Mauricio Alexander Álvarez-López

SVM-based feature selection methods for emotion recognition from multimodal data

Multimodal emotion recognition is an emerging field within affective computing that, by simultaneously using different physiological signals, looks for evaluating an emotional state. Physiological signals such as electroencephalogram (EEG), temperature and electrocardiogram (ECG), to name a few, have been used to assess emotions like happiness, sadness or anger, or to assess levels of arousal or valence. Research efforts in this field so far have mainly focused on building pattern recognition systems with an emphasis on feature extraction and classifier design. A different set of features is extracted over each type of physiological signal, and then all these sets of features are combined, and used to feed a particular classifier. An important stage of a pattern recognition system that has received less attention within this literature is the feature selection stage. Feature selection is particularly useful for uncovering the discriminant abilities of particular physiological signals. The main objective of this paper is to study the discriminant power of different features associated to several physiological signals used for multimodal emotion recognition. To this end, we apply recursive feature elimination and margin-maximizing feature elimination over two well known multimodal databases, namely, DEAP and MAHNOB-HCI. Results show that EEG-related features show the highest discrimination ability. For the arousal index, EEG features are accompanied by Galvanic skin response features in achieving the highest discrimination power, whereas for the valence index, EEG features are accompanied by the heart rate features in achieving the highest discrimination power.

Estimación de los Parámetros de un Modelo de un Horno de Arco Eléctrico Usando Máxima Verosimilitud

In this paper, we present a methodology for estimating the parameters of a model for an electrical arc furnace, by using maximum likelihood estimation. Maximum likelihood estimation is one of the most employed methods for parameter estimation in practical settings. The model for the electrical arc furnace that we consider, takes into account the non-periodic and non-linear variations in the voltage-current characteristic. We use NETLAB, an open source MATLAB® toolbox, for solving a set of non-linear algebraic equations that relate all the parameters to be estimated. Results obtained through simulation of the model in PSCADTM, are contrasted against real measurements taken during the furnances most critical operating point. We show how the model for the electrical arc furnace, with appropriate parameter tuning, captures with great detail the real voltage and current waveforms generated by the system. Results obtained show a maximum error of 5% for the currents root mean square error.

Feature relevance estimation for vibration-based condition monitoring of an internal combustion engine

Condition monitoring of Internal Combustion Engines (ICE) benefits cost-effective operations in the modern industrial sector. Because of this, vibration signals are commonly monitored as part of a non-invasive approach to ICE analysis. However, vibration-based ICE monitoring poses a challenge due to the properties of this kind of signals. They are highly dynamic and non-stationary, let alone the diverse sources involved in the combustion process. In this paper, we propose a feature relevance estimation strategy for vibration-based ICE analysis. Our approach is divided into three main stages: signal decomposition using an Ensemble Empirical Mode Decomposition algorithm, multi-domain parameter estimation from time and frequency representations, and a supervised feature selection based on the Relief-F technique. Accordingly, we decomposed the vibration signals by using self-adaptive analysis to represent nonlinear and non-stationary time series. Afterwards, time and frequency-based parameters were calculated to code complex and/or non-stationary dynamics. Subsequently, we computed a relevance vector index to measure the contribution of each multi-domain feature to the discrimination of different fuel blend estimation/diagnosis categories for ICE. In particular, we worked with an ICE dataset collected from fuel blends under normal and fault scenarios at different engine speeds to test our approach. Our classification results presented nearly 98% of accuracy after using a k-Nearest Neighbors machine. They reveal the way our approach identifies a relevant subset of features for ICE condition monitoring. One of the benefits is the reduced number of parameters.

A comparison of robust Kalman filtering methods for artifact correction in heart rate variability analysis

Heart rate variability (HRV) has received considerable attention for many years, since it provides a quantitative marker for examining the sinus rhythm modulated by the autonomic nervous system (ANS). The ANS plays an important role in clinical and physiological fields. HRV analysis can be performed by computing several time and frequency domain measurements. However, the computation of such measurements can be affected by the presence of artifacts or ectopic beats in the electrocardiogram (ECG) recording. This is particularly true for ECG recordings from Holter monitors. The aim of this work was to study the performance of several robust Kalman filters for artifact correction in Inter-beat (RR) interval time series. For our experiments, two data sets were used: the first data set included 10 RR interval time series from a realistic RR interval time series generator. The second database contains 10 sets of RR interval series from five healthy patients and five patients suffering from congestive heart failure. The standard deviation of the RR interval was computed over the filtered signals. Results were compared with a state of the art processing software, showing similar values and behavior. In addition, the proposed methods offer satisfactory results in contrast to standard Kalman filtering.

Detección de Eventos Sonoros en Señales de Música Usando Procesos Gaussianos

In this paper we present a new methodology for detecting sound events in music signals using Gaussian Processes. Our method firstly takes a timefrequency representation, i.e. the spectrogram, of the input audio signal. Secondly the spectrogram dimension is reduced translating the linear Hertz frequency scale into the logarithmic Mel frequency scale using a triangular filter bank. Finally every short-time spectrum, i.e. every Mel spectrogram column, is classified as “Event” or “Not Event” by a Gaussian Processes Classifier. We compare our method with other event detection techniques widely used. To do so, we use MATLAB® to program each technique and test them using two datasets of music with different levels of complexity. Results show that the new methodology outperforms the standard approaches, getting an improvement by about 1.66 % on the dataset one and 0.45 % on the dataset two in terms of F-measure.