Feature Extraction for Multi-class BCI using Canonical Variates Analysis

Galán, Ferran; Ferrez, Pierre W.; Oliva, Francesc; Guàrdia, Joan; Millán, José del R.

doi:10.1109/wisp.2007.4447615

Cited by 49 publications

(29 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We apply a Laplacian spatial filter and then estimate the power spectral density (PSD) over the last second, in the band 4-48 Hz with a 2 Hz resolution [1]. We compute the PSD features every 62.5 ms using the Welch method with 5 overlapped (25%) Hanning windows of 500 ms. We use canonical variate analysis (CVA) [22] to select the subject-specific features that best reflect the motor-imagery task for each subject and use these to train a Guassian classifier [18]. Evidence about the executed task is accumulated using an exponential smoothing probability integration framework [23].…”

Section: B the Brain-computer Interfacementioning

confidence: 99%

A hybrid BCI for enhanced control of a telepresence robot

Carlson¹,

Tonin²,

Perdikis³

et al. 2013

2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)

View full text Add to dashboard Cite

Abstract-Motor-disabled end users have successfully driven a telepresence robot in a complex environment using a BrainComputer Interface (BCI). However, to facilitate the interaction aspect that underpins the notion of telepresence, users must be able to voluntarily and reliably stop the robot at any moment, not just drive from point to point. In this work, we propose to exploit the user's residual muscular activity to provide a fast and reliable control channel, which can start/stop the telepresence robot at any moment. Our preliminary results show that not only does this hybrid approach increase the accuracy, but it also helps to reduce the workload and was the preferred control paradigm of all the participants.

show abstract

Section: B the Brain-computer Interfacementioning

confidence: 99%

A hybrid BCI for enhanced control of a telepresence robot

Carlson¹,

Tonin²,

Perdikis³

et al. 2013

2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)

View full text Add to dashboard Cite

show abstract

“…To do so, we first computed EEG Power Spectral Densities (PSD) for all electrodes and then ranked the contributions of all channels in all frequency bands through Canonical Variate Analysis (CVA) [10]. Furthermore, we considered different intervals of the spectrogram to characterize changes of discriminability in time.…”

Section: Methodsmentioning

confidence: 99%

“…Following previous studies, we computed the Discriminant Power (DP) of each feature using Canonical Variate Analysis [10]. For this study, we were interested in using this frequency analysis to determine when salient motorrelated EEG features were more likely to appear in time.…”

Section: A Power Spectral Density Estimation and Canonical Variate Anamentioning

confidence: 99%

Combining discriminant and topographic information in BCI: Preliminary results on stroke patients

Biasiucci

Chavarriaga

Hamner

et al. 2011

2011 5th International IEEE/EMBS Conference on Neural Engineering

Self Cite

View full text Add to dashboard Cite

Abstract-Non-Invasive Brain-Computer Interfaces (BCI) convey a great potential in the field of stroke rehabilitation, where the continuous monitoring of mental tasks execution could support the positive effects of standard therapies. In this paper we combine time-frequency analysis of EEG with the topographic analysis to identify and track task-related patterns of brain activity emerging during a single BCI session. 6 Stroke patients executed Motor Imagery of the affected and unaffected hands: EEG sites were ranked depending on their discriminant power (DP) at different time instants and the resulting discriminant periods were used as a prior to extract EEG Microstates. Results show that the combination of these two techniques can provide insights about specific motor-related processes happening at a fine grain temporal resolution. Such events, represented by EEG microstates, can be tracked and used both to quantify changes of underlying neural structures and to provide feedback to patients and therapists.

show abstract

“…The user specific EEG-features extracted using Canonical Variate Analysis (CVA) for multi-class problems [13]. This technique maximizes the separability between the patterns generated by executing the different mental tasks.…”

Section: Bci Research and Ibci Systemmentioning

confidence: 99%

Constructing Ambient Intelligence

Ferscha¹,

Aitenbichler²,

Mühlhäuser³

2008

Communications in Computer and Information Science

View full text Add to dashboard Cite

Abstract. This paper is aimed to introduce IDIAP Brain Computer Interface (IBCI) research that successfully applied Ambience Intelligence (AmI) principles in designing intelligent brain-machine interactions. We proceed through IBCI applications describing how machines can decode and react to the human mental commands, cognitive and emotive states. We show how effective human-machine interaction for brain computer interfacing (BCI) can be achieved through, 1) asynchronous and spontaneous BCI, 2) shared control between the human and machine, 3) online learning and 4) the use of cognitive state recognition. Identifying common principles in BCI research and ambiance intelligence (AmI) research, we discuss IBCI applications. With the current studies on recognition of human cognitive states, we argue for the possibility of designing empathic environments or devices that have a better human like understanding directly from brain signals. MotivationBrain Computer Interfacing (BCI) or Brain Machine Interfacing (BMI) refers to interaction with devices, where user's intentions represented as several brain states are deciphered and translated into actions without requiring any physical action [44] [25] [21]. There is a growing interest in the use of brain signals for communicating and operating devices, which is facilitated by the advances in the the measurement technologies in the past decades. As BCI bypasses the classical neuromuscular communication channels, this technology is intended to use for rehabilitation of tetraplegic or paraplegic patients to improve their communication, mobility and independence. The BCI research also opens up new possibilities in natural interaction for able-bodied people (e.g., for space applications, where environment is inherently hostile and dangerous for astronauts, who could greatly benefit from direct mental teleoperation of external semi-automatic manipulators [26], and for entertainment applications like multimedia gaming [20]). Typical applications of BCI are communication aids such as spelling devices [5] [31] [25] and mobility aids such as wheelchair [41]. In the current paper, we Gangadhar.Garipelli@idiap.ch

show abstract

Feature Extraction for Multi-class BCI using Canonical Variates Analysis

Cited by 49 publications

References 14 publications

A hybrid BCI for enhanced control of a telepresence robot

A hybrid BCI for enhanced control of a telepresence robot

Combining discriminant and topographic information in BCI: Preliminary results on stroke patients

Constructing Ambient Intelligence

Contact Info

Product

Resources

About