Prof. Antanas Verikas
Halmstad University, Sweden
Prof. Antanas Verikas was awarded a PhD degree in pattern recognition from Kaunas University of Technology, Lithuania. Currently he holds a professor position at both Halmstad University Sweden, where he leads the Department of Intelligent Systems, and Kaunas University of Technology, Lithuania. His research interests include learning systems, classification, fuzzy logic, image processing, computer vision, pattern recognition, applied soft computing, and visual media technology. He published more than 170 peer reviewed articles in international journals and conference proceedings and served as Program committee member in numerous international conferences. He is a member of the European Neural Network Society, International Pattern Recognition Society, International Association of Science and Technology for Development, and a member of the IEEE.
Speech Title: Determining Seabed Coverage from Underwater Video
Abstract: The demand for maritime space requires an integrated planning and management approach based on reliable mapping of the seabed. One of the widely used seabed mapping methods is underwater imagery. The main advantage of this method is its cost-effectiveness. However, only a small part of information available in underwater imagery archives is being extracted due to labour-intensive and time-consuming analysis procedures. In this work, we aim at developing an automated seabed imagery recognition and quantification method. Two approaches have been developed and explored, a two-stage algorithm based on traditional processing techniques and a deep convolutional neural network (CNN) based approach. Information characterizing geometry, colour and texture of the seabed region being analysed is used in the first stage, while the reliability of decisions made in the first stage regarding the surrounding regions is taken into account when constructing a feature vector for the second stage. The developed tools were tested in an image recognition task including five benthic classes: red algae, sponge, sand, lithothamnium and kelp. The average accuracy of 90.1% and 92.8% was observed for the first and the second approaches, respectively, using a data set consisting of over 18000 image regions. The future work concerns algorithms for diversifying deep learning models and combining them into a committee as well as unsupervised learning-based algorithms allowing to exploit unlabelled seabed images for training CNN.
Prof. Xabier Basogain
University of the Basque Country, Bilbao, Spain
Xabier Basogain is professor of the University of the Basque Country - Euskal Herriko Unibertsitatea. He is doctor engineer of telecommunications by the Polytechnic University of Madrid, and member of the Department of Engineering Systems and Automatics of the School of Engineering of Bilbao, Spain. He has taught courses in digital systems, microprocessors, digital control, modeling and simulation of discrete events, machine learning, and collaborative tools in education. His research activities include the areas of: a) soft computing and cognitive sciences to STEM; b) learning and teaching technologies applied to online education and inclusive education; c) augmented and virtual reality with mobile technologies.
Speech Title: Computational STEAM Education
Abstract: Educational systems around the world have embarked during the last decade in a set of ambitious paradigmatic projects that can be grouped under the umbrella names of STEM and STEAM. The two fundamental ideas underlying these projects are: the citizens of the modern society are required to have a solid education in the areas of STEM (Science, Technology, Engineering and Mathematics) or STEAM (adding the Arts and Humanities); and these subjects need to be taught and learned not as separate and isolated topics, but rather as integral components of a superior entity. The origin of these projects is a demand of the professional world of industry and services that identifies a substantial change in the qualifications that modern citizens need to bring to their jobs. In particular, technology is prevalent is all aspects of modern society. The academic systems of the world, and the public administrations which set their curriculum and policies, are creating initiatives to address these far reaching challenges. As expected in any large scale project, particularly when it includes diverse constituencies, such as academia, industry, and national politics, the initial phases of the project reveal fundamental conflicts. Our research group has been working during the last 10 years on STEAM and its incorporation into Education. In this conference we describe: a) Computational STEAM, an ontology to describe STEAM projects, and b) three fundamental components of Computational STEAM The Computational STEAM ontology is used to describe formally what a STEAM project is: the goals set out by industry; the content intended for its curriculum; the methodology for teaching and learning; and the working tools expected to be used by a proficient citizen active in the modern society. The ontology is the formal description of goals, content, methods, and means, will serve as standard of reference for the dialog between all communities involved. Each will be able to clearly communicate to the others what they need, and what they can offer. The Computational STEAM three fundamental components are: 1) content or curriculum describes what is to be learned and taught during the twelve years of primary and secondary education in the areas of STEAM. This greatly differs from the current curriculum; 2) methodology and human cognitive scope describe the type of tasks that modern work requires, and the cognitive abilities to be developed in our students; and 3) computation as generative language of action introduces the fundamental idea of creating systems and processes as the means to advance knowledge, provide services and solve problems.The conference illustrates these ideas with some comprehensive examples. Throughout these examples, we focus our attention on the role of educational technologies in the successful implementation of the three components of the ontology in the classrooms.
Prof. Mario Barajas Frutos
University of Barcelona, Spain
Mario Barajas Frutos is a Doctor in Education from the University of Barcelona and Master’s Degree in Educational Technology from San Francisco State University in the USA. He holds degrees in Engineering and in Philosophy and previously taught Mathematics in secondary education. He teaches about Digital Learning Environments, and in the doctoral program ‘Education and Society’ at the Faculty of Education of the University of Barcelona. He is a founder of the new Institute of Educational Research of the same University. He is a member of different Research Committees, Journals and Conferences at an international level. During the last two decades, Dr. Barajas has coordinated and participated in a large number of the European Union funded projects and leads the research group Future Learning (www.futurelearning.org).