Software & Systems

Articles of journal № 2 at 2016 year.

Order result by: Public date | Title | Authors |

11. Preprocessing sets of precedents to construct decision functions in classification problems [№2 за 2016 год]
Authors: Gdansky N.I., Kulikova N.L., Krasheninnikov A.M.
Visitors: 8710
The article considers an important problem of errors in learning samples for subsequent construction using the method of solving functions precedents in problems of new objects classification. The paper researches the main causes of these errors and their impact on the construction of classifiers. Based on the geometric interpretation of a classification problem the authors propose methods to not only analyze the quality of a training sample, but also identify possible causes of the errors contained in it, as well as perform their correction required for the subsequent construction of an effective classifier. For numerical accounting of common emission lobes, which must be removed and corrected in a learning sample, the authors propose using the corresponding maximum allowable threshold values. There are some recommendations for the main subject areas. The algorithm of precedent analysis uses a special measure of single object proximity to an arbitrary class. It is similar to the method of the nearest neighbor with the difference that neighborhood is determined by not a nearest point but several points. The complexity of the proposed algorithms for analysis and correction of training sets is polynomial according to the number of points in the the learning sample. In the first case it is quadratic, in the second case it is linear. A new corrected training set sets smoother class boundaries in the space of characteristic values. Consequently, the data set of points to a greater extent satisfy the compactness hypothesis and give decision functions with a simpler structure, which requires less computing operations to solve the problem of classification.

12. The analysis of activity and development trends of malicious programs “file locker-encoder” type [№2 за 2016 год]
Author: Drobotun E.B.
Visitors: 12120
All companies engaged in development of anti-virus software noted that since the middle of 2013 there has been a burst of malware infection of computers. These malicious programs cipher user information. Thus, they are the most dangerous type of malicious programs of Ransomware class (extortioner programs). These programs not only block access to a computer for victims, but also block users’ access to files using various enciphering algorithms. Usually such malicious programs cipher popular types of the user files, which can be of a certain value: documents, spreadsheets, database files, photos, video and audio files, etc. To encrypt files the user is offered to pay ransom by means of some Internet payment services or cryptocurrency (usually bitcoins). The first versions of such malicious programs appeared in 2006–2007. However, at that time these programs used nonresistant enciphering algorithms, a small size of enciphering keys and extremely inefficient distribution methods. Therefore, they weren't widely distributed. Modern malicious programs do not have these shortcomings. They use quite resistant enciphering algorithms (AES or RSA), rather big size of enciphering keys and effective infection methods (infected web pages and malicious spam e-mails). The paper describes the main tendencies of such programs development on the basis of the analysis of several most widespread types of malicious programs. It also offers possible ways of eliminating consequences of their activity.

13. A software suite for simulating drugs dissolution kinetics [№2 за 2016 год]
Authors: Ivanov S.I., Tiptsova I.A., Matasov A.V., Sinitsa E.A., Gordienko M.G., Menshutina N.V.
Visitors: 9542
Dissolution in the pharmaceutical industry is an essential process at a development stage of new original drugs. It is also important for selection of generic compositions. In order to reduce time and cost for carrying out multiple experiments of dissolution of different substance compositions the authors have developed a software suite for modeling drugs dissolution kinetics. The software suite is created using C# in Microsoft Visual Studio. The basis of software calculation module is a model of a dissolution process based on cellular automata with changing sizes of cells. There is also a modified algorithm developed in order to increase calculation performance. It allows reducing the time of calculation by 1,5 times compared to the traditional algorithm of a cellular automaton model. To test the adequacy of the developed software complex the authors compared experimental data with calculated by the example of dissolution of various drugs. The article presents calculated data and visualization of the software operation on example of dissolution of granules that are distributed inclusions of the system “labrasol-ibuprofen” in a mixture of soluble substances (maltodextrin and gum Arabic).

14. Open software architecture for surgery training suites [№2 за 2016 год]
Authors: Ivaschenko A.V., Gorbachenko N.A., Kolsanov A.V.
Visitors: 6802
The evolution of modern surgical simulators considering the differences in educational tech nologies at different universities determines the relevance of software requirements, such as interoperability, open architecture and the ability to operate in a common information space. This paper describes the basic principles of software open architecture development for surgical simulators designed to teach surgery at medical universities. The paper focuses on the representation of surgical field objects and modeling their interaction with each other, which would provide an opportunity to create new training modules for surgical simulators. In order to create a distributed platform architecture for modeling operational cases the paper proposes using a design pattern “Entity – component”. Considering the specificity of logic for a particular operating case, the paper presents a hierarchy of interaction between software modules. As the example, the authors consider the algorithm of gripping an organ by a hard instrument with two jaws in an endoscope surgery simulation. In addition, the paper considers the basic principles of interaction between objects using the example of a training module endoscope clipping. The practical implementation results of the proposed approach prove that it can be used to describe various aspects of objects’ behavior in a scene within a unified architecture. It provides the flexibility to customize the behavior and active reuse of components. The proposed approach can reduce time and complexity of new surgical simulators development, as well as adapt existing simulation solutions for their implementation and practical application. This work was performed as a part of a project to create a software development kit (SDK) for medical community to deliver new simulation technologies in medicine with the possibility to exchange them in healthcare and medical education system (supported by the Ministry of Education and Science of Russian Federation (grant 2014-14-579-0003), contract 14.607.21.0007).

15. Classification algorithm based on random forest principes for a forecasting problem [№2 за 2016 год]
Authors: Kartiev S.B., Kureichik V.M.
Visitors: 13897
This article considers the methods of constructing ensembles of models to solve the forecasting problem. One of the major forecasting stages is classification. This stage includes the basic logic of predictive models. It describes the “random forest” classification method. It also presents the pros and cons of the methods used. During the research the authors justify the choice of this method for using in the developed forecasting system. The paper presents an algorithm for random forest construction based on a combination of decision-making elements and training methods for generated data structures using a modified random forest (MRF) training algorithm. The fundamental difference of this method is finding the optimal class which possesses the object in question for a forecasting task. The paper describes the software implementation in Java using the principles of generic programming. It also describes the basic data structure as an UML-diagram. The article defines the place of the developed module in the diagnostic system of complex technical systems for software system maintenance using modeling principles based on temporal logic. The experimental research showes the efficiency of the described method compared to existing ones. Classification quality has improved at approximately 5 % compared to previous experiments.

16. A model and algorithmization of the assignment problem under additional constraints [№2 за 2016 год]
Authors: Kordyukov R.Yu., Dopira R.V., Ivanova A.V., Abu-Abed, F.N., Martynov D.V.
Visitors: 10257
The article discusses the problem of optimal selection of candidates for working in tender projects based on financial conditions offered by candidates. It presents key criteria in selecting appropriate applications of candidates on the basis of pre-announced standards. The problem is formalized. The objective function is to minimize the costs for project implementation. The developed model aggregates the source data and constraints into one system and allows operating the initial conditions for their analysis. The authors offer a special algorithm for optimal appointment variants search based on the graph theory, the method of sequential analysis and option screening, as well as implicit enumeration. This algorithm takes into account the requirements for the applications of candidates. It works both in terms of the excistance of enterprises’ maximum and minimum financial constraints, and in their absence. It allows selecting performers for a complex project, which involves the successful completion of many individual projects in its composition. The developed software provides opportunities for creating a list of competitive projects, candidates for their implementation and their applications for certain types of work, taking into account the existing cost, time and probability limits. The algorithm searches all applications that meet the requirements of standards, then it determines the optimal selection among them, taking into account the performers’ possibilities of the acquisition of allocated resources.

17. Fuzzy logic in a sensorless valve electric drive [№2 за 2016 год]
Authors: Lgotchikov V.V., Gorchakov D.V.
Visitors: 11559
The paper considers a 6-step algorithm of valve electric drive sensorless control. The analysis of transient processes in electric drive power circuit showed the decrease of overall performance of a valve electric drive in dynamic modes of operation when the drive is controlled by a sensorless algorithm for determinination of the switching moment using a counterelectromotive force signal integral. In some cases the whole system can become unstable. It's necessary to compensate the increase of current and magnetic circuit saturation by dynamical changing control system parameters, so that the system could operate in a stable condition. To achieve this purpose the article proposes using a fuzzy logic controller. Such controller adjusts the commutation moment of drive phases using the database of fuzzy rules. Fuzzy logic control system uses normalized values of motor current and a rate of rotation as input parameters. Fuzzy logic controller used in electric drive control system will increase a control performance in dynamic modes, such as applying the load or velocity signal changes. Simulink tests show that the designed system with fuzzy logic control allows high quality level of motor control in a wide range of motor speed. The proposed control system also increases load-carrying capability of the whole system.

18. Simulator programs for temperature fields in flat form products [№2 за 2016 год]
Author: Margolis B.I.
Visitors: 10839
The article considers a model of a temperature field in the flat shape product at asymmetric convecti ve-radiant heat transfer of product surfaces to the environment and protecting surfaces (heating elements) of production equipment. The paper presents equations for calculating product temperature distribution using numerical finite-difference methods. There is a calculation example of convective-radiant cooling of a glass plate. The article shows that the calculation results are in a good agreement with published sources. It also states possible solutions for the problem in Matlab. The standard function pdepe in MatLab has become a basis for development of a program that allows simulating a product temperature field according to specified thermal and physical characteristics of a material (thermal conductivity, temperature conductivity) and convectiveradiant heat transfer parameters (a convective heat transfer coefficient and emissivity factors). The paper considers program development features related to setting functions such as differential equations, initial and boundary conditions. There are program codes of functions, of the main program and calculation results of the temperature distribution. A comparative analysis of problem solution in Matlab and the results obtained using the finite-difference relations demonstrates their good agreement. The paper shows the prospects of using standard Matlab functions to solve the identification problems of heat transfer conditions and optimization of product thermal treatment in various technological processes.

19. Semantic relations in text classification based on Bag-of-words model [№2 за 2016 год]
Authors: Nugumanova А.B., Bessmertny I.A., Pecina P., Baiburin Е.M.
Visitors: 13654
The paper contains the results of research concerning quality improvement of automatic text classification based on statistical approach. It considers Bag-of-words model as a basis model of text representation. This is the most popular and the simpliest text representation model that is used in many tasks of automated language processing. The model represents texts as sets of words ignoring their order and relations. Therefore, the semantic similarity of two texts is assessed by a number of matching pairs of words. So, the texts containing few common words are meant to be semantically far from each other. Due to ignoring semantic links, this feature of Bag-of-words model creates a serious problem in such important task of natural language processing as automatic text classification. This paper proposes to enrich Bag-of-words model by semantic links from these texts extracted based on the joint word appearance statistics. Particularly, the contribution of this work consists in a new method of building and using of a semantic links matrix that is further used to display text representations to a space of linked words. The final purpose of this work is proving that the proposed model is more efficient in binary text classification than the traditional Bag-of-words approach. In order to compare these two models the authors carried out a set of experiments based on the standard Reuters 21578 texts collection. The results of the experiments demonstrate improvement of classification quality comparing to known methods.

20. Methods of automatic ontology construction [№2 за 2016 год]
Authors: Platonov A.V., Poleschuk E.A.
Visitors: 11153
The article describes an automatic domain ontology generation process using input text corpora. In particular, it describes the processes similar to Biperpedia, BOEMIE Project systems, etc. This paper includes a description of basic steps of automatic ontology construction, specifically a domain-object extraction process, concept (i.e. terms that combine an object set) extraction process, as well as the process of semantic relations and rules extraction. This paper reviews algorithms for each steps of an ontology construction process. There is a named entity recognition task and regular expression generation based on a genetic programming approach for a domain-object extraction process. The authors propose an idea of using a sequential pattern mining approach for term sequences extraction for an object identification process. The paper contains a description of basic steps of a concept extraction task and a review of a concept attributes extraction task. The article also describes a lexico-syntactic pattern approach for a domain semantic relation extraction process. The authors propose an approach to this task based on association rules mining like in a frequent pattern mining approach. The paper includes three methods of ontology learning evaluation, specifically: a golden sample method, a human evaluation method and an indirect method using client-application evaluation. The paper describes positive and negative aspects of each method and proposes a compromise to estimate the quality of a model.

◄ ← Preview | 1 | 2 | 3 | Next → ►