Volume 22 (2014): Issue 35 (December 2014)

Facial feature points identification plays an important role in many facial image applications, like face detection, face recognition, facial expression classification, etc. This paper describes the early stages of the research in the field of evolving a facial composite, primarily the main steps of face detection and facial features extraction. Technological issues are identified and possible strategies to solve some of the problems are proposed.

As stated in (7), binary coded computer programs can be shown as a metric space. Therefore, they can be measured by metric in a sense of metric space theory. This paper presents the proof that Fréchet metric is a metric on the space of all sequences of elements M={0,1t} Therefore, it is usable to build a system of software metrics based on the metric space theory

The paper examines systems integration and its main levels at higher levels of control. At present, the systems integration is one of the main aspects participating in the consolidation processes and financial flows of a company. Systems Integration is a complicated emotionconsuming process and it is often a problem to choose the right approach and level of integration. The research focused on four levels of integration, while each of them is characterized by specific conditions. At each level, there is a summary of recommendations and practical experience. The paper also discusses systems integration between the information and MES levels. The main part includes user-level integration where we describe an example of such integration. Finally, we list recommendations and also possible predictions of the systems integration as one of the important factors in the future.

The paper presents the simulation study results of the traffic system in the city of Hlohovec. The authors describe the process of building the model in Witness 2013c simulator. The individual entities of simulation model are explained in details, as the Witness simulator is primarily suitable for manufacture or service simulation and not for traffic system simulation. The goal of this paper is to analyse the traffic system and to suggest the changes for improving the traffic in the city of Hlohovec. All proposed measures will bring about 20% improvement of traffic when compared to the current state.

The paper deals with a certain class of nonautonomous ordinary third-order nonlinear differential equations L₃y=f(t,L₀y,L₁y,L₂y) with quasi-derivatives. A criterion of asymptotic stability in Liapunov sense as well as a criterion of instability in Liapunov sense is derived. The results are illustrated by two examples.

The concept of digital manufacturing supposes application of digital technologies in the whole product life cycle. Direct digital manufacturing includes such information technology processes, where products are directly manufactured from 3D CAD model. In digital manufacturing, engineering drawing is replaced by CAD product model. In the contemporary practice, lots of engineering paper-based drawings are still archived. They could be digitalized by scanner and stored to one of the raster graphics format and after that vectorized for interactive editing in the specific software system for technical drawing or for archiving in some of the standard vector graphics file format. The vector format is suitable for 3D model generating, too.The article deals with using of selected integral transformations (Fourier, Hough) in the phase of digitalized raster engineering drawings vectorization.

The article deals with the control of oscillations in a specific type of second-order differential equations. The purpose of the research is to prove the possibility of oscillation frequency control based on a change in the value of a singular perturbation parameter placed into a mathematical model of a nonlinear dynamical system at the highest derivative. The oscillation frequency change caused by a different value of the parameter is verified by numerically modelling the system.

The aim of this paper is to present the possibilities of applying data mining techniques to the problem of analysis of structural relationships in the system of stationary random processes. In this paper, we will approach the area of the random processes, present the process of structural analysis and select suitable circuit data mining methods applicable to the area of structural analysis. We will propose the methodology for the structural analysis in the system of stationary stochastic processes using data mining methods for active experimental approach, based on the theoretical basis.

According to several studies, the European population is rapidly aging far over last years. It is therefore important to ensure that aging population is able to live independently without the support of working-age population. In accordance with the studies, fall is the most dangerous and frequent accident in the everyday life of aging population. In our paper, we present a system to track the human fall by a visual detection, i.e. using no wearable equipment. For this purpose, we used a Kinect sensor, which provides the human body position in the Cartesian coordinates. It is possible to directly capture a human body because the Kinect sensor has a depth and also an infrared camera. The first step in our research was to detect postures and classify the fall accident. We experimented and compared the selected machine learning methods including Naive Bayes, decision trees and SVM method to compare the performance in recognizing the human postures (standing, sitting and lying). The highest classification accuracy of over 93.3% was achieved by the decision tree method.