Publication Details

Single-trial extraction of event-related potentials (ERPs) and classification of visual stimuli by ensemble use of discrete wavelet transform with Huffman coding and machine learning techniques

AMIN Ullah Hafeez, ULLAH Rafi, REZA Faruque Mohammed and MALIK Aamir Saeed. Single-trial extraction of event-related potentials (ERPs) and classification of visual stimuli by ensemble use of discrete wavelet transform with Huffman coding and machine learning techniques. Journal of NeuroEngineering and Rehabilitation, vol. 20, no. 70, 2023, pp. 1-17. ISSN 1743-0003.
Czech title
Extrakce potenciálů souvisejících s událostmi (ERP) a klasifikace vizuálních stimulů s využitím diskrétní vlnkové transformace s Huffmanovým kódováním a technik strojového učení
Type
journal article
Language
english
Authors
Amin Ullah Hafeez ()
Ullah Rafi ()
Reza Faruque Mohammed ()
Malik Aamir Saeed, Ph.D. (DCSY FIT BUT)
Keywords

Single trials analysis (ERPs); visual object detection; discrete wavelet transform; Huffman coding; machine learning classifiers 

Abstract

Background: Presentation of visual stimuli can induce changes in EEG signals that are typically detectable by averaging together data from multiple trials for individual participant analysis as well as for groups or conditions analysis of multiple participants. This study proposes a new method based on the discrete wavelet transform with Huffman coding and machine learning for single-trial analysis of event-related potential (ERPs) and classification of different visual events in the visual object detection task. 

Method: EEG single trials are decomposed with discrete wavelet transform (DWT) up to the 4 th level of decomposition using a biorthogonal B-spline wavelet. The coefficients of DWT in each trial are thresholded to discard sparse wavelet coefficients, while the quality of the signal is well maintained. The remaining optimum coefficients in each trial are encoded into bitstreams using Huffman coding, and the codewords are represented as a feature of the ERP signal. The performance of this method is tested with real visual ERPs of sixty-eight subjects. 
Results: The proposed method significantly discards the spontaneous EEG activity, extracts the single-trial visual ERPs, represents the ERP waveform into a compact bitstream as a feature, and achieves promising results in classifying the visual objects with classification performance metrics: accuracies 93.606.5, sensitivities 93.554.5, specificities 94.854.2, precisions 92.505.5, and area under the curve (AUC) 0.930.3 using SVM and k-NN machine learning classifiers. 
Conclusion: The proposed method suggests that the joint use of discrete wavelet transform (DWT) with Huffman coding has the potential to efficiently extract ERPs from background EEG for studying evoked responses in single-trial ERPs and classifying visual stimuli. The proposed approach has O(N) time complexity and could be implemented in real-time systems, such as the brain-computer interface (BCI), where fast detection of mental events is desired to smoothly operate a machine with minds.
Published
2023
Pages
1-17
Journal
Journal of NeuroEngineering and Rehabilitation, vol. 20, no. 70, ISSN 1743-0003
Publisher
Springer Nature Switzerland AG
DOI
10.1186/s12984-023-01179-8
UT WoS
001000503100001
EID Scopus
2-s2.0-85160951495
BibTeX 
@ARTICLE{FITPUB12746,
   author = "Hafeez Ullah Amin and Rafi Ullah and Mohammed Faruque Reza and Saeed Aamir Malik",
   title = "Single-trial extraction of event-related potentials (ERPs) and classification of visual stimuli by ensemble use of discrete wavelet transform with Huffman coding and machine learning techniques",
   pages = "1--17",
   journal = "Journal of NeuroEngineering and Rehabilitation",
   volume = 20,
   number = 70,
   year = 2023,
   ISSN = "1743-0003",
   doi = "10.1186/s12984-023-01179-8",
   language = "english",
   url = "https://www.fit.vut.cz/research/publication/12746"
}
Files
Back to top