A new fast prototype selection method based on clustering

In supervised classification, a training set T is given to a classifier for classifying new prototypes. In practice, not all information in T is useful for classifiers, therefore, it is convenient to discard irrelevant prototypes from T. This process is known as prototype selection, which is an important task for classifiers since through this process the time for classification or training could be reduced. In this work, we propose a new fast prototype selection method for large datasets, based on clustering, which selects border prototypes and some interior prototypes. Experimental results showing the performance of our method and comparing accuracy and runtimes against other prototype selection methods are reported.     

APROMORE: An advanced process model repository

Business process models are becoming available in large numbers due to their widespread use in many industrial applications such as enterprise and quality engineering projects. On the one hand, this raises a challenge as to their proper management: how can it be ensured that the proper process model is always available to the interested stakeholder? On the other hand, the richness of a large set of process models also offers opportunities, for example with respect to the re-use of existing model parts for new models. This paper describes the functionality and architecture of an advanced process model repository, named APROMORE. This tool brings together a rich set of features for the analysis, management and usage of large sets of process models, drawing from state-of-the art research in the field of process modeling. A prototype of the platform is presented in this paper, demonstrating its feasibility, as well as an outlook on the further development of APROMORE.     

Automated online measurement of limestone particle size distributions using 3D range data

Fully automated online measurement of the size distribution of limestone particles on conveyor belt is presented based on 3D range data collected every minute during 13 h of production. The research establishes the necessary analysis and measurement capabilities to facilitate automatic control of rock crushing or particle agglomeration processes to improve both energy efficiency and product quality. 3D data from laser triangulation is used to provide high resolution data of the surface of the piled limestone particles. The 3D data is unaffected by color variation in the material and is not susceptible to scale or perspective distortion common in 2D imaging. Techniques are presented covering; sizing of particles, determination of non-overlapped and overlapped particles, and mapping of sizing results to distributions comparable to sieving. Detailed variations in the product sieve-size are shown with abrupt changes when the size range of the limestone particles is changed.     

A proposal for student modeling based on ontologies and diagnosis rules

The advances in the educational field and the high complexity of student modeling have provoked it to be one of the aspects more investigated in Intelligent Tutoring Systems (ITSs). The Student Models (SMs) should not only represent the student’s knowledge, but rather they should reflect, as faithfully as possible, the student’s reasoning process. To facilitate this goal, in this article a new approach to student modeling is proposed that benefits from the advantages of Ontological Engineering, advancing in the pursue of a more granular and complete knowledge representation. It’s focused, mainly, on the SM cognitive diagnosis process, and we present a method providing a rich diagnosis about the student’s knowledge state – especially, about the state of learning objectives reached or not. The main goal is to achieve SMs with a good adaptability to the student’s features and a high flexibility for its integration in varied ITSs.     

Graphical versus textual software measurement modelling: an empirical study

Model-driven Engineering (MDE) has attained great importance in both the Software Engineering industry and the research community, where it is now widely used to provide a suitable approach with which to improve productivity when developing software artefacts. In this scenario, measurement models (software artefacts) have become a fundamental point in improvement of productivity, where MDE and Software Measurement can reap mutual benefits. MDE principles and techniques can be used in software measurement to build more automatic and generic solutions, and to achieve this, it is fundamental to be able to develop software measurement models. To facilitate this task, a domain-specific language named “Software Measurement Modelling Language” (SMML) has been developed. This paper tackles the question of whether the use of SMML can assist in the definition of software measurement models. An empirical study was conducted, with the aim of verifying whether SMML makes it easier to construct measurement models which are more usable and maintainable as regards textual notation. The results show that models which do not use the language are more difficult—in terms of effort, correctness and efficiency—to understand and modify than those represented with SMML. Additional feedback was also obtained, to verify the suitability of the graphical representation of each symbol (element or relationship) of SMML.     

Providing effective feedback, monitoring and evaluation to on-line collaborative learning discussions

Learning and knowledge building have become critical competences for people in the knowledge society era. In this paper, we propose a sociolinguistic dialogue model for understanding how learning evolves and how cognitive process is constructed in on-line discussions. The knowledge extracted from this model is used to assess participation behavior, knowledge building and performance. The ultimate purpose is to provide effective feedback, evaluation and monitoring to the discussion process. Seven hundred students from the Open University of Catalonia in Spain participated in this study. Results showed that learning and knowledge building may be greatly enhanced by presenting selected knowledge to learners as for their particular skills exhibited during interaction. In addition, this valuable provision of information is used as a meta cognitive tool for tutors and moderators for monitoring and evaluating the discussion process more conveniently. This contribution presents our conceptual model for interaction management as well as key design guidelines and evaluation results. Implications of this study are remarked and further research directions are proposed.     

Dr. Jekyll vis-à-vis Mr. Hyde: Personality variation between virtual and real worlds

Organizations use virtual-worlds to enhance group discussion; it allows an individual to decouple his or her rendered from actual behavior; resulting in others perceiving him or her to have two or more personalities. Building on self-regulation theory, we examined how satisfaction in the virtual-world was affected by these personality differences. A field study was conducted to attempt to understand this; it involved 297 students engaged in a virtual tutorial group using Second Life. We found that small variations in personality between the virtual and real world groups (such as being helpful, sociable, seeking recognition, or submissive) could lead to greater satisfaction of the discussion.     

Should I e-collaborate with this group? A multilevel model of usage intentions

The use of online collaboration tools for virtual teamwork has been studied extensively, but mainly at the individual-level. We decided to examine the effect of macro-level factors (i.e., team attributes) and applied hierarchical linear modeling analysis to a sample of data collected from 96 individuals nested in 34 virtual teams. Our results suggested that the development of behavioral e-collaboration intentions by individual virtual team members was affected by their perceptions about the system, as described by individual-level IT use theories, and macro-level factors pertaining to the team. The collaboration technology was perceived to be less useful when employed to communicate with social loafers; and collective social loafing negatively influenced the teams’ potency assessments. After controlling for individual-level perceptions of system usefulness, team potency augmented team members’ intentions to use the online collaboration technology with similar teams. It also improved team performance.