PhD: Toward Organic Ambient Intelligence ? EMMA
Under the supervision of Pr Cyrille Bertelle at LITIS, MIT Medialab, ECE Paris
[Thesis] [Slides] [Defense] ISBN: 978-3-8417-4260-5

The Ambient Intelligence (AmI) is a research area investigating AI techniques to create Responsive Environments (RE). Wireless Sensor and Actor Network (WSAN) are the supports for communications between the appliances, the deployed services and Human Computer Interface (HCI). This thesis focuses on the design of RE with autonomic properties i.e. system that have the ability to manage themselves.

Such environments are open, large scale, dynamic and heterogeneous which induce some difficulties in their management by monolithic system. The bio-inspired proposal considers all devices like independent cells forming an intelligent distributed organism. Each cell is programmed by a DNA-RNA process composed of reactive rules describing its internal and external behaviour. These rules are modelled by reactive agents with self-rewriting features offering dynamic reprogramming abilities.
The EMMA framework is composed of a modular Resource Oriented Architecture (ROA) Middleware based on IPv6 LoW Power Wireless Area Networks (6LoWPAN) technology and a MAPE-K architecture to design multi-scale AmI. The different relations between technical issues and theoretical requirements are discussed through the platforms, the network, the middleware, the mobile agents, the application deployment to the intelligent system. Two algorithms for AmI are proposed: an Artificial Neural Controller (ANC) model for automatic control of appliances with learning processes and a distributed Voting Procedures (VP) to synchronize the decisions of several system components over the WSAN.

International Journals

The Networked Sensory Landscape: Capturing and Experiencing Ecological Change Across Scales
Presence: Teleoperators and Virtual Environments. 182-209 MIT Press, May 2017. DOI 10.1162/PRES\_a\_00292
Brian Mayton, Gershon Dublon, Spencer Russell, Evan F. Lynch, Don Derek Haddad, Vasant Ramasubramanian, Clement Duhart, Glorianna Davenport and Joseph A. Paradiso

What role will ubiquitous sensing play in our understanding and experience of ecology in the future? What opportunities are created by weaving a continuously sampling, geographically dense web of sensors into the natural environment, from the ground up? In this article, we explore these questions holistically, and present our work on an environmental sensor network designed to support a diverse array of applications, interpretations, and artistic expressions, from primary ecological research to musical composition. Over the past four years, we have been incorporating our ubiquitous sensing framework into the design and implementation of a large-scale wetland restoration, creating a broad canvas for creative exploration at the landscape scale. The projects we present here span the development and wide deployment of custom sensor node hardware, novel web services for providing real-time sensor data to end user applications, public-facing user interfaces for open-ended exploration of the data, as well as more radical UI modalities, through unmanned aerial vehicles, virtual and augmented reality, and wearable devices for sensory augmentation. From this work, we distill the Networked Sensory Landscape, a vision for the intersection of ubiquitous computing and environmental restoration. Sensor network technologies and novel approaches to interaction promise to reshape presence, opening up sensorial connections to ecological processes across spatial and temporal scales.

A Resource Oriented Framework for Service Choreography over Wireless Sensor and Actor Networks
International Journal of Wireless Information Networks, 2016,
Duhart Clément, Sauvage Pierre and Bertelle Cyrille

Current Internet of Things (IoT) development requires service distribution over Wireless Sensor and Actor Networks (WSAN) to deal with the drastic increasing of network management complexity. Because of the specific constraints of WSAN, some limitations can be observed in centralized approaches. Multi-hop communication used by WSAN introduces transmission latency, packet errors, router congestion and security issues. As it uses local services, a model of decentralized services avoids long path communications between nodes and applications. But the two main issues are then to design (1) the composition of such services and to map (2) them over the WSAN. This contribution proposes a model for decentralized services based on Resource Oriented Architecture in which their communications are designed thanks to an adaptation of Petri Network (1). In addition, the problem of decentralized service mapping and its deployment over a WSAN is successfully resumed by a Pseudo-Boolean Optimization in order to minimize network communication load (2). These contributions are presented using a proposed EMMA middleware as unifying thread.

Toward Organic Computing Approach for Cybernetic Responsive Environment
International Journal of Ambient Systems and Applications (IJASA), december 2015, Volume 3, Number 4. DOI:10.5121/ijasa.2015.3401.
Duhart Clément and Bertelle Cyrille

The developpment of the Internet of Things (IoT) concept revives Responsive Environments (RE) technologies. Nowadays, the idea of a permanent connection between physical and digital world is technologically possible. The capillar Internet relates to the Internet extension into daily appliances such as they become actors of Internet like any hu-man. The parallel development of Machine-to-Machine communications and Arti cial Intelligence (AI) technics start a new area of cybernetic. This paper presents an approach for Cybernetic Organism (Cyborg) for RE based on Organic Computing (OC). In such approach, each appli-ance is a part of an autonomic system in order to control a physical environment. The underlying idea is that such systems must have self-x properties in order to adapt their behavior to external disturbances with a high-degree of autonomy.

Peer Review Conferences

Methodology for Artificial Neural Controllers on Wireless Sensor Network
IEEE ICWiSe 2014 International Conference on Wireless Sensors, novembre 2014
Duhart Clément and Bertelle Cyrille

Wireless Sensor Network (WSN) is composed of autonomous devices which collaborate  to manage an environment. In this paper, distributed Artificial Neural Network (ANN) learning process methodology is investigated to control such environments. After studying ANN complexity to learn several functioning scenarios, a distributed Neural Voting Procedure is proposed to select the most adapted ANN according to decision-making of all nodes. Finally, the use of several Artificial Neural
Controller (ANC) with an arbitration procedure is prefered to the use of one single ANC regarding to execution and deployment costs on the WSN.

Wireless Sensor Network Cloud Services: Towards a Partial Delegation
IEEE SaCoNeT 2014 The 5th International Conference on Smart Communications in Network Technologies, June 2014
Duhart Clément, Cotsaftis Michel and Cyrille Bertelle

Current emerging technologies in Wireless Sensor Networks are providing protocols and operating systems to build up the Internet Of Things which heads towards SaaS approach in the Cloud. However, this paper discusses about the impossibility to directly route all nodes from the Cloud. Hence, this paper proposes a new framework based on mobile agents to distribute and deploy applications over a CoAP middleware. This is mainly performed using a distributed publish-subscribe mechanism on each node. The solution allows agents to model distributed applications and their remote deployments.

Lightweight Distributed Adaptive Algorithm for Voting Procedures by Using Network Average Consensus
Springer PRIMA 2013: Principles and Practice of Multi-Agent Systems, décembre 2013
Duhart Clément, Cotsaftis Michel and Cyrille Bertelle

Consensus Seeking is an important research area in which this work contributes by proposing a new distributed algorithm to solve Voting Procedure problems in mobile networks with link failures under strong constraints on communication capacity.

Approches Multi-Agents pour la Conception de Systèmes de Détection, de Prévention et de Réponse aux Intrusions.
Duhart Clément – – 2011

Le développement permanent des systèmes d’information a comme corollaire une augmentation significative des attaques réseaux. Le caractère vital des données qui transitent sur ces réseaux implique une nécessité de protection et de sûreté. Ce rapport s’intéresse à l’étude d’architectures basées sur des modèles multi-agents permettant la détection, la prévention et éventuellement la réponse du système protégé face à une situation d’intrusion. A partir d’un corpus non exhaustif de publications dans le domaine, ce document présente les différentes réponses actuelles pour traiter les problèmes d’intrusions ainsi que leurs limites.


Conference Talks

A Ubiquitous Sensing Model for Environmental Science, Interaction Research, and Public Engagement with Restored Wetlands SWS 2017: Society of Wetland Scientists. Brian Mayton, Gershon Dublon, Spencer Russell, Evan F. Lynch, Don Derek Haddad, Vasant Ramasubramanian, Clement Duhart, Glorianna Davenport, Joseph A. Paradiso (MIT Media Lab and Living Observatory) Puerto Rico, USA, June 2017.