EOG-Based Eye Movement Classification and Application on HCI Baseball Game

Lin, Chin‐Teng; King, Juang-Tai; Bharadwaj, P. Mani; Chen, Chih‐Hao; Gupta, Akanksha; Ding, Weiping; Prasad, Mukesh

doi:10.1109/access.2019.2927755

Cited by 27 publications

(10 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Four channels are used for recording the horizontal and vertical movement. 40 Gracia et al proposed a Wearable Device for acquisition for EOG and frontalis Electromyography (EMG) signals simultaneously using a facial mask which consist of electrodes. A right leg driver is coupled to amplification stage to increase the CMRR of the ciruit.…”

Section: Discussionmentioning

confidence: 99%

Non-invasive technique to detect diabetic retinopathy based on Electrooculography signal using machine learning classifiers

Archana

Rajalakshmi

2022

Proc Inst Mech Eng H

View full text Add to dashboard Cite

Single-channel Electrooculogram (EOG) is proposed for detecting diabetic retinopathy. The Corneal-retinal potential of the eyes plays a vital role in the acquisition of Electrooculography. Diabetes is the most prevalent disease and for one out of three people with diabetes above 40 years, diabetic retinopathy occurs. It is necessary for the early detection of diabetic retinopathy as it is one of the primary reasons for blindness in the population. The potential difference between cornea and retina leads to the acquisition of EOG signal. The proposed study aims to design a low-cost miniaturized hardware circuit to obtain EOG signal using second order filters without compromising in accuracy of the outcome signal and to classify the signal into normal and diabetic retinopathy subjects by extracting the statistical features like kurtosis, mean, median absolute deviation, standard deviation, and range from software filtered EOG signal. Among the classifiers used, Support vector machine (SVM) shows a higher accuracy of 93.33%. The sensitivity, specificity and Area Under Curve (AUC) values of SVM are 96.43%, 90.625%, 0.93% is considered as more favorable outcome for the proposed method and it supports the developed prototype and processing methodology. The novelty of the research is based on proposing and exploring a non-invasive methodology for Diabetic retinopathy diagnosis based on EOG signal. Thus, the designed hardware is simple in operation and cost effective, provides an affordable and non-invasive diagnostic tool for diabetic retinopathy patients

show abstract

Section: Discussionmentioning

confidence: 99%

Non-invasive technique to detect diabetic retinopathy based on Electrooculography signal using machine learning classifiers

Archana

Rajalakshmi

2022

Proc Inst Mech Eng H

View full text Add to dashboard Cite

show abstract

“…By acquiring the vertical and horizontal EOG, patients with severe motor disabilities have communicated with their surrounding people using EOG based speller [25]. Eight directional eye movement classification algorithm has been an effective way to analyse the aftermath effect of noise in EOG signals [26][27][28]. Several human-machine interface technologies utilize horizontal EOG signal, which has been used as a control strategy for a mobility aid [29].…”

Section: Literature Reviewmentioning

confidence: 99%

Study of electrooculography signal acquisition sites for assistive device applications

Raj¹

2021

IJATEE

View full text Add to dashboard Cite

Electrooculography (EOG) is a technique that involves the measurement of the corneo-retinal standing potential of the eye. The human eye acts as a dipole between the cornea (positive potential) and the retina (negative potential), creating an electric field around the eyeball. The resulting electric signal obtained from this field is called electrooculogram. These signals, generated by eye movements, could be measured by employing different electrode placement configurations for the acquisition. The properties of these signals change depending on the number and placement of the electrodes. The study conducted here describes EOG signal acquisition using new electrode placement configurations that employ fewer facial electrodes placed on the patient. Three pre-gelled disposable electrodes were utilized for this purpose. Only one electrode was placed on a facial location, enhancing patient comfort during the acquisition procedure. To support this study, a lowcost signal acquisition hardware was developed. Using active filtering and amplification, appropriate signal processing techniques were executed upon the horizontal EOG signal acquired to reduce noise and interference due to external conditions. Hence, this paper presents the findings of new electrode placement sites for the acquisition of EOG signals which could be used for assistive device applications while restricting the number of facial electrodes to one. Most of the studies regarding the EOG signal acquisition had been using all electrodes in the face region. In contrast, we reduced the number of electrodes in the face region, thereby providing patient comfort. The comparison was made mainly on the acquired data from these new locations to discover the configuration with the optimal signal response using data obtainedfrom seven healthy subjects. The amplitude values were being compared from the new locations with the standard acquisition sites. The findings of this study were found to have a productive result. The total gain of the system required for new electrode placement configurations was two times more than the total gain required for standard acquisition sites, and also, the amplitude was less but can be helpful for assistive device applications. The average peak to peak amplitude value of the EOG signal for the new site came around about 1.25 volt.

show abstract

“…In [6], a goggle-like device is used to acquire EOG signals to classify eye movements so that players can perform increasingly difficult sequences of eye movements. In [7], EOG is used to position gaze so that an agent throws a baseball in the chosen direction, with eight directional targets available.…”

Section: Introductionmentioning

confidence: 99%

A Reinforcement Learning Assisted Eye-Driven Computer Game Employing a Decision Tree-Based Approach and CNN Classification

et al. 2021

View full text Add to dashboard Cite

Human-Machine Interfaces employing biosignal-based inputs are hard to translate to reallife applications, in part because of the difficulty of developing generalized models to classify physiological events representing a user's actions. In the proposed framework, an Electrooculography (EOG)-based game is operated through a pipeline of decision methods. These include a user-independent classification model of eye movements using a Convolutional Neural Network (CNN), which is fed with images created from signal windows, and an Ensemble of Utility Decision Networks (EUDN), which moderates the impact of oftentimes conflicting ocular events while enabling a more natural level of control over the interface. The CNN and the EUDN replace the normally used feature-based ocular event detection methods for EOG. Finally, a Reinforcement Learning-based game actuation approach simultaneously updates multiple (State, Action) pairs for each rewarded outcome, intervenes to mitigate the consequences of wrongful game Commands, and can be used as part of a "shared-control" paradigm based on EOG. Results show a positive impact of Reinforcement Learning both in improving participants' game performance as well as in reducing some of their subjective workload indicators.

show abstract

EOG-Based Eye Movement Classification and Application on HCI Baseball Game

Cited by 27 publications

References 24 publications

Non-invasive technique to detect diabetic retinopathy based on Electrooculography signal using machine learning classifiers

Non-invasive technique to detect diabetic retinopathy based on Electrooculography signal using machine learning classifiers

Study of electrooculography signal acquisition sites for assistive device applications

A Reinforcement Learning Assisted Eye-Driven Computer Game Employing a Decision Tree-Based Approach and CNN Classification

Contact Info

Product

Resources

About