Using results of eye movement signal analysis in the neural network recognition of otoneurological patients

Juhola, Martti; Aalto, Heikki; Hirvonen, Timo

doi:10.1016/j.cmpb.2007.02.008

Cited by 11 publications

(5 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Some other parameter values were given by our earlier research 12,13,15,16 and were also experimentally found. The following algorithm is divided into two parts: signal analysis and modeling.…”

Section: Methodsmentioning

confidence: 95%

“…(6) Average velocities of slow phases. The sampling frequency of 50 Hz (20 ms interval) is too low for the accurate determination of fast phases, which are commonly short, being normally less than 100 ms. 13 Thus, linear regression is used, as above, to estimate the average angular velocity of each slow phase found. In fact, these are still sheer nystagmus beat candidates since their ''extreme'' cases have to be rejected in the following step.…”

Section: Methodsmentioning

confidence: 99%

“…In addition, if the upper bound calculated proved to be greater than 40°/s, the upper bound would be this value found maximal in our earlier research. 13 This pruning is performed separately for each of the horizontal, vertical, and torsional directions. Thus, if even one of three is invalid for a nystagmus beat candidate, the whole beat is discarded.…”

Section: Methodsmentioning

confidence: 99%

See 2 more Smart Citations

Signal Analysis of Three-dimensional Nystagmus for Otoneurological Investigations

et al. 2010

Self Cite

View full text Add to dashboard Cite

Three-dimensional signal analysis can be applied to eye movements called nystagmus in order to study otoneurological patients suffering from vertigo and other balance problems. We developed an analysis and modeling algorithm for three-dimensional nystagmus measured by a video-oculography system. We were also interested in verifying an otoneurological hands-on convention called Ewald's first law in a strict physiological sense in vestibular patients. We recorded nystagmus from 42 patients all suffering from vertigo or dizziness. The underlying pathology was unilateral in 39 patients, bilateral in one patient, and central in two patients. Video-oculography was used to record three-dimensional nystagmus to separately produce horizontal, vertical, and torsional signals for each eye. On the basis of signal analysis techniques and straightforward vector calculus, we were able to recognize slow phases of nystagmus to compute their angular velocities to estimate from which part of the inner ear the disorder originated. We found that for all 42 patients the plane of one of the two horizontal semicircular canals was the closest. We were able to quantitatively estimate the influence of different semicircular canals, and, despite the pathology, horizontal canals seemed to be predominant in driving the nystagmus. The signal analysis and modeling algorithm developed is effective in studying otoneurological problems registered with nystagmus and opens new insights in three-dimensional nystagmography. Our results strongly support Ewald's first law.

show abstract

Section: Methodsmentioning

confidence: 95%

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Signal Analysis of Three-dimensional Nystagmus for Otoneurological Investigations

et al. 2010

Self Cite

View full text Add to dashboard Cite

show abstract

“…Furthermore, aside from EEG signals, eye movements (EM) data can be used to identify the focus of users' attention, in order to determine their subconscious behaviors [12]. Moreover, in recent times, EM data are more readily available and accessible than in the past; not only are EM data being used in several areas of medicine, but also their popularity is growing among researchers from different disciplines [13]. Emslie et al [14] studied the EM signals of depressed children and normal control; they observed that the rate of EM is slower in children with depression than in normal control.…”

Section: A Related Workmentioning

confidence: 99%

Multimodal Mild Depression Recognition Based on EEG-EM Synchronization Acquisition Network

Zhu

Wang

et al. 2019

IEEE Access

View full text Add to dashboard Cite

In this paper, we used electroencephalography (EEG)-eye movement (EM) synchronization acquisition network to simultaneously record both EEG and EM physiological signals of the mild depression and normal controls during free viewing. Then, we consider a multimodal feature fusion method that can best discriminate between mild depression and normal control subjects as a step toward achieving our longterm aim of developing an objective and effective multimodal system that assists doctors during diagnosis and monitoring of mild depression. Based on the multimodal denoising autoencoder, we use two feature fusion strategies (feature fusion and hidden layer fusion) for fusion of the EEG and EM signals to improve the recognition performance of classifiers for mild depression. Our experimental results indicate that the EEG-EM synchronization acquisition network ensures that the recorded EM and EEG data require that both the data streams are synchronized with millisecond precision, and both fusion methods can improve the mild depression recognition accuracy, thus demonstrating the complementary nature of the modalities. Compared with the unimodal classification approach that uses only EEG or EM, the feature fusion method slightly improved the recognition accuracy by 1.88%, while the hidden layer fusion method significantly improved the classification rate by up to 7.36%. In particular, the highest classification accuracy achieved in this paper was 83.42%. These results indicate that the multimodal deep learning approaches with input data using a combination of EEG and EM signals are promising in achieving real-time monitoring and identification of mild depression.

show abstract

“…For values of the horizontal fast phase, the velocity maximum V max = 400 ∘ /s estimated earlier [16] was used to reject the corresponding nystagmus candidate. Usually noise spikes are steep, generating high velocity values higher than V max , and are not related to actual eye movements.…”

Section: Selection Procedures For Nystagmusmentioning

confidence: 99%

The Classification of Valid and Invalid Beats of Three-Dimensional Nystagmus Eye Movement Signals Using Machine Learning Methods

Juhola

Aalto

Joutsijoki

et al. 2013

Advances in Artificial Neural Systems

Self Cite

View full text Add to dashboard Cite

Nystagmus recordings frequently include eye blinks, noise, or other corrupted segments that, with the exception of noise, cannot be dampened by filtering. We measured the spontaneous nystagmus of 107 otoneurological patients to form a training set for machine learning-based classifiers to assess and separate valid nystagmus beats from artefacts. Video-oculography was used to record threedimensional nystagmus signals. Firstly, a procedure was implemented to accept or reject nystagmus beats according to the limits for nystagmus variables. Secondly, an expert perused all nystagmus beats manually. Thirdly, both the machine and the manual results were united to form the third variation of the training set for the machine learning-based classification. This improved accuracy results in classification; high accuracy values of up to 89% were obtained.

show abstract

Using results of eye movement signal analysis in the neural network recognition of otoneurological patients

Cited by 11 publications

References 17 publications

Signal Analysis of Three-dimensional Nystagmus for Otoneurological Investigations

Signal Analysis of Three-dimensional Nystagmus for Otoneurological Investigations

Multimodal Mild Depression Recognition Based on EEG-EM Synchronization Acquisition Network

The Classification of Valid and Invalid Beats of Three-Dimensional Nystagmus Eye Movement Signals Using Machine Learning Methods

Contact Info

Product

Resources

About