Josep Lluis Arcos - Academia.edu (original) (raw)

Papers by Josep Lluis Arcos

Locating boundaries between coherent and/or repetitive segments of a time series is a challenging... more Locating boundaries between coherent and/or repetitive segments of a time series is a challenging problem pervading many scientific domains. In this paper we propose an unsupervised method for boundary detection, combining three basic principles: novelty, homogene-ity, and repetition. In particular, the method uses what we call structure features, a representation encapsulating both local and global properties of a time series. We demonstrate the usefulness of our approach in detecting music structure boundaries, a task that has received much attention in recent years and for which exist several benchmark datasets and publicly available annotations. We find our method to significantly outperform the best accuracies published so far. Importantly, our boundary approach is generic, thus being applicable to a wide range of time series beyond the music and audio domains.

Content-based approaches to music retrieval are of great relevance as they do not require any kin... more Content-based approaches to music retrieval are of great relevance as they do not require any kind of manually generated annotations. In this paper, we introduce the concept of structure fingerprints, which are compact descrip-tors of the musical structure of an audio recording. Given a recorded music performance, structure fingerprints facilitate the retrieval of other performances sharing the same underlying structure. Avoiding any explicit determination of musical structure, our fingerprints can be thought of as a probability density function derived from a self-similarity matrix. We show that the proposed fingerprints can be compared by using simple Euclidean distances without using any kind of complex warping operations required in previous approaches. Experiments on a collection of Chopin Mazurkas reveal that structure fingerprints facilitate robust and efficient content-based music retrieval. Furthermore , we give a musically informed discussion that also deepens the understanding of this popular Mazurka dataset.

Fuzzy Sets and Systems, 2013

In this paper we present our research on the design of a tool to analyze musical expressivity. Mu... more In this paper we present our research on the design of a tool to analyze musical expressivity. Musical expressivity is a human activity difficult to model compu.

Natural Computing, 2013

In the last decade, bio-inspired self-organising mechanisms have been applied to different domain... more In the last decade, bio-inspired self-organising mechanisms have been applied to different domains, achieving results beyond traditional approaches. However, researchers usually use these mechanisms in an ad-hoc manner. In this way, their interpretation, definition, boundary (i.e. when one mechanism stops, and when another starts), and implementation typically vary in the existing literature, thus preventing these mechanisms from being applied clearly and systematically to solve recurrent problems. To ease engineering of artificial bio-inspired systems, this paper describes a catalogue of bio-inspired mechanisms in terms of modular and reusable design patterns organised into different layers. This catalogue uniformly frames and classifies a variety of different patterns. Additionally, this paper places the design patterns inside existing self-organising methodologies and hints for selecting and using a design pattern.

IEEE Congress on Evolutionary Computation, 2010

The optimisation in dynamic and noisy environments brings closer real-world optimisation. One int... more The optimisation in dynamic and noisy environments brings closer real-world optimisation. One interesting proposal to adapt the PSO for working in dynamic and noisy environments was the incorporation of an evaporation mechanism. The evaporation mechanism avoids the detection of environment changes, providing a continuous adaptation to the environment changes and reducing the effect when the fitness function is subject to noise. However, its performance decreases when the fitness function is not subjected to noise (with respect to methods that use environment change detection). In this paper we propose a new dynamic evaporation policy to adapt the PSO algorithm to dynamic and noisy environments. Our approach improves the performance when the fitness function is dynamic and not subject to noise. It also keeps a similar performance when the fitness function is subject to noise.

Proceedings of the 11th Annual conference on Genetic and evolutionary computation - GECCO '09, 2009

Dealing with imprecise information is a common characteristic in real-world problems. Specificall... more Dealing with imprecise information is a common characteristic in real-world problems. Specifically, when the source of the information are physical sensors, a level of noise in the evaluation has to be assumed. Particle Swarm Optimization is a technique that presented a good behavior when dealing with noisy fitness functions. Nevertheless, the problem is still open. In this paper we propose the use of the evaporation mechanism for managing with dynamic multi-modal optimization problems that are subject to noisy fitness functions. We will show how the evaporation mechanism does not require the detection of environment changes and how can be used for improving the performance of PSO algorithms working in noisy environments.

Proceedings of the 2009 ACM symposium on Applied Computing - SAC '09, 2009

This paper presents a new exploration mechanism based on a heterogeneous multi-agent system that ... more This paper presents a new exploration mechanism based on a heterogeneous multi-agent system that combines attractive and repulsive agents. We provide experimental results about the performance of our mechanism in dynamic environments when resources continuously appear and disappear.

2008 Second IEEE International Conference on Self-Adaptive and Self-Organizing Systems, 2008

This work extends the Particle Swarm Optimization (PSO) algorithm for working on dynamic environm... more This work extends the Particle Swarm Optimization (PSO) algorithm for working on dynamic environments. We propose an evaporation mechanism to solve the outdated memory problem. We empirically show that our evaporation mechanism is able to achieve self-adaption without any knowledge on when changes occur.

Knowledge-Based Systems, 2014

Time series are ubiquitous, and a measure to assess their similarity is a core part of many compu... more Time series are ubiquitous, and a measure to assess their similarity is a core part of many computational systems. In particular, the similarity measure is the most essential ingredient of time series clustering and classification systems. Because of this importance, countless approaches to estimate time series similarity have been proposed. However, there is a lack of comparative studies using empirical, rigorous, quantitative, and large-scale assessment strategies. In this article, we provide an extensive evaluation of similarity measures for time series classification following the aforementioned principles. We consider 7 different measures coming from alternative measure ‘families’, and 45 publicly-available time series data sets coming from a wide variety of scientific domains. We focus on out-of-sample classification accuracy, but in-sample accuracies and parameter choices are also discussed. Our work is based on rigorous evaluation methodologies and includes the use of powerful statistical significance tests to derive meaningful conclusions. The obtained results show the equivalence, in terms of accuracy, of a number of measures, but with one single candidate outperforming the rest. Such findings, together with the followed methodology, invite researchers on the field to adopt a more consistent evaluation criteria and a more informed decision regarding the baseline measures to which new developments should be compared.

IEEE TRANSACTIONS ON MULTIMEDIA, VOL. 16, N. 5, 2014

Automatically inferring the structural properties of raw multimedia documents is essential in tod... more Automatically inferring the structural properties of raw multimedia documents is essential in today’s digitized society. Given its hierarchical and multi-faceted organization, musical pieces represent a challenge for current computational systems. In this article, we present a novel approach to music structure annotation based on the combination of structure features with time series similarity. Structure features encapsulate both local and global properties of a time series, and allow us to detect boundaries between homogeneous, novel, or repeated segments. Time series similarity is used to identify equivalent segments, corresponding to musically meaningful parts. Extensive tests with a total of five benchmark music collections and seven different human annotations show that the proposed approach is robust to different ground truth choices and parameter settings. Moreover, we see that it outperforms previous approaches evaluated under the same framework.

PLOS ONE, 2013

A competent interpretation of a musical composition presents several non-explicit departures from... more A competent interpretation of a musical composition presents several non-explicit departures from the written score. Timing variations are perhaps the most important ones: they are fundamental for expressive performance and a key ingredient for conferring a human-like quality to machine-based music renditions. However, the nature of such variations is still an open research question, with diverse theories that indicate a multi-dimensional phenomenon. In the present study, we consider event-shift timing variations and show that sequences of note onset deviations are robust and reliable predictors of the musical piece being played, irrespective of the performer. In fact, our results suggest that only a few consecutive onset deviations are already enough to identify a musical composition with statistically significant accuracy. We consider a mid-size collection of commercial recordings of classical guitar pieces and follow a quantitative approach based on the combination of standard statistical tools and machine learning techniques with the semi-automatic estimation of onset deviations. Besides the reported results, we believe that the considered materials and the methodology followed widen the testing ground for studying musical timing and could open new perspectives in related research fields.

Scientific Reports, 2012

Popular music is a key cultural expression that has captured listeners’ attention for ages. Many ... more Popular music is a key cultural expression that has captured listeners’ attention for ages. Many of the structural regularities underlying musical discourse are yet to be discovered and, accordingly, their historical evolution remains formally unknown. Here we unveil a number of patterns and metrics characterizing the generic usage of primary musical facets such as pitch, timbre, and loudness in contemporary western popular music. Many of these patterns and metrics have been consistently stable for a period of more than fifty years. However, we prove important changes or trends related to the restriction of pitch transitions, the homogenization of the timbral palette, and the growing loudness levels. This suggests that our perception of the new would be rooted on these changing characteristics. Hence, an old tune could perfectly sound novel and fashionable, provided that it consisted of common harmonic progressions, changed the instrumentation, and increased the average loudness.

ACM Transactions on Autonomous and Adaptive Systems, 2011

This article defines and analyzes a collection of algorithms for persistent storage of data at sp... more This article defines and analyzes a collection of algorithms for persistent storage of data at specific geographical zones exploiting the memory of mobile devices located in these areas. Contrarily to other approaches for data dissemination, our approach uses a viral programming model. Data performs an active role in the storage process. It acts as a virus or a mobile agent,

ACM Symposium on Applied Computing, 2010

This paper studies the use of highly dynamic networks as infrastructures for persistent storage o... more This paper studies the use of highly dynamic networks as infrastructures for persistent storage of data that offer services at specific geographical zones in a decentralized and distributed way. We propose a new algorithm, based on repulsion techniques, to self-organize the nodes that store and serve the information. In this work, we focus on the evaluation of our algorithm when

IEEE Workshop on Engineering of Autonomic and Autonomous Systems, 2011

Today's software applications increasingly feature a great deal of openness, dynamism and unp... more Today's software applications increasingly feature a great deal of openness, dynamism and unpredictable behav- ior, forcing to shift design and engineering from traditional, centralized approaches to nature-inspired, self-organizing tech- niques. Among the others, biology has been adopted as a source of inspiration to solve some of the issues proper of nowadays systems by self-organizing techniques, usually exploited in an ad-hoc

International Symposium/Conference on Music Information Retrieval, 2008

This paper presents a new approach for identifying profes- sional performers in commercial record... more This paper presents a new approach for identifying profes- sional performers in commercial recordings. We propose a Trend-based model that, analyzing the way Narmour's Im- plication-Realization patterns are played, is able to charac- terize performers. Concretely, starting from automatically extracted descriptors provided by state-of-the-art extraction tools, the system performs a mapping to a set of qualita- tive behavior shapes and

Agent-Mediated Electronic Commerce, 1991

This paper explains the inference and reection capabilities of NOOS, an object-centered represent... more This paper explains the inference and reection capabilities of NOOS, an object-centered representation language designed to integrate problem solving and learning. Problem solving and learning in NOOS are modelled by means of concepts, tasks, methods and metalevels. Metalevels allow NOOS to reason own problem solving. Using metalevels, NOOS can reason about preferences in order to make decisions about sets of alternatives present in domain knowledge and problem solving knowledge. Reection in NOOS is provided by inference processes that involve metalevels. Basic reective capabilities include reasoning about alternative methods to solve a task, reasoning about what is known by the system itself, and reasoning about the existence of solutions. A formal model of NOOS inference using Descriptive Dynamic Logic is also presented.

Bio-inspired mechanisms have been extensively used in the last decade for solving optimisation pr... more Bio-inspired mechanisms have been extensively used in the last decade for solving optimisation problems and for decentralised control of sensors, robots or nodes in P2P systems. Different attempts at describing some of these mechanisms have been proposed, some of them under the form of design patterns. However, there is not so far a clear catalogue of these mechanisms, described as

International Journal of Cooperative Information Systems, 2002

Abstract: We present a society of personal information agents that work for a community of users ... more Abstract: We present a society of personal information agents that work for a community of users and that are aware of the physical and social context of their users. We show how context-awareness is a feature that allows the agents to improve their performance when ...

Locating boundaries between coherent and/or repetitive segments of a time series is a challenging... more Locating boundaries between coherent and/or repetitive segments of a time series is a challenging problem pervading many scientific domains. In this paper we propose an unsupervised method for boundary detection, combining three basic principles: novelty, homogene-ity, and repetition. In particular, the method uses what we call structure features, a representation encapsulating both local and global properties of a time series. We demonstrate the usefulness of our approach in detecting music structure boundaries, a task that has received much attention in recent years and for which exist several benchmark datasets and publicly available annotations. We find our method to significantly outperform the best accuracies published so far. Importantly, our boundary approach is generic, thus being applicable to a wide range of time series beyond the music and audio domains.

Content-based approaches to music retrieval are of great relevance as they do not require any kin... more Content-based approaches to music retrieval are of great relevance as they do not require any kind of manually generated annotations. In this paper, we introduce the concept of structure fingerprints, which are compact descrip-tors of the musical structure of an audio recording. Given a recorded music performance, structure fingerprints facilitate the retrieval of other performances sharing the same underlying structure. Avoiding any explicit determination of musical structure, our fingerprints can be thought of as a probability density function derived from a self-similarity matrix. We show that the proposed fingerprints can be compared by using simple Euclidean distances without using any kind of complex warping operations required in previous approaches. Experiments on a collection of Chopin Mazurkas reveal that structure fingerprints facilitate robust and efficient content-based music retrieval. Furthermore , we give a musically informed discussion that also deepens the understanding of this popular Mazurka dataset.

Fuzzy Sets and Systems, 2013

In this paper we present our research on the design of a tool to analyze musical expressivity. Mu... more In this paper we present our research on the design of a tool to analyze musical expressivity. Musical expressivity is a human activity difficult to model compu.

Natural Computing, 2013

In the last decade, bio-inspired self-organising mechanisms have been applied to different domain... more In the last decade, bio-inspired self-organising mechanisms have been applied to different domains, achieving results beyond traditional approaches. However, researchers usually use these mechanisms in an ad-hoc manner. In this way, their interpretation, definition, boundary (i.e. when one mechanism stops, and when another starts), and implementation typically vary in the existing literature, thus preventing these mechanisms from being applied clearly and systematically to solve recurrent problems. To ease engineering of artificial bio-inspired systems, this paper describes a catalogue of bio-inspired mechanisms in terms of modular and reusable design patterns organised into different layers. This catalogue uniformly frames and classifies a variety of different patterns. Additionally, this paper places the design patterns inside existing self-organising methodologies and hints for selecting and using a design pattern.

IEEE Congress on Evolutionary Computation, 2010

The optimisation in dynamic and noisy environments brings closer real-world optimisation. One int... more The optimisation in dynamic and noisy environments brings closer real-world optimisation. One interesting proposal to adapt the PSO for working in dynamic and noisy environments was the incorporation of an evaporation mechanism. The evaporation mechanism avoids the detection of environment changes, providing a continuous adaptation to the environment changes and reducing the effect when the fitness function is subject to noise. However, its performance decreases when the fitness function is not subjected to noise (with respect to methods that use environment change detection). In this paper we propose a new dynamic evaporation policy to adapt the PSO algorithm to dynamic and noisy environments. Our approach improves the performance when the fitness function is dynamic and not subject to noise. It also keeps a similar performance when the fitness function is subject to noise.

Proceedings of the 11th Annual conference on Genetic and evolutionary computation - GECCO '09, 2009

Dealing with imprecise information is a common characteristic in real-world problems. Specificall... more Dealing with imprecise information is a common characteristic in real-world problems. Specifically, when the source of the information are physical sensors, a level of noise in the evaluation has to be assumed. Particle Swarm Optimization is a technique that presented a good behavior when dealing with noisy fitness functions. Nevertheless, the problem is still open. In this paper we propose the use of the evaporation mechanism for managing with dynamic multi-modal optimization problems that are subject to noisy fitness functions. We will show how the evaporation mechanism does not require the detection of environment changes and how can be used for improving the performance of PSO algorithms working in noisy environments.

Proceedings of the 2009 ACM symposium on Applied Computing - SAC '09, 2009

This paper presents a new exploration mechanism based on a heterogeneous multi-agent system that ... more This paper presents a new exploration mechanism based on a heterogeneous multi-agent system that combines attractive and repulsive agents. We provide experimental results about the performance of our mechanism in dynamic environments when resources continuously appear and disappear.

2008 Second IEEE International Conference on Self-Adaptive and Self-Organizing Systems, 2008

This work extends the Particle Swarm Optimization (PSO) algorithm for working on dynamic environm... more This work extends the Particle Swarm Optimization (PSO) algorithm for working on dynamic environments. We propose an evaporation mechanism to solve the outdated memory problem. We empirically show that our evaporation mechanism is able to achieve self-adaption without any knowledge on when changes occur.

Knowledge-Based Systems, 2014

Time series are ubiquitous, and a measure to assess their similarity is a core part of many compu... more Time series are ubiquitous, and a measure to assess their similarity is a core part of many computational systems. In particular, the similarity measure is the most essential ingredient of time series clustering and classification systems. Because of this importance, countless approaches to estimate time series similarity have been proposed. However, there is a lack of comparative studies using empirical, rigorous, quantitative, and large-scale assessment strategies. In this article, we provide an extensive evaluation of similarity measures for time series classification following the aforementioned principles. We consider 7 different measures coming from alternative measure ‘families’, and 45 publicly-available time series data sets coming from a wide variety of scientific domains. We focus on out-of-sample classification accuracy, but in-sample accuracies and parameter choices are also discussed. Our work is based on rigorous evaluation methodologies and includes the use of powerful statistical significance tests to derive meaningful conclusions. The obtained results show the equivalence, in terms of accuracy, of a number of measures, but with one single candidate outperforming the rest. Such findings, together with the followed methodology, invite researchers on the field to adopt a more consistent evaluation criteria and a more informed decision regarding the baseline measures to which new developments should be compared.

IEEE TRANSACTIONS ON MULTIMEDIA, VOL. 16, N. 5, 2014

Automatically inferring the structural properties of raw multimedia documents is essential in tod... more Automatically inferring the structural properties of raw multimedia documents is essential in today’s digitized society. Given its hierarchical and multi-faceted organization, musical pieces represent a challenge for current computational systems. In this article, we present a novel approach to music structure annotation based on the combination of structure features with time series similarity. Structure features encapsulate both local and global properties of a time series, and allow us to detect boundaries between homogeneous, novel, or repeated segments. Time series similarity is used to identify equivalent segments, corresponding to musically meaningful parts. Extensive tests with a total of five benchmark music collections and seven different human annotations show that the proposed approach is robust to different ground truth choices and parameter settings. Moreover, we see that it outperforms previous approaches evaluated under the same framework.

PLOS ONE, 2013

A competent interpretation of a musical composition presents several non-explicit departures from... more A competent interpretation of a musical composition presents several non-explicit departures from the written score. Timing variations are perhaps the most important ones: they are fundamental for expressive performance and a key ingredient for conferring a human-like quality to machine-based music renditions. However, the nature of such variations is still an open research question, with diverse theories that indicate a multi-dimensional phenomenon. In the present study, we consider event-shift timing variations and show that sequences of note onset deviations are robust and reliable predictors of the musical piece being played, irrespective of the performer. In fact, our results suggest that only a few consecutive onset deviations are already enough to identify a musical composition with statistically significant accuracy. We consider a mid-size collection of commercial recordings of classical guitar pieces and follow a quantitative approach based on the combination of standard statistical tools and machine learning techniques with the semi-automatic estimation of onset deviations. Besides the reported results, we believe that the considered materials and the methodology followed widen the testing ground for studying musical timing and could open new perspectives in related research fields.

Scientific Reports, 2012

Popular music is a key cultural expression that has captured listeners’ attention for ages. Many ... more Popular music is a key cultural expression that has captured listeners’ attention for ages. Many of the structural regularities underlying musical discourse are yet to be discovered and, accordingly, their historical evolution remains formally unknown. Here we unveil a number of patterns and metrics characterizing the generic usage of primary musical facets such as pitch, timbre, and loudness in contemporary western popular music. Many of these patterns and metrics have been consistently stable for a period of more than fifty years. However, we prove important changes or trends related to the restriction of pitch transitions, the homogenization of the timbral palette, and the growing loudness levels. This suggests that our perception of the new would be rooted on these changing characteristics. Hence, an old tune could perfectly sound novel and fashionable, provided that it consisted of common harmonic progressions, changed the instrumentation, and increased the average loudness.

ACM Transactions on Autonomous and Adaptive Systems, 2011

This article defines and analyzes a collection of algorithms for persistent storage of data at sp... more This article defines and analyzes a collection of algorithms for persistent storage of data at specific geographical zones exploiting the memory of mobile devices located in these areas. Contrarily to other approaches for data dissemination, our approach uses a viral programming model. Data performs an active role in the storage process. It acts as a virus or a mobile agent,

ACM Symposium on Applied Computing, 2010

This paper studies the use of highly dynamic networks as infrastructures for persistent storage o... more This paper studies the use of highly dynamic networks as infrastructures for persistent storage of data that offer services at specific geographical zones in a decentralized and distributed way. We propose a new algorithm, based on repulsion techniques, to self-organize the nodes that store and serve the information. In this work, we focus on the evaluation of our algorithm when

IEEE Workshop on Engineering of Autonomic and Autonomous Systems, 2011

Today's software applications increasingly feature a great deal of openness, dynamism and unp... more Today's software applications increasingly feature a great deal of openness, dynamism and unpredictable behav- ior, forcing to shift design and engineering from traditional, centralized approaches to nature-inspired, self-organizing tech- niques. Among the others, biology has been adopted as a source of inspiration to solve some of the issues proper of nowadays systems by self-organizing techniques, usually exploited in an ad-hoc

International Symposium/Conference on Music Information Retrieval, 2008

This paper presents a new approach for identifying profes- sional performers in commercial record... more This paper presents a new approach for identifying profes- sional performers in commercial recordings. We propose a Trend-based model that, analyzing the way Narmour's Im- plication-Realization patterns are played, is able to charac- terize performers. Concretely, starting from automatically extracted descriptors provided by state-of-the-art extraction tools, the system performs a mapping to a set of qualita- tive behavior shapes and

Agent-Mediated Electronic Commerce, 1991

This paper explains the inference and reection capabilities of NOOS, an object-centered represent... more This paper explains the inference and reection capabilities of NOOS, an object-centered representation language designed to integrate problem solving and learning. Problem solving and learning in NOOS are modelled by means of concepts, tasks, methods and metalevels. Metalevels allow NOOS to reason own problem solving. Using metalevels, NOOS can reason about preferences in order to make decisions about sets of alternatives present in domain knowledge and problem solving knowledge. Reection in NOOS is provided by inference processes that involve metalevels. Basic reective capabilities include reasoning about alternative methods to solve a task, reasoning about what is known by the system itself, and reasoning about the existence of solutions. A formal model of NOOS inference using Descriptive Dynamic Logic is also presented.

Bio-inspired mechanisms have been extensively used in the last decade for solving optimisation pr... more Bio-inspired mechanisms have been extensively used in the last decade for solving optimisation problems and for decentralised control of sensors, robots or nodes in P2P systems. Different attempts at describing some of these mechanisms have been proposed, some of them under the form of design patterns. However, there is not so far a clear catalogue of these mechanisms, described as

International Journal of Cooperative Information Systems, 2002

Abstract: We present a society of personal information agents that work for a community of users ... more Abstract: We present a society of personal information agents that work for a community of users and that are aware of the physical and social context of their users. We show how context-awareness is a feature that allows the agents to improve their performance when ...