Valorisez vos réalisations phares sur People@HES-SO Plus d'infos
PEOPLE@HES-SO – Annuaire et Répertoire des compétences
PEOPLE@HES-SO – Annuaire et Répertoire des compétences

PEOPLE@HES-SO
Annuaire et Répertoire des compétences

Aide
language
  • fr
  • en
  • de
  • fr
  • en
  • de
  • SWITCH edu-ID
  • Administration
« Retour
Sokhn Maria

Sokhn Maria

Professeur-e HES ordinaire

Compétences principales

Digital Transformation

Knowledge Management

Data Analysis

Information Retrieval

Gamification

  • Contact

  • Enseignement

  • Recherche

  • Publications

  • Conférences

Contrat principal

Professeur-e HES ordinaire

Haute Ecole Arc - Gestion
Espace de l'Europe 21, 2000 Neuchâtel, CH
DECO

HES-SO Master
Av. de Provence 6, 1007 Lausanne, CH
SO Master
Domaine
Economie et services
Filière principale
Master of Science en Business Administration
MSc HES-SO en Business Administration - HES-SO Master
BSc HES-SO en Informatique de gestion - Haute Ecole Arc - Gestion

En cours

SwissRenov - - Circularité et préservation des ressources dans la réhabilitation des bâtiments en Suisse, une opportunité pour les friches industrielles

Rôle: Co-requérant(s)

Financement: innosuisse

Description du projet :

Par une approche globale, il est possible d’optimiser l'utilisation des ressources locales et de minimiser l'impact environnemental lors de la planification, la rénovation et la réhabilitation de bâtiments en Suisse en tirant parti du potentiel de ressources des friches industrielles.

Partenaires universitaires: HEIG-VD, HEIA-FR, HEPIA-GE, UNINE, FHNW, UNIBAS, BFH
Partenaires chargés de la mise en œuvre impliquées: 22

Equipe de recherche au sein de la HES-SO: Sokhn Maria

Durée du projet: 15.01.2024

Statut: En cours

SUDAC 2 - Dear Mena (2021-2024)
AGP

Rôle: Co-requérant(s)

Financement: HES-SO Rectorat; Université de Genève; VS - Institut Systèmes industriels; Universität Zurich; Digitalisation des organisations; Swissuniversities; EPFL; Swisspeace; Zurich University of Teacher Education; Università della svizzera ita

Description du projet : The second phase of SUDAC (2021-24) consolidates the network of cooperation in Switzerland and accomplish its extension in the Global South. SUDAC-2 also enlarges the circle of potential beneficiaries of the infrastructure created by SUDAC both in Switzerland and in the Global South. The following objectives are targeted: 1) The consolidation of the CLOCs: CLOCs should develop into a "public good" open to other Swiss institutions interested in partnering up for research or education projects in the respective region. Local partners will be included in a proper way in these processes, particularly regarding the thematic agenda and to the exchanges between research, education and policy actors. 2) Secure structural funding for partners in the Global South: While the consolidation of the network in Switzerland will rely to a large extent on self-funding by the participating institutions, the contributions to the partners in the Global South and also the interactions between them and the Swiss partners will continue to need additional funding. CLOCs will work on attracting third-party co-funding to increase their sustainability. 3) Transfer the platform of SUDAC into a sustainable structure: At the end of SUDAC-2, the network in Switzerland and the CLOCs will work as "public goods" for further Swiss partners interested in developing education and/or research activities together with academic and non-academic partner institutions in the Global South. SUDAC will assure continued commitment of existing partners and a long-term involvement of Swiss institutions in the fields of research, education, and development.

Equipe de recherche au sein de la HES-SO: Vaccari Aldo , Oswald Philippe , Moghaddam Fariba , Sokhn Maria , Pompili Valérie , Forestal Maël , Rouiller Maxime , Lenoir Cédric

Durée du projet: 01.07.2021 - 30.06.2025

Montant global du projet: 575'000 CHF

Statut: En cours

Digital Arc Hub

Rôle: Requérant(e) principal(e)

Financement: LPR arcjurassien

Description du projet :

À l’heure actuelle, la numérisation n'est plus une option, mais un impératif pour les organisations. La puissance du numérique et les avantages du passage au digital sont considérés comme une opportunité par de nombreuses entreprises dans tous les secteurs. Les entreprises ne doivent plus se contenter d’offrir des produits mais également de s’armer de services compatibles avec l’ère du digital. Un des enjeux majeurs devient ainsi le développement de ces services compatibles qui soutiennent les entreprises dans leur évolution et leur ancrage au sein d’un territoire 4.0. Avant de débuter sa transformation numérique, l’entreprise doit connaître sa maturité digitale. C’est ensuite qu’elle pourra définir une stratégie adaptée.

Le digital arc hub vise à répondre à ces besoins à travers une plateforme au service de la transformation digitale des organisations de l’ensemble du territoire de l’Arc Jurassien. Cette plateforme s’adresse à trois acteurs principaux, les entreprises œuvrant sur le territoire de l’arc jurassien notamment les PMEs, les décideurs et les organisations de recherche. Concrètement le Digital arc hub adressera les aspects suivants : la conception et le développement d'un outil d’auto-diagnostic permettant de mesurer la maturité digitale des entreprises de l’arc jurassien sur la base de modèles de praticiens et d’un outil de visualisation des données provenant de l’outil d’auto-diagnostic.

Equipe de recherche au sein de la HES-SO: Sokhn Maria

Partenaires académiques: Jeanneret Maximiliano, HEG Arc

Durée du projet: 01.09.2019 - 01.08.2021

Statut: En cours

Collective memory

Rôle: Requérant(e) principal(e)

Financement: innosuisse

Description du projet :

Solution based on the combination of user engagement mechanisms with AI algorithms.

Currently, the process of making knowledge accessible and actionable is still time-consuming and not attractive for users. To improve this process and enhance employees experience, PICC-IA proposes a solution based on the combination of user engagement mechanisms with AI algorithms is proposed.

Equipe de recherche au sein de la HES-SO: Sokhn Maria

Statut: En cours

Terminés

Activities-based job matching system

Rôle: Co-requérant(s)

Financement: Innosuisse

Description du projet :

Plus d’un tiers des chômeurs en Suisse sont des chômeurs de longue durée, alors que certaines branches comptent davantage de places vacantes que de chômeurs. Nous souhaitons proposer une solution innovante d’appariement optimal des offres et demandes d'emploi qui ne prend pas appui sur les traditionnelles qualifications et compétences requises, mais sur une documentation du travail demandé et offert (lequel est généralement peu explicité) au moyen d'un référentiel d’activités. Cette documentation s'inscrit dans un accompagnement des employeurs et des demandeurs d'emploi permettant de se recentrer sur le besoin effectif de l'employeur tout en contournant les représentations qui freinent l'embauche des chômeurs de longue durée.

La solution comprend :
- une méthodologie de documentation des offres et demandes,
- un système d’information (SI) opérant l’appariement optimal,
- la formation des agents appelés à utiliser le SI et à accompagner employeurs et chômeurs.
Elle nécessite :
- une recherche qualitative pour l’élaboration d’un référentiel d’activités selon la méthode du profil expérientiel.
- une solution numérique développée selon une approche ergonomique, soumettant des propositions d'appariement hiérarchisées selon l'effort requis de part et d'autre, avec enrichissement continuel du référentiel (active learning, web sémantique).
- une ingénierie collaborative associant des employeurs, des chômeurs et des agents du placement professionnel à ce projet.
Le plan de développement prévoit l’ouverture d’une agence d’inclusion commune aux organisations membres de notre association. Utilisant la solution développée, elle contribuera à réduire les coûts sociaux du chômage tout en offrant des perspectives aux chômeurs de longue durée. Elle vise un taux de réponse aux offres d'emploi de 75% (ORP aujourd'hui : 55%) ainsi qu'un taux de placement durable de 75% (aujourd'hui : non disponible mais estimé à moins de 50%). Dès qu’elle aura fait ses preuves, la solution sera offerte à d’autres entités.

Equipe de recherche au sein de la HES-SO: Maeder Pascal , Rullac Stéphane , Sokhn Maria , Roland Julien

Partenaires professionnels: Cornut, Michel, Association cantons zéro chômeurs de très longue durée

Durée du projet: 01.01.2021 - 30.11.2023

Montant global du projet: 470'000 CHF

Statut: Terminé

DIVERsité-Genre-EnseignemenT
AGP

Rôle: Co-requérant(s)

Financement: Digitalisation des organisations

Description du projet : Voir dossier

Equipe de recherche au sein de la HES-SO: Martin Hélène , Konan N'Dri Paul , Sokhn Maria , Pellaton Camille , Unternährer Charline , Venzin Jonas

Partenaires académiques: HES-SO Rectorat; VS - Institut Informatique; Santé et Social

Durée du projet: 01.10.2018 - 31.03.2020

Montant global du projet: 222'742 CHF

Statut: Terminé

Vaud Integration Vulnerabilities REsponses (VIVRE)
AGP

Rôle: Co-requérant(s)

Description du projet : Voir dossier

Equipe de recherche au sein de la HES-SO: Steiger Bhama , Liu Zhan , Sokhn Maria , Glassey Balet Nicole , Pellaton Camille , Schnorf Martin

Partenaires académiques: BREF-2015

Durée du projet: 01.01.2018 - 31.12.2019

Montant global du projet: 144'600 CHF

Statut: Terminé

LINDAS : technische Unterstützung "Stabilisierungsphase" 2016/2017 - SECO
AGP

Rôle: Collaborateur/trice

Requérant(e)s: VS - Institut Informatique

Financement: SECO

Description du projet : Der Basisdienst LINDAS stellt eine Linked Data lnfrastruktur für die offentliche Verwaltung zur Verfugung und befindet sich seit Marz 2015 im Pilotbetrieb. Diverse Use Cases wurden seither umgesetzt respektive befinden sich in Umsetzung. Die vielfaltigen Moglichkeiten und die Vorteile von Linked Data insbesondere hinsichtlich Datenintegration und Datenpublikation zeigen sich bereits in den ersten Use Cases, z.B. das historisierte Gemeindeverzeichnis des BFS oder die Umweltdaten des BAFU. Der Pilotbetrieb muss in einer nachsten Phase stabilisiert werden. Diese «Stabilisierungsphase» dauert von Mitte 2016 bis Ende 2017 und lässt sich grob in die folgenden Teilbereiche gliedern: ' Umsetzung der geplanten Use Cases, ' Technische Stabilisierung und Ausbau LINDAS, ' Laufende Betriebsunterstutzung, ' Vorbereitungen Betriebsübergabe und technische Voraussetzungen für einen späteren Weiterausbau durch Dritte.

Equipe de recherche au sein de la HES-SO: Cretton Fabian , Evéquoz Florian , Liu Zhan , Sokhn Maria , Le Calvé Anne , Shabani Shaban , Beuchat Jean-Luc , Jungius Christiane

Partenaires académiques: VS - Institut Informatique

Durée du projet: 01.11.2016 - 31.12.2019

Montant global du projet: 98'980 CHF

Statut: Terminé

City-Stories : spatio-temporal search over crowdsourced content - HaslerStiftung
AGP

Rôle: Requérant(e) principal(e)

Financement: Fondation Hasler

Description du projet : A driving force behind the development of novel services tailored to the needs of citizens is the increasing flexibility of social time. Even though city residents may possess valuable information for other citizens visiting their home area, it is hardly usable with today's information systems because of the inevitably scattered information resources. Considering the explosive growth of information, knowledge sharing can ensure valuable interdisciplinary applications and services development. While many organizations propose relevant data sets, they are hardly accessed, analyzed and reused in an integrated way 'despite of the enormous added value such integration would have' because of the heterogeneity of formats, the lack of interoperability, and the inappropriate support for information browsing and visualization. The City-Stories platform for data crowdsourcing and spatio-temporal knowledge visualization will overcome these limitations by jointly addressing three tightly coupled challenges. First, data integration responsible for locating, extracting, and syntactically aligning heterogeneous data. Second, novel approaches to spatio-temporal multimedia search and browsing on top of the integrated data, providing users new perspectives and query types to explore these data. Third, the knowledge crowdsourcing and visualization responsible for gathering users' content and enrich this content with linked data services, in order to offer a novel way of knowledge visualization.

Equipe de recherche au sein de la HES-SO: Sokhn Maria , Shabani Shaban

Partenaires académiques: Université de Fribourg; VS - Institut Informatique; University of Basel; Sokhn Maria, VS - Institut Informatique

Durée du projet: 01.01.2016 - 31.12.2018

Montant global du projet: 392'700 CHF

Statut: Terminé

CrowDPLOS : Disabled pedestrian level of service extracted from crowdsourced images
AGP

Rôle: Collaborateur/trice

Requérant(e)s: VS - Institut Informatique, Cotting Alexandre, VS - Institut Informatique

Financement: Fondation Hasler

Description du projet : CrowDPLOS : Disabled pedestrian level of service extracted from crowdsourced images

Equipe de recherche au sein de la HES-SO: Divorne Sandrine , Rojas Diego , Loubier Jean-Christophe , Liu Zhan , Ertz Olivier , Sandoz Romain , Blanc Nicolas , Sokhn Maria , Ingensand Jens , Shabani Shaban , Cotting Alexandre

Partenaires académiques: CE-RaD; VS - Institut Informatique; VS - Institut Tourisme; FIN-RaD; Cotting Alexandre, VS - Institut Informatique

Durée du projet: 01.04.2017 - 31.12.2018

Montant global du projet: 49'300 CHF

Statut: Terminé

Visibility Improvement for Events Webcasting (VIEW) - CTI 18378.2 PFES-ES
AGP

Rôle: Collaborateur/trice

Requérant(e)s: VS - Institut Informatique, Evéquoz Florian, VS - Institut Informatique

Financement: CTI; Klewel Sàrl

Description du projet : Klewel enregistre des présentations et les publie sur une plateforme Web. Ce projet vise à améliorer leur référencement pour permettre aux clients un meilleur retour sur investissement, et à Klewel de convertir davantage de clients. Des méthodes innovantes seront développées pour améliorer la qualité des données extraites (Deep Learning sur OCR) et générer automatiquement des mots-clés sémantiques (Active Learning sur ASR et OCR) qui seront exposés aux moteurs de recherche

Equipe de recherche au sein de la HES-SO: Cretton Fabian , Genoud Dominique , Evéquoz Florian , Liu Zhan , Sokhn Maria , Mayoraz Calixte , Treboux Jérôme

Partenaires académiques: VS - Institut Informatique; IDIAP; Evéquoz Florian, VS - Institut Informatique

Durée du projet: 01.09.2016 - 30.09.2018

Montant global du projet: 109'218 CHF

Statut: Terminé

Designing new & cross-algorithm interaction for building enterprise knowledge
AGP

Rôle: Collaborateur/trice

Requérant(e)s: VS - Institut Informatique, Le Calvé Anne, VS - Institut Informatique

Financement: CTI

Description du projet : Chèque Inno pour dévelopement chez Exelop SA

Equipe de recherche au sein de la HES-SO: Cretton Fabian , Liu Zhan , Sokhn Maria , Le Calvé Anne

Partenaires académiques: VS - Institut Informatique; Le Calvé Anne, VS - Institut Informatique

Partenaires professionnels: Exelop SA

Durée du projet: 10.10.2016 - 31.08.2018

Montant global du projet: 7'500 CHF

Statut: Terminé

Vaud Integration Vulnerabilities Responses ' VIVRE
AGP

Rôle: Collaborateur/trice

Description du projet : Voir dossier

Equipe de recherche au sein de la HES-SO: Steiger Bhama , Liu Zhan , Sokhn Maria , Glassey Balet Nicole

Partenaires académiques: HES-SO Rectorat

Durée du projet: 04.05.2018 - 04.07.2018

Montant global du projet: 23'318 CHF

Statut: Terminé

Crowdsourced map based mobile application for the wheelchair accessibility in Switzerland - ISNET 16-01
AGP

Rôle: Collaborateur/trice

Requérant(e)s: VS - Institut Informatique, Glassey Balet Nicole, VS - Institut Informatique

Financement: HES-SO Rectorat

Description du projet : Les questions et problématiques liées à l'accessibilité constituent un défi de taille pour les entreprises et collectivités publiques. Si l'expression «développement durable» est souvent associée uniquement à son pilier «environnemental», le pilier «social», notamment dans ses aspects d'équité et d'accessibilité aux personnes à mobilité réduite, reste encore souvent inexploré. L'objectif du projet est de permettre aux personnes à mobilité réduite (personnes en situation de handicap, personnes âgées, familles avec poussettes, etc.) de bénéficier d'une plus grande autonomie en ce qui concerne leurs déplacements. En effet, de nos jours, les outils de planification de voyage/déplacement porte-à-porte, proposent des parcours en voiture, en transports publics, à vélo ou encore à pied. Toutefois, aucun renseignement n'est donné concernant des parcours pour une personne à mobilité réduite. Les personnes concernées doivent elles-mêmes entreprendre leurs propres démarches pour obtenir ces informations. Le projet vise à pallier ce gap afin d'améliorer l'espace de vie des personnes à mobilité réduite. Il leur offrira une plate-forme mobile de génération d'itinéraires personnalisés et adaptés à leurs besoins. Cette plate-forme fera usage de données existantes, souvent cloisonnées dans des silos, et sera complétée/validée par des informations directement fournies par la communauté concernée. L'approche de crowdsourcing sera appliquée avec prise en compte de la mise en place innovante du Web des données via shema.org. Ce projet pilote sera étroitement mené avec des acteurs du terrain et testé dans une région touristique pilote du Valais mêlant réalité urbaine et montagne (Sierre - Val d'Anniviers).

Equipe de recherche au sein de la HES-SO: Cretton Fabian , Loubier Jean-Christophe , Liu Zhan , Sokhn Maria , Glassey Balet Nicole , Le Calvé Anne

Partenaires académiques: VS - Institut Informatique; Glassey Balet Nicole, VS - Institut Informatique

Durée du projet: 01.07.2016 - 31.01.2018

Montant global du projet: 164'700 CHF

Statut: Terminé

Transparence et Démocratie 2.0 - ES-ISNET 14-11
AGP

Rôle: Collaborateur/trice

Requérant(e)s: VS - Institut Informatique

Financement: HES-SO Rectorat

Description du projet : L'objectif de ce projet est de découvrir comment les technologies de l'information et de la communication (ICT) permettent, par l'exploitation de données brutes, d'informations ou d'indicateurs, d'améliorer la mise en oeuvre opérationnelle de politiques publiques dans une démarche d'efficience et de transparence, en mettant à disposition des pouvoirs publics (administrations et conseils communaux) et des citoyens, les outils nécessaires (ex : tableaux de bord énergétique montrant quel bâtiment consomme le plus d'électricité et où sont les pertes insoupçonnées). Ce projet s'inscrit clairement dans un contexte d'efficience administrative et d'Open Data afin de dessiner une nouvelle forme de démocratie : la démocratie 2.0.

Equipe de recherche au sein de la HES-SO: Cretton Fabian , Genoud Dominique , Evéquoz Florian , Loubier Jean-Christophe , Sokhn Maria , Rey Jean-Pierre , Trabichet Jean-Philippe , Hunacek Daniel , Maalouf Eliane , Treboux Jérôme , Cotting Alexandre , Imboden Serge

Partenaires académiques: 539,Informatique de gestion; VS - Institut Informatique; VS - Institut Entrepreneuriat & MANAGEMENT

Durée du projet: 01.03.2015 - 28.02.2017

Montant global du projet: 153'720 CHF

Statut: Terminé

Smart metering et développement durable - ES-ISNET 14-10
AGP

Rôle: Collaborateur/trice

Requérant(e)s: VS - Institut Informatique

Financement: HES-SO Rectorat

Description du projet : L'objectif de ce projet est d'analyser le potentiel de contribution au développement durable du smart metering puis de créer une plateforme web innovante qui fasse le lien entre distributeur d'énergie et client final, dans laquelle le smart metering occupe une place centrale, entouré de services à haute valeur ajoutée (BI, data analytics, prediction, business..).

Equipe de recherche au sein de la HES-SO: Emery Lionel , Latrille Sophie , Glassey Deborah , Genoud Stéphane , Evéquoz Florian , Bonazzi Riccardo , Sokhn Maria , Rey Jean-Pierre , Mastelic Joëlle , Hunacek Daniel

Partenaires académiques: VS - Institut Informatique; VS - Institut Entrepreneuriat & MANAGEMENT

Durée du projet: 01.03.2015 - 31.12.2016

Montant global du projet: 157'400 CHF

Statut: Terminé

"Sémantique et agrégation de graphes" - Private Innovation Competence Center
AGP

Rôle: Collaborateur/trice

Requérant(e)s: VS - Institut Informatique, Le Calvé Anne, VS - Institut Informatique

Description du projet : Dans le cadre du projet « Private Innovation Competence Centre (PICC) », la société Exelop souhaite développer une nouvelle fonctionnalité de recherche basée sur la sémantique linguistique. Cette nouvelle fonctionnalité permettra de créer un nouveau graphe par l'agrégation de graphes (ou sous-graphes) existants dans le système. La fonctionnalité de recherche permet à l'utilisateur d'utiliser des mots-clés pour chercher des correspondances dans les graphes existants, ceci en gérant un enrichissement de la requête notamment par l'ajout automatique de synonymes. Les résultats de la recherche permette de trouver les problèmes et les solutions partielles dans la base de données existante et de créer/agréger un nouveau graphe.

Equipe de recherche au sein de la HES-SO: Cretton Fabian , Grèzes Vincent , Liu Zhan , Sokhn Maria , Le Calvé Anne

Partenaires académiques: VS - Institut Informatique; Le Calvé Anne, VS - Institut Informatique

Durée du projet: 01.04.2016 - 30.06.2016

Statut: Terminé

New trends of Chinese Consumers in Switzerland : A Socail Media Platform Analysis Based on Linked Data - ES-ISNET 14-07
AGP

Rôle: Collaborateur/trice

Financement: HES-SO Rectorat; VS - Institut Informatique; VS - Institut Informatique

Description du projet : This project studies behavior of Chinese consumers in Switzerland by adopting a linked data approach on a Chinese social media platform. We intend to conduct a large-scale analysis with linked data and explore Chinese tourists' attitude and behavior towards Switzerland on Sina Weibo, which has played an important role as a powerful media channel to extend personal networks and informal information sources. We will also conduct some interviewers with key individuals as well as real consumers to provide additional evidence for the findings from Sina Weibo

Equipe de recherche au sein de la HES-SO: Cretton Fabian , Genoud Dominique , Liu Zhan , Sokhn Maria , Glassey Balet Nicole , Le Calvé Anne , Délétroz Nicolas , Treboux Jérôme

Durée du projet: 01.12.2014 - 31.05.2016

Montant global du projet: 187'500 CHF

Statut: Terminé

Knowledge Discovery - Etude d'integration
AGP

Rôle: Requérant(e) principal(e)

Financement: SIG - Services Industriels de Genève

Description du projet : Dans le cadre de l'introduction du projet Equilibre au sein de la SIG, M. Christian Grégo a évoqué l'intérêt d'analyser l'apport des nouvelles technologies sémantiques sur les services de dématérialisation proposés par le projet Equilibre

Equipe de recherche au sein de la HES-SO: Sokhn Maria , Maalouf Eliane

Partenaires académiques: VS - Institut Informatique; Sokhn Maria, VS - Institut Informatique

Durée du projet: 15.06.2014 - 29.02.2016

Montant global du projet: 23'436 CHF

Statut: Terminé

Parapheur Electronique - Analyse de processus métier et des documents - eGOV Innovation Center
AGP

Rôle: Requérant(e) principal(e)

Financement: eGov Innovation Center

Description du projet : Dans le cadre d'un mandat avec Swiss Post Solutions, T2i développe un « Proof of Concept » d'une solution de signature de document électronique. Il s'agit d'une solution permettant d'ajouter une signature électronique sur un document électronique équivalente à une signature à la main. La signature électronique est attachée à une SuisseID qui identifie de manière unique le signataire. La solution « Parapheur électronique » permettra aux signataires de visualiser l'ensemble de documents à signer, d'en sélectionner un, de le transférer à une autre personne ou d'y insérer la signature. Il existe actuellement une première version fonctionnelle de l'application.

Equipe de recherche au sein de la HES-SO: Evéquoz Florian , Sokhn Maria , Maalouf Eliane

Partenaires académiques: VS - Institut Informatique; Sokhn Maria, VS - Institut Informatique

Durée du projet: 11.05.2015 - 31.12.2015

Montant global du projet: 6'720 CHF

Statut: Terminé

Xpert.gov.dashboard - The Ark 713-19
AGP

Rôle: Collaborateur/trice

Requérant(e)s: VS - Institut Informatique

Financement: The Ark

Description du projet : Projet The Ark Energy en collaboration avec TI Informatique. Objectif : tableau de bord énergétique pour les Communes - niveau national

Equipe de recherche au sein de la HES-SO: Genoud Dominique , Evéquoz Florian , Sokhn Maria , Hunacek Daniel , Maalouf Eliane , Treboux Jérôme , Cotting Alexandre

Partenaires académiques: VS - Institut Informatique

Durée du projet: 01.07.2013 - 28.02.2014

Montant global du projet: 55'440 CHF

Statut: Terminé

2024

Modèles de maturité numérique :
Article scientifique ArODES
de la mesure à l’action

Maximiliano Jeanneret Medina, Cédric Baudet, Maria Sokhn

Management & Data Science,  2024, 8, 3

Lien vers la publication

Résumé:

Dans cet article d’opinion, nous synthétisons la recherche sur les modèles de maturité numérique (MMN) en nous concentrant sur leurs finalités et controverses liées à leurs mobilisations par les praticiens. Dans un deuxième temps et en nous appuyant sur des données issues d’un programme de recherche lié sur la transformation numérique des organisations de l’arc jurassien suisse, nous proposons des conseils pratiques pour mobiliser un MMN. Finalement, nous ouvrons des voies futures de collaboration afin de mieux accompagner les organisations dans leur processus de transformation numérique.

Articuler innovation sociale et innovation technologique dans le champ du travail social :
Chapitre de livre ArODES
exemple du projet VIVRE

Paul Konan N'Dri, Bhama Steiger, Maria Sokhn, Fatou N'Diaye, Camille Pellaton

Dans Chimienti, Milena, Cretton, Viviane, Maeder, Pascal, Maggiori, Christian, Probst, Isabelle, Rullac, Stéphane, Innovation et intervention sociales : impacts, méthodes et mise en œuvre dans les domaines de la santé et de l'action sociale  (pp. 231-244). 2024,  Zürich et Genève : Seismo

Lien vers la publication

L'usine du futur : Digital - Dark - Adaptive - Creative
Chapitre de livre

Ouerhani Nabil, Sokhn Maria, Carrino Francesco, al. et

,  L'usine du futur : Digital - Dark - Adaptive - Creative. 2024,  Suisse : Georg Éditeur

Résumé:

Cet ouvrage propose une discussion autour de l'usine du futur et de son développement, soutenu notamment par l'IA. 

De la "Dark Factory" à la "Créative Factory", l’histoire industrielle peut se résumer comme une longue quête de l’automatisation de la fabrication. Les machines de plus en plus sophistiquées et digitalisées permettront d’achever cette quête. Aujourd’hui déjà, des usines industrielles fonctionnent toutes seules pendant des heures, voire des jours. Ce qu'il sera intéressant de découvrir dans la prochaine phase de la révolution industrielle, c'est à quel point nous ferons appel à l’IA pour inventer le monde de demain.

2023

VR in promotion of territory in the new normal :
Article scientifique ArODES
empirical and research approaches in the times of crisis

Julia Wirth, Marina G. Shilina, Maria Sokhn, Leonid P. Preobrazhenskiy

RUDN Journal of Studies in Literature and Journalism,  2023, 28, 4, 809-817

Lien vers la publication

Résumé:

In the New Normal, the most sought-after tools for territory promotion are digital and immersive, and closely intertwined with virtual reality technologies. This research centers on VR projects in Switzerland and Russia, two countries representing contrasting situations in the current tourist and promotion of territory landscape of 2023. The findings of the prior research on the incorporation of immersive VR technology in territory promotion in Switzerland with analogous research conducted in Russia are compared. By examining both theoretical and empirical data, including data analysis and semi-structured interviews with VR project managers in Switzerland and owners/managers in Russia, differences between Switzerland and Russia are identified. A spreading value-centered qualitative approach in English- and French-language scientific discourse on VR-driven territory promotion is connected with cultural heritage and sustainable consumption and is novel for Russia. Conceptual frameworks in this scientific field are still in their early stages. In Switzerland, the VR projects are more complex and are used as a part of territory and corporate promotion, despite the not value centered, but economic motivation. In Russia, VR is viewed as the next stage in the evolution of travel viewing and recreation, and it serves as an advertising tool to attract travelers to territory attractions. The ideas of VR-tours are connected with the past, and historical and cultural heritage. The best projects demonstrate the feasibility of combining on-site visits, VR, and sustainability awareness. VR-project in this case is the instrument of saving.

VR-mediated storytelling of experience in destination branding :
Article scientifique ArODES
hybrid 4D transformations

Marina G. Shilina, Maria Sokhn, Julia Wirth

RUDN journal of studies in literature and journalism,  28, 1, 165-174

Lien vers la publication

Résumé:

In COVID-19 era, destination branding faces the challenge of digitalization and virtual reality (VR) in particular. The fundamentals of VR-mediated storytelling in destination branding are in the process of being developed. There is a luck of research on immersive VRmediated storytelling, scenarios, and messages in destination branding, especially realised with technologies of more complex – hybrid – immersivity (4D). The shift from 2D, 3D to 4D hybrid multisensory VR technologies is not only among the main technology developments – it provokes new research problems with VR-mediated destination branding and storytelling. The authors present the results of theoretical and empirical research of VR-mediated destination storytelling of a brand driven by the newest 4D hybrid multisensory technological approaches on the case of Switzerland. In Switzerland, VR-mediated projects in destination branding are developing actively last years but VR-mediated storytelling research in this field was not provided yet. In this regard, it was chosen 100 destination brand VR projects, presented in 2016–2022, to compare the parameters of VR-mediated storytelling of a brand. VR has to be included into brand storytelling paradigm, which must be rethought for this specific sphere. It was proved that it is more effective to combine different types of experience, virtual and physical both and make the VR-mediated brand storytelling hybrid. In terms of theoretical implications, this paper opened a specific research area by bridging theoretical and empirical ideas of destination branding, VR-mediated storytelling and digital media, technical and social communication.

2021

Un hub au service de la transformation digitale
Article professionnel ArODES

Maria Sokhn

Revue de la CEP,  2021, no 163, pp. 46-47

Lien vers la publication

De l'infobésité à la communauté des pratiques :
Chapitre de livre ArODES
faire du numérique un levier à l'intégration des migrant-e-s installé-e-s en Suisse

N'Dri Paul Konan, Bhama Steiger, Maria Sokhn, Fatou N'Diaye, Camille Pellaton

Dans Costa-Fernandez, Elaine, Ferrandi, Raymonde, Scopsi, Claire, Technologies de l'information et de la communication (TIC), migrations et interculturalité  (pp. 157-172). 2021,  Paris : L'Harmattan

Lien vers la publication

2019

The power of a blockchain-based supply chain
Article scientifique ArODES

Rita Azzi, Rima Kilany Chamoun, Maria Sokhn

Computers industrial engineering,  2019, vol. 135, pp. 582-592

Lien vers la publication

Résumé:

A supply chain is a system of organizations, people, activities, information and resources involved in moving a product or service from supplier to customer. It is designed to maintain the quality of sensitive goods during the whole shipment. Centralized supply chain management systems expose the supply chain to corruption, fraud, and tampering. Blockchain has emerged as a new distributed information technology; it represents a new approach in supply chain area, where visibility and transparency of product flows are the principal challenges. This paper describes how the blockchain can be integrated into the supply chain architecture to create a reliable, transparent, authentic and secure system. To reach this goal, we studied the benefits of introducing the blockchain to the supply chain and the challenges encountered in a blockchain-based supply chain management ecosystem. We combined theoretical and real-world application studies to build our theory about the requirements for an efficient blockchain-based supply chain.

CrowDPLoS
Article scientifique
Building a Crowdsourcing based Disabled Pedestrian Level of Service routing application using Computer Vision and Machine Learning

Sandoz Romain, Ertz Olivier, Ingensand Jens, Blanc Nicolas, Liu Zhan, Rojas Diego, Sokhn Maria, Loubier Jean-Christophe

Consumer Communications and Networking Conference, CCNC IEEE, 2019

Lien vers la publication

Résumé:

The availability of global and scalable tools to assess disabled pedestrian level of service (DPLoS) is a real need, yet still a challenge in today's world. This is due to the lack of tools that can ease the measurement of a level of service adapted to disabled people, and also to the limitation concerns about the availability of information regarding the existing level of service, especially in real time. This paper describes preliminary results to progress on those needs. It also includes a design for a navigation tool that can help a disabled person move around a city by suggesting the most adapted routes according to the person's disabilities. The main topics are how to use advanced computer vision technologies, and how to benefit from the prevalence of handheld devices. Our approach intends to show how crowdsourcing techniques can improve data quality by gathering and combining up-to-date data with valuable field observations.

 

2017

Gaming as a gateway :
Chapitre de livre ArODES
ensuring quality control for crowdsourced data

Shaban Shabani, Maria Sokhn

International Conference on Cooperative Design, Visualization and Engineering (CDVE 2017) : Cooperative Design, Visualization, and Engineering  (pp. 73-76). 2017,  Cham : Springer

Lien vers la publication

Résumé:

Crowdsourcing is a growing topic that has proved to be ca-pable and cost effective solution for various tasks. Over the last decade it has been applied to numerous domains, both in research and enterprise contexts. Though there are several issues that remain open and challeng-ing in crowdsourcing, here we address the issues of quality control and motivation. In this paper we present an ongoing work which explores the use of gamification in crowdsourcing settings, as means to: improve the task assignment and performance, incentivize people to participate and control the quality of their work. The developed crowdsourcing hybrid mobile application is applied to data within cultural heritage domain.

2015

Linked data based framework for tourism decision support system :
Article scientifique ArODES
case study of chinese tourists in Switzerland

Zhan Liu, Anne Le Calvé, Fabian Cretton, Nicole Glassey Balet, Maria Sokhn, Nicolas Délétroz

Journal of computer and communications,  vol. 3, no. 5, pp. 118-126

Lien vers la publication

Résumé:

Switzerland is one of the most desirable European destinations for Chinese tourists; therefore, a better understanding of Chinese tourists is essential for successful business practices. In China, the largest and leading social media platform—Sina Weibo, a hybrid of Twitter and Facebook—has more than 600 million users. Weibo’s great market penetration suggests that tourism operators and markets need to understand how to build effective and sustainable communications on Chinese social media platforms. In order to offer a better decision support platform to tourism destination managers as well as Chinese tourists, we proposed a framework using linked data on Sina Weibo. Linked Data is a term referring to using the Internet to connect related data. We will show how it can be used and how ontology can be designed to include the users’ context (e.g., GPS locations). Our framework will provide a good theoretical foundation for further understand Chinese tourists’ expectation, experiences, behaviors and new trends in Switzerland.

2014

Enhancement of conference organization using ontology based information correlation
Article scientifique ArODES

Hassan Noureddine, Iman Jarkass, Maria Sokhn, Omar Abou Khaled, Elena Mugellini

Computer Science and Information Technology,  2014, vol. 2, no. 2, pp. 63-71

Lien vers la publication

Résumé:

The world today witnessed an important transmission to the virtual world across the web. After years of interaction and exchanges between people, the web becomes saturated with enormous quantity of data in various fields. Therefore, the (semi-)automatic applications become necessity to find appropriate information in a brief time. In this context, we propose a new approach of ontology based information correlation from various web resources. As validator of this approach, we introduce the conference organizer system that will be useful during the setting up of a conference. Where we benefit from semantic web technologies to extract, correlate, rank and store information, and consequently propose a ranked lists of experts and social events depending on the user requests.

2024

Digital business transformation for SMEs :
Conférence ArODES
maturity model for systematic roadmap

Maximiliano Jeanneret Medina, Alessio De Santo, Philippe Oswald, Maria Sokhn

Information Systems and Technologies : WorldCIST 2023

Lien vers la conférence

2023

Digital Business Transformation for SMEs: Maturity Model for Systematic Roadmap
Conférence

Jeanneret Medina Maximiliano Zadkiel, De Santo Alessio, Oswald Philippe, Sokhn Maria

World Conference on Information Systems and Technologies, 04.04.2023 - 06.04.2023, Pisa, Italy

Lien vers la conférence

Résumé:

Digital maturity models (DMM) aim to measure the current level of a company’s digitalization, as well as providing a path towards digital maturity. While many DMMs exist, several challenges surround their application for small and medium-sized enterprises (SME) that would ben the process on their own. The aim of this paper is to describe the development and the evaluation of a tool that assist SMEs with their digital transformation, from the maturity assessment to the setup of a systematic digital transformation roadmap. Following a Design Science Research approach, we elucidated the needs of SME managers regarding digital maturity through interviews (n=10). Then, we developed and evaluated a DMM integrated within an online tool through focus groups (n=3). We finally evaluated our tool in the context of six SME digital transformation initiatives. Our findings highlight that SME managers need prescriptions about digital maturity rather than a sole description of their organization’ maturity stage. Evaluations show good results in terms of utility and validity. Moreover, a need for a more complete and specialized recommendation service was highlighted which pave the way for future research.

A healthcare delivery system powered by semantic data :
Conférence ArODES
description and blockchain

Rita Azzi, Rima Kilany Chamoun, Ahmed Serhrouchni, Maria Sokhn

Advances in information and communication

Lien vers la conférence

Résumé:

Continuous technological progress has been supporting health providers with powerful tools to help them improve the delivery of health services and ensure patients’ safety. These adopted technologies focus on data collection. However, patients’ data are distributed and fragmented, which highly affects the quality of care. In this paper, we propose a blockchain-based approach to improve the management of patients’ data by addressing: the adverse drug interactions or reactions due to inappropriate medication intake. Although the initial target of our contribution is the healthcare system in Lebanon, our solution can be applied to improve any healthcare system. It combines the usage of a blockchain with Semantic Web technologies, where the blockchain provides a secure infrastructure for data sharing and prevents data tampering through a tamper-proof audit log. As for the semantic description of data, it brings a common shared understanding of the data at hand, boosting knowledge discovery, and automating decision making.

2022

A collaborative intelligence approach to fighting COVID-19 false news :
Conférence ArODES
a Chinese case

Zhan Liu, Shaban Shabani, Xianyun Yu, Maria Sokhn, Nicole Glassey Balet

Human centred intelligent systems : proceedings of KES-HCIS 2022 conference

Lien vers la conférence

Résumé:

The rapid outbreak of COVID-19 has heightened interest in news about the pandemic. In addition to obtaining real-time developments about COVID-19, people have learned about prevention methods through the news media. Ironically, false COVID-19 news has spread faster than the virus, posing an additional health threat with advice being as dangerous as infection. In this study, we developed a Chinese news article dataset on COVID-19 misinformation, which contained 1266 verified articles from 118 Chinese digital newspaper platforms from January 2020 to January 2021. This dataset uses machine learning methods to detect false news in the Chinese language. Because automated classification methods, combined with human computation-based approaches, are effective for combating digital misinformation, we applied and evaluated a collaborative intelligence approach that leverages human fact-checking skills with feedback on news stories using four criteria: source, author, message, and spelling. The results show that reliable human feedback can help detect false news with high accuracy.

2021

The Student Journey Map (SJM) :
Conférence ArODES
a scenario-based approach to professionalizing digital education

Emmanuel Fragnière, Maria Sokhn, Camille Pellaton, Charline Unternährer, Randolf Ramseyer

Proceedings of IECON 2021 - 47th Annual Conference of the IEEE Industrial Electronics Society

Lien vers la conférence

Résumé:

The Student Journey Map (SJM) places learners at the center of sharing knowledge, with the support of a teacher who assumes the role of coach in the acquisition and dissemination of know-how. The SJM is designed to be experimented with in combination with the educational scripting approach of the Customer Journey Map. In our qualitative study, we formulated several propositions, the primary one being that it is important to offer face-to-face social exchanges in student-based environments. The SJM helps to compensate for isolation by recreating a social link between students. The teacher begins by establishing the pedagogical scenario of the course with its objectives, the topics to be covered, and practical training sessions. Our experiments show that by using the SJM approach, students collaborate directly with each other, thereby allowing co-learning that does not occur in a merely transposed online teaching approach.

City-Stories :
Conférence ArODES
combining entity linking, multimedia retrieval, and crowdsourcing to make historical data accessible

Laura Rettig, Shaban Shabani, Loris Sauter, Philippe Cudré-Mauroux, Maria Sokhn, Heiko Schuldt

Web engineering : proceedings of the 21st international conference on web engineering

Lien vers la conférence

Résumé:

Digitized historical image collections as provided by individuals or memory institutions often suffer from limited or a complete lack of metadata. In this paper, we present the City-Stories system that combines entity linking, multimedia retrieval, and crowdsourcing to make historical images searchable even across collections.

SAMS :
Conférence ArODES
human-in-the-loop approach to combat the sharing of digital misinformation

Shaban Shabani, Zarina Charlesworth, Maria Sokhn, Heiko Schuldt

Proceedings of the AAAI 2021 Spring Symposium on Combining Machine Learning and Knowledge Engineering

Lien vers la conférence

Résumé:

Spread of online misinformation is an ubiquitous problem especially in the context of social media. In addition to the impact on global health caused by the current COVID-19 pandemic, the spread of related misinformation poses an additional health threat. Detecting and controlling the spread of misinformation using algorithmic methods is a challenging task. Relying on human fact-checking experts is the most reliable approach, however, it does not scale with the volume and speed with which digital misinformation is being produced and disseminated. In this paper, we present the SAMS Human-in-the-loop (SAMS-HITL) approach to combat the detection and the spread of digital misinformation. SAMS-HITL leverages the fact-checking skills of humans by providing feedback on news stories about the source, author, message, and spelling. The SAMS features are jointly integrated into a machine learning pipeline for detecting misinformation. First results indicate that SAMS features have a marked impact on the classification as it improves accuracy by up to 7.1%. The SAMS-HITL approach goes one step further than the traditional human-in-the-loop models in that it helps raising awareness about digital misinformation by allowing users to become self fact-checkers.

2020

Hybrid human-machine classification system for cultural heritage data
Conférence ArODES

Shaban Shabani, Maria Sokhn, Heiko Schuldt

Proceedings of the 2nd Workshop on Structuring and Understanding of Multimedia heritAge Contents (SUMAC'2020)

Lien vers la conférence

Résumé:

The advancement of digital technologies has helped cultural heritage organizations to digitize their data collections and improve the accessibility via online platforms. These platforms have enabled citizens to contribute to the process of digital preservation of cultural heritage by sharing documents and their knowledge. However, many historical datasets have problems due to incomplete metadata. To solve this issue, cultural heritage organizations heavily depend on domain experts. In this paper, we address the issue of completing the metadata of historical digital collections. For this, we introduce a new hybrid human-machine model. This model jointly integrates predictions of a deep multi-input model and inferred labels from multiple crowd judgements. The multi-input model uses visual features extracted from the images and textual features from the metadata, complemented with Wikipedia classes of concepts extracted in the text. On the crowd answer aggregation, our method considers the workers' reliability scores. This score is based on the performance of workers' task history and their performance in our task. We have applied our hybrid approach to a culture heritage platform and the evaluations show that it outperforms both deep learning and crowdsourcing when applied individually.

2019

Detection of satiric news on social media: analysis of the phenomenon with a French dataset
Conférence ArODES

Zhan Liu, Shaban Shabani, Nicole Glassey Balet, Maria Sokhn

Proceedings of the 28th International Conference on Computer Communication and Networks (ICCCN) 2019

Lien vers la conférence

Résumé:

The topic of deceptive and satiric news has drawn attention from both the public and the academic community, as such misinformation has the potential to have extremely adverse effects on individuals and society. Detecting false and satiric news automatically is a challenging problem in deception detection, and it has tremendous real-word political and social influences. In this paper, we contribute a useful French satiric dataset to the research community and provide a satiric news detection system using machine learning to automate classifications significantly. In addition, we present the preliminary results of our research designed to discriminate real news from satiric stories, and thus ultimately reduce false and satiric news distribution.

Building a crowdsourcing based disabled pedestrian level of service routing application using computer vision and machine learning
Conférence ArODES

Nicolas Blanc, Zhan Liu, Olivier Ertz, Diego Rojas, Romain Sandoz, Maria Sokhn, Jens Ingensand, Jean-Christophe Loubier

Proceedings of 2019 16th IEEE Annual consumer communications & networking conference (CCNC), 11-14 January 2019, Las Vegas, USA

Lien vers la conférence

Résumé:

The availability of global and scalable tools to assess disabled pedestrian level of service (DPLoS) is a real need, yet still a challenge in today’s world. This is due to the lack of tools that can ease the measurement of a level of service adapted to disabled people, and also to the limitation concerns about the availability of information regarding the existing level of service, especially in real time. This paper describes preliminary results to progress on those needs. It also includes a design for a navigation tool that can help a disabled person move around a city by suggesting the most adapted routes according to the person’s disabilities. The main topics are how to use advanced computer vision technologies, and how to benefit from the prevalence of handheld devices. Our approach intends to show how crowdsourcing techniques can improve data quality by gathering and combining up-to-date data with valuable field observations.

Creating task-generic features for fake news detection
Conférence ArODES

Alex C. Olivieri, Shaban Shabani, Maria Sokhn, Philippe Cudré-Mauroux

Proceedings of the 52nd Hawaii International Conference on System Sciences (HICSS) 2019

Lien vers la conférence

Résumé:

Information spreads at a pace never seen before on online platforms, even when this information is fake. Fake news can have substantial impact, for instance when it concern politics and influences the results of legislations or elections. Finding a methodology to verify if some piece of news is true or false is hence essential. In this work, we propose a methodology to create task-generic features that are paired with textual features in order to detect fake news. Task-generic features are created by elaborating on metadata attached to answers from Google’s search engine, and by using crowdsourcing for missing values. We experimentally validate our method on a dataset for fake news detection based on the PolitiFact website. Our results show an improvement in F1-Score of 3% over the state of the art, which is significant for a 6-class task.

2018

Semantic network visualization of cultural heritage data
Conférence ArODES

Shaban Shabani, Zhan Liu, Maria Sokhn

Proceedings of the 1st International Workshop on Knowledge Graphs on Travel and Tourism : Full-day workshop at the 18th International Conference on Web Engineering (ICWE 2018)

Lien vers la conférence

Résumé:

Advancement of digital technologies have helped the cultural heritage (CH) organizations such as archives, libraries, and museums to digitize their data collections and improve the accessibility to them. Over the past years various approaches have been developed to enable the visualization of the CH data. In this paper, we present a use case on annotation, linking, visualization and browsing of CH data and suggest some directions to achieve tangible visual analysis. We introduce the semantic linked data search and the method of connected concepts to enhance the users experience when searching for historical data.

Survey :
Conférence ArODES
when semantics meet crowdsourcing to enhance big data variety

Houssein Dhayne, Rima Kilany Chamoun, Maria Sokhn

Proceedings of the IEEE Middle East & North Africa COMMunications Conference (MENACOMM) 2018

Lien vers la conférence

Résumé:

With the rapid growth of collected data and the variety of its content, the need for efficient integration at a Big Data level becomes crucial. Semantic technologies, as a means of integration and coordination of heterogeneous systems, may help big data to manage terminology and relationships to link various data from different data sources. However, and due to the difficulty of integration and analytics of some datasets with high-precision, automated processes cannot reach a high level of accuracy without the human cognitive ability. Crowdsourcing platforms have the potential to integrate (entity matching, entity resolution) and analyze (sentiment analysis, image recognition) heterogeneous data sources when in some cases these integration tasks may prove to be problematic for computers. In this survey, we explore and compare empirical research studies that rely on merging semantic and crowdsourcing technologies. And, in the light of this comparison, we propose a high-level integration workflow, which shows how merging these technologies can enhance the big data integration process and tackle the data analysis challenges.

How to motivate participation and improve quality of crowdsourcing when building accessibility maps
Conférence ArODES

Zhan Liu, Shaban Shabani, Nicole Glassey Ballet, Maria Sokhn, Fabian Cretton

Proceedings of the 3rd Workshop on Accessible Devices and Services (ADS) in the IEEE Consumer Communications & Networking Conference 2018

Lien vers la conférence

Résumé:

Crowdsourcing, as one of the most promising tech-niques for distributed problem-solving, requires sustained human involvement. Therefore, it also brings new challenges to data management, fundamentally data input and its quality. In this paper, we looked at various forms of user motivations and quality control of crowdsourcing when building accessibility maps mobile applications. We discuss how motivations could be used to contribute to our accessibility maps scenarios, and how data can be improved for two types of participants: individual participants and organization participants. We identified three useful techniques for improving data quality: qualification-based, reputation-based, and aggregation-based. In addition, based on our own mobile application (named WEMAP), we evaluated our approaches through focus group discussions and in-depth interviews.

2017

The new information technologies at the service of historical and cultural heritage and tourism promotion
Conférence ArODES

Basma Makhlouf Shabou, Maria Sokhn

Proceedings of Infuture2017

Lien vers la conférence

Résumé:

City-Zen is an interactive spatio-temporal knowledge-browsing platform that aims to valorise cultural heritages. Considering the explosive growth of information, data and knowledge sharing can ensure valuable interdisciplinary applications. While many organizations propose relevant data sets, they are hardly accessed, analysed and reused because of the formats inconsistency and the inappropriate information browsing and visualization. The goal of the project is to valorise the existing cultural heritage through a citizen centric design platform. Based on information qualities, the use case of this project involves a user willing to discover the history of a region and to embark in a cultural journey in the past. This paper exposes the main functionalities City-zen application and shows how those latest should reach the different user needs. It illustrates how historical and cultural heritage valorisation can take advantage from the advancement of new technologies, multimedia & mobile and how those technologies should promote tourism services.

City-Stories :
Conférence ArODES
a multimedia hybrid content and entity retrieval system for historical data

Shaban Shabani, Maria Sokhn, Laura Rettig, Philippe Cudré-Mauroux, Lukas Beck, Heiko Schuldt

Proceedings of the 4th International Workshop on Computational History (HistoInformatics2017)

Lien vers la conférence

Enhancing cultural heritage data through selective crowdsourcing
Conférence ArODES

Alex C. Olivieri, Shaban Shabani, Zhan Liu, Maria Sokhn

Proceedings of International Conference on Advanced Computer Science and Information Systems (ICACSIS) 2017

Lien vers la conférence

Résumé:

Crowdsourcing, or asking for general participation to help contribute to shared goals, has become popular in the cultural heritage domain. However, it also brings new challenges to data quality management. In this paper, we describe a novel approach that used selective crowdsourcing to increase quality control and the number of participants when collecting cultural heritage-related data. We tested our approach in scenarios using a mobile application for cultural heritage travellers. The results showed that the selective crowdsourcing approach can be applied well to complete information and resolve conflict in cultural heritage data.

Assessing data veracity through domain specific knowledge base inspection
Conférence ArODES

Alex C. Olivieri, Shaban Shabani, Maria Sokhn, Philippe Cudré-Mauroux

Proceedings of the International Conference on Advanced Computer Science and Information Systems (ICACSIS) 2017

Lien vers la conférence

Résumé:

The Internet is nowadays a fantastic source of information thanks to the quantity of the information it provides and its dynamicity. However, these features also represent challenges when we want to consider trustworthy information only. On the Internet, the process of verifying information, known as fact-checking, cannot be performed by human experts given the scale of the information that should be manually checked, and the speed to which it changes. In this paper, we propose an approach to evaluate the trustworthiness of online information modeled as RDF Triples. Given a use case, we select a specific ontology (in the following we use movie reviews as a use case) and match its object properties with WordNet. This allows us to understand, for each input triple, which class the subject and the object belong to. We associate SPARQL queries to each class, which are then used by our approach to search for additional evidences in Wikidata. By doing so, our approach generates feature vectors that are used by machine learning classification models to predict the trustworthiness of new input triples. Experiments on real movie data show that our approach provides results that are on par or better than the state of the art in fact checking.

Crowdsourcing-based mobile application for wheelchair accessibility
Conférence ArODES

Zhan Liu, Nicole Glassey Balet, Maria Sokhn, Eline De Gaspari

Proceedings of the 32nd Annual International Technology and Persons with Disabilities Conference Scientific/Research

Lien vers la conférence

Résumé:

Creating an optimal travel plan is not an easy task, particularly for people with mobility disabilities, for whom even simple trips, such as eating out in a restaurant, can be extremely difficult. Many of their travel plans need to be made days or even months in advance, including the route and time of day to travel. These plans must take into account ways in which to navigate the area, as well as the most suitable means of transportation. In response to these challenges, this study was designed to develop a solution that used linked data technologies in the domains of tourism services and e-governance to build a smart city application for wheelchair accessibility. This smart phone application provides useful travel information to enable those with mobility disabilities to travel more easily.

2016

Cityzen :
Conférence ArODES
a social platform for cultural heritage focused tourism

Alex Olivieri, Roland Schegg, Maria Sokhn

Proceedings of the 8th International ACM Conference on Management of Digital EcoSystems (MEDES'16)

Lien vers la conférence

Résumé:

The way tourists organize their travels is evolving day after day. While in the past, information was more obtained by the support of tour operators, nowadays this is mainly ob-tained through the Internet. Among many options, on the Internet it is possible to get information about interesting things a place has and to make reservations. This new touristic paradigm brings attractive opportunities such as saving money and discovering unexploited information pro-posed by tourists that already have visited targeted places. But, it comes with a major shortcoming. Information on the Internet can be overwhelming and it can lead to a lot of time spent on planning a travel. Moreover, the Internet con-tains outdated and incorrect information which can cause incorrect travel planning. These issues can become even more preponderant when dealing with niche domains, such as cultural heritage, where the information is not perva-sive. This paper presents the Cityzen platform for planning cultural heritage focused travels. This platform aims to provide a semantic web oriented data model that acts as central repository and which can be used by tourists for accurately and efficiently planning their sightseeing. This platform deals with cases of incorrect and incomplete in-formation by using the social web as possibility of actively engage users in the information management while they explore the provided information.

An interdisciplinary approach for cultural heritage valorisation and visualization
Conférence ArODES

Basma Makhlouf Shabou, Maria Sokhn, Alex Olivieri

Actes de la première édition du Colloque international sur les bibliothèques et archives à l'ère des humanités numériques (CIBAHN 2016)

Lien vers la conférence

Résumé:

City-Zen is an interactive temporal knowledge-browsing platform that aims to valorise cultural heritages. While many organizations propose relevant data sets, they are hardly accessed, analysed and reused because of the formats inconsistency and the inappropriate information browsing and visualization. The goal of the project is to valorise the existing cultural heritage through a citizen centric design platform. The use case of this project involves a user willing to discover the history of a region and to embark in a cultural journey in the past. This project addresses a novel approach of data analysis of both assessment methods of data quality and spatio-temporal information. The proposed paper will describe the approach, its model and its implementation tests in the context of the State of Wallis.

City eye :
Conférence ArODES
accessibility for all

Zhan Liu, Anne Le Calvé, Maria Sokhn, Roland Schegg

Proceedings of the 9th International Conference on Theory and Practice of Electronic Governance (ICEGOV)

Lien vers la conférence

Résumé:

In today’s world, making a good travel plan is not an easy task for most people. However, the situation is even more complicated for people with disabilities. For them, even simple trips, such as travelling to visit a museum or an exposition, have become extremely difficult. A wide variety of travel planning needs to be made days or months in advance, such as where, when, and how to travel, as well as how to get around and how to choose a suitable means of transportation. As a response in this ongoing project, our intention is to apply our proposed solution of linked data technologies in the domains of tourism services and e-governance to build a smart city. In particular, we want to provide useful travel information to people with disabilities and to make their travelling easier.

From data to decisions
Conférence ArODES

Maria Sokhn, Alexandre Cotting, Florian Evéquoz, Arnaud Zufferey

Proceedings of the 9th International Conference on Theory and Practice of Electronic Governance (ICEGOV2016)

Lien vers la conférence

Résumé:

A revolution over the open data approach has gained importance over the last decade. This revolution is based on the information and communication technology and has been catalyzed by open government directives that have emerged. In this paper we present preliminary results of our approach based on dashboards showing selected open government data as a key element for trends visualization, prediction evaluation and decision support.

2015

From data to data’s transparency
Conférence ArODES

Maria Sokhn, Alexandre Cotting, Eliane Maalouf, Arnaud Zufferey

Proceedings of ICEGOV2015

Lien vers la conférence

Résumé:

Decades ago governments, businesses and other actors used to make benefit of generated data in order to manage and monitor their activities. However traditionally data cleaning and analysis have been time consuming and thus used to be kept limited of access. Making the governmental data available and easily accessible and reusable increases the information visibility and decision makers, thus it improves the transparency and efficiency. In this paper we present an ongoing project, which aims to enhance the transparency and efficiency in Swiss public administration, by making use of dashboards communication power.

2014

Business process fragmentation for enhancing process modeling
Conférence ArODES

Eliane Maalouf, Marcel Di Zuzio, Maria Sokhn

Proceedings of Electronic Governance and Open Society: Challenges in Eurasia (EGOSE) 2014

Lien vers la conférence

Résumé:

Business Process Management (BPM) is accepted to be an efficient approach to capture processes in order to improve operational aspects of an enterprise. Business process modeling and design is the first step in BPM. This paper presents a process fragmentation approach that serves to generate process fragments ready for reuse during modeling in a semantic modeling tool. The fragmentation is based on the Refined Process Structure Tree which is an algorithm to decompose processes based on their workflow graphs.

Enhancing business process modelling for e-government processes using semantic web technologies and linked data principles
Conférence ArODES

Eliane Maalouf, Maria Sokhn

Proceedings of the eChallenges e-2014

Lien vers la conférence

Résumé:

Semantic Web technologies are being applied more and more in business context applications. The domain of Business Process Management (BPM) is no exception. Additionally, Linked Data principles become interesting to apply in this context as well to enrich processes with information from more diverse sources. We aim to apply Semantic Web technologies and Linked Data principles to enhance Business Process modelling of Swiss e-Government public processes. To favour the reuse of processes from a process repository, the modelling tool will assist the user while modelling through auto completion, process translation, decomposition and annotation. Annotations on processes will allow linking those processes to ontology concepts related to the cyber administration standards. This paper will focus on translating processes to Resource Description Framework (RDF) and the creation of the data links, as well as process translation from German to French.

Empathic TV experiences for visually and hearing impaired people using arousal modeling
Conférence ArODES

Joël Dumoulin, Maria Sokhn, Elena Mugellini, Omar Abou Khlaed, Marco Bertini, Alberto Del Bimbo

Proceedings of the 1st Workshop on Empathic Television Experiences (EmpaTeX 2014), 25-27 June 2014, Newcastle, England

Lien vers la conférence

Résumé:

If new televisions are bringing more and more features in our living rooms, they are still lacking an important axis of the TV user experience: emotions. And this is particularly true for visually and hearing impaired people. Therefore, we want to find innovative ways to bring them emotions that are usually conveyed through sound and images, by taking advantage of arousal modeling of films. Such empathic TV experiences will give them the possibility to fully enjoy visual media.

Multimodal context modeling and classification using TBM
Conférence ArODES

Nour Charara, Maria Sokhn, Iman Jarkass, Omar Abou Khaled, Elena Mugellini

Proceedings of the IEEE International Conference on Electro/Information Technology, 5-7 June 2014, Milwaukee, WI, USA

Lien vers la conférence

Résumé:

This paper presents a novel supervised method for context modeling and classification based on Transferable Belief Model (TBM). The task of context classification is to identify, among predefined context types, the one that is currently active in the video-surveillance footage of multipurpose halls. Context is spatially modeled by extracting five discriminative semantic features according to depth zones. These zones are provided by depth-based scene segmentation method. Using mathematical TBM tools, the structured semantic features are processed and the mass functions are modeled on three levels in order to propose classification. In addition to video document indexing and retrieval, this work can improve the machine vision capability in behavior analysis.

Conference organization using ontology based information correlation from multiple web resources
Conférence ArODES

Hassan Noureddine, I. Jarkass, Maria Sokhn, Omar Abou Khaled, Elena Mugellini

Proceedings of the LAAS 2014 - The 20th LAAS International Science Conference, 27-29 March 2014, Hadath, Liban

Lien vers la conférence

Résumé:

Years of information pumping and exchanging across the web, making it saturated by data, especially in the scientific domain. Consequently, the (semi-)automatic applications become a necessity to find appropriate information in a brief time. Therefore, the Web witnessed the evolution of these applications with time. Despite this, the problem has not been fully solved with the presence of a large amount of conflicted and outdated data. In order to get more accurate and ranked results, it was interesting to correlate this information, especially with its existence within multiple sources. This is typically useful during setting up a conference, when we need to find information about social events and experts.

Context identification from video-surveillance scenes of multipurpose halls
Conférence ArODES

Nour Charara, I. Jarkass, Maria Sokhn, Omar Abou Khaled, Elena Mugellini

Proceedings of the LAAS 2014 - The 20th LAAS International Science Conference, Université libanaise, 27-29 March 2014, Hadath, Liban

Lien vers la conférence

Résumé:

A novel method for multimodal context identification from video-surveillance footage of multipurpose halls is presented is this paper. After presenting a dedicated definition of ‘Context’ in computer vision systems, the goal is resumed by detecting the active context type among predefined ones. To this end, a spatial modeling of context is performed by extracting five discriminative semantic features according to depth zones. These zones are detected by depth-based scene segmentation method. These features are processed with the Transferable Belief Model (TBM) to propose a classification. Results show the validity of the method for context recognition.

2013

Tracking a screen and detecting its rate of change on 3-D video scenes of multipurpose halls
Conférence ArODES

Nour Charara, Maria Sokhn, Omar Abou Khaled, Elena Mugellini

Proceedings of the 3rd International Conference on Signal, Image Processing and Applications, 10-11 August 2013, Barcelona, Spain

Lien vers la conférence

Résumé:

This paper presents an automatic approach to track a wide screen in a multipurpose hall video scene. Once the screen is located, this system also generates the temporal rate of change, using edge detection based method. Our approach adopts a scene segmentation algorithm that explores visual features (texture) and depth information to perform efficient screen localization. The cropped region which refers to the wide screen undergoes a salient visual cues extraction to retrieve the emphasized changes required in rate-of-change computation. In addition to video document indexing and retrieval, this work can improve the machine vision capability in behavior analysis and pattern recognition.

Enhanced conference organization based on correlation of web information and ontology based expertise search
Conférence ArODES

Hassan Noureddine, Maria Sokhn, Iman Jarkass, Elena Mugellini, Omar Abou Khaled

International Conference on Information Retrieval and Knowledge Management (ICIRKM 2013), Venice, Italie Avril 2013

Lien vers la conférence

Résumé:

From the importance of the conference and its constructive role in the studies discussion, there must be a strong organization that allows the exploitation of the discussions in opening new horizons. The vast amount of information scattered across the web, make it difficult to find experts, who can play a prominent role in organizing conferences. In this paper we proposed a new approach of extracting researchers’ information from various Web resources and correlating them in order to confirm their correctness. As a validator of this approach, we propose a service that will be useful to set up a conference. Its main objective is to find appropriate experts, as well as the social events for a conference. For this application we us Semantic Web technologies like RDF and ontology to represent the confirmed information, which are linked to another ontology (skills ontology) that are used to present and compute the expertise.

Réalisations

Médias et communication
Nous contacter
Suivez la HES-SO
linkedin instagram facebook twitter youtube rss
univ-unita.eu www.eua.be swissuniversities.ch
Mentions légales
© 2021 - HES-SO.

HES-SO Rectorat