Non-parametric analysis of eye-tracking data by anomaly detection

2017 IEEE Conference on Control Technology and Applications (CCTA)

2017

Self Cite

Abstract-The Volterra model is a well-established option in nonlinear black-box system identification. However, the estimated model is often over-parametrized. This paper presents an approach to reducing the number of parameters of a Volterra model with the kernels parametrized in the orthonormal basis of Laguerre functions by estimating it with a sparse estimation algorithm subject to constraints. The resulting parameter estimates are scrutinized for parameter redundancy and functional dependence by principal component analysis. The benefits of this approach are illustrated by identifying the human smooth pursuit system. Previous studies have suggested that the Volterra model structure is suitable for modeling the human smooth pursuit system both in health and disease. The data sets are obtained by eye tracking in a study performed on 7 test subjects diagnosed with Parkinson's disease and 22 healthy control subjects. In terms of output error, the reduced model has similar performance to that of the full model.

Section: Preliminariesmentioning

confidence: 99%

Constrained SPICE in Volterra-Laguerre modeling of human smooth pursuit

Bro

2017 IEEE Conference on Control Technology and Applications (CCTA)

2017

Self Cite

“…The most apparent flaw of the linear SPS models is their inability to accurately predict the output amplitudes [9]. One way to alleviate this problem is to augment model (12) with a static output nonlinearity, f (x), yielding a Wiener model. Although the underlying system may be dynamically nonlinear, this brief shows that it can be sufficiently well approximated by a Wiener model.…”

Section: Parametric Methodsmentioning

confidence: 99%

“…The structure suggested in [10] to model the SPS is a linear time-invariant Auto-Regressive (ARX) model given by (12) where x(n) is the output at time nT s , s(n) is the input at time nT s , e(n) is zero-mean white Gaussian noise with some variance, θ = [a 1 , a 2 , a 3 , b] T is the parameter vector of the model, q is the forward time-shift operator, and T s is the sampling time. It is assumed that the SPS is described by two independent single-input-single-output models in parallel, one for horizontal and one for vertical movements of the eye.…”

Section: Parametric Methodsmentioning

confidence: 99%

“…An independently acquired data set of eye movement is then tested against the estimated probability density functions (pdfs) to establish any significant deviation from the profile. In [12], pdfs of the trajectory distributions are estimated using kernel density estimation (KDE). However, KDE suffers from large variance of estimates and high computational costs.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Parametric and Nonparametric Analysis of Eye-Tracking Data by Anomaly Detection

Jansson

Rosen

IEEE Trans. Contr. Syst. Technol.

2015

Self Cite

An approach to smooth pursuit eye movement's analysis by means of stochastic anomaly detection is presented and applied to the problem of distinguishing between patients diagnosed with Parkinson's disease and normal controls. Both parametric Wiener model-based techniques and nonparametric modeling utilizing a description of the involved probability density functions in orthonormal bases are considered. The necessity of proper visual stimuli design for the accuracy of mathematical modeling is highlighted and a formal method for producing such stimuli is suggested. The efficacy of the approach is demonstrated on experimental data collected by means of a commercial video-based eye tracker.

“…Common examples include alcohol and drugs [20], as well as mental conditions, such as schizophrenia [13], and neurological conditions, e.g. Parkinson's disease [3], [4], [5], [6], [7], [8], [11].…”

Section: Preliminariesmentioning

confidence: 99%

Nonlinear dynamics of the human smooth pursuit system in health and disease: Model structure and parameter estimation

Bro

2017 IEEE 56th Annual Conference on Decision and Control (CDC)

2017

Abstract-Oculomotor tests (OMT) are administered to quantify symptoms in neurological and mental diseases. Eye movements in response to displayed visual stimuli are registered by an digital video-based eye tracker and processed. Stimuli of simple signal form, e.g. sine waves, are traditionally used in medical practice to test the performance of the oculomotor system in smooth pursuit (SP). The calculated SP gain and the phase shift at the frequency in question are then presented as the test outcome. This paper revisits the problem of quantifying the SP dynamics from eye-tracking data by means of nonlinear system identification. First, a sparse Volterra-Laguerre (VL) model is estimated from an OMT with sufficiently exciting (in frequency and amplitude) stimuli. Then the structure and initial parameter estimates of a polynomial Wiener model (WM) are obtained from the kernel estimates of the VL model. Finally, the parameter distributions of the WM are inferred by a particle filter (PF). In the proposed approach, the performance of the PF is improved by the individualized sparse model structure. Experimental data show that the latter captures the alternations in the SP dynamics due to aging and in Parkinson's disease.