A Predictive Model for Emotion Recognition Based on Individual Characteristics and Autonomic Changes.

Introduction: Studies have repeatedly stated the importance of individual differences in the problem of emotion recognition. The primary focus of this study is to predict Heart Rate Variability (HRV) changes due to affective stimuli from the individual characteristics. These features include age (A), gender (G), linguality (L), and sleep (S). In addition, the best combination of individual variables was explored to estimate emotional HRV. Methods: To this end, HRV indices of 47 college students exposed to images with four emotional categories of happiness, sadness, fear, and relaxation were analyzed. Then, a novel predictive model was introduced based on the regression equation. Results: The results show that different emotional situations provoke the importance of different individual variable combinations. The best variables arrangements to predict HRV changes due to emotional provocations are LS, GL, GA, ALS, and GALS. However, these combinations were changed according to each subject separately. Conclusion: The suggested simple model effectively offers new insight into emotion studies regarding subject characteristics and autonomic parameters. Highlights: HRV affective states was predicted using the individual characteristics.A novel predictive model was proposed utilizing the regression.Distinctive emotional situations provoke the importance of different individual variable combinations.The close association exists between gender and physiological changes in emotional states. Plain Language Summary: In everyday life, emotions play a critical role in health, social relationships, and daily functions. Among physiologicalmeasures, the ANS activity, especially Heart Rate Variability (HRV), plays an important role in many recent theories of emotion. Many studies have analyzed HRV differences in the physiological mechanism of emotional reactions as a function of individual variables such as age, gender, and linguality, as well as other factors like sleep duration. It is the first study that explored the importance of individual characteristic's involvements and combinations was explored in the problem of emotion prediction based on an HRV parameter. To this effect, an emotion predictive model was proposed based on the linear combinations of individual differences with acceptable performance.

The effect of traditional Persian music on the cardiac functioning of young Iranian women.

In the past few decades, several studies have reported the physiological effects of listening to music. The physiological effects of different music types on different people are not similar. Therefore, in the present study, we have sought to examine the effects of traditional Persian music on the cardiac function in young women. Twenty-two healthy females participated in this study. ECG signals were recorded in two conditions: rest and music. For each of the 21 ECG signals (15 morphological and six wavelet based feature) features were extracted. SVM classifier was used for the classification of ECG signals during and before the music. The results showed that the mean of heart rate, the mean amplitude of R-wave, T-wave, and P-wave decreased in response to music. Time-frequency analysis revealed that the mean of the absolute values of the detail coefficients at higher scales increased during rest. The overall accuracy of 91.6% was achieved using polynomial kernel and RBF kernel. Using linear kernel, the best result (with the accuracy rate of 100%) was attained.

Fusion of heart rate variability and pulse rate variability for emotion recognition using lagged poincare plots.

Designing an efficient automatic emotion recognition system based on physiological signals has attracted great interests within the research of human-machine interactions. This study was aimed to classify emotional responses by means of a simple dynamic signal processing technique and fusion frameworks. The electrocardiogram and finger pulse activity of 35 participants were recorded during rest condition and when subjects were listening to music intended to stimulate certain emotions. Four emotion categories, including happiness, sadness, peacefulness, and fear were chosen. Estimating heart rate variability (HRV) and pulse rate variability (PRV), 4 Poincare indices in 10 lags were extracted. The support vector machine classifier was used for emotion classification. Both feature level (FL) and decision level (DL) fusion schemes were examined. Significant differences have been observed between lag 1 Poincare plot indices and the other lagged measures. The mean accuracies of 84.1, 82.9, 79.68, and 76.05% were obtained for PRV, DL, FL, and HRV measures, respectively. However, DL outperformed others in discriminating sadness and peacefulness, using SD1 and total features, correspondingly. In both cases, the classification rates improved up to 92% (with the sensitivity of 95% and specificity of 83.33%). Totally, DL resulted in better performances compared to FL. In addition, the impact of the fusion rules on the classification performances has been confirmed.

Robust transmission of rate coding in the inhibitory Purkinje cell to cerebellar nuclei pathway in awake mice.

Neural coding through inhibitory projection pathways remains poorly understood. We analyze the transmission properties of the Purkinje cell (PC) to cerebellar nucleus (CN) pathway in a modeling study using a data set recorded in awake mice containing respiratory rate modulation. We find that inhibitory transmission from tonically active PCs can transmit a behavioral rate code with high fidelity. We parameterized the required population code in PC activity and determined that 20% of PC inputs to a full compartmental CN neuron model need to be rate-comodulated for transmission of a rate code. Rate covariance in PC inputs also accounts for the high coefficient of variation in CN spike trains, while the balance between excitation and inhibition determines spike rate and local spike train variability. Overall, our modeling study can fully account for observed spike train properties of cerebellar output in awake mice, and strongly supports rate coding in the cerebellum.

The Effect of Creative Tasks on Electrocardiogram: Using Linear and Nonlinear Features in Combination with Classification Approaches.

Objective: Interest in the subject of creativity and its impacts on human life is growing extensively. However, only a few surveys pay attention to the relation between creativity and physiological changes. This paper presents a novel approach to distinguish between creativity states from electrocardiogram signals. Nineteen linear and nonlinear features of the cardiac signal were extracted to detect creativity states. Method: ECG signals of 52 participants were recorded while doing three tasks of Torrance Tests of Creative Thinking (TTCT/ figural B). To remove artifacts, notch filter 50 Hz and Chebyshev II were applied. According to TTCT scores, participants were categorized into the high and low creativity groups: Participants with scores higher than 70 were assigned into the high creativity group and those with scores less than 30 were considered as low creativity group. Some linear and nonlinear features were extracted from the ECGs. Then, Support Vector Machine (SVM) and Adaptive Neuro-Fuzzy Inference System (ANFIS) were used to classify the groups. Results: Applying the Wilcoxon test, significant differences were observed between rest and each three tasks of creativity. However, better discrimination was performed between rest and the first task. In addition, there were no statistical differences between the second and third task of the test. The results indicated that the SVM effectively detects all the three tasks from the rest, particularly the task 1 and reached the maximum accuracy of 99.63% in the linear analysis. In addition, the high creative group was separated from the low creative group with the accuracy of 98.41%. Conclusion: the combination of SVM classifier with linear features can be useful to show the relation between creativity and physiological changes.

Power Spectral Density Analysis of Purkinje Cell Tonic and Burst Firing Patterns From a Rat Model of Ataxia and Riluzole Treated.

INTRODUCTION: Purkinje Cell (PC) output displays a complex firing pattern consisting of high frequency sodium spikes and low frequency calcium spikes, and disruption in this firing behavior may contribute to cerebellar ataxia. Riluzole, neuroprotective agent, has been demonstrated to have neuroprotective effects in cerebellar ataxia. Here, the spectral analysis of PCs firing in control, 3-acetylpyridine (3-AP), neurotoxin agent, treated alone and riluzole plus 3-AP treated were investigated to determine changes in the firing properties. Difference in the power spectra of tonic and burst firing was assessed. Furthermore, the role of calcium-activated potassium channels in the power spectra was evaluated. METHODS: Analysis was performed using Matlab. Power spectral density (PSD) of PCs output were obtained. Peak frequencies were extracted from the spectrum and statistical comparisons were done. In addition, a multi-compartment computational model of a Purkinje cell was used. This computational stimulation allowed us to study the changes in the power spectral density of the PC output as a result of alteration in ion channels. RESULTS: Spectral analysis showed that in the spectrum of tonic and burst firing pattern only high sodium frequency and low calcium frequency was seen, respectively. In addition, there was a significant difference between the frequency components of PCs firing obtained from normal, ataxia and riluzole treated rats. Results indicated that sodium firing frequency of normal, ataxic and treated PCs occurred in approximate frequency of 22.53±5.49, 6.46±0.23, and 31.34±4.07 Hz, respectively; and calcium frequency occurred in frequency of 4.22±2.02, 1.52±1.19, and 3.88±1.37 Hz, respectively. The simulation results demonstrated that blockade of calcium-activated potassium channels in the PC model changed the PSD of the PC model firing activity. This change was similar to PSD changes in ataxia condition. CONCLUSION: These alterations in the spectrum of PC output may be a basis for developing possible new treatment strategies to improve cerebellar ataxia.

Indices from lagged poincare plots of heart rate variability: an efficient nonlinear tool for emotion discrimination.

Interest in human emotion recognition, regarding physiological signals, has recently risen. In this study, an efficient emotion recognition system, based on geometrical analysis of autonomic nervous system signals, is presented. The electrocardiogram recordings of 47 college students were obtained during rest condition and affective visual stimuli. Pictures with four emotional contents, including happiness, peacefulness, sadness, and fear were selected. Then, ten lags of Poincare plot were constructed for heart rate variability (HRV) segments. For each lag, five geometrical indices were extracted. Next, these features were fed into an automatic classification system for the recognition of the four affective states and rest condition. The results showed that the Poincare plots have different shapes for different lags, as well as for different affective states. Considering higher lags, the greatest increment in SD1 and decrements in SD2 occurred during the happiness stimuli. In contrast, the minimum changes in the Poincare measures were perceived during the fear inducements. Therefore, the HRV geometrical shapes and dynamics were altered by the positive and negative values of valence-based emotion dimension. Using a probabilistic neural network, a maximum recognition rate of 97.45% was attained. Applying the proposed methodology based on lagged Poincare indices, a valuable tool for discriminating the emotional states was provided.

Dynamic Hilbert warping, a new measure of RR-interval signals evaluated in the cognitive load estimation.

RR interval (RRI) signals represent the time intervals between successive heart R-waves. These signals are influenced by many cognitive and psychological processes. In this study, a new technique based on the combination of empirical mode decomposition and dynamic Hilbert warping (DHW) was proposed to inference cognitive states from measured RRI signals. Moreover, a set of entropic and statistical measures was extracted to characterize the regularity and temporal distribution in the phase spectra and amplitude envelope of the analytic signals. The discriminating capability of the proposed method was studied in 45 healthy subjects. They performed an arithmetic task with five levels of difficulty. The study indicated the importance of phase information in cognitive load estimation (CLE). The new phase characteristics were able to extract hidden information from the RRI signals. The results revealed a striking decrease in DHW value with increasing load level. The entropic measures of analytic signal also showed an increasing trend as the mental load increased. Although, phase information had an ability to discriminate between more distinct levels as well as between more similar ones, amplitude information was effective only in discriminating between more distinct levels.

Investigating the effect of traditional Persian music on ECG signals in young women using wavelet transform and neural networks.

OBJECTIVE: In the past few decades, several studies have reported the physiological effects of listening to music. The physiological effects of different music types on different people are different. In the present study, we aimed to examine the effects of listening to traditional Persian music on electrocardiogram (ECG) signals in young women. METHODS: Twenty-two healthy females participated in this study. ECG signals were recorded under two conditions: rest and music. For each ECG signal, 20 morphological and wavelet-based features were selected. Artificial neural network (ANN) and probabilistic neural network (PNN) classifiers were used for the classification of ECG signals during and before listening to music. RESULTS: Collected data were separated into two data sets: train and test. Classification accuracies of 88% and 97% were achieved in train data sets using ANN and PNN, respectively. In addition, the test data set was employed for evaluating the classifiers, and classification rates of 84% and 93% were obtained using ANN and PNN, respectively. CONCLUSION: The present study investigated the effect of music on ECG signals based on wavelet transform and morphological features. The results obtained here can provide a good understanding on the effects of music on ECG signals to researchers.

An accurate emotion recognition system using ECG and GSR signals and matching pursuit method.

BACKGROUND: The purpose of the current study was to examine the effectiveness of Matching Pursuit (MP) algorithm in emotion recognition. METHODS: Electrocardiogram (ECG) and galvanic skin responses (GSR) of 11 healthy students were collected while subjects were listening to emotional music clips. Applying three dictionaries, including two wavelet packet dictionaries (Coiflet, and Daubechies) and discrete cosine transform, MP coefficients were extracted from ECG and GSR signals. Next, some statistical indices were calculated from the MP coefficients. Then, three dimensionality reduction methods, including Principal Component Analysis (PCA), Linear Discriminant Analysis, and Kernel PCA were applied. The dimensionality reduced features were fed into the Probabilistic Neural Network in subject-dependent and subject-independent modes. Emotion classes were described by a two-dimensional emotion space, including four quadrants of valence and arousal plane, valence based, and arousal based emotional states. RESULTS: Using PCA, the highest recognition rate of 100% was achieved for sigma = 0.01 in all classification schemes. In addition, the classification performance of ECG features was evidently better than that of GSR features. Similar results were obtained for subject-dependent emotion classification mode. CONCLUSIONS: An accurate emotion recognition system was proposed using MP algorithm and wavelet dictionaries.

An efficient automatic workload estimation method based on electrodermal activity using pattern classifier combinations.

Automatic workload estimation has received much attention because of its application in error prevention, diagnosis, and treatment of neural system impairment. The development of a simple but reliable method using minimum number of psychophysiological signals is a challenge in automatic workload estimation. To address this challenge, this paper presented three different decomposition techniques (Fourier, cepstrum, and wavelet transforms) to analyze electrodermal activity (EDA). The efficiency of various statistical and entropic features was investigated and compared. To recognize different levels of an arithmetic task, the features were processed by principal component analysis and machine-learning techniques. These methods have been incorporated into a workload estimation system based on two types: feature-level and decision-level combinations. The results indicated the reliability of the method for automatic and real-time inference of psychological states. This method provided a quantitative estimation of the workload levels and a bias-free evaluation approach. The high-average accuracy of 90% and cost effective requirement were the two important attributes of the proposed workload estimation system. New entropic features were proved to be more sensitive measures for quantifying time and frequency changes in EDA. The effectiveness of these measures was also compared with conventional tonic EDA measures, demonstrating the superiority of the proposed method in achieving accurate estimation of workload levels.

Contribution of Somatic and Dendritic SK Channels in the Firing Rate of Deep Cerebellar Nuclei: Implication in Cerebellar Ataxia.

INTRODUCTION: Loss of inhibitory output from Purkinje cells leads to hyperexcitability of the Deep Cerebellar Nuclei (DCN), which results in cerebellar ataxia. Also, inhibition of small-conductance calcium-activated potassium (SK) channel increases firing rate of DCN, which could cause cerebellar ataxia. Therefore, SK channel activators can be effective in reducing the symptoms of this disease, and used for the treatment of cerebellar ataxia. In this regard, we hypothesized that blockade of SK channels in different compartments of DCN would increase firing rate with different value. The location of these channels has different effects on increasing firing rate. METHODS: In this study, multi-compartment computational model of DCN was used. This computational stimulation allowed us to study the changes in the firing activity of DCN neuron without concerns about interfering parameters in the experiment. RESULTS: The simulation results demonstrated that blockade of somatic and dendritic SK channel increased the firing rate of DCN. In addition, after hyperpolarization (AHP) amplitude increased with blocking SK channel, and its regularity and resting potential changed. However, action potentials amplitude and duration had no significant changes. The simulation results illustrated a more significant contribution of SK channels on the dendritic tree to the DCN firing rate. SK channels in the proximal dendrites have more impact on firing rate compared to distal dendrites. DISCUSSION: Therefore, inhibition of SK channel in DCN can cause cerebellar ataxia, and SK channel openers can have a therapeutic effect on cerebellar ataxia. In addition, the location of SK channels could be important in therapeutic goals. Dendritic SK channels can be a more effective target compared to somatic SK channels.

Evaluating Autonomic Parameters: The Role of Sleep Duration in Emotional Responses to Music .

OBJECTIVE: It has been recognized that sleep has an important effect on emotion processing. The aim of this study was to investigate the effect of previous night sleep duration on autonomic responses to musical stimuli in different emotional contexts. METHOD: A frequency based measure of GSR, PR and ECG signals were examined in 35 healthy students in three groups of oversleeping, lack of sleep and normal sleep. RESULTS: The results of this study revealed that regardless of the emotional context of the musical stimuli (happy, relax, fear, and sadness), there was an increase in the maximum power of GSR, ECG and PR during the music time compared to the rest time in all the three groups. In addition, the higher value of these measures was achieved while the participants listened to relaxing music. Statistical analysis of the extracted features between each pair of emotional states revealed that the most significant differences were attained for ECG signals. These differences were more obvious in the participants with normal sleeping (p<10-18). The higher value of the indices has been shown, comparing long sleep duration with the normal one. CONCLUSION: There was a strong relation between emotion and sleep duration, and this association can be observed by means of the ECG signals. .

Combination of sLORETA and Nonlinear Coupling for Emotional EEG Source Localization.

The objective of the present study is to investigate the anatomical distribution of the cortical sources of emotional response to music videos by means of electroencephalogram (EEG) analysis. A novel methodology is introduced to determine the nonlinear couplings between different brain regions based on the coherence analysis, nonlinear features of EEG recordings and a source localization method, standard low resolution electromagnetic tomography (sLORETA). 32 channels of EEG time series of 32 subjects available in DEAP database were studied. The Lyapunov exponents and approximate entropy were applied to the EEG. The coherence for Lyapunov exponents and approximate entropy were calculated between each electrode paired to all other electrodes. Considering valence and arousal related effects, the sLORETA was applied to each above mentioned feature to determine emotional processing cortices. Using the proposed methodology, significant differences in sLORETA activity are observed between different emotional states. These changes were dominantly localized in the Brodmann 11 area (frontal lobe). In addition, some evidences provided that the left hemisphere is more activated to valence and arousal-related effects. Results suggest that considering two dimensions of emotions concurrently, a wider brain region was dominated in synchronization: superior frontal gyrus, middle frontal gyrus, and superior parietal lobule. Cooperating nonlinear coupling along with EEG source localization methods could provide an interesting tool for understanding the cortical specialization in emotional processes.

Affective Visual Stimuli: Characterization of the Picture Sequences Impacts by Means of Nonlinear Approaches.

INTRODUCTION: The main objective of the present study was to investigate the effect of preceding pictorial stimulus on the emotional autonomic responses of the subsequent one. METHODS: To this effect, physiological signals, including Electrocardiogram (ECG), Pulse Rate (PR), and Galvanic Skin Response (GSR) were collected. As these signals have random and chaotic nature, nonlinear dynamics of these physiological signals were evaluated with the methods of nonlinear system theory. Considering the hypothesis that emotional responses are usually associated with previous experiences of a subject, the subjective ratings of 4 emotional states were also evaluated. Four nonlinear characteristics (including Detrended Fluctuation Analysis (DFA), based parameters, Lyapunov exponent, and approximate entropy) were implemented. Nine standard features (including mean, standard deviation, minimum, maximum, median, mode, the second, third, and fourth moment) were also extracted. RESULTS: To evaluate the ability of features in discriminating different types of emotions, some classification approaches were appraised, of them, Probabilistic Neural Network (PNN) led to the best classification rate of 100%. The results show that considering the emotional sequences, GSR is the best candidate for the representation of the physiological changes. DISCUSSION: Lower discrimination was attained when the sequence occurred in the diagonal line of valence-arousal coordinates (for instance, positive valence and positive arousal versus negative valence and negative arousal). By employing self-assessment ranks, no obvious improvement was achieved.

An efficient seizure prediction method using KNN-based undersampling and linear frequency measures.

Seizure prediction based on analysis of electroencephalogram signals has generated considerable research interests. A reliable seizure prediction algorithm with minimal computational requirements is prominent issue for medical facilities; however, it has not been addressed correctly. In this study, an optimized novel method is proposed in order to remove computational complexity, and predict epileptic seizures clinically. It is based on the univariate linear features in eight frequency sub-bands. It also employs principal component analysis (PCA) for dimension reduction and optimal feature selection. Class unbalanced problem is tackled by K-nearest neighbor (KNN)-based undersampling combined with support vector machine (SVM) classifier. To find out the best results two types of postprocessing methods were studied. The proposed algorithm was evaluated on seizures and 434.9h of interictal data from 18 patients of Freiburg database. It predicted 100% of seizures with average false alarm rate of 0.13 per hour ranging between 0 and 0.39. Furthermore, G-Mean and F-measure were used for validation which were 0.97 and 0.90, respectively. These results confirmed the discriminative ability of the algorithm. In comparison with other studies, the proposed method improves trade-off between sensitivity and false prediction rate with linear features and low computational requirements and it can potentially be employed in implantable devices. Achieving high performance by linear features, PCA, KNN-based undersampling, and SVM demonstrates that this method can potentially be used in implantable devices.

Introducing treatment strategy for cerebellar ataxia in mutant med mice: combination of acetazolamide and 4-aminopyridine.

Purkinje neurons are the sole output neuron of the cerebellar cortex, and they generate high-frequency action potentials. Electrophysiological dysfunction of Purkinje neurons causes cerebellar ataxia. Mutant med mice have the lack of expression of the Scn8a gene. This gene encodes the NaV1.6 protein. In med Purkinje neurons, regular high-frequency firing is slowed, and med mice are ataxic. The aim of this study was to propose the neuroprotective drugs which could be useful for ataxia treatment in med mice, and to investigate the neuroprotective effects of these drugs by simulation. Simulation results showed that Kv4 channel inhibitors and BK channel activators restored the normal electrophysiological properties of the med Purkinje neurons. 4-Aminopyridine (4-AP) and acetazolamide (ACTZ) were proposed as neuroprotective drugs for Kv4 channel inhibitor and BK channel activator, respectively.