Search

In low-power hardware implementations for classification algorithms, it is often essential to use physical resources efficiently. In this sense, the use of modulo-M integer operations instead of floating-point arithmetic, can lead to better performance, especially when M represents the dynamic range of an arithmetic block of the Residue Number System (RNS) [1,2]. Following this premise, this work is aiming to provide a methodology for implementing a classifier, specifically a Support Vector Machine (SVM) [3], using modulo-M integers and proposing a method for the use of Residue Number System.

Metabolomic studies generate large amounts of data, whose complexity increases if they are derived from in vivo experiments. As a result, analysis methods highly used in metabolomics, such as Partial Least Squares Discriminant Analysis (PLS-DA), can have particular difficulties with this type of data. However, there is evidence that indicates that Support Vector Machines (SVMs) can better deal with complex data. On the other hand, chronic exposure to organochlorines is a public health problem. It has been associated with diseases such as cancer. Therefore, its identification is relevant to reduce their impact on human health. This study explores the performance of SVMs in classifying metabolic profiles and identifying relevant metabolites in studies of exposure to organochlorines. For this purpose, two experiments were conducted: in the first one, organochlorine exposure was evaluated in HepG2 cells; and, in the second one, it was evaluated in serum samples of agricultural workers exposed to pesticides. The performance of SVMs was compared with that of PLS-DA. Four kernel functions were assessed in SVMs, and the accuracy of both methods was evaluated using a k-fold cross-validation test. In order to identify the most relevant metabolites, Recursive Feature Elimination (RFE) was used in SVMs and Variable Importance in Projection (VIP) in PLS-DA. The results show that SVMs exhibit a higher percentage of accuracy with fewer training samples and better performance in classifying the samples from the exposed agricultural workers. Finally, a workflow based on SVMs for the identification of biomarkers in samples with high biological complexity is proposed.

The search for models which can accurately forecast the market trend has developed over the past decades. Technical indicators and oscillators are the most usually employed inputs in the prediction models. These inputs basically rely on prices and the evolution of the index itself, which may cause some problems like multicolinearity and autocorrelation, in the case of linear models, or overoptimization and noise, in the case of neural networks. This paper proposes filtering the inputs to be employed in the models. To this end, their impact on the forecast will be analysed. A support vector machine will be used to this end, in order to characterize both inputs (indicators and oscillators) and output (market trend). Doing this, it can be assessed whether the relationship between the different inputs and the market trend offers relevant information regarding the contribution of the inputs in the prediction process and whether this contribution remains constant over time. Those inputs will be selected, which obtain more stable forecasts in order to obtain more consistent predictions.

Battery management systems are used to monitor power batteries in electric vehicles and solar power systems. They control the charge and discharge, identity and correct many problems in these batteries. Nowadays, measurements on each cell or stack of cells, which compose the battery, are necessary to ensure the safety and integrity of the system, because the battery cells degrade unequally since they are not built identically. A new methodology is presented in this work, for identification cells with finished life cycle in batteries parallel cells associations, without using temperature measurements, cell monitoring and State of Health estimators, through Support Vector Machines and Wavelet Transform. The proposed method opens possibilities for a new strategy of battery management in electric vehicles, inserting Battery Management System in the charging stations and allowing more sophisticated diagnoses.

Context: Nowadays, the images of the Earth surface and the algorithms for their classification are widely available. In particular, the algorithms are promising in the differentiating of cotton crops stages, but it is necessary to establish the capabilities of the different algorithms in order to identify their advantages, and disadvantages. Method: This paper describes the assessment process in which the Support Vector Machines (SVM) and random-forest technique (decision trees) are compared with the maximum likelihood estimation when differentiating the stages of cotton crops. A RapidEye satellite image of a geographic area in the municipality of San Pelayo, Cordoba (Colombia), is used for the study. Using a set of sampling polygons, a random sample of 6000 pixels was taken (2000 training and 4000 for validating the classifications.) Confusion matrices, and R (data processing and analysis software) were used during the validation process Results: The maximun likelihood estimation presented a correct classification percentage of 68.95%. SVM correctly classified 81.325% of the cases and the decision trees correctly classified 78.925%. The confidence test for the classifications showed non-overlapping intervals, and SVM obtained the highest values. Conclusions: It was possible to confirm the superiority of the technique based on support vector machines for the proposed verification zones. However, this technique requires a number of classes that comprehensively represent the variations of the image (in order to guarantee a minimum number of support vectors) to avoid confusion in the classification of non-sampled areas. This was less evident in the other two classification techniques analysed.

Abstract The objective of this research was to determine seismic events latitude and longitude using support vector machines (SVMs) and seismic records from “El Rosal” station, which is located 40 kilometers northwest of Bogotá, Colombia. A total of 504 SVMs models were tested to determine latitude and 504 models for longitude, with various combinations of complexity factor and kernel function exponent, applied to earthquakes of 2, 2.5, 3 and 3.5 ML in time windows of 15 , 10 and 5 seconds. The best results showed errors of 40 kilometers for latitude and 30 kilometers for longitude, with respect to the place where the earthquakes were generated. These outcomes might be improved by applying additional descriptors during SVMs training stages, such descriptors can be related to Fourier frequency spectra, predominant period and wavelet transform coefficients.

The recognition images of cattle brand in an automatic way is a necessity to governmental organs responsible for this activity. To help this process, this work presents a method that consists in using Bag of Visual Words for extracting of characteristics from images of cattle brand and Support Vector Machines Multi-Class for classification. This method consists of six stages: a) select database of images; b) extract points of interest (SURF); c) create vocabulary (K-means); d) create vector of image characteristics (visual words); e) train and sort images (SVM); f) evaluate the classification results. The accuracy of the method was tested on database of municipal city hall, where it achieved satisfactory results, reporting 86.02% of accuracy and 56.705 seconds of processing time, respectively.

Se clasificó la anchoveta (Engraulis ringens) y sardina común (Strangomera bentincki) detectadas mediante equipos acústicos en la zona centro-sur de Chile, mediante el método de Máquinas de Vectores Soporte (SVM). Para esto se utilizaron descriptores de cardúmenes extraídos desde ecogramas, que fueron clasificados como morfológicos, batimétricos, energéticos y posicional espacial. Para lograr clasificaciones precisas mediante la utilización de esta metodología, fue necesario optimizar parámetros correspondientes al Kernel-Gaussiano, γ y de penalización del modelo C, mediante el análisis del efecto de la calibración sobre las matrices de confusión resultantes de la clasificación de las especies analizadas. El método SVM ajustó correctamente el 95,3% de los cardúmenes de anchoveta y sardina común. Los parámetros óptimos del Kernel-Gaussiano γ y de penalización C obtenidos mediante la metodología propuesta fueron γ = 450 y C = 0,95, respectivamente. Los parámetros mencionados incidieron de manera importante en la matriz de confusión y los porcentajes de clasificación final, por lo que se sugiere establecer, en aplicaciones futuras de este método, un protocolo experimental de calibración. La sardina común fue la especie con menor error de clasificación en el conjunto de las matrices de confusión. El descriptor correspondiente a profundidad del fondo fue el más sensible al SVM, la segunda variable en importancia es el descriptor distancia a la costa.The support vector machines (SVM) method was used to classify the anchovy (Engraulis ringens) and common sardine (Strangomera bentincki) species detected in south-central Chile by means of acoustic equipment. For this, descriptors of fish schools (morphology, bathymetry, energy, spatial position) extracted from ecograms were used. In order to obtain precise classifications using this methodology, it was necessary to optimize the parameters Gaussian-Kernel γ and penalty term C by analyzing the effect of the calibration on the confusion matrices resulting from the classification of the species under study. The SVM method correctly classified 95.3% of anchovy and sardine schools. The optimal parameters of the Gaussian-Kernel γ and penalty C obtained with the proposed methodology were γ = 450 and C = 0.95. These parameters have an important influence over the confusion matrix and the final classifications percentages, suggesting the development of experimental protocols for calibrating these parameters in future applications of this methodology. In all the confusion matrices, the common sardine showed the lowest classification error. The bottom depth was the descriptor that was most sensitive to the SVM, followed by school-shore distance.

La predicción de series de tiempo es un importante problema de investigación debido a sus implicaciones en ingeniería, economía, finanzas y ciencias sociales. Un importante tópico de esta problemática es el desarrollo de nuevos modelos y su comparación con aproximaciones previas en términos de la precisión del pronóstico. Recientemente, las máquinas de vectores de soporte (SVM) han sido usadas para la predicción de series de tiempo, pero las experiencias reportadas son limitadas y hay algunos problemas relacionados con su especificación. El objetivo de este artículo es proponer una técnica novedosa para estimar algunas constantes en las SVM que usualmente son fijadas en forma empírica por el modelador. La técnica propuesta es usada para estimar varias SVM con el fin de pronosticar cinco series benchmark; los resultados obtenidos son comparados con las estadísticas reportadas en otros artículos. La metodología propuesta permite obtener SVM competitivas para las series pronosticadas en comparación con los resultados obtenidos usando otros modelos más tradicionales.Time series prediction is an important research problem due to its implications in engineering, economics, finance and social sciences. An important topic about this problematic is the development of new models and its comparison with previous approaches in terms of forecast accuracy. Recently, support vector machines (SVM) have been used for time series prediction, but the reported experiences are limited and there are some problems related to its specification. The aim of this paper is to propose a novel technique for estimating some constants of the SVM usually fixed empirically by the modeler. The proposed technique is used to estimate several SVM with the aim of forecast five benchmark time series; the obtained results are compared with the statistics reported in other papers. The proposed method allow us to obtain competitive SVM for the time series forecasted in comparison with the results obtained using other most traditional models.

This paper presents two pattern recognition approaches using Partial Discharges fingerprints as input features to classify PD patterns. A multi-layer perceptron (MLP) backpropagation neural network and a support vector machine (SVM) were trained to recognize three types of PD patterns. Experimental results showed that the algorithms can achieve high recognition rates. Moreover, the Discrete wavelet transform (DWT) was used to denoise PD signals as a prior stage to the classification process. Different mother wavelets were tested for different levels of decomposition in order to find appropriate wavelet parameters for better signal to noise ratio (SNR) and less distortion after the denoising process.

Currently, VoIP company technicians conduct tests to classify call quality as good or bad. Even though, there are automatic platforms that make test VoIP calls to classify them, they do not perform audio processing to detect False Answer Supervision (FAS), which is a common and undesirable feature of VoIP calls. In this paper, a Vector Support Machine (SVM) along with several functions used in voice recognition were implemented to emulate the human decision procedure (the task of audio classification and analysis performed by technicians). The experiments were based on the comparison between the results obtained from the current classification methods and those derived from the SVM. A 10-fold cross-validation was used to evaluate the system performance. The tests results from the proposed methodology show a better percentage of successful classification compared to a selected automatic platform called CheckMyRoutes.

One of the principal inconveniences that analysis and information processing presents is that of the representation of dataset. Normally, one encounters a high number of samples, each one with thousands of variables, and in many cases with irrelevant information and noise. Therefore, in order to represent findings in a clearer way, it is necessary to reduce the amount of variables. In this paper, a novel variable selection technique for multivariable data analysis, inspired on stochastic methods and designed to work with support vector machines (SVM), is described. The approach is demonstrated in a food application involving the detection of adulteration of olive oil (more expensive) with hazelnut oil (cheaper). Fingerprinting by H NMR spectroscopy was used to analyze the different samples. Results show that it is possible to reduce the number of variables without affecting classification results.

Despite the leading role that micro-entrepreneurship plays in economic development, and the high failure rate of microenterprise start-ups in their early years, very few studies have designed financial distress models to detect the financial problems of micro-entrepreneurs. Moreover, due to a lack of research, nothing is known about whether non-financial information and nonparametric statistical techniques improve the predictive capacity of these models. Therefore, this paper provides an innovative financial distress model specifically designed for microenterprise startups via support vector machines (SVMs) that employs financial, non-financial, and macroeconomic variables. Based on a sample of almost 5,500 micro- entrepreneurs from a Peruvian Microfinance Institution (MFI), our findings show that the introduction of non-financial information related to the zone in which the entrepreneurs live and situate their business, the duration of the MFI-entrepreneur relationship, the number of loans granted by the MFI in the last year, the loan destination, and the opinion of experts on the probability that microenterprise start-ups may experience financial problems, significantly increases the accuracy performance of our financial distress model. Furthermore, the results reveal that the models that use SVMs outperform those which employ traditional logistic regression (LR) analysis.

This paper presents the results obtained by developing a methodology to detect 5 types of heartbeats (Normal (N), Right bundle branch block (RBBB), Left bundle branch block (LBBB), Premature atrial contraction (APC) and Premature ventricular contraction (PVC)), using Wavelet transform packets with non-adaptative mode applied on features extraction from heartbeats. It was used the Shannon function to calculate the entropy and It was added an identification nodes stage per every type of cardiac signal in the Wavelet tree. The using of Wavelet packets transform allows the access to information which results of decomposition of low and high frecuency, giving providing a more integral analysis than achieved by the discrete Wavelet transform. Three families of mother Wavelet were evaluated on transformation: Daubechies, Symlet and Reverse Biorthogonal, which were results from a previous research in that were identified the mother Wavelet that had higher entropy with the cardiac signals. With non-adaptive mode, the computational cost is reduced when Wavelet packets are used; this cost represents the most marked disadvantage from the transform. To classify the heartbeats were used Support Vector Machines and Multilayer Perceptron. The best classification error was achieved employing Support Vector Machine and a radial basis function; it was 2.57 %.

RESUMEN: En este trabajo, se propone una metodología para la selección automática de los parámetros libres de la técnica de regresión basada en mínimos cuadrados máquinas de vectores de soporte (LS-SVM), a partir de un análisis de validación cruzada generalizada multidimensional sobre el conjunto de ecuaciones lineales de LS-SVM. La técnica desarrollada no requiere de un conocimiento a priori por parte del usuario acerca de la influencia de los parámetros libres en los resultados. Se realizan experimentos sobre dos bases de datos artificiales y dos bases de datos reales. De acuerdo a los resultados obtenidos, se concluye que el algoritmo desarrollado calcula regresiones apropiadas con errores relativos competentes.

This paper discusses a research related with the innovative use of a decision support system based on data mining (to evaluate historical information) and the support vector machine method to determine the optimal values related with the cooling efficiency of a gas turbine blade and to determine the adequate selection of components to build scenarios under uncertainty. This research allows the selection of a specific number of optimal values for components, in a time horizon of a power energy installation (approximately four hours). These components are evaluated with data from an information repository of a successful energy system. The intent of this research is to apply the computational properties of an established model of intelligent optimization. The case study allowed the analysis of the individual features of each component with the emulation from set matching features (optimal values reached by our hybrid algorithm). This way it is possible to predict a better functionality in this kind of system.

Introduction: The tests used to classify older adults at risk of falls are questioned in literature. Tools from the field of artificial intelligence are an alternative to classify older adults more precisely. Objective: To identify the risk of falls in the elderly through electromyographic signals of the lower limb, using tools from the field of artificial intelligence. Methods: A descriptive study design was used. The unit of analysis was made up of 32 older adults (16 with and 16 without risk of falls). The electrical activity of the lower limb muscles was recorded during the functional walking gesture. The cycles obtained were divided into training and validation sets, and then from the amplitude variable, select attributes using the Weka software. Finally, the Support Vector Machines (SVM) classifier was implemented. Results: A classifier of two classes (elderly adults with and without risk of falls) based on SVM was built, whose performance was: Kappa index 0.97 (almost perfect agreement strength), sensitivity 97%, specificity 100%. Conclusions: The SVM artificial intelligence technique applied to the analysis of lower limb electromyographic signals during walking can be considered a precision tool of diagnostic, monitoring and follow-up for older adults with and without risk of falls.

Nowadays, it is imperative to reduce the energy bill in order to contribute to a more sustainable planet. In this sense, the use of materials that contribute to the energy efficiency of buildings is a very important contribution to achieve this goal. Mortars incorporating phase change materials (PCM) can make an important contribution to this end, due to its thermal storage capacity, increasing the energy efficiency of buildings. In this work several mortars with different PCM contents were developed, using different binders (cement, aerial lime, hydraulic lime and gypsum). The aim of this study was to apply data mining techniques such as artificial neural networks (ANN), support vector machines (SVM) and multiple linear regressions (MLR) to forecast the compressive and flexural strengths of these mortars at different exposure temperatures. It was concluded that ANN models have the best predictive capacity both for compressive strength and flexural strength. However, the SVM models have a flexural strength forecasting capacity very close to ANN models.

In recent decades, transportation planning researchers have used diverse types of machine learning (ML) algorithms to research a wide range of topics. This review paper starts with a brief explanation of some ML algorithms commonly used for transportation research, specifically Artificial Neural Networks (ANN), Decision Trees (DT), Support Vector Machines (SVM) and Cluster Analysis (CA). Then, these different methodologies used by researchers for modeling travel mode choice are collected and compared with the Multinomial Logit Model (MNL) which is the most commonly-used discrete choice model. Finally, the characterization of ML algorithms is discussed and Random Forest (RF), a variant of Decision Tree algorithms, is presented as the best methodology for modeling travel mode choice.

Due to the growing energy demand and the eminent global warming, there is special interest in the prediction of irradiance based on the reflectance obtained from satellites such as NASA Landsat, since it allows to know where it is more efficient to place photovoltaic receivers. Although there are studies for obtaining regression models with alternative Kernel functions, their performance for classification models is unknown and it is here where this research focuses. The study couples alternative Kernel functions to the support vector machines (SVM) algorithm for classification problems, where the best configuration for these algorithms is explored to finally obtain a set of irradiance maps zoned by class.

Pollution in dense populations such as the Metropolitan Area of Guadalajara grows exponentially, affecting the health of citizens and reducing their quality of life. One of the main research challenges pursued with the study of Smart Cities is environmental pollution to improve the well-being of citizens and to protect natural areas. Therefore, it is urgent the development of information technologies that allow to reduce this problem by the scientific analysis of data, to classify the zones with greater contamination. Currently, these data are captured by constant monitoring stations, generating a large volume of information representing a challenge for the classification process. This work proposes a model for the automatic execution of a classification algorithm using Support Vector Machine implementing libraries in python for parallel processing. As a result, we obtain two main subsystems: one of the Parameters of Configuration for the storage and cleaning of data and the design of the algorithm parallelized in the cloud importing modules mpi4py, numpy and sklearn.svm.

A tool that can perform the automatic identification of cattle brandings is essential for the government agencies responsible for the record, control and inspection of this activity. This article presents a novel hybrid method that uses Convolutional Neural Networks (CNN) to extract features from images and Support Vector Machines (SVM) to classify the brandings. The experiments were performed using a cattle branding image set provided by the City Hall of Bagé, Brazil. Metrics of Overall Accuracy, Recall, Precision, Kappa Coefficient, and Processing Time were used in order to assess the proposed tool. The results obtained here were satisfactory, reaching a Overall Accuracy of 93.11% in the first experiment with 39 brandings and 1,950 sample images, and 95.34% of accuracy in the second experiment, with the same 39 brandings, but with 2,730 sample images. The processing time attained in the experiments was 31.661s and 41.749s, respectively.

ABSTRACT The aim of this study was to present and to evaluate methodologies for the estimation of soil resistance to penetration (RP) using artificial intelligence prediction techniques. In order to do so, a data base with values of physical-water characteristics of the soils available in the literature was used, and the performances of Artificial Neural Networks (ANN) and Support Vector Machines (SVM) were evaluated. The models generated from the ANNs were implemented through the multilayer perceptron with backpropagation algorithm of Matlab software, varying the number of neurons in the input and intermediate layers. For the procedure from SVM, the RapidMiner software was used, varying input variables, the kernel function and the coefficients of these functions. The efficiency of the techniques was analyzed by the ratio 1:1, and later, compared to the Busscher non-linear model (Busscher, 1990). The results showed that the artificial intelligence models (ANN and SVM) are efficient and have predictive capacity superior to the Busscher model, under data conditions of soils with textural classes and different, and similar managements, although with higher performance index values for conditions of soils of the same textural class exposed to the same management.

The automatic prediction of the course of action of agents involved in social or economic trends is an imperative challenge nowadays. However, it is a difficult task because stance or opinion is often spread throughout long, complex texts, such as news articles. The current study tests sentence predicates as features to automatically determine the writer’s stance in news articles. We capture the semantics and stance of the text by encoding features such as the attribute of copulative sentences, the predicate of transitive sentences, adjectival phrases, and the section of the article. Under the assumption that these features are informative enough to model the semantics of the text, each word sequence is disambiguated and assigned a sentiment value using weighting rules. Different experiments were run using either SentiWordNet and ML-Senticon to determine words’ sentiment. Feature vectors are automatically built to populate a database that is tested using two machine learning algorithms. An efficiency of 69% was achieved using a SVM with Gaussian kernel along with a feature selection strategy. This score outperformed the bag-of-words baseline in 12%. These results are promising considering that the sentiment analysis is performed on very complex texts written in Spanish.

This paper presents a comparative study of the measurement features used as inputs of a fault locator based on Support Vector Machines, which is aimed to analyze single-phase faults. Studies have shown that a huge database is required to obtain high performance, but a problem is associated with the excessive computing time required to evaluate such databases. This study examines properly these inputs to determine which are the most significant ones in terms of performance. Tests are performed on a 75 bus 34.5 kV distribution system, with 75000 shunt faults, implemented in ATP. According to the results, 12 features related to magnitude variations of phase voltage and current between fault and pre-fault steady states were relevant to achieve a performance of 96.3%, with a computational time of training and cross-validation of approximately six minutes.

Artificial intelligence (AI) is an interdisciplinary subject in science and engineering that makes it possible for machines to learn from data. Artificial Intelligence applications include prediction, recommendation, classification and recognition, object detection, natural language processing, autonomous systems, among others. The topics of the articles in this special issue include deep learning applied to medicine [1, 3], support vector machine applied to ecosystems [2], human-robot interaction [4], clustering in the identification of anomalous patterns in communication networks [5], expert systems for the simulation of natural disaster scenarios [6], real-time algorithms of artificial intelligence [7] and big data analytics for natural disasters [8].

The conventional cytology is one of the most used techniques, being widely accepted, inexpensive, and with control mechanisms. With the objective of alleviating the workload of to experts, some researchers have proposed the development of tools for computer vision to detect and classify the transformations in the cells of the cervix region. In this paper, is presented the use of the support vector machines (SVM) as a computational method for classification of cervical cells in normal and abnormal conditions, based solely on the extracted features of the region occupied by the nucleus without use of the characteristics of the cytoplasm. The importance of this approach lies in that the nuclei are the region that can be more easily segmented into complex images Pap smear. These images show a high degree of overlapping cells and is difficult to distinguish the exact boundaries of the regions occupied by the cytoplasm. As of study between the linear and RBF kernels on function AUC measures as F, H and half negative predictability was found that performed well RBF values keeping 0.91% AUC. The results indicate a reduction from the rate of false negative Pap test. H mean was used in order to compare the results of SVM with RBF kernel respect to other investigations, obtaining 91.28% above the same.

Título en ingles: Protein secondary structure prediction using support vector machines Abstract : Among the computational methods used for predicting secondary structure proteins highlights the use of support vector machines. This research shows the predicted secondary structure of protein from its primary amino acid sequence using Support Vector Machines. As inputs, in the proposed methodology, features are used from different structural motifs or text strings associated with the primary structure which represents the secondary structure, such as R-group and the probability that the amino acid at position adopts a central particular secondary structure. For feature extraction method is used coding of sequences in which each symbol in the primary structure is associated with each symbol in the secondary structure. The use of this encoding method reduces the dimensionality of the data of thousands of characteristics only 220 of these. The results obtained are comparable to those reported in the literature, taking about 70% accuracy. Furthermore, it is possible to reduce computational cost in the construction of classifiers because this work models the problem of multi classification as a group of binary classifiers. Key words: coding methodology; support vector machines; prediction of protein secondary structure. Resumen: Entre los métodos computacionales utilizados para la predicción de la estructura secundaria de proteínas, se destaca el uso de máquinas de soporte vectorial. Este trabajo de investigación presenta la predicción de la estructura secundaria de proteínas desde su secuencia primaria de aminoácidos usando Máquinas de Soporte Vectorial. Como entradas, en la metodología propuesta, se utilizan características de los diferentes motivos estructurales o cadenas de texto asociadas a la estructura primaria que representa la estructura secundaria, tales como el R-grupo y la probabilidad de que el aminoácido en la posición central adopte una determinada estructura secundaria. Para la extracción de características se utiliza un método de codificación de secuencias en el que cada símbolo en la estructura primaria se relaciona con cada símbolo en la estructura secundaria. El uso de este método de codificación permite reducir la dimensionalidad de los datos de miles de características a sólo 220 de estas. Los resultados obtenidos son comparables a los registrados en la literatura, teniendo cerca de un 70% de precisión. Además, se logra reducir los costos computacionales en la construcción de los clasificadores debido a que este trabajo modela el problema de multi-clasificación como un grupo de clasificadores binarios. Palabras clave: máquinas de soporte vectorial; metodología de codificación; predicción de la estructura secundaria de proteínas.