Bilal Farooq

Distributed Classification of Urban Congestion Using VANET

Vehicular ad hoc networks (VANETs) can efficiently detect traffic congestion, but detection is not enough, because congestion can be further classified as recurrent and non-recurrent congestion (NRC). In particular, NRC in an urban network is mainly caused by incidents, work zones, special events, and adverse weather. We propose a framework for the real-time distributed classification of congestion into its components on a heterogeneous urban road network using VANET. We present models built on an understanding of the spatial and temporal causality measures and trained on synthetic data extended from a real case study of Cologne. Our performance evaluation shows a predictive accuracy of 87.63% for the deterministic classification tree, 88.83% for the nave Bayesian classifier, 89.51% for random forest, and 89.17% for the boosting technique. This framework can assist transportation agencies in reducing urban congestion by developing effective congestion mitigation strategies knowing the root causes of congestion.Vehicular Ad-hoc NETworks (VANET) can efficiently detect traffic congestion, but detection is not enough because congestion can be further classified as recurrent and non-recurrent congestion (NRC). In particular, NRC in an urban network is mainly caused by incidents, workzones, special events and adverse weather. We propose a framework for the real-time distributed classification of congestion into its components on a heterogeneous urban road network using VANET. We present models built on an understanding of the spatial and temporal causality measures and trained on synthetic data extended from a real case study of Cologne. Our performance evaluation shows a predictive accuracy of 87.63\% for the deterministic Classification Tree (CT), 88.83\% for the Naive Bayesian classifier (NB), 89.51\% for Random Forest (RF) and 89.17\% for the boosting technique. This framework can assist transportation agencies in reducing urban congestion by developing effective congestion mitigation strategies knowing the root causes of congestion.

Associations Generation in Synthetic Population for Transportation Applications: Graph-Theoretic Solution

The generation of synthetic populations through simulation methods is an important research topic and has a key application in agent-based modeling of transport and land use. The next step in this research area is the generation of complete synthetic households; this research area requires some way to associate synthetic persons with household positions. This work formulated the person to the position matching problem as a bipartite graph matching and tested two models for determining match utility with data from the 2000 Swiss census. The functions tested were both multinomial logit models, one based on the household size attribute and the other on household type. Synthetic persons were matched into the head position of real households, and then the remaining population was used to run a second match with a separately calibrated version of the size choice model for the spouse position. This method is a long list-based approach that keeps the original marginal consistent. Results show that the size choice model returns the best results for head and spouse positions, although both models provide a good match quality as measured by the distributions of individual attributes in real and matched populations as well as the distributions of unique attribute combinations. Possible extensions include matching to other household positions and evaluating the performance of these synthetic households in modeling applications.

Ubiquitous monitoring of pedestrian dynamics: Exploring wireless ad hoc network of multi-sensor technologies

In this paper we incorporate various automatic sensor technologies in Ad Hoc network to monitor pedestrian activities at the entire facility level. A case study is demonstrated during a large street festival in Montréal covering more than ten street blocks. We used WiFi technology, computer vision tools, and infrared counters to develop the detailed estimates on attendance, movement, and activity patterns of pedestrians over time and space, which can be used for future planning, operations, and financing.

Virtual Immersive Reality for Stated Preference Travel Behaviour Experiments: A Case study of Autonomous Vehicles on Urban Roads

Stated preference experiments have been criticized for lack of realism. This issue is particularly visible when the scenario does not have a well understood prior reference, as in the case of research into demand for autonomous vehicles. The paper presents Virtual Immersive Reality Environment (VIRE), which is capable of developing highly realistic, immersive, and interactive choice scenarios. We demonstrate the use of VIRE in researching pedestrian preferences related to autonomous vehicles and associated infrastructure changes on urban streets in Montréal, Canada. The results are compared with predominantly used approaches: text-only and visual aid. We show that VIRE results in respondents having better understanding of the scenario and it yields more consistent results.

Multidimensional Indicator Analysis for Transport Policy Evaluation

The need for forecasting the direct and indirect effects of land use and transport policies on society, the environment, and the local economy has led to the development of integrated land use and transport (LUTI) models. The land use and transport policy evaluation is based on point estimators of economic sustainability indicators, usually computed at an aggregate level (e.g., social welfare) despite the fact that the models and simulation are based on the individual. A methodology based on the strength of microsimulation in three dimensions (space, time, and agents) is presented. By multiple simulation runs of the LUTI model UrbanSim, the distributions of inequality and accessibility indicators in space and time were generated, and their variance was measured. The methodology was first applied in a base case scenario (in which the then current trend existed) of the Limmattal region including Zurich, Switzerland, and then on a public transport investment scenario. The results of the two scenarios were then compared on the basis of actual distributions rather than the mean point values of the indicators. The proposed methodology differed from the point-based policy evaluation frameworks in terms of details and insightfulness that could better support the process of informed decision making.

An efficient hierarchical model for multi-source information fusion

Abstract In urban and transportation research, important information is often scattered over a wide variety of independent datasets which vary in terms of described variables and sampling rates. As activity-travel behavior of people depends particularly on socio-demographics and transport/urban-related variables, there is an increasing need for advanced methods to merge information provided by multiple urban/transport household surveys. In this paper, we propose a hierarchical algorithm based on a Hidden Markov Model (HMM) and an Iterative Proportional Fitting (IPF) procedure to obtain quasi-perfect marginal distributions and accurate multi-variate joint distributions. The model allows for the combination of an unlimited number of datasets. The model is validated on the basis of a synthetic dataset with 1,000,000 observations and 8 categorical variables. The results reveal that the hierarchical model is particularly robust as the deviation between the simulated and observed multivariate joint distributions is extremely small and constant, regardless of the sampling rates and the composition of the datasets in terms of variables included in those datasets. Besides, the presented methodological framework allows for an intelligent merging of multiple data sources. Furthermore, heterogeneity is smoothly incorporated into micro-samples with small sampling rates subjected to potential sampling bias. These aspects are handled simultaneously to build a generalized probabilistic structure from which new observations can be inferred. A major impact in term of expert systems is that the outputs of the hierarchical model (HM) model serve as a basis for a qualitative and quantitative analyses of integrated datasets.

Discriminative conditional restricted Boltzmann machine for discrete choice and latent variable modelling

Conventional methods of estimating latent behaviour generally use attitudinal questions which are subjective and these survey questions may not always be available. We hypothesize that an alternative approach can be used for latent variable estimation through an undirected graphical models. For instance, non-parametric artificial neural networks. In this study, we explore the use of generative non-parametric modelling methods to estimate latent variables from prior choice distribution without the conventional use of measurement indicators. A restricted Boltzmann machine is used to represent latent behaviour factors by analyzing the relationship information between the observed choices and explanatory variables. The algorithm is adapted for latent behaviour analysis in discrete choice scenario and we use a graphical approach to evaluate and understand the semantic meaning from estimated parameter vector values. We illustrate our methodology on a financial instrument choice dataset and perform statistical analysis on parameter sensitivity and stability. Our findings show that through non-parametric statistical tests, we can extract useful latent information on the behaviour of latent constructs through machine learning methods and present strong and significant influence on the choice process. Furthermore, our modelling framework shows robustness in input variability through sampling and validation.