University Sétif 1 FERHAT ABBAS Faculty of Sciences
Catégories
Ajouter le résultat dans votre panier Affiner la recherche
Emotional facial expression Recognition / Soualah,Khalil
Titre : Emotional facial expression Recognition Type de document : texte imprimé Auteurs : Soualah,Khalil, Auteur ; Touahria,Mohamed, Directeur de thèse Editeur : Setif:UFA Année de publication : 2018 Importance : 1 vol (59 f .) Format : 29 cm Langues : Français (fre) Langues originales : Français (fre) Catégories : Thèses & Mémoires:Informatique Mots-clés : Apprentissage machine
Apprentissage profond
Expressions des emo-tions faciales
Réseau de neurones convolutifs
Reconnaissance des expressions faciales
K plus proche voisinIndex. décimale : 004 - Informatique Note de contenu :
Sommaire
Contents
List of figures
Acknowledgements
Abstract
Introdiction
Theoretical background
Emotional facial expressions recognition
Dataset and implementation
Conclusion
Bibliography
Côte titre : MAI/0221 Emotional facial expression Recognition [texte imprimé] / Soualah,Khalil, Auteur ; Touahria,Mohamed, Directeur de thèse . - [S.l.] : Setif:UFA, 2018 . - 1 vol (59 f .) ; 29 cm.
Langues : Français (fre) Langues originales : Français (fre)
Catégories : Thèses & Mémoires:Informatique Mots-clés : Apprentissage machine
Apprentissage profond
Expressions des emo-tions faciales
Réseau de neurones convolutifs
Reconnaissance des expressions faciales
K plus proche voisinIndex. décimale : 004 - Informatique Note de contenu :
Sommaire
Contents
List of figures
Acknowledgements
Abstract
Introdiction
Theoretical background
Emotional facial expressions recognition
Dataset and implementation
Conclusion
Bibliography
Côte titre : MAI/0221 Exemplaires (1)
Code-barres Cote Support Localisation Section Disponibilité MAI/0221 MAI/0221 Mémoire Bibliothéque des sciences Français Disponible
Disponible
Titre : Emotional Facial Expression Recognition Type de document : texte imprimé Auteurs : Hefassa, Maroua, Auteur ; Touahria,Mohamed, Directeur de thèse Editeur : Setif:UFA Année de publication : 2019 Importance : 1 vol (63 f .) Format : 29 cm Langues : Français (fre) Catégories : Thèses & Mémoires:Informatique Mots-clés : Apprentissage automatique
Réseaux de neurones convolutionnels
Reconnais-sance des expressions facialesIndex. décimale : 004 - Informatique Résumé : L’expression faciale est l’un des moyens puissants et naturels permettant aux êtres humains de communiquer leurs émotions et leurs intentions. La capacité à reconnaître les ex-pressions faciales émotionnelles est complexe lors des interactions. Dans le domaine de l'informatique affective, il s’agit de créer un modèle montrant l'importance de l'expression faciale. Dans notre étude, la méthode de reconnaissance des expressions faciales émotion-nelles est appliquée aux jeux de données Cohn Kanade et Japanese Female Facial Expression pour classifier les expressions faciales universellement reconnues. Dans nos expériences, nous proposons des architectures de réseaux de neurones convolutionnels profonds et ajustons deux modèles de pré-entraînement formés sur deux jeux de données tels que l’Inception et VGG-16 qui ont donné de meilleurs résultats. L'apprentissage en profondeur a le potentiel d'améliorer l'interaction homme-machine car sa capacité à apprendre des fonctionnalités permettra aux machines de développer leur perception. De plus, en ayant la perception, les machines fourni-ront potentiellement des réponses plus faciles, améliorant ainsi l'expérience de l'utilisateur. Note de contenu :
Sommaire
ACKNOWLEDGEMENTS ....................................................................................................1
ABSTRACT .................................................................................................2
CONTENTS ...................................................................................................3
LIST OF FIGURES ..............................................................................................................6
LIST OF TABLES ................................................................................................................7
INTRODUCTION ................................................................................................................8
1 THEORETICAL BACKGROUND ............................................................................ 10
1.1 INTRODUCTION ................................................................................... 10
1.2 MACHINE LEARNING CATEGORIES ........................................................................................................... 10
1.2.1 Supervised Learning ......................................................................................................... 10
1.2.2 Unsupervised Learning ............................................................................................................... 11
1.3 MACHINE LEARNING TASKS .................................................................................................. 11
1.3.1 Classification ................................................................................................... 11
1.3.1.1 Support Vector Machine .......................................................................................................... 12
1.3.1.2 Naïve Bayes Classifier ....................................................................................................... 13
1.3.1.3 Decision Tree ........................................................................................................ 14
1.3.1.4 Random Forest ................................................................................................ 14
1.3.1.5 Neural Network ................................................................................................. 15
1.3.1.6 Boosting ............................................................................................................... 16
1.3.2 Regression ............................................................................................................ 16
1.3.3 Clustering............................................................................................... 17
1.3.4 Deep Learning ........................................................................................................ 17
1.3.4.1 Optimization in deep learning ........................................................................................................... 18 1.3.4.2 Regularization for deep learning ....................................................................................................... 18
1.3.4.2.1 Dropout............................................................................................ 18
1.3.4.2.2 Batch normalization ................................................................................................ 19
1.3.4.2.3 Data Augmentation ................................................................................................... 19
1.3.4.3 Model parameters..................................................................................20
1.3.4.3.1 epoch ................................................................................................. 20
1.3.4.3.2 Batch ........................................................................................ 20
1.3.4.3.3 Batch size .........................................................................................
1.3.4.3.4 Loss function ..................................................................................................
20 1.3.4.3.5 Activation function ........................................................................................................... 20 1.3.4.4 Deep Learning Architectures ............................................................................................................. 21 1.3.4.4.1 Autoencoders (AE) ....................................................................................................... 21
1.3.4.4.2 Deep Belief Network (DBN) .......................................................................................................... 22
1.3.5 Convolutional Neural Networks .................................................................................................. 23
1.3.6 Transfer learning .......................................................................................................... 25
1.3.6.1 ImageNet ...................................................................................................... 25
1.3.6.2 Pretrained model ....................................................................................................... 25
1.3.6.2.1 VGG-16........................................................................................................ 25
1.3.6.2.2 Inception ............................................................................................................ 26
1.4 CONCLUSION .......................................................................................... 26
2 EMOTIONAL FACIAL EXPRESSIONS RECOGNITION ..................................... 27
2.1 INTRODUCTION ............................................................................................... 27
2.2 FACIAL EXPRESSIONS RECOGNITION APPLICATION DOMAIN ........................................................................... 27
4
2.3 PAUL EKMAN’S BASIC EMOTIONS ............................................................................................................ 27
2.4 EMOTIONAL FACIAL EXPRESSIONS RECOGNITION PROBLEMS .......................................................................... 29
2.5 FACIAL EXPRESSIONS RECOGNITION PROCESS ............................................................................................. 29
2.5.1 Face Detection ....................................................................................................... 30
2.5.1.1 Knowledge-based methods .............................................................................................................. 30
2.5.1.2 Feature invariant approaches ........................................................................................................... 30
2.5.2 Feature Extraction ....................................................................................................... 31
2.5.2.1 Appearance based methods ............................................................................................................. 31
2.5.2.1.1 Gabor Features ............................................................................................................................ 32
2.5.2.1.2 Haar features................................................................................33
2.5.2.1.3 Local Binary Pattern (LBP) features ............................................................................................... 34
2.5.2.2 Geometric feature based methods.................................................................................................... 35
2.5.3 Expression classification / recognition ........................................................................................ 35
2.6 CONCLUSION ........................................................................................................ 36
3 DATASET AND IMPLEMENTATION TOOLS ...................................................... 37
3.1 INTRODUCTION .................................................................................................................................. 37
3.2 AVAILABLE EMOTIONAL DATASET............................................................................................................ 37
3.2.1 Cohn-Kanade facial expression database .................................................................................... 37
3.2.2 Japanese Female Facial Expression (JAFFE) Dataset .................................................................... 39
3.3 IMPLEMENTATION FRAMEWORK AND TOOLS ............................................................................................. 39
3.3.1 Python ....................................................................................................................................... 40
3.3.2 Scikit-learn ................................................................................................................................. 40
3.3.3 Tensorflow ................................................................................................................................. 40
3.3.4 Keras ......................................................................................................................................... 40
3.3.5 Jupyter notebook ....................................................................................................................... 41
3.3.6 Google Colab ............................................................................................................................. 41
3.3.7 Kaggle ....................................................................................................................................... 42
3.4 MODEL EVALUATION METRICS ................................................................................................................ 42
3.4.1 Accuracy .................................................................................................................................... 42
3.4.2 Precision .................................................................................................................................... 42
3.4.3 Recall ......................................................................................................................................... 42
3.4.4 F1-score ..................................................................................................................................... 43
3.4.5 Confusion matrix ........................................................................................................................ 43
3.5 PROPOSED APPROACHES ....................................................................................................................... 43
3.5.1 Machine learning approaches .................................................................................................... 44
3.5.2 Deep learning approaches .......................................................................................................... 44
3.6 CONCLUSION ..................................................................................................................... 44
4 EXPERIMENTS AND RESULTS .............................................................................. 45
4.1 INTRODUCTION .................................................................................................................................. 45
4.2 MACHINE LEARNING APPROACHES ........................................................................................................... 45
4.2.1 Decision tree classifier ................................................................................................................ 45
4.2.2 XGBOOST classifier ..................................................................................................................... 45
4.2.3 Random forest classifier ............................................................................................................. 46
4.2.4 SVM classifier ........................................................................................................................ 46
4.2.5 Machine learning algorithms results ........................................................................................... 46
4.3 DEEP LEARNING APPROACHES ................................................................................................................ 47
4.3.1 Ck 48 dataset ............................................................................................................................. 47
4.3.1.1 Convolution neural network ............................................................................................................. 47
4.3.1.1.1 Model and architecture interpretation ......................................................................................... 48
4.3.1.1.2 Model compiling ........................................................................................................ 49
4.3.1.2 Transfer learning ....................................................................................................52
4.3.1.2.1 VGG-16 pretrained model ............................................................................................................ 53
4.3.1.2.2 Inception V3 pretrained model..................................................................................................... 54
4.3.2 JAFFE datasets ....................................................................................................... 56
4.3.2.1 Convolution neural networks ............................................................................................................ 56
4.3.2.1.1 First CNN architecture................................................................................................... 56
4.3.2.1.2 Second CNN architecture ............................................................................................................. 57
4.4 RESULTS COMPARISONS ........................................................................................................................ 60
4.4.1 First dataset (CK 48) ................................................................................................... 60
4.4.2 Second dataset (JAFFE)................................................................................................. 60
4.5 CONCLUSION ..................................................................................................................................... 61
CONCLUSION ................................................................................................................... 6
BIBLIOGRAPHY............................................................................................Côte titre : MAI/0328 En ligne : https://drive.google.com/file/d/1t_VL8jADg2PCheEX0lY6XF8hvoSu3pQp/view?usp=shari [...] Format de la ressource électronique : Emotional Facial Expression Recognition [texte imprimé] / Hefassa, Maroua, Auteur ; Touahria,Mohamed, Directeur de thèse . - [S.l.] : Setif:UFA, 2019 . - 1 vol (63 f .) ; 29 cm.
Langues : Français (fre)
Catégories : Thèses & Mémoires:Informatique Mots-clés : Apprentissage automatique
Réseaux de neurones convolutionnels
Reconnais-sance des expressions facialesIndex. décimale : 004 - Informatique Résumé : L’expression faciale est l’un des moyens puissants et naturels permettant aux êtres humains de communiquer leurs émotions et leurs intentions. La capacité à reconnaître les ex-pressions faciales émotionnelles est complexe lors des interactions. Dans le domaine de l'informatique affective, il s’agit de créer un modèle montrant l'importance de l'expression faciale. Dans notre étude, la méthode de reconnaissance des expressions faciales émotion-nelles est appliquée aux jeux de données Cohn Kanade et Japanese Female Facial Expression pour classifier les expressions faciales universellement reconnues. Dans nos expériences, nous proposons des architectures de réseaux de neurones convolutionnels profonds et ajustons deux modèles de pré-entraînement formés sur deux jeux de données tels que l’Inception et VGG-16 qui ont donné de meilleurs résultats. L'apprentissage en profondeur a le potentiel d'améliorer l'interaction homme-machine car sa capacité à apprendre des fonctionnalités permettra aux machines de développer leur perception. De plus, en ayant la perception, les machines fourni-ront potentiellement des réponses plus faciles, améliorant ainsi l'expérience de l'utilisateur. Note de contenu :
Sommaire
ACKNOWLEDGEMENTS ....................................................................................................1
ABSTRACT .................................................................................................2
CONTENTS ...................................................................................................3
LIST OF FIGURES ..............................................................................................................6
LIST OF TABLES ................................................................................................................7
INTRODUCTION ................................................................................................................8
1 THEORETICAL BACKGROUND ............................................................................ 10
1.1 INTRODUCTION ................................................................................... 10
1.2 MACHINE LEARNING CATEGORIES ........................................................................................................... 10
1.2.1 Supervised Learning ......................................................................................................... 10
1.2.2 Unsupervised Learning ............................................................................................................... 11
1.3 MACHINE LEARNING TASKS .................................................................................................. 11
1.3.1 Classification ................................................................................................... 11
1.3.1.1 Support Vector Machine .......................................................................................................... 12
1.3.1.2 Naïve Bayes Classifier ....................................................................................................... 13
1.3.1.3 Decision Tree ........................................................................................................ 14
1.3.1.4 Random Forest ................................................................................................ 14
1.3.1.5 Neural Network ................................................................................................. 15
1.3.1.6 Boosting ............................................................................................................... 16
1.3.2 Regression ............................................................................................................ 16
1.3.3 Clustering............................................................................................... 17
1.3.4 Deep Learning ........................................................................................................ 17
1.3.4.1 Optimization in deep learning ........................................................................................................... 18 1.3.4.2 Regularization for deep learning ....................................................................................................... 18
1.3.4.2.1 Dropout............................................................................................ 18
1.3.4.2.2 Batch normalization ................................................................................................ 19
1.3.4.2.3 Data Augmentation ................................................................................................... 19
1.3.4.3 Model parameters..................................................................................20
1.3.4.3.1 epoch ................................................................................................. 20
1.3.4.3.2 Batch ........................................................................................ 20
1.3.4.3.3 Batch size .........................................................................................
1.3.4.3.4 Loss function ..................................................................................................
20 1.3.4.3.5 Activation function ........................................................................................................... 20 1.3.4.4 Deep Learning Architectures ............................................................................................................. 21 1.3.4.4.1 Autoencoders (AE) ....................................................................................................... 21
1.3.4.4.2 Deep Belief Network (DBN) .......................................................................................................... 22
1.3.5 Convolutional Neural Networks .................................................................................................. 23
1.3.6 Transfer learning .......................................................................................................... 25
1.3.6.1 ImageNet ...................................................................................................... 25
1.3.6.2 Pretrained model ....................................................................................................... 25
1.3.6.2.1 VGG-16........................................................................................................ 25
1.3.6.2.2 Inception ............................................................................................................ 26
1.4 CONCLUSION .......................................................................................... 26
2 EMOTIONAL FACIAL EXPRESSIONS RECOGNITION ..................................... 27
2.1 INTRODUCTION ............................................................................................... 27
2.2 FACIAL EXPRESSIONS RECOGNITION APPLICATION DOMAIN ........................................................................... 27
4
2.3 PAUL EKMAN’S BASIC EMOTIONS ............................................................................................................ 27
2.4 EMOTIONAL FACIAL EXPRESSIONS RECOGNITION PROBLEMS .......................................................................... 29
2.5 FACIAL EXPRESSIONS RECOGNITION PROCESS ............................................................................................. 29
2.5.1 Face Detection ....................................................................................................... 30
2.5.1.1 Knowledge-based methods .............................................................................................................. 30
2.5.1.2 Feature invariant approaches ........................................................................................................... 30
2.5.2 Feature Extraction ....................................................................................................... 31
2.5.2.1 Appearance based methods ............................................................................................................. 31
2.5.2.1.1 Gabor Features ............................................................................................................................ 32
2.5.2.1.2 Haar features................................................................................33
2.5.2.1.3 Local Binary Pattern (LBP) features ............................................................................................... 34
2.5.2.2 Geometric feature based methods.................................................................................................... 35
2.5.3 Expression classification / recognition ........................................................................................ 35
2.6 CONCLUSION ........................................................................................................ 36
3 DATASET AND IMPLEMENTATION TOOLS ...................................................... 37
3.1 INTRODUCTION .................................................................................................................................. 37
3.2 AVAILABLE EMOTIONAL DATASET............................................................................................................ 37
3.2.1 Cohn-Kanade facial expression database .................................................................................... 37
3.2.2 Japanese Female Facial Expression (JAFFE) Dataset .................................................................... 39
3.3 IMPLEMENTATION FRAMEWORK AND TOOLS ............................................................................................. 39
3.3.1 Python ....................................................................................................................................... 40
3.3.2 Scikit-learn ................................................................................................................................. 40
3.3.3 Tensorflow ................................................................................................................................. 40
3.3.4 Keras ......................................................................................................................................... 40
3.3.5 Jupyter notebook ....................................................................................................................... 41
3.3.6 Google Colab ............................................................................................................................. 41
3.3.7 Kaggle ....................................................................................................................................... 42
3.4 MODEL EVALUATION METRICS ................................................................................................................ 42
3.4.1 Accuracy .................................................................................................................................... 42
3.4.2 Precision .................................................................................................................................... 42
3.4.3 Recall ......................................................................................................................................... 42
3.4.4 F1-score ..................................................................................................................................... 43
3.4.5 Confusion matrix ........................................................................................................................ 43
3.5 PROPOSED APPROACHES ....................................................................................................................... 43
3.5.1 Machine learning approaches .................................................................................................... 44
3.5.2 Deep learning approaches .......................................................................................................... 44
3.6 CONCLUSION ..................................................................................................................... 44
4 EXPERIMENTS AND RESULTS .............................................................................. 45
4.1 INTRODUCTION .................................................................................................................................. 45
4.2 MACHINE LEARNING APPROACHES ........................................................................................................... 45
4.2.1 Decision tree classifier ................................................................................................................ 45
4.2.2 XGBOOST classifier ..................................................................................................................... 45
4.2.3 Random forest classifier ............................................................................................................. 46
4.2.4 SVM classifier ........................................................................................................................ 46
4.2.5 Machine learning algorithms results ........................................................................................... 46
4.3 DEEP LEARNING APPROACHES ................................................................................................................ 47
4.3.1 Ck 48 dataset ............................................................................................................................. 47
4.3.1.1 Convolution neural network ............................................................................................................. 47
4.3.1.1.1 Model and architecture interpretation ......................................................................................... 48
4.3.1.1.2 Model compiling ........................................................................................................ 49
4.3.1.2 Transfer learning ....................................................................................................52
4.3.1.2.1 VGG-16 pretrained model ............................................................................................................ 53
4.3.1.2.2 Inception V3 pretrained model..................................................................................................... 54
4.3.2 JAFFE datasets ....................................................................................................... 56
4.3.2.1 Convolution neural networks ............................................................................................................ 56
4.3.2.1.1 First CNN architecture................................................................................................... 56
4.3.2.1.2 Second CNN architecture ............................................................................................................. 57
4.4 RESULTS COMPARISONS ........................................................................................................................ 60
4.4.1 First dataset (CK 48) ................................................................................................... 60
4.4.2 Second dataset (JAFFE)................................................................................................. 60
4.5 CONCLUSION ..................................................................................................................................... 61
CONCLUSION ................................................................................................................... 6
BIBLIOGRAPHY............................................................................................Côte titre : MAI/0328 En ligne : https://drive.google.com/file/d/1t_VL8jADg2PCheEX0lY6XF8hvoSu3pQp/view?usp=shari [...] Format de la ressource électronique : Exemplaires (1)
Code-barres Cote Support Localisation Section Disponibilité MAI/0328 MAI/0328 Mémoire Bibliothéque des sciences Français Disponible
Disponible
Titre : Energy routing Type de document : texte imprimé Auteurs : Ahmed Sebaihi, Auteur ; ali Tercha, Auteur Année de publication : 2022 Importance : 1 vol (49 f .) Format : 29cm Langues : Français (fre) Catégories : Thèses & Mémoires:Informatique Mots-clés : Informatique
Power systems
Energy tradingIndex. décimale : 004 Informatique Résumé :
Energy from small-scale Distributed Energy Resources (DERs) in households, workplaces, factories, and
other locations is traded between local energy prosumers and consumers in peer-to-peer (P2P) energy trading
system. The rising cost of energy and the finite availability of fossil fuels make it inevitable that distributed
energy, such as renewable energy, will be introduced into the existing supply system in the future.Energy Internet
(EI) is a futuristic evolution of the energy system, conceived as a peer-to-peer energy trading network,
with the characteristics of a futuristic system of diverse prosumers. EI is a model of the information internet
paradigm, with characteristics such as an energy router for managing optimal power and communication. EI
faced some problems such as:Subscriber Matching,Energy Efficient-path and Congestion Management. In this
work, we propose a Q-learning based solution for matching subscribers and shortestpath-based efficient-energy
routing. The new solution is applied in mono and multi-source in addition to multi-path scenarios. The results
obtained show its efficiency in terms of cost and power losses in small and large-scale power energy internet
systems.Côte titre : MAI/0570 En ligne : https://drive.google.com/file/d/1BOT4ZKYgLQKPnGIVUcs4wHmH1amOYYu8/view?usp=share [...] Format de la ressource électronique : Energy routing [texte imprimé] / Ahmed Sebaihi, Auteur ; ali Tercha, Auteur . - 2022 . - 1 vol (49 f .) ; 29cm.
Langues : Français (fre)
Catégories : Thèses & Mémoires:Informatique Mots-clés : Informatique
Power systems
Energy tradingIndex. décimale : 004 Informatique Résumé :
Energy from small-scale Distributed Energy Resources (DERs) in households, workplaces, factories, and
other locations is traded between local energy prosumers and consumers in peer-to-peer (P2P) energy trading
system. The rising cost of energy and the finite availability of fossil fuels make it inevitable that distributed
energy, such as renewable energy, will be introduced into the existing supply system in the future.Energy Internet
(EI) is a futuristic evolution of the energy system, conceived as a peer-to-peer energy trading network,
with the characteristics of a futuristic system of diverse prosumers. EI is a model of the information internet
paradigm, with characteristics such as an energy router for managing optimal power and communication. EI
faced some problems such as:Subscriber Matching,Energy Efficient-path and Congestion Management. In this
work, we propose a Q-learning based solution for matching subscribers and shortestpath-based efficient-energy
routing. The new solution is applied in mono and multi-source in addition to multi-path scenarios. The results
obtained show its efficiency in terms of cost and power losses in small and large-scale power energy internet
systems.Côte titre : MAI/0570 En ligne : https://drive.google.com/file/d/1BOT4ZKYgLQKPnGIVUcs4wHmH1amOYYu8/view?usp=share [...] Format de la ressource électronique : Exemplaires (1)
Code-barres Cote Support Localisation Section Disponibilité MAI/0570 MAI/0570 Mémoire Bibliothéque des sciences Anglais Disponible
Disponible
Titre : Energy routing protocol in Energy Internet Type de document : texte imprimé Auteurs : Guettar, Haithem, Auteur ; Djamila Mechta, Auteur Importance : 1 vol (36 f .) Format : 29 cm Langues : Français (fre) Catégories : Thèses & Mémoires:Informatique Mots-clés : Congestion management
Optimization
P2P Distributed energy tradingIndex. décimale : 004 - Informatique Résumé :
The energy internet is a new emerging concept which is mainly associated with
peer to peer energy trading in a smart grid power network. This new power system
(EI) aims to make the use of energy renewable resources eective and it also supports
the bidirectional power and data
ow. As any power system, energy internet has
faced three main issues; subscriber matching, energy ecient path and congestion
management. In this paper, we proposed a grey wolf optimization based on an energy
routing algorithm to determine a non-congestion minimum loss path. A subscriber
matching was developed to determine which producer/producers should be assigned
for each consumer by optimizing the tness, this mechanism provides a solution for
both mono and multi- source consumers. For the multi-source consumers an energy
moth
ames optimization algorithm is proposed to choose the best producers and their
energy capacities that satised the consumer's requests , the producers' selection is
based on the lowest tness ie; the less coast and less power loss. Finally, simulation
results show the eectiveness of the proposed approach.Côte titre : MAI/0464 En ligne : https://drive.google.com/file/d/14wrC8f7laDhOiCMP6k8RcwtZb6jlPvBp/view?usp=shari [...] Format de la ressource électronique : Energy routing protocol in Energy Internet [texte imprimé] / Guettar, Haithem, Auteur ; Djamila Mechta, Auteur . - [s.d.] . - 1 vol (36 f .) ; 29 cm.
Langues : Français (fre)
Catégories : Thèses & Mémoires:Informatique Mots-clés : Congestion management
Optimization
P2P Distributed energy tradingIndex. décimale : 004 - Informatique Résumé :
The energy internet is a new emerging concept which is mainly associated with
peer to peer energy trading in a smart grid power network. This new power system
(EI) aims to make the use of energy renewable resources eective and it also supports
the bidirectional power and data
ow. As any power system, energy internet has
faced three main issues; subscriber matching, energy ecient path and congestion
management. In this paper, we proposed a grey wolf optimization based on an energy
routing algorithm to determine a non-congestion minimum loss path. A subscriber
matching was developed to determine which producer/producers should be assigned
for each consumer by optimizing the tness, this mechanism provides a solution for
both mono and multi- source consumers. For the multi-source consumers an energy
moth
ames optimization algorithm is proposed to choose the best producers and their
energy capacities that satised the consumer's requests , the producers' selection is
based on the lowest tness ie; the less coast and less power loss. Finally, simulation
results show the eectiveness of the proposed approach.Côte titre : MAI/0464 En ligne : https://drive.google.com/file/d/14wrC8f7laDhOiCMP6k8RcwtZb6jlPvBp/view?usp=shari [...] Format de la ressource électronique : Exemplaires (1)
Code-barres Cote Support Localisation Section Disponibilité MAI/0464 MAI/0464 Mémoire Bibliothéque des sciences Français Disponible
DisponibleEnhancing a Collaborative Recommender System Based on Deep Learning for Online Resources / Manar Nedjai
Titre : Enhancing a Collaborative Recommender System Based on Deep Learning for Online Resources Type de document : texte imprimé Auteurs : Manar Nedjai, Auteur ; Roumaissa Dana, Auteur ; Mediani,Chahrazed, Directeur de thèse Année de publication : 2023 Importance : 1 vol (59 f .) Format : 29cm Langues : Français (fre) Catégories : Thèses & Mémoires:Informatique Mots-clés : Collaborative filtering
Recommender systemsIndex. décimale : 004 Informatique Résumé : Recommender Systems are software that can be used to filter out data from the volumes of
data available online and provide recommendations to users in their area of interest. Recommender
systems are classified into three types which are collaborative, content-based and hybrid.
Among the proposed classifications, the collaborative filtering approach consists of finding
the item that satisfies the user using other similar users evaluations. In recent years, deep neural
networks have yielded immense success on many fields. However, some recent works have
focused on combining deep learning with recommendation and have shown improvement in performance.
In this thesis, we presented a novel model CFDAE to recommend online resources
based on collaborative filtering using the denoising autoencoder, our model can perform good
results in rating prediction of explicit feedback.Côte titre : MAI/0708 En ligne : https://drive.google.com/file/d/1gGj42ULJFZ11uwRcTO-gI1ySus9bQy8j/view?usp=drive [...] Format de la ressource électronique : Enhancing a Collaborative Recommender System Based on Deep Learning for Online Resources [texte imprimé] / Manar Nedjai, Auteur ; Roumaissa Dana, Auteur ; Mediani,Chahrazed, Directeur de thèse . - 2023 . - 1 vol (59 f .) ; 29cm.
Langues : Français (fre)
Catégories : Thèses & Mémoires:Informatique Mots-clés : Collaborative filtering
Recommender systemsIndex. décimale : 004 Informatique Résumé : Recommender Systems are software that can be used to filter out data from the volumes of
data available online and provide recommendations to users in their area of interest. Recommender
systems are classified into three types which are collaborative, content-based and hybrid.
Among the proposed classifications, the collaborative filtering approach consists of finding
the item that satisfies the user using other similar users evaluations. In recent years, deep neural
networks have yielded immense success on many fields. However, some recent works have
focused on combining deep learning with recommendation and have shown improvement in performance.
In this thesis, we presented a novel model CFDAE to recommend online resources
based on collaborative filtering using the denoising autoencoder, our model can perform good
results in rating prediction of explicit feedback.Côte titre : MAI/0708 En ligne : https://drive.google.com/file/d/1gGj42ULJFZ11uwRcTO-gI1ySus9bQy8j/view?usp=drive [...] Format de la ressource électronique : Exemplaires (1)
Code-barres Cote Support Localisation Section Disponibilité MAI/0708 MAI/0708 Mémoire Bibliothéque des sciences Anglais Disponible
DisponibleEnhancing a Content-Based Recommender System using Deep Learning for Online Resources / hanane Bouaziz
PermalinkPermalinkPermalinkEnsemble Deep Learning-based Semantic Segmentation and Classification of Leaves Images for Agricultural Apple and Wheat Diseases’ Detection / Naryméne Kebiche
PermalinkPermalinkL’épidémiologie des fakenews sur les Réseaux sociaux, étude comparative entre Twitter et FaceBook. / Laouarem ,Raihen
PermalinkPermalinkPermalinkPermalinkEstimation des précipitations à partir des images satellitaires en utilisant les réseaux de neurones profonds / Dounia Zed Sid
Permalink