A5033383250- Blind Source Separation Techniques
- Muscle activation and electromyography studies
- EEG and Brain-Computer Interfaces
- Non-Invasive Vital Sign Monitoring
- ECG Monitoring and Analysis
- Speech and Audio Processing
- Spectroscopy and Chemometric Analyses
- Neuroscience and Neural Engineering
- Reproductive Biology and Fertility
- Image and Signal Denoising Methods
- Ovarian function and disorders
- Medical Image Segmentation Techniques
- Neural Networks and Applications
- Ultrasound Imaging and Elastography
- Advanced Vision and Imaging
- Heart Rate Variability and Autonomic Control
- Cellular Automata and Applications
- Robotics and Sensor-Based Localization
- Analog and Mixed-Signal Circuit Design
- Motor Control and Adaptation
- Phonocardiography and Auscultation Techniques
- Advanced Adaptive Filtering Techniques
- Neural Networks Stability and Synchronization
- Control Systems and Identification
- Image Retrieval and Classification Techniques
University of Maribor
2012-2021
Development Fund
2021
Gorenje (Slovenia)
2021
<para xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> This paper studies a novel decomposition technique, suitable for blind separation of linear mixtures signals comprising finite-length symbols. The observed symbols are first modeled as channel responses in multiple-input–multiple-output (MIMO) model, while the inputs conceptually considered sparse positive pulse trains carrying information about symbol arising times. Our approach compensates and...
This study addresses online decomposition of high-density surface electromyograms (EMG) in real time. The proposed method is based on the previously published Convolution Kernel Compensation (CKC) technique and shares same paradigm, i.e., compensation motor unit action potentials direct identification (MU) discharges. In contrast to version CKC, which operates batch mode requires ~ 10 s EMG signal, real-time implementation begins with processing 3 signal initialization stage continues...
We investigated the changes in muscle fiber conduction velocity, recruitment and derecruitment thresholds, discharge rate of low-threshold motor units during a series ramp contractions. The aim was to compare adjustments unit activity relative duration that each active task. Multichannel surface electromyographic (EMG) signals were recorded from abductor pollicis brevis eight healthy men 12-s contractions (n = 25) which force increased decreased linearly 0 10% maximum. maximal exhibited...
In this paper, a multimethod approach for heartbeat and respiration detection from an optical interferometric signal is proposed. Optical interferometer sensitive device that detects physical changes of optical-fiber length due to external perturbations. When in direct or indirect contact with human body (e.g., hidden bed mattress), mechanical acoustic activity cardiac muscle reflect the signal, enabling entirely unobtrusive monitoring respiration. A novel, two-phased was developed purpose....
Segmentation of ovarian ultrasound images using cellular neural networks (CNNs) is studied in this paper. The segmentation method consists five successive steps where the first four uses CNNs. In step, only rough position follicles determined. second results are improved by expansion detected follicles. third previously undetected inexpressive determined, while fourth step detects ovary. All joined fifth step. templates for CNNs were obtained applying genetic algorithm. has been tested on 50...
This paper introduces a new approach in image registration, that is multisensor registration Hough parameter space. Visual and thermal images of building fronts were aimed to be aligned order inspect properties buildings. Some preprocessing visible was necessary comparable their counterparts, namely downsampling color space conversion from RGB grayscale intensity. For each pair, edges detected with Canny edge detector and, as result, binary obtained. These further processed by transform...
In this paper, a method is presented for monitoring of basic human vital functions (heartbeat and respiration) by using optical fibre interferometer. Optical interferometer sensitive device which detects physical changes the length. If person in contact with fibre, such as having it bed, interferometers responds to small length induced heartbeat breathing. This allows unobtrusive continuous person's life signs. The interferometer, however, has cosine signal transfer characteristic,...
A cost-efficient plastic optical fiber (POF) system for unobtrusive monitoring of human vital signs is presented. The based on speckle interferometry. laser diode butt-coupled to the POF whose exit face projects patterns onto a linear sensor array. Sequences acquired images are transformed into one-dimensional signals by using phase-shifting method. analyzed band-pass filtering and Morlet-wavelet-based multiresolutional approach detection cardiac respiratory activities, respectively. tested...
Abstract Objective To establish whether we might predict the outcome of unstimulated in‐vitro fertilization/intracytoplasmic sperm injection (IVF/ICSI) cycles with quantitative indices perifollicular blood flow assessed three‐dimensional (3D) reconstruction power Doppler images. Methods This prospective study included an analysis 52 cycles. Color and ultrasound examinations a single dominant preovulatory follicle were performed on day oocyte pick‐up. With 3D processing, obtained i.e....
We address in this paper a method to perform blind separation of over-determined instantaneous linear mixtures non-stationary sources. Our contribution is focused on the identification single source autoterms which correspond diagonal Spatial Time-Frequency Distribution sources vector with only one non-zero entry. These latter matrices are processed into an iterative joint-diagonalization scheme provides estimation mixing matrix.