We present the design and functionality of Big Data Start Platform (BDSP), a web system wherein users can perform Big Data tasks anytime, anywhere through any device with a browser and access to Internet. BDSP integrates different data sources and data processing tasks through web services. Its purpose is to serve in three ways: as a tool for rapid-prototyping of Big Data projects; as a base platform to be tuned and extended according to need; and as a training vehicle both in data analysis and in developing software for Big Data tasks.

This paper presents a study designed to understand the effect of using a talking head in academic videos frequently used in video-based learning approaches, such Massive Open Online Courses. The experiment consisted of exposing participants to videos about different types of open software licenses. Each participant was exposed to 3 videos, each with a different condition: instructor always presented (talking head condition), only instructor's voice present (only audio condition), and instructor presented only at the beginning of the video (mixed condition). Dependent variables included cognitive load, and emotional states (valance and arousal) obtained with electroencephalography, a personal assessment of the difficulty of the material, personal opinion regarding the social presence and performance in a memory test. The results indicate an increase in the cognitive load in the mixed condition, which may have implications regarding the use of the talking head in the design of academic videos.

We describe an evolutionary approach to one of the most challenging problems in computer music: modeling how skilled musicians manipulate sound properties such as timing and amplitude in order to express their view of the emotional content of musical pieces. Starting with a collection of audio recordings of real performances, we apply a sequential-covering genetic algorithm in order to obtain computational models for different aspects of expressive performance. We use these models to automatically synthesize performances with the timing and energy expressiveness that characterizes the music generated by a professional musician. The reported results indicate that evolutionary computation is an appropriate technique for solving the problem considered. Specifically, our evolutionary algorithm provides a number of potential advantages over other supervised learning algorithms, such as a method for non-deterministically obtaining models capturing different possible interpretations of a musical piece.

MML 2010, the International Workshop on Machine Learning and Music, continues a series of workshops related to artificial intelligence and machine learning in music. In this short article the Programme Chairs summarize the content of the workshop.

Music has a long and rich tradition within machine learning.Some of the first applications of early computing machinery were statistical models of melody learned through the analysis of examples.Today machine learning is applied to highly complex music textures and used routinely for music classification, generation and improvisation, music analysis, and performance analysis, to name just a few key applications.Due to the steady increase in available data, most music processing applications can now be supported by some machine learning component.Methods for machine learning in music can be described in terms of their application task, the representation and characteristics of the input data, and the machine learning algorithm used.Though detailed musicological studies will always require clean symbolic data, the classical boundary of audio versus symbolic input is now starting to dissipate as many methods now translate audio data to the symbolic domain where learning takes place, then back again where learned results are applied to the audio signal.For this Special Issue of Intelligent Data Analysis we are pleased to present five articles that cover a wide range of application tasks and music data types.Submission to this Special Issue was solicited by the Editors and each submission was given three reviews by experts in the field, with a second round if necessary, followed by a check of

We present a machine learning approach to modeling bowing control parameter contours in violin performance. Using accurate sensing techniques we obtain relevant timbre-related bowing control parameters such as bow transversal velocity, bow pressing force, and bow-bridge distance of each performed n ote. Each performed note is represented by a curve parameter vector and a number of note classes are defined. The principal components of the data represented by the set of curve parameter vectors are obtained for each class. Once curve parameter vectors are expressed in the new space defined by the principal components, we train a model based on inductive logic programming, able to predict curve parameter vectors used for rendering bowing controls. We evaluate the prediction results and show the potential of the model by predicting bowing control parameter contours from an annotated input score.

In this paper we present a genre classification framework for audio music based on a symbolic classification system. Audio signals are transformed into a symbolic representation of harmony using a chord transcription algorithm, based on the computati

Professional musicians intuitively manipulate sound properties such as pitch, timing, amplitude and timbre in order to produce expressive performances of particular pieces. However, there is little explicit information about how and in which musical

The goal of this work is to identify famous tenors from commercial recordings. Our approach is based on training expressive singer-specific models and using them to classify new musical fragments interpreted by singers that perform arias from the training set. In this paper we focus on expressive timing variations and build the models by applying machine learning techniques to a body of data consisting of high-level descriptors extracted from audio recordings. The experimental results show evidence that performers can be automatically identified at a rate significantly better than random choice.

The study of human brain functions has dramatically increased in recent years greatly due to the advent of functional magnetic resonance imaging. This paper presents a genetic programming approach to the problem of classifying the instantaneous cognitive state of a person based on his/her functional magnetic resonance imaging data. The problem provides a very interesting case study of training classifiers with extremely high dimensional, sparse and noisy data. We apply genetic programming for both feature selection and classifier training. We present a successful case study of induced classifiers which accurately discriminate between cognitive states produced by listening to different auditory stimuli.

A central issue of all approaches to composing adaptive software is a level of indirection for intercepting and redirecting interactions among program entities. It has been pointed out that separation of concerns is one of the key techniques for reconfigurable software design. In this paper we describe a general framework for the separation of concerns in concurrent applications. Concurrency issues are separated and treated as orthogonal to the system base functionality. The framework combines declarative and imperative programming and provides a powerful mechanism for synchronizing concurrent computations. We describe a particular implementation of the framework (for both uniprocessors and distributed systems) as an extension to the Java programming language, and comment on how model-based verification methods can be automatically applied to programs in the resulting language.

In this paper, we describe an evolutionary approach to inducing a generative model of expressive music performance for Jazz saxophone. We begin with a collection of audio recordings of real Jazz saxophone performances from which we extract a symbolic representation of the musician's expressive performance. We then apply an evolutionary algorithm to the symbolic representation in order to obtain computational models for different aspects of expressive performance. Finally, we use these models to automatically synthesize performances with the expressiveness that characterizes the music generated by a professional saxophonist.

We propose a novel approach to the task of identifying performers from their playing styles. We investigate how skilled musicians (Jazz saxophone players in particular) express and communicate their view of the musical and emotional content of musical pieces and how to use this information in order to automatically identify performers. We study deviations of parameters such as pitch, timing, amplitude and timbre both at an inter-note level and at an intra-note level. Our approach to performer identification consists of establishing a performer dependent mapping of inter-note features (essentially a "score" whether or not the score physically exists) to a repertoire of inflections characterized by intra-note features. We present a successful performer identification case study

The task of programming concurrent systems is substantially more difficult than the task of programming sequential systems with respect to both correctness and efficiency. This paper describes (1) a powerful mechanism for elegantly synchronizing concurrent and distributed computations which supports a declarative model of concurrency that avoids explicitly suspending and resuming computations, (2) its implementation (for both uniprocessors and distributed systems) as an extension to the Java programming language, and (3) how model-based verification methods can be directly applied to programs in the resulting language.

In this paper we describe a machine learning approach to one of the most challenging aspects of computer music: modeling the knowledge applied by a musician when performing a score in order to produce an expressive performance of a piece. We apply machine learning techniques to a set of monophonic Jazz standards recordings in order to induce both rules and a numeric model for expressive performance. We implement a tool for automatic expressive performance transformations of Jazz melodies using the induced knowledge.

This brief announcement outlines a new model for high-level concurrent and distributed programming based on constraint entailment, and how model-based verification methods can be directly applied to Java programs synchronizing using the model.

The task of programming concurrent systems is substantially more difficult than the task of programming sequential systems with respect to both correctness and efficiency. In this paper we describe a constraint-based methodology for writing concurrent applications. A system is modeled as: (a) a set of processes containing a sequence of "markers" denoting the processes points of interest; and (b) a constraint store. Process synchronization is specified by incrementally adding constraints on the markers execution order into the constraint store. The constraint store contains a declarative specification based on a temporal constraint logic program. The store, thus, acts as a coordination entity which on the one hand encapsulates the system synchronization requirements, and on the other hand, provides a declarative specification of the system concurrency issues. This provide great advantages in writing concurrent programs and manipulating them while preserving correctness.