Interactive data visualization of high-dimensional data: A dimensionality reduction viewpoint
The objective of the emergent research area, so-called interactive data visualization (IntDataVis), is to link the field of dimensionality reduction (DR) with that of information visualization (IV), in order to harness the special properties of the latter within DR frameworks. In particular, the properties of controllability and interactivity are of interest, which should make the DR outcomes significantly more understandable and tractable for the (no-necessarily-expert neither data analytics nor the nature of data) user. These two properties provide the user with freedom to select the best way for representing the input data. In this talk, a brief overview of some remarkable works on IntDataVis is outlined, with special interest on a benchmark framework interactive model followed from a mixture of different DR techniques’ outcomes along with a generalized kernel-based formulation of spectral DR. Also, trends and open issues are discussed.
Dr. Diego Hernán Peluffo-Ordóñez
Prof. Diego Peluffo was born in Pasto – Colombia in 1986. He received his degree in electronic engineering, the M.Eng. and the Ph.D. degree in industrial automation from the Universidad Nacional de Colombia, Manizales – Colombia, in 2008, 2010 and 2013, respectively. He undertook his doctoral internship at KU Leuven – Belgium. Afterward, he worked as a post-doc at Université Catholique de Louvain at Louvain la-Neuve, Belgium. In 2014, he worked as an assistant teacher at Universidad Cooperativa de Colombia – Pasto. From 2015 to 2017, he worked as a researcher/professor at Universidad Técnica del Norte – Ecuador.
Currently, he is working as a professor at the School of Mathematical Sciences and Information Technology, and researcher at the Computational Intelligence Research Line from Yachay Tech – Ecuador. He is a supervisor and external member of ALEPHSYS (Algorithms embedded in Physical Systems) research group from Universitat Rovira i Virgila – Spain. He is invited lecturer at Corporación Universitaria Autónoma de Nariño – Colombia, and member of the SEDMATEC Research Group. He is the head of the SDAS Research Group.
His main research interests are kernel-based and spectral methods for multiple-annotators-driven classification, data clustering, and dimensionality reduction. His applications of interest encompass analysis of complex high-dimensional data, signals, imaging and videos analysis for medical and industry scenarios.
Pattern recognition using Attractor Networks: Applications to Automotive Video, Fingerprints and Gestures
Attractor neural networks, as dynamical systems are usually used as models for solving a variety of problems. Because of their inherent nature of parallel and distributed information processing, attractor neural networks are promising computational models for a wide variety of scientific and engineering applications including process control, signal and image processing, pattern recognition and classification, etc. This work explores the emergence of spatially localized information in Attractor Neural Networks with metric connectivity. The spatial information examined is arranged in blocks and bumps activity/memory structures and characterized on the small-world topology (local to random connectivity) of the network. The transition between local (spatially structured) and global information is evaluated for the network storage capacity and the network topological parameters. Applications to real world patterns are investigated. The feasibility of storing and retrieving automotive traffic videos using a sparse-coding ANN with a small-world topology was demonstrated. The approach was successfully tested on two complex patterns, the traffic video sequences of a Kiev crossroad and a Valencia roundabout, for different combinations of the involved network parameters. In another application, the metric network was successfully tested for different noisy fingerprint configurations, and the retrieval proved to be robust with a large basin of attraction. The dynamical evolution led to a final network state that matched better to the corresponding reference fingerprint, from an apparently more distant candidate, helping to distinguish between two fingerprints which could be attributed to the same individual. Also, overlapped fingerprints found in forensic scenarios could be separated using metric attractor neural networks. Finally, the recognition of 2D gestures is presented, an attractor network ensemble is used to learn the highly correlated dataset. The patterns are divided in subsets, that are assigned to different ensemble modules. The attractor ensemble proved to recognize the gestures for different initial condition showing robustness to gesture translation, multi-stroke and rotation to a certain degree. The input optimization of the patterns to the ensemble subsets to maximize the pattern retrieval in terms of quantity and quality opens up an interesting approach to pattern recognition using attractor networks.
Mario Gonzalez received a Ph.D. in Computer Science from the Autonomous University of Madrid (UAM) in 2012. His doctoral research was carried out within the Research Group of Biological Neurocomputation of the Polytechnic School at UAM, participating in projects funded by the Ministry of Education and Science of Spain. He made a doctoral stay at the Faculty of Engineering of the University of Porto (FEUP), Portugal, funded by the EMECW Lot 20 program. He is currently a lecturer and researcher at Universidad de las Américas, Quito, Ecuador. He has published in the area of Artificial Intelligence, information processing using neural networks, complex systems and socio-physics. He has collaborated in multidisciplinary projects in areas such as Attractor Networks modeling and pattern recognition, Air Quality modeling using machine learning, Tele-medicine for physical activity detection and rehabilitation, and Socio-physical modeling, among others.
LALA Project: Framework for the adoption of learning analytics in Latin America
Learning analytics proposes the development of guides, methodologies, techniques and technological tools that support the analysis of educational data. This talk will present the LALA methodological framework (The LALA Framework) whose objective is to support the development of the culture of learning analytics in higher education institutions in Latin America. This methodological framework guides the design, implementation and adoption of learning analytical tools from four fundamental dimensions: (1) the institutional dimension, related to the political and strategic aspects of the institution; (2) the technological dimension, related to the technical aspects associated with the design and implementation of technological tools; (3) the ethical dimension, related to the ethical aspects of data processing and management; and (4) the communal dimension, related to the generation of a research community and good practices around learning analytics in Latin America.
Miguel Zúñiga Prieto
Miguel Zúñiga Prieto received a Ph.D. in Informatics from Universitat Politècnica de València, Spain. He received his MS degree in Technology Management from Universidad San Francisco de Quito, Quito – Ecuador (2005). He holds a Diploma in Innovative Pedagogies from Universidad Técnica Particular de Loja, Cuenca – Ecuador (2008). At Universidad de Cuenca, he is an Associate Professor in the Faculty of Engineering and Director of the Computers Science Department, working in the Software Engineering Group. His skills and experience include the management of software development and research projects. He is currently coordinating the Universidad de Cuenca research team in the Erasmus+ project “Building Capacity to Use Learning Analytics to Improve Higher Education in Latin America (LALA)”. The LALA Project seeks to develop the local capacity to create, adapt and use Learning Analytics tools in Higher Education Institutions in Latin America, for which it has the participation of 3 European and 4 Latin American universities. He has also participated in the project “Desarrollo Incremental de Servicios Cloud Dirigido por Modelos y Orientado al Valor del Cliente (Value@Cloud)” funded by the Ministry of Economy and Competitiveness, Spain.