Comparison of classification techniques for the control of EOG-based HCIs

López, Alberto; Flecha, José Ramón Villar; Fernández, Marta; Ferrero, Francisco

doi:10.1016/j.bspc.2022.104263

Cited by 12 publications

(3 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A meta-analysis by Lopez et al (2023) Tsai et al (2008) utilized two-dimensional eye movements to allow users to generate characters by "drawing" them with their eyes but faced challenges with a relatively low accuracy rate of 72.1%, possibly due to involuntary saccades. The process of writing letters also implied significant messaging duration.…”

Section: Previous Workmentioning

confidence: 99%

Leveraging Deep Neural Networks for Lucid Dream Communication via Two-Dimensional Electrooculography

Amo,

Godt,

Leugering

et al. 2023

Preprint

View full text Add to dashboard Cite

This paper introduces a novel approach to lucid dream communication, leveraging electrooculographical signals for real-time, natural language messaging within dreams. Beyond traditional horizontal eye movement techniques, our methodology incorporates vertical eye movements, enhancing the expressive range of communication. Recognizing the potential for lucid dream communication in diverse settings, including home and laboratory environments with varying conditions, we explore two distinct approaches.Methodologically, we employ a grid system enabling dreamers to encode messages into eye gestures. We develop two Deep Neural Network models for classifying and decoding eye movement data. One model integrates a dynamic threshold algorithm with a convolutional neural network for gesture classification, while the other uses a static threshold algorithm and rate of change analysis for classification, followed by transformer-based decoding of grid-encoded natural language sentences. Tested in two pilot studies with awake participants, our setups exhibit promising results.In Pilot Study 1, we attained an average accuracy of 77.6% in classifying eye gestures across subjects. Pilot Study 2 demonstrates an average accuracy of 97.6% in classifying elementary gestures, sustaining a 90.3% average accuracy post-decoding, successfully recovering the original English language message in most cases. Our method exhibits an average eye typing speed of 19.7 characters per minute.Our results emphasize the practicality of real-time natural language dream communication, demonstrating its applicability in both laboratory and home settings. If successfully replicated during lucid dreaming states, this pioneering method holds the potential to pave the way for novel research on dreams, memory, and consciousness.

show abstract

Section: Previous Workmentioning

confidence: 99%

Leveraging Deep Neural Networks for Lucid Dream Communication via Two-Dimensional Electrooculography

Amo,

Godt,

Leugering

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…High-pass filtering is utilized to eliminate low-frequency drift and baseline wander from EOG signals, facilitating the isolation of components associated with rapid eye movements. The benefits of employing high-pass filtering include [25,26]:…”

Section: High-pass Filteringmentioning

confidence: 99%

A review for filtering techniques of the Electrooculography (EOG) signals

Aws M Abdullah,

Ali R Ibrahim,

Ammar A Al-Hamadani

et al. 2023

Global J. Eng. Technol. Adv.

View full text Add to dashboard Cite

Electrooculography (EOG) is a non-invasive method employed for the measurement of the electrical potential produced by ocular movements. EOG signals frequently encounter contamination from diverse forms of interference, thereby impeding precise analysis and interpretation. In order to address these obstacles, numerous filtering methodologies have been devised to ameliorate the quality of EOG signals. The objective of this paper is to examine the filtering techniques commonly employed for EOG signals, elucidating their respective benefits and limitations.

show abstract

“…The use of EOG in [3][4][5][6][7] the literature reviewed shows mostly its application by users with motor disabilities, turning their eyes to communicate. Therefore, the monitoring of biological signals such as EOG allows the integration of everyday objects, as mentioned in [8], where writing is performed by selecting a group of limited words for the response of short sentences; another application handled in [9] has is the electrical control of a wheelchair by eye movements; as well as in [10], the recognition of eye movement by different parameters detected in the signal, when visualizing different abstract images; the movement of the mouse cursor when receiving a signal from both eyes is described in [11], and the directional control of a robot in [12] were designed by a method based on saccadic movements and eye reflexes that were obtained as the average speed, maximum speed and voltage range in the developed model and did not include the fixed gaze and blinking movement.…”

Section: Introductionmentioning

confidence: 99%

EOG Signal Classification with Wavelet and Supervised Learning Algorithms KNN, SVM and DT

Perez

Reynoso

Gutiérrez

et al. 2023

Sensors

View full text Add to dashboard Cite

The work carried out in this paper consists of the classification of the physiological signal generated by eye movement called Electrooculography (EOG). The human eye performs simultaneous movements, when focusing on an object, generating a potential change in origin between the retinal epithelium and the cornea and modeling the eyeball as a dipole with a positive and negative hemisphere. Supervised learning algorithms were implemented to classify five eye movements; left, right, down, up and blink. Wavelet Transform was used to obtain information in the frequency domain characterizing the EOG signal with a bandwidth of 0.5 to 50 Hz; training results were obtained with the implementation of K-Nearest Neighbor (KNN) 69.4%, a Support Vector Machine (SVM) of 76.9% and Decision Tree (DT) 60.5%, checking the accuracy through the Jaccard index and other metrics such as the confusion matrix and ROC (Receiver Operating Characteristic) curve. As a result, the best classifier for this application was the SVM with Jaccard Index.

show abstract

Comparison of classification techniques for the control of EOG-based HCIs

Cited by 12 publications

References 23 publications

Leveraging Deep Neural Networks for Lucid Dream Communication via Two-Dimensional Electrooculography

Leveraging Deep Neural Networks for Lucid Dream Communication via Two-Dimensional Electrooculography

A review for filtering techniques of the Electrooculography (EOG) signals

EOG Signal Classification with Wavelet and Supervised Learning Algorithms KNN, SVM and DT

Contact Info

Product

Resources

About