Dr Mihaita is currently a Senior Lecturer in the University of Technology in Sydney, Faculty of Engineering and IT, leading the newly created UTS Future Mobility Research lab. Before joining UTS, she was a Senior Research Scientist and team leader in the ADAIT group from NICTA (now Data61) and continues to act as an affiliated Senior Researcher.
Dr Adriana-Simona MIHAITA received her PhD from the “Institute National Polytechnique de Grenoble”, France in 2012, after 3 years of being awarded an “Allocation de Recherche” by the French government in automatic control and computer science and an International ERASMUS scholarship for her master thesis. Her PhD research focused on building an event-driven automatic control method for hybrid systems using Markov Chains; she also worked as a teaching assistant in Computer Science in the University of Lumiere Lyon 2 in France. After her graduation she worked for 3 years as a Teaching Assistant and Research Scientist in the ERPI research group from University of Lorraine, France before moving to Australia in 2015.
Her main research focus is how to engage traffic simulation and optimization using machine learning and artificial intelligence to improve traffic congestion, predicting the duration of traffic accidents and estimating their urban impact, while also leveraging smart analytics for connected and autonomous vehicles in a smart city environment. She is highly engaged in smart city modelling and worked on traffic plan optimization inside ecological neighbourhoods using evolutionary algorithms.
Dr Mihaita holds several leadership roles in various initiatives such as: currently C.I. in the ARC Linkage Project LP180100114 under the Australian-Singapore Strategic Collaboration Partnership (a $2.4 mil program for collaborations between the two countries on solving congestion problems), and previously: transport leader and scrum master in the “Premiere’s Innovation Initiative” (a $3.9mil program and sole winner of the TfNSW congestion program), the “On-Demand Mobility” trials in Northern Beaches in partnership with Keolis Downer, as well as “the Investigation of positioning accuracy of connected vehicles” operated by the Road Safety Centre in Transport for NSW (TfNSW).
Over the years, Dr Mihaita’s work and collaborative engagement has received various recognition awards such as:
- 2018 (Nov) - National ITS Award on Research Excellence – team award based for research work on the “Artificial Intelligence for traffic congestion management”, a work done in collaboration with Transport for New South Wales.
- 2018 (Sept) – two collaborative “Smart City Awards” from the Committee for Sydney: “Best industry-led partnership” & “Project of the year” for the “On-Demand Transport Initiative” in Northern Beaches/Macquarie Park led by Keolis Downer together with our team in Data61 and also AECOM, Via and GoGet.
- 2018 (July) – personal nomination as finalist in the “51 Most Impactful Smart Cities Leaders”, World CSR day 2019.
- 2018 (August) –“2018 Your Leadership Voice: Women in Focus Program” personal award from the Monash Business School, Melbourne, Australia to develop leadership and project management capabilities for women in science.
- 2015 – National ITS Award on Research Excellence – ADAIT team award.
- 2013 – 1st prize at the International 3D Simulation Competition organized by FlexSim France as a team leader.
She is currently a Program Committee Member for the Australasian Data Mining Conference (AusDM’19), 2–5 December 2019, ITS Australia Summit, 28-29 August 2019, Melbourne, Australia, serves as reviewer for TRB, IFAC WC, Journal of ITS, Journal Simulation Modelling Practice and Theory, KSII, JCLP, etc. and is main organiser of various Special Interest Sessions during ITS World Congresses’, focused on topics such as: Crowd movement analysis and modelling, MaaS, Predictive Analytics, On Demand Passenger Transport, Big-data analytics.
Her publications and activity can be found at my personal website.
Can supervise: YES
- traffic modelling and simulation
- machine learning and artificial intelligence
- connected and autonomous vehicles
- multi-agent simulation
- multi-objective optimization
- evolutionary/genetic algorithms
- smart city
Mihăiţă, AS, Dupont, L, Chery, O, Camargo, M & Cai, C 2019, 'Evaluating air quality by combining stationary, smart mobile pollution monitoring and data-driven modelling', Journal of Cleaner Production, vol. 221, pp. 398-418.View/Download from: UTS OPUS or Publisher's site
© 2019 Elsevier Ltd Air pollution impact assessment is a major objective for various community councils in large cities, which have lately redirected their attention towards using more low-cost sensing units supported by citizen involvement. However, there is a lack of research studies investigating real-time mobile air-quality measurement through smart sensing units and even more of any data-driven modelling techniques that could be deployed to predict air quality accurately from the generated data-sets. This paper addresses these challenges by: a) proposing a comparative and detailed investigation of various air quality monitoring devices (both fixed and mobile), tested through field measurements and citizen sensing in an eco-neighbourhood from Lorraine, France, and by b) proposing a machine learning approach to evaluate the accuracy and potential of such mobile generated data for air quality prediction. The air quality evaluation consists of three experimenting protocols: a) first, we installed fixed passive tubes for monitoring the nitrogen dioxide concentrations placed in strategic locations highly affected by traffic circulation in an eco-neighbourhood, b) second, we monitored the nitrogen dioxide registered by citizens using smart and mobile pollution units carried at breathing level; results revealed that mobile-captured concentrations were 3–5 times higher than the ones registered by passive-static monitoring tubes and c) third, we compared different mobile pollution stations working simultaneously, which revealed noticeable differences in terms of result variability and sensitivity. Finally, we applied a machine learning modelling by using decision trees and neural networks on the mobile-generated data and show that humidity and noise are the most important factors influencing the prediction of nitrogen dioxide concentrations of mobile stations.
Mihăiţă, AS, Ortiz, MB, Camargo, M & Cai, C 2019, 'Predicting Air Quality by Integrating a Mesoscopic Traffic Simulation Model and Simplified Air Pollutant Estimation Models', International Journal of Intelligent Transportation Systems Research, vol. 17, no. 2, pp. 125-141.View/Download from: Publisher's site
© 2018, Springer Science+Business Media, LLC, part of Springer Nature. Continuous growth in traffic demand has led to a decrease in the air quality in various urban areas. More than ever, local authorities for environmental protection and urban planners are interested in performing detailed investigations using traffic and air pollution simulations for testing various urban scenarios and raising citizen awareness where necessary. This article is focused on the traffic and air pollution in the eco-neighbourhood 'Nancy Grand Cœur', located in a medium-size city from north-eastern France. The main objective of this work is to build an integrated simulation model which would predict and visualize various environmental changes inside the neighbourhood such as: air pollution, traffic flow or meteorological information. Firstly, we conduct a data profiling analysis on the received data sets together with a discussion on the daily and hourly traffic patterns, average nitrogen dioxide concentrations and the regional background concentrations recorded in the eco-neighbourhood for the study period. Secondly, we build the 3D mesoscopic traffic simulation model using real data sets from the local traffic management centre. Thirdly, by using reliable data sets from the local air-quality management centre, we build a regression model to predict the evolution of nitrogen dioxide concentrations, as a function of the simulated traffic flow and meteorological data. We then validate the estimated results through comparisons with real data sets, with the purpose of supporting the traffic engineering decision-making and the smart city sustainability. The last section of the paper is reserved for further regression studies applied to other air pollutants monitored in the eco-neighbourhood, such as sulphur dioxide and particulate matter and a detailed discussion on benefit and challenges to conduct such studies.
Mihăiţă, AS, Dupont, L & Camargo, M 2018, 'Multi-objective traffic signal optimization using 3D mesoscopic simulation and evolutionary algorithms', Simulation Modelling Practice and Theory, vol. 86, pp. 120-138.View/Download from: UTS OPUS or Publisher's site
© 2018 Elsevier B.V. Modern cities are currently facing rapid urban growth and struggle to maintain a sustainable development. In this context, 'eco-neighbourhoods' became the perfect place for testing new innovative ideas that would reduce congestion and optimize traffic flow. The main motivation of this work is a true and stated need of the Department of Transport in Nancy, France, to improve the traffic flow in a central eco-neighbourhood currently under reconfiguration, reduce travel times and test various traffic control scenarios for a better interconnectivity between urban intersections. Therefore, this paper addresses a multi-objective simulation-based signal control problem through the case study of 'Nancy Grand Cœur' (NGC) eco-neighbourhood with the purpose of finding the optimal traffic control plan to reduce congestion during peak hours. Firstly, we build the 3D mesoscopic simulation model of the most circulated intersection (C129) based on specifications from the traffic management centre. The simulation outputs from various scenario testing will be then used as inputs for the optimisation and comparative analysis modules. Secondly, we propose a multi-objective optimization method by using evolutionary algorithms and find the optimal traffic control plan to be used in C129 during morning and evening rush hours. Lastly, we take a more global view and extend the 3D simulation model to three other interconnected intersections, in order to analyse the impact of local optimisation on the surrounding traffic conditions in the eco-neighbourhood. The current proposed simulation-optimisation framework aims at supporting the traffic engineering decision-making process and the smart city dynamic by favouring a sustainable mobility.
Wen, T, Mihăiţă, A-S, Nguyen, H, Cai, C & Chen, F 2018, 'Integrated Incident Decision-Support using Traffic Simulation and Data-Driven Models', Transportation Research Record, vol. 2672, pp. 247-256.View/Download from: UTS OPUS or Publisher's site
This paper introduces the framework of an innovative incident management platform with the main objective of providing decision-support and situation awareness for transport management purposes on a real-time basis. The logic of the platform is to detect and then classify incidents into two types: recurrent and non-recurrent, based on their frequency and characteristics. Under this logic, recurrent incidents trigger the data-driven machine learning module which can predict and analyze the incident impact, in order to facilitate informed decisions for transport management operators. Non-recurrent incidents activate the simulation module, which then evaluates quantitatively the performance of candidate response plans in parallel. The simulation output is used for choosing the most appropriate response plan for incident management. The current platform uses a data processing module to integrate complementary data sets, for the purpose of improving modeling outputs. Two real-world case studies are presented: 1) for recurrent incident management using a data-driven model, and 2) for non-recurrent incident management using traffic simulation with parallel scenario evaluation. The case studies demonstrate the viability of the proposed incident management framework, which provides an integrated approach for real-time incident decision-support on large-scale networks.
Mihăiţă, AS, Cai, C & Chen, F 2017, 'Event-triggered control for improving the positioning accuracy of connected vehicles equipped with DSRC', IFAC-PapersOnLine, vol. 50, no. 1, pp. 8518-8524.View/Download from: Publisher's site
© 2017 Vehicle-to-Vehicle communication and Dedicated Short Range Communication (DSRC) systems have gained an increasing popularity in building vehicular applications for improving road safety, but the high level of positioning accuracy at the centimetre level is still far from being achieved. Various outages in transmitting the positioning information between neighbouring vehicles and errors in broadcasting their current locations can lead to a fail in generating accurate collision alerts that would affect the road safety. The goal of this paper is to propose a modelling framework for applying an event-triggered control when the location transmitted by connected vehicles equipped with DSRC is lost due to unforeseen events. Firstly, we model the evolution of the DSRC transmitted positioning as a multi-state stochastic switching system by taking into consideration the distance from the transmitted location to the road center. A control interval is defined for the evolution of the positioning signal by using the road width to define the boundaries. Secondly, we propose an analytic method for determining the exit probabilities from the control interval, with the scope of anticipating any position anomalies and help applying the event triggered control in advance rather than when the control boundaries have been already reached. Thirdly, we apply a cooperative location estimation method for improving the broadcast position information by using the accumulating trajectory segments from the moment of the anomaly alert.
Mihăiţă, AS, Mocanu, S & Lhoste, P 2016, 'Probabilistic analysis of a class of continuous-time stochastic switching systems with event-driven control', European Journal of Automation (JESA), vol. to appear, pp. to appear-to appear.
Monticolo, D, Mihaita, S, Darwich, H & Hilaire, V 2014, 'An agent-based system to build project memories during engineering projects', Knowledge-Based Systems, vol. 68, pp. 88-102.View/Download from: Publisher's site
Engineering projects are organizations where several actors with different professional fields and know-how work together to carry out the same aim: to develop a new product. Inside these organizations, heterogeneous and distributed information has to be managed in order to create project memories that will be useful in future projects. In this paper we describe a Multi-Agent System (MAS), which is based on the social and cooperative approach to support the knowledge management process all along mechanical design projects. Indeed, this multi-agent system, called KATRAS, aims to capitalize and reuse knowledge according to the roles involved in the design projects. We will present in this paper how the agents capitalize six different types of knowledge (professional vocabulary, process, expertise, project evolution, and return of experience) and how they help the professional actors to reuse knowledge. © 2014 Elsevier B.V. All rights reserved.
Monticolo, D & Mihăiţă, AS 2014, 'A multi Agent System to Manage Ideas during Collaborative Creativity Workshops', International Journal of Future Computer and Communication (IJFCC), vol. 3, pp. 66-70.View/Download from: Publisher's site
Mihaita, S & Mocanu, S 2011, 'Simulation in continuous time for the oriented control of events of stochastic switching systems: Modeling, control, and simulation of the stochastic switching systems', Journal Europeen des Systemes Automatises, vol. 45, no. 1-3, pp. 157-172.View/Download from: Publisher's site
This paper presents a continuous time simulation method for stochastic switching systems while applying event-based control. The main system we have used is a multi-state integrator having a switching behavior, being described by a continuous-time Markov Chain. The objective of the event-based control method is to maintain the continuous system state variable between extreme limits. Control stopping limits have also been taken into consideration. Finally we present the results we have obtained in order to minimize a quadratic energy cost while applying event-based control. © 2011 Lavoisier, Paris.
Mihăiţă, AS & Mocanu, S 2011, 'Simulation en temps continu pour la commande orientée événements des systèmes stochastiques à commutation', European Journal of Automation (JESA), vol. 45, pp. 157-172.
Mao, T, Mihăiţă, AS & Cai, C 2019, 'Traffic Signal Control Optimisation under Severe Incident Conditions using Genetic Algorithm', ITS World Congress 2019 (ITSWC2019), Singapore.
Shaffiei, S, Mihăiţă, AS & Cai, C 2019, 'Demand Estimation and Prediction for Short-term Traffic Forecasting in Existence of Non-recurrent Incidents', ITS World Congress 2019 (ITSWC2019), Singapore.
Mihăiţă, AS, Dupont, L, Cherry, O, Camargo, M & Cai, C 2018, 'Air quality monitoring using stationary versus mobile sensing units: a case study from Lorraine, France', 25th ITS World Congress (ITSWC 2018), Copenhagen, Denmark.
Wen, T, Mihăiţă, AS, Nguyen, H & Cai, C 2018, 'Integrated Incident decision support using traffic simulation and data-driven models', Transportation Research Board 97th Annual Meeting (TRB 2018),Washington D.C..
Mihăiţă, AS, Tyler, P, MWall, J, Vecovsky, V & Cai, C 2017, 'Positioning and collision alert investigation for DSRC-equipped light vehicles through a case study in CITI', ITS World Congress 2017, Montreal.
Mihăiţă, AS, Tyler, P, Menon, A, Wen, T, Ou, Y, Cai, C & Chen, F 2017, 'An investigation of positioning accuracy transmitted by connected heavy vehicles using DSRC', Transportation Research Board - 96th Annual Meeting, Washington, D.C..
Mihăiţă, AS, Ortiz, MB & Camargo, M 2016, 'Integrating a mesoscopic traffic simulation model and a simplified NO2 estimation model for predicting the impact of air pollution', 23rd World Congress on Intellient Transportation Systems (ITSWC 2016), Melbourne, Australia, 10-14 October 2016.
Mihăiţă, AS, Benavides, M & Camargo, M 2016, 'Integrating a mesoscopic traffic simulation model and a simplified NO2 estimation model', 23rd World COngress in Intelligent Transportation Systems, Melbourne.
Mihəiţə, AS, Camargo, M & Lhoste, P 2014, 'Optimization of a complex urban intersection using discrete event simulation and evolutionary algorithms', IFAC Proceedings Volumes (IFAC-PapersOnline), pp. 8768-8774.
© IFAC. Dealing with traffic management for complex crossroads is a challenging problem for traffic control planners. As a contribution to solve this problem, the present paper develops a mesoscopic simulation model for detecting the most suited fire plan for a complex road intersection, using a discrete event simulation tool and an evolutionary algorithm optimization. The modeling goal is to eliminate congestion by choosing an appropriate fire plan which will be adapted to the actual configuration of the intersection, as well as to a future reconfiguration meant to accept a higher inflow of vehicles. The proposed model is applied to a down-town crossroads from Nancy, France. Four different configurations of the input data flow were studied under the proposed simulation-optimization approach, and an optimal fire plan is proposed.
Mihăiţă, AS, Camargo, M & Lhoste, P 2014, 'Evaluating the impact of the traffic reconfiguration of a complex urban intersection', 10th International Conference on Modelling, Optimization and Simulation (MOSIM 2014), Nancy, France, 5-7 November 2014.
Issa, F, Monticolo, D, Gabriel, A & Mihăiţă, AS 2014, 'An Intelligent System based on Natural Language Processing to support the brain purge in the creativity process', IAENG International Conference on Artificial Intelligence and Applications (ICAIA'14) Hong Kong.
Monticolo, D & Mihăiţă, AS 2013, 'A Multi Agent System to manage ideas during Collaborative Creativity Workshops', 5th International Conference on Future Computer and Communication, Phuket, Thailand.
Mihaita, A-S & Mocanu, S 2012, 'Un nouveau modéle de l'énergie de commande des systèmes stochastiques à commutation', https://controls.papercept.net/conferences/conferences/CIFA12/program/C…, Septième Conférence Internationale Francophone d'Automatique (CIFA 2012), Grenoble, France.View/Download from: UTS OPUS
Cet article présente une méthode de calcul analytique pour les temps moyennes et les probabilités de sortie de la zone de contrôle appliquée sur une classe de systèmes stochastiques à commutation, nécessaire pour construire le modèle énergétique. Le modèle utilisé est un intégrateur à commutation avec des états multiples qui est caractérisé par une chaîne de Markov en temps continu. Pour limiter l'évolution aléatoire de la variable d'état, une zone de contrôle a été considérée. Un critère quadratique pour minimiser l'énergie consommée quand on applique le contrôle basé sur les événements est utilisé pour lequel nous calculons les temps de sortie et les probabilités de sortir de la zone de contrôle. La validation des temps de sortie et des probabilités par des résultats numériques est présentée à la fin de cet article.
In this paper we present a method for constructing an approximative stationary energy model of a stochastic switching system while applying event-based control. The main model used is a multi-state integrator with random switching behavior, upon event occurrence, which has been described using a continuous Markov chain. Applying event-based control has been done in the purpose of maintaining the continuous system state variable between extreme boundaries. The sojourn times and the probabilities to hit the limits have also been used for the computation of the average energy consumed during the stationary mode of the Markov chain. Mean times between intermediary stopping points and extreme limits are also provided as well as a quadratic criterion for square deviations from imposed target limits. © 2011 IFAC.
Mihăiţă, S 2012, 'Approche probabiliste pour la commande orientée événement des systèmes stochastiques ‵q commutation'.
- Australian National University, Canberra
- Swinburne University of Technology,Melbourne
- National Technology University of Singapore
- National Univeristy of Singapore
- ENGSI France
- Fortescue Metal group
- Roads and Maritime Services
- Transport for NSW
- National Research Foundation Singapore