Juan Alfonso Lara

A system for knowledge discovery in e-learning environments within the European Higher Education Area - Application to student data from Open University of Madrid, UDIMA

In todays open and dynamic learning environment, a significant percentage of students have a preference for flexible learning systems whereby they can reconcile their academic pursuits with their job responsibilities and family obligations.Non face-to-face educational models, like e-learning (electronic learning), evolved in order to offer such flexibility. E-learning systems have major strengths but also pose major challenges to the educational community.One such challenge is the large spatial and temporal gap between the teacher and student, which is an obstacle to student follow-up by teachers. The information generated by virtual learning systems sometimes overwhelms instructors who are unable to process the data without the support of special-purpose techniques and tools that are useful for analysing large dataflows. Student supervision is essential for detecting student behaviours that can lead to course dropout.The use of time analysis techniques promises to be a good option for evaluating educational data.The proposal that we present is able to identify students that are likely to drop out.The proposed system outperforms all of on the analysed proposals.The number of students correctly classified by our system describes a logarithmic behaviour.

Developing front-end Web 2.0 technologies to access services, content and things in the future Internet

The future Internet is expected to be composed of a mesh of interoperable web services accessible from all over the web. This approach has not yet caught on since global user-service interaction is still an open issue. This paper states one vision with regard to next-generation front-end Web 2.0 technology that will enable integrated access to services, contents and things in the future Internet. In this paper, we illustrate how front-ends that wrap traditional services and resources can be tailored to the needs of end users, converting end users into prosumers (creators and consumers of service-based applications). To do this, we propose an architecture that end users without programming skills can use to create front-ends, consult catalogues of resources tailored to their needs, easily integrate and coordinate front-ends and create composite applications to orchestrate services in their back-end. The paper includes a case study illustrating that current user-centred web development tools are at a very early stage of evolution. We provide statistical data on how the proposed architecture improves these tools. This paper is based on research conducted by the Service Front End (SFE) Open Alliance initiative.

Data preparation for KDD through automatic reasoning based on description logic

Abstract Without data preparation, data mining algorithms cannot operate on data within the knowledge discovery in databases (KDD) process. In fact, the success of later KDD phases largely depends on the data preparation stage. The use of mechanisms for automatically preparing data saves a lot of time and resources within the KDD process. These resources will then be available for use at later, less automatable stages, for example, during results interpretation. We have proposed a general-purpose mechanism applicable to multiple domains in order to improve the data preparation phase in the KDD process. This mechanism processes and automatically converts input data to a suitable format for the application of different data preparation techniques based on a known syntax. It is based on the use of description logic. Taking a generic UML2 data model as a reference, this mechanism is able to check whether any XML data source whatsoever can be transformed and modelled as a subsumption or instance of the above UML2 model. Thus it automatically identifies a consistent, non-ambiguous and finite set of XLST transformations which are used to prepare the data for the application of data mining techniques, obviating the need to expend resources on the preliminary preparation and formatting stage. The proposed mechanism was applied on structurally complex data from four different domains. In order to test the validity of the proposal, we have applied data mining techniques to extract knowledge from the prepared data. The sound results of applying our proposal to several different domains confirm that it is applicable to any XML data source, as well as being correct, computationally efficient and saving time during the data preparation phase.

Comparing Posturographic Time Series through Events Detection

The comparison of two time series and the extraction of subsequences that are common to the two is a complex data mining problem. Many existing techniques, like the discrete Fourier transform (DFT), offer solutions for comparing two whole time series. Often, however, the important thing is to analyse certain regions, known as events, rather than the whole times series. This applies to domains like the stock market, seismography or medicine. In this paper, we propose a method for comparing two time series by analysing the events present in the two. The proposed method is applied to time series generated by stabilometric and posturographic systems within a branch of medicine studying balance-related functions in human beings.

A soft computing framework for classifying time series based on fuzzy sets of events

It is not always possible to decide whether or not a part of a time series is an event.The use of event certainty is necessary and useful in those cases.This framework is an evolution of an earlier one used for classifying time series.Our new proposal takes into account the concept of event certainty.The new framework improves the time series classification results of its predecessor. Time series are sequences of data gathered over a period of time that emerge in different domains and whose analysis requires the application of specialized techniques, like, for example, data mining. Many existing time series data mining techniques, like the discrete Fourier transform (DFT), offer solutions for analysing whole time series. Often, however, it is more important to analyse certain regions of interest, known as events, rather than whole time series. Event identification is a highly complex task, as it is not always possible to determine with absolute certainty whether or not a segment of a time series is an event. In such cases, the best practice is to establish the certainty of this segment being a time series event, thus outputting a fuzzy set of events.In this paper we propose a framework that is capable of identifying events and establishing the degree of certainty that a domain expert would assign to the identified events based on a previous training process assisted by a panel of experts. Having identified the events, the proposed framework can be used to classify time series. This is done by means of a process that combines time series comparison and time series reference model generation by analysing the events contained in the respective time series and the certainties of the identified events. The proposed framework is an evolution of an earlier framework that we developed which did not apply soft computing techniques to identify and manage the time series events.We have used our framework to classify times series generated in the electroencephalography (EEG) area. EEG is a neurological exploration used to diagnose nervous system disorders. The performance of the framework was evaluated in terms of classification accuracy. The results confirmed that, thanks to the use of soft computing techniques, the new framework substantially improves the time series classification results of its predecessor.

A UML profile for the conceptual modelling of structurally complex data

ContextDomains where data have a complex structure requiring new approaches for knowledge discovery from data are on the increase. In such domains, the information related to each object under analysis may be composed of a very broad set of interrelated data instead of being represented by a simple attribute table. This further complicates their analysis. ObjectiveIt is becoming more and more necessary to model data before analysis in order to assure that they are properly understood, stored and later processed. On this ground, we have proposed a UML extension that is able to represent any set of structurally complex hierarchically ordered data. Conceptually modelled data are human comprehensible and constitute the starting point for automating other data analysis tasks, such as comparing items or generating reference models. MethodThe proposed notation has been applied to structurally complex data from the stabilometry field. Stabilometry is a medical discipline concerned with human balance. We have organized the model data through an implementation based on XML syntax. ResultsWe have applied data mining techniques to the resulting structured data for knowledge discovery. The sound results of modelling a domain with such complex and wide-ranging data confirm the utility of the approach. ConclusionThe conceptual modelling and the analysis of non-conventional data are important challenges. We have proposed a UML profile that has been tested on data from a medical domain, obtaining very satisfactory results. The notation is useful for understanding domain data and automating knowledge discovery tasks.

Sensor-Generated Time Series Events: A Definition Language

There are now a great many domains where information is recorded by sensors over a limited time period or on a permanent basis. This data flow leads to sequences of data known as time series. In many domains, like seismography or medicine, time series analysis focuses on particular regions of interest, known as events, whereas the remainder of the time series contains hardly any useful information. In these domains, there is a need for mechanisms to identify and locate such events. In this paper, we propose an events definition language that is general enough to be used to easily and naturally define events in time series recorded by sensors in any domain. The proposed language has been applied to the definition of time series events generated within the branch of medicine dealing with balance-related functions in human beings. A device, called posturograph, is used to study balance-related functions. The platform has four sensors that record the pressure intensity being exerted on the platform, generating four interrelated time series. As opposed to the existing ad hoc proposals, the results confirm that the proposed language is valid, that is generally applicable and accurate, for identifying the events contained in the time series.

Comparing Time Series through Event Clustering

The comparison of two time series and the extraction of subsequences that are common to the two is a complex data mining problem. Many existing techniques, like the Discrete Fourier Transform (DFT), offer solutions for comparing two whole time series. Often, however, the important thing is to analyse certain regions, known as events, rather than the whole times series. This applies to domains like the stock market, seismography or medicine. In this paper, we propose a method for comparing two time series by analysing the events present in the two. The proposed method is applied to time series generated by stabilometric and posturographic systems within a branch of medicine studying balance-related functions in human beings.

A multi-agent system for minimizing information indeterminacy within information fusion scenarios in peer-to-peer networks with limited resources

Abstract Information fusion (IF) has gained ground in recent years. It is increasingly used in applications involving networks of heterogeneous elements that communicate with each other peer-to-peer. This is thanks primarily to the advance of the Internet of Things (IoT) and the emergence of paradigms like holonic information fusion. However, heterogeneous peer-to-peer networks often depend on limited resources (energy, communication capacity, time, etc.). On these grounds, network components necessarily have to behave intelligently. They also have to be autonomous and be able to coordinate their actions in order to obtain results in the presence of vague or uncertain data. In this paper, we present a multi-agent information fusion system model that relies on collaborative peers to improve the quality of the information handled by the agents. The idea behind the model is to query the peers that have historically performed better for a given agent and information type (such as a certain data field). We report the results of the experiments we conducted on a proof-of-concept implementation of the proposed system model, consisting of a statistically significant number of simulation runs on two case studies with different numbers of agents and messages. The results show that the performance of an open peer-to-peer network of agents with no predefined structure, measured as mean traffic per agent (i.e. the use of resources) for replies of different quality and as the strict success rate, improves significantly when the members of the network adopt the intelligent mechanisms proposed in this article. This system model has a broad spectrum of application domains, ranging from mobile recommendation systems to decision-making applications in critical environments.

Data mining for modeling students’ performance: A tutoring action plan to prevent academic dropout ☆

Abstract E-learning systems generate huge amounts of data, whose analysis may become a daunting task which makes it necessary to use computational analytical techniques and tools. We propose the use of knowledge discovery techniques to analyse historical student course grade data in order to predict whether or not a student will drop out of a course. Logistic regression models are used for the purpose of classification. Experiments conducted with data on over 100 students for several distance learning courses confirm the predictive power of our proposal. Using the resulting predictive models we have designed a tutoring action plan. Applying this plan, we managed to reduce the dropout rate by 14% with respect to previous academic years in which no dropout prevention mechanism was applied. Our main contribution is a tool and a tutoring plan that can be used by our educational institution (and others) to reduce dropout rate in e-learning courses.