportation trips to the special event areas, thereby contributing to a more adaptive transportation system. Furthermore, for multiple concurrent event scenarios, the proposed algorithm is able to disaggregate gross trip counts into their most likely components related to specific events and routine behavior. Using real data from Singapore, we show that the presented model outperforms the best baseline model by up to 26% in R2 and also has explanatory power for its individual components.

stat.ML↗

arXiv2018

Beyond expectation: Deep joint mean and quantile regression for spatio-temporal problems

Spatio-temporal problems are ubiquitous and of vital importance in many research fields. Despite the potential already demonstrated by deep learning methods in modeling spatio-temporal data, typical approaches tend to focus solely on conditional expectations of the output variables being modeled. In this paper, we propose a multi-output multi-quantile deep learning approach for jointly modeling several conditional quantiles together with the conditional expectation as a way to provide a more complete "picture" of the predictive density in spatio-temporal problems. Using two large-scale datasets from the transportation domain, we empirically demonstrate that, by approaching the quantile regression problem from a multi-task learning perspective, it is possible to solve the embarrassing quantile crossings problem, while simultaneously significantly outperforming state-of-the-art quantile regression methods. Moreover, we show that jointly modeling the mean and several conditional quantiles not only provides a rich description about the predictive density that can capture heteroscedastic properties at a neglectable computational overhead, but also leads to improved predictions of the conditional expectation due to the extra information and a regularization effect induced by the added quantiles.

stat.ML↗