Alberto Caballero

Using cognitive agents in social simulations

Multi-Agent-Based Social Simulation (MABS) is a paradigm devoted to using agents as the modelling metaphor to simulate autonomous entities in a social world composed of a number of independent and interacting entities. Such models try to reproduce real environments and situations of interest within such environments. Most MABS platforms used today (e.g. MASON, Repast, NetLogo) see agents as very simple entities. However, there are situations in which a more intelligent kind of agent is needed. For example, when a society of persons with different roles and high-level behaviours must be modelled. In this paper, we address how to incorporate agents with cognitive skills into MABS.

On the Behaviour of the TRSIM Model for Trust and Reputation

We study here the behaviour of a trust and reputation model for agents in P2P environment, where agents act as providers or consumers of resources. We present partial results of the refinement process of our model in order to identify the suitable structure, functions, and parameters to correctly manage trust and reputation. We show some experimental results comparing several alternatives to obtain the quality of the response given the requirements, and the increase of the satisfaction of the recommended response when it uses a right way to estimate trust and reputation values using stored information about similar tasks.

OntoSakai: On the optimization of a Learning Management System using semantics and user profiling

Abstract This paper proposes recommendation services and user profiling features in Learning Management Systems (LMS) by means of a semantic intelligent system combining context information and expert knowledge. LMS users’ context is represented through an ontology model called OntoSakai. It consists of four ontologies parceling different areas of the learning process: competences, users’ profiles, learning tools and semantic classification of the elements in an LMS. Thus, we provide a standardized common vocabulary about LMS elements and academic tasks developed within these platforms. This model also enables inference processes about the behavior of LMS users. Indeed, our system incorporates an extensible set of expert rules to offer recommendation and user profiling services. This combination of context information and expert knowledge could be easily integrated with other systems in the academic world in order to promote the interoperability between them. Specifically, in this paper we integrate our proposal into Sakai, a well-known LMS for university-level. As a result of this integration, OntoSakai is able to generate users’ profiles aimed at personalizing the use of LMS tools and to recommend resources to reach the optimum benefit in both lecturing and learning. As a proof of concept, a real case often detected in on-line students is shown as a running scenario where the services offered by OntoSakai could help them to improve their experiences and academic results.

Heart health risk assessment system: a nonintrusive proposal using ontologies and expert rules.

According to the World Health Organization, the worlds leading cause of death is heart disease, with nearly two million deaths per year. Although some factors are not possible to change, there are some keys that help to prevent heart diseases. One of the most important keys is to keep an active daily life, with moderate exercise. However, deciding what a moderate exercise is or when a slightly abnormal heart rate value is a risk depends on the person and the activity. In this paper we propose a context-aware system that is able to determine the activity the person is performing in an unobtrusive way. Then, we have defined ontology to represent the available knowledge about the person (biometric data, fitness status, medical information, etc.) and her current activity (level of intensity, heart rate recommended for that activity, etc.). With such knowledge, a set of expert rules based on this ontology are involved in a reasoning process to infer levels of alerts or suggestions for the users when the intensity of the activity is detected as dangerous for her health. We show how this approach can be accomplished by using only everyday devices such as a smartphone and a smartwatch.

A new model for trust and reputation management with an ontology based approach for similarity between tasks

This paper proposes a new trust and reputation model to assist decision making process into agents in P2P environments, taking WSMO as the base for definition of tasks to contract. This work shows the integration of trust and reputation model and WSMO in two ways: 1) how agents use WSMO as ontology to define their requirements, responses, domain-dependent features and metrics; and 2) how the Web services discovery process in WSMO may be improved using trust and reputation criteria given by the model from data stored by consumer agents in previous interactions.

Semantic description of multimedia contents for the optimization of the advertising impact on TV program grids

The problem of advertising impact optimization in program grids consists to find a fully design of advertising contents in the program grid maximizing the satisfaction of advertisers and viewers. In this work, the problem of advertising impact optimization of program grids is approached. Standards for semantic description of multimedia contents are used for expressing contents in a television grid and the optimization process is based on semantic similarity measures between the descriptions of the TV contents. The overall optimization of the advertising impact is guaranteed using an evolutive approach.

Analysis and evaluation of lecturers’ activity in Learning Management Systems: Subjective and objective perceptions

ABSTRACT Learning Management Systems (LMS) have become the principal resource for the distribution of educational material and collaboration among lecturers and students in Higher Education. The potential of these platforms does not limit to a simple manager of contents, but they also offer a wide range of tools that support the development of different methodologies according to the learning modality, namely on-campus, blended or online. This work analyzes the use of LMS and the interactions with their different tools from the lecturers’ point of view, in order to detect possible incidents, check the tools’ utility and evaluate their complexity. All these metrics represent valuable information to the Degree Coordinators, if they are presented in a suitable manner, to detect and resolve deficiencies in the methodology. For the analysis of the teaching activity two methods are employed: (1) surveys, to measure the subjective perception of lecturers when using LMS tools; and (2) visual analysis of the real lecturer’s activity through OnlineData, a graphical analytic tool developed as part of our work to monitor LMS tools metrics. The results of both methods show differences among the perceived self-usage and actual usage, especially for the e-learning methodologies

A TOOL FOR PRACTICING ABOUT CLASSIC CRYPTOGRAPHIC ALGORITHMS INTEGRATED IN VIRTUAL LEARNING ENVIRONMENTS

Classic cryptographic techniques and algorithms are typically taught in all basic courses of cybersecurity because they are the foundations of modern cryptographic techniques used to implement symmetric encryption or hashing algorithms. The correct comprehension of the operation of these algorithms can be facilitated if students get familiar with classical encryption algorithms. This paper shows a tool that has been specially conceived for practicing with classic cryptographic algorithms. The main functionalities of this tool rely on its ability to graphically illustrate the operation of the algorithms in a step-by-step way accompanied with detailed explanations about the basis of the algorithms are offered. The proposed tool also evaluates the most relevant metrics related to the performance of the classical algorithms such as consumed time, entropy, strength or weakness, among others. Furthermore, a set of predefined illustrative examples are included in order to allow the student compare several configurations taking into account these metrics. These examples could be used to discuss the robustness of each algorithm against cryptanalytic attacks, like those based on language statistics. Nevertheless, the tool also allows teachers or students to define new examples in order to study the internal details of each algorithm. The tool has been deployed as a web-based system and integrated in a virtual learning environment in order to enhance the usefulness and effectivity when assisting the teaching-learning process.

User Profiling Based on Similarity, Trust and Reputation

This paper offers a proposal for user profiling based on similarity, trust and reputation notions. We present a general profile ontology to model the basic concepts related to the profile assignment process. Based on this ontology, we propose an adaptive mechanism to guide the interactions between user and broker agents aimed to select the most suitable profile taking into account the users requirements and preferences. Broker agents estimate the suitability of the profiles using trust and reputation information coming from its own experiences or from other brokers. Under uncertainty conditions, similarity between two set of users requirements and preferences is also used. The evaluation of suitability of each suggested profile to the users requirements and the similarity between two set ofusers requirements are based on the service discovery processes proposed by WSMO.

Adaptability of the TRSIM Model to Some Changes in Agents Behaviour

Trust and reputation models are very useful tools to assist decision making process within agents. They can help to represent and to approximately predict the behaviour of the agents in a system. Trust and reputation values can be used to recognize the agents with a good-expected performance. This way, trust and reputation models offer an adaptive mechanism to guide interactions between agents. In this paper we study the behaviour of TRSIM model when it is applied to consumer-provider scenario. We present several experimental evidences related with the stability of the model for different types of requirements of the consumer, and recognition of different types of providers. Also, we study the ability of the model to adapt to behavioural changes of provider agents.