Fig 1 - uploaded by Christoph Guger
Content may be subject to copyright.
Positions of the 29 electrodes used for the EEG recording. The electrode positions with bold circles belong to the international 10–20 system. The other positions are inserted in between, in order to increase spatial resolution.
Source publication
The information transfer rate, given in bits per trial, is used as an evaluation measurement in a brain-computer interface (BCI). Three subjects performed four motor-imagery (left hand, right hand, foot, and tongue) and one mental-calculation task. Classification of the electroencephalogram (EEG) patterns is based on band power estimates and hidden...
Context in source publication
Context 1
... The EEG was recorded from 29 gold electrodes, 17 of which were placed according to the international 10-20 system (see Fig. 1). The ground electrode was glued to the fore- head. The EEG signals were filtered between 0.5 Hz and 30 Hz and sampled at frequency of 256 Hz. EEG trials containing elec- tromyogram (EMG) or electrooculogram (EOG) artifacts were excluded from the data sets. The number of artifact-free trials are summarized in Table ...
Similar publications
Brain Computer Interface (BCI) systems control the user's environment via his/her brain signals. Brain signals related to motor imagery (MI) have become a widespread method employed by the BCI community. Despite the large number of references describing the MI signal treatment, there is not enough information related to the available programming la...
Using neural correlates of intentionally induced human emotions may offer alternative imagery strategies to control brain-computer interface (BCI) applications. In this paper, self-induced emotions, i.e., emotions induced by participants performing sad or happy related emotional imagery, are compared to motor imagery (MI) in a two-class electroence...
A motor imagery (MI)-based brain–computer interface (BCI) is a system that enables humans to interact with their environment by translating their brain signals into control commands for a target device. In particular, synchronous BCI systems make use of cues to trigger the motor activity of interest. So far, it has been shown that electroencephalog...
Motor imagery electroencephalography is widely used in the brain-computer interface systems. Due to inherent characteristics of electroencephalography signals, accurate and real-time multiclass classification is always challenging. In order to solve this problem, a multiclass posterior probability solution for twin SVM is proposed by the ranking co...
The aim of this paper is to show that machine learning techniques can be used to derive a classifying function for human brain signal data measured by magnetoencephalography (MEG), for the use in a brain computer in- terface (BCI). This is especially helpful for evaluating quickly whether a BCI approach based on electroencephalography, on which tra...
Citations
... Accuracy was then calculated as the number of correct responses divided by the total number of tasks (12 per session), averaged over all subjects in a given session. On this basis and considering that a binary (left/right) symbol could be transmitted every 50 s (15 s rest + 35 s task), ITR could also be calculated [42]. ...
Functional transcranial Doppler (fTCD) ultrasound can detect cerebral blood flow lateralization to the left/right hemisphere during different tasks. This study aims to test the effectiveness of neurofeedback in improving the individual capacity to lateralize blood flow with mental activity. Bilateral monitoring of blood velocity (CBV) in the middle cerebral arteries was performed in 14 subjects engaged in 15 min of training, followed by a 15 min test in each of four sessions. A ball, displayed on a screen, moved right or left, according to the current right/left difference in normalized CBVs, thus providing a visual neurofeedback of lateralization. The subjects were invited to control the left/right movement of the depicted ball by appropriately orienting their mental activity, freely exploring different strategies. These attempts were completely free and unsupervised during training, while during the test, the subjects were required to follow randomized left/right cues lasting 35 s. Performance was assessed using receiver operating characteristic (ROC) analysis. With training, responses to left and right cues diverged more rapidly and consistently. Accuracy improved significantly from 0.51 to 0.65, and the area under the ROC increased from 0.55 to 0.69. These results demonstrate the effectiveness of neurofeedback in improving lateralization capacity, with implications for the development of fTCD-based brain–computer interfaces.
... Specifically, a common spatial pattern (CSP) based squeeze-and-excitation convolutional neural networks (CSP-SECNN) [40] was innovatively applied to classify rotation-related visual EEG in this study. Finally, classification accuracy and ITR [41] were compared between 2D and 3D paradigm. ...
Steady-State Visual Evoked Potentials (SSVEP) have proven to be practical in Brain-Computer Interfaces (BCI), particularly when integrated with augmented reality (AR) for real-world application. However, unlike conventional computer screen-based SSVEP (CS-SSVEP), which benefits from stable experimental environments, AR-based SSVEP (AR-SSVEP) systems are susceptible to the interference of real-world environment and device instability. Particularly, the performance of AR-SSVEP significantly declines as the target frequency increases. Therefore, our study introduced a 3D paradigm that combines flicker frequency with rotation patterns as stimuli, enabling expansion of target sets without additional frequencies. In the proposed design, in addition to the conventional frequency-based SSVEP feature, bio-marker elicited by visual perception of rotation was investigated. An experimental comparison between this novel 3D paradigm and a traditional 2D approach, which increases targets by adding frequencies, reveals significant advantages. The 12-class 3D paradigm achieved an accuracy of 76.5% and an information transfer rate (ITR) of 70.42 bits/min using 1-second EEG segments. In contrast, the 2D paradigm exhibited a lower performance with 72.07% accuracy and 62.28 bits/min ITR. The result underscores the 3D paradigm’s superiority in enhancing the practical applications of SSVEP-based BCIs in AR settings, especially with shorter time windows, by effectively expanding target recognition without compromising system efficiency.
... Therefore, several supervised learning based decoders such as extended-CCA (ECCA) [13] and task-related component analysis (TRCA) [14], have been proposed, achieving high accuracy with shorter EEG segments. Compared with unsupervised methods, the supervised methods can get higher information transfer rate (ITR) [15]. However, supervised learning methods require users to perform calibration experiments to collect EEG data elicited by each stimulus for model training, making the process highly time-consuming [16,17]. ...
The Brain-Computer Interface (BCI) enables direct brain-to-device communication, with the Steady-State Visual Evoked Potential (SSVEP) paradigm favored for its stability and high accuracy across various fields. In SSVEP BCI systems, supervised learning models significantly enhance performance over unsupervised models, achieving higher accuracy in less time. However, prolonged data collection can cause user fatigue and even trigger photosensitive epilepsy, creating a negative user experience. Thus, reducing calibration time is crucial. To address this, Cross-Stimulus transfer learning (CSTL) can shorten calibration by utilizing only partial frequencies. Traditional CSTL methods, affected by time-domain impulse response variations, are suitable only for adjacent frequency transfers, limiting their general applicability. We introduce an Empirical Mode Decomposition (EMD) Based Fuzzy Model (EMD-Fuzzy), which employs EMD to extract crucial frequency information and achieves stimulus transfer in the frequency domain through Fast Fourier Transform (FFT) to mitigate time-domain differences. Combined with a Fuzzy Decoder that uses fuzzy logic for representation learning, our approach delivers promising preliminary results in offline tests and state-of-the-art performance. With only 4 frequencies, our method achieved an accuracy of 82.75% (16.30%) and an information transfer rate (ITR) of 186.56 (52.09) bits/min on the 40-target Benchmark dataset. In online tests, our method demonstrates robust efficacy, achieving an averaged accuracy of 86.30% (6.18%) across 7 subjects. This performance underscores the effectiveness of integrating EMD and fuzzy logic into EEG decoding for CSTL and highlights our method's potential in real-time applications where consistent and reliable decoding is crucial.
... Various factors, including BCI type, signal processing techniques, and user proficiency, affect ITRs. [106][107][108][109][110] Enhancing signal-to-noise ratios is identified as crucial for improving target detection accuracy, 27,111 with various preprocessing techniques employed for signal-to-noise ratio optimization. 112,113 Usability Challenges BCI usability challenges revolve around the intensive training required for medical professionals and the alignment of ITRs with user expectations. ...
... Technical challenges 9,15,27,86,[101][102][103][104][105][106][107][108][109][110][111][112][113] BCIs face technical challenges due to non-stationary brain signals, influenced by emotional states, noise, and diversity in signal patterns. Limited training data and cognitive, neurophysiological, and psychological factors contribute to performance variability. ...
Brain-Computer Interfaces (BCIs), a remarkable technological advancement in neurology and neurosurgery, mark a significant leap since the inception of electroencephalography (EEG) in 1924. These interfaces effectively convert central nervous system signals into commands for external devices, offering revolutionary benefits to patients with severe communication and motor impairments due to a myriad of neurological conditions like stroke, spinal cord injuries, and neurodegenerative disorders. BCIs enable these individuals to communicate and interact with their environment, using their brain signals to operate interfaces for communication and environmental control. This technology is especially crucial for those completely locked in, providing a communication lifeline where other methods fall short. The advantages of BCIs are profound, offering autonomy and an improved quality of life for patients with severe disabilities. They allow for direct interaction with various devices and prostheses, bypassing damaged or non-functional neural pathways. However, challenges persist, including the complexity of accurately interpreting brain signals, the need for individual calibration, and ensuring reliable, long-term use. Additionally, ethical considerations arise regarding autonomy, consent, and the potential for dependence on technology. Despite these challenges, BCIs represent a transformative development in neurotechnology, promising enhanced patient outcomes and a deeper understanding of brain-machine interfaces.
... They often exhibit a poor signal-to-noise ratio, with significant trial-to-trial intra-subject variability. 4 EEG-BCI modalities lack task specificity, 5 and their complexity and time-consuming nature make them less suitable for routine clinical use. 6 Surface Electromyogram (sEMG) could be a viable alternative to address these drawbacks of the EEG-BCI modality for robot-assisted therapy. ...
Background Active participation of stroke survivors during robot-assisted movement therapy is essential for sensorimotor recovery. Robot-assisted therapy contingent on movement intention is an effective way to encourage patients’ active engagement. For severely impaired stroke patients with no residual movements, a surface electromyogram (EMG) has been shown to be a viable option for detecting movement intention. Although numerous algorithms for EMG detection exist, the detector with the highest accuracy and lowest latency for low signal-to-noise ratio (SNR) remains unknown. Methods This study, therefore, investigates the performance of 13 existing EMG detection algorithms on simulated low SNR (0dB and -3dB) EMG signals generated using three different EMG signal models: Gaussian, Laplacian, and biophysical model. The detector performance was quantified using the false positive rate (FPR), false negative rate (FNR), and detection latency. Any detector that consistently showed FPR and FNR of no more than 20%, and latency of no more than 50ms, was considered an appropriate detector for use in robot-assisted therapy. Results The results indicate that the Modified Hodges detector – a simplified version of the threshold-based Hodges detector introduced in the current study – was the most consistent detector across the different signal models and SNRs. It consistently performed for ~90% and ~40% of the tested trials for 0dB and -3dB SNR, respectively. The two statistical detectors (Gaussian and Laplacian Approximate Generalized Likelihood Ratio) and the Fuzzy Entropy detectors have a slightly lower performance than Modified Hodges. Conclusions Overall, the Modified Hodges, Gaussian and Laplacian Approximate Generalized Likelihood Ratio, and the Fuzzy Entropy detectors were identified as the potential candidates that warrant further investigation with real surface EMG data since they had consistent detection performance on low SNR EMG data.
... There are, however, several drawbacks to EEG-BCI systems. They often exhibit a poor signal-tonoise ratio, with significant trial-to-trial intra-subject variability, 4 EEG-BCI modalities lack task specificity, 5 and their complexity and time-consuming nature make them less suitable for routine clinical use. 6 Surface Electromyogram (sEMG) could be a viable alternative to address these drawbacks of the EEG-BCI modality for robot-assisted therapy. ...
Background
Active participation of stroke survivors during robot-assisted movement therapy is essential for sensorimotor recovery. Robot-assisted therapy contingent on movement intention is an effective way to encourage patients’ active engagement. For severely impaired stroke patients with no residual movements, a surface electromyogram (EMG) has been shown to be a viable option for detecting movement intention. Although numerous algorithms for EMG detection exist, the detector with the highest accuracy and lowest latency for low signal-to-noise ratio (SNR) remains unknown.
Methods
This study, therefore, investigates the performance of 13 existing EMG detection algorithms on simulated low SNR (0dB and -3dB) EMG signals generated using three different EMG signal models: Gaussian, Laplacian, and biophysical model. The detector performance was quantified using the false positive rate (FPR), false negative rate (FNR), and detection latency. Any detector that consistently showed FPR and FNR of no more than 20%, and latency of no more than 50ms, was considered an appropriate detector for use in robot-assisted therapy.
Results
The results indicate that the Modified Hodges detector – a simplified version of the threshold-based Hodges detector introduced in the current study – was the most consistent detector across the different signal models and SNRs. It consistently performed for ~90% and ~40% of the tested trials for 0dB and -3dB SNR, respectively. The two statistical detectors (Gaussian and Laplacian Approximate Generalized Likelihood Ratio) and the Fuzzy Entropy detectors have a slightly lower performance than Modified Hodges.
Conclusions
Overall, the Modified Hodges, Gaussian and Laplacian Approximate Generalized Likelihood Ratio, and the Fuzzy Entropy detectors were identified as the potential candidates that warrant further investigation with real surface EMG data since they had consistent detection performance on low SNR EMG data.
... 20 Unlike electromyography systems, EEG-BCI modalities lack task specificity. 21 Moreover, their complexity and time-consuming nature make them less suitable for routine clinical use. 22 Surface Electromyogram (sEMG) could be a viable alternative to address these drawbacks of the EEG-BCI modality for robot-assisted therapy. ...
... 20 The use of sophisticated signal processing techniques can increase the delay in intent detection, which can result in inappropriately timed robotic assistance leading to suboptimal recovery 12 , 21 EEG-BCI modalities do not precisely identify which limb segment is intended to move due to its low information rate. 21 Event-related desynchronization of the EEG sensorimotor rhythm may not necessarily reflect movement intention. 22 Critical for practical use, current EEG-BCI systems are too complex and time-consuming for clinical work. ...
... Change in the manuscript: They often exhibit a poor signal-to-noise ratio, with significant trial-to-trial intra-subject variability [20]. Unlike EMG systems, EEG-BCI modalities lack task specificity [21]. Moreover, their complexity and time-consuming nature prevent their routine clinical use [23]. ...
Background Active participation of stroke survivors during robot-assisted movement therapy is essential for sensorimotor recovery. Robot-assisted therapy contingent on movement intention is an effective way to encourage patients’ active engagement. For severely impaired stroke patients with no residual movements, a surface electromyogram (EMG) has been shown to be a viable option for detecting movement intention. Although numerous algorithms for EMG detection exist, the detector with the highest accuracy and lowest latency for low signal-to-noise ratio (SNR) remains unknown. Methods This study, therefore, investigates the performance of 13 existing EMG detection algorithms on simulated low SNR (0dB and -3dB) EMG signals generated using three different EMG signal models: Gaussian, Laplacian, and biophysical model. The detector performance was quantified using the false positive rate (FPR), false negative rate (FNR), and detection latency. Any detector that consistently showed FPR and FNR of no more than 20%, and latency of no more than 50ms, was considered an appropriate detector for use in robot-assisted therapy. Results The results indicate that the Modified Hodges detector – a simplified version of the threshold-based Hodges detector introduced in the current study – was the most consistent detector across the different signal models and SNRs. It consistently performed for ~90% and ~40% of the tested trials for 0dB and -3dB SNR, respectively. The two statistical detectors (Gaussian and Laplacian Approximate Generalized Likelihood Ratio) and the Fuzzy Entropy detectors have a slightly lower performance than Modified Hodges. Conclusions Overall, the Modified Hodges, Gaussian and Laplacian Approximate Generalized Likelihood Ratio, and the Fuzzy Entropy detectors were identified as the potential candidates that warrant further investigation with real surface EMG data since they had consistent detection performance on low SNR EMG data.
... Each try is considered complete when the user successfully performs two same turns, either left or right, depending on the command of the researcher. To evaluate the experiment, four metrics assess the participant's performance: the time taken to complete a single try, the number of missed commands, the total number of completed tries, and Information Transfer Rate (ITR) index [52], [53]. The targets (N) of the experiment are two, and the classification accuracy (P) for each participant is calculated by dividing the number of correct commands by the total number of commands executed. ...
The field of Brain-Computer Interface (BCI) has been rapidly expanding in the last few years and it is applicable in several fields. This study introduces a BCI-controlled wheelchair that utilizes Motor Imagery (MI) mental commands for turning left and right and Electrooculogram (EOG) signals, raising the eyebrows, for starting and stopping. The wheelchair offers 4 Degrees of Freedom (DoF), allowing users to move forward, stop, turn left, and turn right. The Emotiv Epoc headset is used to record the raw EEG data, the Common Spatial Patterns (CSP) algorithm is utilized to extract features from the data, and the Support Vector Machine (SVM) is employed to classify the mental commands. A total of 28 subjects, with half of them being individuals with motor and brain disabilities such as brain paralysis, severe brain disability, epilepsy, and spastic tetraplegia, participated in 5 experiments to assess the proposed BCI system. The results show that all participants, including those with disabilities, successfully adapted to and operated the BCI-controlled wheelchair with high accuracy and precision.
... Test accuracy was defined as the ratio of the number of corrected trials to the total number of trials in the test set. ITR was calculated as follows [44]: ...
Brain-computer interfaces (BCIs) can restore impaired cognitive functions in people with neurological disorders such as stroke. Musical ability is a cognitive function that is correlated with non-musical cognitive functions, and restoring it can enhance other cognitive functions. Pitch sense is the most relevant function to musical ability according to previous studies of amusia, and thus decoding pitch information is crucial for BCIs to be able to restore musical ability. This study evaluated the feasibility of decoding pitch imagery information directly from human electroencephalography (EEG). Twenty participants performed a random imagery task with seven musical pitches (C4-B4). We used two approaches to explore EEG features of pitch imagery: multiband spectral power at individual channels (IC) and differences between bilaterally symmetric channels (DC). The selected spectral power features revealed remarkable contrasts between left and right hemispheres, low- (<13 Hz) and high-frequency (> 13 Hz) bands, and frontal and parietal areas. We classified two EEG feature sets, IC and DC, into seven pitch classes using five types of classifiers. The best classification performance for seven pitches was obtained using IC and multiclass Support Vector Machine with an average accuracy of 35.68±7.47% (max. 50%) and an information transfer rate (ITR) of 0.37±0.22 bits/sec. When grouping the pitches to vary the number of classes (K = 2-6), the ITR was similar across K and feature sets, suggesting the efficiency of DC. This study demonstrates for the first time the feasibility of decoding imagined musical pitch directly from human EEG.
... 17 There are, however, several drawbacks to EEG-BCI systems: 1) They have a poor signal-to-noise ratio (SNR) with large trial-to-trial intra-subject variability. 20 The use of sophisticated signal processing techniques can increase the delay in intent detection, which can result in inappropriately timed robotic assistance leading to suboptimal recovery 12,21 2) EEG-BCI modalities do not precisely identify which limb segment is intended to move due to its low information rate. 21 3) Event-related desynchronization of the EEG sensorimotor rhythm may not necessarily reflect movement intention. ...
... 20 The use of sophisticated signal processing techniques can increase the delay in intent detection, which can result in inappropriately timed robotic assistance leading to suboptimal recovery 12,21 2) EEG-BCI modalities do not precisely identify which limb segment is intended to move due to its low information rate. 21 3) Event-related desynchronization of the EEG sensorimotor rhythm may not necessarily reflect movement intention. 22 4) Critical for practical use, current EEG-BCI systems are too complex and time-consuming for clinical work. ...
Background: Active participation of stroke survivors during robot-assisted movement therapy is essential for sensorimotor recovery. Robot-assisted therapy contingent on movement intention is an effective way to encourage patients' active engagement. For severely impaired stroke patients with no residual movements, a surface electromyogram (EMG) has been shown to be a viable option for detecting movement intention. Although numerous algorithms for EMG detection exist, the detector with the highest accuracy and lowest latency for low signal-to-noise ratio (SNR) remains unknown.
Methods: This study, therefore, investigates the performance of 13 existing EMG detection algorithms on simulated low SNR (0dB and -3dB) EMG signals generated using three different EMG signal models: gaussian, Laplacian, and biophysical model. The detector performance was quantified using the false positive rate (FPR), false negative rate (FNR), and detection latency. Any detector that consistently showed FPR and FNR of no more than 20%, and latency of no more than 50ms, was considered an appropriate detector for use in robot-assisted therapy.
Results: The results indicate that the Modified Hodges detector – a simplified version of the threshold-based Hodges detector introduced in the current study – was the most consistent detector across the different signal models and SNRs. It consistently performed for ~90% and ~40% of the tested trials for 0dB and -3dB SNR, respectively. The two statistical detectors (Gaussian and Laplacian Approximate Generalized Likelihood Ratio) and the Fuzzy Entropy detectors have a slightly lower performance than Modified Hodges.
Conclusions: Overall, the Modified Hodges, Gaussian and Laplacian Approximate Generalized Likelihood ratio, and the Fuzzy Entropy detectors were identified as the potential candidates that warrant further investigation with real surface EMG data since they had consistent detection performance on low SNR EMG data.
