[The use of artificial neural networks in evaluation of posturographic data]. / Die Anwendung künstlicher neuronaler Netze bei der Auswertung posturografischer Messungen.

BACKGROUND: Posturography methods have been applied in clinical neurootology to evaluate the equilibrium function of patients. Methods of statistical analysis play an important role for improving data processing and to support the interpretation of the results. In contrast to conventional statistics, artificial neural networks are model-free and non-parametric. The aim of the presented study was to investigate how accurately these methods are able to discriminate between healthy and equilibrium-disturbed subjects. PATIENTS AND METHODS: 51 healthy volunteers participated in this study. 2 static posturography measurements were recorded before and 40 min after alcohol intake (0.4‰-0.6‰). Recorded signals were processed by 4 different methods in order to estimate power spectral densities (0 Hz-25 Hz). 11 different methods of artificial neural networks were investigated. The ability of artificial neural networks for classification was evaluated in patients with an acute unilateral vestibular loss. RESULTS: It turned out that estimating power spectral densities by means of autoregressive modelling and subsequent classification by Support-Vector Machine or by Learning Vector Quantization Networks are most accurate. Validation analysis yielded mean classification errors for the test set of 4.2 ± 2.2%. CONCLUSIONS: Analysis of neurootological data by artificial neural networks proved to be a sensitive recognition method of even small changes of the postural system.

Evaluation of PERCLOS based current fatigue monitoring technologies.

In an overnight driving simulation study three commercially available devices of fatigue monitoring technologies (FMT) were applied to test their accuracy. 16 volunteers performed driving tasks during eight sessions (40 min each) separated by 15 minutes breaks. The main output variable of FMT devices, which is the percentage of eye closure (PERCLOS), the driving performance (standard deviation of lateral position in lane, SDL), the electroencephalogram (EEG) and electrooculogram (EOG) were recorded during driving. In addition, the subjective self-rated Karolinska sleepiness scale (KSS) was assessed every 2 min. As expected, Pearson product-moment correlation coefficient (PMCC) yielded significant linear dependence between KSS and PERCLOS as well as between SDL and PERCLOS. However, if PMCC was estimated within smaller data segments (3 min) as well as without averaging across subjects then strongly decreased correlation coefficients resulted. To further validate PERCLOS at higher temporal resolution its ability to discriminate between mild and strong fatigue was investigated and compared to the results of the same analysis for EEG/EOG. Spectral-domain features of both types of signals were classified using Support-Vector Machines (SVM). Results suggest that EEG/EOG indicate driver fatigue much better than PERCLOS. Therefore, current FMT devices perform acceptably if temporal resolution is low (> 20 min). But, even under laboratory conditions large errors have to be expected if fatigue is estimated on an individual level and with high temporal resolution.

Monitoring of drowsiness and microsleep.

An overview is presented of different studies on monitoring and detection of drowsiness and microsleep (MS) during driving simulation.

Improved experimental method for the determination of optical constants by excitation of surface plasmon polaritons.

We propose an improved method for attenuated-total-reflection experiments in the Otto configuration. This new technique overcomes the difficulties that arise from the nonuniformity of the air coupling gap. Thus attenuated-total-reflection measurements, under ideal adapted conditions, can be made for a wide range of wavelengths. The determination of optical constants by a three-parameter least-square fit of the experimental data to Fresnel's theory always yields ambiguous results. We found that the ambiguity is caused by the loss of the phase angle in the reflectometry. Measurements for many air gap thicknesses in normal or extreme attenuated-total-reflection techniques, overcome this difficulty.

Experimental verification of a virtual-mode treatment for the excitation of surface plasmon polaritons by attenuated total reflection.

Attenuated-total-reflection spectra obtained by the optical excitation of surface plasmon polaritons can be interpreted in terms of two different virtual modes. It is shown that the HWHM of absorptance as a function of the incidence angle can be described by the decay constant of one of the modes. The attenuated-total-reflection resonance angle, on the other hand, is determined by the phase of another virtual mode. An experimental verification of this virtual-mode treatment is carried out for thick aluminum films.