Investigating Critical Frequency Bands and Channels for EEG-Based Emotion Recognition with Deep Neural Networks
Citations
777 citations
Cites background from "Investigating Critical Frequency Ba..."
...Zheng and Lu [76] found that classification accuracies were higher when calculating features from set of manually selected critical channels rather than from all channels....
[...]
...Zheng and Lu [76] compared the classification acc uracy J....
[...]
699 citations
622 citations
Cites background from "Investigating Critical Frequency Ba..."
...examined dominant frequency bands and channels of EEG in an emotion recognition system [212]....
[...]
600 citations
Cites background or methods from "Investigating Critical Frequency Ba..."
...The experimental results demonstrate that the proposed method achieves better recognition performance than the state-of-the-art methods, in which the average recognition accuracy of 90.4 percent is achieved for subject dependent experiment while 79.95 percent for subject independent cross-validation one on the SEED database, and the average accuracies of 86.23, 84.54 and 85.02 percent are respectively obtained for valence, arousal and dominance classifications on the DREAMER database....
[...]
...%) of Subject Independent LOSO Cross Validation EEG-Based Emotion Recognition Experiments on SEED Database Using DGCNN Method Feature d band u band a band b band g band all (d; u; a;b; g) DGCNN DE 49.79 / 10.94 46.36 / 12.06 48.29 / 12.28 56.15 /14.01 54.87 / 17.53 79.95 / 9.02 PSD 50.36 / 9.66 48.85 / 9.44 43.39 / 8.22 56.39 / 10.9 51.81 / 10.88 64.27 / 13.80 DASM 44.31 / 6.67 43.79 / 6.31 44.64 / 8.94 47.53 / 11.95 47.13 / 10.89 52.50 / 11.92 RASM 43.42 / 4.07 42.69 / 7.11 42.77 / 7.43 49.52 / 10.22 46.37 / 12.1 58.46 / 10.08 DCAU 48.52 / 10.23 52.44 / 9.26 44.46 / 8.39 52.55 / 13.31 50.97 / 13.66 65.19 / 10.49 Table 4 shows the information about the EEG features we extracted from the DREAMER database....
[...]
...For the comparison purpose, we also include the experimental results of [19] with deep belief networks (DBN) [55] and support vector machine (SVM) [56] in Table 2....
[...]
...Both subject-dependent experiments and subject-independent cross validation experiments on SEED database had been conducted and the experimental results indicated that the DGCNN method achieves better recognition performance than the state-of-the-art methods such as the SVM, DBN, KPCA, TCA, T-SVM and TPT methods....
[...]
...Convolutional neural networks (CNN) is one of the most famous DNN approaches and had been widely used to cope with various classification problems, such as image classification [34], [35], [36], [37], object detection [38], tracking [39] and segmentation [40]....
[...]
511 citations
Cites background or result from "Investigating Critical Frequency Ba..."
...The findings of these neural patterns are consistent with previous emotion studies [14], [17], [42], [59], [61]....
[...]
...From our previous work[40], [41], [42], we have found that...
[...]
References
1,503 citations
"Investigating Critical Frequency Ba..." refers background in this paper
...The field of Affective Computing (AC) aspires to narrow the communicative gap between the highly emotional human and the emotionally challenged computer by developing computational systems that recognize and respond to human emotions [4]....
[...]
1,347 citations
1,241 citations
"Investigating Critical Frequency Ba..." refers background in this paper
...[38], [39] showed that frontal EEG asymmetry is related to approach and withdrawal emotions, with approach tendencies reflected in left frontal activity...
[...]
1,039 citations
"Investigating Critical Frequency Ba..." refers background or result in this paper
...Previous neuroscience studies [54], [55] have shown that EEG alpha bands reflect attentional processing and beta bands reflect emotional and cognitive processing in the brain....
[...]
...3 to 50 Hz and the recordings seriously contaminated by EMG are removed manually in our study; 2) the subjects are not asked to show their facial expressions explicitly, but rather stay still throughout the experiments; 3) the findings of these neural patterns are consistent with previous emotion studies with EEG [22], [42], [54], [57], [61]....
[...]