An Interval-based Multiobjective Approach to Feature Subset Selection Using Joint Modeling of Objectives and Variables

This paper studies feature subset selection in classification using a multiobjective estimation of distribution algorithm. We consider six functions, namely area under ROC curve, sensitivity, specificity, precision, F1 measure and Brier score, for evaluation of feature subsets and as the objectives of the problem. One of the characteristics of these objective functions is the existence of noise in their values that should be appropriately handled during optimization. Our proposed algorithm consists of two major techniques which are specially designed for the feature subset selection problem. The first one is a solution ranking method based on interval values to handle the noise in the objectives of this problem. The second one is a model estimation method for learning a joint probabilistic model of objectives and variables which is used to generate new solutions and advance through the search space. To simplify model estimation, l1 regularized regression is used to select a subset of problem variables before model learning. The proposed algorithm is compared with a well-known ranking method for interval-valued objectives and a standard multiobjective genetic algorithm. Particularly, the effects of the two new techniques are experimentally investigated. The experimental results show that the proposed algorithm is able to obtain comparable or better performance on the tested datasets.

Analysing written production competence descriptors for academic and professional purposes and their calibration to the CEFR

The Common European Framework of Reference for Languages (CEFR) "describes in a comprehensive way what language learners have to learn to do in order to use a language for communication and what knowledge and skills they have to develop so as to be able to act effectively" (Council of Europe, 2001: 1). This paper reports on the findings of two studies whose purpose was to assess written production competence descriptors meant for their inclusion into the Academic and Professional English Language Portfolio KELP) for students of engineering and architecture. The main objective of these studies was to establish whether the language competence descriptors were a satisfactory valid tool in their language programmes from the point of view of clarity, relevance and reliability, as perceived by the students and fellow English for Academic Purposes (RAP) / English for Science and Technology (EST) instructors. The studies shed light on how to improve unsatisfactory descriptors. Results show that the final descriptor lists were on the whole well calibrated and fairly well written: the great majority was considered valid for both teachers and students involved.

Time-Frequency based Feature Selection for Discrimination of non stationary Biosignals.

This research proposes a generic methodology for dimensionality reduction upon time-frequency representations applied to the classification of different types of biosignals. The methodology directly deals with the highly redundant and irrelevant data contained in these representations, combining a first stage of irrelevant data removal by variable selection, with a second stage of redundancy reduction using methods based on linear transformations. The study addresses two techniques that provided a similar performance: the first one is based on the selection of a set of the most relevant time?frequency points, whereas the second one selects the most relevant frequency bands. The first methodology needs a lower quantity of components, leading to a lower feature space; but the second improves the capture of the time-varying dynamics of the signal, and therefore provides a more stable performance. In order to evaluate the generalization capabilities of the methodology proposed it has been applied to two types of biosignals with different kinds of non-stationary behaviors: electroencephalographic and phonocardiographic biosignals. Even when these two databases contain samples with different degrees of complexity and a wide variety of characterizing patterns, the results demonstrate a good accuracy for the detection of pathologies, over 98%.The results open the possibility to extrapolate the methodology to the study of other biosignals.

A new feature extraction method for signal classification applied to cat spinal cord signals

In the spinal cord of the anesthetized cat, spontaneous cord dorsum potentials (CDPs) appear synchronously along the lumbo-sacral segments. These CDPs have different shapes and magnitudes. Previous work has indicated that some CDPs appear to be specially associated with the activation of spinal pathways that lead to primary afferent depolarization and presynaptic inhibition. Visual detection and classification of these CDPs provides relevant information on the functional organization of the neural networks involved in the control of sensory information and allows the characterization of the changes produced by acute nerve and spinal lesions. We now present a novel feature extraction approach for signal classification, applied to CDP detection. The method is based on an intuitive procedure. We first remove by convolution the noise from the CDPs recorded in each given spinal segment. Then, we assign a coefficient for each main local maximum of the signal using its amplitude and distance to the most important maximum of the signal. These coefficients will be the input for the subsequent classification algorithm. In particular, we employ gradient boosting classification trees. This combination of approaches allows a faster and more accurate discrimination of CDPs than is obtained by other methods.

Feature selection in the reconstruction of complex network representations of spectral data

Complex networks have been extensively used in the last decade to characterize and analyze complex systems, and they have been recently proposed as a novel instrument for the analysis of spectra extracted from biological samples. Yet, the high number of measurements composing spectra, and the consequent high computational cost, make a direct network analysis unfeasible. We here present a comparative analysis of three customary feature selection algorithms, including the binning of spectral data and the use of information theory metrics. Such algorithms are compared by assessing the score obtained in a classification task, where healthy subjects and people suffering from different types of cancers should be discriminated. Results indicate that a feature selection strategy based on Mutual Information outperforms the more classical data binning, while allowing a reduction of the dimensionality of the data set in two orders of magnitude

Mining recurring concepts in a dynamic feature space

Most data stream classification techniques assume that the underlying feature space is static. However, in real-world applications the set of features and their relevance to the target concept may change over time. In addition, when the underlying concepts reappear, reusing previously learnt models can enhance the learning process in terms of accuracy and processing time at the expense of manageable memory consumption. In this paper, we propose mining recurring concepts in a dynamic feature space (MReC-DFS), a data stream classification system to address the challenges of learning recurring concepts in a dynamic feature space while simultaneously reducing the memory cost associated with storing past models. MReC-DFS is able to detect and adapt to concept changes using the performance of the learning process and contextual information. To handle recurring concepts, stored models are combined in a dynamically weighted ensemble. Incremental feature selection is performed to reduce the combined feature space. This contribution allows MReC-DFS to store only the features most relevant to the learnt concepts, which in turn increases the memory efficiency of the technique. In addition, an incremental feature selection method is proposed that dynamically determines the threshold between relevant and irrelevant features. Experimental results demonstrating the high accuracy of MReC-DFS compared with state-of-the-art techniques on a variety of real datasets are presented. The results also show the superior memory efficiency of MReC-DFS.

La evolución del paisaje fluvial en la confluencia de los ríos Tajo y Jarama

La tesis doctoral que se presenta realiza un análisis de la evolución del paisaje fluvial de las riberas de los ríos Tajo y Jarama en el entorno de Aranjuez desde una perspectiva múltiple. Contempla y conjuga aspectos naturales, tales como los hidrológicos, geomorfológicos y ecológicos; también culturales, como la regulación hidrológica y la gestión del agua, las intervenciones en cauce y márgenes, la evolución de la propiedad y los cambios de usos del suelo, fundamentalmente. Este análisis ha permitido identificar el sistema de factores, dinámico y complejo, que ha creado este paisaje, así como las interrelaciones, conexiones, condicionantes y dependencias de los descriptores paisajísticos considerados. Por ejemplo, se han estudiado las relaciones cruzadas observadas entre dinámica fluvial-propiedad de la tierra-estado de conservación, cuestiones que hasta la fecha no habían sido tratadas, evaluadas o cuantificadas en otros trabajos dedicados a esta zona. La investigación se ha organizado en tres fases fundamentales que han dado lugar a los capítulos centrales del documento (capítulos 2, 3 y 4). En primer lugar, se ha realizado una caracterización de los factores, naturales y culturales, que organizan el paisaje de este territorio eminentemente fluvial (geomorfología, factores climáticos e hidrológicos, vegetación, propiedad de la tierra y elementos culturales de significación paisajística). A continuación, se ha realizado el estudio de la evolución del paisaje fluvial mediante el análisis de diversos elementos, previamente identificados y caracterizados. Para ello se han procesado imágenes aéreas correspondientes a cinco series temporales así como varios planos antiguos, obteniendo una amplia base de datos que se ha analizado estadísticamente. Finalmente, se han contrastado los resultados parciales obtenidos en los capítulos anteriores, lo que ha permitido identificar relaciones causales entre los factores que organizan el paisaje y la evolución de los elementos que lo constituyen. También, interconexiones entre factores o entre elementos. Este método de trabajo ha resultado muy útil para la comprensión del funcionamiento y evolución de un sistema complejo, como el paisaje de la vega de Aranjuez, un territorio con profundas y antiguas intervenciones culturales donde lo natural, en cualquier caso, siempre subyace. Es posible que la principal aportación de este trabajo, también su diferencia más destacada respecto a otros estudios de paisaje, haya sido mostrar una visión completa y exhaustiva de todos los factores que han intervenido en la conformación y evolución del paisaje fluvial, destacando las relaciones que se establecen entre ellos. Esta manera de proceder puede tener una interesante faceta aplicada, de tal manera que resulta un instrumento muy útil para el diseño de planes de gestión de este territorio fluvial. No en vano, una parte sustancial de la vega del Tajo-Jarama en Aranjuez es un Lugar de Importancia Comunitaria (LIC) y su posterior e ineludible declaración como Zona de Especial Conservación (ZEC) de la Red Natura 2000, de acuerdo con lo establecido en la Directiva 92/43/CE, exige la elaboración de un Plan de Gestión que, en gran medida, podría nutrirse de lo presentado, analizado e interpretado en este trabajo. En este sentido, conviene señalar la conciencia ya asumida de considerar, por su carácter integrador de la realidad territorial, el paisaje como elemento clave para la gestión adecuada de la naturaleza y el territorio. Por otra parte, se considera que los resultados de esta Tesis Doctoral permitirían plantear medidas para la puesta en valor de un paisaje sobresaliente, cuyos límites sobrepasan con creces los que en la actualidad conforman el Paisaje Cultural declarado por la UNESCO. En suma, el análisis de este espacio fluvial realizado con la profundidad y amplitud que permite el método de trabajo seguido puede utilizarse para el diseño de estrategias que dirijan la evolución de este territorio en una línea que garantice su conservación global en términos paisajísticos, patrimoniales y ecológicos, permitiendo además, de este modo, su uso equilibrado como recurso económico, cultural o educativo. This doctoral thesis shows an analysis of fluvial landscape evolution from multiple perspectives on the banks of Tagus and Jarama rivers, around Aranjuez. The thesis contemplates and combines natural features, such as hydrological, geomorphological and ecological features, as well as cultural features, like hydrological regulation and water management, interventions in channels and margins, changes in ownership and land use changes, mainly. This analysis has allowed to identify the factors system, dynamic and complex, that this landscape has created, as well as the interrelationships, connections, constraints and dependencies among considered landscape descriptors. For example, we have studied the relationships observed among fluvial dynamics- land ownership -conservation status, issues not addressed, assessed or quantified up to now in other works about this area. The research is organized into three major phases that led to the paper's central chapters (Chapters 2, 3 and 4). First, there has been a characterization of the factors, both natural and cultural, that organize the landscape of this predominantly fluvial area (geomorphology, climate and hydrological factors, vegetation, land and cultural elements of landscape significance). Then, it was made to study of fluvial landscape evolution by analyzing various elements previously identified and characterized. Aerial images were processed for five series and several old maps, obtaining an extensive database, that has been analyzed statistically. Finally, we have contrasted the partial results obtained in the previous chapters, making it possible to identify causal relationships between the factors that organize the landscape and the evolution of the elements that constitute it. This working method has been very useful for understanding the operation and evolution of a complex system, as the landscape of the Vega de Aranjuez, a territory with deep and ancient cultural interventions where anyway, nature feature always lies. It is possible that the main contribution of this work, also its most prominent difference compared with other studies of landscape, has been to show a complete and exhaustive view of all factors involved in the formation and evolution of the fluvial landscape, highlighting the relationships established among them. This approach could have an interesting applied facet, so that is a very useful tool for designing management plans on this river territory. Not surprisingly, a substantial part of the valley of the Tagus-Jarama in Aranjuez is a Site of Community Importance (SCI) and their subsequent and inevitable declaration as Special Area of Conservation (SAC) of the Natura 2000 network, in accordance with the provisions Directive 92/43/EC, requires the development of a management plan that largely could draw on what was presented, analyzed and interpreted in this paper. In this regard, it should be noted conscience and assumed to consider, on the inclusiveness of territorial reality, the landscape as a key element for the proper management of nature and territory. On the other hand, it is considered that the results of this thesis allow to propose measures for enhancement of outstanding scenery, which go well beyond the boundaries that currently the Cultural Landscape declared by UNESCO. In sum, the analysis of this river area made with the depth and breadth that enables working method can be used to design strategies that address the evolution of this territory in a line that guarantees global conservation landscape terms, heritage and ecological, also, allowing its use as a balancing economic, cultural or educational resource.

Automatic blood glucose classification for gestational diabetes with feature selection: decision trees vs neural networks

Automatic blood glucose classification may help specialists to provide a better interpretation of blood glucose data, downloaded directly from patients glucose meter and will contribute in the development of decision support systems for gestational diabetes. This paper presents an automatic blood glucose classifier for gestational diabetes that compares 6 different feature selection methods for two machine learning algorithms: neural networks and decision trees. Three searching algorithms, Greedy, Best First and Genetic, were combined with two different evaluators, CSF and Wrapper, for the feature selection. The study has been made with 6080 blood glucose measurements from 25 patients. Decision trees with a feature set selected with the Wrapper evaluator and the Best first search algorithm obtained the best accuracy: 95.92%.

Brain structures identification based on feature descriptor

Traumatic Brain Injury -TBI- -1- is defined as an acute event that causes certain damage to areas of the brain. TBI may result in a significant impairment of an individuals physical, cognitive and psychosocial functioning. The main consequence of TBI is a dramatic change in the individuals daily life involving a profound disruption of the family, a loss of future income capacity and an increase of lifetime cost. One of the main challenges of TBI Neuroimaging is to develop robust automated image analysis methods to detect signatures of TBI, such as: hyper-intensity areas, changes in image contrast and in brain shape. The final goal of this research is to develop a method to identify the altered brain structures by automatically detecting landmarks on the image where signal changes and to provide comprehensive information to the clinician about them. These landmarks identify injured structures by co-registering the patient?s image with an atlas where landmarks have been previously detected. The research work has been initiated by identifying brain structures on healthy subjects to validate the proposed method. Later, this method will be used to identify modified structures on TBI imaging studies.

Multi-Camera very wide baseline feature matching based on view-adaptive junction detection

This paper presents a strategy for solving the feature matching problem in calibrated very wide-baseline camera settings. In this kind of settings, perspective distortion, depth discontinuities and occlusion represent enormous challenges. The proposed strategy addresses them by using geometrical information, specifically by exploiting epipolar-constraints. As a result it provides a sparse number of reliable feature points for which 3D position is accurately recovered. Special features known as junctions are used for robust matching. In particular, a strategy for refinement of junction end-point matching is proposed which enhances usual junction-based approaches. This allows to compute cross-correlation between perfectly aligned plane patches in both images, thus yielding better matching results. Evaluation of experimental results proves the effectiveness of the proposed algorithm in very wide-baseline environments.

Fast human pose estimation using 3D Zernike descriptors

Markerless video-based human pose estimation algorithms face a high-dimensional problem that is frequently broken down into several lower-dimensional ones by estimating the pose of each limb separately. However, in order to do so they need to reliably locate the torso, for which they typically rely on time coherence and tracking algorithms. Their losing track usually results in catastrophic failure of the process, requiring human intervention and thus precluding their usage in real-time applications. We propose a very fast rough pose estimation scheme based on global shape descriptors built on 3D Zernike moments. Using an articulated model that we configure in many poses, a large database of descriptor/pose pairs can be computed off-line. Thus, the only steps that must be done on-line are the extraction of the descriptors for each input volume and a search against the database to get the most likely poses. While the result of such process is not a fine pose estimation, it can be useful to help more sophisticated algorithms to regain track or make more educated guesses when creating new particles in particle-filter-based tracking schemes. We have achieved a performance of about ten fps on a single computer using a database of about one million entries.

Signal analysis and feature generation for pattern identification of partial discharges in high-voltage equipment

This paper proposes a method for the identification of different partial discharges (PDs) sources through the analysis of a collection of PD signals acquired with a PD measurement system. This method, robust and sensitive enough to cope with noisy data and external interferences, combines the characterization of each signal from the collection, with a clustering procedure, the CLARA algorithm. Several features are proposed for the characterization of the signals, being the wavelet variances, the frequency estimated with the Prony method, and the energy, the most relevant for the performance of the clustering procedure. The result of the unsupervised classification is a set of clusters each containing those signals which are more similar to each other than to those in other clusters. The analysis of the classification results permits both the identification of different PD sources and the discrimination between original PD signals, reflections, noise and external interferences. The methods and graphical tools detailed in this paper have been coded and published as a contributed package of the R environment under a GNU/GPL license.

Speech Signals Feature Extraction Model for a Speaker’s Gender and Age Identification System

Durante el proceso de producción de voz, los factores anatómicos, fisiológicos o psicosociales del individuo modifican los órganos resonadores, imprimiendo en la voz características particulares. Los sistemas ASR tratan de encontrar los matices característicos de una voz y asociarlos a un individuo o grupo. La edad y sexo de un hablante son factores intrínsecos que están presentes en la voz. Este trabajo intenta diferenciar esas características, aislarlas y usarlas para detectar el género y la edad de un hablante. Para dicho fin, se ha realizado el estudio y análisis de las características basadas en el pulso glótico y el tracto vocal, evitando usar técnicas clásicas (como pitch y sus derivados) debido a las restricciones propias de dichas técnicas. Los resultados finales de nuestro estudio alcanzan casi un 100% en reconocimiento de género mientras en la tarea de reconocimiento de edad el reconocimiento se encuentra alrededor del 80%. Parece ser que la voz queda afectada por el género del hablante y las hormonas, aunque no se aprecie en la audición. ABSTRACT Particular elements of the voice are printed during the speech production process and are related to anatomical and physiological factors of the phonatory system or psychosocial factors acquired by the speaker. ASR systems attempt to find those peculiar nuances of a voice and associate them to an individual or a group. Age and gender are inherent factors to the speaker which may be represented in voice. This work attempts to differentiate those characteristics, isolate them and use them to detect speaker’s gender and age. Features based on glottal pulse and vocal tract are studied and analyzed in order to achieve good results in both tasks. Classical methodologies (such as pitch and derivates) are avoided since the requirements of those techniques may be too restrictive. The final scores achieve almost 100% in gender recognition whereas in age recognition those scores are around 80%. Factors related to the gender and hormones seem to affect the voice although they are not audible.

Lagrangian descriptors: a method for revealing phase space structures of general time dependent dynamical systems

Lagrangian descriptors are a recent technique which reveals geometrical structures in phase space and which are valid for aperiodically time dependent dynamical systems. We discuss a general methodology for constructing them and we discuss a "heuristic argument" that explains why this method is successful. We support this argument by explicit calculations on a benchmark problem. Several other benchmark examples are considered that allow us to assess the performance of Lagrangian descriptors with both finite time Lyapunov exponents (FTLEs) and finite time averages of certain components of the vector field ("time averages"). In all cases Lagrangian descriptors are shown to be both more accurate and computationally efficient than these methods.

A survey of feature selection in Internet traffic characterization

In the last decade, the research community has focused on new classification methods that rely on statistical characteristics of Internet traffic, instead of pre-viously popular port-number-based or payload-based methods, which are under even bigger constrictions. Some research works based on statistical characteristics generated large fea-ture sets of Internet traffic; however, nowadays it?s impossible to handle hun-dreds of features in big data scenarios, only leading to unacceptable processing time and misleading classification results due to redundant and correlative data. As a consequence, a feature selection procedure is essential in the process of Internet traffic characterization. In this paper a survey of feature selection methods is presented: feature selection frameworks are introduced, and differ-ent categories of methods are briefly explained and compared; several proposals on feature selection in Internet traffic characterization are shown; finally, future application of feature selection to a concrete project is proposed.