An unsupervised approach to feature discretization and selection

Many learning problems require handling high dimensional datasets with a relatively small number of instances. Learning algorithms are thus confronted with the curse of dimensionality, and need to address it in order to be effective. Examples of these types of data include the bag-of-words representation in text classification problems and gene expression data for tumor detection/classification. Usually, among the high number of features characterizing the instances, many may be irrelevant (or even detrimental) for the learning tasks. It is thus clear that there is a need for adequate techniques for feature representation, reduction, and selection, to improve both the classification accuracy and the memory requirements. In this paper, we propose combined unsupervised feature discretization and feature selection techniques, suitable for medium and high-dimensional datasets. The experimental results on several standard datasets, with both sparse and dense features, show the efficiency of the proposed techniques as well as improvements over previous related techniques.

Efficient feature selection filters for high-dimensional data

Feature selection is a central problem in machine learning and pattern recognition. On large datasets (in terms of dimension and/or number of instances), using search-based or wrapper techniques can be cornputationally prohibitive. Moreover, many filter methods based on relevance/redundancy assessment also take a prohibitively long time on high-dimensional. datasets. In this paper, we propose efficient unsupervised and supervised feature selection/ranking filters for high-dimensional datasets. These methods use low-complexity relevance and redundancy criteria, applicable to supervised, semi-supervised, and unsupervised learning, being able to act as pre-processors for computationally intensive methods to focus their attention on smaller subsets of promising features. The experimental results, with up to 10(5) features, show the time efficiency of our methods, with lower generalization error than state-of-the-art techniques, while being dramatically simpler and faster.

Factorization by invariant embedding of elliptic problems: circular and star-shaped domains

Dissertação apresentada para obtenção do grau de Doutor em Matemática na especialidade de Equações Diferenciais, pela Universidade Nova de Lisboa,Faculdade de Ciências e Tecnologia

Robot visual localization through local feature fusion: an evaluation of multiple classifiers combination approaches

In the last decade, local image features have been widely used in robot visual localization. In order to assess image similarity, a strategy exploiting these features compares raw descriptors extracted from the current image with those in the models of places. This paper addresses the ensuing step in this process, where a combining function must be used to aggregate results and assign each place a score. Casting the problem in the multiple classifier systems framework, in this paper we compare several candidate combiners with respect to their performance in the visual localization task. For this evaluation, we selected the most popular methods in the class of non-trained combiners, namely the sum rule and product rule. A deeper insight into the potential of these combiners is provided through a discriminativity analysis involving the algebraic rules and two extensions of these methods: the threshold, as well as the weighted modifications. In addition, a voting method, previously used in robot visual localization, is assessed. Furthermore, we address the process of constructing a model of the environment by describing how the model granularity impacts upon performance. All combiners are tested on a visual localization task, carried out on a public dataset. It is experimentally demonstrated that the sum rule extensions globally achieve the best performance, confirming the general agreement on the robustness of this rule in other classification problems. The voting method, whilst competitive with the product rule in its standard form, is shown to be outperformed by its modified versions.

Feature Discretization with Relevance and Mutual Information Criteria

Feature discretization (FD) techniques often yield adequate and compact representations of the data, suitable for machine learning and pattern recognition problems. These representations usually decrease the training time, yielding higher classification accuracy while allowing for humans to better understand and visualize the data, as compared to the use of the original features. This paper proposes two new FD techniques. The first one is based on the well-known Linde-Buzo-Gray quantization algorithm, coupled with a relevance criterion, being able perform unsupervised, supervised, or semi-supervised discretization. The second technique works in supervised mode, being based on the maximization of the mutual information between each discrete feature and the class label. Our experimental results on standard benchmark datasets show that these techniques scale up to high-dimensional data, attaining in many cases better accuracy than existing unsupervised and supervised FD approaches, while using fewer discretization intervals.

Exploiting the bin-class histograms for feature selection on discrete data

In machine learning and pattern recognition tasks, the use of feature discretization techniques may have several advantages. The discretized features may hold enough information for the learning task at hand, while ignoring minor fluctuations that are irrelevant or harmful for that task. The discretized features have more compact representations that may yield both better accuracy and lower training time, as compared to the use of the original features. However, in many cases, mainly with medium and high-dimensional data, the large number of features usually implies that there is some redundancy among them. Thus, we may further apply feature selection (FS) techniques on the discrete data, keeping the most relevant features, while discarding the irrelevant and redundant ones. In this paper, we propose relevance and redundancy criteria for supervised feature selection techniques on discrete data. These criteria are applied to the bin-class histograms of the discrete features. The experimental results, on public benchmark data, show that the proposed criteria can achieve better accuracy than widely used relevance and redundancy criteria, such as mutual information and the Fisher ratio.

The web feature service: transaction standard: an example of prototype implementation

Trabalho de Projecto apresentado como requisito parcial para obtenção do grau de Mestre em Ciência e Sistemas de Informação Geográfica

XDense: A Dense Grid Sensor Network for Distributed Feature Extraction

XXXIII Simpósio Brasileiro de Redes de Computadores e Sistemas Distribuídos (SBRC 2015). 15 to 19, May, 2015, III Workshop de Comunicação em Sistemas Embarcados Críticos. Vitória, Brasil.

XDense: A Dense Grid Sensor Network for Distributed Feature Extraction

XXXIII Simpósio Brasileiro de Redes de Computadores e Sistemas Distribuídos (SBRC 2015), III Workshop de Comunicação em Sistemas Embarcados Críticos. Vitória, Brasil.

Feature Extraction in Densely Sensed Environments: Extensions to Multiple Broadcast Domains

The vision of the Internet of Things (IoT) includes large and dense deployment of interconnected smart sensing and monitoring devices. This vast deployment necessitates collection and processing of large volume of measurement data. However, collecting all the measured data from individual devices on such a scale may be impractical and time consuming. Moreover, processing these measurements requires complex algorithms to extract useful information. Thus, it becomes imperative to devise distributed information processing mechanisms that identify application-specific features in a timely manner and with a low overhead. In this article, we present a feature extraction mechanism for dense networks that takes advantage of dominance-based medium access control (MAC) protocols to (i) efficiently obtain global extrema of the sensed quantities, (ii) extract local extrema, and (iii) detect the boundaries of events, by using simple transforms that nodes employ on their local data. We extend our results for a large dense network with multiple broadcast domains (MBD). We discuss and compare two approaches for addressing the challenges with MBD and we show through extensive evaluations that our proposed distributed MBD approach is fast and efficient at retrieving the most valuable measurements, independent of the number sensor nodes in the network.

The impact of questions rotation in response accuracy

Dissertação apresentada como requisito parcial para obtenção do grau de Mestre em Estatística e Gestão de Informação

Factorization of elliptic boundary value problems by invariant embedding and application to overdetermined problems

Dissertação para obtenção do Grau de Doutor em Matemática

A model to simulate the moment-rotation and crack width of FRC members reinforced with longitudinal bars

The present work describes a model for the determination of the moment–rotation relationship of a cross section of fiber reinforced concrete (FRC) elements that also include longitudinal bars for the flexural reinforcement (R/FRC). Since a stress–crack width relationship (σ–w)(σ–w) is used to model the post-cracking behavior of a FRC, the σ–w directly obtained from tensile tests, or derived from inverse analysis applied to the results obtained in three-point notched beam bending tests, can be adopted in this approach. For a more realistic assessment of the crack opening, a bond stress versus slip relationship is assumed to simulate the bond between longitudinal bars and surrounding FRC. To simulate the compression behavior of the FRC, a shear friction model is adopted based on the physical interpretation of the post-peak compression softening behavior registered in experimental tests. By allowing the formation of a compressive FRC wedge delimited by shear band zones, the concept of concrete crushing failure mode in beams failing in bending is reinterpreted. By using the moment–rotation relationship, an algorithm was developed to determine the force–deflection response of statically determinate R/FRC elements. The model is described in detail and its good predictive performance is demonstrated by using available experimental data. Parametric studies were executed to evidence the influence of relevant parameters of the model on the serviceability and ultimate design conditions of R/FRC elements failing in bending.

Peripheral refraction with eye and head rotation with contact lenses

Purpose: To evaluate the impact of eye and head rotation in the measurement of peripheral refraction with an open-field autorefractometer in myopic eyes wearing two different center-distance designs of multifocal contact lenses (MFCLs). Methods: Nineteen right eyes from 19 myopic patients (average central M ± SD = −2.67 ± 1.66 D) aged 20–27 years (mean ± SD = 23.2 ± 3.3 years) were evaluated using a Grand-Seiko autorefractometer. Patients were fitted with one multifocal aspheric center-distance contact lens (Biofinity Multifocal D®) and with one multi-concentric MFCL (Acuvue Oasys for Presbyopia). Axial and peripheral refraction were evaluated by eye rotation and by head rotation under naked eye condition and with each MFCL fitted randomly and in independent sessions. Results: For the naked eye, refractive pattern (M, J0 and J45) across the central 60◦ of the horizontal visual field values did not show significant changes measured by rotating the eye or rotating the head (p > 0.05). Similar results were obtained wearing the Biofinity D, for both testing methods, no obtaining significant differences to M, J0 and J45 values (p > 0.05). For Acuvue Oasys for presbyopia, also no differences were found when comparing measurements obtained by eye and head rotation (p > 0.05). Multivariate analysis did not showed a significant interaction between testing method and lens type neither with measuring locations (MANOVA, p > 0.05). There were significant differences in M and J0 values between naked eyes and each MFCL. Conclusion: Measurements of peripheral refraction by rotating the eye or rotating the head in myopic patients wearing dominant design or multi-concentric multifocal silicone hydrogel contact lens are comparable.

Epigastric pain: incarceration or rotation?

Introduction: Acute intrathoracic gastric volvulus occurs when the stomach has a twist mesenteroaxial/organoaxial or chest cavity resulting in a dilatation or rupture of the diaphragmatic hiatus or diaphragmatic hernia. The purpose of this work is to show a interesting case of gastric volvulus in a patient with several comorbidities. Case Report: A 77-year-old female with past history of hiatal hernia and mental disease associated with diabetes and atrial fibrillation. Patient went to the emergency department due to vomiting associated with blood. Analytical parameters (WBC, HGB, PCR, metabolic panel and liver function), showed no significant alterations. Thoracic X-ray revealed an enlarged mediastinum due to herniation of the stomach. A computed tomography (CT) scan confirmed intrathoracic localization of the gastric antrum with twist. Patient’s symptoms were relieved by nasogastric intubation and analgesia. After six months, the patient is still asymptomatic. Conclusion: In general, the treatment of an acute gastric volvulus requires an emergent surgical repair. In patients who are not surgical candidates (with comorbidities or an inability to tolerate anesthesia), endoscopic reduction should be attempted. Chronic gastric volvulus may be treated non-emergently, and surgical treatment is increasingly being performed using a laparoscopic approach. In this case, it is a chronic form that was solved with the placement of the nasogastric tube. A nasogastric decompression is an option in the chronic form of hiatal hernia associated to gastric volvulus in patients with serious comorbidities.