EEG-Based Emotion Classification for Verifying the Korean Emotional Movie Clips with Support Vector Machine (SVM)

Emotion plays a crucial role in understanding each other under natural communication in daily life. Electroencephalogram (EEG), based on emotion classification, has been widely utilized in the fields of interdisciplinary studies because of emotion representation’s objectiveness. In this paper, it aimed to introduce the Korean continuous emotional database and investigate brain activity during emotional processing. Moreover, we selected emotion-related channels for verifying the generated database using the Support Vector Machine (SVM). First, we recorded EEG signals, collected from 28 subjects, to investigate the brain activity across brain areas while watching movie clips by five emotions (anger, excitement, fear, sadness, and happiness) and a neutral state. We analyzed EEG raw signals to investigate the emotion-related brain area and select suitable emotion-related channels using spectral power across frequency bands, i.e., alpha and beta bands. As a result, we select the eight-channel set, namely, AF3-AF4, F3-F4, F7-F8, and P7-P8, from statistical and brain topography analysis. We perform the classification using SVM and achieve the best accuracy of 94.27% when utilizing the selected channels set with five emotions. In conclusion, we provide a fundamental emotional database reflecting Korean feelings and the evidence of different emotions for application to broaden area.

A hybrid deep neural network for classification of schizophrenia using EEG Data

Schizophrenia is a serious mental illness that causes great harm to patients, so timely and accurate detection is essential. This study aimed to identify a better feature to represent electroencephalography (EEG) signals and improve the classification accuracy of patients with schizophrenia and healthy controls by using EEG signals. Our research method involves two steps. First, the EEG time series is preprocessed, and the extracted time-domain and frequency-domain features are transformed into a sequence of red–green–blue (RGB) images that carry spatial information. Second, we construct hybrid deep neural networks (DNNs) that combine convolution neural networks and long short-term memory to address RGB images to classify schizophrenic patients and healthy controls. The results show that the fuzzy entropy (FuzzyEn) feature is more significant than the fast Fourier transform (FFT) feature in brain topography. The deep learning (DL) method that we propose achieves an average accuracy of 99.22% with FuzzyEn and an average accuracy of 96.34% with FFT. These results show that the best effect is to extract fuzzy features as input features from EEG time series and then use a hybrid DNN for classification. Compared with the most advanced methods in this field, significant improvements have been achieved.

Phineas Gage's great legacy

ABSTRACT. The case of Phineas Gage is an integral part of medical folklore. His accident still causes astonishment and curiosity and can be considered as the case that most influenced and contributed to the nineteenth century's neuropsychiatric discussion on the mind-brain relationship and brain topography. It was perhaps the first case to suggest the role of brain areas in determining personality and which specific parts of the brain, when affected, can induce specific mental changes. In addition, his case contributed to the emergence of the scientific approaches that would later culminate in psychosurgery. Gage is a fixed element in the studies of neurology, psychology, and neuroscience, having been solidified as one of the greatest medical curiosities of all time, deserving its prominence.

0354 Age-Related Spectral Changes in NREM And REM Sleep in Mice are Global and Not Local

Introduction Brain topography modulates age-related changes in the human sleep electroencephalogram, which are linked with differences in integrity of specific cortical areas and may reflect local changes in sleep homeostasis. In mice, there is conflicting evidence regarding the topography of age-related changes for NREM and REM sleep. To disambiguate this issue, we investigated in mice the topography of age-related spectral differences for REM and NREM sleep. Methods LFP electrodes were implanted in 5 cortical areas and in the hippocampus of 17 C57/BL6 mice (8 young and 9 old, mean age = 7.5 and 16 months). Mice LFPs were recorded for a week and states of vigilance were semi-automatically detected in light and dark periods (12h-12h). Spectral analysis was run on 4s windows. Values were averaged for each electrode and in each period of the light/dark cycle in REM/NREM sleep for slow delta (0.25-2Hz), delta (2-4Hz), theta (4-8Hz), sigma (10-16Hz) and ripples (150-200Hz). Mixed models were computed separately for REM and NREM in dark and light period, with age as group factor and electrode and frequency as repeated factors. Results Two-way interactions were found between age and frequency and between electrode and frequency, for NREM and REM in dark and light periods. Each frequency band, except ripples, showed a topographical signature in NREM and REM (e.g. higher power in anterior compared to posterior areas for delta band in NREM sleep). These relative patterns did not change in older mice, but global changes occurred on all electrodes: in older mice, delta power was globally higher in NREM and REM sleep whereas sigma power was lower in REM sleep. Conclusion Age-related changes in spectral power of sleeping mice do not vary according to brain topography as in humans. Sleep deprivation studies are needed to investigate whether age is associated with global changes in sleep homeostasis in mice. Support This work has been supported by the Quebec Fonds de Recherche Nature et Technologies (FQRNT).

“Plis de passage” Deserve a Role in Models of the Cortical Folding Process

Cortical folding is a hallmark of brain topography whose variability across individuals remains a puzzle. In this paper, we call for an effort to improve our understanding of the pli de passage phenomenon, namely annectant gyri buried in the depth of the main sulci. We suggest that plis de passage could become an interesting benchmark for models of the cortical folding process. As an illustration, we speculate on the link between modern biological models of cortical folding and the development of the Pli de Passage Frontal Moyen (PPFM) in the middle of the central sulcus. For this purpose, we have detected nine interrupted central sulci in the Human Connectome Project dataset, which are used to explore the organization of the hand sensorimotor areas in this rare configuration of the PPFM.

Predicting aging of brain metabolic topography using variational autoencoder

Predicting future brain topography can give insight into neural correlates of aging and neurodegeneration. Due to variability in aging process, it has been challenging to precisely estimate brain topographical change according to aging. Here, we predict age-related brain metabolic change by generating future brain 18F-Fluorodeoxyglucose PET. A cross-sectional PET dataset of cognitively normal subjects with different age was used to develop a generative model. The model generated PET images using age information and characteristic individual features. Predicted regional metabolic changes were correlated with the real changes obtained by follow-up data. This model was applied to produce a brain metabolism aging movie by generating PET at different ages. Normal population distribution of brain metabolic topography at each age was estimated as well. In addition, a generative model using APOE4 status as well as age as inputs revealed a significant effect of APOE4 status on age-related metabolic changes particularly in the calcarine, lingual cortex, hippocampus and amygdala. It suggested APOE4 could be a factor affecting individual variability in age-related metabolic degeneration in normal elderly. This predictive model may not only be extended to understanding cognitive aging process, but apply to development of a preclinical biomarker for various brain disorders.