An efficient P300 detection algorithm based on Kernel Principal Component Analysis-Support Vector Machine

• Published in: Computers & electrical engineering Vol. 97; p. 107608
• Main Authors: Hashmi, Mohammad Farukh, Kene, Jagdish D., Kotambkar, Deepali M., Matte, Praveen, Keskar, Avinash G.
• Format: Journal Article
• Language: English
• Published: Amsterdam Elsevier Ltd 01.01.2022; Elsevier BV
• Subjects: Accuracy; Algorithms; Brain-Computer Interface Technology (BCI); Discrete Wavelet Transform (DWT); Human-computer interface; Kernel Principal Component Analysis (KPCA); Principal components analysis; Signal classification; Signal detection; Single-trial P300 detection; Support Vector Machine (SVM); Support vector machines; Brain-Computer Interface Technology (BCI); Kernel Principal Component Analysis (KPCA); Discrete Wavelet Transform (DWT); Single-trial P300 detection; Support Vector Machine (SVM)
• ISSN: 0045-7906; 1879-0755
• DOI: 10.1016/j.compeleceng.2021.107608

Human-machine interaction using brain signals has been made possible by the advent of a technology popularly known as a brain-computer interface (BCI). P300 is the most studied event related potentials (ERP) and is used in many BCI systems. The existing multi-trial P300 detection methods suffer drawbacks of being time-consuming and computationally complex, whereas, the existing single-trial methods are apt at achieving only moderate accuracy levels. In this paper, a novel approach to achieve a high level of accuracy for a single trial P300 signal detection amidst noise and artifacts. In this method, features were obtained from wavelet coefficients; subsequently, feature dimensions were reduced, thereby enhancing the speed of classification along with a manifold improvement in the accuracy of P300 signal classification. An accuracy of 98.53% was achieved for Subject S1 and 99.25% for Subject S2 using the proposed method. A high level of accuracy was obtained, compared to many existing techniques. Moreover, the speed of classification improved with the use of reduced feature dimensions.