[Application to performance augmentation in high-throughput tasks] The conventional goal for a br... more [Application to performance augmentation in high-throughput tasks] The conventional goal for a brain-computer interface has been to restore, for paralyzed individuals, a seamless interaction with the world. The shared vision in this research area is that one day patients will control a prosthetic device with signals originating directly from their brain. This review provides a new perspective on the brain-computer interface (BCI), by asking instead “How can BCI be used to assist neurologically healthy individuals in specifically demanding tasks?” The limited signal-to-noise ratio (SNR) of noninvasive brain signals suggests that one must tailor the application of BCI to tasks where a small increment in information can make a large difference. High throughput tasks may provide such a scenario, as will be exemplified in this review for one such task: rapid visual target detection. BCI can assist in this task by prioritizing perceived target images. Due to the speeded nature of this and...
Proceedings of the 25th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (IEEE Cat. No.03CH37439)
Abstrucf-In this paper we use linear discrimination for learning EEG signatures of object recogni... more Abstrucf-In this paper we use linear discrimination for learning EEG signatures of object recognition events in a rapid serial visual presentation (RSVP) task. We record EEG using a high spatial density array (63 electrodes) during the rapid presentation (50-200 msec per image) of ...
Simultaneous EEG/fMRI has the potential to yield high resolution spatio-temporal information abou... more Simultaneous EEG/fMRI has the potential to yield high resolution spatio-temporal information about brain function. However, because of the low signal-to-noise and signal-to-inference ratios of these imaging modalities, most EEG and fMRI analysis methods estimate relevant activity through trial or event-locked averaging. However, averaging places a limit on the utility of EEG/fMRI, as it does not permit assessment of inter-trial variability critical for understanding the relationship between neural processing and variation in behavioral responses. Single-trial variability may arise as a result of changes in attention, adaptation, or habituation, as well as changes in the recording environment. Our group has developed single-trial EEG analysis based on linear discrimination [1,2] which enables one to relate response variability across trial/stimulus presentation to the underlying electrophysiological variability [3,4]. In this study, we assess whether EEG acquired simultaneously with fMRI is of high enough quality to allow use of such single-trial techniques.
We describe a real-time EEG-based brain-computer interface (BCI) system for triaging imagery pres... more We describe a real-time EEG-based brain-computer interface (BCI) system for triaging imagery presented using rapid serial visual presentation (RSVP). A target image in a sequence of non-target distractor images elicits in the EEG a stereotypical spatio-temporal response, which can be detected. A pattern classifier uses this response to re-prioritize the image sequence, placing detected targets in the front of an image stack. We use single-trial analysis based on linear discrimination to recover spatial components that reflect differences in EEG activity evoked by target vs. non-target images. We find an optimal set of spatial weights for 59 EEG sensors within a sliding 50 ms time window. Using this simple classifier allows us to process EEG in real-time. The detection accuracy across five subjects is on average 92%, i.e. in a sequence of 2500 images, resorting images based on detector output results in 92% of target images being moved from a random position in the sequence to one of the first 250 images (first 10% of the sequence). The approach leverages the highly robust and invariant object recognition capabilities of the human visual system, using single-trial EEG analysis to efficiently detect neural signatures correlated with the recognition event.
Index Terms— electroencephalography, brain–computer interface , cortically–coupled computer vision, rapid serial visual presentation, image triage.
Event-related potentials (ERPs) recorded at the scalp are indicators of brain activity associated... more Event-related potentials (ERPs) recorded at the scalp are indicators of brain activity associated with event-related information processing; hence they may be suitable for the assessment of changes in cognitive processing load. While the measurement of ERPs in a laboratory setting and classifying those ERPs is trivial, such a task presents major challenges in a " real world " setting where the EEG signals are recorded when subjects freely move their eyes and the sensory inputs are continuously, as opposed to discretely presented. Here we demonstrate that with the aid of second-order blind identification (SOBI), a blind source separation (BSS) algorithm: (1) we can extract ERPs from such challenging data sets; (2) we were able to obtain meaningful single-trial ERPs in addition to averaged ERPs; and (3) we were able to estimate the spatial origins of these ERPs. Finally, using back-propagation neural networks as classifiers, we show that these single-trial ERPs from specific brain regions can be used to determine moment-to-moment changes in cognitive processing load during a complex " real world " task.
Simultaneous EEG/fMRI has the potential to yield high resolution spatio-temporal information abou... more Simultaneous EEG/fMRI has the potential to yield high resolution spatio-temporal information about brain function. However, because of the low signal-to-noise and signal-to-inference ratios of these imaging modalities, most EEG and fMRI analysis methods estimate relevant activity through trial or event-locked averaging. However, averaging places a limit on the utility of EEG/fMRI, as it does not permit assessment of inter-trial variability critical for understanding the relationship between neural processing and variation in behavioral responses. Single-trial variability may arise as a result of changes in attention, adaptation, or habituation, as well as changes in the recording environment. Our group has developed single-trial EEG analysis based on linear discrimination [1,2] which enables one to relate response variability across trial/stimulus presentation to the underlying electrophysiological variability [3,4]. In this study, we assess whether EEG acquired simultaneously with fMRI is of high enough quality to allow use of such single-trial techniques.
The 2006 IEEE International Joint Conference on Neural Network Proceedings, 2006
Abstract Event-related potentials (ERPs) recorded at the scalp are indicators of brain activity a... more Abstract Event-related potentials (ERPs) recorded at the scalp are indicators of brain activity associated with event-related information processing; hence they may be suitable for the assessment of changes in cognitive processing load. While the measurement of ERPs in a ...
[Application to performance augmentation in high-throughput tasks] The conventional goal for a br... more [Application to performance augmentation in high-throughput tasks] The conventional goal for a brain-computer interface has been to restore, for paralyzed individuals, a seamless interaction with the world. The shared vision in this research area is that one day patients will control a prosthetic device with signals originating directly from their brain. This review provides a new perspective on the brain-computer interface (BCI), by asking instead “How can BCI be used to assist neurologically healthy individuals in specifically demanding tasks?” The limited signal-to-noise ratio (SNR) of noninvasive brain signals suggests that one must tailor the application of BCI to tasks where a small increment in information can make a large difference. High throughput tasks may provide such a scenario, as will be exemplified in this review for one such task: rapid visual target detection. BCI can assist in this task by prioritizing perceived target images. Due to the speeded nature of this and...
Proceedings of the 25th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (IEEE Cat. No.03CH37439)
Abstrucf-In this paper we use linear discrimination for learning EEG signatures of object recogni... more Abstrucf-In this paper we use linear discrimination for learning EEG signatures of object recognition events in a rapid serial visual presentation (RSVP) task. We record EEG using a high spatial density array (63 electrodes) during the rapid presentation (50-200 msec per image) of ...
Simultaneous EEG/fMRI has the potential to yield high resolution spatio-temporal information abou... more Simultaneous EEG/fMRI has the potential to yield high resolution spatio-temporal information about brain function. However, because of the low signal-to-noise and signal-to-inference ratios of these imaging modalities, most EEG and fMRI analysis methods estimate relevant activity through trial or event-locked averaging. However, averaging places a limit on the utility of EEG/fMRI, as it does not permit assessment of inter-trial variability critical for understanding the relationship between neural processing and variation in behavioral responses. Single-trial variability may arise as a result of changes in attention, adaptation, or habituation, as well as changes in the recording environment. Our group has developed single-trial EEG analysis based on linear discrimination [1,2] which enables one to relate response variability across trial/stimulus presentation to the underlying electrophysiological variability [3,4]. In this study, we assess whether EEG acquired simultaneously with fMRI is of high enough quality to allow use of such single-trial techniques.
We describe a real-time EEG-based brain-computer interface (BCI) system for triaging imagery pres... more We describe a real-time EEG-based brain-computer interface (BCI) system for triaging imagery presented using rapid serial visual presentation (RSVP). A target image in a sequence of non-target distractor images elicits in the EEG a stereotypical spatio-temporal response, which can be detected. A pattern classifier uses this response to re-prioritize the image sequence, placing detected targets in the front of an image stack. We use single-trial analysis based on linear discrimination to recover spatial components that reflect differences in EEG activity evoked by target vs. non-target images. We find an optimal set of spatial weights for 59 EEG sensors within a sliding 50 ms time window. Using this simple classifier allows us to process EEG in real-time. The detection accuracy across five subjects is on average 92%, i.e. in a sequence of 2500 images, resorting images based on detector output results in 92% of target images being moved from a random position in the sequence to one of the first 250 images (first 10% of the sequence). The approach leverages the highly robust and invariant object recognition capabilities of the human visual system, using single-trial EEG analysis to efficiently detect neural signatures correlated with the recognition event.
Index Terms— electroencephalography, brain–computer interface , cortically–coupled computer vision, rapid serial visual presentation, image triage.
Event-related potentials (ERPs) recorded at the scalp are indicators of brain activity associated... more Event-related potentials (ERPs) recorded at the scalp are indicators of brain activity associated with event-related information processing; hence they may be suitable for the assessment of changes in cognitive processing load. While the measurement of ERPs in a laboratory setting and classifying those ERPs is trivial, such a task presents major challenges in a " real world " setting where the EEG signals are recorded when subjects freely move their eyes and the sensory inputs are continuously, as opposed to discretely presented. Here we demonstrate that with the aid of second-order blind identification (SOBI), a blind source separation (BSS) algorithm: (1) we can extract ERPs from such challenging data sets; (2) we were able to obtain meaningful single-trial ERPs in addition to averaged ERPs; and (3) we were able to estimate the spatial origins of these ERPs. Finally, using back-propagation neural networks as classifiers, we show that these single-trial ERPs from specific brain regions can be used to determine moment-to-moment changes in cognitive processing load during a complex " real world " task.
Simultaneous EEG/fMRI has the potential to yield high resolution spatio-temporal information abou... more Simultaneous EEG/fMRI has the potential to yield high resolution spatio-temporal information about brain function. However, because of the low signal-to-noise and signal-to-inference ratios of these imaging modalities, most EEG and fMRI analysis methods estimate relevant activity through trial or event-locked averaging. However, averaging places a limit on the utility of EEG/fMRI, as it does not permit assessment of inter-trial variability critical for understanding the relationship between neural processing and variation in behavioral responses. Single-trial variability may arise as a result of changes in attention, adaptation, or habituation, as well as changes in the recording environment. Our group has developed single-trial EEG analysis based on linear discrimination [1,2] which enables one to relate response variability across trial/stimulus presentation to the underlying electrophysiological variability [3,4]. In this study, we assess whether EEG acquired simultaneously with fMRI is of high enough quality to allow use of such single-trial techniques.
The 2006 IEEE International Joint Conference on Neural Network Proceedings, 2006
Abstract Event-related potentials (ERPs) recorded at the scalp are indicators of brain activity a... more Abstract Event-related potentials (ERPs) recorded at the scalp are indicators of brain activity associated with event-related information processing; hence they may be suitable for the assessment of changes in cognitive processing load. While the measurement of ERPs in a ...
Uploads
Papers by Adam D Gerson
Index Terms— electroencephalography, brain–computer interface , cortically–coupled computer vision, rapid serial visual presentation, image triage.
Index Terms— electroencephalography, brain–computer interface , cortically–coupled computer vision, rapid serial visual presentation, image triage.