Detecting Interbrain Synchronization in EEG Hyperscanning with MUSE-S EEG headban

• Hyperscanning simultaneously measures brain activity from multiple subjects and supports research on social interaction, teamwork, and collaboration.Source: §I · p. 1
• EEG is presented as the most feasible brain-imaging technique for real-life hyperscanning applications.Source: §I · p. 1
• Consumer-oriented EEG devices are increasingly used in real-life situations, including prior MUSE-S mental-workload classification studies.Source: §I · p. 1
• The present study preliminarily evaluates whether MUSE-S can detect interbrain synchronization and informs a more extensive experiment.Source: §I · p. 1

• Five two-person recordings involved five healthy adult volunteers using MUSE-S EEG headsets with textile electrodes.Source: A. Recording setup · p. 1
• The analysis selected the AF7 and AF8 channels, while TP1 and TP2 were discarded because of excessive artifacts.Source: A. Recording setup · p. 1
• Three Tetris game sessions alternated with 1-minute relaxation periods in each recording.Source: A. Recording setup · p. 1
• The sessions represented cooperation, swapped control over separate wells, and competition between participants.Source: A. Recording setup · p. 1

• The setup used Lab Streaming Layer streams and stored EEG together with recorded keystrokes in .xdf files.Source: S EEG devices over Bluetooth. The… · p. 2, Figure 2 · p. 2
• Laptop A ran LabRecorder, the Tetris game, keystroke recording, and MuseLSL2 for one participant’s data.Source: Figure 2 · p. 2
• Laptop A provided duplicate monitors and keyboards so the two participants could use the game setup.Source: Figure 2 · p. 2
• Laptop B ran MuseLSL2 to capture the other participant’s MUSE-S data.Source: Figure 2 · p. 2

• EEG signals sampled at 256 Hz were visualized, marked by session boundaries, and filtered from 0.5 to 42 Hz with a 6th-order Butterworth bandpass filter.Source: B. Data Preprocessing and Feature… · p. 2
• The two data streams were resampled so their samples occurred at exactly the same timestamps.Source: B. Data Preprocessing and Feature… · p. 2
• Sessions were divided into 10-second segments with 8-second overlap, producing 475 relaxation and 2161 gaming segments.Source: B. Data Preprocessing and Feature… · p. 2
• Ten features comprised four scaled power spectral densities, two within-stream coherences, and four inter-stream coherences.Source: B. Data Preprocessing and Feature… · p. 2
• Features were computed from 0 to 45 Hz in 0.5 Hz steps, forming 91 × 10 matrices that were augmented for CNN input.Source: B. Data Preprocessing and Feature… · p. 2
• An inter-stream-only subset used four features and was augmented into 91 × 20 matrices for classification.Source: B. Data Preprocessing and Feature… · p. 2

C. Classification

• A CNN classifier was applied to augmented EEG feature matrices to identify patterns associated with the two conditions.The network included convolutional and fully connected layers with ReLU and sigmoid activations.Source: C. Classification · pp. 2–3
• The feature matrices represented either the full feature set or only inter-stream cross-coherence features.The two feature configurations corresponded to the alternatives evaluated by the classifier.Source: Figure 3 · p. 3
• The full-feature configuration used batch size 32 and learning rate 0.00009, whereas the inter-stream configuration used batch size 16 and learning rate 0.0002.Both configurations used Adam optimization and binary cross-entropy loss.Source: C. Classification · p. 3
• 70% of the data were randomly assigned to training and 30% to testing across 50 runs of 50 epochs.Gaming samples were randomly downsampled to match the 475 relaxation feature matrices in each run.Source: C. Classification · p. 3

III. RESULTS AND DISCUSSION

• The full-feature model learned to discriminate relaxation and gaming during approximately the first few epochs, despite a learning rate of 0.00009.Training loss and classification accuracy were aggregated over 50 runs for the reported comparison.Source: §III · p. 3, Figure 4 · p. 3
• The full feature set produced nearly perfect discrimination between relaxation and gaming despite data acquisition with a consumer-oriented wireless EEG device.The authors attribute part of this separability to the differing eye states between conditions.Source: §III · p. 3
• 94% training accuracy was reached after 50 epochs using only inter-stream cross-coherence features.Testing accuracy became limited at about 75–80% after 20 epochs.Source: §III · p. 3
• 79% accuracy using only interbrain features and consumer-oriented EEG devices was considered noteworthy.The authors also noted information leakage between subjects because there were only five subjects and random cross-validation was used.Source: §III · p. 3

• Five hyperscanning EEG recordings used CNN models to discriminate relaxation and gaming during two-player Tetris sessions.The analysis used power spectral density and cross-coherence features.Source: §IV · p. 4
• Spectral and cross-coherence features enabled easy discrimination of relaxation and gaming with a low-complexity consumer-oriented EEG headband using prefrontal channels.Source: §IV · p. 4
• Inter-subject cross-coherence features alone still discriminated the two brain states, indicating that the headband detected some interaction between subjects’ brain activity.Source: §IV · p. 4
• More extensive hyperscanning recordings are needed, and future experiments will better control collaborative and competitive tasks.The study did not promisingly discriminate the different game types.Source: §IV · p. 4