
Roger NkambouUniversity of Quebec in Montreal | UQAM · Department of Computer Science
Roger Nkambou
Professor
About
270
Publications
75,534
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
2,967
Citations
Introduction
Additional affiliations
September 1996 - present
Publications
Publications (270)
The majority of Sub-Saharan African countries are facing a very negative teacher-learner ratio: one teacher for over 120 learners. In order to support the learner training, we propose optimizing search engines for learning contexts, to enable learners to take optimal advantage of the vast reservoir of Open Educational Resources (OER) available on t...
The design of ontologies is a non-trivial task that can simply be reduced to the reuse of one or more existing ontologies. However, since an expert in knowledge engineering would only need a part of the ontology to perform a specific task, obtaining this partition will sometimes require the modularization of existing ontologies. There exist two cat...
Defining adaptation rules is an important step in the design of adaptive systems. This paper proposes using a constrained multi-modal neural network to extract adaptation rules. The proposed approach enhances a serious game’s adaptive capability, which aims to help learners improve their socio-moral reasoning skills. The neural network takes learne...
In our previous works, we presented Logic-Muse as an Intelligent Tutoring System that helps learners improve logical reasoning skills in multiple contexts. Logic-Muse components were validated and argued by experts throughout the designing process (ITS researchers, logicians, and reasoning psychologists). A catalog of reasoning errors (syntactic an...
This paper proposes a model that will learn piloting actions using Recurrent Neural Networks. Neural networks, a sub-branch of machine learning, have been widely used for generalization problems. They can learn hidden patterns from data. They have been widely used to learn generalized human behaviors from data representing many behaviors. This rese...
Intelligent educational systems currently use ontological knowledge modeling for their expert component. The associated semantics of the ontological languages allow for capturing highly complex domain knowledge. However, the automatic manipulation of knowledge to support the execution of a complex task by humans is a current research issue. This pa...
To accurately replicate the procedures and actions of piloting an aircraft, it is important to create an intelligent system capable of analyzing and executing tasks using established protocols in the field. In this study, we introduce a cognitive agent based on the ACT-R cognitive architecture that incorporates an ontological reference model into i...
Deep learning has succeeded in various applications, including image classification and feature learning. However, there needs to be more research on its use in Intelligent Tutoring Systems or Serious Games, particularly in modeling user behavior during learning or gaming sessions using multi-modal data. Creating an effective user model is crucial...
Frequent Sequence Mining (FSM) is a fundamental task in data mining. Although FSM algorithms extract frequent patterns, they cannot discover patterns that periodically appear in the data. However, periodic trends are found in many areas such as market basket analysis, where discovering itemsets periodically purchased by customers can help understan...
The main goal of this paper is to set up a model of piloting tasks (the Attentional Task Model) which require attention for operating an aircraft. This model serves as a tool to predict attentional measurements with each task of a complete list of piloting actions. The main objective of this Attentional Task Model is to provide attention scores for...
In this presentation, we introduce a functional size automation tool from texts or software requirements written in natural language. First, we developed a new technique for writing software requirements to facilitate the process of automating software functional sizing. Secondly, we developed a tool to automatically measure the software functional...
Knowledge modeling in the context of an intelligent educational system remains a key research issue. Indeed, intelligent learning systems need a high-quality knowledge formalization of the domain theory related to the context. Ontology-based languages allow a detailed semantic description of knowledge that can support the intelligent system in unde...
Machine learning models are biased toward data seen during the training steps. The models will tend to give good results in classes where there are many examples and poor results in those with few examples. This problem generally occurs when the classes to predict are imbalanced and this is frequent in educational data where for example, there are...
The use of machine learning techniques for safety analysis, incident and accident investigation, fault detection and also for the study of piloting behaviors has gained popularity within the aviation community. This paper present a methodology that uses machine learning for the analysis of piloting behaviors in order to highlight behavioral profile...
Deep Knowledge Tracing (DKT), as well as other machine learning approaches, is biased toward data used during the training step. Thus, for problems where we have few amounts of data for training, the generalization power will be low, and the models will tend to work well on classes containing many samples and poorly on those with few. This situatio...
This article proposes an improvement of search engines in a learning or training context. Indeed, the learner requests resources or learning content in a training or learning situation. The same goes for the trainer, who wishes to select the appropriate resources available to his learners. Unfortunately, existing search engines produce an enormous...
The domain of software functional size measurement automation, from software specification documents, has been a research topic over the last years. The literature consulted shows that attempts to automate the process of measuring the software functional size has obtained little success at the industry level. Several tools for automating the measur...
The domain of software functional size measurement automation, from software specification documents, has been a research topic over the last years. The literature consulted shows that attempts to automate the process of measuring the software functional size has obtained little success at the industry level. Several tools for automating the measur...
The web is one of the primary sources of information for finding learning oriented documents. In addition, the main suitable way to find information and documents on the Internet is by using search engines. Search engines are constantly improving in terms of selection algorithms and in terms of the Human Machine interface (HMI). Also, these search...
Background
Social cognition and competence are a key part of daily interactions and essential for satisfying relationships and well-being. Pediatric neurological and psychological conditions can affect social cognition and require assessment and remediation of social skills. To adequately approximate the complex and dynamic nature of real-world soc...
Massive open online courses (MOOCs) are used by universities and institutions offer valuable free courses to huge numbers of people around the world through MOOC platforms. However, because of the huge number of learners, they often not receive sufficient support from instructors and their peers during the learning process, leading to high dropout,...
This research focus specifically on the eye-gaze movement of novice vs. expert clinicians to perform their clinical reasoning. The eye gaze data are spatiotemporal sequences representing the dynamic of the clinician’s eye movements in the visual space to perform a clinical reasoning tasks. The objective is to do a comparative analyses of the eye mo...
In our previous works, we presented Logic-Muse as an Intelligent Tutoring System that helps learners improve logical reasoning skills in multiple contexts. Logic-Muse components were validated and argued by experts throughout the designing process (ITS researchers, logicians and reasoning psychologists). A Bayesian network with expert validation ha...
We present a serious game designed to help players/learners develop socio-moral reasoning (SMR) maturity. It is based on an existing computerized task that was converted into a game to improve the motivation of learners. The learner model is computed using a hybrid deep learning architecture, and adaptation rules are provided by both human experts...
This paper presents a simple and intuitive technique to accelerate the convergence of first-order optimization algorithms. The proposed solution modifies the update rule, based on the variation of the direction of the gradient and the previous step taken during training. Results after tests show that the technique has the potential to significantly...
MOOCs (Massive Open Online Courses) are definitely one of the best approach to support the international agenda about inclusive and equitable education and lifelong learning opportunities for all (SDG4) [1]. A great deal universities and institutions offer valuable free courses to their numerous students and to people around the word through MOOC p...
Mental-Imagery based Brain-Computer Interfaces (MI-BCI) present new opportunities to interact with digital technologies, such as wheelchairs or neuroprostheses, only by performing mental imagery tasks (e.g., imagining an object rotating or imagining hand movements). MI-BCIs can also be used for several applications such as communication or post-str...
This paper presents a research project in science education that is positioned at the intersection of computer science and context in learning. The main objective is to create a software tool that will participate, from the inception to the achievement, in the design of a leaning scenario, based on context effects. To this end, the
software will a...
Context-based science learning (CBL) creates instances for authentic inquiry pertaining to students’ environment. It allows students to build their conceptions through interactions between a scientific model and an observable and specific example. In order to avoid the risk of building their conceptions from paradigmatic examples, this article pres...
In this paper we propose a hybrid architecture combining Deep Neural Network architectures with expert's knowledge to automatically evaluate socio-moral reasoning maturity. Socio-moral reasoning represents a key ability to sustain efficient adaptive social interactions. In the proposed solutions , expert knowledge is first computed using NLP and in...
Mental Imagery based Brain-Computer Interfaces (MI-BCI) enable their users to control an interface, e.g., a prosthesis, by performing mental imagery tasks only, such as imagining a right arm movement while their brain activity is measured and processed by the system. Designing and using a BCI requires users to learn how to produce different and sta...
Gifted students are characterized by a low level of attention and workload. Thus, it is very important to detect the variation of these values in real time when children are solving problems. A low value of workload or attention could be an indicator that the child is gifted. In this paper, we conducted a preliminary study in order to detect when c...
High utility pattern mining is an emerging data science task, which consists of discovering patterns having a high importance in databases. The utility of a pattern can be measured in terms of various objective criterias such as its profit, frequency, and weight. Among the various kinds of high utility patterns that can be discovered in databases,...
We present a modified version of the Adam (Adaptive moment estimation) optimization algorithm, able to improve the speed of convergence and finds a better minimum for the loss function compared to the original algorithm. The proposed solution borrows some ideas from the momentum based optimizer and the exponential decay technique. The current step...
Prediction of emotions is important for understanding human be-havior and modeling users in learning environments. In this paper,we present a deep multi-modal architecture for emotions predic-tion, which takes advantage of deep learning, user multimodal dataand the hierarchy of human memory. The architecture consists ofthe combination of Long Short...
This paper reports on the research conducted by a team from the Quebec-Canadian research project TEEC, and its advances. This team is responsible for the context modeling and design of a context gap calculator, the Mazcalc. The Mazcalc is a computer artifact that consists in measuring the context effects between two given didactic situations having...
This paper reports on the research conducted by a team from the France-Quebec research project TEEC, and its advances. This team is responsible for modelling and designing of a context gap calculator, the MazCalc. The MazCalc is a computer artifact aimed at measuring the effects of two distinct context with the same object of study. In a Context-Ba...
We propose a model that employs convolutional neural networks (CNN) to evaluate sociomoral reasoning maturity, a key social ability, necessary for adaptive social functioning. Our model is used in a serious game to evaluate learners. It uses pre-annotated textual data (verbatims) and a coding scheme (SoMoral) applied by experts in psychology. State...
Logic-Muse is an Intelligent Tutoring System (ITS) that helps improve deductive reasoning skills in multiple contexts. All its three main components (The learner, the tutor and the expert models) have been developed while relying on the help of experts and on important work in the field of reasoning and computer science. It is now known that one ca...
Sequential pattern mining is an efficient technique for discovering recurring structures or patterns from very large datasets, with a very large field of applications. It aims at extracting a set of attributes, shared across time among a large number of objects in a given database. Previous studies have developed two major classes of sequential pat...
This paper presents a research project in science education that is positioned at the intersection of computer science and context in learning. The main objective is to improve learning process by creating a software tool that participates, from the inception to the achievement, in the design of leaning scenarios, based on context effects, and, to...
Sequential pattern mining is an important data mining problem widely addressed by the data mining community, with a very large field of applications. The sequence pattern mining aims at extracting a set of attributes, shared across time among a large number of objects in a given database. The work presented in this paper is directed towards the gen...
Proceedings of the 10th International and Interdisciplinary Conference, CONTEXT 2017, Paris, France, June 20-23, 2017
MOOCs are definitely one of the best approach to support the international agenda about inclusive and equitable quality education and promote lifelong learning opportunities for all (SDG4). Many great universities and institutions offer valuable free courses to their numerous students and to people around the word through MOOC platforms. However, b...
Ontological syntax standardized by the W3C offer the expressiveness needed in the formulation of complex concepts. However, the codification of an ontology is a process of formalization of thought that sometimes requires extensive knowledge and is often inaccessible in the layperson’s logic. The G-OWL (for Graphical OWL) language has been designed...
User profile inference on online social networks is a key task for targeted advertising and building recommender systems that rely on social network data. However, current algorithms for user profiling suffer from one or more of the following limitations: (1) assuming that the full social graph or a large training set of crawled data is available f...
In our previous works, we presented Logic-Muse as an ITS that helps improve logical reasoning skills in multiple contexts. All its three main components (the learner, tutor and expert models) have been developed while relying on the help of experts and on important work in the field of reasoning and computer science. The main purpose of this paper...
Autism spectrum disorder (ASD) is a neurological disorder affecting the way in which the brain processes information. Autism is characterized by impairments in learning and communication, in social interaction, imaginative ability as well as in repetitive and restricted patterns of behavior [9]. This research contributes to the advancement of intel...
A major issue in introducing new technological tools in the classroom is that the teachers who are meant to use them often do not receive the necessary training. This is the case of electronic dictionaries, which are seldom used by both students and teachers, despite their benefits for improving vocabulary development and academic achievement [14]....
This research contributes to the advancement of intelligent tutoring systems by proposing an affective intelligent tutoring system in the field of specialized education. The Integrated Specialized Learning Application (ISLA) helps autistic children manage their emotions by analyzing the learning trace and considering the learner’s current performan...
In this paper, we describe an innovative project where Web technologies are exploited to develop an Intelligent Tutoring System (ITS) that uses a Learning Management System (LMS) as its learning interface. The resulting ITS has been instantiated into a specific system called STI-DICO which aims at helping future French primary school teachers to ac...
The Web Ontology Language (OWL-2) aims at offering a family of syntax such as RDF/XML, Manchester Turtle and others, for building ontologies. Ontology engineering is a complex task that requires skills that are rarely accessible to content experts. On the other hand, to model contents pertaining to a specific domain, graphical modeling is a techniq...
The Web Ontology Language (OWL-2) aims at offering a family of syntax such as RDF/XML, Manchester Turtle and others, for building ontologies. Ontology engineering is a complex task that requires skills that are rarely accessible to content experts. On the other hand, to model contents pertaining to a specific domain, graphical modeling is a techniq...
Autism spectrum disorder (ASD) is a neurological disorder affecting the way in which the brain processes information. It can affect all aspects of a person’s development. Autism is characterized by impairments in learning and communication, in the social interaction, imaginative ability as well as in repetitive and restricted patterns of behavior (...
In this paper we present a participatory approach to design Logic-Muse, an Intelligent Tutoring System that helps learners develop reasoning skills in multiple contexts (situations). The study was conducted jointly with the active participation of experts in the field of logic and the psychology of reasoning. An explicit catalogue of systematic err...
Along their life-cycle, ontologies typically undergo a number of modifications that might deplete their structural quality. Ontology restructuring is a process of improving that quality by reconsidering the way the specifications are spread across the class and property hierarchies. This often leads to the discovery of new abstractions whose releva...
Algorithms for social network user profiling suffer from one or more of the following limitations: (1) assuming that the full social graph is available for training, (2) not exploiting the rich information that is available in social networks such as group memberships and likes, (3) treating numeric attributes as nominal attributes, and (4) not ass...
We present PGPI+ (Partial Graph Profile Inference+) an improved algorithm for user profiling in online social networks. PGPI+ infers user profiles under the constraint of a partial social graph using rich information about users (e.g. group memberships, views and likes) and handles nominal and numeric attributes. Experimental results with 20,000 us...
In this paper, we propose a mobile spoken dialogue system with a new spoken dialogue understanding architecture (SLU). This new SLU module combines an ontology and a dependency graph to do semantic analysis. The turn analysis algorithm integrated in the SLU module uses, at each turn of the dialogue, the dependencies generated by Stanford parser and...
Sequential rule mining is an important data mining problem with multiple applications. An important limitation of algorithms for mining sequential rules common to multiple sequences is that rules are very specific and therefore many similar rules may represent the same situation. This can cause three major problems: (1) similar rules can be rated q...
This paper describes the design and implementation of Logic-Muse, an Intelligent Tutoring System (ITS) that helps learners develop reasoning skills on various contents. The study was conducted jointly with the active participation of logicians and reasoning psychologists. Logic-Muse’s current version was internally validated. It is focused on propo...
Most algorithms for user profile inference in online social networks assume that the full social graph is available for training. This assumption is convenient in a research setting. However, in real-life, the full social graph is generally unavailable or may be very costly to obtain or update. Thus, several of these algorithms may be inapplicable...
In science learning, context is an important dimension of any scientific object or phenomenon, and context-dependent variations prove to be as critical for deep understanding as are abstract concepts, laws and rules. The hypothesis presented is that a context gap between two students can be illuminating to highlight the respective general-particula...
Quelle serait la façon la plus adéquate d'apporter de l'aide à des étudiants en philoso-phie ? Le but est de les aider à améliorer leurs compétences en lecture et en écriture de texte. La réponse à cette question a mené à la conception d'un environnement d'autoapprentissage in-formatisé, le GYM-Tuteur. Cet article décrit les aspects théoriques, mét...