Binary DE-Based Channel Selection and Weighted Ensemble of SVM Classification for Novel Brain–Computer Interface Using Devanagari Script-Based P300 Speller Paradigm

Chaurasiya, Rahul Kumar; Londhe, Narendra D.; Ghosh, Subhojit

doi:10.1080/10447318.2016.1203047

Cited by 31 publications

(5 citation statements)

References 89 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, this accuracy diminishes when the number of trials is reduced. Specifically, for 3-5 trials, the P300 detection accuracy falls within the range of 73-88% (Chaurasiya et al, 2016;Kshirsagar & Londhe, 2019). In comparison to the above-mentioned studies, the proposed approach reports a comparable performance of 81.12% accuracy using a simple classifier on a single trial.…”

Section: Comparative Analysismentioning

confidence: 72%

Comparative Evaluation of Facial Paradigms for Devanagari Script-based P300 Speller: Preliminary Findings

Bhandari,

Londhe,

Kshirsagar

2024

JDSIS

View full text Add to dashboard Cite

Display paradigm design is an important stage in the design of any brain-computer interface (BCI) device including the P300 speller system. Conventional grey-to-white intensification limits the usability of the existing Devanagari-script-based P300 speller (DSP3S) as it suffers from reduced visual contrast, diminished user engagement, limited personalization, minimal cognitive stimulation, and the risk of visual fatigue. The use of a facial paradigm can address the above-mentioned limitations through emotionally resonant stimuli, offering diverse cognitive stimulation, and potentially reducing visual fatigue by introducing dynamic and engaging facial stimuli. In this context, this study is the first attempt to investigate the efficacy of facial paradigms in further improving the usability of DSP3S. The authors investigated three facial paradigms based on the smiley face, famous face, and family faces for DSP3S. The three facial paradigms are evaluated based on their effectiveness, efficiency, and satisfaction. Effectiveness was measured using classification performance and amplitude difference waveform. Whereas efficiency and satisfaction were measured using NASA-TLX, VAS-F scale, and SUS respectively. The obtained results showed that using the proposed family face intensification, efficiency, and satisfaction could be improved. However, no significant difference was observed in effectiveness among the three display paradigms. In this study, apart from investigating the usability of three display paradigms, authors also propose brain signal decoding using morphological filtering and extreme gradient boosting (XGBoost). Finally, the study concludes that the design of display paradigms using different intensification patterns affects the usability of the speller system and should be taken into consideration.

show abstract

Section: Comparative Analysismentioning

confidence: 72%

Comparative Evaluation of Facial Paradigms for Devanagari Script-based P300 Speller: Preliminary Findings

Bhandari,

Londhe,

Kshirsagar

2024

JDSIS

View full text Add to dashboard Cite

show abstract

“…Eliminating or shortening the calibration also reduces the mental load for the users; our experiments reflect that most subjects did not feel obvious fatigue. Second, by applying a zero-calibrated CNN (the subject-independent CNN or the self-training-based CNN) as a P300 detection model, this system achieves comparable performances to those of traditional P300 BCIs with full calibration [41], [42], [43]. Additionally, to the best of our knowledge, few studies have implemented zero-calibrated models online.…”

Section: Discussionmentioning

confidence: 99%

Eliminating or Shortening the Calibration for a P300 Brain–Computer Interface Based on a Convolutional Neural Network and Big Electroencephalography Data: An Online Study

Gao

Huang

et al. 2023

IEEE Trans. Neural Syst. Rehabil. Eng.

View full text Add to dashboard Cite

A brain-computer interface (BCI) measures and analyzes brain activity and converts it into computer commands to control external devices. Traditional BCIs usually require full calibration, which is time-consuming and makes BCI systems inconvenient to use. In this study, we propose an online P300 BCI spelling system with zero or shortened calibration based on a convolutional neural network (CNN) and big electroencephalography (EEG) data. Specifically, three methods are proposed to train CNNs for the online detection of P300 potentials: (i) training a subject-independent CNN with data collected from 150 subjects; (ii) adapting the CNN online via a semisupervised learning/self-training method based on unlabeled data collected during the user's online operation; and (iii) fine-tuning the CNN with a transfer learning method based on a small quantity of labeled data collected before the user's online operation. Note that the calibration process is eliminated in the first two methods and dramatically shortened in the third method. Based on these methods, an online P300 spelling system is developed. Twenty subjects participated in our online experiments. Average accuracies of 89.38%, 94.00% and 93.50% were obtained by the subject-independent CNN, the self-training-based CNN and the transfer learning-based CNN, respectively. These results demonstrate the effectiveness of our methods, and thus, the convenience of the online P300-based BCI system is substantially improved.

show abstract

“…Related work First degree polynomial Zhang et al (2016a), Haque et al (2016), Zhang et al (2016bZhang et al ( , 2017b, Krawczyk et al (2016Krawczyk et al ( , 2015, , Krawczyk et al (2013), , , Chaurasiya et al (2016), Obo et al (2016), Zhang et al (2017a), Onan et al (2016), Pourtaheri and Zahiri (2016), Saleh et al (2016, Ojha et al (2017), Davidsen and Padmavathamma (2015), Lacy et al (2015a), Kim and Cho (2015), Sikdar et al (2015Sikdar et al ( , 2014b, Jackowski et al (2014), Jackowski (2014,2015), Ojha et al (2014Ojha et al ( , 2015, Schaefer (2013), Wozniak (2009), Sikdar et al (2012Sikdar et al ( , 2014aSikdar et al ( , 2013, Kim and Cho (2008a), Liu et al (2007), Escovedo et al (2013aEscovedo et al ( , 2014Escovedo et al ( , 2013c…”

Section: Methodsmentioning

confidence: 99%

“…A wide variety of methods were proposed for this task, such as using genetic algorithms (Krawczyk et al, 2016;Ojha et al, 2017), particle swarm optimization (Saleh et al, 2016), flower pollination (Zhang et al, 2017a), differential evolution (Sikdar et al, 2012;Zhang et al, 2016bZhang et al, , 2017b, etc. Those methods can be applied to both homogeneous (Chaurasiya et al, 2016;Zhang et al, 2016bZhang et al, , 2017b and heterogeneous (Zhang et al, 2014;Ojha et al, 2015) base learner sets. For classification, methods may also differ in the number of voting weights, either by using one voting weight per classifier (e.g., Zhang et al, 2014;Obo et al, 2016) or one voting weight per classifier per class (e.g., Fatima et al, 2013;Sikdar et al, 2015;Davidsen & Padmavathamma, 2015).…”

Section: Linear Modelsmentioning

confidence: 99%

A survey of evolutionary algorithms for supervised ensemble learning

Cagnini

Dôres

Freitas

et al. 2023

The Knowledge Engineering Review

View full text Add to dashboard Cite

This paper presents a comprehensive review of evolutionary algorithms that learn an ensemble of predictive models for supervised machine learning (classification and regression). We propose a detailed four-level taxonomy of studies in this area. The first level of the taxonomy categorizes studies based on which stage of the ensemble learning process is addressed by the evolutionary algorithm: the generation of base models, model selection, or the integration of outputs. The next three levels of the taxonomy further categorize studies based on methods used to address each stage. In addition, we categorize studies according to the main types of objectives optimized by the evolutionary algorithm, the type of base learner used and the type of evolutionary algorithm used. We also discuss controversial topics, like the pros and cons of the selection stage of ensemble learning, and the need for using a diversity measure for the ensemble’s members in the fitness function. Finally, as conclusions, we summarize our findings about patterns in the frequency of use of different methods and suggest several new research directions for evolutionary ensemble learning.

show abstract

Binary DE-Based Channel Selection and Weighted Ensemble of SVM Classification for Novel Brain–Computer Interface Using Devanagari Script-Based P300 Speller Paradigm

Cited by 31 publications

References 89 publications

Comparative Evaluation of Facial Paradigms for Devanagari Script-based P300 Speller: Preliminary Findings

Comparative Evaluation of Facial Paradigms for Devanagari Script-based P300 Speller: Preliminary Findings

Eliminating or Shortening the Calibration for a P300 Brain–Computer Interface Based on a Convolutional Neural Network and Big Electroencephalography Data: An Online Study

A survey of evolutionary algorithms for supervised ensemble learning

Contact Info

Product

Resources

About