arXiv subjects

Bilal Farooq

Publications and source records attributed to Bilal Farooq.

90 records · Page 5Linked to original sources

arXiv2019

Perturbation Methods for Protection of Sensitive Location Data: Smartphone Travel Survey Case Study

Smartphone based travel data collection has become an important tool for the analysis of transportation systems. Interest in sharing travel survey data has gained popularity in recent years as "Open Data Initiatives" by governments seek to allow the public to use these data, and hopefully be able to contribute their findings and analysis to the public sphere. The public release of such precise information, particularly location data such as place of residence, opens the risk of privacy violation. At the same time, in order for such data to be useful, as much spatial resolution as possible is desirable for utility in transportation applications and travel demand modeling. This paper evaluates geographic random perturbation methods (i.e. Geo-indistinguishability and the Donut geomask) in protecting the privacy of respondents whose residential location may be published. We measure the performance of location privacy methods, preservation of utility and randomness in the distribution of perturbation distances with varying parameters. It is found that both methods produce distributions of spatial perturbations that conform closely to common probability distributions and as a result, that the original locations can be inferred with little information and a high degree of precision. It is also found that while Achieved K-estimate anonymity increases linearly with desired anonymity for the Donut geomask, Geo-Indistinguishability is highly dependent upon its privacy budget factor (epsilon) and is not very effective at assuring desired Achieved K-estimate anonymity.

cs.CR↗

arXiv2019

DeepWait: Pedestrian Wait Time Estimation in Mixed Traffic Conditions Using Deep Survival Analysis

Pedestrian's road crossing behaviour is one of the important aspects of urban dynamics that will be affected by the introduction of autonomous vehicles. In this study we introduce DeepSurvival, a novel framework for estimating pedestrian's waiting time at unsignalized mid-block crosswalks in mixed traffic conditions. We exploit the strengths of deep learning in capturing the nonlinearities in the data and develop a cox proportional hazard model with a deep neural network as the log-risk function. An embedded feature selection algorithm for reducing data dimensionality and enhancing the interpretability of the network is also developed. We test our framework on a dataset collected from 160 participants using an immersive virtual reality environment. Validation results showed that with a C-index of 0.64 our proposed framework outperformed the standard cox proportional hazard-based model with a C-index of 0.58.

cs.HC↗

arXiv2019

Information processing constraints in travel behaviour modelling: A generative learning approach

Travel decisions tend to exhibit sensitivity to uncertainty and information processing constraints. These behavioural conditions can be characterized by a generative learning process. We propose a data-driven generative model version of rational inattention theory to emulate these behavioural representations. We outline the methodology of the generative model and the associated learning process as well as provide an intuitive explanation of how this process captures the value of prior information in the choice utility specification. We demonstrate the effects of information heterogeneity on a travel choice, analyze the econometric interpretation, and explore the properties of our generative model. Our findings indicate a strong correlation with rational inattention behaviour theory, which suggest that individuals may ignore certain exogenous variables and rely on prior information for evaluating decisions under uncertainty. Finally, the principles demonstrated in this study can be formulated as a generalized entropy and utility based multinomial logit model.

econ.EM↗

arXiv2019

Multi-Objective Autonomous Braking System using Naturalistic Dataset

A deep reinforcement learning based multi-objective autonomous braking system is presented. The design of the system is formulated in a continuous action space and seeks to maximize both pedestrian safety and perception as well as passenger comfort. The vehicle agent is trained against a large naturalistic dataset containing pedestrian road-crossing trials in which respondents walked across a road under various traffic conditions within an interactive virtual reality environment. The policy for brake control is learned through computer simulation using two reinforcement learning methods i.e. Proximal Policy Optimization and Deep Deterministic Policy Gradient and the efficiency of each are compared. Results show that the system is able to reduce the negative influence on passenger comfort by half while maintaining safe braking operation.

cs.RO↗

arXiv2019

Ensemble Convolutional Neural Networks for Mode Inference in Smartphone Travel Survey

We develop ensemble Convolutional Neural Networks (CNNs) to classify the transportation mode of trip data collected as part of a large-scale smartphone travel survey in Montreal, Canada. Our proposed ensemble library is composed of a series of CNN models with different hyper-parameter values and CNN architectures. In our final model, we combine the output of CNN models using "average voting", "majority voting" and "optimal weights" methods. Furthermore, we exploit the ensemble library by deploying a Random Forest model as a meta-learner. The ensemble method with random forest as meta-learner shows an accuracy of 91.8% which surpasses the other three ensemble combination methods, as well as other comparable models reported in the literature. The "majority voting" and "optimal weights" combination methods result in prediction accuracy rates around 89%, while "average voting" is able to achieve an accuracy of only 85%.

cs.LG↗

arXiv2019

Analysis of distracted pedestrians' waiting time: Head-Mounted Immersive Virtual Reality application

This paper analyzes the distracted pedestrians' waiting time before crossing the road in three conditions: 1) not distracted, 2) distracted with a smartphone and 3) distracted with a smartphone in the presence of virtual flashing LED lights on the crosswalk as a safety measure. For the means of data collection, we adapted an in-house developed virtual immersive reality environment (VIRE). A total of 42 volunteers participated in the experiment. Participants' positions and head movements were recorded and used to calculate walking speeds, acceleration and deceleration rates, surrogate safety measures, time spent playing smartphone game, etc. After a descriptive analysis on the data, the effects of these variables on pedestrians' waiting time are analyzed by employing a cox proportional hazard model. Several factors were identified as having impact on waiting time. The results show that an increase in initial walk speed, percentage of time the head was oriented toward smartphone during crossing, bigger minimum missed gaps and unsafe crossings resulted in shorter waiting times. On the other hand, an increase in the percentage of time the head was oriented toward smartphone during waiting time, crossing time and maze solving time, means longer waiting times for participants.

cs.HC↗

arXiv2019

A semi-supervised deep residual network for mode detection in Wi-Fi signals

Due to their ubiquitous and pervasive nature, Wi-Fi networks have the potential to collect large-scale, low-cost, and disaggregate data on multimodal transportation. In this study, we develop a semi-supervised deep residual network (ResNet) framework to utilize Wi-Fi communications obtained from smartphones for the purpose of transportation mode detection. This framework is evaluated on data collected by Wi-Fi sensors located in a congested urban area in downtown Toronto. To tackle the intrinsic difficulties and costs associated with labelled data collection, we utilize ample amount of easily collected low-cost unlabelled data by implementing the semi-supervised part of the framework. By incorporating a ResNet architecture as the core of the framework, we take advantage of the high-level features not considered in the traditional machine learning frameworks. The proposed framework shows a promising performance on the collected data, with a prediction accuracy of 81.8% for walking, 82.5% for biking and 86.0% for the driving mode.

cs.LG↗

arXiv2019

Virtual Immersive Reality based Analysis of Behavioral Responses in Connected and Autonomous Vehicle Environment

Recently, we developed a dynamic distributed end-to-end vehicle routing system (E2ECAV) using a network of intelligent intersections and level 5 CAVs (Djavadian & Farooq, 2018). The case study of the downtown Toronto Network showed that E2ECAV has the ability to maximize throughput and reduce travel time up to 40%. However, the efficiency of these new technologies relies on the acceptance of users in adapting to them and their willingness to give control fully or partially to CAVs. In this study a stated preference laboratory experiment is designed employing Virtual Reality Immersive Environment (VIRE) driving simulator to evaluate the behavioral response of drivers to E2ECAV. The aim is to investigate under what conditions drivers are more willing to adapt. The results show that factors such as locus of control, congestion level and ability to multi-task have significant impact.

cs.HC↗

arXiv2018

A Perspective on the Challenges and Opportunities for Privacy-Aware Big Transportation Data

In recent years, and especially since the development of the smartphone, enormous amounts of data relevant for transportation have become available. These data hold out the potential to redefine how transportation system (i.e. design, planning and operations) is done. While researchers in both academia and industry are making advances in using this data to transportation system ends (e.g. information inference from collected data), little attention has been paid to four larger scale challenges that will need to be overcome if the potential for Big Transportation Data is to be harnessed for transportation decision-making purposes. This paper aims to provide awareness of these large-scale challenges and provides insight into how we believe these challenges are likely to be met.

cs.CY↗

arXiv2018

A blockchain framework for smart mobility

A blockchain framework is presented for addressing the privacy and security challenges associated with the Big Data in smart mobility. It is composed of individuals, companies, government and universities where all the participants collect, own, and control their data. Each participant shares their encrypted data to the blockchain network and can make information transactions with other participants as long as both party agrees to the transaction rules (smart contract) issued by the owner of the data. Data ownership, transparency, auditability and access control are the core principles of the proposed blockchain for smart mobility Big Data.

cs.CY↗

arXiv2018

Mobility Mode Detection Using WiFi Signals

We utilize Wi-Fi communications from smartphones to predict their mobility mode, i.e. walking, biking and driving. Wi-Fi sensors were deployed at four strategic locations in a closed loop on streets in downtown Toronto. Deep neural network (Multilayer Perceptron) along with three decision tree based classifiers (Decision Tree, Bagged Decision Tree and Random Forest) are developed. Results show that the best prediction accuracy is achieved by Multilayer Perceptron, with 86.52% correct predictions of mobility modes.

cs.LG↗

arXiv2018

Impact of Distributed Routing of Intelligent Vehicles on Urban Traffic

The impact of distributed dynamic routing with different market penetration rates (MPRs) of connected autonomous vehicles (CAVs) and congestion levels has been investigated on urban streets. Downtown Toronto network is studied in an agent-based traffic simulation. The higher the MPRs of CAVs--especially in the case of highly congested urban networks--the higher the average speed, the lower the mean travel time, and the higher the throughput.

physics.soc-ph↗

arXiv2018

Modelling Latent Travel Behaviour Characteristics with Generative Machine Learning

In this paper, we implement an information-theoretic approach to travel behaviour analysis by introducing a generative modelling framework to identify informative latent characteristics in travel decision making. It involves developing a joint tri-partite Bayesian graphical network model using a Restricted Boltzmann Machine (RBM) generative modelling framework. We apply this framework on a mode choice survey data to identify abstract latent variables and compare the performance with a traditional latent variable model with specific latent preferences -- safety, comfort, and environmental. Data collected from a joint stated and revealed preference mode choice survey in Quebec, Canada were used to calibrate the RBM model. Results show that a signficant impact on model likelihood statistics and suggests that machine learning tools are highly suitable for modelling complex networks of conditional independent behaviour interactions.

cs.LG↗

arXiv2018

Impact of Smartphone Distraction on Pedestrians' Crossing Behaviour: An Application of Head-Mounted Immersive Virtual Reality

A novel head-mounted virtual immersive/interactive reality environment (VIRE) is utilized to evaluate the behaviour of participants in three pedestrian road crossing conditions while 1) not distracted, 2) distracted with a smartphone, and 3) distracted with a smartphone with a virtually implemented safety measure on the road. Forty-two volunteers participated in our research who completed thirty successful (complete crossing) trials in blocks of ten trials for each crossing condition. For the two distracted conditions, pedestrians are engaged in a maze-solving game on a virtual smartphone, while at the same time checking the traffic for a safe crossing gap. For the proposed safety measure, smart flashing and color changing LED lights are simulated on the crosswalk to warn the distracted pedestrian who initiates crossing. Surrogate safety measures as well as speed information and distraction attributes such as direction and orientation of participant's head were collected and evaluated by employing a Multinomial Logit (MNL) model. Results from the model indicate that females have more dangerous crossing behaviour especially in distracted conditions; however, the smart LED treatment reduces this negative impact. Moreover, the number of times and the percentage of duration the head was facing the smartphone during a trial and a waiting time respectively increase the possibility of unsafe crossings; though, the proposed treatment reduces the safety crossing rate. Hence, our study shows that the smart LED light safety treatment indeed improves the safety of distracted pedestrians and enhances the successful crossing rate.

cs.HC↗

arXiv2018

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

Stated preference experiments have been known to suffer from the lack of realism. This issue is particularly visible when the scenario doesn't have a well understood prior reference e.g. in case of the autonomous vehicles related scenarios. We present Virtual Immersive Reality Environment (VIRE) that is capable of developing highly realistic, immersive, and interactive choice scenario. We demonstrate the use of VIRE in the pedestrian preferences related to autonomous vehicles and associated infrastructure changes on urban streets of Montréal. The results are compared with predominantly used approaches i.e. text-only and visual aid. We show that VIRE results in better understanding of the scenario and consistent results.

cs.HC↗

arXiv2017

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.

cs.LG↗

arXiv2017

An investigation into machine learning approaches for forecasting spatio-temporal demand in ride-hailing service

In this paper, we present machine learning approaches for characterizing and forecasting the short-term demand for on-demand ride-hailing services. We propose the spatio-temporal estimation of the demand that is a function of variable effects related to traffic, pricing and weather conditions. With respect to the methodology, a single decision tree, bootstrap-aggregated (bagged) decision trees, random forest, boosted decision trees, and artificial neural network for regression have been adapted and systematically compared using various statistics, e.g. R-square, Root Mean Square Error (RMSE), and slope. To better assess the quality of the models, they have been tested on a real case study using the data of DiDi Chuxing, the main on-demand ride hailing service provider in China. In the current study, 199,584 time-slots describing the spatio-temporal ride-hailing demand has been extracted with an aggregated-time interval of 10 mins. All the methods are trained and validated on the basis of two independent samples from this dataset. The results revealed that boosted decision trees provide the best prediction accuracy (RMSE=16.41), while avoiding the risk of over-fitting, followed by artificial neural network (20.09), random forest (23.50), bagged decision trees (24.29) and single decision tree (33.55).

cs.LG↗

arXiv2017

Integrated Microsimulation Framework for Dynamic Pedestrian Movement Estimation in Mobility Hub

We present an integrated microsimulation framework to estimate the pedestrian movement over time and space with limited data on directional counts. Using the activity-based approach, simulation can compute the overall demand and trajectory of each agent, which are in accordance with the available partial observations and are in response to the initial and evolving supply conditions and schedules. This simulation contains a chain of processes including: activities generation, decision point choices, and assignment. They are considered in an iteratively updating loop so that the simulation can dynamically correct its estimates of demand. A Markov chain is constructed for this loop. These considerations transform the problem into a convergence problem. A Metropolitan Hasting algorithm is then adapted to identify the optimal solution. This framework can be used to fill the lack of data or to model the reactions of demand to exogenous changes in the scenario. Finally, we present a case study on Montreal Central Station, on which we tested the developed framework and calibrated the models. We then applied it to a possible future scenario for the same station.

math.OC↗