Kisan Call Centre - To harness potential of ICT in Agriculture by answer farm...
Nafiz prasented an eeg-based brain computer interface for
1. AN EEG-BASED BRAIN COMPUTER
INTERFACE FOR
EMOTION RECOGNITION AND ITS
APPLICATION IN
PATIENTS WITH DISORDER OF
CONSCIOUSNESS
HAIYUN HUANG, QIUYOU XIE, JIAHUI PAN, YANBIN HE, ZHENFU WEN,
RONGHAO YU AND YUANQING LI,
2019
PRESENTED BY
NAFIZ ISHTIAQUE AHMED
23-JANUARY-2020
UOU- UNIVERSITY OF ULSAN
Computational
Neural
Engineering Lab.
2. DISORDER OF CONSCIOUSNESS (DOC)
Brain Injuries :
Coma,
Vegetative state (VS),
Minimal conscious state
(MCS),
Emergence from MCS (EMCS)
3. INTRODUCTION
Emotion has strong connection with Consciousness.
If DOC patients emotion is recognized then it can help to
assess their residual consciousness as well as their impaired
brain functions.
As DOC patients suffers from severe motor impairments and
unable to provide proper emotion expressions; So far doctors
cannot detect their emotional states.
4. EMOTION RECOGNITION
Evoked Mechanisms Accuracy
Viewing Picture EEG 80.77%
listening to music EEG 82.29% ± 3.06%
Watching videos EEG, pupillary responses,
and gaze distances
76.4%
Watching videos EEG 79.28%
listening to music
(Real-time)
EEG 53.96%
Emotion Recognition of Healthy people.
5. INTRODUCTION
EEG is significant and widely used for identifying
human emotion state.
This paper shows EEG Based BCI system to
recognize
the emotions of DOC patients at real-time.
Emotion evoked by 2 class video clips
Positive
Negative
6. SUBJECTS
Control group
(validate the BCI system)
10 student (8-male, 2-female)
Mean age 26
Normal vision and hearing
DOC Patient
(applied the BCI system)
8 patient (6-male, 2-female)
Mean age 35
Stable condition with normal vision
and hearing
No psychiatric medications (2-days)
Clinical diagnosis
2 patient-VS,
5 patient-MSC,
1 patient-EMCS
7. STIMULUS
Initially, 140 Chinese movie clips (30s) that contained positive
or negative scenes was collected.
10 volunteers evaluate their emotions with a level (i.e., not at
all, slightly, or extremely) and a keywords (i.e., positive or
negative) while watching the clips.
Finally, 40 Chinese video clips(20 positive ,20 negative ) that all
volunteers scored as extremely positive or negative were
selected.
Only 2 emotional state is chosen because complex and many
emotional states may increase the burden on the patients.
9. DATA ANALYSIS
Baseline corrected by subtracting the mean value of the 1s
signal before the stimulus start.
Notch filter was applied to remove the 50 Hz power-line noise.
Tenth order minimum-phase FIR bandpass filter between 0.1 to
70 Hz.
Online - Spectral power – STFT - a non-overlapped Hanning
window of 1 second- band power values are calculated by
averaging the power values in each frequency bands -
logarithmic scale – SVM model – Prediction.
Offline - preprocessing, feature extraction -classification
procedures are the same as online method - 10 times 5-fold
cross-validation.
12. Topographical maps of the classification weight of each electrode :
average of the weights of all five subbands
1. The left frontal areas correlated to
positive emotion.
2. The right hemisphere mainly processed
negative emotion .
3. The reported frontal midline areas were
associated with the process of positive
emotion.
13. Topographies of different frequency bands
1. Depicts the average power changes for negative
and positive emotions in the five bands (delta,
theta, alpha, beta, and gamma).
2. In the delta band, the right anterior areas were
activated more for positive emotion than for
negative emotion.
3. In the theta band, the prefrontal regions and
occipital lobe show higher power during positive
emotional state than during negative emotional
state.
4. In the alpha band, the power decreased in the right
frontal areas during negative emotion, the power of
the frontal areas increased during positive emotion.
5. In the beta and gamma bands, the power in the
lateral temporal areas for positive emotion was
significantly higher than that for negative emotion.
16. CONCLUSION
1. An EEG-based BCI system to distinguish video-induced positive
and negative emotions.
2. Positive & Negative emotions were well evoked and recognized
by this BCI system.
3. This system provides an potential approach to detect the
emotions in patients with DOC.
4. The emotion BCI system may be a potential tool for evaluating
the consciousness levels of patients with DOC.
Editor's Notes
Coma
A coma is when a person shows no signs of being awake and no signs of being aware.
A person in a coma lies with their eyes closed and doesn't respond to their environment, voices or pain.
Vegetative state
awake but is showing no signs of awareness.
open their eyes
wake up and fall asleep at regular intervals
have basic reflexes (such as blinking when they're startled by a loud noise or withdrawing their hand when it's squeezed hard).
Minimally conscious state
A person who shows inconsistent awareness.
They may have periods where they can communicate or respond to commands, such as moving a finger when asked.
the research of emotion recognition in patients with DOC may help us assess their residual consciousness and the impaired brain functions.
However, none of the existing studies has developed an EEG-based emotion recognition system for patients with DOC.
Then, the video clip that represents a positive/negative emotion, respectively, is played and the EEG data are collected and processed simultaneously. Then, the online recognition result is displayed on the screen as feedback. In this study, a smiling/crying cartoon face is presented as feedback, which represents the detection of a positive/negative emotion, respectively.
5 session total 10 trails and 10 test
several differences between the experimental procedures for DOC patients compared with healthy subject like braek time depending upon patients condition
the research of emotion recognition in patients with DOC may help us assess their residual consciousness and the impaired brain functions.
the importance of the theta band in emotion recognition
P4 is EMCS patient thus his emotion reorganization rate is higher
Patient P4 achieved the highest online accuracy among all patients, The electrodes that correlated with the top-20 features were mainly located in the temporal lobe, central area and occipital lobe.
For positive emotion, the frontal midline had a significant higher theta response.
Meanwhile, as shown in Fig. 3(b), the parietal and frontal areas were activated more in the alpha band in response to positive emotion.
In the beta and gamma frequency bands, the occipital lobe presented greater activation for positive emotional state than negative emotional state