Lilian Berton

Music Genre Classification Using Traditional and Relational Approaches

Given the huge size of music collections available on the Web, automatic genre classification is crucial for the organization, search, retrieval and recommendation of music. Different kinds of features have been employed as input to classification models which have been shown to achieve high accuracy in classification scenarios under controlled environments. In this work, we investigate two components of the music genre classification process: a novel feature vector obtained directly from a description of the musical structure described in MIDI files (named as structural features), and the performance of relational classifiers compared to the traditional ones. Neither structural features nor relational classifiers have been previously applied to the music genre classification problem. Our hypotheses are: (i) the structural features provide a more effective description than those currently employed in automatic music genre classification tasks, and (ii) relational classifiers can outperform traditional algorithms, as they operate on graph models of the data that embed information on the similarity between music tracks. Results from experiments carried out on a music dataset with unbalanced distribution of genres indicate these hypotheses are promising and deserve further investigation.

Graph Construction Based on Labeled Instances for Semi-supervised Learning

Semi-Supervised Learning (SSL) techniques have become very relevant since they require a small set of labeled data. In this context, graph-based algorithms have gained prominence in the area due to their capacity to exploiting, besides information about data points, the relationships among them. Moreover, data represented in graphs allow the use of collective inference (vertices can affect each other), propagation of labels (autocorrelation among neighbors) and use of neighborhood characteristics of a vertex. An important step in graph-based SSL methods is the conversion of tabular data into a weighted graph. The graph construction has a key role in the quality of the classification in graph-based methods. This paper explores a method for graph construction that uses available labeled data. We provide extensive experiments showing the proposed method has many advantages: good classification accuracy, quadratic time complexity, no sensitivity to the parameter k > 10, sparse graph formation with average degree around 2 and hub formation from the labeled points, which facilitates the propagation of labels.

Link prediction in graph construction for supervised and semi-supervised learning

Many real-world domains are relational in nature since they consist of a set of objects related to each other in complex ways. However, there are also flat data sets and if we want to apply graph-based algorithms, it is necessary to construct a graph from this data. This paper aims to: i) increase the exploration of graph-based algorithms and ii) proposes new techniques for graph construction from flat data. Our proposal focuses on constructing graphs using link prediction measures for predicting the existence of links between entities from an initial graph. Starting from a basic graph structure such as a minimum spanning tree, we apply a link prediction measure to add new edges in the graph. The link prediction measures considered here are based on structural similarity of the graph that improves the graph connectivity. We evaluate our proposal for graph construction in supervised and semi-supervised classification and we confirm the graphs achieve better accuracy.

A naïve Bayes model based on overlapping groups for link prediction in online social networks

Link prediction in online social networks is useful in numerous applications, mainly for recommendation. Recently, different approaches have considered friendship groups information for increasing the link prediction accuracy. Nevertheless, these approaches do not consider the different roles that common neighbors may play in the different overlapping groups that they belong to. In this paper, we propose a new approach that uses overlapping groups structural information for building a naïve Bayes model. From this proposal, we show three different measures derived from the common neighbors. We perform experiments for both unsupervised and supervised link prediction strategies considering the link imbalance problem. We compare sixteen measures in four well-known online social networks: Flickr, LiveJournal, Orkut and Youtube. Results show that our proposals help to improve the link prediction accuracy.

Regular graph construction for semi-supervised learning

Semi-supervised learning (SSL) stands out for using a small amount of labeled points for data clustering and classification. In this scenario graph-based methods allow the analysis of local and global characteristics of the available data by identifying classes or groups regardless data distribution and representing submanifold in Euclidean space. Most of methods used in literature for SSL classification do not worry about graph construction. However, regular graphs can obtain better classification accuracy compared to traditional methods such as k-nearest neighbor (kNN), since kNN benefits the generation of hubs and it is not appropriate for high-dimensionality data. Nevertheless, methods commonly used for generating regular graphs have high computational cost. We tackle this problem introducing an alternative method for generation of regular graphs with better runtime performance compared to methods usually find in the area. Our technique is based on the preferential selection of vertices according some topological measures, like closeness, generating at the end of the process a regular graph. Experiments using the global and local consistency method for label propagation show that our method provides better or equal classification rate in comparison with kNN.

Performing edge detection by Difference of Gaussians using q-Gaussian kernels

In image processing, edge detection is a valuable tool to perform the extraction of features from an image. This detection reduces the amount of information to be processed, since the redundant information (considered less relevant) can be disconsidered. The technique of edge detection consists of determining the points of a digital image whose intensity changes sharply. This changes are, for example, due to the discontinuities of the orientation on a surface. A well known method of edge detection is the Difference of Gaussians (DoG). The method consists of subtracting two Gaussians, where a kernel has a standard deviation smaller than the previous one. The convolution between the subtraction of kernels and the input image results in the edge detection of this image. This paper introduces a method of extracting edges using DoG with kernels based on the q-Gaussian probability distribution, derived from the q-statistic proposed by Constantino Tsallis. To demonstrate the methods potential, we compare the introduced method with the tradicional DoG using Gaussians kernels. The results showed that the proposed method can extract edges with more accurate details.

Informativity-based graph: Exploring mutual kNN and labeled vertices for semi-supervised learning

Data repositories are getting larger and in most of the cases, only a small subset of their data items is labeled. In such scenario semi-supervised learning (SSL) techniques have become very relevant. Among these algorithms, those based on graphs have gained prominence in the area. An important step in graph-based SSL methods is the conversion of tabular data into a weighted graph. However, most of the SSL literature focuses on developing label inference algorithms without studying graph construction methods and its effect on the base algorithm performance. This paper provides a novel technique for building graph by using mutual kNN and labeled vertices. The use of prior information, i.e., to consider the small fraction of labeled vertices, has been underexplored in SSL literature and mutual kNN has been only explored in clustering. The empirical evaluation of the proposed graph showed promising results in terms of accuracy, when it is applied to the label propagation task. Additionally, the resultant networks have lower average degree than kNN networks.

RGCLI: Robust Graph that Considers Labeled Instances for Semi-Supervised Learning

Abstract Graph-based semi-supervised learning (SSL) provides a powerful framework for the modeling of manifold structures in high-dimensional spaces. Additionally, graph representation is effective for the propagation of the few initial labels existing in training data. Graph-based SSL requires robust graphs as input for an accurate data mining task, such as classification. In contrast to most graph construction methods, which ignore the labeled instances available in SSL scenarios, a previous study proposed a graph-construction method, named GBILI, to exploit the informativeness conveyed by such instances available in a semi-supervised classification domain. Here, we have improved the method proposing an optimized algorithm referred to as Robust Graph that Considers Labeled Instances (RGCLI) for the generation of more robust graphs. The contributions of this paper are threefold: i) reduction of GBILI time complexity from quadratic to O ( nk log n ) . This enhancement allows addressing large datasets; ii) demonstration of RGCLI mathematical properties, proving the constructed graph is an optimal graph to model the smoothness assumption of SSL; and iii) evaluation of the efficacy of the proposed approach in a comprehensive semi-supervised classification scenario with several datasets, including an image segmentation task, which needs a large graph to represent the image. Such experiments show the use of labeled vertices in the graph construction process improves the graph topology, hence, the learning task in which it will be employed.

O problema de caminho mínimo com incertezas e restrições de tempo

The shortest path problem in graphs with uncertainties in the parameters is an important problem in the mathematical programming, since it has a wide range of applications in different areas of Computation and Engineering, such as: computer networks, telecommunications, transportation, manufacturing, etc. However, due to its high computational complexity, there are few algorithms in the literature. In this paper is proposed an algorithm, based on Okada and Soper algorithm, which uses two uncertainty parameters, cost and time, with time restrictions in the nodes. The uncertainties are discussed using the fuzzy set theory.

Identifying abnormal nodes in complex networks by using random walk measure

Identifying outlier nodes is an important task in complex network mining. In this paper, we analyze the problem of identifying outliers in a network structure and propose an outlier measure by using the random walk distance measure and the dissimilarity index between pairs of vertices. Our method determines a “view” to the whole network for each node and infers that outliers are those nodes whose views differ significantly from majority of the nodes. Usually, outlier is detected by applying a specific criteria, for example, the farthest ones from the central node. Consequently, only one type of outliers satisfying the predefined criteria can be determined. On the other hand, our method incorporates both local and global information of the network due to random walk feature and can give more general outlier detection results. We have applied the method to artificial and real networks and some interesting results have been obtained.