Nicolette Formosa - Academia.edu (original) (raw)

Uploads

Papers by Nicolette Formosa

Research paper thumbnail of Evaluating the Impact of Lane Marking Quality on the Operation of Autonomous Vehicles

Journal of Transportation Engineering, Part A: Systems

Research paper thumbnail of Appraising Machine and Deep Learning Techniques for Traffic Conflict Prediction with Class Imbalance

Research paper thumbnail of Pollution around Malta's sea

Research paper thumbnail of Predicting real-time traffic conflicts using deep learning

Accident Analysis & Prevention, Mar 1, 2020

Recently, technologies for predicting traffic conflicts in real-time have been gaining momentum d... more Recently, technologies for predicting traffic conflicts in real-time have been gaining momentum due to their proactive nature of application and the growing implementation of ADAS technology in intelligent vehicles. In ADAS, machine learning classifiers are utilised to predict potential traffic conflicts by analysing data from in-vehicle sensors. In most cases, a condition is 5 classified as a traffic conflict when a safety surrogate (e.g. time-to-collision, TTC) crosses a predefined threshold. This approach, however, largely ignores other factors that influence traffic conflicts such as speed variance, traffic density, speed and weather conditions. Considering all these factors in detecting traffic conflicts is rather complex as it requires an integration and mining of heterodox data, the unavailability of traffic conflicts and conflict prediction models capable of extracting meaningful and accurate information in a timely manner. In addition, the model has to effectively handle large imbalanced data. To overcome these limitations, this paper presents a centralised digital architecture and employs a Deep Learning methodology to predict traffic conflicts. Highly disaggregated traffic data and in-vehicle sensors data from an instrumented vehicle are collected from a section of the UK M1 motorway to build the model. Traffic conflicts are identified by a Regional-Convolution Neural Network (R-CNN) model which detects lane markings and tracks vehicles from images captured by a single frontfacing camera. This data is then integrated with traffic variables and calculated safety surrogate measures (SSMs) via a centralised digital architecture to develop a series of Deep Neural Network (DNN) models to predict these traffic conflicts. The results indicate that TTC, as expected, varies by speed, weather and traffic density and the best DNN model provides an accuracy of 94% making it reliable to employ in ADAS technology as proactive safety management strategies. Furthermore, by exchanging this traffic conflict awareness data, connected vehicles (CVs) can mitigate the risk of traffic collisions.

Research paper thumbnail of Validating a Traffic Conflict Prediction Technique for Motorways Using a Simulation Approach

Sensors, Jan 12, 2022

This article is an open access article distributed under the terms and conditions of the Creative... more This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY

Research paper thumbnail of Developing a Vehicle Re-routing Algorithm using Connected Vehicle (CV) Technology

arXiv (Cornell University), Aug 30, 2022

Vehicle Ad-hoc Networks (VANETs) act as the core of vehicular communications and provide the fund... more Vehicle Ad-hoc Networks (VANETs) act as the core of vehicular communications and provide the fundamental wireless communication architecture to support both vehicle-to-vehicle (V2V) and vehicle-to-infrastructure (V2I) communication. Therefore, by leveraging only communication technologies, Connected Vehicles (CVs) can navigate through the dynamic road network. However, such vehicles are still in their infancy but are expected to have a significant impact on safety and mobility such as reducing non-recurrent congestion in case of a vehicle breakdown or other roadway incidents. To evaluate their impacts, this research examines the benefits of having CVs when a vehicle breakdown occurs by developing an intelligent proactive rerouting algorithm. Due to a lack of real-world data, this paper adopts an integrated simulated framework consisting of a V2X (OMNET++) communication simulator and a traffic microscopic simulator (SUMO). The developed algorithm functions such that when a vehicle is broken down within a live traffic lane, the system detects the breakdown, generates warning messages immediately and transmits them to approaching vehicles. Based on the real-time notification, informed vehicles proactively reroute to alternative roads to avoid the breakdown zone. Two scenarios were developed where a breakdown occurs within and outside a junction for both V2X-enabled and disabled systems. Results show that V2X-enabled CV rerouting mechanism can improve the traffic efficiency by reducing congestion and enhance the traffic safety by smoothing accelerations and decelerations of affected vehicles with low infrastructure costs. The algorithm would be useful to highways agencies (Department for Transport) and vehicle manufacturers in introducing CVs onto existing road networks.

Research paper thumbnail of A New Modeling Approach for Predicting Vehicle-Based Safety Threats

IEEE Transactions on Intelligent Transportation Systems, Oct 1, 2022

Research paper thumbnail of Developing a Vehicle Re-routing Algorithm using Connected Vehicle (CV) Technology

arXiv (Cornell University), Aug 30, 2022

Vehicle Ad-hoc Networks (VANETs) act as the core of vehicular communications and provide the fund... more Vehicle Ad-hoc Networks (VANETs) act as the core of vehicular communications and provide the fundamental wireless communication architecture to support both vehicle-to-vehicle (V2V) and vehicle-to-infrastructure (V2I) communication. Therefore, by leveraging only communication technologies, Connected Vehicles (CVs) can navigate through the dynamic road network. However, such vehicles are still in their infancy but are expected to have a significant impact on safety and mobility such as reducing non-recurrent congestion in case of a vehicle breakdown or other roadway incidents. To evaluate their impacts, this research examines the benefits of having CVs when a vehicle breakdown occurs by developing an intelligent proactive rerouting algorithm. Due to a lack of real-world data, this paper adopts an integrated simulated framework consisting of a V2X (OMNET++) communication simulator and a traffic microscopic simulator (SUMO). The developed algorithm functions such that when a vehicle is broken down within a live traffic lane, the system detects the breakdown, generates warning messages immediately and transmits them to approaching vehicles. Based on the real-time notification, informed vehicles proactively reroute to alternative roads to avoid the breakdown zone. Two scenarios were developed where a breakdown occurs within and outside a junction for both V2X-enabled and disabled systems. Results show that V2X-enabled CV rerouting mechanism can improve the traffic efficiency by reducing congestion and enhance the traffic safety by smoothing accelerations and decelerations of affected vehicles with low infrastructure costs. The algorithm would be useful to highways agencies (Department for Transport) and vehicle manufacturers in introducing CVs onto existing road networks.

Research paper thumbnail of Appraising Machine and Deep Learning Techniques for Traffic Conflict Prediction with Class Imbalance

Data Science for Transportation, Apr 6, 2023

Research paper thumbnail of Developing vehicle-based traffic conflict prediction algorithms using deep learning

With the rapid growth of artificial intelligence technologies such as big data analytic, machine ... more With the rapid growth of artificial intelligence technologies such as big data analytic, machine learning, and image recognition, the vehicle industry has undergone dramatic changes. The vehicle is no longer a simple mechanical structure, but it engages with the driver, environment and infrastructure. For instance, intelligent vehicles aim to improve vehicle and driver safety by utilising multiple Advanced Driver Assistance Systems (ADAS). These emerging technologies in the automotive industry have introduced safety-related challenges and consequently, research has attempted to address these challenges by designing and developing proactive safety management systems for these vehicles. In particular, to proactively mitigate the risk of collision, there is a need to predict traffic conflicts to prevent collisions.Existing safety prediction algorithms assess and quantify the threat level surrounding the ego-vehicle. However, they are not able to plan the best response to a fully unexpe...

Research paper thumbnail of Validating a Traffic Conflict Prediction Technique for Motorways Using a Simulation Approach

Sensors (Basel, Switzerland), 2022

With the ever-increasing advancements in the technology of driver assistant systems, there is a n... more With the ever-increasing advancements in the technology of driver assistant systems, there is a need for a comprehensive way to identify traffic conflicts to avoid collisions. Although significant research efforts have been devoted to traffic conflict techniques applied for junctions, there is dearth of research on these methods for motorways. This paper presents the validation of a traffic conflict prediction algorithm applied to a motorway scenario in a simulated environment. An automatic video analysis system was developed to identify lane change and rear-end conflicts as ground truth. Using these conflicts, the prediction ability of the traffic conflict technique was validated in an integrated simulation framework. This framework consisted of a sub-microscopic simulator, which provided an appropriate testbed to accurately simulate the components of an intelligent vehicle, and a microscopic traffic simulator able to generate the surrounding traffic. Results from this framework sh...

Research paper thumbnail of A New Modeling Approach for Predicting Vehicle-Based Safety Threats

IEEE Transactions on Intelligent Transportation Systems, 2022

Research paper thumbnail of Real-time modelling and interpolation of spatio-temporal marine pollution

Due to the complexity of the interactions involved in various dynamic systems, known physical, bi... more Due to the complexity of the interactions involved in various dynamic systems, known physical, biological or chemical laws cannot adequately describe the dynamics behind these processes. The study of these systems thus depends on measurements often taken at various discrete spatial locations through time by noisy sensors. For this reason, scientists often necessitate interpolative, visualisation and analytical tools to deal with the large volumes of data common to these systems. The starting point of this study is the seminal research by C. Shannon on sampling and reconstruction theory and its various extensions. Based on recent work on the reconstruction of stochastic processes, this paper develops a novel real-time estimation method for nonstationary stochastic spatio-temporal behaviour based on the Integro-Difference Equation (IDE). This methodology is applied to collected marine pollution data from a Norwegian fjord. Comparison of the results obtained by the proposed method with...

Research paper thumbnail of Predicting real-time traffic conflicts using deep learning

Accident Analysis & Prevention

Recently, technologies for predicting traffic conflicts in real-time have been gaining momentum d... more Recently, technologies for predicting traffic conflicts in real-time have been gaining momentum due to their proactive nature of application and the growing implementation of ADAS technology in intelligent vehicles. In ADAS, machine learning classifiers are utilised to predict potential traffic conflicts by analysing data from in-vehicle sensors. In most cases, a condition is classified as a traffic conflict when a safety surrogate (e.g. time-to-collision, TTC) crosses a predefined threshold. This approach, however, largely ignores other factors that influence traffic conflicts such as speed variance, traffic density, speed and weather conditions. Considering all these factors in detecting traffic conflicts is rather complex as it requires an integration and mining of heterodox data, the unavailability of traffic conflicts and conflict prediction models capable of extracting meaningful and accurate information in a timely manner. In addition, the model has to effectively handle large imbalanced data. To overcome these limitations, this paper presents a centralised digital architecture and employs a Deep Learning methodology to predict traffic conflicts. Highly disaggregated traffic data and in-vehicle sensors data from an instrumented vehicle are collected from a section of the UK M1 motorway to build the model. Traffic conflicts are identified by a Regional-Convolution Neural Network (R-CNN) model which detects lane markings and tracks vehicles from images captured by a single frontfacing camera. This data is then integrated with traffic variables and calculated safety surrogate measures (SSMs) via a centralised digital architecture to develop a series of Deep Neural Network (DNN) models to predict these traffic conflicts. The results indicate that TTC, as expected, varies by speed, weather and traffic density and the best DNN model provides an accuracy of 94% making it reliable to employ in ADAS technology as proactive safety management strategies. Furthermore, by exchanging this traffic conflict awareness data, connected vehicles (CVs) can mitigate the risk of traffic collisions.

Research paper thumbnail of Pollution around Malta's sea

Research paper thumbnail of Evaluating the Impact of Lane Marking Quality on the Operation of Autonomous Vehicles

Journal of Transportation Engineering, Part A: Systems

Research paper thumbnail of Appraising Machine and Deep Learning Techniques for Traffic Conflict Prediction with Class Imbalance

Research paper thumbnail of Pollution around Malta's sea

Research paper thumbnail of Predicting real-time traffic conflicts using deep learning

Accident Analysis & Prevention, Mar 1, 2020

Recently, technologies for predicting traffic conflicts in real-time have been gaining momentum d... more Recently, technologies for predicting traffic conflicts in real-time have been gaining momentum due to their proactive nature of application and the growing implementation of ADAS technology in intelligent vehicles. In ADAS, machine learning classifiers are utilised to predict potential traffic conflicts by analysing data from in-vehicle sensors. In most cases, a condition is 5 classified as a traffic conflict when a safety surrogate (e.g. time-to-collision, TTC) crosses a predefined threshold. This approach, however, largely ignores other factors that influence traffic conflicts such as speed variance, traffic density, speed and weather conditions. Considering all these factors in detecting traffic conflicts is rather complex as it requires an integration and mining of heterodox data, the unavailability of traffic conflicts and conflict prediction models capable of extracting meaningful and accurate information in a timely manner. In addition, the model has to effectively handle large imbalanced data. To overcome these limitations, this paper presents a centralised digital architecture and employs a Deep Learning methodology to predict traffic conflicts. Highly disaggregated traffic data and in-vehicle sensors data from an instrumented vehicle are collected from a section of the UK M1 motorway to build the model. Traffic conflicts are identified by a Regional-Convolution Neural Network (R-CNN) model which detects lane markings and tracks vehicles from images captured by a single frontfacing camera. This data is then integrated with traffic variables and calculated safety surrogate measures (SSMs) via a centralised digital architecture to develop a series of Deep Neural Network (DNN) models to predict these traffic conflicts. The results indicate that TTC, as expected, varies by speed, weather and traffic density and the best DNN model provides an accuracy of 94% making it reliable to employ in ADAS technology as proactive safety management strategies. Furthermore, by exchanging this traffic conflict awareness data, connected vehicles (CVs) can mitigate the risk of traffic collisions.

Research paper thumbnail of Validating a Traffic Conflict Prediction Technique for Motorways Using a Simulation Approach

Sensors, Jan 12, 2022

This article is an open access article distributed under the terms and conditions of the Creative... more This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY

Research paper thumbnail of Developing a Vehicle Re-routing Algorithm using Connected Vehicle (CV) Technology

arXiv (Cornell University), Aug 30, 2022

Vehicle Ad-hoc Networks (VANETs) act as the core of vehicular communications and provide the fund... more Vehicle Ad-hoc Networks (VANETs) act as the core of vehicular communications and provide the fundamental wireless communication architecture to support both vehicle-to-vehicle (V2V) and vehicle-to-infrastructure (V2I) communication. Therefore, by leveraging only communication technologies, Connected Vehicles (CVs) can navigate through the dynamic road network. However, such vehicles are still in their infancy but are expected to have a significant impact on safety and mobility such as reducing non-recurrent congestion in case of a vehicle breakdown or other roadway incidents. To evaluate their impacts, this research examines the benefits of having CVs when a vehicle breakdown occurs by developing an intelligent proactive rerouting algorithm. Due to a lack of real-world data, this paper adopts an integrated simulated framework consisting of a V2X (OMNET++) communication simulator and a traffic microscopic simulator (SUMO). The developed algorithm functions such that when a vehicle is broken down within a live traffic lane, the system detects the breakdown, generates warning messages immediately and transmits them to approaching vehicles. Based on the real-time notification, informed vehicles proactively reroute to alternative roads to avoid the breakdown zone. Two scenarios were developed where a breakdown occurs within and outside a junction for both V2X-enabled and disabled systems. Results show that V2X-enabled CV rerouting mechanism can improve the traffic efficiency by reducing congestion and enhance the traffic safety by smoothing accelerations and decelerations of affected vehicles with low infrastructure costs. The algorithm would be useful to highways agencies (Department for Transport) and vehicle manufacturers in introducing CVs onto existing road networks.

Research paper thumbnail of A New Modeling Approach for Predicting Vehicle-Based Safety Threats

IEEE Transactions on Intelligent Transportation Systems, Oct 1, 2022

Research paper thumbnail of Developing a Vehicle Re-routing Algorithm using Connected Vehicle (CV) Technology

arXiv (Cornell University), Aug 30, 2022

Vehicle Ad-hoc Networks (VANETs) act as the core of vehicular communications and provide the fund... more Vehicle Ad-hoc Networks (VANETs) act as the core of vehicular communications and provide the fundamental wireless communication architecture to support both vehicle-to-vehicle (V2V) and vehicle-to-infrastructure (V2I) communication. Therefore, by leveraging only communication technologies, Connected Vehicles (CVs) can navigate through the dynamic road network. However, such vehicles are still in their infancy but are expected to have a significant impact on safety and mobility such as reducing non-recurrent congestion in case of a vehicle breakdown or other roadway incidents. To evaluate their impacts, this research examines the benefits of having CVs when a vehicle breakdown occurs by developing an intelligent proactive rerouting algorithm. Due to a lack of real-world data, this paper adopts an integrated simulated framework consisting of a V2X (OMNET++) communication simulator and a traffic microscopic simulator (SUMO). The developed algorithm functions such that when a vehicle is broken down within a live traffic lane, the system detects the breakdown, generates warning messages immediately and transmits them to approaching vehicles. Based on the real-time notification, informed vehicles proactively reroute to alternative roads to avoid the breakdown zone. Two scenarios were developed where a breakdown occurs within and outside a junction for both V2X-enabled and disabled systems. Results show that V2X-enabled CV rerouting mechanism can improve the traffic efficiency by reducing congestion and enhance the traffic safety by smoothing accelerations and decelerations of affected vehicles with low infrastructure costs. The algorithm would be useful to highways agencies (Department for Transport) and vehicle manufacturers in introducing CVs onto existing road networks.

Research paper thumbnail of Appraising Machine and Deep Learning Techniques for Traffic Conflict Prediction with Class Imbalance

Data Science for Transportation, Apr 6, 2023

Research paper thumbnail of Developing vehicle-based traffic conflict prediction algorithms using deep learning

With the rapid growth of artificial intelligence technologies such as big data analytic, machine ... more With the rapid growth of artificial intelligence technologies such as big data analytic, machine learning, and image recognition, the vehicle industry has undergone dramatic changes. The vehicle is no longer a simple mechanical structure, but it engages with the driver, environment and infrastructure. For instance, intelligent vehicles aim to improve vehicle and driver safety by utilising multiple Advanced Driver Assistance Systems (ADAS). These emerging technologies in the automotive industry have introduced safety-related challenges and consequently, research has attempted to address these challenges by designing and developing proactive safety management systems for these vehicles. In particular, to proactively mitigate the risk of collision, there is a need to predict traffic conflicts to prevent collisions.Existing safety prediction algorithms assess and quantify the threat level surrounding the ego-vehicle. However, they are not able to plan the best response to a fully unexpe...

Research paper thumbnail of Validating a Traffic Conflict Prediction Technique for Motorways Using a Simulation Approach

Sensors (Basel, Switzerland), 2022

With the ever-increasing advancements in the technology of driver assistant systems, there is a n... more With the ever-increasing advancements in the technology of driver assistant systems, there is a need for a comprehensive way to identify traffic conflicts to avoid collisions. Although significant research efforts have been devoted to traffic conflict techniques applied for junctions, there is dearth of research on these methods for motorways. This paper presents the validation of a traffic conflict prediction algorithm applied to a motorway scenario in a simulated environment. An automatic video analysis system was developed to identify lane change and rear-end conflicts as ground truth. Using these conflicts, the prediction ability of the traffic conflict technique was validated in an integrated simulation framework. This framework consisted of a sub-microscopic simulator, which provided an appropriate testbed to accurately simulate the components of an intelligent vehicle, and a microscopic traffic simulator able to generate the surrounding traffic. Results from this framework sh...

Research paper thumbnail of A New Modeling Approach for Predicting Vehicle-Based Safety Threats

IEEE Transactions on Intelligent Transportation Systems, 2022

Research paper thumbnail of Real-time modelling and interpolation of spatio-temporal marine pollution

Due to the complexity of the interactions involved in various dynamic systems, known physical, bi... more Due to the complexity of the interactions involved in various dynamic systems, known physical, biological or chemical laws cannot adequately describe the dynamics behind these processes. The study of these systems thus depends on measurements often taken at various discrete spatial locations through time by noisy sensors. For this reason, scientists often necessitate interpolative, visualisation and analytical tools to deal with the large volumes of data common to these systems. The starting point of this study is the seminal research by C. Shannon on sampling and reconstruction theory and its various extensions. Based on recent work on the reconstruction of stochastic processes, this paper develops a novel real-time estimation method for nonstationary stochastic spatio-temporal behaviour based on the Integro-Difference Equation (IDE). This methodology is applied to collected marine pollution data from a Norwegian fjord. Comparison of the results obtained by the proposed method with...

Research paper thumbnail of Predicting real-time traffic conflicts using deep learning

Accident Analysis & Prevention

Recently, technologies for predicting traffic conflicts in real-time have been gaining momentum d... more Recently, technologies for predicting traffic conflicts in real-time have been gaining momentum due to their proactive nature of application and the growing implementation of ADAS technology in intelligent vehicles. In ADAS, machine learning classifiers are utilised to predict potential traffic conflicts by analysing data from in-vehicle sensors. In most cases, a condition is classified as a traffic conflict when a safety surrogate (e.g. time-to-collision, TTC) crosses a predefined threshold. This approach, however, largely ignores other factors that influence traffic conflicts such as speed variance, traffic density, speed and weather conditions. Considering all these factors in detecting traffic conflicts is rather complex as it requires an integration and mining of heterodox data, the unavailability of traffic conflicts and conflict prediction models capable of extracting meaningful and accurate information in a timely manner. In addition, the model has to effectively handle large imbalanced data. To overcome these limitations, this paper presents a centralised digital architecture and employs a Deep Learning methodology to predict traffic conflicts. Highly disaggregated traffic data and in-vehicle sensors data from an instrumented vehicle are collected from a section of the UK M1 motorway to build the model. Traffic conflicts are identified by a Regional-Convolution Neural Network (R-CNN) model which detects lane markings and tracks vehicles from images captured by a single frontfacing camera. This data is then integrated with traffic variables and calculated safety surrogate measures (SSMs) via a centralised digital architecture to develop a series of Deep Neural Network (DNN) models to predict these traffic conflicts. The results indicate that TTC, as expected, varies by speed, weather and traffic density and the best DNN model provides an accuracy of 94% making it reliable to employ in ADAS technology as proactive safety management strategies. Furthermore, by exchanging this traffic conflict awareness data, connected vehicles (CVs) can mitigate the risk of traffic collisions.

Research paper thumbnail of Pollution around Malta's sea