arXiv subjects

Bilal Farooq

Publications and source records attributed to Bilal Farooq.

At least 73 records · Page 4Linked to original sources

arXiv2021

Demand for shared mobility to complement public transportation: Human driven and autonomous vehicles

Recent advances in communication technologies and automated vehicles have opened doors for alternative mobility systems (taxis, carpool, demand-responsive services, peer-to-peer ridesharing, and car sharing, shared autonomous vehicles/shuttles). These new mobility services have gathered interest from researchers, public and private sectors as potential solutions to address last-mile problem--especially in low density areas where implementation of high frequency buses is not feasible. In this study we investigate the effects of ride-sharing service on travel demand and welfare, as it complements public transportation under different scenarios. Two types of management and vehicle types are considered: crowdsourced human driven vehicles (HDV) (e.g. Uber, Lyft) and centrally operated shared autonomous vehicles (SAV). The influence of fare discount on demand and mode shift is also investigated. A case study of Oakville road network in Ontario, Canada is conducted using real data. The results reveal that ride-sharing having the potential of increasing ridership by 76 per cent and decreasing wait time by 47 per cent under centrally operated shared autonomous vehicles with 50 per cent fare discount for sharing.

eess.SY↗

arXiv2021

Demand for shared mobility to replace private mobility using connected and automated vehicles

We examine how introduction of Shared Connected and Automated vehicles (SCAVs) as a new mobility mode could affect travel demand, welfare, as well as traffic congestion in the network. To do so, we adapt an agent-based day-to-day adjustment process and develop a central dispatching system, which is implemented on an in-house traffic microsimulator. We consider a two-sided market in which demand and SCAV fleet size change endogenously. For dispatching SCAV fleet size, we take changing traffic conditions into account. There are two available transport modes: private Connected Automated Vehicles (CAVs) and SCAVs. The designed system is applied on downtown Toronto network using real data. The results show that demand of SCAVs goes up by 43 per cent over seven study days from 670 trips on the first day to 959 trips on the seventh day. Whereas, there is a 10 per cent reduction in private CAV demand from 2807 trips to 2518 trips during the same duration. Moreover, total travel time of the network goes down by seven per cent indicating that traffic congestion was reduced in the network.

eess.SY↗

arXiv2021

ResLogit: A residual neural network logit model for data-driven choice modelling

This paper presents a novel deep learning-based travel behaviour choice model.Our proposed Residual Logit (ResLogit) model formulation seamlessly integrates a Deep Neural Network (DNN) architecture into a multinomial logit model. Recently, DNN models such as the Multi-layer Perceptron (MLP) and the Recurrent Neural Network (RNN) have shown remarkable success in modelling complex and noisy behavioural data. However, econometric studies have argued that machine learning techniques are a `black-box' and difficult to interpret for use in the choice analysis.We develop a data-driven choice model that extends the systematic utility function to incorporate non-linear cross-effects using a series of residual layers and using skipped connections to handle model identifiability in estimating a large number of parameters.The model structure accounts for cross-effects and choice heterogeneity arising from substitution, interactions with non-chosen alternatives and other effects in a non-linear manner.We describe the formulation, model estimation, interpretability and examine the relative performance and econometric implications of our proposed model.We present an illustrative example of the model on a classic red/blue bus choice scenario example. For a real-world application, we use a travel mode choice dataset to analyze the model characteristics compared to traditional neural networks and Logit formulations.Our findings show that our ResLogit approach significantly outperforms MLP models while providing similar interpretability as a Multinomial Logit model.

econ.EM↗

arXiv2021

Decoding pedestrian and automated vehicle interactions using immersive virtual reality and interpretable deep learning

To ensure pedestrian friendly streets in the era of automated vehicles, reassessment of current policies, practices, design, rules and regulations of urban areas is of importance. This study investigates pedestrian crossing behaviour, as an important element of urban dynamics that is expected to be affected by the presence of automated vehicles. For this purpose, an interpretable machine learning framework is proposed to explore factors affecting pedestrians' wait time before crossing mid-block crosswalks in the presence of automated vehicles. To collect rich behavioural data, we developed a dynamic and immersive virtual reality experiment, with 180 participants from a heterogeneous population in 4 different locations in the Greater Toronto Area (GTA). Pedestrian wait time behaviour is then analyzed using a data-driven Cox Proportional Hazards (CPH) model, in which the linear combination of the covariates is replaced by a flexible non-linear deep neural network. The proposed model achieved a 5% improvement in goodness of fit, but more importantly, enabled us to incorporate a richer set of covariates. A game theoretic based interpretability method is used to understand the contribution of different covariates to the time pedestrians wait before crossing. Results show that the presence of automated vehicles on roads, wider lane widths, high density on roads, limited sight distance, and lack of walking habits are the main contributing factors to longer wait times. Our study suggested that, to move towards pedestrian-friendly urban areas, national level educational programs for children, enhanced safety measures for seniors, promotion of active modes of transportation, and revised traffic rules and regulations should be considered.

cs.HC↗

arXiv2020

A Differentially Private Multi-Output Deep Generative Networks Approach For Activity Diary Synthesis

In this work, we develop a privacy-by-design generative model for synthesizing the activity diary of the travel population using state-of-art deep learning approaches. This proposed approach extends literature on population synthesis by contributing novel deep learning to the development and application of synthetic travel data while guaranteeing privacy protection for members of the sample population on which the synthetic populations are based. First, we show a complete de-generalization of activity diaries to simulate the socioeconomic features and longitudinal sequences of geographically and temporally explicit activities. Second, we introduce a differential privacy approach to control the level of resolution disclosing the uniqueness of survey participants. Finally, we experiment using the Generative Adversarial Networks (GANs). We evaluate the statistical distributions, pairwise correlations and measure the level of privacy guaranteed on simulated datasets for varying noise. The results of the model show successes in simulating activity diaries composed of multiple outputs including structured socio-economic features and sequential tour activities in a differentially private manner.

cs.LG↗

arXiv2020

Deep Learning Based Proactive Multi-Objective Eco-Routing Strategies for Connected and Automated Vehicles

This study exploits the advancements in information and communication technology (ICT), connected and automated vehicles (CAVs), and sensing, to develop proactive multi-objective eco-routing strategies. For a robust application, several GHG costing approaches are examined. The predictive models for the link level traffic and emission states are developed using long short term memory deep network with exogenous predictors. It is found that proactive routing strategies outperformed the myopic strategies, regardless of the routing objective. Whether myopic or proactive, the multi-objective routing, with travel time and GHG minimization as objectives, outperformed the single objective routing strategies, causing a reduction in the average travel time (TT), average vehicle kilometre travelled (VKT), total GHG and total NOx by 17%, 21%, 18%, and 20%, respectively. Finally, the additional TT and VKT experienced by the vehicles in the network contributed adversely to the amount of GHG and NOx produced in the network.

math.OC↗

arXiv2020

Smart Mobility Ontology: Current Trends and Future Directions

Ontology is the explicit and formal representation of the concepts in a domain and relations among them. Transportation science is a wide domain dealing with mobility over various complex and interconnected transportation systems, such as land, aviation, and maritime transport, and can take considerable advantage from ontology development. While several studies can be found in the recent literature, there exists a large potential to improve and develop a comprehensive smart mobility ontology. The current chapter aims to present different aspects of ontology development in general, such as ontology development methods, languages, tools, and software. Subsequently, it presents the currently available mobility-related ontologies developed across different domains, such as transportation, smart cities, goods mobility, sensors. Current gaps in the available ontologies are identified, and future directions regarding ontology development are proposed that can incorporate the forthcoming autonomous and connected vehicles, mobility as a service (MaaS), and other disruptive transportation technologies and services.

cs.AI↗

arXiv2020

Greenhouse Gas Emission Prediction on Road Network using Deep Sequence Learning

Mitigating the substantial undesirable impact of transportation systems on the environment is paramount. Thus, predicting Greenhouse Gas (GHG) emissions is one of the profound topics, especially with the emergence of intelligent transportation systems (ITS). We develop a deep learning framework to predict link-level GHG emission rate (ER) (in CO2eq gram/second) based on the most representative predictors, such as speed, density, and the GHG ER of previous time steps. In particular, various specifications of the long-short term memory (LSTM) networks with exogenous variables are examined and compared with clustering and the autoregressive integrated moving average (ARIMA) model with exogenous variables. The downtown Toronto road network is used as the case study and highly detailed data are synthesized using a calibrated traffic microsimulation and MOVES. It is found that LSTM specification with speed, density, GHG ER, and in-links speed from three previous minutes performs the best while adopting 2 hidden layers and when the hyper-parameters are systematically tuned. Adopting a 30 second updating interval improves slightly the correlation between true and predicted GHG ERs, but contributes negatively to the prediction accuracy as reflected on the increased root mean square error (RMSE) value. Efficiently predicting GHG emissions at a higher frequency with lower data requirements will pave the way to non-myopic eco-routing on large-scale road networks {to alleviate the adverse impact on the global warming

eess.SP↗

arXiv2020

Prediction of Traffic Flow via Connected Vehicles

We propose a Short-term Traffic flow Prediction (STP) framework so that transportation authorities take early actions to control flow and prevent congestion. We anticipate flow at future time frames on a target road segment based on historical flow data and innovative features such as real time feeds and trajectory data provided by Connected Vehicles (CV) technology. To cope with the fact that existing approaches do not adapt to variation in traffic, we show how this novel approach allows advanced modelling by integrating into the forecasting of flow, the impact of the various events that CV realistically encountered on segments along their trajectory. We solve the STP problem with a Deep Neural Networks (DNN) in a multitask learning setting augmented by input from CV. Results show that our approach, namely MTL-CV, with an average Root-Mean-Square Error (RMSE) of 0.052, outperforms state-of-the-art ARIMA time series (RMSE of 0.255) and baseline classifiers (RMSE of 0.122). Compared to single task learning with Artificial Neural Network (ANN), ANN had a lower performance, 0.113 for RMSE, than MTL-CV. MTL-CV learned historical similarities between segments, in contrast to using direct historical trends in the measure, because trends may not exist in the measure but do in the similarities.

cs.NI↗

arXiv2020

Actor-based Risk Analysis for Blockchains in Smart Mobility

Blockchain technology is a crypto-based secure ledger for data storage and transfer through decentralized, trustless peer-to-peer systems. Despite its advantages, previous studies have shown that the technology is not completely secure against cyber attacks. Thus, it is crucial to perform domain specific risk analysis to measure how viable the attacks are on the system, their impact and consequently the risk exposure. Specifically, in this paper, we carry out an analysis in terms of quantifying the risk associated to an operational multi-layered Blockchain framework for Smart Mobility Data-markets (BSMD). We conduct an actor-based analysis to determine the impact of the attacks. The analysis identified five attack goals and five types of attackers that violate the security of the blockchain system. In the case study of the public permissioned BSMD, we highlight the highest risk factors according to their impact on the victims in terms of monetary, privacy, integrity and trust. Four attack goals represent a risk in terms of economic losses and one attack goal contains many threats that represent a risk that is either unacceptable or undesirable.

cs.CR↗

arXiv2020

Multimodal Autonomous Last Mile Delivery System Design and Application

With the rapid increase in congestion, alternative solutions are needed to efficiently use the capacity of our existing networks. This paper focuses on exploring the emerging autonomous technologies for on-demand food delivery in congested urban cities. Three different last mile food delivery systems are proposed in this study employing aerial and ground autonomous vehicles technologies. The three proposed systems are: robot delivery system, drone delivery system and a hybrid delivery system. In the hybrid system the concept of hub-and-spoke network is explored in order to consolidate orders and reach more destinations in less time. To investigate the performance of the three proposed delivery systems, they are applied to the city of Mississauga network, in an in-house agent-based simulation in MATLAB. 18 Scenarios are tested differing in terms of demand and fleet size. The results show that the hybrid robot-drone delivery system performs the best with a fleet side of 25 robots and 15 drones and with an average preparation and delivery time less than the individual robot and drone system by 48% and 42% respectively.

cs.CY↗

arXiv2020

Applications of brain imaging methods in driving behaviour research

Applications of neuroimaging methods have substantially contributed to the scientific understanding of human factors during driving by providing a deeper insight into the neuro-cognitive aspects of driver brain. This has been achieved by conducting simulated (and occasionally, field) driving experiments while collecting driver brain signals of certain types. Here, this sector of studies is comprehensively reviewed at both macro and micro scales. Different themes of neuroimaging driving behaviour research are identified and the findings within each theme are synthesised. The surveyed literature has reported on applications of four major brain imaging methods. These include Functional Magnetic Resonance Imaging (fMRI), Electroencephalography (EEG), Functional Near-Infrared Spectroscopy (fNIRS) and Magnetoencephalography (MEG), with the first two being the most common methods in this domain. While collecting driver fMRI signal has been particularly instrumental in studying neural correlates of intoxicated driving (e.g. alcohol or cannabis) or distracted driving, the EEG method has been predominantly utilised in relation to the efforts aiming at development of automatic fatigue/drowsiness detection systems, a topic to which the literature on neuro-ergonomics of driving particularly has shown a spike of interest within the last few years. The survey also reveals that topics such as driver brain activity in semi-automated settings or the brain activity of drivers with brain injuries or chronic neurological conditions have by contrast been investigated to a very limited extent. Further, potential topics in relation to driving behaviour are identified that could benefit from the adoption of neuroimaging methods in future studies.

cs.HC↗

arXiv2020

A bi-partite generative model framework for analyzing and simulating large scale multiple discrete-continuous travel behaviour data

The emergence of data-driven demand analysis has led to the increased use of generative modelling to learn the probabilistic dependencies between random variables. Although their apparent use has mostly been limited to image recognition and classification in recent years, generative machine learning algorithms can be a powerful tool for travel behaviour research by replicating travel behaviour by the underlying properties of data structures. In this paper, we examine the use of generative machine learning approach for analyzing multiple discrete-continuous (MDC) travel behaviour data. We provide a plausible perspective of how we can exploit the use of machine learning techniques to interpret the underlying heterogeneities in the data. We show that generative models are conceptually similar to the choice selection behaviour process through information entropy and variational Bayesian inference. Without loss of generality, we consider a restricted Boltzmann machine (RBM) based algorithm with multiple discrete-continuous layers, formulated as a variational Bayesian inference optimization problem. We systematically describe the proposed machine learning algorithm and develop a process of analyzing travel behaviour data from a generative learning perspective. We show parameter stability from model analysis and simulation tests on an open dataset with multiple discrete-continuous dimensions from a data size of 293,330 observations. For interpretability, we derive the conditional probabilities, elasticities and perform statistical analysis on the latent variables. We show that our model can generate statistically similar data distributions for travel forecasting and prediction and performs better than purely discriminative methods in validation. Our results indicate that latent constructs in generative models can accurately represent the joint distribution consistently on MDC data.

stat.ML↗

arXiv2020

Composite Travel Generative Adversarial Networks for Tabular and Sequential Population Synthesis

Agent-based transportation modelling has become the standard to simulate travel behaviour, mobility choices and activity preferences using disaggregate travel demand data for entire populations, data that are not typically readily available. Various methods have been proposed to synthesize population data for this purpose. We present a Composite Travel Generative Adversarial Network (CTGAN), a novel deep generative model to estimate the underlying joint distribution of a population, that is capable of reconstructing composite synthetic agents having tabular (e.g. age and sex) as well as sequential mobility data (e.g. trip trajectory and sequence). The CTGAN model is compared with other recently proposed methods such as the Variational Autoencoders (VAE) method, which has shown success in high dimensional tabular population synthesis. We evaluate the performance of the synthesized outputs based on distribution similarity, multi-variate correlations and spatio-temporal metrics. The results show the consistent and accurate generation of synthetic populations and their tabular and spatially sequential attributes, generated over varying spatial scales and dimensions.

cs.LG↗

arXiv2020

A multi-layered blockchain framework for smart mobility data-markets

Blockchain has the potential to render the transaction of information more secure and transparent. Nowadays, transportation data are shared across multiple entities using heterogeneous mediums, from paper collected data to smartphone. Most of this data are stored in central servers that are susceptible to hacks. In some cases shady actors who may have access to such sources, share the mobility data with unwanted third parties. A multi-layered Blockchain framework for Smart Mobility Data-market (BSMD) is presented for addressing the associated privacy, security, management, and scalability challenges. Each participant shares their encrypted data to the blockchain network and can transact information with other participants as long as both parties agree to the transaction rules 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 data-market. In a case study of real-time mobility data sharing, we demonstrate the performance of BSMD on a 370 nodes blockchain running on heterogeneous and geographically-separated devices communicating on a physical network. We also demonstrate how BSMD ensures the cybersecurity and privacy of individual by safeguarding against spoofing and message interception attacks and providing information access management control.

cs.CY↗

arXiv2019

Multi-Level Taxonomy and Critical Review of Eco-Routing Methods

Routing decisions are initially based on minimizing travel time. Nevertheless, eco-routing considers the environmental aspect (e.g. emissions, fuel, and exposure) and was introduced to replace the initial routing concept to mitigate the undesirable impact of transportation systems on the environment. This review paper aims to provide a four level taxonomy and map eco-routing studies to the proposed taxonomy. Furthermore, the strengths and weaknesses of the presented models are summarized. In the literature reviewed, special emphasis was given to the role of vehicle connectivity in eco-routing. The main findings include: the microscopic level of aggregation of the flow and emission/fuel models was rarely employed for large case studies due to the associated complexity; one objective was optimized at a time for a majority of the studies; and all of the reviewed studies were applied in a centralized routing system environment.

eess.SY↗

arXiv2019

A blockchain-based user-centric emission monitoring and trading system for multi-modal mobility

Since the transport sector accounts for one of the highest shares of greenhouse gases (GHG) emissions, several existing proposals state the idea to control the by the transportation sector caused GHG emissions through an Emission Trading Systems (ETS). However, most existing approaches integrate GHG emissions through the fuel consumption and car registration, limiting the tracing of emissions in more complex modes e.g. shared vehicles, shared rides and even public transportation. This paper presents a new design of a user-centric ETS and its implementation as a carbon Blockchain framework for Smart Mobility Data-market (cBSMD). The cBSMD allows for the seamless transactions of token-equivalent GHG emissions when realizing a trip, or an emission trading action as well as the transaction of individual, service or system-wide emission performance data. We demonstrate an instance of the cBSMD implementation for the transactions of an ETS where all travellers receive a certain amount of emission credits in the form of tokens, linked to the GHG price and a total emission cap. Travellers use their tokens each time they emit GHG when travelling in a multi-modal network, purchase tokens for a given trip when they have an insufficient token amount or sell when having a surplus of tokens due to a lower amount of emitted GHG. This instance of cBSMD is then applied to a case-study of 24hours of mobility of 3,186 travellers from Oakville, Ontario, Canada, where we showcase different cBSMD transactions and analyze token usage and emission performance.

cs.CY↗

arXiv2019

Privacy-Aware Distributed Mobility Choice Modelling over Blockchain

A generalized distributed tool for mobility choice modelling is presented, where participants do not share personal raw data, while all computations are done locally. Participants use Blockchain based Smart Mobility Data-market (BSMD), where all transactions are secure and private. Nodes in blockchain can transact information with other participants as long as both parties agree to the transaction rules issued by the owner of the data. A case study is presented where a mode choice model is distributed and estimated over BSMD. As an example, the parameter estimation problem is solved on a distributed version of simulated annealing. It is demonstrated that the estimated model parameters are consistent and reproducible.

cs.CR↗