Multi-Kernel Temporal and Spatial Convolution for EEG-Based Emotion Classification.

Deep learning using an end-to-end convolutional neural network (ConvNet) has been applied to several electroencephalography (EEG)-based brain-computer interface tasks to extract feature maps and classify the target output. However, the EEG analysis remains challenging since it requires consideration of various architectural design components that influence the representational ability of extracted features. This study proposes an EEG-based emotion classification model called the multi-kernel temporal and spatial convolution network (MultiT-S ConvNet). The multi-scale kernel is used in the model to learn various time resolutions, and separable convolutions are applied to find related spatial patterns. In addition, we enhanced both the temporal and spatial filters with a lightweight gating mechanism. To validate the performance and classification accuracy of MultiT-S ConvNet, we conduct subject-dependent and subject-independent experiments on EEG-based emotion datasets: DEAP and SEED. Compared with existing methods, MultiT-S ConvNet outperforms with higher accuracy results and a few trainable parameters. Moreover, the proposed multi-scale module in temporal filtering enables extracting a wide range of EEG representations, covering short- to long-wavelength components. This module could be further implemented in any model of EEG-based convolution networks, and its ability potentially improves the model's learning capacity.

Learning Subject-Generalized Topographical EEG Embeddings Using Deep Variational Autoencoders and Domain-Adversarial Regularization.

Two of the biggest challenges in building models for detecting emotions from electroencephalography (EEG) devices are the relatively small amount of labeled samples and the strong variability of signal feature distributions between different subjects. In this study, we propose a context-generalized model that tackles the data constraints and subject variability simultaneously using a deep neural network architecture optimized for normally distributed subject-independent feature embeddings. Variational autoencoders (VAEs) at the input level allow the lower feature layers of the model to be trained on both labeled and unlabeled samples, maximizing the use of the limited data resources. Meanwhile, variational regularization encourages the model to learn Gaussian-distributed feature embeddings, resulting in robustness to small dataset imbalances. Subject-adversarial regularization applied to the bi-lateral features further enforces subject-independence on the final feature embedding used for emotion classification. The results from subject-independent performance experiments on the SEED and DEAP EEG-emotion datasets show that our model generalizes better across subjects than other state-of-the-art feature embeddings when paired with deep learning classifiers. Furthermore, qualitative analysis of the embedding space reveals that our proposed subject-invariant bi-lateral variational domain adversarial neural network (BiVDANN) architecture may improve the subject-independent performance by discovering normally distributed features.

A Comparative Study of Window Size and Channel Arrangement on EEG-Emotion Recognition Using Deep CNN.

Emotion recognition based on electroencephalograms has become an active research area. Yet, identifying emotions using only brainwaves is still very challenging, especially the subject-independent task. Numerous studies have tried to propose methods to recognize emotions, including machine learning techniques like convolutional neural network (CNN). Since CNN has shown its potential in generalization to unseen subjects, manipulating CNN hyperparameters like the window size and electrode order might be beneficial. To our knowledge, this is the first work that extensively observed the parameter selection effect on the CNN. The temporal information in distinct window sizes was found to significantly affect the recognition performance, and CNN was found to be more responsive to changing window sizes than the support vector machine. Classifying the arousal achieved the best performance with a window size of ten seconds, obtaining 56.85% accuracy and a Matthews correlation coefficient (MCC) of 0.1369. Valence recognition had the best performance with a window length of eight seconds at 73.34% accuracy and an MCC value of 0.4669. Spatial information from varying the electrode orders had a small effect on the classification. Overall, valence results had a much more superior performance than arousal results, which were, perhaps, influenced by features related to brain activity asymmetry between the left and right hemispheres.

Warmer Environments Increase Implicit Mental Workload Even If Learning Efficiency Is Enhanced.

Climate change is one of the most important issues for humanity. To defuse this problem, it is considered necessary to improve energy efficiency, make energy sources cleaner, and reduce energy consumption in urban areas. The Japanese government has recommended an air conditioner setting of 28°C in summer and 20°C in winter since 2005. The aim of this setting is to save energy by keeping room temperatures constant. However, it is unclear whether this is an appropriate temperature for workers and students. This study examined whether thermal environments influence task performance over time. To examine whether the relationship between task performance and thermal environments influences the psychological states of participants, we recorded their subjective rating of mental workload along with their working memory score, electroencephalogram (EEG), heart rate variability, skin conductance level (SCL), and tympanum temperature during the task and compared the results among different conditions. In this experiment, participants were asked to read some texts and answer questions related to those texts. Room temperature (18, 22, 25, or 29°C) and humidity (50%) were manipulated during the task and participants performed the task at these temperatures. The results of this study showed that the temporal cost of task and theta power of EEG, which is an index for concentration, decreased over time. However, subjective mental workload increased with time. Moreover, the low frequency to high frequency ratio and SCL increased with time and heat (25 and 29°C). These results suggest that mental workload, especially implicit mental workload, increases in warmer environments, even if learning efficiency is facilitated. This study indicates integrated evidence for relationships among task performance, psychological state, and thermal environment by analyzing behavioral, subjective, and physiological indexes multidirectionally.

Statistical sleep pattern modelling for sleep quality assessment based on sound events.

A good sleep is important for a healthy life. Recently, several consumer sleep devices have emerged on the market claiming that they can provide personal sleep monitoring; however, many of them require additional hardware or there is a lack of scientific evidence regarding their reliability. In this paper we proposed a novel method to assess the sleep quality through sound events recorded in the bedroom. We used subjective sleep quality as training label, combined several machine learning approaches including kernelized self organizing map, hierarchical clustering and hidden Markov model, obtained the models to indicate the sleep pattern of specific quality level. The proposed method is different from traditional sleep stage based method, provides a new aspect of sleep monitoring that sound events are directly correlated with the sleep of a person.

Personal sleep pattern visualization using sequence-based kernel self-organizing map on sound data.

We propose a method to discover sleep patterns via clustering of sound events recorded during sleep. The proposed method extends the conventional self-organizing map algorithm by kernelization and sequence-based technologies to obtain a fine-grained map that visualizes the distribution and changes of sleep-related events. We introduced features widely applied in sound processing and popular kernel functions to the proposed method to evaluate and compare performance. The proposed method provides a new aspect of sleep monitoring because the results demonstrate that sound events can be directly correlated to an individual's sleep patterns. In addition, by visualizing the transition of cluster dynamics, sleep-related sound events were found to relate to the various stages of sleep. Therefore, these results empirically warrant future study into the assessment of personal sleep quality using sound data.

Familiarity effects in EEG-based emotion recognition.

Although emotion detection using electroencephalogram (EEG) data has become a highly active area of research over the last decades, little attention has been paid to stimulus familiarity, a crucial subjectivity issue. Using both our experimental data and a sophisticated database (DEAP dataset), we investigated the effects of familiarity on brain activity based on EEG signals. Focusing on familiarity studies, we allowed subjects to select the same number of familiar and unfamiliar songs; both resulting datasets demonstrated the importance of reporting self-emotion based on the assumption that the emotional state when experiencing music is subjective. We found evidence that music familiarity influences both the power spectra of brainwaves and the brain functional connectivity to a certain level. We conducted an additional experiment using music familiarity in an attempt to recognize emotional states; our empirical results suggested that the use of only songs with low familiarity levels can enhance the performance of EEG-based emotion classification systems that adopt fractal dimension or power spectral density features and support vector machine, multilayer perceptron or C4.5 classifier. This suggests that unfamiliar songs are most appropriate for the construction of an emotion recognition system.

Effects of individual health topic familiarity on activity patterns during health information searches.

BACKGROUND: Non-medical professionals (consumers) are increasingly using the Internet to support their health information needs. However, the cognitive effort required to perform health information searches is affected by the consumer's familiarity with health topics. Consumers may have different levels of familiarity with individual health topics. This variation in familiarity may cause misunderstandings because the information presented by search engines may not be understood correctly by the consumers. OBJECTIVE: As a first step toward the improvement of the health information search process, we aimed to examine the effects of health topic familiarity on health information search behaviors by identifying the common search activity patterns exhibited by groups of consumers with different levels of familiarity. METHODS: Each participant completed a health terminology familiarity questionnaire and health information search tasks. The responses to the familiarity questionnaire were used to grade the familiarity of participants with predefined health topics. The search task data were transcribed into a sequence of search activities using a coding scheme. A computational model was constructed from the sequence data using a Markov chain model to identify the common search patterns in each familiarity group. RESULTS: Forty participants were classified into L1 (not familiar), L2 (somewhat familiar), and L3 (familiar) groups based on their questionnaire responses. They had different levels of familiarity with four health topics. The video data obtained from all of the participants were transcribed into 4595 search activities (mean 28.7, SD 23.27 per session). The most frequent search activities and transitions in all the familiarity groups were related to evaluations of the relevancy of selected web pages in the retrieval results. However, the next most frequent transitions differed in each group and a chi-squared test confirmed this finding (P<.001). Next, according to the results of a perplexity evaluation, the health information search patterns were best represented as a 5-gram sequence pattern. The most common patterns in group L1 were frequent query modifications, with relatively low search efficiency, and accessing and evaluating selected results from a health website. Group L2 performed frequent query modifications, but with better search efficiency, and accessed and evaluated selected results from a health website. Finally, the members of group L3 successfully discovered relevant results from the first query submission, performed verification by accessing several health websites after they discovered relevant results, and directly accessed consumer health information websites. CONCLUSIONS: Familiarity with health topics affects health information search behaviors. Our analysis of state transitions in search activities detected unique behaviors and common search activity patterns in each familiarity group during health information searches.