{"title":"Syntax description synthesis using gradient boosted trees","authors":"A. Astashkin, K. Chuvilin","doi":"10.23919/FRUCT.2017.8071289","DOIUrl":"https://doi.org/10.23919/FRUCT.2017.8071289","url":null,"abstract":"The article considers partially formalized text documents. For such documents, it is not possible to construct a formal grammar. Therefore, an external syntax description is used to build the syntax tree. The problem is the high labor intensity and the high professional requirements for manual preparation of such descriptions. It is proposed to use machine learning methods to automate this process. The training set is composed using the documents with known syntax description. Each document is represented as a syntax tree using the TEXnous parser. Each node of these trees represents a syntax element, and the set of nodes forms the training set. A way of a single syntax element description is proposed so that a formal description of the syntax elements constitutes the space of classes. In the article, this space is limited to the set of parser modes used during the documents analysis. A set of scientific articles is used for the experiments. XGBoost implementation of gradient boosted trees is chosen for result classification problem.","PeriodicalId":114353,"journal":{"name":"2017 20th Conference of Open Innovations Association (FRUCT)","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134231046","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Network anomaly detection using artificial neural networks","authors":"Sergey Andropov, A. Guirik, M. Budko, M. Budko","doi":"10.23919/FRUCT.2017.8071288","DOIUrl":"https://doi.org/10.23919/FRUCT.2017.8071288","url":null,"abstract":"This paper presents a method of identifying and classifying network anomalies using an artificial neural network for analyzing data gathered via Netflow protocol. Potential anomalies and their properties are described. We propose using a multilayer perceptron, trained with the backpropagation algorithm. We experiment both with datasets acquired from a real ISP monitoring system and with datasets modified to simulate the presence of anomalies; some Netflow records are modified to contain known patterns of several network attacks. We evaluate the viability of the approach by practical experimentation with various anomalies and iteration sizes.","PeriodicalId":114353,"journal":{"name":"2017 20th Conference of Open Innovations Association (FRUCT)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116857285","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"M3-Driven smart space creation using a DD-WRT-Based device","authors":"S. Mikhailov, A. Kashevnik","doi":"10.23919/FRUCT.2017.8071323","DOIUrl":"https://doi.org/10.23919/FRUCT.2017.8071323","url":null,"abstract":"The paper describes the process of smart space creation based on integration of Smart-M3 platform with a DD-WRT-based device. Smart-M3 is an open source platform which implements concept of smart space. Wi-Fi router is used as platform hosting which reduces the number of devices participating in smart space-based scenarios. The article covers a process of compilation and installation of Smart-M3 platform on DD-WRT-based Wi-Fi router. Evaluation shows that smart space organized this way can be used for scenarios with few participants. The authors developed “Smart-M3 Control Panel” web-service which allows users to control Smart-M3 platform by a graphical web interface. “Smart-M3 Control Panel” user can view the current status of platform; launch, stop, and reload it; view information storage content and change it; download log files; and change startup options. SocketIO interface was used for the user interaction with web service.","PeriodicalId":114353,"journal":{"name":"2017 20th Conference of Open Innovations Association (FRUCT)","volume":"123 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128414787","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Source code quality classification based on software metrics","authors":"Petr Vytovtov, E. Markov","doi":"10.23919/FRUCT.2017.8071355","DOIUrl":"https://doi.org/10.23919/FRUCT.2017.8071355","url":null,"abstract":"Nowadays the software development speed is raising constantly. Therefore software development companies need a tool for checking source code quality to increase software maintainability and decreasing the number of errors in it. Moreover the systems of automated programming require the similar tool as well. As a result we have started developing a library for LLVM compiler which can evaluate source code quality at compile time and a programmer could receive information about source code quality and values of software metrics which are used for evaluating quality. In automated programming systems our library will be useful as well as a part of feedback step for increasing quality of generated source code.","PeriodicalId":114353,"journal":{"name":"2017 20th Conference of Open Innovations Association (FRUCT)","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134592039","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
D. Namiot, Manfred Sneps-Sneppe Ventspils, Y. Daradkeh
{"title":"On internet of things education","authors":"D. Namiot, Manfred Sneps-Sneppe Ventspils, Y. Daradkeh","doi":"10.23919/FRUCT.2017.8071327","DOIUrl":"https://doi.org/10.23919/FRUCT.2017.8071327","url":null,"abstract":"In this paper, we discuss educational courses for Internet of Things and related areas such as Machine to Machine communications and Smart Cities. The Internet of Things models introduce many new business prospects and, of course, they should be presented in the university curriculum. The purpose of the discussed educational program is to examine issues related to information and communication technologies used in Internet of Things projects and related areas based on them, such as Smart Cities. The educational course proposed in this paper aims to introduce students to modern information technology, standing for such areas as Machine to Machine communications, Internet of Things, and Smart Cities.","PeriodicalId":114353,"journal":{"name":"2017 20th Conference of Open Innovations Association (FRUCT)","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131068288","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Analytical attack modeling and security assessment based on the common vulnerability scoring system","authors":"E. Doynikova, A. Chechulin, Igor Kotenko","doi":"10.23919/FRUCT.2017.8071292","DOIUrl":"https://doi.org/10.23919/FRUCT.2017.8071292","url":null,"abstract":"The paper analyzes an approach to the analytical attack modeling and security assessment on the base of the Common Vulnerability Scoring System (CVSS) format, considering different modifications that appeared in the new version of the CVSS specification. The common approach to the analytical attack modeling and security assessment was suggested by the authors earlier. The paper outlines disadvantages of previous CVSS version that influenced negatively on the results of the attack modeling and security assessment. Differences between new and previous CVSS versions are analyzed. Modifications of the approach to the analytical attack modeling and security assessment that follow from the CVSS modifications are suggested. Advantages of the modified approach are described. Case study that illustrates enhanced approach is provided.","PeriodicalId":114353,"journal":{"name":"2017 20th Conference of Open Innovations Association (FRUCT)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116894001","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Adaptive Q-Routing with random echo and route memory","authors":"Maksim Kavalerov, Y. Shilova, Y. Likhacheva","doi":"10.23919/FRUCT.2017.8071304","DOIUrl":"https://doi.org/10.23919/FRUCT.2017.8071304","url":null,"abstract":"Mobile ad hoc networks require routing algorithms that provide high performance in terms of delivery times of packets for dynamically changing topologies under various load conditions. A routing algorithm is proposed which is based on adaptive Q-routing technique with Full Echo extension. The proposed algorithm, called Adaptive Q-routing with Random Echo and Route Memory (AQRERM), has the improved performance in terms of overshoot and settling time of the learning. It also greatly improves stability of routing under conditions of high load for the benchmark example.","PeriodicalId":114353,"journal":{"name":"2017 20th Conference of Open Innovations Association (FRUCT)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124886005","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"A concept of continuous user authentication based on behavioral biometrics","authors":"A. Eremin, K. Kogos, A. Filina","doi":"10.23919/FRUCT.2017.8071293","DOIUrl":"https://doi.org/10.23919/FRUCT.2017.8071293","url":null,"abstract":"This paper focuses on continuous user authentication based on its interaction with the device. Behavioral authentication provides the ability to partially abandon passwords. Furthermore, the use of human behavior, for example, how he holds the device in hand, interacts with a screen, as a means of authentication is sufficiently protected from compromise, since an attacker cannot make an exact copy your gait or motion. Use of auxiliary factors such as the proximity of the trusted peripheral device, Wi-Fi network, location, helps simplify authentication.","PeriodicalId":114353,"journal":{"name":"2017 20th Conference of Open Innovations Association (FRUCT)","volume":"56 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127643719","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Influence of features discretization on accuracy of random forest classifier for web user identification","authors":"A. A. Vorobeva","doi":"10.23919/FRUCT.2017.8071354","DOIUrl":"https://doi.org/10.23919/FRUCT.2017.8071354","url":null,"abstract":"Web user identification based on linguistic or stylometric features helps to solve several tasks in computer forensics and cybersecurity, and can be used to prevent and investigate high-tech crimes and crimes where computer is used as a tool. In this paper we present research results on influence of features discretization on accuracy of Random Forest classifier. To evaluate the influence were carried out series of experiments on text corpus, contains Russian online texts of different genres and topics. Was used data sets with various level of class imbalance and amount of training texts per user. The experiments showed that the discretization of features improves the accuracy of identification for all data sets. We obtained positive results for extremely low amount of online messages per one user, and for maximum imbalance level.","PeriodicalId":114353,"journal":{"name":"2017 20th Conference of Open Innovations Association (FRUCT)","volume":"56 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132742434","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Y. Sheynin, V. Olenev, I. Lavrovskaya, I. Korobkov, S. Kochura, V. Shkolniy, Dmitry Dymov
{"title":"Computer-Aided design system for on-board SpaceWire networks simulation and design","authors":"Y. Sheynin, V. Olenev, I. Lavrovskaya, I. Korobkov, S. Kochura, V. Shkolniy, Dmitry Dymov","doi":"10.23919/FRUCT.2017.8071340","DOIUrl":"https://doi.org/10.23919/FRUCT.2017.8071340","url":null,"abstract":"The paper provides an analysis of existing simulation tools for the on-board and local area networks. We overview the main abilities of the existing software and then propose the computer-aided design (CAD) system for SpaceWire onboard networks design and simulation. This CAD system will support the full on-board network design and simulation flow, which begins from the network topology automated generation and finishes with getting the simulation results and statistics.","PeriodicalId":114353,"journal":{"name":"2017 20th Conference of Open Innovations Association (FRUCT)","volume":"64 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122528500","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}