Ocular Artifacts Reduction in EEG Signals Acquired at Construction Sites by Applying a Dependent Component Analysis (DCA)

Yizhi Liu, Mahmoud Habibnezhad, Houtan Jebelli, Somayeh Asadi, Sang Hyun Lee

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Workers' poor mental status (e.g., stress and mental fatigue) is a critical factor in accidents, errors, and loss of productivity at construction sites. With recent advances in wearable technologies, workers' mental status can be monitored by examining patterns of brainwaves in their electroencephalogram (EEG) signal. Acquiring high-quality EEG in the field using a wearable device is a critical step in assessing worker mental status because there are several types of significant signal artifacts (i.e., noise) can interfere with the actual signal. Among them, ocular signal artifacts (e.g., eye movements and blinks) are the most challenging because they share a similar frequency range with EEG. To reduce ocular artifacts, researchers applied principal component analysis (PCA) and independent component analysis (ICA) method to separate intrinsic artifacts from workers' brainwave signals. Though it reduces ocular signal artifacts, it is limited to detect and reduce dependent signal noises, particularly ocular artifacts (e.g., eye blinking and eye movement). To address this limitation, the authors apply a dependence component analysis (DCA) method for detecting correlative signal artifacts. Nine construction workers' brainwaves collected at multiple construction sites were used to examine the performance of the proposed method. Then, the performance of the DCA is compared with two traditional methods, PCA and ICA. According to the results, there are significant improvements in the output signal-to-noise ratio (SNR) and mean square error (MSE) compared to ICA and PCA. The results confirm that the proposed DCA method outperforms the traditional methods in reducing ocular signal artifacts from a wearable EEG headset at construction sites. The result opens up the opportunity to capture a higher quality EEG and get a better assessment of workers' mental status in the field using a wearable EEG in the field.

Original languageEnglish (US)
Title of host publicationConstruction Research Congress 2020
Subtitle of host publicationComputer Applications - Selected Papers from the Construction Research Congress 2020
EditorsPingbo Tang, David Grau, Mounir El Asmar
PublisherAmerican Society of Civil Engineers (ASCE)
Pages1281-1289
Number of pages9
ISBN (Electronic)9780784482865
StatePublished - 2020
EventConstruction Research Congress 2020: Computer Applications - Tempe, United States
Duration: Mar 8 2020Mar 10 2020

Publication series

NameConstruction Research Congress 2020: Computer Applications - Selected Papers from the Construction Research Congress 2020

Conference

ConferenceConstruction Research Congress 2020: Computer Applications
CountryUnited States
CityTempe
Period3/8/203/10/20

All Science Journal Classification (ASJC) codes

  • Civil and Structural Engineering
  • Building and Construction

Fingerprint Dive into the research topics of 'Ocular Artifacts Reduction in EEG Signals Acquired at Construction Sites by Applying a Dependent Component Analysis (DCA)'. Together they form a unique fingerprint.

Cite this