Robust Multi-Scenario Speech-Based Emotion Recognition System.

Every human being experiences emotions daily, e.g., joy, sadness, fear, anger. These might be revealed through speech-words are often accompanied by our emotional states when we talk. Different acoustic emotional databases are freely available for solving the Emotional Speech Recognition (ESR) task. Unfortunately, many of them were generated under non-real-world conditions, i.e., actors played emotions, and recorded emotions were under fictitious circumstances where noise is non-existent. Another weakness in the design of emotion recognition systems is the scarcity of enough patterns in the available databases, causing generalization problems and leading to overfitting. This paper examines how different recording environmental elements impact system performance using a simple logistic regression algorithm. Specifically, we conducted experiments simulating different scenarios, using different levels of Gaussian white noise, real-world noise, and reverberation. The results from this research show a performance deterioration in all scenarios, increasing the error probability from 25.57% to 79.13% in the worst case. Additionally, a virtual enlargement method and a robust multi-scenario speech-based emotion recognition system are proposed. Our system's average error probability of 34.57% is comparable to the best-case scenario with 31.55%. The findings support the prediction that simulated emotional speech databases do not offer sufficient closeness to real scenarios.

A Wrapper Feature Selection Algorithm: An Emotional Assessment Using Physiological Recordings from Wearable Sensors.

Assessing emotional state is an emerging application field boosting research activities on the topic of analysis of non-invasive biosignals to find effective markers to accurately determine the emotional state in real-time. Nowadays using wearable sensors, electrocardiogram and thoracic impedance measurements can be recorded, facilitating analyzing cardiac and respiratory functions directly and autonomic nervous system function indirectly. Such analysis allows distinguishing between different emotional states: neutral, sadness, and disgust. This work was specifically focused on the proposal of a k-fold approach for selecting features while training the classifier that reduces the loss of generalization. The performance of the proposed algorithm used as the selection criterion was compared to the commonly used standard error function. The proposed k-fold approach outperforms the conventional method with 4% hit success rate improvement, reaching an accuracy near to 78%. Moreover, the proposed selection criterion method allows the classifier to produce the best performance using a lower number of features at lower computational cost. A reduced number of features reduces the risk of overfitting while a lower computational cost contributes to implementing real-time systems using wearable electronics.

Activity Recognition Using Wearable Physiological Measurements: Selection of Features from a Comprehensive Literature Study.

Activity and emotion recognition based on physiological signal processing in health care applications is a relevant research field, with promising future and relevant applications, such as health at work or preventive care. This paper carries out a deep analysis of features proposed to extract information from the electrocardiogram, thoracic electrical bioimpedance, and electrodermal activity signals. The activities analyzed are: neutral, emotional, mental and physical. A total number of 533 features are tested for activity recognition, performing a comprehensive study taking into consideration the prediction accuracy, feature calculation, window length, and type of classifier. Feature selection to know the most relevant features from the complete set is implemented using a genetic algorithm, with a different number of features. This study has allowed us to determine the best number of features to obtain a good error probability avoiding over-fitting, and the best subset of features among those proposed in the literature. The lowest error probability that is obtained is 22.2%, with 40 features, a least squares error classifier, and 40 seconds window length.

Smart Sound Processing for Defect Sizing in Pipelines Using EMAT Actuator Based Multi-Frequency Lamb Waves.

Pipeline inspection is a topic of particular interest to the companies. Especially important is the defect sizing, which allows them to avoid subsequent costly repairs in their equipment. A solution for this issue is using ultrasonic waves sensed through Electro-Magnetic Acoustic Transducer (EMAT) actuators. The main advantage of this technology is the absence of the need to have direct contact with the surface of the material under investigation, which must be a conductive one. Specifically interesting is the meander-line-coil based Lamb wave generation, since the directivity of the waves allows a study based in the circumferential wrap-around received signal. However, the variety of defect sizes changes the behavior of the signal when it passes through the pipeline. Because of that, it is necessary to apply advanced techniques based on Smart Sound Processing (SSP). These methods involve extracting useful information from the signals sensed with EMAT at different frequencies to obtain nonlinear estimations of the depth of the defect, and to select the features that better estimate the profile of the pipeline. The proposed technique has been tested using both simulated and real signals in steel pipelines, obtaining good results in terms of Root Mean Square Error (RMSE).

Assessment of Mental, Emotional and Physical Stress through Analysis of Physiological Signals Using Smartphones.

Determining the stress level of a subject in real time could be of special interest in certain professional activities to allow the monitoring of soldiers, pilots, emergency personnel and other professionals responsible for human lives. Assessment of current mental fitness for executing a task at hand might avoid unnecessary risks. To obtain this knowledge, two physiological measurements were recorded in this work using customized non-invasive wearable instrumentation that measures electrocardiogram (ECG) and thoracic electrical bioimpedance (TEB) signals. The relevant information from each measurement is extracted via evaluation of a reduced set of selected features. These features are primarily obtained from filtered and processed versions of the raw time measurements with calculations of certain statistical and descriptive parameters. Selection of the reduced set of features was performed using genetic algorithms, thus constraining the computational cost of the real-time implementation. Different classification approaches have been studied, but neural networks were chosen for this investigation because they represent a good tradeoff between the intelligence of the solution and computational complexity. Three different application scenarios were considered. In the first scenario, the proposed system is capable of distinguishing among different types of activity with a 21.2% probability error, for activities coded as neutral, emotional, mental and physical. In the second scenario, the proposed solution distinguishes among the three different emotional states of neutral, sadness and disgust, with a probability error of 4.8%. In the third scenario, the system is able to distinguish between low mental load and mental overload with a probability error of 32.3%. The computational cost was calculated, and the solution was implemented in commercially available Android-based smartphones. The results indicate that execution of such a monitoring solution is negligible compared to the nominal computational load of current smartphones.

Automatic classification of background EEG activity in healthy and sick neonates.

The overall aim of our research is to develop methods for a monitoring system to be used at neonatal intensive care units. When monitoring a baby, a range of different types of background activity needs to be considered. In this work, we have developed a scheme for automatic classification of background EEG activity in newborn babies. EEG from six full-term babies who were displaying a burst suppression pattern while suffering from the after-effects of asphyxia during birth was included along with EEG from 20 full-term healthy newborn babies. The signals from the healthy babies were divided into four behavioural states: active awake, quiet awake, active sleep and quiet sleep. By using a number of features extracted from the EEG together with Fisher's linear discriminant classifier we have managed to achieve 100% correct classification when separating burst suppression EEG from all four healthy EEG types and 93% true positive classification when separating quiet sleep from the other types. The other three sleep stages could not be classified. When the pathological burst suppression pattern was detected, the analysis was taken one step further and the signal was segmented into burst and suppression, allowing clinically relevant parameters such as suppression length and burst suppression ratio to be calculated. The segmentation of the burst suppression EEG works well, with a probability of error around 4%.

Sea clutter reduction and target enhancement by neural networks in a marine radar system.

The presence of sea clutter in marine radar signals is sometimes not desired. So, efficient radar signal processing techniques are needed to reduce it. In this way, nonlinear signal processing techniques based on neural networks (NNs) are used in the proposed clutter reduction system. The developed experiments show promising results characterized by different subjective (visual analysis of the processed radar images) and objective (clutter reduction, target enhancement and signal-to-clutter ratio improvement) criteria. Moreover, a deep study of the NN structure is done, where the low computational cost and the high processing speed of the proposed NN structure are emphasized.

Design of two-dimensional zero reference codes with a genetic algorithm.

In mask-alignment systems a reference signal is needed to align the mask with the silicon wafers. The optical reference signal is the autocorrelation of two two-dimensional (2D) codes with binary transmittance. For a long time, one-dimensional codes have been used in grating-measurement systems to obtain a reference signal. The design of this type of code has needed a great computational effort, which limits the size of the code to about 100 elements. Recently, we have applied genetic algorithms to design codes with arbitrary length. We propose the application of these algorithms to design 2D codes to generate 2D optical signals used in mask-alignment systems.

Optimal design of optical reference signals by use of a genetic algorithm.

A new technique for the generation of optical reference signals with optimal properties is presented. In grating measurement systems a reference signal is needed to achieve an absolute measurement of the position. The optical signal is the autocorrelation of two codes with binary transmittance. For a long time, the design of this type of code has required great computational effort, which limits the size of the code to approximately 30 elements. Recently, the application of the dividing rectangles (DIRECT) algorithm has allowed the automatic design of codes up to 100 elements. Because of the binary nature of the problem and the parallel processing of the genetic algorithms, these algorithms are efficient tools for obtaining codes with particular autocorrelation properties. We design optimum zero reference codes with arbitrary length by means of a genetic algorithm enhanced with a restricted search operator.