oddělení-TKO-SIX

Browse

Now showing 1 - 5 of 26

Parkinson Disease Detection from Speech Articulation Neuromechanics
(Frontiers, 2017-08-25) Gomez-Vilda, Pedro; Mekyska, Jiří; Manuel Ferrandez, Jose; Palacios-Alonso, Daniel; Gómez-Rodellar, Andrés; Rodellar Biarge, María Victoria; Galáž, Zoltán; Smékal, Zdeněk; Eliášová, Ilona; Košťálová, Milena; Rektorová, Irena
Aim: The research described is intended to give a description of articulation dynamics as a correlate of the kinematic behavior of the jaw-tongue biomechanical system, encoded as a probability distribution of an absolute joint velocity. This distribution may be used in detecting and grading speech from patients affected by neurodegenerative illnesses, as Parkinson Disease. Hypothesis: The work hypothesis is that the probability density function of the absolute joint velocity includes information on the stability of phonation when applied to sustained vowels, as well as on fluency if applied to connected speech. Methods: A dataset of sustained vowels recorded from Parkinson Disease patients is contrasted with similar recordings from normative subjects. The probability distribution of the absolute kinematic velocity of the jaw-tongue system is extracted from each utterance. A Random Least Squares Feed-Forward Network (RLSFN) has been used as a binary classifier working on the pathological and normative datasets in a leave-one-out strategy. Monte Carlo simulations have been conducted to estimate the influence of the stochastic nature of the classifier. Two datasets for each gender were tested (males and females) including 26 normative and 53 pathological subjects in the male set, and 25 normative and 38 pathological in the female set. Results: Male and female data subsets were tested in single runs, yielding equal error rates under 0.6% (Accuracy over 99.4%). Due to the stochastic nature of each experiment, Monte Carlo runs were conducted to test the reliability of the methodology. The average detection results after 200 Montecarlo runs of a 200 hyperplane hidden layer RLSFN are given in terms of Sensitivity (males: 0.9946, females: 0.9942), Specificity (males: 0.9944, females: 0.9941) and Accuracy (males: 0.9945, females: 0.9942). The area under the ROC curve is 0.9947 (males) and 0.9945 (females). The equal error rate is 0.0054 (males) and 0.0057 (females). Conclusions: The proposed methodology avails that the use of highly normalized descriptors as the probability distribution of kinematic variables of vowel articulation stability, which has some interesting properties in terms of information theory, boosts the potential of simple yet powerful classifiers in producing quite acceptable detection results in Parkinson Disease.
Series-, Parallel-, and Inter-Connection of Solid-State Arbitrary Fractional-Order Capacitors: Theoretical Study and Experimental Verification
(IEEE, 2018-02-27) Kartci, Aslihan; Agambayev, Agamyrat; Herencsár, Norbert; Salama, Khaled Nabil
In the paper, general analytical formulas are introduced for the determination of equivalent impedance, magnitude, and phase, i.e. order, for n arbitrary fractional-order capacitors (FoCs) connected in series, parallel, and their interconnection. The approach presented helps to evaluate these relevant quantities in the fractional domain since the order of each element has a significant effect on the impedance of each FoC and their equivalent capacitance cannot be considered. Three types of solid-state fractional-order passive capacitors of different orders, using ferroelectric polymer and reduced Graphene Oxide-percolated P(VDF-TrFE-CFE) composite structures, are fabricated and characterized. Using an impedance analyzer, the behavior of the devices was found to be stable in the frequency range 0.2MHz–20MHz, with a phase angle deviation of ±4 degrees. Multiple numerical and experimental case studies are given, in particular for two and three connected FoCs. The fundamental issues of the measurement units of the FoCs connected in series and parallel are derived. A MATLAB open access source code is given in Appendix for easy calculation of the equivalent FoC magnitude and phase. The experimental results are in good agreement with the theoretical assumptions.
Performance Analysis of Oustaloup Approximation for the Design of Fractional-Order Analogue Circuits
(IEEE, 2018-11-05) Koton, Jaroslav; Stavnesli, Jorgen Hagset; Freeborn, Todd
The description and definition of various systems using fractional-order calculus continues to gain attention in a variety of field of engineering. This is especially true for the design of analogue function blocks, where the factional-order Laplace operator s , whereas 0 < < 1, is frequently used to design the fractional to design the transfer functions of these blocks. In this paper we focus on analysing the Oustaloup approximation of s to provide a tool that can support selecting the appropriate approximation to obtain a response that satisfies the designers’ requirements of approximation error in magnitude and/or phase in a specific frequency range for the minimal possible order N of the approximation
Optimized High Resolution 3D Dense-U-Net Network for Brain and Spine Segmentation
(MDPI, 2019-02-15) Kolařík, Martin; Burget, Radim; Uher, Václav; Říha, Kamil; Dutta, Malay Kishore
The 3D image segmentation is the process of partitioning a digital 3D volumes into multiple segments. This paper presents a fully automatic method for high resolution 3D volumetric segmentation of medical image data using modern supervised deep learning approach. We introduce 3D Dense-U-Net neural network architecture implementing densely connected layers. It has been optimized for graphic process unit accelerated high resolution image processing on currently available hardware (Nvidia GTX 1080ti). The method has been evaluated on MRI brain 3D volumetric dataset and CT thoracic scan dataset for spine segmentation. In contrast with many previous methods, our approach is capable of precise segmentation of the input image data in the original resolution, without any pre-processing of the input image. It can process image data in 3D and has achieved accuracy of 99.72% on MRI brain dataset, which outperformed results achieved by human expert. On lumbar and thoracic vertebrae CT dataset it has achieved the accuracy of 99.80%. The architecture proposed in this paper can also be easily applied to any task already using U-Net network as a segmentation algorithm to enhance its results. Complete source code was released online under open-source license.
Differential Second-Order Voltage-Mode All-Pass Filter Using Current Conveyors
(Kaunas University of Technology, 2016-10-10) Koton, Jaroslav; Herencsár, Norbert; Horng, Jiun-Wei
In this paper, a new circuit solution of analogue pseudo-differential second-order all-pass filter operating in the voltage mode is presented. Pseudo-differential, since both input and output terminals are differential, however, the circuit topology features single-ended structure. As active elements the differential difference current conveyors and second-generation current conveyors are advantageously used. The proposed filter features quality factor control without disturbing the polefrequency using single passive element. The designed circuit is less complex compared to fully-differential solutions by maintaining sufficient common-mode rejection ratio. The behaviour of the filter is described by means of symbolic analysis and also by simulations using the UCC-N1B integrated circuit. Furthermore, the performance of the proposed pseudo- differential filter has been validated by experimental measurements.

Browse

Recent Submissions