Skip to main content

Samir Bennani

Followers

50

Following

2

Co-authors

2

Public Views

Jeewantinie Kapilaratne

Nagaoka University of Technology

International Journal of Electrical and Computer Engineering (IJECE)

PUC-RJ

Daliana Lobo Torres

Angelo Bonfitto

Politecnico di Torino

Mahendra Gourisaria

Uploads

Papers by Samir Bennani

Railway Track Faults Detection Based on Image Processing Using Mobilenet

The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences

The use of rail transport is increasing. Damaged rails interrupt traffic to carry out repairs. In... more The use of rail transport is increasing. Damaged rails interrupt traffic to carry out repairs. In fact, when a conductor or railway operator reports a damaged rail that interrupted the traffic in the affected area. A team of specialized agents dispatch to the site and carries out the repairs. Hence, the importance of automation of railway track faults detection to ensure track safety and reduce maintenance costs. In this work, we propose a method using image processing technologies and deep learning networks. We have studied the correlation effects of MobileNetV2 and optimization algorithms on accuracy and other performance metrics to generate a model that can achieve good performance in classifying railway track faults. The results show that the Rmsprop can improve the effectiveness of feature extraction and classification of MobileNetV2.

Knowledge graph-based method for solutions detection and evaluation in an online problem-solving community

International Journal of Electrical and Computer Engineering (IJECE)

Online communities are a real medium for human experiences sharing. They contain rich knowledge o... more Online communities are a real medium for human experiences sharing. They contain rich knowledge of lived situations and experiences that can be used to support decision-making process and problem-solving. This work presents an approach for extracting, representing, and evaluating components of problem-solving knowledge shared in online communities. Few studies have tackled the issue of knowledge extraction and its usefulness evaluation in online communities. In this study, we propose a new approach to detect and evaluate best solutions to problems discussed by members of online communities. Our approach is based on knowledge graph technology and graphs theory enabling the representation of knowledge shared by the community and facilitating its reuse. Our process of problem-solving knowledge extraction in online communities (PSKEOC) consists of three phases: problems and solutions detection and classification, knowledge graph constitution and finally best solutions evaluation. The ex...

Boosting E-learner’s Motivation through Identifying his/her Emotional States

Iraqi journal of science, 2021

The main objective of e-learning platforms is to offer a high quality instructing, training and e... more The main objective of e-learning platforms is to offer a high quality instructing, training and educational services. This purpose would never be achieved without taking the students' motivation into consideration. Examining the voice, we can decide the emotional states of the learners after we apply the famous theory of psychologist SDT (Self Determination Theory). This article will investigate certain difficulties and challenges which face e-learner: the problem of leaving their courses and the student's isolation.Utilizing Gussian blending model (GMM) so as to tackle and to solve the problems of classification, we can determine the learning abnormal status for e-learner. Our framework is going to increase the students’ motivation through utilizing the notion of agent. Furthermore, it helps to assess teacher with the learning efficiency through putting attention on the learners who have the problems to accomplish the courses' objectives.This will help educatorsto contr...

Automatisation Hyperparameters Tuning Process for Times Series Forecasting: Application to Passenger’s Flow Prediction on a Railway Network

The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences

Many industries and companies in various fields are interested in time series analysis to predict... more Many industries and companies in various fields are interested in time series analysis to predict the future. However, in time series modeling, precision is lacking as time progress. In this paper, an architecture is proposed, allowing on the one hand keep the prediction accurate over time using the Walk Forward Optimization (WFO); On the other hand, automate the choice of parameters of the statistical models (ARIMA) introducing "AutoArima"; The RNN models, especially LSTM architectures (LSTM, Bi-LSTM, Stacked LSTM) using the function Optuna. Moreover, to avoid overfitting the LSTM models, an automatic function is implemented in the presented architecture. To demonstrate the validity of this research, a comparison of three models applied to a railway company to predict the flow of passengers is made. In particular, the naive model constitutes a reference base, the ARIMA model which had demonstrated its performances in several research, and finally, following the last progress in the neural networks the LSTM architecture is introduced in the paper. According to the results, the implemented architecture has great potential and more accurate predictions by using WFO. Through the comparisons of the models made, Each model has proven its performance according to the case of study. More concretely the mean absolute error obtained by LSTM for the railway stations is 0,13 compared to 0,15 obtained by ARIMA and 0,16 for the naive model, showing a small superiority for LSTM over ARIMA. On the other side, ARIMA excels on the Train lines.

Cognitive Learning Style Detection in e-Learning Environments using Artificial Neural Network

International Journal of Emerging Technologies in Learning (iJET)

COVID-19 pandemic has impacted all aspects of our lives including learning. With the particular g... more COVID-19 pandemic has impacted all aspects of our lives including learning. With the particular growth of e-learning, teaching approaches are being implemented at a distance on online platforms due to this pandemic. In this context, to make student involved throughout the online course, it is recommended to create an efficient platform similar to the traditional learning mode. In this study, we aims to improve learning style detection process by exploring additional such as cognitive traits. In fact, we have proposed novel approach based on Artificial neural network that classify students according to their level of cognitive learning styles in real-time. The proposed automated approach will certainly provide tutors with exhaustive information that helps them in achieving an improved and innovative online learning method. The results obtained are quite interesting and demonstrate the relevance of our solution.

Towards a New Mobile Educational Model

International Journal of Systems Applications, Engineering & Development, 2021

The development of mobile technologies and wireless networks encourages more research on Mobile L... more The development of mobile technologies and wireless networks encourages more research on Mobile Learning. Reviewing irregular verbs on a bus or organizing a training schedule on a Smartphone is becoming more common today. Mobile learning complements and enhances existing learning systems. Its development has been slowed in the early 2000s by both technical limitations and lack of dedicated teaching models. This article focuses on educational issues and proposes a solution by adopting the Method for Engineering Learning Systems MISA. Our work aims to identify basic elements, key characteristics and dimensions for developing the appropriate content for mobility. These elements are the basis for customization of the MISA method. Indeed, the different steps of MISA are governed by operating principles which ensure greater consistency and flexibility. Taking into account the specifications of Mobile learning in the development of these principles, we can adapt MISA to design a mobile lea...

Competency-Based Assessment

Learning and Performance Assessment, 2020

Competency-based Assessment (CBA) is the measurement of student's competency against a standa... more Competency-based Assessment (CBA) is the measurement of student's competency against a standard of performance. It is a process of collecting evidences to analyze student's progress and achievement. In higher education, Competency-based Assessment puts the focus on learning outcomes to constantly improve academic programs and meet labor market demands. As of to date, competencies are described using natural language but rarely used in e-learning systems, and the common sense idea is that: the way competency is defined shapes the way it is conceptualized, implemented and assessed. The main objective of this chapter is to introduce and discuss Competency-based Assessment from a methodological and technical perspectives. More specifically, the objective is to highlight ongoing issues regarding competency assessment in higher education in the 21st century, to emphasis the benefits of its implementation and finally to discuss some competency modeling and assessment techniques.

Mobile Serious Game Design using User Experience: Modeling of Software Product Line Variability

International Journal of Emerging Technologies in Learning (iJET), 2019

In recent years, gamification has emerged as a new approach to increasing learner engagement. It ... more In recent years, gamification has emerged as a new approach to increasing learner engagement. It covers a very wide range of games with very different purposes and with many fields of application. However, most of the gamification solutions proposed do not adopt the same modeling approach and little attention has been paid to mobile serious games (MSG) belonging to different pedagogical contexts. In order to overcome these difficulties, we have developed in this paper a generic model based on the Software Product Line (SPL) approach to manage the common and variable points of the MSG product set. We have also focused on the User eXperience (UX) concept to study the aspects that most affect the player’s experience in the context of MSGs. These aspects have been modeled in the form of features in the SPL Feature Model. MSG designers can use the model proposed during the development process, both to manage variability and to create an effective and fun learning environment.

Towards an Adaptive competency-based learning System using assessment

E-learning is not restricted to publishing online content. The challenge is to apply pedagogical ... more E-learning is not restricted to publishing online content. The challenge is to apply pedagogical models using new information and communication technologies in order to adjust the learning process. This adaptation will take place by proposing an adaptive learning system. There are several e-learning environment adaptation approaches such as adaptive hypermedia and semantic web. In our proposed system, we focus on evaluation that has not been, up till now, given its real value in the e-learning environment. The purpose is to implement an adaptive learning system for individualized pedagogical paths through a personalized diagnosis of learners’ performances. This proposed system relies mainly on assessment and the competency-based approach as a framework. To achieve this goal, we adopt an enhanced cycle of formative assessment while adhering to a service-oriented architecture. The system will be implemented as an activity in a pedagogical scenario defined responding to the learner’s n...

A Neuro-Fuzzy Inference System for the Evaluation of Reading/Writing Competencies Acquisition in an E-Learning Environnement

In the field of education, the evaluation of learning is one of the most important operations thr... more In the field of education, the evaluation of learning is one of the most important operations through the learning process. The evaluation concern arises in a more enhanced way in online learning environment given the significant reduction in direct contact of the tutor with the learners. In this paper, we address the specific problem of educational assessment of reading/writing competencies acquisition in amazigh language, based on the interactions of learners with an assessment test which consists of different items and served in a LMS platform. An online model based on artificial intelligence techniques, specifically multi-input-multi-output adaptive neuro-fuzzy inference System noted also CANFIS for co-active ANFIS, is proposed. The training and testing data, generated from the study of the curricula and the referential framework, are presented to the designed system for the optimization of inference engine parameters. Results of training and testing the system show an acceptabl...

Recommendation Systems on E-Learning and Social Learning: A Systematic Review

Electronic Journal of e-Learning

E-learning is renowned as one of the highly effective modalities of learning. Social learning, in... more E-learning is renowned as one of the highly effective modalities of learning. Social learning, in turn, is considered to be of major importance as it promotes collaboration between learners. For properly managing learning resources, recommender systems have been implemented in e-learning to enhance learners' experience. Whilst recommender systems are of widespread concern in online learning, it is still unclear to educators how recommender systems can improve the learning process and have a positive impact on learning. This paper seeks to provide an overview of the recommender systems proposed in e-learning between 2007 and the first part of 2021. Out of 100 initially identified publications for the period between 2007 and the first part of 2021, 51 articles were included for final synthesis, according to specific criteria. The descriptive results show that most of the disciplines involved in educational recommender systems papers have approached e-learning in a general way with...

Serious Games Modeling

by Samir Bennani, Asmaâ RETBI, and Chaimae Meftah

Recently, serious games have become a crucial strategy that is devoted to improve e-learning. Now... more Recently, serious games have become a crucial strategy that is devoted to improve e-learning. Nowadays, they play an important role in attaching player and learner to learn by having fun and to retain as much pedagogical information as possible. As a result, it is necessary to extend the life cycle of an SG, enriching it with important educational content, as well as an appropriate model that will increase the learner's performance and profitability and, avoid the boring aspect of SG in the future. In our article, we will discuss the effectiveness of serious games in the world of education. Then, we will propose a study on the Freemium model that we will adopt to improve the modeling of serious games for the benefit of e-learning, and finally, we will discuss the strengths of the existing model that we intend to develop in future communications.

A Novel Hybrid Recommendation Approach Based on Correlation and Co-occurrence Between Activities Within Social Learning Network

by Asmaâ RETBI and Samir Bennani

Automatic Composition of Instructional Units in Virtual Learning Environments

International Journal of Emerging Technologies in Learning (iJET), 2018

In this paper, a new approach for automatic composition of instructional units based on a new var... more In this paper, a new approach for automatic composition of instructional units based on a new variant of Harmony Search Algorithm is proposed. The purpose is to solve curriculum sequencing issue by designing and arranging learning content in a suitable sequence. By suitable sequence we mean a learning sequence that fits learner level and presents the content in a way that conveys its structure to learner. Results show that the proposed approach is promising. For instance, individualized courseware plan are generated “on the spot” carefully considering both students characteristics and subject-matter coherence.

Service Orchestration Algorithm for Web Services: Evaluation and Analysis

With the growing need for service oriented architecture and the rise of cloud computing, web serv... more With the growing need for service oriented architecture and the rise of cloud computing, web services have become the focus of many researchers and software developers. Our area of focus is web service composition. In this paper we are presenting an evaluation and analysis of the proposed orchestration algorithm in

Ontology of the CBA: Towards Operationalization and Implementation

Innovations in Smart Cities and Applications

To remedy inefficiency and increase the quality of learning, training systems have adopted a peda... more To remedy inefficiency and increase the quality of learning, training systems have adopted a pedagogical approach based on competence bases. It is a concept that is common to the academic and professional communities; which imposes the use of ontology of the CBA to conceptualize a dynamic repository, determining the terminological semantics of skills, which is sectorial with pedagogical norms. We propose a CBA ontology that focuses on explicit modeling of competency in order to provide a shared formal representation that promotes exchange, interoperability and collaboration among the various users in the learning systems. Our goal is not just to build an appropriate ontology. Our ambition is to implement this solution in an authoring system to assist tutors with didactic intentions based on skills to produce CBA based educational content.

A Novel ontology-based automatic method to predict learning style using Felder-silverman model

2018 17th International Conference on Information Technology Based Higher Education and Training (ITHET)

learning style is considered as preferred manner in which learners acquire effectively new knowle... more learning style is considered as preferred manner in which learners acquire effectively new knowledge. Individual’s learning style contains mainly his preferences, his expectations and his needs. In addition, it represents a key asset in improving teaching methods that meet learners’ needs. During the last decades, the identification of learning style methods has been relied on two basic measure methods: collaborative and automated ones. In this paper, we propose automatic test PRFSLM is based on Felder-Silverman learning style model (FSLM) that helps instructors to create and personalize their placement task’s items. Our proposed ontology-based automatic method aims (1) to assess the learner’s prerequisites and also (2) to provide explicitly an extensive knowledge about learner preferences that could predict his own learning style at the beginning of an online training.

Adaptive Educational Games Using Game Metrics

Video games are ostensibly adopted in the education field thanks to their engaging, immersive and... more Video games are ostensibly adopted in the education field thanks to their engaging, immersive and adaptive capacities. The greatest problematic in educational games design is how to create a ludic and adaptive experience without neglecting the learning objectives. To create an adaptive educational game modeling the player/learner is a must. In fact, determining the playing/learning style and measuring the player’s abilities and performances will help in adjusting the game content and difficulty. The aim of this paper is to explain how the Adaptive Mechanism for Educational Games (AMEG) adapts the game using metrics. We will define the kind of metrics that the mechanism collects and how they are used to define the learning/playing style as well as their importance in gameplay and learning content adaptation.

Actor’s knowledge massive identification in the learning management system

Intelligent Systems and Learning Data Analytics in Online Education, 2021

Toward a Use of Ontology to Reinforcing Semantic Classification of Message Based On LSA

World Academy of Science, Engineering and Technology, International Journal of Computer, Electrical, Automation, Control and Information Engineering, 2010

1101 Abstract— For best collaboration, Asynchronous tools and part icularly the discussion forums... more 1101 Abstract— For best collaboration, Asynchronous tools and part icularly the discussion forums are the most used thanks to t heir flexibility in terms of time. To convey only the messages that belong to a theme of interest of the tutor in order to help him during his tutoring work , use of a tool for classification of these messages is indispensable. For this we have proposed a semantics classification tool of messages of a disc ussion forum that is based on LSA (Latent Semantic Analysis), which includes a thesaurus to organize the vocabulary. Benefits offered by formal ontology can overcome the insufficiencies that a thesaurus generates during i ts use and encourage us then to use it in our semantic classifier. In this work we propose the use of some functionali ties that a OWL ontology proposes. We then explain how functionalities like “ObjectProperty”, ”SubClassOf” and “Datatype” property make our class ification more intelligent by way of integrating new terms. New te rms fou...

Railway Track Faults Detection Based on Image Processing Using Mobilenet

The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences

The use of rail transport is increasing. Damaged rails interrupt traffic to carry out repairs. In... more The use of rail transport is increasing. Damaged rails interrupt traffic to carry out repairs. In fact, when a conductor or railway operator reports a damaged rail that interrupted the traffic in the affected area. A team of specialized agents dispatch to the site and carries out the repairs. Hence, the importance of automation of railway track faults detection to ensure track safety and reduce maintenance costs. In this work, we propose a method using image processing technologies and deep learning networks. We have studied the correlation effects of MobileNetV2 and optimization algorithms on accuracy and other performance metrics to generate a model that can achieve good performance in classifying railway track faults. The results show that the Rmsprop can improve the effectiveness of feature extraction and classification of MobileNetV2.

Knowledge graph-based method for solutions detection and evaluation in an online problem-solving community

International Journal of Electrical and Computer Engineering (IJECE)

Online communities are a real medium for human experiences sharing. They contain rich knowledge o... more Online communities are a real medium for human experiences sharing. They contain rich knowledge of lived situations and experiences that can be used to support decision-making process and problem-solving. This work presents an approach for extracting, representing, and evaluating components of problem-solving knowledge shared in online communities. Few studies have tackled the issue of knowledge extraction and its usefulness evaluation in online communities. In this study, we propose a new approach to detect and evaluate best solutions to problems discussed by members of online communities. Our approach is based on knowledge graph technology and graphs theory enabling the representation of knowledge shared by the community and facilitating its reuse. Our process of problem-solving knowledge extraction in online communities (PSKEOC) consists of three phases: problems and solutions detection and classification, knowledge graph constitution and finally best solutions evaluation. The ex...

Boosting E-learner’s Motivation through Identifying his/her Emotional States

Iraqi journal of science, 2021

The main objective of e-learning platforms is to offer a high quality instructing, training and e... more The main objective of e-learning platforms is to offer a high quality instructing, training and educational services. This purpose would never be achieved without taking the students' motivation into consideration. Examining the voice, we can decide the emotional states of the learners after we apply the famous theory of psychologist SDT (Self Determination Theory). This article will investigate certain difficulties and challenges which face e-learner: the problem of leaving their courses and the student's isolation.Utilizing Gussian blending model (GMM) so as to tackle and to solve the problems of classification, we can determine the learning abnormal status for e-learner. Our framework is going to increase the students’ motivation through utilizing the notion of agent. Furthermore, it helps to assess teacher with the learning efficiency through putting attention on the learners who have the problems to accomplish the courses' objectives.This will help educatorsto contr...

Automatisation Hyperparameters Tuning Process for Times Series Forecasting: Application to Passenger’s Flow Prediction on a Railway Network

The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences

Many industries and companies in various fields are interested in time series analysis to predict... more Many industries and companies in various fields are interested in time series analysis to predict the future. However, in time series modeling, precision is lacking as time progress. In this paper, an architecture is proposed, allowing on the one hand keep the prediction accurate over time using the Walk Forward Optimization (WFO); On the other hand, automate the choice of parameters of the statistical models (ARIMA) introducing "AutoArima"; The RNN models, especially LSTM architectures (LSTM, Bi-LSTM, Stacked LSTM) using the function Optuna. Moreover, to avoid overfitting the LSTM models, an automatic function is implemented in the presented architecture. To demonstrate the validity of this research, a comparison of three models applied to a railway company to predict the flow of passengers is made. In particular, the naive model constitutes a reference base, the ARIMA model which had demonstrated its performances in several research, and finally, following the last progress in the neural networks the LSTM architecture is introduced in the paper. According to the results, the implemented architecture has great potential and more accurate predictions by using WFO. Through the comparisons of the models made, Each model has proven its performance according to the case of study. More concretely the mean absolute error obtained by LSTM for the railway stations is 0,13 compared to 0,15 obtained by ARIMA and 0,16 for the naive model, showing a small superiority for LSTM over ARIMA. On the other side, ARIMA excels on the Train lines.

Cognitive Learning Style Detection in e-Learning Environments using Artificial Neural Network

International Journal of Emerging Technologies in Learning (iJET)

COVID-19 pandemic has impacted all aspects of our lives including learning. With the particular g... more COVID-19 pandemic has impacted all aspects of our lives including learning. With the particular growth of e-learning, teaching approaches are being implemented at a distance on online platforms due to this pandemic. In this context, to make student involved throughout the online course, it is recommended to create an efficient platform similar to the traditional learning mode. In this study, we aims to improve learning style detection process by exploring additional such as cognitive traits. In fact, we have proposed novel approach based on Artificial neural network that classify students according to their level of cognitive learning styles in real-time. The proposed automated approach will certainly provide tutors with exhaustive information that helps them in achieving an improved and innovative online learning method. The results obtained are quite interesting and demonstrate the relevance of our solution.

Towards a New Mobile Educational Model

International Journal of Systems Applications, Engineering & Development, 2021

The development of mobile technologies and wireless networks encourages more research on Mobile L... more The development of mobile technologies and wireless networks encourages more research on Mobile Learning. Reviewing irregular verbs on a bus or organizing a training schedule on a Smartphone is becoming more common today. Mobile learning complements and enhances existing learning systems. Its development has been slowed in the early 2000s by both technical limitations and lack of dedicated teaching models. This article focuses on educational issues and proposes a solution by adopting the Method for Engineering Learning Systems MISA. Our work aims to identify basic elements, key characteristics and dimensions for developing the appropriate content for mobility. These elements are the basis for customization of the MISA method. Indeed, the different steps of MISA are governed by operating principles which ensure greater consistency and flexibility. Taking into account the specifications of Mobile learning in the development of these principles, we can adapt MISA to design a mobile lea...

Competency-Based Assessment

Learning and Performance Assessment, 2020

Competency-based Assessment (CBA) is the measurement of student's competency against a standa... more Competency-based Assessment (CBA) is the measurement of student's competency against a standard of performance. It is a process of collecting evidences to analyze student's progress and achievement. In higher education, Competency-based Assessment puts the focus on learning outcomes to constantly improve academic programs and meet labor market demands. As of to date, competencies are described using natural language but rarely used in e-learning systems, and the common sense idea is that: the way competency is defined shapes the way it is conceptualized, implemented and assessed. The main objective of this chapter is to introduce and discuss Competency-based Assessment from a methodological and technical perspectives. More specifically, the objective is to highlight ongoing issues regarding competency assessment in higher education in the 21st century, to emphasis the benefits of its implementation and finally to discuss some competency modeling and assessment techniques.

Mobile Serious Game Design using User Experience: Modeling of Software Product Line Variability

International Journal of Emerging Technologies in Learning (iJET), 2019

In recent years, gamification has emerged as a new approach to increasing learner engagement. It ... more In recent years, gamification has emerged as a new approach to increasing learner engagement. It covers a very wide range of games with very different purposes and with many fields of application. However, most of the gamification solutions proposed do not adopt the same modeling approach and little attention has been paid to mobile serious games (MSG) belonging to different pedagogical contexts. In order to overcome these difficulties, we have developed in this paper a generic model based on the Software Product Line (SPL) approach to manage the common and variable points of the MSG product set. We have also focused on the User eXperience (UX) concept to study the aspects that most affect the player’s experience in the context of MSGs. These aspects have been modeled in the form of features in the SPL Feature Model. MSG designers can use the model proposed during the development process, both to manage variability and to create an effective and fun learning environment.

Towards an Adaptive competency-based learning System using assessment

E-learning is not restricted to publishing online content. The challenge is to apply pedagogical ... more E-learning is not restricted to publishing online content. The challenge is to apply pedagogical models using new information and communication technologies in order to adjust the learning process. This adaptation will take place by proposing an adaptive learning system. There are several e-learning environment adaptation approaches such as adaptive hypermedia and semantic web. In our proposed system, we focus on evaluation that has not been, up till now, given its real value in the e-learning environment. The purpose is to implement an adaptive learning system for individualized pedagogical paths through a personalized diagnosis of learners’ performances. This proposed system relies mainly on assessment and the competency-based approach as a framework. To achieve this goal, we adopt an enhanced cycle of formative assessment while adhering to a service-oriented architecture. The system will be implemented as an activity in a pedagogical scenario defined responding to the learner’s n...

A Neuro-Fuzzy Inference System for the Evaluation of Reading/Writing Competencies Acquisition in an E-Learning Environnement

In the field of education, the evaluation of learning is one of the most important operations thr... more In the field of education, the evaluation of learning is one of the most important operations through the learning process. The evaluation concern arises in a more enhanced way in online learning environment given the significant reduction in direct contact of the tutor with the learners. In this paper, we address the specific problem of educational assessment of reading/writing competencies acquisition in amazigh language, based on the interactions of learners with an assessment test which consists of different items and served in a LMS platform. An online model based on artificial intelligence techniques, specifically multi-input-multi-output adaptive neuro-fuzzy inference System noted also CANFIS for co-active ANFIS, is proposed. The training and testing data, generated from the study of the curricula and the referential framework, are presented to the designed system for the optimization of inference engine parameters. Results of training and testing the system show an acceptabl...

Recommendation Systems on E-Learning and Social Learning: A Systematic Review

Electronic Journal of e-Learning

E-learning is renowned as one of the highly effective modalities of learning. Social learning, in... more E-learning is renowned as one of the highly effective modalities of learning. Social learning, in turn, is considered to be of major importance as it promotes collaboration between learners. For properly managing learning resources, recommender systems have been implemented in e-learning to enhance learners' experience. Whilst recommender systems are of widespread concern in online learning, it is still unclear to educators how recommender systems can improve the learning process and have a positive impact on learning. This paper seeks to provide an overview of the recommender systems proposed in e-learning between 2007 and the first part of 2021. Out of 100 initially identified publications for the period between 2007 and the first part of 2021, 51 articles were included for final synthesis, according to specific criteria. The descriptive results show that most of the disciplines involved in educational recommender systems papers have approached e-learning in a general way with...

Serious Games Modeling

by Samir Bennani, Asmaâ RETBI, and Chaimae Meftah

Recently, serious games have become a crucial strategy that is devoted to improve e-learning. Now... more Recently, serious games have become a crucial strategy that is devoted to improve e-learning. Nowadays, they play an important role in attaching player and learner to learn by having fun and to retain as much pedagogical information as possible. As a result, it is necessary to extend the life cycle of an SG, enriching it with important educational content, as well as an appropriate model that will increase the learner's performance and profitability and, avoid the boring aspect of SG in the future. In our article, we will discuss the effectiveness of serious games in the world of education. Then, we will propose a study on the Freemium model that we will adopt to improve the modeling of serious games for the benefit of e-learning, and finally, we will discuss the strengths of the existing model that we intend to develop in future communications.

A Novel Hybrid Recommendation Approach Based on Correlation and Co-occurrence Between Activities Within Social Learning Network

by Asmaâ RETBI and Samir Bennani

Automatic Composition of Instructional Units in Virtual Learning Environments

International Journal of Emerging Technologies in Learning (iJET), 2018

In this paper, a new approach for automatic composition of instructional units based on a new var... more In this paper, a new approach for automatic composition of instructional units based on a new variant of Harmony Search Algorithm is proposed. The purpose is to solve curriculum sequencing issue by designing and arranging learning content in a suitable sequence. By suitable sequence we mean a learning sequence that fits learner level and presents the content in a way that conveys its structure to learner. Results show that the proposed approach is promising. For instance, individualized courseware plan are generated “on the spot” carefully considering both students characteristics and subject-matter coherence.

Service Orchestration Algorithm for Web Services: Evaluation and Analysis

With the growing need for service oriented architecture and the rise of cloud computing, web serv... more With the growing need for service oriented architecture and the rise of cloud computing, web services have become the focus of many researchers and software developers. Our area of focus is web service composition. In this paper we are presenting an evaluation and analysis of the proposed orchestration algorithm in

Ontology of the CBA: Towards Operationalization and Implementation

Innovations in Smart Cities and Applications

To remedy inefficiency and increase the quality of learning, training systems have adopted a peda... more To remedy inefficiency and increase the quality of learning, training systems have adopted a pedagogical approach based on competence bases. It is a concept that is common to the academic and professional communities; which imposes the use of ontology of the CBA to conceptualize a dynamic repository, determining the terminological semantics of skills, which is sectorial with pedagogical norms. We propose a CBA ontology that focuses on explicit modeling of competency in order to provide a shared formal representation that promotes exchange, interoperability and collaboration among the various users in the learning systems. Our goal is not just to build an appropriate ontology. Our ambition is to implement this solution in an authoring system to assist tutors with didactic intentions based on skills to produce CBA based educational content.

A Novel ontology-based automatic method to predict learning style using Felder-silverman model

2018 17th International Conference on Information Technology Based Higher Education and Training (ITHET)

learning style is considered as preferred manner in which learners acquire effectively new knowle... more learning style is considered as preferred manner in which learners acquire effectively new knowledge. Individual’s learning style contains mainly his preferences, his expectations and his needs. In addition, it represents a key asset in improving teaching methods that meet learners’ needs. During the last decades, the identification of learning style methods has been relied on two basic measure methods: collaborative and automated ones. In this paper, we propose automatic test PRFSLM is based on Felder-Silverman learning style model (FSLM) that helps instructors to create and personalize their placement task’s items. Our proposed ontology-based automatic method aims (1) to assess the learner’s prerequisites and also (2) to provide explicitly an extensive knowledge about learner preferences that could predict his own learning style at the beginning of an online training.

Adaptive Educational Games Using Game Metrics

Video games are ostensibly adopted in the education field thanks to their engaging, immersive and... more Video games are ostensibly adopted in the education field thanks to their engaging, immersive and adaptive capacities. The greatest problematic in educational games design is how to create a ludic and adaptive experience without neglecting the learning objectives. To create an adaptive educational game modeling the player/learner is a must. In fact, determining the playing/learning style and measuring the player’s abilities and performances will help in adjusting the game content and difficulty. The aim of this paper is to explain how the Adaptive Mechanism for Educational Games (AMEG) adapts the game using metrics. We will define the kind of metrics that the mechanism collects and how they are used to define the learning/playing style as well as their importance in gameplay and learning content adaptation.

Actor’s knowledge massive identification in the learning management system

Intelligent Systems and Learning Data Analytics in Online Education, 2021

Toward a Use of Ontology to Reinforcing Semantic Classification of Message Based On LSA

World Academy of Science, Engineering and Technology, International Journal of Computer, Electrical, Automation, Control and Information Engineering, 2010

1101 Abstract— For best collaboration, Asynchronous tools and part icularly the discussion forums... more 1101 Abstract— For best collaboration, Asynchronous tools and part icularly the discussion forums are the most used thanks to t heir flexibility in terms of time. To convey only the messages that belong to a theme of interest of the tutor in order to help him during his tutoring work , use of a tool for classification of these messages is indispensable. For this we have proposed a semantics classification tool of messages of a disc ussion forum that is based on LSA (Latent Semantic Analysis), which includes a thesaurus to organize the vocabulary. Benefits offered by formal ontology can overcome the insufficiencies that a thesaurus generates during i ts use and encourage us then to use it in our semantic classifier. In this work we propose the use of some functionali ties that a OWL ontology proposes. We then explain how functionalities like “ObjectProperty”, ”SubClassOf” and “Datatype” property make our class ification more intelligent by way of integrating new terms. New te rms fou...