63 results found
Zhu L, Krishnan R, Sivakumar A, et al., Traffic monitoring and anomaly detection based on simulation of Luxembourg Road network, IEEE Intelligent Transportation Systems Conference - ITSC 2019, Publisher: IEEE
Traffic incidents which commonly result fromtraffic accidents, anomalous construction events and inclementweather can cause a wide range of negative impacts on urbanroad networks. Developing a high efficiency and transferabletraffic incident detection system plays an important role insolving the imbalance caused by traffic incidents betweentraffic demand and capacity. However, the existing literatureon transferability of traffic incident detection is rather limited.The objective of this paper is to provide an accurateand transferable incident detection approach based on therelationship between traffic variables and observed trafficincidents, in particular at a network level. We propose a deeplearning based method which has been calibrated using partof the collected traffic variables and the pre-assigned trafficincidents and then tested against the rest of the dataset. Theproposed method is compared to other benchmarks commonlyused in traffic incident detection, in terms of detection rate, falsepositive rate, f-measurement and detection time. The resultsindicate that the proposed method is significantly promising fortraffic incident detection with high accuracy and transferabilitycompared to the more widely used techniques in the literature.
Zhu L, Krishnan R, Guo F, et al., Early identification of recurrent congestion in heterogeneous urban traffic, IEEE Intelligent Transportation Systems Conference - ITSC 2019, Publisher: IEEE
Urban traffic congestion has become a criticalissue that not only affects the quality of daily lives but alsoharms the environment and economy. Traffic patterns arerecurrent in nature, so is congestion. However, little attentionhas been paid to the development of methods that wouldenable early warning of the formation of congestion and itspropagation. This paper proposes a method for automatedearly congestion detection operating over time horizons rangingfrom half an hour to three hours. The method uses a deeplearning technique, Convolutional Neural Networks (CNN), andadapts it to the specific context of urban roads. Empiricalresults are reported from a busy traffic corridor in the city ofBath. Comprehensive evaluation metrics, including DetectionRate, False Positive Rate and Mean Time to Detection, areused to evaluate the performance of the proposed methodcompared to more conventional machine learning methodsincluding Feed-forward Neural Network and Random Forest.The results indicate that recurrent congestion can indeed bepredicted before it occurs and demonstrates that CNN basedmethod offers superior detection accuracy compared to theconventional machine learning methods in this context.
Dong Y, Polak J, Sivakumar A, et al., 2019, Disaggregate short-term location prediction based on recurrent neural network and an agent-based platform, Transportation Research Record: Journal of the Transportation Research Board, Vol: 2673, Pages: 657-668, ISSN: 0361-1981
With the growing popularity of mobile and sensory devices, there has been a strong research interest in short-term disaggregate-level location prediction. Such predictive models have huge application potential in several sectors to change and improve people’s daily life and experience. Existing methods in this research stream have mainly focused on the prediction of sequence of location, with valuable temporal information overlooked. In addition, data limitations have constrained the development and understanding from different algorithms. In this paper, the authors propose a recurrent neural network-based method (RNN and LSTM, long short-term memory) for the next and future location prediction. This model predicts the sequence in time, thus it can predict both when and where an individual will be in the future and the duration of the stay at each location. The predictive model is developed based on an agent-based simulation platform that can produce realistic spatial-temporal trajectory data at the individual level. Analysis of the simulated data has shown that RNN and LSTM are capable of predicting future locations with better results than other comparative methods, especially for agents with high location variability. Online prediction with true location information fed into the model later in the day would greatly improve the predicted results. However, significant variations can be observed at the zonal level, with all methods performing much better on frequently visited locations than less visited locations or irregular visits.
Manca F, Sivakumar A, Polak J, 2019, The effect of social influence and social interactions on the adoption of a new technology: The use of bike sharing in a student population, Transportation Research Part C: Emerging Technologies, Vol: 105, Pages: 611-625, ISSN: 0968-090X
The present study investigates how social influence and social interactions can affect the adoption of new technologies, using stated preference (SP) survey data combined with an “accelerated reality” experience of social interaction among the respondents. Specifically, the intention to use a pro-environmental transport mode (the bike sharing) during a public transport strike within a cohort of students has been analysed. Previous studies have modelled social influence effects using SP data by providing a hypothetical scenario with simulated interactions or information about social conformity processes (i.e. social adoption) during the survey. In our paper, in addition to the impact of assumed social norms, the effect of live/real social interactions is included in the survey. SP survey is developed to investigate the effect of Level-of-Service attributes on the hypothetical choices in the scenario of a public transport strike. Besides the pre-defined attributes characterising the alternatives in the SP design, the survey includes techniques to acquire information on conformity and social interactions. Specifically, the interviewees undertake a before and after stated preference experiment (SP1 and SP2), with a period of group discussion in between the two parts. This SP experiment involves different cognitive and interpersonal mechanisms, such as the functional information exchange on benefits and drawbacks of cycling and bike sharing. The aim is to establish whether hypothetical scenarios of social conformity are different from real/live social interactions and whether these social influence processes actually affect the individuals' mode choice. A joint SP1/SP2 mixed logit (ML) model has been estimated to explore the choice behaviour of individuals and allows us to incorporate the inertia/propensity to change behaviour between SP1 and SP2. Moreover, considering the “Reflexive Layers of Influence” (RLI) framework, the processes generated by
Wu C, Le Vine S, Sivakumar A, et al., 2019, Traveller preferences for free-floating carsharing vehicle allocation mechanisms, Transportation Research Part C: Emerging Technologies, Vol: 102, Pages: 1-19, ISSN: 0968-090X
Free-floating carsharing (FFCS) fleets are inherently volatile spatio-temporally, which presents both a logistical challenge for operators and a service reliability issue for customers. In this study we present a stated-choice survey to investigate the attractiveness to customers of two mechanisms for managing fleet volatility: Virtual Queuing (VQ) and Guaranteed Advance Reservation (GAR). We investigate socio-demographic features and “Big Five” personality traits that are associated ceteris paribus with choosing to use the existing FFCS service model, willingness-to-pay (WTP) for VQ and GAR, and risky-choice behaviour under the uncertainty of FFCS systems. Data (n = 289; 232 employed in analysis) are sourced from existing users of a FFCS service in London, UK. Within the survey context, we found that customers are on average not willing to pay for VQ (i.e. negative WTP), however have £0.54 per journey WTP for GAR, with low-frequency FFCS users and users scoring highly on the Big Five “Conscientiousness” dimension having larger WTP for GAR. When analysing the two dimensions of uncertainty, we found that respondents exhibit risk-seeking behaviour towards price and weaker and insignificant risk-aversion towards walking time. This pattern holds across the three standard model types of nonlinear risky-choice behaviour that we investigated. The results are intended to be useful both to policymakers and carsharing operators who are likely, as the industry matures, to seek mechanisms to differentiate their service offers to better serve individual market segments with distinctive characteristics.
Sivakumar A, 2019, Handbook on Transport and Urban Planning in the Developed World, JOURNAL OF TRANSPORT GEOGRAPHY, Vol: 77, Pages: 143-143, ISSN: 0966-6923
Manca F, Sivakumar A, Hess S, 2019, Travel demand modelling, data collection and well-being, Transportation, Vol: 46, Pages: 303-305, ISSN: 0049-4488
Karamanis R, Angeloudis P, Sivakumar A, et al., 2018, Dynamic Pricing in One-Sided Autonomous Ride-Sourcing Markets, 21st IEEE International Conference on Intelligent Transportation Systems (ITSC), Publisher: IEEE, Pages: 3645-3650, ISSN: 2153-0009
Sivakumar A, Hess S, 2018, New and emerging methods for the improved modelling of travel behaviour: Transportation Research Part B: Special issue of papers from the IATBR 2015 conference, Transportation Research Part B: Methodological, ISSN: 0191-2615
Daina N, Latinopoulos C, Manca F, et al., 2018, An analysis of the joint dynamics of attitudes, intentions and behaviour in e-cycling, hEART 2018 - 7th Symposium of the European Association for Research in Transportation
Manca F, Sivakumar A, Polak J, et al., 2018, An empirical exploration of endogeneity in hybrid choice models with social influence measures, 15th International Conference on Travel Behaviour Research
Karamanis R, Angeloudis P, Sivakumar A, et al., Market dynamics between public transport and competitive ride-sourcing providers, 7th Symposium of the European Association for Research in Transportation, Publisher: hEART
Hess S, Sivakumar A, 2017, Recent developments and future topics in choice modelling for travel behaviour research, Journal of Choice Modelling, Vol: 25, Pages: 1-2, ISSN: 1755-5345
Pawlak J, Polak J, Sivakumar A, 2017, A framework for joint modelling of activity choice, duration, and productivity while travelling, Transportation Research Part B: Methodological, Vol: 106, Pages: 153-172, ISSN: 0191-2615
Recent developments in mobile information and communication technologies (ICT), vehicle automation, and the associated debates on the implications for the operation of transport systems and for the appraisal of investment has heightened the importance of understanding how people spend travel time and how productive they are while travelling. To date, however, no approach has been proposed that incorporates the joint modelling of in-travel activity type, activity duration and productivity behaviour.To address this critical gap, we draw on a recently developed PPS framework (Pawlak et al., 2015) to develop a new joint model of activity type choice, duration and productivity. In our framework, we use copulas to provide a flexible link between a discrete choice model of activity type choice, a hazard-based model for activity duration, and a log-linear model of productivity. Our model is readily amenable to estimation, which we demonstrate using data from the 2008 UK Study of Productive Use of Rail Travel-time. We hence show how journey-, respondent-, attitude-, and ICT-related factors are related to expected in-travel time allocation to work and non-work activities, and the associated productivity.To the best of our knowledge, this is the first framework that both captures the effects of different factors on activity choice, duration and productivity, and models links between these aspects of behaviour. Furthermore, the convenient interpretation of the parameters in the form of semi-elasticities enables the comparison of effects associated with the presence of on-board facilities (e.g., workspace, connectivity) or equipment use, facilitating use of the model outputs in applied contexts.
Manca F, Sivakumar A, Axsen J, et al., 2018, Investigating social influence mechanisms and their inclusion in discrete choice models: recent findings on electric vehicle purchase preferences, 50th Universities’ Transport Study Group Annual Conference
Manca F, Sivakumar A, Daina N, et al., 2017, Exploring the inclusion of social influence in a hybrid choice model of electric vehicle (EV) purchase preferences, 6th Symposium of the European Association for Research in Transportation
Daina N, Sivakumar A, Polak JW, 2017, Electric vehicle charging choices: modelling and implications for smart charging services, Transportation Research Part C: Emerging Technologies, Vol: 81, Pages: 36-56, ISSN: 1879-2359
The rollout of electric vehicles (EV) occurring in parallel with the decarbonisation of the power sector can bring uncontested environmental benefits, in terms of CO2 emission reduction and air quality. This roll out, however, poses challenges to power systems, as additional power demand is injected in context of increasingly volatile supply from renewable energy sources. Smart EV charging services can provide a solution to such challenges. The development of effective smart charging services requires evaluating pre-emptively EV drivers’ response. The current practice in the appraisal of smart charging strategies largely relies on simplistic or theoretical representation of drivers’ charging and travel behaviour. We propose a random utility model for joint EV drivers’ activity-travel scheduling and charging choices. Our model easily integrates in activity-based demand modelling systems for the analyses of integrated transport and energy systems. However, unlike previous charging behaviour models used in integrated transport and energy system analyses, our model empirically captures the behavioural nuances of tactical charging choices in smart grid context, using empirically estimated charging preferences. We present model estimation results that provide insights into the value placed by individuals on the main attributes of the charging choice and draw implications charging service providers.
Calastri C, Hess S, Sivakumar A, 2017, Editorial: Triggers of behavioural change in an evolving world, European Journal of Transport and Infrastructure Research, Vol: 17, Pages: 304-305, ISSN: 1567-7141
Latinopoulos C, Sivakumar A, Polak JW, 2017, Response of electric vehicle drivers to dynamic pricing of parking and charging services: risky choice in early reservations, Transportation Research Part C - Emerging Technologies, Vol: 80, Pages: 175-189, ISSN: 0968-090X
When clusters of electric vehicles charge simultaneously in urban areas, the capacity of the power network might not be adequate to accommodate the additional electricity demand. Recent studies suggest that real-time control strategies, like dynamic pricing of electricity, can spread the demand and help operators to avoid costly infrastructure investments. To assess the effectiveness of dynamic pricing, it is necessary to understand how electric vehicle drivers respond to uncertain future prices when they charge their vehicle away from home. Even when data is available from electric vehicle trials, the lack of variability in electricity prices renders them insufficient for this analysis. We resolve this problem by designing a survey where we observe the stated preferences of the respondents for hypothetical charging services. A novel feature of this survey is its interface, which resembles an online or smartphone application for parking-and-charging reservations. The time-of-booking choices are evaluated within a risky-choice modelling framework, where expected utility and non-expected utility specifications are compared to understand how people perceive price probabilities. In the progress, we bring together theoretical frameworks of forward-looking behaviour in contexts where individuals were subject to equivalent price uncertainties. The results suggest that a) the majority of the electric vehicle drivers are risk averse by choosing a certain price to an uncertain one and b) there is a non-linearity in their choices, with a disproportional influence by the upper end of the price distribution. This approach gives new perspectives in the way people plan their travel activities in advance and highlights the impact of uncertainty when managing limited resources in dense urban centres. Similar surveys and analyses could provide valuable insights in a wide range of innovative mobility applications, including car-sharing, ride-sharing and on-demand services.
Latinopoulos C, Sivakumar A, Polak JW, 2017, Modeling electric vehicle charging behaviour: What is the relationship between charging location, driving distance and range anxiety?, Annual Meeting of the Transportation Research Board
For parking operators and charging service providers it is critical to understand the factors that influence the demand for charging electric vehicles away from home. This information will not only help them to better anticipate the impact on the power grid, but also to develop revenue maximizing demand response strategies. Recent studies suggest that observable and unobservable attributes of travel demand affect the location and the frequency of charging events. Nevertheless, it is unlikely that there is a simple one way causality in the relationship, since the distinctive characteristics of electric vehicles might also lead to transformations in travel behaviour. In order to examine these ambiguous interrelationships we develop two models: a binary logistic regression for home charging vs out-of-home charging and an ordered logit regression for the daily distance driven with an electric vehicle. Attitudes and perceptions of individuals towards range constraints are indirectly captured with latent constructs like schedule flexibility or mobility necessity. The data used for the analysis were collected through the administration of an online survey to electric vehicle drivers in the UK and Ireland. Results show that there is an intrinsic link between charging and travel behaviour with potential implications both in a strategic and an operational level.
Manca F, Sivakumar A, Daina N, et al., 2017, Including social influence in choice models: comparison of different formulations, 5th International Choice Modelling Conference
Daina N, Sivakumar A, Polak JW, 2016, Modelling electric vehicles use: a survey on the methods, Renewable and Sustainable Energy Reviews, Vol: 68, Pages: 447-460, ISSN: 1879-0690
In the literature electric vehicle use is modelled using of a variety of approaches in power systems, energy and environmental analyses as well as in travel demand analysis. This paper provides a systematic review of these diverse approaches using a twofold classification of electric vehicle use representation, based on the time scale and on substantive differences in the modelling techniques. For time of day analysis of demand we identify activity-based modelling (ABM) as the most attractive because it provides a framework amenable for integrated cross-sector analyses, required for the emerging integration of the transport and electricity network. However, we find that the current examples of implementation of AMB simulation tools for EV-grid interaction analyses have substantial limitations. Amongst the most critical there is the lack of realism how charging behaviour is represented.
Daina N, Sivakumar A, Polak JW, Supporting users’ decision making in complex environments: a choice model based recommender system for demand response in electric vehicle charging, hEART 2016: 5th Symposium of the European Association for Research in Transportation
Pawlak J, Circella G, Polak J, et al., 2016, Is there anything exceptional about ICT use while travelling? A time allocation framework for and empirical insights into multitasking patterns and well-being implications from the Canadian General Social Survey, 95th Annual Meeting of Transportation Research Board, Publisher: Transportation Research Board
Zolfaghari A, Polak J, Sivakumar A, 2016, Choice set imputation in atomistic spatial choice models, Transportation Research Record, Vol: 2564, Pages: 138-146, ISSN: 0361-1981
Constructing the universal choice set in spatial choice models developed at the level of elemental alternatives (atomistic models) is challenging because disaggregate data on the attributes of nonchosen alternatives are often not available. Even when the disaggregate data on nonchosen alternatives are available, matching two data sources will inevitably be error prone given that they might be collected at different times and they might have different coding for categorical variables. An important practical question in the estimation of such atomistic models, therefore, is how to construct the universal choice set in the absence of disaggregate data on the attributes of the nonchosen alternatives. This paper presents a novel approach for spatial imputation of attributes of nonchosen alternatives for estimation and application of atomistic spatial choice models in the absence of disaggregate data. The proposed approach uses the iterative proportional fitting algorithm to impute the attributes of nonchosen alternatives from aggregated data on elemental alternatives. The proposed method is validated with a Monte Carlo experiment and applied to real data in the London residential location choice context.
Daina, Polak, Sivakumar, 2015, Capturing the Effect Range of Anxiety on Electric Vehicle Charging Behaviour: An Integrated Choice and Latent Variable Approach, 4th symposium of the European Association for Research in Transportation (hEART)
Pawlak J, Circella G, Polak J, et al., 2015, Is there anything exceptional about ICT use while travelling? Time allocation framework for and empirical insights into multitasking patterns and their well-being implications. APPENDIX: MODEL DERIVATION
Pawlak J, Circalla G, Polak J, et al., 2016, Is There Anything Exceptional about ICT Use while Travelling as Compared to Other Contexts, and is it Good or Bad? Empirical Insights into Multitasking Patterns and their Well-being Implications, International Association for Travel Behaviour Research (IATBR)
Pawlak J, Le Vine S, Polak J, et al., 2015, ICT and Physical Mobility – State of Knowledge and Future Outlook, ICT and Physical Mobility – State of Knowledge and Future Outlook, Munich, Publisher: Institute for Mobility Research ifmo: A Research Facility of the BMW Group
Pawlak J, Polak J, Sivakumar A, et al., 2015, Investigating Diffusion of Relationships between ICT and Travel Behaviour by Pooling Independent Cross-sectional Data across Time, 94th Annual Meeting of Transportation Research Board
This data is extracted from the Web of Science and reproduced under a licence from Thomson Reuters. You may not copy or re-distribute this data in whole or in part without the written consent of the Science business of Thomson Reuters.