EEG-based emotion estimation using adaptive tracking of discriminative frequency components.

EEG-based emotion recognition has received increasing attention in the past few decades. The frequency components that give effective discrimination between different emotion states are subject specific. Identification of these subject-specific discriminative frequency components (DFCs) is important for the accurate classification of emotional activities. This paper investigated the potential of adaptive tracking of DFCs as an effective method for choosing the discriminative bands of EEG patterns and improving emotion recognition performance. 13 healthy volunteers were emotionally elicited by pictures selected from the International Affective Picture System (IAPS). Discriminative frequency components were tracked and analyzed for each subject and classification of three emotions (pleasant/high arousal, neutral, unpleasant/high arousal) was performed by employing a Hidden Markov Model (HMM) and a Support Vector Machine (SVM). Our results showed that adaptive tracking of DFCs improved classification accuracies significantly and the highest average accuracy of 82.85% was achieved by SVM.

The timing of theta phase synchronization accords with vigilant attention.

Vigilant attention plays an important role in some industries and everyday life. However, its mechanism relating to phase synchronization of cortical oscillations is still unknown, which hinders the development of predicting and preventing vigilant attentional deficit. This study utilized psychomotor vigilance test (PVT) to elicit vigilance decrement. High and low levels of vigilant attention were represented by short and long reaction time, respectively. Electroencephalogram (EEG) was collected and phase synchronization between prefrontal and parietal cortices was analyzed by using debiased weighted phase lag index (dWPLI). The result suggests that vigilant attention of high level has earlier timing of theta (4-8Hz) phase synchronization, compared with that of low level. We concluded that phase synchronization may relate closely with the variation of vigilant attention.

Improve the generalization of emotional classifiers across time by using training samples from different days.

Electroencephalographic (EEG)-based emotion recognition has attracted increasing attention from the field of human-computer interaction (HCI). However, there are a number of challenges for machines to correctly recognize human emotional states. One problem is how to generalize the emotion model across time, since the brain may show different patterns of EEG for the same emotion experience at different time. This study investigated the feasibility of adding samples from different days to the training set to improve the generalization of the emotion classifier. Eight subjects participated in this experiment, and they were asked to watch different kinds of movie clips to produce neutral, positive or negative emotional states for different trials. Five sessions in five different days were conducted for each subject. EEG signals were recorded throughout the experiment. Support vector machine was used to perform a classification of the three emotional states, in which the training samples may come from 1, 2, 3 or 4 days' sessions but have a same number. The results showed that three categories were classified with average accuracies of 64.9%, 68.7%, 70.9%, and 73.0% respectively for 1-day, 2-day, 3-day and 4-day conditions. N-day condition represented the case in which data from N days were sent to train the SVM and the remaining 5-N days were used to form the testing set. Importantly, the accuracy had an increasing trend with the number of days in the training set for all subjects. Compared with 1-day condition, the accuracy of 4-day condition has about 10% improvement with a peak of 81.2% By analyzing the selected features in 4-day condition, we found the distributions of the selected features were relatively stable across days. The classifier did select emotion-relevant features and reject time-relevant features. These results suggested that incorporation of samples from different days to the training set could improve the generalization of an emotion classifier across time.

Cortical excitability effects of stimulation intensity change speed during NMES.

Rehabilitation method of motor dysfunction is a challenging issue of neural rehabilitation. Neuromuscular electrical stimulation (NMES) has been frequently used in rehabilitation therapy to improve neural recovery such as stroke and spinal cord injury. Stimulus, acting on sensorimotor neural system components, resulted in the increased cortical excitability which accompanied with motor performance improvement. Stimulus information conveyed by sensory system included below four elementary attributes: modality, location, intensity, and timing. But, few works has been reported about effect of the stimulation intensity change speed (SICS). In this paper, we studied the effects of SICS by event-related desynchronization (ERD) or event-related synchronization (ERS) and EEG source analysis by exact low resolution brain electric tomography (eLORETA). The results suggested that brain function areas were sensitive to SICS. Using fast SICS could evoked more significant cortical excitability than the slow one. We demonstrated the availability of an efficient NMES method, additionally implied the rehabilitation potential of cortical excitability enhancement in sensorimotor cortex for motor dysfunction.

Research on EEG features of attended & unattended vigilance.

Vigilance refers to the brain alertness to objective things, including the concentration of attention and the capability to response emergencies. It is of great importance to study vigilance monitoring to avoid accidents caused by decrease of vigilance. In this study, traditional Mackworth Clock Test (MCT) was modified to induce decline of attended and unattended vigilance. We analyzed EEG features in different levels of attended vigilance and assessed unattended vigilance by amplitude of mismatch negative (MMN) which can be evoked by audio odd ball stimulations. The results show that with attended vigilance going down, power of theta and alpha bands of electroencephalogram (EEG) increases and Lempel-Ziv Complexities (LZC) show an undulated decline tendency. And with unattended vigilance going down, amplitude of MMN reduces significantly. This research has great reference value for the further vigilance study.

Radiotherapy patients with identification study on continuous quality improvement / 中华放射肿瘤学杂志

Objective To study the recogniting patients identity for the safety and reliability of radiotherapy. Methods Through PDCA 4 footwork, namely, plan, do, check, action the technicians in the hospital to improve patients' identity verification.Results After 4 months of PDCA cycle,the patient identity verification qualified rate increase gradually,from 88.17% up to 99.07%,the privacy of patients satisfaction rate rose from 52. 69% to 98. 15%. The patients identification accuracy rate of 100%, technicians working efficiency has been greatly improved. Conclusions The measure of patient identification can improve the working process of radiotherapy for safety and efficiency and can get better privacy protection.

An online hybrid brain-computer interface combining multiple physiological signals for webpage browse.

The hybrid brain computer interface (hBCI) could provide higher information transfer rate than did the classical BCIs. It included more than one brain-computer or human-machine interact paradigms, such as the combination of the P300 and SSVEP paradigms. Research firstly constructed independent subsystems of three different paradigms and tested each of them with online experiments. Then we constructed a serial hybrid BCI system which combined these paradigms to achieve the functions of typing letters, moving and clicking cursor, and switching among them for the purpose of browsing webpages. Five subjects were involved in this study. They all successfully realized these functions in the online tests. The subjects could achieve an accuracy above 90% after training, which met the requirement in operating the system efficiently. The results demonstrated that it was an efficient system capable of robustness, which provided an approach for the clinic application.

Sample entropy analysis of EEG in ischemic stroke patients / 国际生物医学工程杂志

Objective To explore the nonlinear complexity characteristics of electroencephalogram (EEG) in ischemic stroke patients with different course. Methods Sample entropy of all bands of EEG signals in 20 ischemic stroke patients and 10 healthy controls was extracted and analyzed using statistical analysis methods. Results The full-band EEG in sample entropy of stroke patients was significantly lower than that of healthy controls in most locations. Theα-band sample entropy of different course had significant differences in the frontal, temporal and occipital lobe (P<0.05), and the parameters had significant negative linear correlation with the post-stroke time in some locations. Conclusions There is an abnormal neural electrical activity in post-stroke patients. It is feasible to detect the aberrant EEG complexity using sample entropy, which is worth of further research.

Research on Mental Fatigue Detecting Method Based on Sleep Deprivation Models / 生物医学工程学杂志

Mental fatigue is an important factor of human health and safety. It is important to achieve dynamic mental fatigue detection by using electroencephalogram (EEG) signals for fatigue prevention and job performance improvement. We in our study induced subjects' mental fatigue with 30 h sleep deprivation (SD) in the experiment. We extracted EEG features, including relative power, power ratio, center of gravity frequency (CGF), and basic relative power ratio. Then we built mental fatigue prediction model by using regression analysis. And we conducted lead optimization for prediction model. Result showed that R2 of prediction model could reach to 0.932. After lead optimization, 4 leads were used to build prediction model, in which R' could reach to 0.811. It can meet the daily applicatioi accuracy of mental fatigue prediction.

Brain Vigilance Analysis Based on the Measure of Complexity / 生物医学工程学杂志

Vigilance is defined as the ability to maintain attention for prolonged periods of time. In order to explore the variation of brain vigilance in work process, we designed addition and subtraction experiment with numbers of three digits to induce the vigilance to change, combined it with psychomotor vigilance task (PVT) to measure this process of electroencephalogram (EEG), extracted and analyzed permutation entropy (PE) of 11 cases of subjects' EEG and made a brief comparison with nonlinear parameter sample entropy (SE). The experimental results showed that: PE could well reflect the dynamic changes of EEG when vigilance decreases, and has advantages of fast arithmetic speed, high noise immunity, and low requirements for EEG length. This can be used as a measure of the brain vigilance indicators.

Research Progress on the Interaction Effects and Its Neural Mechanisms between Physical Fatigue and Mental Fatigue / 生物医学工程学杂志

Fatigue is an exhaustion state caused by prolonged physical work and mental work, which can reduce working efficiency and even cause industrial accidents. Fatigue is a complex concept involving both physiological and psychological factors. Fatigue can cause a decline of concentration and work performance and induce chronic diseases. Prolonged fatigue may endanger life safety. In most of the scenarios, physical and mental workloads co-lead operator into fatigue state. Thus, it is very important to study the interaction influence and its neural mechanisms between physical and mental fatigues. This paper introduces recent progresses on the interaction effects and discusses some research challenges and future development directions. It is believed that mutual influence between physical fatigue and mental fatigue may occur in the central nervous system. Revealing the basal ganglia function and dopamine release may be important to explore the neural mechanisms between physical fatigue and mental fatigue. Future effort is to optimize fatigue models, to evaluate parameters and to explore the neural mechanisms so as to provide scientific basis and theoretical guidance for complex task designs and fatigue monitoring.

Non-linear research of alertness levels under sleep deprivation / 生物医学工程学杂志

We applied Lempel-Ziv complexity (LZC) combined with brain electrical activity mapping (BEAM) to study the change of alertness under sleep deprivation in our research. Ten subjects were involved in 36 hours sleep deprivation (SD), during which spontaneous electroencephalogram (EEG) experiments and auditory evoked EEG experiments-Oddball were recorded once every 6 hours. Spontaneous and evoked EEG data were calculated and BEAMs were structured. Results showed that during the 36 hours of SD, alertness could be divided into three stages, i. e. the first 12 hours as the high stage, the middle 12 hours as the rapid decline stage and the last 12 hours as the low stage. During the period SD, LZC of Spontaneous EEG decreased over the whole brain to some extent, but remained consistent with the subjective scales. By BEAMs of event related potential, LZC on frontal cortex decreased, but kept consistent with the behavioral responses. Therefore, LZC can be effective to reflect the change of brain alertness. At the same time LZC could be used as a practical index to monitor real-time alertness because of its simple computation and fast calculation.

Bi-modal enhancement effect from combination of visual and auditory stimulus / 国际生物医学工程杂志

Objective To investigate the cognitive difference between uni-modal (V,A) and bi-modal (VA)target stimuli from both vision and audition,and then to study the neural mechanisms of bi-modal enhancement.Methods This experiment adopted a speeded target stimuli detection task, both behavioral and electroencephalographic responses to uni-modal and bi-modal target stimuli which were combined from visual and auditory target stimuli,were recorded from 14 normal subjects using a 64-channel EEG NeuroScan system.The differences of cognitive between uni-modal and bi-modal stimulus were tested from both behavioral (reaction time (RT) and error rate (ER)) and event-related potentials (ERPs) (P2 latency and amplitude,P3 latency and amplitude)data,and the correlation between behavioral and ERPs results were analyzed.Results As a result,the RT,ER and P3 latency has significant difference between uni-modal and bi-modal target stimuli.In addition,there were significant correlation between behavioral data and P3 latency,especially from the RT and P3 latency.Conclusion By comparing the difference between uni-modal and bi-modal from both behavioral and ERPs results,we could reached the conclusion that the neural mechanism of bi-modal target detection was predominant over that of vision and audition uni-modal target detection,the enhancement take place not only involved in early ERP components (such as P1 and N1),but engaged at the late ERP components (such as P2 and P3).