Ana Marilza Pernas

Enriching Adaptation in E-Learning Systems through a Situation-Aware Ontology Network

Purpose – The broader adoption of the internet along with web‐based systems has defined a new way of exchanging information. That advance added by the multiplication of mobile devices has required systems to be even more flexible and personalized. Maybe because of that, the traditional teaching‐controlled learning style has given up space to a new way of learning, which is more flexible and adequate to the learners needs. The purpose of this research is to go further into the semantic modeling of adaptive web based learning systems. Particularly, the paper focuses on those learning systems that consider in their definition the awareness of students context in order to properly react to the student needs.Design/methodology/approach – In this paper the authors introduce a semantic model of the student context in terms of an ontology network. This semantic model is explored in order to detect the “current situation” of students when they are navigating into e‐learning environments. The final objective is to...

Towards a distributed architecture for context-aware mobile applications in UbiComp

The applications in Ubiquitous Computing (UbiComp) environments must be aware of their contexts of interest and adapt to changes in them. Thus, a major research challenge in the area of UbiComp is related to context awareness. Considering the high distribution, heterogeneity, dynamism, and mobility of ubiquitous environments, this paper presents an architectural model for context awareness, called EXEHDA-UC (Execution Environment for Highly Distributed Applications - Ubiquitous Context awareness). The proposal includes elements to support contextual data acquisition, actuation on the environment, and processing of contextual information. We consider that the main contribution of this work is an architecture that supports the managing of the acquisition, storage, and processing of context data, in a distributed way, independently of the application, in an autonomic and rule-based perspective. To assess the functionalities of the EXEHDA-UC, we present a case study, highlighting the prototypes developed, technologies employed, and tests realized.

A Distributed Architecture for Supporting Context-Aware Applications in UbiComp

The applications in Ubiquitous Computing (UbiComp) environments must be aware of their contexts of interest and adapt to changes in them. Thus, a major research challenge in the area of UbiComp is related to context awareness. Considering the high distribution, heterogeneity, dynamism, and mobility of ubiquitous environments, this paper presents an architecture for context awareness, named UbiC (Ubiquitous Context awareness), which is integrated to EXEHDA middleware (Execution Environment for Highly Distributed Applications). We consider that the main contribution of this work is an architecture that enables the acquisition, storage, and processing of context data, in a distributed way, independently of the application, in a rule-based autonomic perspective, and with support to mobility. To assess the functionalities of the UbiC architecture, we present a case study, highlighting prototypes developed, technologies employed, and tests realized.

A Semantic Approach for Learning Situation Detection

A number of ubiquitous systems are considering how to deal with situation-awareness to act in a personalized manner according to users needs. Indeed, most of the research efforts in situation-awareness are generally focused on the implementation of common characteristics, differing basically on the relevant context observed and how this contextual information is managed. Consequently, little attention has been paid to an abstract and general view for situation-awareness. The goal of this work is to provide a shift of the attention focus from the implementation to the modeling phase. Our objectives are (1) to define the conceptual modeling of situation-awareness for adaptive and ubiquitous learning systems, (2) to identify its relevant concepts, relationships, and structural, dynamic and representational elements, (3) to propose a method for situation detection. The domain concepts are explored by an application scenario that allows the understanding of the situations configured in u-learning systems and their dynamic factors. The conceptual model was implemented in the CONIC module, which was evaluated in an e-learning system specifying the application and constructing the improvements necessaries to deploy the system in a real application for tests.

An Architectural Model for Situation Awareness in Ubiquitous Computing

One of the major research challenges of Ubiquitous Computing (UbiComp) is related to the need of the applications being aware of the situational context awareness, and when appropriate, respond to it. This paper presents an architecture for situation awareness, called EXEHDA-SA (Execution Environment for Highly Distributed Applications-Situation Awareness). We consider that the main contribution of this work is the architecture that supports acquisition, processing, and dissemination of contextual information, in a distributed way, independently of the application, in an autonomic perspective and rule-based. To assess the functionality of the EXEHDA-SA, we present a case study implemented in Didactic Laboratory of Seed Analysis (LDAS), at Faculty of Agronomy (FAEM), Federal University of Pelotas (UFPel).

Discussing the Challenges Related to Deployment of Computational Thinking in Brazilian Basic Education

Computational thinking aims to employ Computer Science foundations to solve problems in different knowledge areas. This paper describes projects related to computational thinking and starts a discussion on the challenges for implementing computational thinking in primary and secondary education in Brazil.

Enabling Situation-Aware Behavior in Web-Based Learning Systems

Adaptive systems need to be aware about the user context and the occurrence of specific events to properly react to. In particular, web-based educational systems have to be improved in order to consider the learner in his/her current situation. Thus, the main objective of this paper is to present a system able to recognize the situations configured in an e-learning environment, aiming at suggesting better actions to be followed by students each time are necessary, for example, when the learner encounters a difficulty to solve an exercise or spend a lot of time to finish a course. In this work, our solution is developed as an extension of an already functional learning environment, called AdaptWeb®, and enables situation-aware behavior customized to its audience. The main challenge is monitoring events and detecting situations.

Modeling Adaptive Situations According with Context and Learning Scenarios

This paper presents an architecture to transform an existent e-learning environment in a situation-aware environment, bringing the concepts of context awareness, situation and scenario to this environment. For a specific scenario, ontologies may be employed to represent the knowledge that the system has on the domain to be studied, on the situation where the study is being performed and also based in the student profile. In this sense, we present an alternative to transform the vision of situation-awareness in a daily reality, automatically defining the student situation and recommending adaptive actions.

Situation-Aware Smart Environment Modeling

The term ubiquitous smart system is utilized to characterize applications that are able to perceive the user context and properly react, according to the occurrence of specific events. Lately, several solutions have been developed in order to propose new approaches focused on ubiquitous computing, in general, not exploring a general model that could be broadly applied and calibrated respecting the context of interests of specific ubiquitous applications. In this sense the objective of this work is to propose a system model and functioning that is capable of recommending situation-aware actions to users, implemented in a Situation as a Service way. The system enables customized behavior, depending on user’s situation, which is the main research challenge considering that a number of context elements have to be evaluated. A use-case shows how ubiquitous applications can automatically define the user situations and recommend personalized actions within a residential home-care scenario.

EXEHDA-RR: Machine Learning and MCDA with Semantic Web in IoT Resources Classification

Currently, a lot of resources are connected to the Internet, many simultaneously requesting and providing services. The adequate selection of resources that best meet the demands of users with a broad range of options has been a relevant and current research challenge. Based on the non-functional parameters of QoS play a significant role in the ranking of these resources according to the services they offer. This paper aims to aggregate machine learning in the pre-classification of EXEHDA middleware resources, to reduce the computational cost generated by MCDA algorithms. We presented the proposed software architecture (EXEHDA-RR), and the obtained results with the integration of machine learning in the classification process are promissing, and indicate to the research continuation.