Designing Phase-Sensitive Common Spatial Pattern Filter to Improve Brain-Computer Interfacing

Chakraborty, Biswadeep; Ghosh, Lidia; Konar, Amit

doi:10.1109/tbme.2019.2954470

Cited by 13 publications

(10 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…where R 12 d1 , R 13 d1 and R 14 d1 represent diagonal correlation matrices that are calculated using correlation between class 1 and 2, class 1 and 3 and class 1and 4, respectively; entries of which are calculated using (12). Likewise, R 12 d2 , R 13 d2 and R 14 d2 denote diagonal correlation matrices between classes 1 and 2, 1 and 3 and 1 and 4, respectively; entries of which are calculated using (15). The problem for class 1 against the other classes is calculated by replacing Q 1 (w) and Q 2 (w) in ( 16) and ( 17) and solve these functions.…”

Section: Multi-class Problemmentioning

confidence: 99%

See 1 more Smart Citation

Correlation-based common spatial pattern (CCSP): A novel extension of CSP for classification of motor imagery signal

et al. 2021

View full text Add to dashboard Cite

Common spatial pattern (CSP) is shown to be an effective pre-processing algorithm in order to discriminate different classes of motor-based EEG signals by obtaining suitable spatial filters. The performance of these filters can be improved by regularized CSP, in which available prior information is added in terms of regularization terms into the objective function of conventional CSP. Variety of prior information can be used in this way. In this paper, we used time correlation between different classes of EEG signal as the prior information, which is clarified similarity between different classes of signal for regularizing CSP. Furthermore, the proposed objective function can be easily extended to more than two-class problems. We used three different standard datasets to evaluate the performance of the proposed method. Correlation-based CSP (CCSP) outperformed original CSP as well as the existing regularized CSP, Principle Component Cnalysis (PCA) and Fisher Discriminate Analysis (FDA) in both two-class and multi-class scenarios. The simulation results showed that the proposed method outperformed conventional CSP by 6.9% in 2-class and 2.23% in multi-class problem in term of mean classification accuracy.

show abstract

Section: Multi-class Problemmentioning

confidence: 99%

“…As we know, an EEG signal includes amplitude and phase information; however, the phase information entirely ignored in CSP filter calculation. To solve this problem, three different methods have been presented in [15]. In the first method, phase information of EEG signal added to CSP objective function.…”

Section: Introductionmentioning

confidence: 99%

Correlation-based common spatial pattern (CCSP): A novel extension of CSP for classification of motor imagery signal

et al. 2021

View full text Add to dashboard Cite

show abstract

“…The sensitivity to noise and over-fitting are eliminated by adding suitable regularizing constraints [38] in the CSP objective function (8). To utilize discriminating wave-shapes and/or spectral information of RHMI and LHMI, there are 3 alternatives: i) using CSP features along with temporal [39] and spectral features [40] of EEG for classification, ii) undertaking CSP in narrow sub-bands of the useful frequency spectrum for MI, and then selecting the best set of features from the CSP features in b sub-bands using a mutual information based feature section [41] hereafter called Filter Bank CSP (FBCSP) and iii) considering both magnitude and phase of the EEG samples in the CSP formulation [42] to derive optimal CSP features. Here, we adopt both (ii) FBCSP and (iii) Magnitude-Phase CSP (MPCSP) independently, and compare their relative performance with classical CSP in the experiment section.…”

Section: ) Feature Extractionmentioning

confidence: 99%

“…Here, we adopt both (ii) FBCSP and (iii) Magnitude-Phase CSP (MPCSP) independently, and compare their relative performance with classical CSP in the experiment section. A brief outline to [42] is given in the Appendix.…”

Section: ) Feature Extractionmentioning

confidence: 99%

“…C respectively defined in the complex plane. Later they adopted Lagrange multiplier technique to optimize an objective function (A.1) equivalent to (8) the details of which are available in [42]. The CSP features thus obtained, in conjunction with a standard Linear Discriminant Analysis (LDA) classifier improves the classification accuracy to more than 98% at the cost of additional computational overhead.…”

mentioning

confidence: 99%

See 1 more Smart Citation

A hybrid brain-computer interface for closed-loop position control of a robot arm

Rakshit

Konar

Nagar

2020

IEEE/CAA J. Autom. Sinica

Self Cite

View full text Add to dashboard Cite

Brain-Computer Interfacing has currently added a new dimension in assistive robotics. Existing brain-computer interfaces designed for position control applications suffer from two fundamental limitations. First, most of the existing schemes employ open-loop control, and thus are unable to track the positional errors, resulting in failures in taking necessary online corrective actions. There are traces of one or fewer works dealing with closed-loop EEG-based position control. The existing closedloop brain-induced position control schemes employ a fixed order link selection rule, which often creates a bottleneck for timeefficient control. Second, the existing brain-induced position controllers are designed to generate the position response like a traditional first-order system, resulting in a large steady-state error. This paper overcomes the above two limitations by keeping provisions for (Steady-State Visual Evoked Potential induced) link-selection in an arbitrary order as required for efficient control and also to generate a second-order response of the position-control system with gradually diminishing overshoots/undershoots to reduce steady-state errors. Besides the above, the third novelty is to utilize motor imagery and P300 signals to design the hybrid brain-computer interfacing system for the said application with gradually diminishing error-margin by speed reversal at the zero-crossings of positional errors. Experiments undertaken reveal that the steady-state error is reduced to 0.2%. The paper also provides a thorough analysis of stability of the closed-loop system performance using Root Locus technique.

show abstract

Error-Induced Brain-Actuated Motor Command Generation for Speed-Profile Setting in a 2-Loop Position Control of a Robot Arm

Konar,

De,

Mondal

et al. 2024

Advances in Intelligent Systems and Computing

View full text Add to dashboard Cite

Designing Phase-Sensitive Common Spatial Pattern Filter to Improve Brain-Computer Interfacing

Cited by 13 publications

References 29 publications

Correlation-based common spatial pattern (CCSP): A novel extension of CSP for classification of motor imagery signal

Correlation-based common spatial pattern (CCSP): A novel extension of CSP for classification of motor imagery signal

A hybrid brain-computer interface for closed-loop position control of a robot arm

Error-Induced Brain-Actuated Motor Command Generation for Speed-Profile Setting in a 2-Loop Position Control of a Robot Arm

Contact Info

Product

Resources

About