The Experts below are selected from a list of 213264 Experts worldwide ranked by ideXlab platform
Roberto Therón - One of the best experts on this subject based on the ideXlab platform.
-
Visual Learning Analytics for a Better Impact of Big Data
Radical Solutions and Learning Analytics, 2020Co-Authors: Roberto TherónAbstract:Visual Learning analytics is an emerging research field in the intersection of Visual analytics and Learning analytics that is suited to address the many challenges that big data brings to the education domain. Although recent research endeavours have approached the analysis of educational processes through Visual analytics, the theoretical foundations of both fields have remained mainly within their boundaries. This chapter aims at mitigating this problem by describing a reference model for Visual Learning analytics that can guide the design and development of successful systems. A discussion of data, methods, users and objectives’ implications within the frame of the reference model highlights why Visual Learning analytics is regarded as a particularly promising technology to improve educational processes.
-
Visual Learning analytics techniques applied in software engineering subjects
Frontiers in Education Conference, 2014Co-Authors: Miguel A Conde, Francisco Jose Garciapenalvo, Diego Gomezaguilar, Roberto TherónAbstract:The technology applied to educational contexts, and specially the Learning platforms, provides students and teachers with a set of tools and spaces to carry out the Learning processes. Information related to the participation and interaction of these stakeholders with their peers and with the platform is recorded. It would be useful to exploit this information in order to make decisions. However this is a complex activity mainly because of the huge quantity of information stored. This work presents a Visual Learning analytics system that makes possible the exploitation of that information. The system includes several tools that help to analyze users' interaction attending to different dimensions, such as: when interaction is carried out, which are more important contents for users, how they interact with others, etc. This system has been tested with the subject information recorded during five academic years. From this analysis it is possible to show that Visual Learning analytics may help to improve educational practices.
-
FIE - Visual Learning analytics techniques applied in software engineering subjects
2014 IEEE Frontiers in Education Conference (FIE) Proceedings, 2014Co-Authors: Miguel A Conde, Francisco José García-peñalvo, Diego Alonso Gómez-aguilar, Roberto TherónAbstract:The technology applied to educational contexts, and specially the Learning platforms, provides students and teachers with a set of tools and spaces to carry out the Learning processes. Information related to the participation and interaction of these stakeholders with their peers and with the platform is recorded. It would be useful to exploit this information in order to make decisions. However this is a complex activity mainly because of the huge quantity of information stored. This work presents a Visual Learning analytics system that makes possible the exploitation of that information. The system includes several tools that help to analyze users' interaction attending to different dimensions, such as: when interaction is carried out, which are more important contents for users, how they interact with others, etc. This system has been tested with the subject information recorded during five academic years. From this analysis it is possible to show that Visual Learning analytics may help to improve educational practices.
Maximeliana Masela - One of the best experts on this subject based on the ideXlab platform.
-
INDONESIAN UNIVERSITY STUDENTS’ Visual Learning STYLE: LEARNERS’ AND TEACHERS’ PERSPECTIVES
ETERNAL (English Teaching Learning and Research Journal), 2020Co-Authors: Maximeliana Masela, Adaninggar Septi SubektiAbstract:This study aimed to investigate Indonesian undergraduate non-English department students' Visual Learning style and their and teachers' perspectives on the uses of Visual aids to promote Learning. It was conducted to fill the gap in the literature on the scarcity of empirical studies in the field of Learning style in the Indonesian context despite the potentials of instruction accommodating learners' Learning styles. 127 students participated in the study through a survey and descriptive analysis, this study found that the participants, in general, had a high level of Visual Learning style, suggesting that class instruction should provide Visual media and activities reported to be effective by the participants. Four participants with the highest Visual Learning style levels along with three teachers of General English classes were interviewed. Through Thematic Analysis of the interview results, the study found that both the students and teachers reported that teachers used certain Visual media for certain purposes, for example, pictures for brainstorming activities, videos for providing input for further discussions, and writing on the boards to explain grammar. Based on the findings, possible implications and contributions are mentioned along with limitations and possible future studies.
-
AN EXPLORATION OF Visual Learning STYLE OF NON-ENGLISH MAJOR COLLEGE STUDENTS: LEARNERS’ AND TEACHERS’ VOICES
2020Co-Authors: Maximeliana MaselaAbstract:The purposes of this study were to investigate the level of Visual Learning style of students of non-English major in a university in Indonesia and the perspectives of the students and teachers on the use of Visual aids to improve the students’ Learning. By applying mixed method, this study was done in two steps. First, the quantitative analysis was done in order to answer the first research question about the students’ level of Visual Learning style. Therefore, the questionnaires were distributed to 127 students of non-English major within a week. Second, the qualitative analysis was conducted to answer the second research question on the perspectives of students and teachers about the use of Visual aids to improve Learning. Hence, four students and three teachers who taught General English were interviewed. The finding showed that the learners had high level of Visual Learning style. Furthermore, the use of pictures, videos, boards, and games were found as the Visual aids that were used by the teachers in teaching English to the learners. In addition, the future studies were suggested to be conducted in the context of Indonesian Senior High School students as the students also learned English as one of their subjects in the school.
Fernando De La Torre - One of the best experts on this subject based on the ideXlab platform.
-
Feature and Region Selection for Visual Learning
IEEE transactions on image processing : a publication of the IEEE Signal Processing Society, 2016Co-Authors: Ji Zhao, Liantao Wang, Ricardo Cabral, Fernando De La TorreAbstract:Visual Learning problems such as object classification and action recognition are typically approached using extensions of the popular bag-of-words (BoW) model. Despite its great success, it is unclear what Visual features the BoW model is Learning: Which regions in the image or video are used to discriminate among classes? Which are the most discriminative Visual words? Answering these questions is fundamental for understanding existing BoW models and inspiring better models for Visual recognition. To answer these questions, this paper presents a method for feature selection and region selection in the Visual BoW model. This allows for an intermediate Visualization of the features and regions that are important for Visual Learning. The main idea is to assign latent weights to the features or regions, and jointly optimize these latent variables with the parameters of a classifier (e.g., support vector machine). There are four main benefits of our approach: (1) Our approach accommodates non-linear additive kernels such as the popular $\chi^2$ and intersection kernel; (2) our approach is able to handle both regions in images and spatio-temporal regions in videos in a unified way; (3) the feature selection problem is convex, and both problems can be solved using a scalable reduced gradient method; (4) we point out strong connections with multiple kernel Learning and multiple instance Learning approaches. Experimental results in the PASCAL VOC 2007, MSR Action Dataset II and YouTube illustrate the benefits of our approach.
-
Fixed-Rank Representation for Unsupervised Visual Learning
arXiv: Computer Vision and Pattern Recognition, 2012Co-Authors: Risheng Liu, Zhouchen Lin, Fernando De La TorreAbstract:Subspace clustering and feature extraction are two of the most commonly used unsupervised Learning techniques in computer vision and pattern recognition. State-of-the-art techniques for subspace clustering make use of recent advances in sparsity and rank minimization. However, existing techniques are computationally expensive and may result in degenerate solutions that degrade clustering performance in the case of insufficient data sampling. To partially solve these problems, and inspired by existing work on matrix factorization, this paper proposes fixed-rank representation (FRR) as a unified framework for unsupervised Visual Learning. FRR is able to reveal the structure of multiple subspaces in closed-form when the data is noiseless. Furthermore, we prove that under some suitable conditions, even with insufficient observations, FRR can still reveal the true subspace memberships. To achieve robustness to outliers and noise, a sparse regularizer is introduced into the FRR framework. Beyond subspace clustering, FRR can be used for unsupervised feature extraction. As a non-trivial byproduct, a fast numerical solver is developed for FRR. Experimental results on both synthetic data and real applications validate our theoretical analysis and demonstrate the benefits of FRR for unsupervised Visual Learning.
-
CVPR - Fixed-rank representation for unsupervised Visual Learning
2012 IEEE Conference on Computer Vision and Pattern Recognition, 2012Co-Authors: Risheng Liu, Zhouchen Lin, Fernando De La TorreAbstract:Subspace clustering and feature extraction are two of the most commonly used unsupervised Learning techniques in computer vision and pattern recognition. State-of-the-art techniques for subspace clustering make use of recent advances in sparsity and rank minimization. However, existing techniques are computationally expensive and may result in degenerate solutions that degrade clustering performance in the case of insufficient data sampling. To partially solve these problems, and inspired by existing work on matrix factorization, this paper proposes fixed-rank representation (FRR) as a unified framework for unsupervised Visual Learning. FRR is able to reveal the structure of multiple subspaces in closed-form when the data is noiseless. Furthermore, we prove that under some suitable conditions, even with insufficient observations, FRR can still reveal the true subspace memberships. To achieve robustness to outliers and noise, a sparse regularizer is introduced into the FRR framework. Beyond subspace clustering, FRR can be used for unsupervised feature extraction. As a non-trivial byproduct, a fast numerical solver is developed for FRR. Experimental results on both synthetic data and real applications validate our theoretical analysis and demonstrate the benefits of FRR for unsupervised Visual Learning.
Bartosz Wieloch - One of the best experts on this subject based on the ideXlab platform.
-
Cross-task code reuse in genetic programming applied to Visual Learning
International Journal of Applied Mathematics and Computer Science, 2014Co-Authors: Wojciech Jaśkowski, Krzysztof Krawiec, Bartosz WielochAbstract:We propose a method that enables effective code reuse between evolutionary runs that solve a set of related Visual Learning tasks. We start with introducing a Visual Learning approach that uses genetic programming individuals to recognize objects. The process of recognition is generative, i.e., requires the learner to restore the shape of the processed object. This method is extended with a code reuse mechanism by introducing a crossbreeding operator that allows importing the genetic material from other evolutionary runs. In the experimental part, we compare the performance of the extended approach to the basic method on a real-world task of handwritten character recognition, and conclude that code reuse leads to better results in terms of fitness and recognition accuracy. Detailed analysis of the crossbred genetic material shows also that code reuse is most profitable when the recognized objects exhibit Visual similarity.
-
Multitask Visual Learning using genetic programming
Evolutionary computation, 2008Co-Authors: Wojciech Jaśkowski, Krzysztof Krawiec, Bartosz WielochAbstract:We propose a multitask Learning method of Visual concepts within the genetic programming (GP) framework. Each GP individual is composed of several trees that process Visual primitives derived from input images. Two trees solve two different Visual tasks and are allowed to share knowledge with each other by commonly calling the remaining GP trees (subfunctions) included in the same individual. The performance of a particular tree is measured by its ability to reproduce the shapes contained in the training images. We apply this method to Visual Learning tasks of recognizing simple shapes and compare it to a reference method. The experimental verification demonstrates that such multitask Learning often leads to performance improvements in one or both solved tasks, without extra computational effort.
-
GECCO - Knowledge reuse in genetic programming applied to Visual Learning
Proceedings of the 9th annual conference on Genetic and evolutionary computation - GECCO '07, 2007Co-Authors: Wojciech Jaskowski, Krzysztof Krawiec, Bartosz WielochAbstract:We propose a method of knowledge reuse for an ensemble of genetic programming-based learners solving a Visual Learning task. First, we introduce a Visual Learning method that uses genetic programming individuals to represent hypotheses. Individuals-hypotheses process image representation composed of Visual primitives derived from the training images that contain objects to be recognized. The process of recognition is generative, i.e., an individual is supposed to restore the shape of the processed object by drawing its reproduction on a separate canvas. This canonical method is extended with a knowledge reuse mechanism that allows a learner to import genetic material from hypotheses that evolved for the other decision classes (object classes). We compare the performance of the extended approach to the basic method on a real-world tasks of handwritten character recognition, and conclude that knowledge reuse leads to significant convergence speedup and, more importantly, significantly reduces the risk of overfitting.
Juan J. Cuadrado-gallego - One of the best experts on this subject based on the ideXlab platform.
-
APPLYING Visual Learning IN THE TEACHING OF SOFTWARE MEASUREMENT CONCEPTS
International Journal of Software Engineering and Knowledge Engineering, 2011Co-Authors: Juan J. Cuadrado-gallego, Borja Martin Herrera, Oscar Pastor, Beatriz MarínAbstract:Applying new Learning methodologies in education, such as Visual Learning based on virtual reality and three-dimensional (3D) environments, is an important aspect in education, since it offers possibilities that can remarkably improve the current education system. Technological advances, along with the chance to create and represent the varying contents offered by information technologies, make the new Learning methodologies the focus of attention in the future. Currently, 3D methodologies are only used in Computer Science to improve physical characteristics (virtual laboratories, virtual worlds, etc.), but they are not used to improve the internal mental processes by which human beings understand and retain abstract concepts. In these cases, the use of Visual Learning helps to clarify them. In Computer Science, particularly in Software measurement courses, the complexity of the concepts is possibly greater than in other courses because there is a lot of Learning material that is based on abstract concepts that students find hard to recognize in the real world. In this paper, we present a Visual environment that can be used to learn software measurement concepts like the IFPUG functional size measurement method. To validate the new Learning model, an experiment was carried out.
-
C3S2E - Visual Learning techniques for software measurement
Proceedings of The Fourth International C* Conference on Computer Science and Software Engineering - C3S2E '11, 2011Co-Authors: Juan J. Cuadrado-gallego, Borja Martín-herrera, Pablo Rodríguez-soriaAbstract:In Computer Science, particularly in Software Engineering and Software Measurement, the level of abstraction and complexity of some concepts is very high. That implies a difficulty for the students when they try to assimilate those concepts because in many cases they cannot make mental associations between the idea and a real image. With the development and use of new Learning techniques such as Visual Learning, the assimilation of these software measurement concepts could be facilitate by the use of a more intuitive way than traditional resources, improving Learning results and in consequence academic results. To validate this hypothesis, CuBIT Software Measurement Laboratory developed a software functional size Visual course and carried out an experiment at the University of Alcala, Spain, comparing the traditional teaching methods with the use of these Visual Learning techniques. The results of this experiment, presented in this paper, indicate that the use of Visual Learning techniques could improve the Learning process.
