Manifold Feature Fusion with Dynamical Feature Selection for Cross-Subject Emotion Recognition

Affective computing systems can decode cortical activities to facilitate emotional human–computer interaction. However, personalities exist in neurophysiological responses among different users of the brain–computer interface leads to a difficulty for designing a generic emotion recognizer that is adaptable to a novel individual. It thus brings an obstacle to achieve cross-subject emotion recognition (ER). To tackle this issue, in this study we propose a novel feature selection method, manifold feature fusion and dynamical feature selection (MF-DFS), under transfer learning principle to determine generalizable features that are stably sensitive to emotional variations. The MF-DFS framework takes the advantages of local geometrical information feature selection, domain adaptation based manifold learning, and dynamical feature selection to enhance the accuracy of the ER system. Based on three public databases, DEAP, MAHNOB-HCI and SEED, the performance of the MF-DFS is validated according to the leave-one-subject-out paradigm under two types of electroencephalography features. By defining three emotional classes of each affective dimension, the accuracy of the MF-DFS-based ER classifier is achieved at 0.50–0.48 (DEAP) and 0.46–0.50 (MAHNOBHCI) for arousal and valence emotional dimensions, respectively. For the SEED database, it achieves 0.40 for the valence dimension. The corresponding accuracy is significantly superior to several classical feature selection methods on multiple machine learning models.

Invariant timescale hierarchy across the cortical somatosensory network

The ability of cortical networks to integrate information from different sources is essential for cognitive processes. On one hand, sensory areas exhibit fast dynamics often phase-locked to stimulation; on the other hand, frontal lobe areas with slow response latencies to stimuli must integrate and maintain information for longer periods. Thus, cortical areas may require different timescales depending on their functional role. Studying the cortical somatosensory network while monkeys discriminated between two vibrotactile stimulus patterns, we found that a hierarchical order could be established across cortical areas based on their intrinsic timescales. Further, even though subareas (areas 3b, 1, and 2) of the primary somatosensory (S1) cortex exhibit analogous firing rate responses, a clear differentiation was observed in their timescales. Importantly, we observed that this inherent timescale hierarchy was invariant between task contexts (demanding vs. nondemanding). Even if task context severely affected neural coding in cortical areas downstream to S1, their timescales remained unaffected. Moreover, we found that these time constants were invariant across neurons with different latencies or coding. Although neurons had completely different dynamics, they all exhibited comparable timescales within each cortical area. Our results suggest that this measure is demonstrative of an inherent characteristic of each cortical area, is not a dynamical feature of individual neurons, and does not depend on task demands.

Non-linear dynamical feature of center of pressure extracted by approximate entropy in people with various stages of Parkinson’s Disease

Introduction : Postural instability, one of the most important features of Parkinson’s Disease (PD), is associated with increased falls and loss of independence in these population. It is postulated the abilities of individuals to adjust to environmental perturbation for postural control is different in various stages of PD. The aim of current study is to investigate the non-linear dynamical feature of COP in various stages of PD and in different environmental challenges. Method : 38 persons with PD (mild PD =19, moderate PD =6 and sever PD =13) and 33 healthy aged, gender, weight and height matched subjects were asked to stand on force plate in four test conditions included: 1) Rigid Surface with Opened Eyes, 2) Rigid Surface with Closed Eyes, 3) Foam Surface with Opened Eyes, and 4) Foam Surface with Closed Eyes. COP velocity and Approximate Entropy (ApEn) in both Anteroposterior (AP)/Mediolateral (ML) directions were calculated. A Mixed ANOVA 4*2*2 (Group*Vision*Surface) test was applied for statistical analysis . Results : Both COP velocity and COP ML ApEn were significantly higher in participants with PD in comparison to healthy individuals. Moreover, COP ML ApEn increased by eye closure in all studied groups but the amount of this increase was lesser in PD groups. For COP velocity, vision, surface and group interaction was significant in all directions (P ≤ 0.016). For COP ApEn, vision, surface and group interaction (P = 0.002) were statistically meaningful in only ML direction. Conclusion : Balance system irregularity is more in people with PD compared to healthy matched individuals. In addition, their adaptive capacity of the postural control system in response to environmental perturbation is reduced. PD induced complexity of the postural control system is associated with the loss of adaptive behavior that is organized over the confluence of constraints of the individual, environment and task.

Dynamical feature extraction at the sensory periphery guides chemotaxis

Behavioral strategies employed for chemotaxis have been described across phyla, but the sensorimotor basis of this phenomenon has seldom been studied in naturalistic contexts. Here, we examine how signals experienced during free olfactory behaviors are processed by first-order olfactory sensory neurons (OSNs) of the Drosophila larva. We find that OSNs can act as differentiators that transiently normalize stimulus intensity—a property potentially derived from a combination of integral feedback and feed-forward regulation of olfactory transduction. In olfactory virtual reality experiments, we report that high activity levels of the OSN suppress turning, whereas low activity levels facilitate turning. Using a generalized linear model, we explain how peripheral encoding of olfactory stimuli modulates the probability of switching from a run to a turn. Our work clarifies the link between computations carried out at the sensory periphery and action selection underlying navigation in odor gradients.

Statistical Discriminability Estimation for Pattern Classification Based on Neural Incremental Attribute Learning

Feature ordering is a significant data preprocessing method in Incremental Attribute Learning (IAL), a novel machine learning approach which gradually trains features according to a given order. Previous research has shown that, similar to feature selection, feature ordering is also important based on each feature's discrimination ability, and should be sorted in a descending order of their discrimination ability. However, such an ordering is crucial for the performance of IAL. As the number of feature dimensions in IAL is increasing, feature discrimination ability also should be calculated in the corresponding incremental way. Based on Single Discriminability (SD), where only the feature discrimination ability is computed, a new filter statistical feature discrimination ability predictive metric, called the Accumulative Discriminability (AD), is designed for the dynamical feature discrimination ability estimation. Moreover, a criterion that summarizes all the produced values of AD is employed with a GA (Genetic Algorithm)-based approach to obtain the optimum feature ordering for classification problems based on neural networks by means of IAL. Compared with the feature ordering obtained by other approaches, the method proposed in this paper exhibits better performance in the final classification results. Such a phenomenon indicates that, (i) the feature discrimination ability should be incrementally estimated in IAL, and (ii) the feature ordering derived by AD and its corresponding approaches are applicable with IAL.