We have proposed an improved model for visual tracking using an adaptive coupled-layer visual model. The model is capable of tracking articulated objects using simple local visual descriptors, that are weakly connected into a geometric constellation. The model is capable of robustly adding and removing the local descriptors through probabilistic maps generated by the high level features such as motion and color. At the same time, the model allows utilization of additional probabilistic maps of arbitrary high-level features. The model was analyzed on a comprehensive database of video recordings and was compared to eleven current state-of-the-art trackers. The experiments have shown that the proposed tracker outperforms the state-of-the-art under several performance criteria.
COBISS.SI-ID: 9431124
In practical finite-impulse-response (FIR) digital filter applications, it is often necessary to represent the filter coefficients with a finite number of bits, e.g. because of a need to use low cost fixed-point DSP processors. The finite wordlength restriction increases the filter deviation, which can be reduced substantially if the optimal finite wordlength coefficients are used. The time needed to compute these coefficients is greatly reduced with the help of a lower bound on the deviation increase. In this work an improved lower bound for the increase of minimax approximation error that is caused by the finite wordlength restriction is improved by using the well known LLL algorithm. The proposed methodology was evaluated on 50 different sets of filter design frequency-domain specification.
COBISS.SI-ID: 8955476
ProBiS algorithm performs structural comparison of a query protein against a predefined database of proteins and reports proteins that have common binding sites with the query protein. It is is one of the fastest local similarity search engines available as an on-line service that is used in structural bioinformatics, drug repositioning, and prediction of protein function. Even so, the growing size of protein database requires the development of faster algorithms for structural comparison of proteins. In this article, we present a parallel implementation of ProBiS that speeds-up ProBiS algorithm by a factor of 50-110 (depending on the query protein), using a cluster of 14 8-core computers. Parallel ProBiS distributes pairwise protein comparisons among the processor cores on the cluster, working most efficiently on large databases and large query proteins that take longer to compare. Its parallelization is asynchronous and can be used efficiently on heterogeneous computer systems and resources provided by hyperthreading.
COBISS.SI-ID: 4993050
In this paper we focus on the comparison of classical and meshless methods. We compare Finite Difference Method (FDM), Finite Element Method (FEM), Meshless Local Petrov Galerkin method (MLPG) and Diffuse Approximate Method (DAM). Methods are compared on solution of non-stationary elliptic partial differential equation at different boundary conditions and with different distributions of computational nodes. We show that DAM is the most promising method regarding the computational time, accuracy and stability. The results are elaborated through detailed numerical analysis. The comparison of strong form meshless method (DAM) against the weak form meshless method (MLPG) is presented in this paper for the first time.
COBISS.SI-ID: 2024699
We propose a new methodology for extracting the respiration rate based on the amplitude changes in the body surface potential differences between two proximal body electrodes of a wireless body sensor. The sensor can be designed as a plaster-like reusable unit that can be easily fixed onto the surface of the body. We explore the influence of the sensor’s position on the quality of the extracted results using multi-channel ECG measurements and considering all the pairs of two neighboring electrodes as potential respiration-rate sensors. The analysis of the clinical measurements, which also include reference thermistor-based respiration signals, shows that the proposed approach is a viable option for monitoring the respiration frequency and for a rough classification of breathing types. We found the best positions for the respiration body sensor and demonstrated that a single sensor for body surface potential difference on proximal skin electrodes can be used for combined measurements of respiratory and cardiac activities.
COBISS.SI-ID: 26182951