Unsupervised Eye Blink Artifact Identification in Electroencephalogram

Egambaram, Ashvaany; Badruddin, Nasreen; Asirvadam, Vijanth S.; Fauvet, Éric; Stolz, Christophe; Begum, Tahamina

doi:10.1109/tencon.2018.8650467

Cited by 4 publications

(4 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Then, the eye blink region detection, eye blink component extraction and eye blink artifact removal are explained. Finally, the performance metric is calculated upon the removal output accordingly with the original simulated EEG data that is juxtaposed with the performance metric from Egambaram et al [19] to prove the effectiveness of our method.…”

Section: Methodsmentioning

confidence: 99%

“…For example, EMD is incorporated with canonical correlation analysis (CCA) in a way that the EMD is made to produce partial separation of eye blink artifact from the EEG data. The CCA is used to find the canonical weights that can be used to approximate the eye blink component that is free from EEG mixing [19]. Nevertheless, EMD can be utilized solely to extract the eye blink component without combining it with other techniques for its empirical method in decomposing the input signal.…”

Section: Eye Blink Component Extractionmentioning

confidence: 99%

“…X(t) is the eye blink contaminated-EEG, while Y(t) is the pure EEG component and Z(t) is the eye blink artifact. The EEG data used in the experiment to assess the proposed technique is simulated in a way that it is possible to compare the performance metrics values, which is documented in [19]. Exponential functions represent the eye blink components Z(t) with different peak magnitudes that can be expressed mathematically as follows:…”

Section: Eeg Dataset Preparationmentioning

confidence: 99%

“…The EEG dataset used to measure the performance metric is fully-simulated EEG data as described in Subsection 3.1. This is done to compare the performance metrics with the eye blink removal technique proposed by Egambaram et al [19]. The generation of fully-simulated EEG for component Y(t), Z(t) and X(t) are iterated until 100 units are obtained.…”

Section: Eeg Dataset Structurementioning

confidence: 99%

See 3 more Smart Citations

Eye Blink Identification and Removal From Single-Channel Eeg Using Emd With Energy Threshold and Adaptive Filter

Jefri

Rahman

Malek

et al. 2023

IIUMEJ

View full text Add to dashboard Cite

Electroencephalography (EEG) is a non-invasive method for measuring electrical activity in the brain, which reflects the underlying neural activity of the brain. In recent years, portable EEG devices become more ubiquitous in domestic uses, research and clinical applications due to their compact design and ease of use in various settings. Like many other biosignal modalities, EEG devices are prone to the interference of physiological artifacts, mainly from eye blinking. However, since portable EEGs are equipped with only a few channels at most or sometimes just a single channel, removing the eye blink artifact from the EEG data is a challenge. The conventional artifact removal method using source separation cannot be applied to a single-channel EEG signal. Eye blink artifact removal is important because its spectrum overlaps with the EEG’s theta and delta frequency bands, which can be confused with brain activity. Univariate-based removal method is compatible with EEG data with few channels. This paper presents a method to remove eye blink artifact based on single-channel EEG processing using Empirical Mode Decomposition (EMD) and Adaptive Noise Cancellation (ANC) system. By applying energy thresholds in EMD, there is no need to incorporate EMD with other methods to extract eye blink component accurately. ANC is used to converge the extracted eye blink component for effective eye blink artifact removal with very minimal changes to affected EEG data. The proposed method was tested on simulated EEG signals, and the result showed a good Root Mean-Square Error (RMSE) average value of the cleaned EEG ( ) and a high Correlation Coefficient (CC) average value of the cleaned EEG ( ). ABSTRAK: Electroensefalografi (EEG) adalah kaedah bukan invasif untuk mengukur aktiviti elektrik di dalam otak, yang mencerminkan aktiviti saraf dalam otak. Kebelakangan ini, peranti EEG mudah alih menjadi lebih meluas dalam kegunaan domestik, penyelidikan dan aplikasi klinikal kerana reka bentuknya yang padat dan kemudahan penggunaan dalam pelbagai tetapan. Seperti kebanyakan modaliti biosignal yang lain, peranti EEG terdedah kepada gangguan artifak fisiologi, terutamanya daripada mata kerdipan mata. Walau bagaimanapun, memandangkan EEG mudah alih dilengkapi dengan paling banyak pun hanya beberapa saluran, atau kadangkala hanya satu saluran, mengalih keluar artifak kerdipan mata daripada data EEG adalah satu cabaran. Kaedah penyingkiran artifak konvensional menggunakan pemisahan sumber tidak dapat digunakan pada alat EEG satu saluran. Penyingkiran artifak berkelip mata adalah penting kerana spektrumnya bertindih dengan jalur frekuensi theta dan delta EEG, maka boleh dikelirukan dengan aktiviti otak. Kaedah penyingkiran berasaskan univariat adalah serasi untuk data EEG dengan saluran yang sedikit. Kertas kerja ini membentangkan kaedah untuk membuang artifak kelip mata berdasarkan pemprosesan EEG saluran tunggal menggunakan Penguraian Mod Empirikal (EMD) dan Pembatalan Bunyi Adaptif (ANC). Dengan menggunakan ambang tenaga dalam EMD, tiada keperluan untuk menggabungkan EMD dengan kaedah lain bagi mengekstrak komponen kerdipan mata dengan tepat. ANC digunakan untuk menumpu komponen kerdipan mata yang diekstrak bagi penyingkiran artifak kerdipan mata yang berkesan dengan perubahan yang sangat minimum pada data EEG yang terjejas. Kaedah yang dicadangkan telah diuji pada signal EEG yang disimulasi, serta hasilnya menunjukkan nilai purata Ralat Min Kuasa Dua Purata (RMSE) yang baik bagi EEG yang dibersihkan (0.3211±0.2738), dan nilai purata Pekali Korelasi (CC) yang baik bagi EEG yang dibersihkan (0.9430±0.0839). ABSTRAK: Sabut gentian kelapa sawit berpotensi sebagai bahan mentah biojisim lignoselulosa bagi menambah nilai produk biojisim seperti bahan bio api generasi kedua, biokomposit atau biotenaga. Walau bagaimanapun, komposisi lignin yang wujud dalam biojisim lignoselulosa menentang proses tambah nilai dan melindungi komposisi selulosa, dengan itu mengehadkan penukaran selulosa kepada produk yang lebih berharga. Kaedah hibrid ozonasi-ultrasonik sebagai kaedah merendahkan lignin, mula mendapat perhatian sebagai kaedah berkesan. Selain itu, Reka Bentuk Kotak-Behnken (BBD) telah digunakan bagi menyiasat setiap kesan pembolehubah bebas pada keadaan proses prarawatan menggunakan kaedah permukaan tindak balas (RSM), iaitu masa tindak balas (30-90) min, suhu tindak balas (20 -40) oC dan kadar aliran ozon (1-3) L/min terhadap tindak balas pada peratusan degradasi lignin (%). Keadaan optimum bagi proses prarawatan ditentukan menggunakan graf fungsi keboleh inginan. Dapatan kajian menunjukkan bahawa masa tindak balas, suhu tindak balas, dan kadar aliran ozon mempunyai kesan yang signifikan terhadap degradasi lignin (p<0.05). Keadaan optimum peratusan degradasi lignin tertinggi adalah pada 92.08% pada suhu tindak balas 30 oC dengan kadar aliran ozon 2 L/min selama 60 minit masa tindak balas. Penurunan puncak penyerapan lignin pada 1638 cm-1 dan 1427 cm-1 disokong oleh keputusan analisis peningkatan kehabluran sampel selepas prarawatan degradasi lignin sebanyak 80.20% dan telah disahkan oleh perubahan morfologi sabut gentian selepas proses prarawatan menunjukkan bahawa sebatian lignin telah berjaya didegradasi daripada produk selulosa sabut gentian.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Eye Blink Component Extractionmentioning

confidence: 99%

Section: Eeg Dataset Preparationmentioning

confidence: 99%

Section: Eeg Dataset Structurementioning

confidence: 99%

See 2 more Smart Citations