The paper investigates four novel methods for noncontact measurement of heart rate (HR) and consequently its derivate HR variability, an important marker of autonomic activity proven to be predictive of likelihood of future health related events. The discussed methods are divided into the following two groups: the methods measuring electromagnetic energy generated by the bioelectrical activity within the cardiac muscle (referred to as direct methods), and the methods measuring displacement of a part of the subject's body caused by the periodic physical contractions of the heart (referred to as indirect methods). The results indicate that noncontact measuring of HR is possible, especially for distances of less than 50 cm meeting essential requirements for HR diagnostic purposes.
COBISS.SI-ID: 10278484
This paper describes a procedure for metrological evaluation of skin conductance measurement. Three commercial devices for measuring skin conductance were calibrated by comparison with a precision digital ohmmeter used as a reference. Combined measurement uncertainty of skin conductance meters was calculated by means of uncertainty of reference instrument and uncertainties due to measurement repeatability, reproducibility, resolution and environmental condition. Measurement uncertainty analysis showed that contributions due to resolution and sensitivity of the measuring device, usually obtained from specifications, are negligible when compared to uncertainty of measuring method.
COBISS.SI-ID: 9940052
In this paper we address the impact of weak ground truth and the impact of the users’ facial expressiveness on the emotion detection accuracy. We implemented an appearance-based emotion detection algorithm and we tested its performance with datasets with different ground truths and facial expressivenesses.
COBISS.SI-ID: 9919060
This paper presents algorithms for fast measurement and the non-parametric estimation of the unknown changing frequency, amplitude, and phase difference of the signals from two channels with the same frequency, as well as other power quantities, such as the apparent, the active, and the reactive power. The possibilities for systematic error reduction through use of the interpolated discrete Fourier transform (IDFT) using the Rife-Vincent windows class I (RV-I) is described. Parameters are calculated from the DFT coefficients around the component peaks by summation to reduce the leakage effects. The optimum for reducing the time of measurement and for reducing systematic errors under non-coherent conditions of sampling real noisy signals could be the estimation with the three cycles window using the three-point interpolation and the RV-I window order 3.
COBISS.SI-ID: 10035540
Digitalization as the main part of measurement consists of prefiltering, sampling, windowing, and quantization. In addition to this, the dynamics of the analogue-to-digital (A/D) conversion are also important. Here a trade-off between the number of references for generating the reference levels and the number of steps of the conversion is presented. The differential tracking b-bit A/D conversion gives better results than the classical A/D conversion with the successive approximation procedure, due to b-times more available sampling points, and the adaptive property of the A/D procedure that every previous approximation step to signal becomes the center of observation with an exponential increase in resolution in the new step. Considering together the systematic and the random errors in the signal parameters estimation, shows the advantage of the adaptive A/D conversion at lower values of the sampling ratio.
COBISS.SI-ID: 10206548