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.).