Gissel VelardeInternational University of Applied Sciences
Gissel Velarde
PhD. Computer Science and Engineering (Machine Learning)
About
24
Publications
26,209
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
110
Citations
Introduction
PhD in Computer Science and Engineering from Aalborg University. Author of Artificial Era.
Additional affiliations
October 2012 - April 2017
Education
September 2006 - February 2008
University of Applied Sciences, FH Südwestfallen, Soest, Germany
Field of study
- Electronic Systems and Engineering Management
January 2000 - December 2004
February 1990 - December 2002
Conservatorio Purinacional de Música
Field of study
- Piano
Publications
Publications (24)
We present a novel method of classification and segmentation of melodies in symbolic representation. The method is based on filtering pitch as a signal over time with the Haar-wavelet, and we evaluate it on two tasks. The filtered signal corresponds to a single-scale signal ws from the continuous Haar wavelet transform. The melodies are first segme...
This dissertation presents novel convolution-based methods for music analysis. The aim of this research project was two-fold: first, to design, implement and evaluate a convolution-based automated framework for the analysis of music with applications to music segmentation, pattern discovery, and classification; and second, to study convolution in r...
We present a novel convolution-based method for classification of audio and symbolic representations of music, which we apply to classification of music by style. Pieces of music are first sampled to pitch–time representations (spectrograms or piano-rolls) and then convolved with a Gaussian filter, before being classified by a support vector machin...
This paper introduces an open source and reproducible implementation of Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) networks for time series forecasting. We evaluated LSTM and GRU networks because of their performance reported in related work. We describe our method and its results on two datasets. The first dataset is the S&P BSE...
This paper evaluates XGboost's performance given different dataset sizes and class distributions, from perfectly balanced to highly imbalanced. XGBoost has been selected for evaluation, as it stands out in several benchmarks due to its detection performance and speed. After introducing the problem of fraud detection, the paper reviews evaluation me...
XGboost’s performance is evaluated given different dataset sizes and class distributions, from perfectly balanced to highly imbalanced in applications to fraud detection.
This paper presents a method for time series forecasting with deep learning and its assessment on two datasets. The method starts with data preparation, followed by model training and evaluation. The final step is a visual inspection. Experimental work demonstrates that a single time series can be used to train deep learning networks if time series...
This paper presents a method for time series forecasting with deep learning and its assessment on two datasets. The method starts with data preparation, followed by model training and evaluation. The final step is a visual inspection. Experimental work demonstrates that a single time series can be used to train deep learning networks if time series...
This short paper aims to explain why and how to implement a successful Artificial Intelligence and Machine Learning strategy. First, it briefly explains applications that are known to be profitable. It then reviews what is needed to develop and execute a strategy, considering different success criteria and what considerations are necessary to selec...
Artificial Intelligence (AI) is a trend in innovation and research expected to significantly impact society and firms. However, there are various opinions about its possible effects. This study compares the World Intellectual Property Organization (WIPO) statistics with opinions from 21 AI researchers, self-identified as professors and postdocs. Wi...
Con este trabajo de ciencia, Velarde nos acerca a cuestionamientos actuales, perennes y de la ciencia ficción. Velarde teje una historia cautivante de lo que ella ha llamado la Era artificial, y presenta las predicciones sobre el impacto tecnológico gracias a los avances de la inteligencia artificial.
My research indicates that Bolivia is facing a magnificent opportunity during the fourth industrial revolution, primarily because of Bolivians’ attitude towards entrepreneurship, their youth, and the nature of businesses to be powered by artificial intelligence. The book raises 7 fundamental elements for the execution of a 4.0 strategy as well as 7...
Mi investigación indica que Bolivia está frente a una magnífica oportunidad para aprovechar las circunstancias de la cuarta revolución industrial, sobre todo por la actitud de los bolivianos hacia el emprendimiento, su juventud y la naturaleza de los negocios que pueden ser potenciados por la inteligencia artificial. Pero existen desafios important...
La Inteligencia Artificial posiblemente revolucionará absolutamente todo durante la llamada cuarta revolución industrial, que conlleva varias tecnologías emergentes y puede que progrese sin precedentes en la historia de la humanidad debido a su velocidad y alcances. El gobierno, la academia, la industria y la sociedad civil muestran interés por com...
Artificial Intelligence may revolutionize everything during the so-called fourth industrial revolution, which carries several emerging technologies and could progress without precedents in human history due to its speed and scope. Government, academia, industry, and civil society show interest in understanding the multidimensional impact of the eme...
Presentación en línea: https://youtu.be/6vkJRqxt9NU, sobre el impacto de la Inteligencia Artificial (AI) en Bolivia, Latinoamérica y el Mundo. La IA será la tecnología omnipresente en la próxima revolución industrial. Se preveen cambios acelerados de dimensiones que superan a las anteriores revoluciones industriales. Las espectativas sobre el impac...
These are the slides of my PhD defense taken place on April 6, 2017, at 13:00 Seminar Room 3.563, Aalborg University, Rendsburggade 14, 9000 Aalborg. The presentation contains convolution-based methods for music analysis developed together with my supervisors Associate Professor David Meredith, Aalborg University and Senior Lecturer Tillman Weyde C...
We propose a method for music classification based on the use of convolutional models on symbolic pitch–time representations (i.e. piano-rolls) which we apply to composer recognition. An excerpt of a piece to be classified is first sampled to a 2D pitch–time representation which is then subjected to various transformations, including convolu-tion w...
We present a computational method for pattern discovery based on the application of the wavelet transform to symbolic representations of melodies or monophonic voices. We model the importance of a discovered pattern in terms of the compression ratio that can be achieved by using it to describe that part of the melody covered by its occurrences. The...
We present the computational method submitted to the MIREX 2014 Discovery of Repeated Themes & Sections task, and the results on the monophonic version of the JKU Patterns Development Database.
Regression analysis is a powerful and conceptually simple technique for historical data exploration of welding parameters in laser welding process for coil joining. This technique combined with a Quality Control Data System based on camera sensors and a dynamic pattern extraction technique can help to identify important features and relationships i...
Melody is one of the most important elements of analysis in musical units. It carries implicit information regarding harmony and rhythm. Music analysts achieve their task by auditory and visual perception based on experience and contextualization. Can the wavelet technique identify patterns and structures in melody? Western musical examples taken f...
Tuning parameters is essential for the results of the welding process. In order to optimize the tuning process of welding
parameters, we propose a system based on historical data of laser welding machines. On a given combination of materials, the
system extracts patterns dynamically and classifies new cases with a relative accuracy, which depends o...