Nuno Fonseca

Genetic Algorithm Approach to Polyphonic Music Transcription

Automatic music transcription (extracting musical notes from a polyphonic audio stream) is a very complex task that continues waiting for solutions, due to the harmonic complexity of musical sounds. Traditional approaches try to extract the information directly from the audio stream, but by taking into account that a polyphonic audio stream is no more than a combination of several notes, music transcription can be considered as a search problem where the goal is to find the sequence of the notes that best models our audio signal. By taking advantage of the genetic algorithms to explore a large search space we present a new approach to the music transcription problem. The results obtained show the feasibility of the approach.

A Genetic Algorithm Approach with Harmonic Structure Evolution for Polyphonic Music Transcription

This paper presents a genetic algorithm approach with harmonic structure evolution for polyphonic music transcription. Automatic music transcription is a very complex problem that continues waiting for solutions due to the harmonic complexity of musical sounds. More traditional approaches try to extract the information directly from the audio stream, but by taking into account that a polyphonic audio stream is no more than a combination of several musical notes, music transcription can be addressed as a search space problem where the goal is to find the sequence of notes that best models our audio signal. By taking advantage of the genetic algorithms to explore large search spaces we present a new approach to the music transcription problem. In order to reduce the harmonic overfitting several techniques were used including the encoding of the harmonic structure of the internal synthesizer inside the individuals genotype as a way to evolve towards the instrument played on the original audio signal. The results obtained in polyphonic piano transcriptions show the feasibility of the approach.

Concatenative singing voice resynthesis

The concept of capturing the sound of “something” for later replication is not new, and it is used in many synthesizers. But capturing sounds and use them as an audio effect, is less common. This paper presents an approach for the resynthesis of a singing voice, based on concatenative techniques, that uses pre-recorded audio material as an high level semantic audio effect, replacing an original audio recording with the sound of a different singer, while trying to keep the same musical/phonetic performance.

Fragmentation and Frontier Evolution for Genetic Algorithms Optimization in Music Transcription

Although traditional approaches in evolutionary computation encode each individual to represent the entire problem, the idea that an individual could be used to represent only part of it, is not new. Several different approaches exist that are based on decomposing the problem in smaller blocks/fragments, but the act of fragmentation can in some cases create unresolved issues, particularly on the fragments frontiers. This paper presents a method for optimizing some genetic algorithms applications, by fragment the problem in smaller ones, but keeping attention to frontier issues. While this paper focus on the application of the method to the music transcription problem, the proposed approach can be used on many other scenarios (signal processing, image analysis, etc.).

Monitoring the Progress of Programming Students Supported by a Digital Teaching Assistant

Several studies have shown that there is an important link between continual monitoring by the teachers and the students’ performance. Unfortunately, the teachers cannot be continuously looking for what the students are doing. To overcome this situation, we propose the use of CodeInsights, a tool capable of capturing, in an autonomous, transparent and unobtrusive manner, information about the students’ performance and then, based on teacher’s expectations, notify them about possible deviations in the specific context of programming courses. The decision on whether the system should or should not notify the teacher is supported by an artificial cognitive selective attention mechanism. Although CodeInsights, provided with the described mechanism, hasn’t been fully tested in a real case scenario, we present some specific examples of how it can be used to assist teachers.

MPI Farm Programs on Non-dedicated Clusters

MPI has been extremely successful. In areas like e.g. particle physics most of the available parallel programs are based on MPI. Unfortunately, they must be run in dedicated clusters or parallel machines, being unable to use for long running applications the growing pool of idle time of general-purpose desktop computers. Additionally, MPI offers a quite low level interface, which is hard to use for most scientist programmers. In the research described in this paper, we tried to see how far we could go to solve those two problems, keeping the portability of MPI programs, but drawing upon one restriction – only programs following the FARM paradigm were to be supported. The developed library – MpiFL – did provide us significant insight. It is now being successfully used at the physics department of the University of Coimbra, despite some shortcomings.

Abstract 3003: Targeting nucleolin: A potential strategy to overcome stroma-mediated bevacizumab resistance in lung cancer

Proceedings: AACR Annual Meeting 2014; April 5-9, 2014; San Diego, CA Background Noticing the limitations of chemotherapy and the possibility of interrupting the tumor vascular network, there has been an increasing interest in targeting the tumor vasculature and developing agents to disrupt angiogenesis. Anti-angiogenic drugs, such as bevacizumab, have become a standard treatment option in lung cancer. In spite some clinical success with these inhibitors, disappointing results have been reported with patients being intrinsically refractory to anti-VEGF therapies or, following treatment response, ultimately becoming refractory and showing relapse. Moreover, it has been described that not only the tumor cells, but several host factors and stromal components also play an important role in resistance to bevacizumab (Cascone et al., JCI 2011). Aims 1) Validate nucleolin as a therapeutic target for a previous developed F3 peptide-targeted pH sensitive liposome containing doxorubicin (Moura et al., BCRT 2012) in human lung cancer models resistant to bevacizumab and assess the potential to overcome anti-angiogenic resistance. 2) Assess nucleolin expression in patients-derived lung cancer. Experimental design/Results Aiming at confirming the potential application of a previously developed nanoparticle on lung cancer, cellular association studies were carried with flow cytometry. Cell lines with intrinsic (A549 cells) and acquired (H1975, H441 cells) resistance to bevacizumab were incubated with fluorescently-labeled liposomes, either non-targeted (SLpH) or targeted by a non-specific (SLpHNS) or F3 (SLpHF3) peptide, for 1 h at 37 or 4oC (temperature not permissive to endocytosis). Results demonstrated a 30 to 170-fold higher extent of association of F3-targeted liposomes by lung cancer cells than the the controls, suggesting a ligand-specific interaction. Improved association and intracellular delivery of encapsulated DXR enabled by F3-targeted liposomes, justified a 9.6-fold increase of DXR cytotoxicity relative to the non-targeted counterparts. In order to assess the clinical potential of the developed nucleolin-targeted strategy, immunohistochemistry of human specimens derived from lung cancer patients with surgical staged disease was performed aiming at investigating the expression of nucleolin. Results generated so far revealed that nucleolin was highly expressed in different types of cells in the tumor microenvironment of patient-derived lung tumors, in a tumor-specific manner. Main Conclusion The generated results render an important indication of the therapeutic potential of the tested nucleolin-targeted strategy against Bevazcizumab-resistant lung cancer. Acknowledgements Grants: QREN/FEDER/COMPETE (Ref 23240); PEst-C/SAU/LA0001/2011 Â. Valerio-Fernandes is a graduate student from PhD program on Biomedicine and Experimental Biology, Center for Neuroscience and Cell Biology, University of Coimbra (FCT fellowship SFRH/BD/51191/2010) Citation Format: Ângela Valerio-Fernandes, Nuno Fonseca, Vera Moura, Ana Ladeirinha, Teresa Ferreira, Ana Alarcao, Lina Carvalho, Sergio Simoes, Joao Nuno Moreira. Targeting nucleolin: A potential strategy to overcome stroma-mediated bevacizumab resistance in lung cancer. [abstract]. In: Proceedings of the 105th Annual Meeting of the American Association for Cancer Research; 2014 Apr 5-9; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2014;74(19 Suppl):Abstract nr 3003. doi:10.1158/1538-7445.AM2014-3003

Selective delivery of points of interest

In our daily life, we are increasingly surrounded by devices that expose us to quantities of information well behind our cognitive capabilities. To overcome this problem various authors propose mechanisms capable of selecting only the most relevant pieces of information. In this paper, we propose an approach for information selection based on the concepts of relevance, selective attention and diversity. The idea is to select the most promising items in terms of surprise and usefulness and dismiss those that are less promising. We illustrate our approach with an example of an application for restaurant selection and show the first results from an initial evaluation of this system.