University of Maribor

About: University of Maribor is a education organization based out in Maribor, Slovenia. It is known for research contribution in the topics: Population & KEKB. The organization has 3987 authors who have published 13077 publications receiving 258339 citations. The organization is also known as: Univerza v Mariboru.

Multi-Objective Differential Evolution for feature selection in Facial Expression Recognition systems

Abstract: Feature selection using Multi-Objective Differential Evolution (DEMO) is proposed.This efficient selection is integrated in advanced Facial Emotion Recognition system.Emotion-specific and more discriminative features over all emotions selection strategies.Emotion recognition accuracy of proposed algorithm comparable to state-of-the-art.Feature selection by using DEMO enormously reduces a feature vector length. This paper proposes an efficient feature selection system applied to a Facial Expression Recognition (FER) system. This system, capable of recognizing seven prototypical emotions including neutral expression, is based on a histogram of oriented gradient descriptor (HOG) and difference feature vectors. The emotion feature selection was carried out by using an appropriately modified multi-objective differential evolution algorithm. The number of used features was minimized, while the emotion recognition accuracy of the support vector machine classifiers was maximized simultaneously. The emotion-specific features and the more discriminative features over all emotions selection strategies were developed, whereby the latter strategy proved to be more efficient using the Friedman statistical test. This person-independent FER system with proposed feature selection was validated on three commonly used evaluation databases, where the mean emotion recognition rate was 98.37% on the Cohn Kanade database, 92.75% on the JAFFE database, and 84.07% on the MMI database, while the number of used features lowered up to 89% with respect to the original difference feature vector length. Compared to the state-of-the-art, the proposed FER method offers good results, while also greatly lowering the number of used features, which, in return, minimizes the computational cost of training the classifiers. The optimization proposed in this paper can be generalized easily to a feature selection for an arbitrary multi-objective, as well as many-objective, problem.

Real-Time Motor Unit Identification From High-Density Surface EMG

Abstract: 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 the same decomposition paradigm, i.e., compensation of motor unit action potentials and direct identification of motor unit (MU) discharges. In contrast to previously published version of CKC, which operates in batch mode and requires ~ 10 s of EMG signal, the real-time implementation begins with batch processing of ~ 3 s of the EMG signal in the initialization stage and continues on with iterative updating of the estimators of MU discharges as blocks of new EMG samples become available. Its detailed comparison to previously validated batch version of CKC and asymptotically Bayesian optimal linear minimum mean square error (LMMSE) estimator demonstrates high agreement in identified MU discharges among all three techniques. In the case of synthetic surface EMG with 20 dB signal-to-noise ratio, MU discharges were identified with average sensitivity of 98%. In the case of experimental EMG, real-time CKC fully converged after initial 5 s of EMG recordings and real-time and batch CKC agreed on 90% of MU discharges, on average. The real-time CKC identified slightly fewer MUs than its batch version (experimental EMG, 4 MUs versus 5 MUs identified by batch CKC, on average), but required only 0.6 s of processing time on regular personal computer for each second of multichannel surface EMG.

Wettability and surface composition of partly and fully regenerated cellulose thin films from trimethylsilyl cellulose.

Abstract: The wettability and surface free energy (SFE) of partly and fully regenerated cellulose model surfaces from spin coated trimethylsilyl cellulose were determined by static contact angle (SCA) measurements. In order to gain detailed insight into the desilylation reaction of the surfaces the results from SCA measurements were compared with data from other surface analytical methods, namely thickness measurements, X-ray photoelectron spectroscopy (XPS) and attenuated total reflectance infrared spectroscopy (ATR-IR). Additionally, the influence of ultra high vacuum treatment (UHV) during XPS measurements on the water wettability and surface morphology of regenerated cellulose thin films was investigated. The wetting of polar and non-polar liquids increased with prolonged regeneration time, which is reflected in the higher SFE values and polarities of the films. After UHV treatment the water SCA of partly regenerated films decreases, whereas fully regenerated cellulose shows a higher water SCA. Therefore it is assumed that volatile desilylation products tend to adsorb on partly regenerated films, which strongly influences their wettability.

Hybrid self-adaptive cuckoo search for global optimization

Abstract: Adaptation and hybridization typically improve the performances of original algorithm. This paper proposes a novel hybrid self-adaptive cuckoo search algorithm, which extends the original cuckoo search by adding three features, i.e., a balancing of the exploration search strategies within the cuckoo search algorithm, a self-adaptation of cuckoo search control parameters and a linear population reduction. The algorithm was tested on 30 benchmark functions from the CEC-2014 test suite, giving promising results comparable to the algorithms, like the original differential evolution (DE) and original cuckoo search (CS), some powerful variants of modified cuckoo search (i.e., MOCS, CS-VSF) and self-adaptive differential evolution (i.e., jDE, SaDE), while overcoming the results of a winner of the CEC-2014 competition L-Shade remains a great challenge for the future.

Preparation and properties of water-based magnetic fluids.

Abstract: Stable suspensions of superparamagnetic iron oxide nanoparticles in water (water-based ferrofluids) were prepared using citric acid (CA) as a surfactant. The influences of different factors on the amount of nanoparticles in a stable suspension were systematically studied. These factors, including the temperature, the pH value and the concentration of CA applied during the adsorption of the CA onto the nanoparticles and during their suspension in water, were evaluated. The highest content of nanoparticles in a stable suspension was obtained when the CA was absorbed at pH values of around 5.2, where two carboxyl groups are dissociated, and when the nanoparticles were suspended at a pH of around 10, where all three carboxyl groups of the CA are in a dissociated state.