E-commerce Time Series Forecasting using LSTM Neural Network and Support Vector Regression

Autor: Ghassen Chniti, Houda Bakir, Hédi Zaher

Publikováno v: BDIOT

The purpose of this paper is to provide a robust forecasting model to predict phone prices on European markets using Long Short Term Memory neural network (LSTM) and Support Vector Regression (SVR). We propose a comparison study of time series foreca

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::69e17bf11323a8def7606bf867d99bd4
https://doi.org/10.1145/3175684.3175695

Multi-Dimensional Methods for Registering and Searching for Documents

Autor: Manuel Zacklad, Mohamed Hédi Zaher, Camille Vaucelle

Publikováno v: France, Patent n° : FR2957703. 2011
HAL

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::d406528e69130e355d8ba4344b8a5a12
https://hal-utt.archives-ouvertes.fr/hal-02953996

Document et modèle pour l'action, une méthode pour le web socio-sémantique. Application à un web 2.0 en développement durable

Autor: Gilbert Isoard, Jean-Pierre Cahier, L'Hédi Zaher

Publikováno v: Document Numérique
Document Numérique, Lavoisier, 2010, 13 (2), pp.75-96. ⟨10.3166/DN.13.2.75-96⟩
Document numérique-Revue des sciences et technologies de l'information. Série Document numérique
Document numérique-Revue des sciences et technologies de l'information. Série Document numérique, 2010, 13 (2), pp.75-96. ⟨10.3166/DN.13.2.75-96⟩

International audience; We present the DOCMA method (DOCument and Model for Action) focused toSocio-Semantic web applications in large communities of interest. DOCMA is dedicated toend-users without any knowledge in Information Science. Community Mem

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0d1f40be16aec0a2614e071d69687c05
https://hal-utt.archives-ouvertes.fr/hal-02882129

Cooperative Building of Multiple Points-of-View Topic Maps with Hypertopic

Autor: Claude Guittard, L'Hédi Zaher, Jean-Pierre Cahier

Publikováno v: Scaling Topic Maps ISBN: 9783540708735
TMRA
Scaling Topic Maps : third international conference on topic maps research and applications, TMRA 2007
Maicher, Lutz; Garshol, Lars Marius (informaticien). Scaling Topic Maps : third international conference on topic maps research and applications, TMRA 2007, 4999, Springer Berlin Heidelberg, pp.154-159, 2008, Lecture Notes in Computer Science, 978-3-540-70873-5. ⟨10.1007/978-3-540-70874-2_15⟩

International audience; This paper presents socio-semantic web applications based on the Hypertopic knowledge representation model. The Hypertopic [4] model is used to collaboratively construct topic maps with multiple user points-of-view within rela

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6d38d0833682d1214075116e85366acd
https://doi.org/10.1007/978-3-540-70874-2_15

Applications of Knowledge Engineering Approaches for Design

Autor: Nada Matta, L'Hédi Zaher

Publikováno v: Methods and Tools for Effective Knowledge Life-Cycle-Management ISBN: 9783540784302
Methods and Tools for Effective Knowledge Life-Cycle-Management
Methods and Tools for Effective Knowledge Life-Cycle-Management, Springer Berlin Heidelberg, pp.363-373, 2008, ⟨10.1007/978-3-540-78431-9_20⟩

International audience; In this chapter, we present knowledge engineering (KE) and knowledge management (KM) techniques and applications in design. Then, we introduce an original model of knowledge representation called Hypertopic, and different meth

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b6307d1c4df3748ca96c02f13a971e6c
https://doi.org/10.1007/978-3-540-78431-9_20