Brain Computer Music Interfacing for Composition 2019-
Creation of a system that uses electroencephalogram (EEG) information to compose and perform music.
Advisor: João Luís Garcia Rosa
I received my BSc in Information Systems from the Univerity of Uberlândia and Msc in Applied Computing from the University of São Paulo, Ribeirão Preto, Brazil. Currently, I am a PhD candidate in Computer Science at University of São Paulo, São Carlos, Brazil.
My research interests are Brain Computer Music Interfacing Music Imagery Information Retrieval, Brain Computer Interface, Computer Music, Signal Processing, Complex Networks, Information Retrieval, Machine Learning, Pattern Recognition, Data Mining, Bio-inspired Computing, Natural Language Processing.
Actually I am working with Brain Computer Music Interfacing for composition which can transfer thought to script, known as the P300 event-related potential. In my Msc research I worked with Heterogeneous Information Networks, Natural Language Processing, Information Retrival and Information Extraction. In my undergraduate dissertation I worked with automatic music transcription for monophonic songs.
Institute of Mathematics and Computer Sciences – São Carlos
Av. Trab. São Carlense, 400 - Parque Arnold Schimidt, São Carlos - SP, CEP 13566-590
Faculty of Philosophy, Sciences and Letters at Ribeirão Preto - FFCLRP
Department of Computing and Mathematics - DCM
Av. Bandeirantes, 3900 - Vila Virginia, Ribeirão Preto - SP, CEP 14040-900
Faculty of Computer Science - FACOM
Rodovia LMG 746, Km 1, Campus Monte Carmelo - Monte Carmelo-MG - CEP 38500-000.
Praça José Miranda, s/n Centro, Romaria - MG, CEP 38520-000
Creation of a system that uses electroencephalogram (EEG) information to compose and perform music.
Advisor: João Luís Garcia Rosa
This work presents the creation of a Heterogeneous Information Network using classical similarity measures, terminology products and the attributes of documents by an algorithm called NetworkCreator. As a contribution, an algorithm called NetworkCreator was created that from medical records and scientific articles builds an HIN with related documents, was also created. The algorithm HeteSimTKSQuery to calculate similarity measures between documents of different types which are in HIN. Terminology products with meta-paths were also explored. The results were efficient, reaching on average 89% accuracy in some cases. However, it is important to note that all HIN presented in the researched literature were constructed only by one type of data coming from a single source. The results show that the algorithms are feasible to solve the problems of HIN construction and search for similarity. But it still needs improvement. In the future one can work on detection in the detection of node granularity of these networks and try to reduce the network construction runtime.
Advisor: Alessandra Alaniz Macedo
Scolarship: Coordenação de Aperfeiçoamento de Pessoal de Nível Superior, CAPES, Brazil.
The development of computational techniques for transcription of monophonic piano, alto saxophone, and sweet flute songs performed in a semi-controlled environment. It includes the creation of a library of computational functions that identify notes, rhythm, and measurement, in different supervised and unsupervised classification methods. Among the algorithms were implemented RNAs, K-Means, KNN, Decision Tree Trees, and The signal processing method itself was systematically applied to identify its suitability or problem. For this study, we created a database of 100 songs, in ascending order of musical complexity. The songs played for one instrument were also played for the other two. Thus, the total dataset has a total of 300 songs that are clean, plus 900 songs with gradual levels of real and artificial noise for each song. All dataset contains 2100 songs. Also, manual segmentation was performed as a gold standard to test the experiments. Later more piano songs were added.
Advisor: Daniel Duarte Abdala.
Scolarship: Fundação de Amparo à Pesquisa do Estado de Minas Gerais,FAPEMIG.
Avenida Trabalhador são-carlense, 400 - Centro CEP: 13566-590 - São Carlos - SP