Vitaliy Kolodyazhniy

An affective computing approach to physiological emotion specificity: Toward subject-independent and stimulus-independent classification of film-induced emotions

The hypothesis of physiological emotion specificity has been tested using pattern classification analysis (PCA). To address limitations of prior research using PCA, we studied effects of feature selection (sequential forward selection, sequential backward selection), classifier type (linear and quadratic discriminant analysis, neural networks, k-nearest neighbors method), and cross-validation method (subject- and stimulus-(in)dependence). Analyses were run on a data set of 34 participants watching two sets of three 10-min film clips (fearful, sad, neutral) while autonomic, respiratory, and facial muscle activity were assessed. Results demonstrate that the three states can be classified with high accuracy by most classifiers, with the sparsest model having only five features, even for the most difficult task of identifying the emotion of an unknown subject in an unknown situation (77.5%). Implications for choosing PCA parameters are discussed.

Estimation of human circadian phase via a multi-channel ambulatory monitoring system and a multiple regression model

Reliable detection of circadian phase in humans using noninvasive ambulatory measurements in real-life conditions is challenging and still an unsolved problem. The masking effects of everyday behavior and environmental input such as physical activity and light on the measured variables need to be considered critically. Here, we aimed at developing techniques for estimating circadian phase with the lowest subject burden possible, that is, without the need of constant routine (CR) laboratory conditions or without measuring the standard circadian markers, (rectal) core body temperature (CBT), and melatonin levels. In this validation study, subjects (N = 16) wore multi-channel ambulatory monitoring devices and went about their daily routine for 1 week. The devices measured a large number of physiological, behavioral, and environmental variables, including CBT, skin temperatures, cardiovascular and respiratory function, movement/posture, ambient temperature, and the spectral composition and intensity of light received at eye level. Sleep diaries were logged electronically. After the ambulatory phase, subjects underwent a 32-h CR procedure in the laboratory for measuring unmasked circadian phase based on the “midpoint” of the salivary melatonin profile. To overcome the complex masking effects of confounding variables during ambulatory measurements, multiple regression techniques were applied in combination with the cross-validation approach to subject-independent prediction of circadian phase. The most accurate estimate of circadian phase was achieved using skin temperatures, irradiance for ambient light in the blue spectral band, and motion acceleration as predictors with lags of up to 24 h. Multiple regression showed statistically significant improvement of variance of prediction error over the traditional approaches to determining circadian phase based on single predictors (motion acceleration or sleep log), although CBT was intentionally not included as the predictor. Compared to CBT alone, our method resulted in a 40% smaller range of prediction errors and a nonsignificant reduction of error variance. The proposed noninvasive measurement method could find applications in sleep medicine or in other domains where knowing the exact endogenous circadian phase is important (e.g., for the timing of light therapy).

An Improved Method for Estimating Human Circadian Phase Derived From Multichannel Ambulatory Monitoring and Artificial Neural Networks

Recently, we developed a novel method for estimating human circadian phase with noninvasive ambulatory measurements combined with subject-independent multiple regression models and a curve-fitting approach. With this, we were able to estimate circadian phase under real-life conditions with low subject burden, i.e., without need of constant routine (CR) laboratory conditions, and without measuring standard circadian markers, such as core body temperature (CBT) or pineal hormone melatonin rhythms. The precision of ambulatory-derived estimated circadian phase was within an error of 12 ± 41 min (mean ± SD) in comparison to melatonin phase during a CR protocol. The physiological measures could be reduced to a triple combination: skin temperatures, irradiance in the blue spectral band of ambient light, and motion acceleration. Here, we present a nonlinear regression model approach based on artificial neural networks for a larger data set (25 healthy young males), including both the original data and additional data collected in the same protocol and using the same equipment. Throughout our validation study, subjects wore multichannel ambulatory monitoring devices and went about their daily routine for 1 wk. The devices collected a large number of physiological, behavioral, and environmental variables, including CBT, skin temperatures, cardiovascular and respiratory functions, movement/posture, ambient temperature, spectral composition and intensity of light perceived at eye level, and sleep logs. After the ambulatory phase, study volunteers underwent a 32-h CR protocol in the laboratory for measuring unmasked circadian phase (i.e., “midpoint” of the nighttime melatonin rhythm). To overcome the complex masking effects of many different confounding variables during ambulatory measurements, neural network–based nonlinear regression techniques were applied in combination with the cross-validation approach to subject-independent prediction of circadian phase. The most accurate estimate of circadian phase with a prediction error of −3 ± 23 min (mean ± SD) was achieved using only two types of the measured variables: skin temperatures and irradiance for ambient light in the blue spectral band. Compared to our previous linear multiple regression modeling approach, motion acceleration data can be excluded and prediction accuracy, nevertheless, improved. Neural network regression showed statistically significant improvement of variance of prediction error over traditional approaches in determining circadian phase based on single predictors (CBT, motion acceleration, or sleep logs), even though none of these variables was included as predictor. We, therefore, have identified two sets of noninvasive measures that, combined with the prediction model, can provide researchers and clinicians with a precise measure of internal time, in spite of the masking effects of daily behavior. This method, here validated in healthy young men, requires testing in a clinical or shiftwork population suffering from circadian sleep-wake disorders. (Author correspondence: vitaliy.kolodyazhniy@sbg.ac.at)

Insights into behavioral vulnerability to differential sleep pressure and circadian phase from a functional ADA polymorphism.

Sleep loss affects human behavior in a nonuniform manner, depending on the cognitive domain and also the circadian phase. Besides, evidence exists about stable interindividual variations in sleep loss–related performance impairments. Despite this evidence, only a few studies have considered both circadian phase and neurobehavioral domain when investigating trait-like vulnerability to sleep manipulation. By applying a randomized, crossover design with 2 sleep pressure conditions (40 h sleep deprivation vs. 40 h multiple naps), we investigated the influence of a human adenosine deaminase (ADA) polymorphism (rs73598374) on several behavioral measures throughout nearly 2 circadian cycles. Confirming earlier studies, we observed that under sleep deprivation the previously reported vulnerable G/A-allele carriers felt overall sleepier than G/G-allele carriers. As expected, this difference was no longer present when sleep pressure was reduced by the application of multiple naps. Concomitantly, well-being was worse in the G/A genotype under sleep loss when compared to the nap protocol, and n-back working memory performance appeared to be specifically susceptible to sleep-wake manipulation in this genotype. When considering psychomotor vigilance performance, however, a higher sensitivity to sleep-wake manipulation was detected in homozygous participants, but specifically at the end of the night and only for optimal task performance. Although these data are based on a small sample size and hence require replication (12 G/A- and 12 G/G-allele carriers), they confirm the assumption that interindividual differences regarding the effect of sleep manipulation highly depend on the cognitive task and circadian phase, and thus emphasize the necessity of a multimethodological approach. Moreover, they indicate that napping might be suitable to counteract endogenously heightened sleep pressure depending on the neurobehavioral domain.

Pre- to postsleep change in psychophysiological reactivity to emotional films: Late-night REM sleep is associated with attenuated emotional processing.

Rapid eye movement (REM) sleep has been postulated to facilitate emotional processing of negative stimuli. However, empirical evidence is mixed and primarily based on self-report data and picture-viewing studies. This study used a full-length aversive film to elicit intense emotion on one evening, and an emotionally neutral control film on another evening while psychophysiological and experiential responses were measured. Subsequent sleep was monitored polysomnographically, and specific film scenes were presented again on the next morning. Correlation analyses revealed that participants with longer late-night REM sleep after the aversive film showed higher increase of electrodermal reactivity and less reduction of facial corrugator muscle reactivity to negative film scenes on the next morning. This indicates that REM sleep may be associated with attenuated emotional processing of prolonged and intense emotional stimuli from pre- to postsleep.

Differential impact in young and older individuals of blue-enriched white light on circadian physiology and alertness during sustained wakefulness

We tested the effect of different lights as a countermeasure against sleep-loss decrements in alertness, melatonin and cortisol profile, skin temperature and wrist motor activity in healthy young and older volunteers under extendend wakefulness. 26 young [mean (SE): 25.0 (0.6) y)] and 12 older participants [(mean (SE): 63.6 (1.3) y)] underwent 40-h of sustained wakefulness during 3 balanced crossover segments, once under dim light (DL: 8 lx), and once under either white light (WL: 250 lx, 2,800 K) or blue-enriched white light (BL: 250 lx, 9,000 K) exposure. Subjective sleepiness, melatonin and cortisol were assessed hourly. Skin temperature and wrist motor activity were continuously recorded. WL and BL induced an alerting response in both the older (p = 0.005) and the young participants (p = 0.021). The evening rise in melatonin was attentuated under both WL and BL only in the young. Cortisol levels were increased and activity levels decreased in the older compared to the young only under BL (p = 0.0003). Compared to the young, both proximal and distal skin temperatures were lower in older participants under all lighting conditions. Thus the color temperature of normal intensity lighting may have differential effects on circadian physiology in young and older individuals.

A NEURO-FUZZY MODEL FOR DIMENSIONALITY REDUCTION AND ITS APPLICATION

A novel neuro-fuzzy approach to nonlinear dimensionality reduction is proposed. The approach is an auto-associative modification of the Neuro-Fuzzy Kolmogorovs Network (NFKN) with a “bottleneck” hidden layer. Two training algorithms are considered. The validity of theoretical results and the advantages of the proposed model are confirmed by an experiment in nonlinear principal component analysis and an application in the visualization of high-dimensional wastewater treatment plant data.

Attend or defend? Sex differences in behavioral, autonomic, and respiratory response patterns to emotion–eliciting films

Sex differences in emotional reactivity have been studied primarily for negative but less so for positive stimuli; likewise, sex differences in the psychophysiological response-patterning during such stimuli are poorly understood. Thus, the present study examined sex differences in response to negative/positive and high/low arousing films (classified as threat-, loss-, achievement-, and recreation-related, vs. neutral films), while measuring 18 muscular, autonomic, and respiratory parameters. Sex differences emerged for all films, but were most prominent for threat-related films: Despite equivalent valence and arousal ratings, women displayed more facial-muscular and respiratory responding than men and pronounced sympathetic activation (preejection period, other cardiovascular and electrodermal measures), while men showed coactivated sympathetic/parasympathetic responding (including increased respiratory sinus arrhythmia). This indicates a prototypical threat-related defense response in women, while men showed a pattern of sustained orienting, which can be understood as a shift toward less threat proximity in the defense cascade model. Clinical implications are discussed within a socio-evolutionary framework.

Metabolic decoupling in daily life in patients with panic disorder and agoraphobia

Various studies have assessed autonomic and respiratory underpinnings of panic attacks, yet the psychophysiological functioning of panic disorder (PD) patients has rarely been examined under naturalistic conditions at times when acute attacks were not reported. We hypothesized that emotional activation in daily life causes physiologically demonstrable deviations from efficient metabolic regulation in PD patients. Metabolic coupling was estimated as within-individual correlations between heart rate (HR) and indices of metabolic activity, i.e., physical activity (measured by 3-axial accelerometry, Acc), and minute ventilation (Vm, measured by calibrated inductive plethysmography, as proxy for oxygen consumption). A total of 565 daytime hours were recorded in 19 PD patients and 20 healthy controls (HC). Pairwise cross-correlations of minute-by-minute averages of these metabolic indices were calculated for each participant and then correlated with several indices of self-reported anxiety. Ambulatory HR was elevated in PD (p = .05, d = 0.67). Patients showed reduced HR-Acc (p < .006, d = 0.97) and HR-Vm coupling (p < .009, d = 0.91). Combining Vm and Acc to predict HR showed the strongest group separation (p < .002, d = 1.07). Discriminant analyses, based on the combination of Vm and Acc to predict HR, classified 77% of all participants correctly. In PD, HR-Acc coupling was inversely related to trait anxiety sensitivity, as well as tonic and phasic daytime anxiety. The novel method that was used demonstrates that anxiety in PD may reduce efficient long-term metabolic coupling. Metabolic decoupling may serve as physiological characteristic of PD and might aid diagnostics for PD and other anxiety disorders. This measure deserves further study in research on health consequences of anxiety and psychosocial stress.

Landscape multidimensional scaling

We revisit the problem of representing a high-dimensional data set by a distance-preserving projection onto a two-dimensional plane. This problem is solved by well-known techniques, such as multidimensional scaling. There, the data is projected onto a flat plane and the Euclidean metric is used for distance calculation. In real topographic maps, however, travel distance (or time) is not determined by (Euclidean) distance alone, but also influenced by map features such as mountains or lakes. We investigate how to utilize landscape features for a distance-preserving projection. A first approach with rectangular cylindrical mountains in the MDS landscape is presented.