Associative classification is a pattern recognition approach that integrates classification and association rule discovery to build accurate classification models. These models are formed by a collection of contrast patterns that fulfill some restrictions. In this paper, we introduce an experimental comparison of the impact of using different restrictions in the classification accuracy. To the best of our knowledge, this is the first time that such analysis is performed, deriving some interesting findings about how restrictions impact on the classification results. Contrasting these results with previously published papers, we found that their conclusions could be unintentionally biased by the restrictions they used. We found, for example, that the jumping restriction could severely damage the pattern quality in the presence of dataset noise. We also found that the minimal support restriction has a different effect in the accuracy of two associative classifiers, therefore deciding which one is the best depends on the support value. This paper opens some interesting lines of research, mainly in the creation of new restrictions and new pattern types by joining different restrictions.

Speech emotion recognition has become the heart of most human computer interaction applications in the modern world. The growing need to develop emotionally intelligent devices has opened up a lot of research opportunities. Most researchers in this field have applied the use of handcrafted features and machine learning techniques in recognising speech emotion. However, these techniques require extra processing steps and handcrafted features are usually not robust. They are computationally intensive because the curse of dimensionality results in low discriminating power. Research has shown that deep learning algorithms are effective for extracting robust and salient features in dataset. In this study, we have developed a custom 2D-convolution neural network that performs both feature extraction and classification of vocal utterances. The neural network has been evaluated against deep multilayer perceptron neural network and deep radial basis function neural network using the Berlin database of emotional speech, Ryerson audio-visual emotional speech database and Surrey audio-visual expressed emotion corpus. The described deep learning algorithm achieves the highest precision, recall and F1-scores when compared to other existing algorithms. It is observed that there may be need to develop customized solutions for different language settings depending on the area of applications.

Nowadays, computers, as well as smart devices, are connected through communication networks making them more vulnerable to attacks. Honeypots are proposed as deception tools but usually used as part of a proactive defense strategy. Hence, this article demonstrates how honeypots data can be analyzed in an active defense strategy. Furthermore, anomaly detection based on unsupervised machine learning techniques allows to build autonomous systems and to detect unknown anomalies without the need for prior knowledge. However, the unsupervised techniques applied for honeypots data analysis do not value the advantages of these tools’ data, particularly the high probability that they include a large number of previously unseen anomalies with unexpected and diverse patterns. Therefore, in the present work, the aim is to improve the unsupervised anomaly detection in honeypots data by varying the data feature subset and the parameterization of the anomaly detection algorithm. To this purpose, an outlier ensemble with LOF (Local Outlier Factor) as a base algorithm is proposed. The ensemble outperforms existing solutions as depicted in the experiments where a detection rate higher than 92% is achieved.

Online Analytical Processing (OLAP) comprises tools and algorithms that allow querying multidimensional databases. It is based on the multidimensional model, where data can be seen as a cube such that each cell contains one or more measures that can be aggregated along dimensions. In a Big Data scenario, traditional data warehousing and OLAP operations are clearly not sufficient to address current data analysis requirements, for example, social network analysis. Furthermore, OLAP operations and models can expand the possibilities of graph analysis beyond the traditional graph-based computation. Nevertheless, there is not much work on the problem of taking OLAP analysis to the graph data model. This paper proposes a formal multidimensional model for graph analysis, that considers the basic graph data, and also background information in the form of dimension hierarchies. The graphs in this model are node- and edge-labelled directed multi-hypergraphs, called graphoids, which can be defined at several different levels of granularity using the dimensions associated with them. Operations analogous to the ones used in typical OLAP over cubes are defined over graphoids. The paper presents a formal definition of the graphoid model for OLAP, proves that the typical OLAP operations on cubes can be expressed over the graphoid model, and shows that the classic data cube model is a particular case of the graphoid data model. Finally, a case study supports the claim that, for many kinds of OLAP-like analysis on graphs, the graphoid model works better than the typical relational OLAP alternative, and for the classic OLAP queries, it remains competitive.

Comision Nacional de Investigacion Cientifica y Tecnologica (CONICYT) CONICYT FONDECYT 11180337 Comision Nacional de Investigacion Cientifica y Tecnologica (CONICYT) CONICYT FONDECYT 1160738 1181809 Comision Nacional de Investigacion Cientifica y Tecnologica (CONICYT) PIA/BASAL AFB180003

Because of high dimensionality, correlation among covariates, and noise contained in data, dimension reduction (DR) techniques are often employed to the application of machine learning algorithms. Principal Component Analysis (PCA), Linear Discriminant Analysis (LDA), and their kernel variants (KPCA, KLDA) are among the most popular DR methods. Recently, Supervised Kernel Principal Component Analysis (SKPCA) has been shown as another successful alternative. In this paper, brief reviews of these popular techniques are presented first. We then conduct a comparative performance study based on three simulated datasets, after which the performance of the techniques are evaluated through application to a pattern recognition problem in face image analysis. The gender classification problem is considered on MORPH-II and FG-NET, two popular longitudinal face aging databases. Several feature extraction methods are used, including biologically-inspired features (BIF), local binary patterns (LBP), histogram of oriented gradients (HOG), and the Active Appearance Model (AAM). After applications of DR methods, a linear support vector machine (SVM) is deployed with gender classification accuracy rates exceeding 95% on MORPH-II, competitive with benchmark results. A parallel computational approach is also proposed, attaining faster processing speeds and similar recognition rates on MORPH-II. Our computational approach can be applied to practical gender classification systems and generalized to other face analysis tasks, such as race classification and age prediction.

We propose a hybrid application of Population Based Ant Colony Optimization that uses a data mining procedure to wisely initialize the pheromone entries. Hybridization of metaheuristics with data mining techniques has been studied by several research

Distance Measuring between two mixed data objects is the basis of many learning algorithms. The complex relevance between heterogeneous – various types/scales – attributes has a significant influence on the measured results. In this paper, we propose an End-to-End Distance Measuring method for mixe d data based on deep relevance learning, called E2DM. Existing methods confuse the attributes space by mapping the discrete attribute values to new continuous values, or discretize continuous attributes values without considering the relevance. In contrast, E2DM directly manipulates on the original data with data conversion and relevance learning simultaneously to avoid information loss and attribute space confusion. E2DM firstly estimates internal relevance (i.e., relevance within the attribute) influenced distance by considering the categorical attribute value frequency and mapping numerical attribute values into multiple bins. Then it takes a wrapper approach to iteratively optimize relevance influenced distance and bin boundaries using a Frobenius-norm deviation as its objective function. Co-occurrence Mover’s Distance is proposed to explicitly explore relevance between attributes in each iteration. Finally, the distance for numerical attribute values is refined based on the original values and the fallen bin centers. Experimental results on a number of real-world datasets demonstrate that E2DM outperforms the state-of-the-art methods.

A family of algorithms for time series classification (TSC) involve running a sliding window across each series, discretising the window to form a word, forming a histogram of word counts over the dictionary, then constructing a classifier on the histograms. A recent evaluation of two of this type of algorithm, Bag of Patterns (BOP) and Bag of Symbolic Fourier Approximation Symbols (BOSS) found a significant difference in accuracy between these seemingly similar algorithms. We investigate this phenomenon by deconstructing the classifiers and measuring the relative importance of the four key components between BOP and BOSS. We find that whilst ensembling is a key component for both algorithms, the effect of the other components is mixed and more complex. We conclude that BOSS represents the state of the art for dictionary-based TSC. Both BOP and BOSS can be classed as bag of words approaches. These are particularly popular in Computer Vision for tasks such as image classification. We adapt three techniques used in Computer Vision for TSC: Scale Invariant Feature Transform; Spatial Pyramids; and Histogram Intersection. We find that using Spatial Pyramids in conjunction with BOSS (SP) produces a significantly more accurate classifier. SP is significantly more accurate than standard benchmarks and the original BOSS algorithm. It is not significantly worse than the best shapelet-based or deep learning approaches, and is only outperformed by an ensemble that includes BOSS as a constituent module.

To extract structured knowledge from unstructured text sources we need to understand the semantic relationships between entities. State-of-the-art relation extraction techniques take advantage of the abundance of data on the web. However, in domains with sparse data such as social networks which ha ve limited occurrences of entities and relationship patterns, bootstrapping techniques and pattern detection methods are inefficient and inaccurate. In this paper, we introduce REDS, a Relation Extraction approach based on Distant Supervision. REDS extracts the named entities from text documents and assigns a fingerprint to each potential relationship among the named entities. Then, it queries a knowledge repository for similar matches to each fingerprint. An assessor uses the query results and the data statistics to measure the validity of the relationships corresponding to the queried fingerprints, and labels each potential relationship with the predicted type. In addition to handling the relation extraction in presence of data sparsity, REDS uses an information retrieval framework that makes it scalable and capable of dealing with noisy data. We implement and test REDS on a non-English historical archive consisting of unstructured notarial acts and structured civil registers; By means of manual evaluations REDS achieves precision of 0.90.