Véronique Deslandres

Véronique Deslandres
Claude Bernard University Lyon 1 | UCBL · Laboratoire d'informatique en images et systèmes d'information (LIRIS)

PhD in Computer Sciences - Artificial Intelligence

About

29
Publications
3,929
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
172
Citations
Introduction
My current research interests are in the simulation of urban policies with a realistic modelling of citizen behavior using multi-agent structures and reinforcement learning. The goal is to predict the impact of the policy and provide urban manager assistance to various adjustment and tests. We're using decentralized learning methods adapted to and a multiagent, multi-level solution named Clustered Deep Q-Network (CDQN) to override the non-stationarity and scalability issues.

Publications

Publications (29)
Conference Paper
Abstract Designing a public urban policy is a demanding process which requires both time and money with no warranty of its efficiency. It involves knowledge about the purpose of urban design, behaviors of users and needs in terms of mobility. We believe that in the near future, decision makers will have to react and more frequently adapt public po...
Chapter
This chapter presents the results of a project known as Aires de Livraison du Futur (ALF) conducted by three academic research teams namely, LIRIS SILEX, LIRIS GrAMA and LET, two SMEs- Interface Transport and SEMCO, one large group-Volvo and a local authority-Grand Lyon. Delivery services are increasing due to just-in-time management, the developme...
Book
Le but du projet est d'améliorer la livraison (et la collecte) des marchandises en ville en appliquant aux aires de livraison la démarche de réservation des salles de réunions. Outre la réservation préalable, faite par un logisticien/exploitant transport, l'ajustement par le chauffeur-livreur doit être possible pour lui permettre de tenir compte de...
Book
A system for reserving Delivery Areas and adjusting the reservation during the delivery journey
Conference Paper
Full-text available
This paper presents a research project named ALF (Aires de Livraison du Futur, Next Generation Delivery Areas). The project purpose is to increase the use of delivery areas by prior booking by professional delivery operators, and make dynamic adjustment of their booking, if necessary. Information technologies with mobile communicating devices and i...
Article
In this paper, a framework for clustering clinical pathways is proposed which is based on a hybrid model that uses the recent b-colouring clustering approach coupled with Markov chain models. The approach allows firstly associating each cluster with a set of dominant sequences which guarantee robust partitioning and gives a solution to the cluster...
Article
Full-text available
The graph b-coloring is an interesting technique that can be applied to various domains. The proper b-coloring problem is the assignment of colors (classes) to the vertices of one graph so that no two adjacent vertices have the same color, and for each color class there exists at least one dominating vertex which is adjacent (dissimilar) to all oth...
Chapter
Full-text available
In our current approach we employ a greedy strategy tackle the re-coloring problem defined in Section 4.1. The major reasons for utilizing a greedy strategy is, as in other many approaches based on some greedy algorithms, we believe that it is useful as well as crucial for handling real world data, especially for large scale data. Based on this hyp...
Conference Paper
Full-text available
Cluster analysis is one of the most important aspects in the data mining process for discovering groups and identifying interesting distributions or patterns over the considered data sets. A new method for sequences clustering and prediction is presented in this paper, which is based on a hybrid model that uses our b-coloring based clustering appro...
Conference Paper
We consider the problem of dynamic clustering which has been addressed in many contexts and applications including dynamic information retrieval, Web documents classification, etc. The goal is to efficiently maintain homogenous and well-separated clusters as new data are inserted or existing data are removed. We propose a framework called dynamic...
Conference Paper
Full-text available
Face with an increasing demand of activity analysis and assessment tools for hospital centers (HC), a decision support system is proposed for health care professionals. The system provides aid in analyzing and predicting health care pathways of patients (each clinical pathway being described by several hospital stays of one patient in various HC)....
Conference Paper
This paper proposes a new greedy algorithm to improve the specified b-coloring partition while satisfying b-coloring property. The b-coloring based clustering method in [3] enables to build a fine partition of the data set (classical or symbolic) into clusters even when the number of clusters is not pre-defined. It has several desirable clustering...
Article
To date, quality control methods remain underutilized in a number of companies due to the amount of knowledge required for their selection and implementation. A knowledge-based advisory system called SYSMIQ (SYStème pour la Maîtrise Intelligente de la Qualité, i.e., intelligent system for quality control) has now been developed to assist decision m...
Conference Paper
Graph coloring is used to characterize some properties of graphs. A b-coloring of a graph G (using colors 1,2,...,k) is a coloring of the vertices of G such that (i) two neighbors have different colors (proper coloring) and (ii) for each color class there exists a dominating vertex which is adjacent to all other k-1 color classes. In the French hea...
Conference Paper
Full-text available
Graph coloring is used to characterize some properties of graphs. A b-coloring of a graph G (using colors 1,2,...,k) is a coloring of the vertices of G such that (i) two neighbors have different colors (proper coloring) and (ii) for each color class there exists a dominating vertex which is adjacent to all other k-1 color classes. In this paper, ba...
Article
Full-text available
This paper initially introduces specificities of small and medium enterprises (SME) networks, then deals with the recent evolution of the Knowledge Management (KM). In coherence with this evolution, we describe a knowledge management process based on a community of practices which can be applied to these types of groups. The main conclusion is that...
Article
Full-text available
Companies are now economically bound to collaborate with other enterprises, forming horizontal networks that are generally goal-based and are of a limited duration. This article specifically addresses networks of industrial small and medium enterprises (SMEs). Thanks to a five-years study, some of the main characteristics of such networks will be c...
Article
Implementation of formal quality policy in manufacturing environments requires extensive knowledge in many different fields: (1) knowledge of the problems that can be found; (2) knowledge of the methods and procedures that can definitively improve the process; (3) knowledge of the quality techniques that can be used; and (4) how to implement these...

Network

Cited By

Projects

Projects (6)
Project
Multi-agent learning in partially observed environments for self-adaptation capabilities
Project
Future smart cities will be provided with a huge amount of data, which could be exploited for the design and adaptation of urban policies Specific AI techniques could help to co design and self-adapt such policies.
Archived project
Works around inter-firm cooperation before the social network vague