Posts tagged "iot"

Dynamic Learning of the Environment for Eco-Citizen Behavior

Context Presentation

The development of sustainable smart cities requires the deployment of Information and Communication Technology (ICT) to ensure better services and available information at any time and everywhere. As IoT devices become more powerful and low-cost, the implementation of an extensive sensor network for an urban context can be expensive.

This thesis addresses the problem of estimating missing information in urban contexts. The objective is to estimate accurate environmental information where physical sensors are not available. The proposed solution, HybridIoT, uses the Adaptive Multi-Agent System (AMAS) to estimate accurate environmental information under conditions of uncertainty arising from the urban application context in which the project is applied, such as openness, heterogeneity and large-scale, which have not been explored by the state-of-the-art solutions.

illustration - Davide Guastella

Keywords

Smart city, Cooperative Multi-Agent Systems, Missing Information Estimation, Heterogeneous Data Integration

Scientific goals

- Limiting the number of ad hoc devices to be deployed in an urban environment

- The exploitation of heterogeneous data acquired from mobile, intermittent devices

- Real-time processing of information

- Self-calibration of the system

Contacts

davide.guastella@irit.fr, Marie-Pierre.Gleizes@irit.fr, valerie.camps@irit.fr

Toward a Smart IoT Services Placement in the Fog

Context Presentation

Fog computing has emerged as a strong distributed computation paradigm to support applications with stringent latency requirements. It offers almost ubiquitous computation capacities over a large geographical area. However, Fog systems are highly heterogeneous and dynamic which makes IoT services placement decision quite challenging considering nodes mobility that may decrease the placement decision quality over time.

IoT-Fog Services placement problem needs to be thoroughly investigated to ensure the efficiency of such environments. In this thesis, we consider various parameters such as nodes mobility, energy efficiency and applications Quality of Service (QoS) requirements to propose efficient strategies for IoT services placement in the Fog.

image - tanissia DJEMAI

Keywords

Internet of Things, Optimization, Mobility, Fog Computing, QoS, Energy.

Scientific goals

•    Propose efficient approaches for IoT applications (services) placement in the Fog,

•    Analyze their impact on the energy consumption of Fog infrastructures and the Quality of Service (QoS) of  applications.

Contacts

tanissia.djemai@irit.fr, patricia.stolf@irit.fr, monteil@laas.fr, jean-marc.pierson@irit.fr

myGates

Context Presentation

MyGates is a part of autOCampus project to experiment and validates the smart mobility particularly for electrics, connected and autonomous vehicles in a dense urban environment.

In that way, a gates management system for autonomous vehicles will make easier experiments. It combines an automatic license plate with a car model recognizer to make it usable for classic car. It also contains database to keep information over authorized car and application designed for security officer to give temporary authorization for delivering driver with a photo of the vehicle and the plate.

MyGates is designed to be added on existing gates and only create the automation system with SALTO automaton that already are managing gates. MyGates will belong to the AIoT platform that will come out in the regional platform of research and innovation (PRRI) context containing smart camera and other smart devices.

mygates - Vincent-Nam Dang

Keywords

Autonomous Vehicles, Gates, CNN, ALPR, Salto, Nvidia Jetson Nano, autOCampus

Scientific goals

•    Create automatic and connected gates managements with plate and car model recognition

•    Create a classifier with many classes that are very similar

Contacts

vincent-nam.dang@irit.fr, thiebolt@irit.fr

 

accessOCampus - A Universal Access System for Smart Doors and Gates

Context Presentation

On site access control exists almost everywhere in today's modern world. Keys have already been replaced by access cards in most places but accessOCampus aims to improve on these existing systems even more.

For less than 200€ (excluding the optional thermal camera) an accessOCampus client module can be built, this includes : NFC access card recognition, passcode entry, face recognition and a large screen for access related information. The system can also be locked down or forced open globally by an authorized security personnel via the easy to use web interface.

In theory, accessOCampus can be used to log who has entered any given zone and provide detailed information on those people. For instance, if any given access card is stolen we can detect who used it via face recognition either silently or to refuse access.This project could be implemented in select zones of Toulouse University to provide a low-cost high fidelity access system.

IMG_20200624_103950 - Sebastian Lucas

Keywords

neOCampus, IOT, Smart Building, Security, Access, Face Recognition

 Scientific goals

•    Provide a high security solution to restricted zones

•    Facilitate zone entry for the end user via face recognition•    Display easy to understand information

Contacts

gomme600@hotmail.com, Francois.Thiebolt@irit.fr

SANDMAN: a Multi-Agent System for Anomaly Detection in Smart Buildings

Context Presentation

The number of sensors in buildings is constantly increasing, thanks to more accessible costs and the obvious interest of their use for optimized management. In this thesis we are interested in the use of data from these sensors to detect anomalies in buildings. These data, which are very numerous, can be of unknown and heterogeneous types.An anomaly is defined as unexpected and undesirable behaviour in a system and may depend on the context. In order to be able to deploy an anomaly detection system as widely as possible, it is necessary to create a decision support tool for energy experts. To address these issues, a system based on cooperative multi-agent systems implementing AMAS theory is being developed that allows anomalies to be detected by supervised learning. The anomaly detection system must take advantage of the feedback from one or more experts who label certain instances as anomalies or non-anomalies. These feedback are used for learning. The system we develop allows the addition or removal of new sensors without interrupting the detection of anomalies.

image016

 

The system classifies situations

 

Scientific Goals

- Improve energy efficiency

- Detect anomalies in real time

- Learn continuously from the expert feedback

Keywords

Multi-Agent Systems, Smart Buildings, Internet of Things, Supervised Learning, Anomaly Detection

Contacts

Maxime.houssin@irit.fr

 

 

Déploiement de services autonomiques dans un contexte IoT

Au cours des dernières années, l'Internet des objets (IoT) a évolué à une vitesse exceptionnelle permettant ainsi de connecter un nombre important d'objets hétérogènes (capteurs, actionneurs, smartphone, application, etc.). Les domaines d'applications sont ainsi très larges avec des applications industrielles (usine du futur), dans les collectivités (villes intelligentes, campus intelligent), écologiques et économiques (gestion de l'énergie) ou bien encore individuels (aide au diagnostic médical, confort de vie, domotique). De nombreux verrous sont à lever en terme de recherche notamment dû au nombre d’entités important (potentiellement plusieurs milliers, millions, milliards d’objets), à la quantité d’information « brut » générée et au besoin de construire de nouveaux usages à base de nouveaux services les plus intelligents possibles le tout sous des contraintes de qualité de service variées. Cette thèse se concentrera plus particulièrement sur ce dernier point. Les infrastructures à mettre en place pour déployer une architecture IoT font l’objet de travaux dans les organismes de standardisation (ETSI, OneM2M, etc) ou consortium industriel (OCF, OMA, etc) avec actuellement un rapprochement sensible vers les architectures de type fog ou edge computing (EdgeX). Le modèle classique de l’IoT amenant les devices à envoyer des informations via les gateways au cloud qui ensuite fournit les services aux applications trouve des extensions dans l’approche fog ou edge permettant de rapprocher les services au plus proche des usagers en s’appuyant notamment sur les gateways.

S3P6

Figure 1 : « IoT services placement  in a Fog computing infrastructure »

Objectifs scientifiques

 L’objectif de la thèse est de concevoir un Framework autonome et intelligent pour  le placement et l’orchestration des services d’applications IoT sur une infrastructure hautement distribuée, dynamique et hétérogène , le but est de pouvoir  prendre en compte différents critères de qualité de services (QoS) et les coûts énergétiques  avec une gestion des  differents niveaux de virtualisation ( conteneur,VM, OSGi etc.) et une tolérance au passage à l’échelle, aux changements de contexte (etat et performances du réseau, mobilité utilisateurs), aux pannes et au anomalies.

Contacts

tanissia.djemai@irit.fr, patricia.stolf@irit.fr, jean-marc.pierson@irit.fr, monteil@laas.fr

 

Stratégies de caching dans l’Internet des Objets

La prolifération des objets connectés et la demande croissante d’une distribution fondée sur le contenu ont motivé le développement d'approches centrées sur les données. De nos jours, les personnes utilisent leurs appareils pour partager leurs propres contenus et ils sont intéressés par d’autres contenus sans avoir à se soucier de leur localisation. Pour faire face à cette demande, le concept de réseaux centrés sur l'information «Information-Centric Networking» a vu le jour. ICN propose une nouvelle architecture où les contenus sont récupérés en utilisant des noms de contenus uniques à la place des adresses de nœuds. Cette approche peut fournir un service d'infrastructure de réseau mieux adapté à l'utilisation actuelle en termes de distribution de contenus, de mobilité et de défaillances dans l’Internet des objets.

L’objectif de ce stage est de proposer une stratégie de caching qui tient compte des limitations des réseaux de capteurs. L’idée est d’utiliser des techniques de placement de données permettant de réduire les temps de réponses ainsi que l'énergie consommée par le réseau. 

S3P2

Figure 1 : « Stratégie de caching qui consiste à cacher sur la moitié du trajet »

Objectifs scientifiques

Les objectifs du stage sont :

 Etude des stratégies de caching existantes dans les réseaux de capteurs 

 Proposer une stratégie optimale pour le placement des contenus

 Evaluation de performance (Consommation d’énergie, diversité, stretch, délais, …)

 

Contacts

Ilyes.Fathallah@irit.fr, Ghada.Jaber@irit.fr, Rahim.Kacimi@irit.fr

 

 

Back to Top