Search results for "active learning"
showing 10 items of 184 documents
An Active Learning Approach for Classifying Explosion Quakes
2022
In this work, an Active Learning approach for improving the classification of passed seismo-volcanic events is proposed. Here we study the specific case of Explosion Quakes from Stromboli Volcano versus other seismo-volcanic events, recorded as seismograms, and the use of Random Forest as a Classification method. In conformity with the active learning paradigm, the approach recalls the human intervention for the annotation of uncertain data. The uncertainty is established by the event probabilities, predicted by a trained random forest classifier. The human intervention consists of editing and relabelling the data into these main three classes: Explosion Quakes, Non-Explosion Quakes or Non-…
Interactive Learning Environment as Innovative Teaching Method for Entrepreneurship Education
2014
The main aim of this paper is to show an innovative web-based interactive learning environment (ILE) for promoting and improving entrepreneurship in a complex and non-linear business context. The web-based ILE allows the interaction among participants both at national and international level in order to stimulate the sharing of knowledge and experience. The adoption of an ILE as teaching method will help entrepreneurs to become more aware of their entrepreneurial attributes and skills and see entrepreneurship as a realistic and interesting career path.
Iconic framework for cooperative coding
2018
The description of an innovative framework built on top of Web-based visual programming environment is the primary aim of this contribution. In the last decade, many frameworks oriented to visual languages have been introduced in literature to improve the skill on programming languages, but at the best of our knowledge, no framework has been specially designed to support collaborative work on heterogeneous distributed environments. Therefore, SIRENE introduces a new framework in which beginners and experts can cooperate to develop algorithms by using a visual and iconic paradigm. Students, in the classroom or connected from everywhere, can be involved into the definition of the algorithm, c…
Active Learning Methods for Efficient Hybrid Biophysical Variable Retrieval
2016
Kernel-based machine learning regression algorithms (MLRAs) are potentially powerful methods for being implemented into operational biophysical variable retrieval schemes. However, they face difficulties in coping with large training data sets. With the increasing amount of optical remote sensing data made available for analysis and the possibility of using a large amount of simulated data from radiative transfer models (RTMs) to train kernel MLRAs, efficient data reduction techniques will need to be implemented. Active learning (AL) methods enable to select the most informative samples in a data set. This letter introduces six AL methods for achieving optimized biophysical variable estimat…
Aerial Spectrum Surveying: Radio Map Estimation with Autonomous UAVs
2020
Radio maps are emerging as a popular means to endow next-generation wireless communications with situational awareness. In particular, radio maps are expected to play a central role in unmanned aerial vehicle (UAV) communications since they can be used to determine interference or channel gain at a spatial location where a UAV has not been before. Existing methods for radio map estimation utilize measurements collected by sensors whose locations cannot be controlled. In contrast, this paper proposes a scheme in which a UAV collects measurements along a trajectory. This trajectory is designed to obtain accurate estimates of the target radio map in a short time operation. The route planning a…
Inquiry-based environments for bio-signal processing training in engineering education
2021
Active student engagement, teaching via experience in real-life settings and learning by doing, are pedagogical strategies appropriate to improve student-reasoning skills. By building models, performing investigations, examining and explaining experimental results, using theoretical and computational thinking, constructing representations, undergraduates can acquire a deeper understanding of fundamental disciplinary concepts while reinforcing transversal abilities. In this framework, Engineering courses should be designed with the final objective to develop practical skills, focusing on hands-on activities. This contribution presents two different inquiry-based learning environments recent…
Active learning in digital communications with low-cost software defined radio
2021
Las comunicaciones digitales se enseñan tradicionalmente en sesiones de laboratorio desde un punto de vista teórico, utilizando plataformas de simulación. Sin embargo, el sistema de Acreditación Académica incluye la dimensión de "lo que se espera que los estudiantes sean capaces de hacer", lo que plantea la necesidad de disminuir la brecha entre las sesiones de laboratorio simuladas y un enfoque más práctico y realista. En este trabajo, proponemos una metodología para mejorar el aprendizaje de los aspectos prácticos relacionados con los cursos de Comunicaciones Digitales, así como para aumentar la motivación de los estudiantes, mediante el uso de dispositivos de radio definida por software …
Meaningful learning in business through serious games
2017
Purpose: The requirements of a business executive include the talent and creativity to solve problems and adapt to continuous changes presented by the economic and social environment. However, the university does not often prepare students in these skills. Businesses simulations are didactic tools in which participants assume a role and make decisions which affect the results of the company. This paper aims to provide empirical evidence on the effectiveness of business simulations in university teaching. Design/methodology: We have implemented business simulations in a course in the College of Economics at the University of Valencia, during the 2015-2016 academic year. Questionnaires were u…
Asymptotic optimality of myopic information-based strategies for Bayesian adaptive estimation
2016
This paper presents a general asymptotic theory of sequential Bayesian estimation giving results for the strongest, almost sure convergence. We show that under certain smoothness conditions on the probability model, the greedy information gain maximization algorithm for adaptive Bayesian estimation is asymptotically optimal in the sense that the determinant of the posterior covariance in a certain neighborhood of the true parameter value is asymptotically minimal. Using this result, we also obtain an asymptotic expression for the posterior entropy based on a novel definition of almost sure convergence on "most trials" (meaning that the convergence holds on a fraction of trials that converge…
The Raising Factor, That Great Unknown. A Guided Activity for Undergraduate Students
2020
In the first years of their economics degree programs, students will face many problems successfully dealing with a range of subjects with quantitative content. Specifically, in the field of statistics, difficulties to reach some basic academic achievements have been observed. Hence, a continuing challenge for statistics teachers is how to make this subject more appealing for students through the design and implementation of new teaching methodologies. The latter tend to follow two main approaches. On the one hand, it is useful for the learning process to propose practical activities that can connect theoretical concepts with real applications in the economic context. On the other hand, we …