Volume 7 Issue 5


Volume 7 Issue 4

Download one file 114


Magomedov S.G.,
Lebedev A.S.

A tool for automatic parallelization of affine programs for systems with shared and distributed memory

Effective programming of parallel architectures has always been a challenge, and it is especially complicated with their modern diversity. The task of automatic parallelization of program code was formulated from the moment of the appearance of the first parallel computers made in Russia (for example, PS2000). To date, programming languages and technologies have been developed that simplify the work of a programmer (T-System, MC#, Erlang, Go, OpenCL), but do not make parallelization automatic. The current situation requires the development of effective programming tools for parallel computing systems. Such tools should support the development of parallel programs for systems with shared and distributed memory. The paper deals with the problem of automatic parallelization of affine programs for such systems. Methods for calculating space-time mappings that optimize the locality of the program are discussed. The implementation of developed methods is done in Haskell within the source-to-source translator performing automatic parallelization. A comparison of the performance of parallel variants of lu, atax, syr2k programs obtained using the developed tool and the modern Pluto tool is made. The experiments were performed on two x86_64 machines connected by the InfiniBand network. OpenMP and MPI were used as parallelization technologies. The performance of the resulting parallel program indicates the practical applicability of the developed tool for affine programs parallelization.

Keywords: automatic parallelization, affine programs, polyhedral model, locality optimization, integer linear programming.


Chesalin A.N.,
Grodzenskiy S.Ya.,
Nilov M.Yu.,
Agafonov A.N.

Modification of the WaldBoost algorithm to improve the efficiency of solving pattern recognition problems in real-time 81

The implementation of the WaldBoost algorithm is considered, and its modification is proposed, which allows to significantly reduce the number of weak classifiers to achieve a given classification accuracy. The efficiency of the proposed algorithm is shown by specific examples. The paper studies modifications of compositions (ensembles) of algorithms for solving real-time pattern recognition problems. The aim of the study is to improve the known machine learning algorithms for pattern recognition using a minimum amount of time (the minimum number of used classifiers) and with a given accuracy of the results. We consider the implementation of the WaldBoost algorithm, which combines two algorithms: adaptive boosting of weak classifiers – AdaBoost (adaptive boosting), which has a high generalizing ability, and the sequential probability ratio test – SPRT (Wald test), which is the optimal rule of decision-making when distinguishing two hypotheses. It is noted that when using the WaldBoost, the values of the actual probability of classification errors, as a rule, are less than given because of the approximate boundaries of the SPRT, so that the classification process uses an excessive series of weak classifiers. In this regard, we propose a modification of the WaldBoost based on iterative refinement of the decision boundaries, which can significantly reduce the number of used weak classifiers required for pattern recognition with a given accuracy. The efficiency of the proposed algorithm is shown by specific examples. The results are confirmed by statistical modeling on several data sets. It is noted that the results can be applied in the refinement of other cascade classification algorithms.

Keywords: algorithm ensembles, adaptive boosting, AdaBoost, WaldBoost, sequential analysis.



Romanov A.M.

A review on control systems hardware and software for robots of various scale and purpose. Part 1. Industrial robotics 59

A review of robotic systems is presented. The paper analyzes applied hardware and software solutions and summarizes the most common block diagrams of control systems. The analysis of approaches to control systems scaling, the use of intelligent control, achieving fault tolerance, reducing the weight and size of control system elements belonging to various classes of robotic systems is carried out. The goal of the review is finding common approaches used in various areas of robotics to build on their basis a uniform methodology for designing scalable intelligent control systems for robots with a given level of fault tolerance on a unified component base. This part is dedicated to industrial robotics. The following conclusions are made: scaling in industrial robotics is achieved through the use of the modular control systems and unification of main components; multiple industrial robot interaction is organized using centralized global planning or the use of previously simulated control programs, eliminating possible collisions in working area; intellectual technologies in industrial robotics are used primarily at the strategic level of the control system which is usually non-real time, and in some cases even implemented as a remote cloud service; from the point of view of ensuring fault tolerance, the industrial robots developers are primarily focused on the early prediction of faults and the planned decommissioning of the robots, and are not on highly-avaliability in case of failures; industrial robotics does not impose serious requirements on the dimensions and weight of the control devices.

Keywords: robotics, industrial robots, control systems, mobile robots, manipulators.



Kulikov G.V.,
Nguyen Van Dung

Influence of synchronization errors оn the noise immunity of coherent reception of M-PSK signals 53

Signals with multiple phase-shift keying (M-PSK) have long been successfully used for highspeed information transfer in many applications – a number of adopted protocols of IEEE 802.11 wireless networks, digital satellite television DVB-S, DVB-S2/S2X systems, cellular networks CDMA and others. The most important characteristic of such systems is their noise immunity, which depends not only on the propagation conditions of radio waves in the communication channel, but also on the quality of operation of the component nodes of the information transmission systems themselves. The paper investigates the influence of the inaccuracy of estimating the frequency and phase of the carrier and the inaccuracy of the clock synchronization system on the noise immunity of coherent reception of M-PSK signals. Analytical expressions were obtained by statistical radio engineering methods. The expressions allow calculating the dependence of the probability of a bit error on the signal-to-noise ratio for various errors of the receiver auxiliary systems. In this case, the magnitudes of the errors were assumed to be either constant (static error) or dynamically changing (dynamic error). The dynamic errors were modeled using the Monte Carlo method, and the dynamic errors themselves were assumed to be Gaussian random variables. It is shown that the inaccuracy of estimating these parameters strongly influences the noise immunity of the coherent reception of the M-PSK signal, and this effect increases with increasing signal positionality. Estimates of the maximum permissible errors of the analyzed systems are given. When M-PSK signals are received, a tolerable value of the frequency of the reference oscillations can be considered as a ΔωTs value of about 0.05. The allowable inaccuracy of the carrier phase estimation depends on the positioning of the signal and varies from π/36–π/72 for 2PSK to π/180 for 32PSK. The allowable time offset of the clock moments can be considered the value of 3–5% of the clock interval duration.

Keywords: multiple phase-shift keying, frequency, phase, clock time, signal-to-noise ratio, static shift, dynamic shift, bit error rate.



Naumova Yu.A.,
Gordeeva I.V.

Analysis of mathematical models for description of the fractional composition of disperse elastic fillers 32

The paper presents a comparative analysis of integral and differential mathematical models describing the particle size distribution of dispersed elastic fillers. Crushed vulcanizates obtained by high temperature shear grinding were studied as objects of research. Technogenic waste – waste passenger car tires and rubber elements of gas mask facepieces – were used as raw materials. Data on the distribution of the crushed vulcanizate particles were obtained by laser diffraction using the particle size analyzer Fritsch Analysette 22 Microtec plus (“Fritsch”, Germany). It was found that the distribution curves are unimodal asymmetric curves. Search and analysis of mathematical models were carried out using a specialized software product TableCurve 2D v5.01 (Jandel Scientific). Four- and five-parameter equations pertaining to the class of logistic models were tested to describe the integral cumulative distribution curves of the rubber powder particles. In order to justify the choice of a suitable mathematical model to describe the fractional composition of the crushed vulcanizes, the adequacy of the models was assessed, the structural characteristics of the variation series, the statistical moments of distribution and the indicators of its shape were determined. It was found that according to a number of criteria it is appropriate to use the logarithmically normal distribution function for the description and analysis of the rubber powders fractional composition. It is suggested that regardless of the nature of the feedstock, the described implementation of high temperature shear grinding provides products having an identical shape of rubber powder particles size distribution.

Keywords: elastic fillers, crushed vulcanizates, method of high temperature shear grinding, particle size distribution, mathematical models, distribution function.



Mandych I.A.,
Bykova A.V.

Trends in innovation and investment development of high-tech enterprises 70

The article deals with the main prospects and problems of investing in innovative activities of high-tech enterprises. The principles of construction of venture investment and the mechanism of venture financing of a project when creating technological innovation were investigated. The overview of the Russian venture capital market shows the positive dynamics associated with the termination of a significant outflow of funds from the market and the growth in the number of newly created funds. There were also revealed promising areas for the development of the venture capital market and support high-tech enterprises, namely: success stories; low profitability of traditional investment instruments; the growth of activity of state corporations; growth in the number of startups focused on the international market; state support; angel investing growth; promotion of VC and innovations; the emergence of smart industries. Such barriers to the development of venture capital investment as the disunity of the market, the lack of co-investment. There were made conclusions about the prospects of engaging businesses in the processes of research and development of new products, as well as its promotion in promising markets among partners with special competencies, and that human resources are becoming the most important component of the success of high-tech industries.

Keywords: innovations, investments, high-tech business, venture investment, entrepreneur.