Julie Dugdale | University of Grenoble (original) (raw)

Papers by Julie Dugdale

Proceedings of the Annual Hawaii International Conference on System Sciences

The behaviours of citizens during bushfires may determine whether they live or die. Using 100 cit... more The behaviours of citizens during bushfires may determine whether they live or die. Using 100 citizen witness statements from the 2009 Australian bushfires, we show how people react to bushfire smoke. Eightynine witnesses expressly mention smoke, not necessarily in combination with fire. This prompted behaviours including: seeking further information, monitoring the situation, effecting a fire plan (including evacuation), alerting people to danger and fire risk, and going home. Computational simulators have been used to assess civilians' risk and to help with evacuation efforts. Despite works that accurately model fire spread and people's behaviours in response to perceiving fire, the issue of how people react to seeing smoke from a bushfire is rarely considered. We discuss how the identified behaviours may be incorporated into an agent-based simulator of bushfire.

2022 IEEE 19th International Conference on Software Architecture (ICSA)

The Internet of Behaviors (IoB) puts human behavior at the core of engineering intelligent connec... more The Internet of Behaviors (IoB) puts human behavior at the core of engineering intelligent connected systems. IoB links the digital world to human behavior to establish human-driven design, development, and adaptation processes. This paper defines the novel concept by an IoB model based on a collective effort interacting with software engineers, humancomputer interaction scientists, social scientists, and cognitive science communities. The model for IoB is created based on an exploratory study that synthesizes state-of-the-art analysis and experts interviews. The architecture of a real industry 4.0 manufacturing infrastructure helps to explain the IoB model and it's application. The conceptual model was used to successfully implement a socio-technical infrastructure for a crowd monitoring and queue management system for the Uffizi Galleries, Florence, Italy. The experiment, which started in the fall of 2016 and was operational in the fall of 2018, used a data-driven approach to feed the system with real-time sensory data. It also incorporated prediction models on visitors' mobility behavior. The system's main objective was to capture human behavior, model it, and build a mechanism that considers changes, adapts in real-time, and continuously learns from repetitive behaviors. In addition to the conceptual model and the real-life evaluation, this paper provides recommendations from experts and gives future directions for IoB to become a significant technological advancement in the coming few years.

International audienceThis paper addresses modeling and simulating pedestrian trajectories when i... more International audienceThis paper addresses modeling and simulating pedestrian trajectories when interacting with an autonomous vehicle in a shared space. Pedestrian motion models integrating pedestrians interactions with an autonomous vehicle already exist. However, they fail to accurately predict the individual trajectory of each pedestrian, and they do not deal with the diversity of possible pedestrian interactions with the vehicle in a shared space (front, back or lateral). Moreover, previous works do not sufficiently provide a quantitative evaluation of the model's predictions. In this paper, we propose an hybrid pedestrian model that combines the social force model and a new decision model for conflicting pedestrian-vehicle interactions. The proposed model integrates different observed pedestrians behaviors, as well as the behaviors of the social groups of pedestrians. We validate the model and evaluate its predictive potential through qualitative and quantitative compariso...

Proceedings of the Annual Hawaii International Conference on System Sciences, 2020

Proceedings of the Annual Hawaii International Conference on System Sciences, 2022

Clearly, the year 2020 has shown how sensitive human society is to crisis situations. This is not... more Clearly, the year 2020 has shown how sensitive human society is to crisis situations. This is not only a simple matter of fact, this is also and mainly the consequence of the hyper connection of this human society. There is actually no more absorption space for our world and society to absorb any significant disruption and avoid its spreading across the whole planet. However, the progress of human society, in addition to being considered as the main cause of this dangerous evolution, could also provide avenues to deal with it: data science, artificial intelligence, social networks and more globally information technologies are amazing avenues that "in charge" institutions and governments should deeply consider to take the right path to deal with the tremendous next challenges of the century (global warming, pandemics, overpopulation and lack of resources, disbalance north and south, drop of biodiversity, etc.). The DIRECT minitrack of the eGov track of HICSS 54 presents nine great papers addressing these issues but also these perspectives. The following presents each of these articles.

This paper addresses modeling and simulating pedestrian trajectories when interacting with an aut... more This paper addresses modeling and simulating pedestrian trajectories when interacting with an autonomous vehicle in a shared space. Pedestrian motion models integrating pedestrians interactions with an autonomous vehicle already exist. However, they fail to accurately predict the individual trajectory of each pedestrian, and they do not deal with the diversity of possible pedestrian interactions with the vehicle in a shared space (front, back or lateral). Moreover, previous works do not sufficiently provide a quantitative evaluation of the model’s predictions. In this paper, we propose an hybrid pedestrian model that combines the social force model and a new decision model for conflicting pedestrian-vehicle interactions. The proposed model integrates different observed pedestrians behaviors, as well as the behaviors of the social groups of pedestrians. We validate the model and evaluate its predictive potential through qualitative and quantitative comparisons with ground truth traje...

Spring Simulation Conference (SpringSim 2020), 2020

The nature of the social relationship within a pedestrian group influences the group's structure ... more The nature of the social relationship within a pedestrian group influences the group's structure and behavior and thus its entitativity (i.e. the perception of a group as a unit by other pedestrians). However, existing crowd models ignore the diversity of social relationships and have limitations in reproducing group avoidance behaviors. The proposed model is an adaptation of the social force model that addresses group social relationships. The approach is calibrated by comparing the distances and angles between members of the simulated groups with observations in real crowds. Results show that intra-group distances are a key factor in collision avoidance behavior. Simulation of collision avoidance shows that group members behavior fits better with empirical data than the original model and that individuals avoid splitting groups. By simply tuning the distribution of social relationships in the simulated crowd, the model can be used to reproduce crowd behaviors in several contexts.

Informatica (Slovenia), 2018

This paper presents a Multi-Agent System (MAS) approach for designing an air pollution simulator.... more This paper presents a Multi-Agent System (MAS) approach for designing an air pollution simulator. The aim is to simulate the concentration of air pollutants emitted from sources (e.g. factories) and to investigate the emergence of cooperation between the emission source managers and its impact on air quality. The emission sources are controlled by agents. The agents try to achieve their goals (i.e. increase production which has the side effect of raising air pollution) and also cooperate with others agents by altering their emission rate according to the air quality. The agents play an adapted version of the evolutionary N-Person Prisoners’ Dilemma game in a non deterministic environment; they have two decisions: decrease, or increase the emission. The rewards/penalties are influenced by the pollutant concentration which is, in turn, determined using climatic parameters. In order to give predictions about the concentration of pollutants: Particulates Matter (PM10), Sulphur Oxide and...

ArXiv, 2019

Citizens and Emergency Managers need to be able to distinguish ''fake'' (untrue) ... more Citizens and Emergency Managers need to be able to distinguish ''fake'' (untrue) news posts from real news posts on social media during disasters. This paper is based on an online survey conducted in 2018 that produced 341 responses from invitations distributed via email and through Facebook. It explores to what extent and how citizens generally assess whether postings are ''true'' or ''fake,'' and describes indicators of the trustworthiness of content that users would like. The mean response on a semantic differential scale measuring how frequently users attempt to verify the news trustworthiness (a scale from 1-never to 5-always) was 3.37. The most frequent message characteristics citizens' use are grammar and the trustworthiness of the sender. Most respondents would find an indicator of trustworthiness helpful, with the most popular choice being a colored graphic. Limitations and implications for assessments of trustworthiness d...

This paper describes the design of an Internet of Things (IoT) system for building evacuation. Th... more This paper describes the design of an Internet of Things (IoT) system for building evacuation. There are two main design decisions for such systems: i) specifying the platform on which the IoT intelligent components should be located; and ii) establishing the level of collaboration among the components. For safety-critical systems, such as evacuation, real-time performance and evacuation time are critical. The approach aims to minimize computational and evacuation delays and uses Queuing Network (QN) models. The approach was tested, by computer simulation, on a real exhibition venue in Alan Turing Building, Italy, that has 34 sets of IoT sensors and actuators. Experiments were performed that tested the effect of segmenting the physical space into different sized virtual cubes. Experiments were also conducted concerning the distribution of the software architecture. The results show that using centralized architectural pattern with a segmentation of the space into large cubes is the ...

Proceedings of the 52nd Hawaii International Conference on System Sciences, 2019

In this paper we propose an analysis of social cohesion in terms of 3 factors: emotions, social n... more In this paper we propose an analysis of social cohesion in terms of 3 factors: emotions, social norms, and mutual knowledge. These factors have previously been analysed separately in terms of Beliefs, Desires, Intentions (BDI) logics, but have not been merged into a unified model. The goal of this paper is to provide a unified agent-based model and describe its implementation in the GAMA simulation platform. The simulator is applied to an evacuation case study and different scenarios are run to evaluate the impact of the 3 factors on cohesion, as well as the effect of cohesion on evacuation. This paper describes first results and concludes with interesting future prospects.

Proceedings of the 52nd Hawaii International Conference on System Sciences, 2019

Proceedings of the 51st Hawaii International Conference on System Sciences, 2018

Future Generation Computer Systems, 2018

Hybrid clouds are increasingly used to outsource non-critical applications to public clouds. Howe... more Hybrid clouds are increasingly used to outsource non-critical applications to public clouds. However, the main challenge within such environments, is to ensure a cost-efficient distribution of the systems between the resources that are on/off premises. For Multi Agent Systems (MAS), this challenge is deepened due to irregular workload progress and intensive communication between the agents, which may result in high computing and data transfer costs. Thus, in this paper we propose a generic framework for adaptive cost-efficient deployment of MAS with a special focus on hybrid clouds. The framework is based mainly on the use of a performance evaluation process that consists of simulating various partitioning options to estimate and optimize the overall deployment costs. Further, to cope with the irregular workload changes within a MAS and dynamically adapt its initial deployment, we propose an extended version of the Fiduccia-Mattheyses algorithm (E-FM). The experimental results highlight the efficiency of E-FM and show that an efficient MAS deployment to hybrid clouds depends on various factors such as the cloud providers and their different cost-models, the network state, the used partitioning algorithm, and the initial deployment.

Journal of the International Society for Telemedicine and eHealth, 2018

This paper describes the origins and progress of an international project to advance disaster eHe... more This paper describes the origins and progress of an international project to advance disaster eHealth (DEH) – the application of eHealth technologies to enhance the delivery of healthcare in disasters. The study to date has focused on two major themes; the role of DEH in facilitating inter-agency communication in disaster situations, and the fundamental need to promote awareness of DEH in the education of disaster managers and health professionals. The paper deals mainly with on-going research on the second of these themes, surveying the current provision of disaster medicine education, the design considerations for a DEH programme for health professionals, the key curriculum topics, and the optimal delivery mode.

Revue d'intelligence artificielle, 2015

Nous présentons une approche pour la conception d'un système multi-agent de préparation des acteu... more Nous présentons une approche pour la conception d'un système multi-agent de préparation des acteurs communaux à la gestion de crises, dans le contexte d'une interaction via des tables tangibles distribuées. Notre point focal est celui des normes qui régissent ces interventions. Le rôle du système est d'analyser la validité des interventions au sens de ces normes et de transmettre des feedbacks appropriés. La perspective normative permet une modélisation unifiée des 3 facettes (production, coordination et communication) de la collaboration. Nous présentons les premières étapes de conception, qui s'appuie sur la plateforme JaCaMo, ainsi qu'un exemple d'application à des scénarios simples. ABSTRACT. We present an approach for the design of a multi-agent system for the training of municipal services to natural crisis management, under remote and connected tangible interaction. Our focus is on the protocols that govern human intervention. The system role is to analyze the validity of intervention with respect to these norms and to generate appropriate feedbacks. We propose a unified modeling of the 3 facets of collaboration (production, coordination and communication) under the normative perspective. We present the first designing steps, which draws on the JaCaMo framework, together with an application example to simple scenarios.

2016 49th Hawaii International Conference on System Sciences (HICSS), 2016

This paper describes an agent based approach for simulating the control of an air pollution crisi... more This paper describes an agent based approach for simulating the control of an air pollution crisis. A Gaussian Plum air pollution dispersion model (GPD) is combined with an Artificial Neural Network (ANN) to predict the concentration levels of three different air pollutants. The two models (GPM and ANN) are integrated with a MAS (multi-agent system). The MAS models pollutant sources controllers and air pollution monitoring agencies as software agents. The population of agents cooperates with each other in order to reduce their emissions and control the air pollution. Leaks or natural sources of pollution are modelled as uncontrolled sources. A cooperation strategy is simulated and its impact on air pollution evolution is assessed and compared. The simulation scenario is built using data about Annaba (a city in NorthEast Algeria). The simulation helps to compare and assess the efficiency of policies to control air pollution during crises, and takes in to account uncontrolled sources.

Lecture Notes in Business Information Processing, 2015

The paper describes a MAS (multi-agent system) simulation approach for controlling PM10 (Particul... more The paper describes a MAS (multi-agent system) simulation approach for controlling PM10 (Particulate Matter) crisis peaks. A dispersion model is used with an Artificial Neural Network (ANN) to predict the PM10 concentration level. The dispersion and ANN models are integrated into a MAS system. PM10 source controllers are modelled as software agents. The MAS is composed of agents that cooperate with each other for reducing their emissions and control the air pollution peaks. Different control strategies are simulated and compared using data from Annaba (North-East Algeria). The simulator helps to compare and assess the efficiency of policies to control peaks in PM10.

The emergence of mixed agent-human societies poses challenges in designing companion agents that ... more The emergence of mixed agent-human societies poses challenges in designing companion agents that are able to form meaningful relationships with humans. This paper describes the first step in developing companion agents. Problem/situations have been identified where companion agents may provide important social contact with humans. Based on a scenario, interactions between human and artificial agents have been modelled in the Brahms modelling and simulation environment. This provides us with a far deeper understanding of the roles that a companion agent should fulfil and how it could switch from one social role to another.

Lecture Notes in Computer Science, 2003

Until recently virtual applications rarely incorporated any deep social, cultural or emotional ca... more Until recently virtual applications rarely incorporated any deep social, cultural or emotional capabilities exhibited in normal human interaction. In this paper, we present a methodology to develop virtual actors with believable communications skills who may provide a sufficient feeling of immersion to reproduce an efficient simulation of human activities. We focus on the relationship between gestures and verbal activities during communicative acts. We will show that an approach based on video analysis is valuable for the design of a system allowing realistic interactions between the avatars and/or the avatars and the environment. Although the analysis is still in progress, we present some preliminary results from our experiments.

Proceedings of the Annual Hawaii International Conference on System Sciences

The behaviours of citizens during bushfires may determine whether they live or die. Using 100 cit... more The behaviours of citizens during bushfires may determine whether they live or die. Using 100 citizen witness statements from the 2009 Australian bushfires, we show how people react to bushfire smoke. Eightynine witnesses expressly mention smoke, not necessarily in combination with fire. This prompted behaviours including: seeking further information, monitoring the situation, effecting a fire plan (including evacuation), alerting people to danger and fire risk, and going home. Computational simulators have been used to assess civilians' risk and to help with evacuation efforts. Despite works that accurately model fire spread and people's behaviours in response to perceiving fire, the issue of how people react to seeing smoke from a bushfire is rarely considered. We discuss how the identified behaviours may be incorporated into an agent-based simulator of bushfire.

2022 IEEE 19th International Conference on Software Architecture (ICSA)

The Internet of Behaviors (IoB) puts human behavior at the core of engineering intelligent connec... more The Internet of Behaviors (IoB) puts human behavior at the core of engineering intelligent connected systems. IoB links the digital world to human behavior to establish human-driven design, development, and adaptation processes. This paper defines the novel concept by an IoB model based on a collective effort interacting with software engineers, humancomputer interaction scientists, social scientists, and cognitive science communities. The model for IoB is created based on an exploratory study that synthesizes state-of-the-art analysis and experts interviews. The architecture of a real industry 4.0 manufacturing infrastructure helps to explain the IoB model and it's application. The conceptual model was used to successfully implement a socio-technical infrastructure for a crowd monitoring and queue management system for the Uffizi Galleries, Florence, Italy. The experiment, which started in the fall of 2016 and was operational in the fall of 2018, used a data-driven approach to feed the system with real-time sensory data. It also incorporated prediction models on visitors' mobility behavior. The system's main objective was to capture human behavior, model it, and build a mechanism that considers changes, adapts in real-time, and continuously learns from repetitive behaviors. In addition to the conceptual model and the real-life evaluation, this paper provides recommendations from experts and gives future directions for IoB to become a significant technological advancement in the coming few years.

International audienceThis paper addresses modeling and simulating pedestrian trajectories when i... more International audienceThis paper addresses modeling and simulating pedestrian trajectories when interacting with an autonomous vehicle in a shared space. Pedestrian motion models integrating pedestrians interactions with an autonomous vehicle already exist. However, they fail to accurately predict the individual trajectory of each pedestrian, and they do not deal with the diversity of possible pedestrian interactions with the vehicle in a shared space (front, back or lateral). Moreover, previous works do not sufficiently provide a quantitative evaluation of the model's predictions. In this paper, we propose an hybrid pedestrian model that combines the social force model and a new decision model for conflicting pedestrian-vehicle interactions. The proposed model integrates different observed pedestrians behaviors, as well as the behaviors of the social groups of pedestrians. We validate the model and evaluate its predictive potential through qualitative and quantitative compariso...

Proceedings of the Annual Hawaii International Conference on System Sciences, 2020

Proceedings of the Annual Hawaii International Conference on System Sciences, 2022

Clearly, the year 2020 has shown how sensitive human society is to crisis situations. This is not... more Clearly, the year 2020 has shown how sensitive human society is to crisis situations. This is not only a simple matter of fact, this is also and mainly the consequence of the hyper connection of this human society. There is actually no more absorption space for our world and society to absorb any significant disruption and avoid its spreading across the whole planet. However, the progress of human society, in addition to being considered as the main cause of this dangerous evolution, could also provide avenues to deal with it: data science, artificial intelligence, social networks and more globally information technologies are amazing avenues that "in charge" institutions and governments should deeply consider to take the right path to deal with the tremendous next challenges of the century (global warming, pandemics, overpopulation and lack of resources, disbalance north and south, drop of biodiversity, etc.). The DIRECT minitrack of the eGov track of HICSS 54 presents nine great papers addressing these issues but also these perspectives. The following presents each of these articles.

This paper addresses modeling and simulating pedestrian trajectories when interacting with an aut... more This paper addresses modeling and simulating pedestrian trajectories when interacting with an autonomous vehicle in a shared space. Pedestrian motion models integrating pedestrians interactions with an autonomous vehicle already exist. However, they fail to accurately predict the individual trajectory of each pedestrian, and they do not deal with the diversity of possible pedestrian interactions with the vehicle in a shared space (front, back or lateral). Moreover, previous works do not sufficiently provide a quantitative evaluation of the model’s predictions. In this paper, we propose an hybrid pedestrian model that combines the social force model and a new decision model for conflicting pedestrian-vehicle interactions. The proposed model integrates different observed pedestrians behaviors, as well as the behaviors of the social groups of pedestrians. We validate the model and evaluate its predictive potential through qualitative and quantitative comparisons with ground truth traje...

Spring Simulation Conference (SpringSim 2020), 2020

The nature of the social relationship within a pedestrian group influences the group's structure ... more The nature of the social relationship within a pedestrian group influences the group's structure and behavior and thus its entitativity (i.e. the perception of a group as a unit by other pedestrians). However, existing crowd models ignore the diversity of social relationships and have limitations in reproducing group avoidance behaviors. The proposed model is an adaptation of the social force model that addresses group social relationships. The approach is calibrated by comparing the distances and angles between members of the simulated groups with observations in real crowds. Results show that intra-group distances are a key factor in collision avoidance behavior. Simulation of collision avoidance shows that group members behavior fits better with empirical data than the original model and that individuals avoid splitting groups. By simply tuning the distribution of social relationships in the simulated crowd, the model can be used to reproduce crowd behaviors in several contexts.

Informatica (Slovenia), 2018

This paper presents a Multi-Agent System (MAS) approach for designing an air pollution simulator.... more This paper presents a Multi-Agent System (MAS) approach for designing an air pollution simulator. The aim is to simulate the concentration of air pollutants emitted from sources (e.g. factories) and to investigate the emergence of cooperation between the emission source managers and its impact on air quality. The emission sources are controlled by agents. The agents try to achieve their goals (i.e. increase production which has the side effect of raising air pollution) and also cooperate with others agents by altering their emission rate according to the air quality. The agents play an adapted version of the evolutionary N-Person Prisoners’ Dilemma game in a non deterministic environment; they have two decisions: decrease, or increase the emission. The rewards/penalties are influenced by the pollutant concentration which is, in turn, determined using climatic parameters. In order to give predictions about the concentration of pollutants: Particulates Matter (PM10), Sulphur Oxide and...

ArXiv, 2019

Citizens and Emergency Managers need to be able to distinguish ''fake'' (untrue) ... more Citizens and Emergency Managers need to be able to distinguish ''fake'' (untrue) news posts from real news posts on social media during disasters. This paper is based on an online survey conducted in 2018 that produced 341 responses from invitations distributed via email and through Facebook. It explores to what extent and how citizens generally assess whether postings are ''true'' or ''fake,'' and describes indicators of the trustworthiness of content that users would like. The mean response on a semantic differential scale measuring how frequently users attempt to verify the news trustworthiness (a scale from 1-never to 5-always) was 3.37. The most frequent message characteristics citizens' use are grammar and the trustworthiness of the sender. Most respondents would find an indicator of trustworthiness helpful, with the most popular choice being a colored graphic. Limitations and implications for assessments of trustworthiness d...

This paper describes the design of an Internet of Things (IoT) system for building evacuation. Th... more This paper describes the design of an Internet of Things (IoT) system for building evacuation. There are two main design decisions for such systems: i) specifying the platform on which the IoT intelligent components should be located; and ii) establishing the level of collaboration among the components. For safety-critical systems, such as evacuation, real-time performance and evacuation time are critical. The approach aims to minimize computational and evacuation delays and uses Queuing Network (QN) models. The approach was tested, by computer simulation, on a real exhibition venue in Alan Turing Building, Italy, that has 34 sets of IoT sensors and actuators. Experiments were performed that tested the effect of segmenting the physical space into different sized virtual cubes. Experiments were also conducted concerning the distribution of the software architecture. The results show that using centralized architectural pattern with a segmentation of the space into large cubes is the ...

Proceedings of the 52nd Hawaii International Conference on System Sciences, 2019

In this paper we propose an analysis of social cohesion in terms of 3 factors: emotions, social n... more In this paper we propose an analysis of social cohesion in terms of 3 factors: emotions, social norms, and mutual knowledge. These factors have previously been analysed separately in terms of Beliefs, Desires, Intentions (BDI) logics, but have not been merged into a unified model. The goal of this paper is to provide a unified agent-based model and describe its implementation in the GAMA simulation platform. The simulator is applied to an evacuation case study and different scenarios are run to evaluate the impact of the 3 factors on cohesion, as well as the effect of cohesion on evacuation. This paper describes first results and concludes with interesting future prospects.

Proceedings of the 52nd Hawaii International Conference on System Sciences, 2019

Proceedings of the 51st Hawaii International Conference on System Sciences, 2018

Future Generation Computer Systems, 2018

Hybrid clouds are increasingly used to outsource non-critical applications to public clouds. Howe... more Hybrid clouds are increasingly used to outsource non-critical applications to public clouds. However, the main challenge within such environments, is to ensure a cost-efficient distribution of the systems between the resources that are on/off premises. For Multi Agent Systems (MAS), this challenge is deepened due to irregular workload progress and intensive communication between the agents, which may result in high computing and data transfer costs. Thus, in this paper we propose a generic framework for adaptive cost-efficient deployment of MAS with a special focus on hybrid clouds. The framework is based mainly on the use of a performance evaluation process that consists of simulating various partitioning options to estimate and optimize the overall deployment costs. Further, to cope with the irregular workload changes within a MAS and dynamically adapt its initial deployment, we propose an extended version of the Fiduccia-Mattheyses algorithm (E-FM). The experimental results highlight the efficiency of E-FM and show that an efficient MAS deployment to hybrid clouds depends on various factors such as the cloud providers and their different cost-models, the network state, the used partitioning algorithm, and the initial deployment.

Journal of the International Society for Telemedicine and eHealth, 2018

This paper describes the origins and progress of an international project to advance disaster eHe... more This paper describes the origins and progress of an international project to advance disaster eHealth (DEH) – the application of eHealth technologies to enhance the delivery of healthcare in disasters. The study to date has focused on two major themes; the role of DEH in facilitating inter-agency communication in disaster situations, and the fundamental need to promote awareness of DEH in the education of disaster managers and health professionals. The paper deals mainly with on-going research on the second of these themes, surveying the current provision of disaster medicine education, the design considerations for a DEH programme for health professionals, the key curriculum topics, and the optimal delivery mode.

Revue d'intelligence artificielle, 2015

Nous présentons une approche pour la conception d'un système multi-agent de préparation des acteu... more Nous présentons une approche pour la conception d'un système multi-agent de préparation des acteurs communaux à la gestion de crises, dans le contexte d'une interaction via des tables tangibles distribuées. Notre point focal est celui des normes qui régissent ces interventions. Le rôle du système est d'analyser la validité des interventions au sens de ces normes et de transmettre des feedbacks appropriés. La perspective normative permet une modélisation unifiée des 3 facettes (production, coordination et communication) de la collaboration. Nous présentons les premières étapes de conception, qui s'appuie sur la plateforme JaCaMo, ainsi qu'un exemple d'application à des scénarios simples. ABSTRACT. We present an approach for the design of a multi-agent system for the training of municipal services to natural crisis management, under remote and connected tangible interaction. Our focus is on the protocols that govern human intervention. The system role is to analyze the validity of intervention with respect to these norms and to generate appropriate feedbacks. We propose a unified modeling of the 3 facets of collaboration (production, coordination and communication) under the normative perspective. We present the first designing steps, which draws on the JaCaMo framework, together with an application example to simple scenarios.

2016 49th Hawaii International Conference on System Sciences (HICSS), 2016

This paper describes an agent based approach for simulating the control of an air pollution crisi... more This paper describes an agent based approach for simulating the control of an air pollution crisis. A Gaussian Plum air pollution dispersion model (GPD) is combined with an Artificial Neural Network (ANN) to predict the concentration levels of three different air pollutants. The two models (GPM and ANN) are integrated with a MAS (multi-agent system). The MAS models pollutant sources controllers and air pollution monitoring agencies as software agents. The population of agents cooperates with each other in order to reduce their emissions and control the air pollution. Leaks or natural sources of pollution are modelled as uncontrolled sources. A cooperation strategy is simulated and its impact on air pollution evolution is assessed and compared. The simulation scenario is built using data about Annaba (a city in NorthEast Algeria). The simulation helps to compare and assess the efficiency of policies to control air pollution during crises, and takes in to account uncontrolled sources.

Lecture Notes in Business Information Processing, 2015

The paper describes a MAS (multi-agent system) simulation approach for controlling PM10 (Particul... more The paper describes a MAS (multi-agent system) simulation approach for controlling PM10 (Particulate Matter) crisis peaks. A dispersion model is used with an Artificial Neural Network (ANN) to predict the PM10 concentration level. The dispersion and ANN models are integrated into a MAS system. PM10 source controllers are modelled as software agents. The MAS is composed of agents that cooperate with each other for reducing their emissions and control the air pollution peaks. Different control strategies are simulated and compared using data from Annaba (North-East Algeria). The simulator helps to compare and assess the efficiency of policies to control peaks in PM10.

The emergence of mixed agent-human societies poses challenges in designing companion agents that ... more The emergence of mixed agent-human societies poses challenges in designing companion agents that are able to form meaningful relationships with humans. This paper describes the first step in developing companion agents. Problem/situations have been identified where companion agents may provide important social contact with humans. Based on a scenario, interactions between human and artificial agents have been modelled in the Brahms modelling and simulation environment. This provides us with a far deeper understanding of the roles that a companion agent should fulfil and how it could switch from one social role to another.

Lecture Notes in Computer Science, 2003

Until recently virtual applications rarely incorporated any deep social, cultural or emotional ca... more Until recently virtual applications rarely incorporated any deep social, cultural or emotional capabilities exhibited in normal human interaction. In this paper, we present a methodology to develop virtual actors with believable communications skills who may provide a sufficient feeling of immersion to reproduce an efficient simulation of human activities. We focus on the relationship between gestures and verbal activities during communicative acts. We will show that an approach based on video analysis is valuable for the design of a system allowing realistic interactions between the avatars and/or the avatars and the environment. Although the analysis is still in progress, we present some preliminary results from our experiments.