Optimización de la predicción de problemas financieros en empresas sanitarias privadas españolas aplicando algoritmos genéticos / Optimization of the prediction of financial problems in Spanish private health companies using genetic algorithms

Objetivo: Presentar una metodología para optimizar, a través de la Z'-Score de Altman para empresas privadas, la predicción de entrada en situación de concurso de acreedores (bancarrota) en empresas privadas del sector sanitario español. Método: El método propuesto consiste en la aplicación de los algoritmos genéticos (AG) para encontrar los coeficientes de la fórmula de la cadena de ratios propuestos por Altman en su versión para empresas privadas que optimicen la predicción en empresas privadas sanitarias españolas, maximizando la sensibilidad y la especificidad, y con ello reduciendo los errores de tipo I y tipo II. Con este propósito se ha utilizado una muestra de 5903 empresas del sector sanitario privado español obtenidas de las bases de datos de Sistema de Análisis de Balances Ibéricos (SABI) entre los años 2007 y 2015. Resultados: El modelo predictivo obtenido con los AG presenta mayor exactitud, sensibilidad y especificidad que el propuesto por Altman para empresas privadas, tanto con los datos de test como con todos los datos de la muestra. Conclusiones: El hallazgo más importante del presente estudio es establecer una metodología que logra identificar unos coeficientes optimizados para la Z de Altman, lo cual permite realizar una predicción más precisa de la bancarrota en las empresas sanitarias privadas españolas

Objective: This paper presents a methodology to optimize, using Altman's Z-Score for private companies, the prediction of private companies of the Spanish health sector entering a situation of bankruptcy. Method: The proposed method consists of the application of genetic algorithms (GA) to find the coefficients of the formula of the chain of ratios proposed by Altman in the version of the score for private companies which optimize the prediction for Spanish private health companies, maximizing sensitivity and specificity, and thereby reducing type I and type II errors. For this purpose, a sample of 5,903 companies from the Spanish private health sector obtained from the database of the Iberian Balance Analysis System (SABI) between 2007 and 2015 was used. Results: The results show that the predictive model obtained with the AG presents greater accuracy, sensitivity and specificity than that proposed by Altman for private companies with both test data and all sample data. Conclusions: The most important finding of this study was to establish a methodology that can identify the optimized coefficients for the Altman Z-Score, which allows a more accurate prediction of bankruptcy in Spanish private healthcare companies

[Optimization of the prediction of financial problems in Spanish private health companies using genetic algorithms]. / Optimización de la predicción de problemas financieros en empresas sanitarias privadas españolas aplicando algoritmos genéticos.

OBJECTIVE: This paper presents a methodology to optimize, using Altman's Z-Score for private companies, the prediction of private companies of the Spanish health sector entering a situation of bankruptcy. METHOD: The proposed method consists of the application of genetic algorithms (GA) to find the coefficients of the formula of the chain of ratios proposed by Altman in the version of the score for private companies which optimize the prediction for Spanish private health companies, maximizing sensitivity and specificity, and thereby reducing type I and type II errors. For this purpose, a sample of 5,903 companies from the Spanish private health sector obtained from the database of the Iberian Balance Analysis System (SABI) between 2007 and 2015 was used. RESULTS: The results show that the predictive model obtained with the AG presents greater accuracy, sensitivity and specificity than that proposed by Altman for private companies with both test data and all sample data. CONCLUSIONS: The most important finding of this study was to establish a methodology that can identify the optimized coefficients for the Altman Z-Score, which allows a more accurate prediction of bankruptcy in Spanish private healthcare companies.

Evidence of a Task-Independent Neural Signature in the Spectral Shape of the Electroencephalogram.

Genetic and neurophysiological studies of electroencephalogram (EEG) have shown that an individual's brain activity during a given cognitive task is, to some extent, determined by their genes. In fact, the field of biometrics has successfully used this property to build systems capable of identifying users from their neural activity. These studies have always been carried out in isolated conditions, such as relaxing with eyes closed, identifying visual targets or solving mathematical operations. Here we show for the first time that the neural signature extracted from the spectral shape of the EEG is to a large extent independent of the recorded cognitive task and experimental condition. In addition, we propose to use this task-independent neural signature for more precise biometric identity verification. We present two systems: one based on real cepstrums and one based on linear predictive coefficients. We obtained verification accuracies above 89% on 4 of the 6 databases used. We anticipate this finding will create a new set of experimental possibilities within many brain research fields, such as the study of neuroplasticity, neurodegenerative diseases and brain machine interfaces, as well as the mentioned genetic, neurophysiological and biometric studies. Furthermore, the proposed biometric approach represents an important advance towards real world deployments of this new technology.

EEG biometric identification: a thorough exploration of the time-frequency domain.

OBJECTIVE: Although interest in using electroencephalogram (EEG) activity for subject identification has grown in recent years, the state of the art still lacks a comprehensive exploration of the discriminant information within it. This work aims to fill this gap, and in particular, it focuses on the time-frequency representation of the EEG. APPROACH: We executed qualitative and quantitative analyses of six publicly available data sets following a sequential experimentation approach. This approach was divided in three blocks analysing the configuration of the power spectrum density, the representation of the data and the properties of the discriminant information. A total of ten experiments were applied. MAIN RESULTS: Results show that EEG information below 40 Hz is unique enough to discriminate across subjects (a maximum of 100 subjects were evaluated here), regardless of the recorded cognitive task or the sensor location. Moreover, the discriminative power of rhythms follows a W-like shape between 1 and 40 Hz, with the central peak located at the posterior rhythm (around 10 Hz). This information is maximized with segments of around 2 s, and it proved to be moderately constant across montages and time. SIGNIFICANCE: Therefore, we characterize how EEG activity differs across individuals and detail the optimal conditions to detect subject-specific information. This work helps to clarify the results of previous studies and to solve some unanswered questions. Ultimately, it will serve as guide for the design of future biometric systems.

Herramienta para la evaluación acústica de la voz en entornos hospitalarios: EVALUA / A tool for the acoustic assessment of the voice in clinical environments: EVALUA

En el ámbito de la evaluación acústica del sistema fonador, las diferentes herramientas conocidas no están exentas de la necesidad de interpretar sus resultados y de un conocimiento amplio de las características de la señal de voz en los diferentes dominios de representación. En este trabajo se presenta una simple y robusta herramienta de software que tiene como objetivo documentar la calidad de voz a partir de una grabación de una vocal sostenida, cuantificando objetivamente y de forma automática 4 fenómenos físicos que permiten realizar una medición de la calidad de la voz. Estos 4 fenómenos físicos se han denominado: estabilidad de la voz, riqueza espectral, presencia de ruido e irregularidades en las masas. Se ha desarrollado un software que de manera automática identifica las variaciones de la normalidad de los 4 fenómenos físicos y, por tanto, permite diferenciar de forma objetiva las voces normales de las patológicas. Para el análisis de las prestaciones del sistema que se presenta se han evaluado 86 locutores de control y 155 locutores con patologías laríngeas variadas con diferentes grados de disfonía. En el estudio realizado se ha obtenido una sensibilidad del 89% y una especificidad de 89,5% en la discriminación entre voces normales y patológicas. Con el estudio clínico realizado hemos demostrado que la herramienta es clínicamente relevante en la evaluación y documentación de pacientes con trastornos de la voz (AU)

In the field of acoustic evaluation of the phonatory system, the distinct available tools are not exempt from the need to interpret their results and for extensive knowledge of the characteristics of the speech signal in the different domains of representation. This article presents a simple and robust software tool that aims to document voice quality from a recording of a sustained vowel. This tool measures four physical phenomena that define voice quality objectively and automatically. These four physical phenomena are referred to as: voice stability, spectral richness, the presence of noise, and mass irregularities. We have developed a software tool that automatically identifies variations in the four physical phenomena with respect to their normal ranges, and therefore allows normal voice to be differentiated from pathological voices. To analyze the performance of this system, we evaluated 86 speakers in a control group and 155 speakers with various laryngeal disorders and distinct degrees of dysphonia. A sensitivity of 89% and a specificity of 89.5% were obtained in discriminating between normal and pathological voices. This clinical study shows that the tool is clinically relevant in the assessment and documentation of patients with voice disorders (AU)

Application of the Teager-Kaiser energy operator in bearing fault diagnosis.

Condition monitoring of rotating machines is important in the prevention of failures. As most machine malfunctions are related to bearing failures, several bearing diagnosis techniques have been developed. Some of them feature the bearing vibration signal with statistical measures and others extract the bearing fault characteristic frequency from the AM component of the vibration signal. In this paper, we propose to transform the vibration signal to the Teager-Kaiser domain and feature it with statistical and energy-based measures. A bearing database with normal and faulty bearings is used. The diagnosis is performed with two classifiers: a neural network classifier and a LS-SVM classifier. Experiments show that the Teager domain features outperform those based on the temporal or AM signal.

Transformation of hand-shape features for a biometric identification approach.

The present work presents a biometric identification system for hand shape identification. The different contours have been coded based on angular descriptions forming a Markov chain descriptor. Discrete Hidden Markov Models (DHMM), each representing a target identification class, have been trained with such chains. Features have been calculated from a kernel based on the HMM parameter descriptors. Finally, supervised Support Vector Machines were used to classify parameters from the DHMM kernel. First, the system was modelled using 60 users to tune the DHMM and DHMM_kernel+SVM configuration parameters and finally, the system was checked with the whole database (GPDS database, 144 users with 10 samples per class). Our experiments have obtained similar results in both cases, demonstrating a scalable, stable and robust system. Our experiments have achieved an upper success rate of 99.87% for the GPDS database using three hand samples per class in training mode, and seven hand samples in test mode. Secondly, the authors have verified their algorithms using another independent and public database (the UST database). Our approach has reached 100% and 99.92% success for right and left hand, respectively; showing the robustness and independence of our algorithms. This success was found using as features the transformation of 100 points hand shape with our DHMM kernel, and as classifier Support Vector Machines with linear separating functions, with similar success.

Offline geometric parameters for automatic signature verification using fixed-point arithmetic.

This paper presents a set of geometric signature features for offline automatic signature verification based on the description of the signature envelope and the interior stroke distribution in polar and Cartesian coordinates. The features have been calculated using 16 bits fixed-point arithmetic and tested with different classifiers, such as hidden Markov models, support vector machines, and Euclidean distance classifier. The experiments have shown promising results in the task of discriminating random and simple forgeries.