Unsupervised clustering method to detect microsaccades

Otero‐Millan, Jorge; Alba-Castro, José Luis; Macknik, Stephen L.; Martínez-Conde, Susana

doi:10.1167/14.2.18

Cited by 100 publications

(88 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…This method has the advantage of considering intraand interindividual variation in high-frequency noise and saccades [15,21] . The combination of the variable velocity algorithm and the clustering technique allowed the definition of a low-velocity limit for potential fixational saccades, which ensured optimal conditions for the detection of all true fixational saccades [16] . Previous studies have shown that fixational saccades with an amplitude of around 0.15 degrees are the most frequent, and, therefore, the upper limit for the amplitude of fixational saccades has been set to 1 degree [22,23] .…”

Section: Discussionmentioning

confidence: 99%

“…Ophthalmic Res 2017;58:142-149 DOI: 10.1159/000476038 145 these 3 parameters were used to construct a space vector, and the total number of space vectors was grouped according to length using the clustering technique described previously [16] .…”

Section: Fixation and Diabetic Maculopathymentioning

confidence: 99%

“…An example is shown in Figure 1 . This technique allowed an objective extraction of fixational saccades with a low detection error while maintaining a boundary between fixational and nonfixational saccades [16] .…”

Section: Fixation and Diabetic Maculopathymentioning

confidence: 99%

See 2 more Smart Citations

Binocular Fixation Reduces Fixational Eye Movements in the Worst Eye of Patients with Center-Involving Diabetic Macular Edema

Jakobsen

Larsen²,

Bek³

2017

Ophthalmic Res

View full text Add to dashboard Cite

Purpose: Treatment of diabetic maculopathy with vascular endothelial growth factor inhibitors is in some patients ineffective, and, therefore, parameters predicting visual outcome after treatment should be identified. It has been shown that fixational saccades are increased in patients with reduced visual acuity secondary to diabetic maculopathy, but it is unknown to what extent these saccades in an eye affected by diabetic maculopathy are influenced by the other eye during binocular fixation. Methods: In 57 eyes from 29 diabetic patients with clinically significant macular edema, fixational eye movements were recorded using the iView X™ video-based eye tracker, and quantitative measures of fixation with the worst eye obtained during monocular and binocular fixation were compared. Results: Fixational saccades during monocular fixation had a significantly higher frequency (p = 0.005), a larger amplitude (p = 0.03), and involved a larger retinal area (p = 0.02) than during binocular fixation. There was a significant negative correlation (r² = 0.18, p = 0.02) between visual acuity and the area of fixation during monocular but not during binocular fixation (r² = 0.007, p = 0.68). Conclusion: Binocular fixation can reduce the area of fixation and the amplitude of fixational saccades in the worst eye of patients with diabetic maculopathy. Fixational saccades in diabetic maculopathy should be studied during monocular fixation.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Fixation and Diabetic Maculopathymentioning

confidence: 99%

See 1 more Smart Citation

Binocular Fixation Reduces Fixational Eye Movements in the Worst Eye of Patients with Center-Involving Diabetic Macular Edema

Jakobsen

Larsen²,

Bek³

2017

Ophthalmic Res

View full text Add to dashboard Cite

show abstract

“…During fixations, subjects often make very small eye movements called microsaccades [13,47]. These are saccades with amplitudes of less than 2 ı of visual angle.…”

Section: Eye Tracking: a Gold Standard For Overt Attentionmentioning

confidence: 99%

How to Measure Attention?

Mancaş

Ferrera

2016

From Human Attention to Computational Attention

View full text Add to dashboard Cite

Researchers who are interested in attention generally have one or more of the following goals: (1) to identify sources of information in the environment that are selected and prioritized by the observer, (2) to quantify the effect of attention on task performance, and (3) to identify neural correlates of attention. When considering methods to measure attention, it is important to distinguish between overt and covert orienting mechanisms. Overt attention is expressed by movements of the body and can be measured directly by determining the position and velocity of the relevant effectors -primarily the eyes, head, and hands. Covert orienting refers to the ability to direct attention without body movement and is primarily measured by differences in task performance (e.g., reaction time) that cannot be attributed to changes in the external stimulus.In this chapter, we will focus on quantitative techniques that provide finegrain spatial and temporal information about attentive responses at a macroscale. We do not discuss the many psychophysical paradigms that have been used to infer attention based on the speed and accuracy of observer judgments. Micromeasurements of single neuron or several neurons using microelectrodes are not described here. However, in the Chap. 6, the use of microelectrodes to measure single neuron responses is described.At a macroscale, the attentive response can be either measured directly in the brain or indirectly through participants' behavior. Only one of the techniques that M. Mancas ( ) Numediart Institute, University of Mons (UMONS), 31, Bd. Dolez,

show abstract

“…Exists several methods and algorithms for identifying saccades in electrooculograms, the vast majority of them based on kinetic thresholds [11,14,31,26], using suppervised learning [28,6], unsupervised learning [20] or other novel approachs [18,22] like particle filters [8]. These methods were designed to work in a not constrained scheme having advantages in a lot of scenarios.…”

Section: Introductionmentioning

confidence: 99%

Non Spontaneous Saccadic Movements Identification in Clinical Electrooculography Using Machine Learning

Becerra-García

García−Bermúdez

Joya-Caparrós

et al. 2015

Advances in Computational Intelligence

View full text Add to dashboard Cite

Abstract. In this paper we evaluate the use of the machine learning algorithms Support Vector Machines, K-Nearest Neighbors, CART decision trees and Naive Bayes to identify non spontaneous saccades in clinical electrooculography tests. Our approach tries to solve problems like the use of manually established thresholds present in classical methods like identification by velocity threshold (I-VT) or identification by dispersion threshold (I-DT). We propose a modification to an adaptive threshold estimation algorithm for detecting signal impulses without the need of any user input. Also, a set of features were selected to take advantage of intrinsic characteristics of clinical electrooculography tests. The models were evaluated with signals recorded to subjects affected by Spinocerebellar Ataxia type 2 (SCA2). Results obtained by the algorithm shows accuracies over 97%, recalls over 97% and precisions over 91% for the four models evaluated.

show abstract

Unsupervised clustering method to detect microsaccades

Cited by 100 publications

References 48 publications

Binocular Fixation Reduces Fixational Eye Movements in the Worst Eye of Patients with Center-Involving Diabetic Macular Edema

Binocular Fixation Reduces Fixational Eye Movements in the Worst Eye of Patients with Center-Involving Diabetic Macular Edema

How to Measure Attention?

Non Spontaneous Saccadic Movements Identification in Clinical Electrooculography Using Machine Learning

Contact Info

Product

Resources

About