This volume contains proceedings of the Fifth International conference on Analysis of Images, Social Networks, and Texts (AIST 2016)1. The previous conferences in 2012{2015 attracted a signi cant number of students, researchers, academics and engineers working on interdisciplinary data analysis of images, texts, and social networks.
The broad scope of AIST makes it an event where researchers from di erent domains, such as image and text processing, exploiting various data analysis techniques, can meet and exchange ideas. We strongly believe that this may lead to crossfertilisation of ideas between researchers relying on modern data analysis machinery. Therefore, AIST brings together all kinds of applications of data mining and machine learning techniques. The conference allows specialists from di erent elds to meet each other, present their work, and discuss both theoretical and practical aspects of their data analysis problems. Another important aim of the conference is to stimulate scientists and people from the industry to bene t from the knowledge exchange and identify possible grounds for fruitful collaboration.
The conference was held during April 6{8, 2016. Following an already established tradition, the conference was organised in Yekaterinburg, a cross-roads between European and Asian parts of Russia, the capital of Urals region.The key topics of AIST are analysis of images and videos; natural language processing and computational linguistics; social network analysis; pattern recognition, machine learning and data mining; recommender systems and collaborative technologies; semantic web, ontologies and their applications.
The Program Committee and the reviewers of the conference included wellknown experts in data mining and machine learning, natural language processing, image processing, social network analysis, and related areas from leading institutions of 27 countries including Australia, Bangladesh, Belgium, Brazil, Croatia, Cyprus, Egypt, Estonia, Finland, France, Germany, Greece, India, Ireland, Israel, Italy, Japan, Lithuania, Norway, Portugal, Qatar, Russia, Spain, Switzerland, The Netherlands, UK, Ukraine, and USA.
This year we have received 142 submissions mostly from Russia but also from Australia, Austria, France, Hungary, India, Italy, Mexico, Norway, Sweden, UK, USA and Vietnam.
Out of 142 only 30 papers were accepted as regular oral papers. Thus, the acceptance rate of this volume was around 21%. In order to encourage young practitioners and researchers we included 3 papers of industry speakers to the main volume and 38 papers to the supplementary proceedings. Each submission was reviewed by at least three reviewers, experts in their elds, in order to supply detailed and helpful comments.
The conference featured several invited talks and industry session dedicated to current trends and challenges.
Invited talks: { Mehdi Kaytoue (Universite de Lyon, CNRS, INSA-Lyon, France), Finding
Duplicate Labels in Behavioral Data: an Application for E-Sport Analytics. { Attila Kertesz-Farkas (Higher School of Economics, Russia), False Discovery Rate Control for Database Search Methods over Heterogeneous Biological Data { Radhakrishnan Delhibabu (Kazan Federal University, Russia), Analysis of Anisotropic Di usion in Image Processing
The business speakers also covered a wide variety of topics2. We have included three of those invited talks into the main volume: { Denis Nikiforov, Alexander Korchagin and Ruslan Sivakov (Centre of Information Technology, Ekaterinburg, Russia) An Ontology-Driven Approach to Electronic Document Structure Design { Tatyana Prisyach (Speech Technology Center, St. Petersburg, Russia), Valentin Mendelev and Dmitry Ubskiy (ITMO-University, St. Petersburg, Russia), Data Augmentation for Training of Noise Robust Acoustic Models { Alexander Semenov (Higher School of Economics, Russia) and Peter Romov (Yandex, Russia), Performance of Machine Learning Algorithms in Predicting Game Outcome from Drafts in Dota
We would also like to mention the best conference papers selected by the Program Committee within each section: { On Complexity of Searching a Subset of Vectors with Shortest Average under a Cardinality Restriction by Anton Eremeev, Alexander Kelmanov, and Artem Pyatkin (Machine Learning and Data Mining ); { The Problem of The Optimal Packing of The Equal Radius Circles for NonEuclidean Metric by Alexander Kazakov, Anna Lempert and Huy Liem Nguyen (Data Analysis, Social Networks & Complex Data ); { Parallel Non-blocking Deterministic Algorithm for Online Topic Modeling by Oleksandr Frei and Murat Apishev (Natural Language Processing ); { Image Processing Algorithms with Structure Transferring Properties on the Basis of Gamma-normal Model by Inessa Gracheva and Andrey Kopylov (Analysis of Images and Video).
The nal round of SNA Hackathon 20163 co-organised by OK.Ru and AIST team has taken place in conjunction with the main conference on April 6{8.
We would like to thank the authors for submitting their papers and the members of the Program Committee for their e orts in providing exhaustive 2 the detailed program of AIST 2016 Business Day can be found at a separate website: http://dataconf.org 3 http://snahackathon.org/
vi reviews. We would also like to express special gratitude to all the invited speakers and industry representatives.
We deeply thank all the partners and sponsors. Our golden sponsors are Exactpro4 and OK.Ru5. Exactpro, a fully owned subsidiary of London Stock Exchange Group, specialises in quality assurance for exchanges, investment banks, brokers and other nancial sector organisations. OK.Ru, a part of Mail.Ru Group, is one of the two largest Russian social networking services. Our bronze sponsor is Centre of Information Technologies (Centre IT)6. This is a Russian engineering company that specializes in creating exclusive IT solutions and services for the interdepartmental electronic interaction both on the national and international levels.
We would like to acknowledge the Scienti c Fund of Higher School of Economics for providing AIST participants with travel grants. Our special thanks goes to Springer editors who helped us, starting from the rst conference call to the nal version of the proceedings. Last but not least, we are grateful to all organisers, especially to Eugeniya Vlasova, and the volunteers, whose endless energy saved us at the most critical stages of the conference preparation.
Traditionally, we would like to mention the Russian word \aist" is more than just a simple abbreviation (in Cyrillic), it means a \stork". Since it is a wonderful free bird, a symbol of happiness and peace, this stork brought us the inspiration to organise the AIST conference. So we believe that this young and rapidly growing conference will be bringing inspiration to data scientists around the World!
Michael Khachay
Valery Labunets Natalia Loukachevitch
Sergey Nikolenko Alexander Panchenko
Andrey Savchenko Konstantin Vorontsov Organisation
National Research University Higher School of Economics, Moscow, Russia Krasovsky Institute of Mathematics and Mechanics of Ural Branch of Russian Academy of Sciences, Russia Ural Federal University, Russia Computing Centre of Lomonosov Moscow State University, Russia National Research University Higher School of Economics & Steklov Institute of Mathematics of Russian Academy of Sciences, St. Petersburg, Russia Technische Universitat Darmstadt, Germany & Universite catholique de Louvain, Belgium National Research University Higher School of Economics, Nizhny Novgorod, Russia Dorodnicyn Computing Centre of Russian Academy of Sciences, Russia
National Research University Higher School of Economics, Russia
Ekaterina Borovitina National Research University Higher School of Economics, Moscow National Research University Higher School of Economics, Moscow National Research University Higher School of Economics, Moscow Ural Federal University, Yekaterinburg Chelyabinsk State University, Russia
Krasovsky Institute of Mathematics and Mechanics of Ural Branch of Russian Academy of Sciences, Russia, Yekaterinburg Yandex, Moscow Webgames & National Research University Higher School of Economics, Moscow National Research University Higher School of Economics, Moscow National Research University Higher School of Economics, Moscow National Research University Higher School of Economics, Moscow
Anastasia Osmolovskaya Aurelien Bossard Jean-Leon Bouraoui Leonid Boytsov Pavel Braslavski Evgeny Burnaev
Artem Chernodub Institute of Mathematical Machines and Systems Problems of Ukraine National Academy of Science,
Ukraine Vladimir Chernov Institute for Image Processing of Russian Academy of Science, Russia Ekaterina Chernyak National Research University Higher School of Economics, Russia Marina Chicheva Samara National Research University, Russia Bonaventura Coppola IBM Research, USA Hernani Costa University of Malaga, Spain Boris Dobrov Lomonosov Moscow State University, Russia So a Dokuka National Research University Higher School of Economics, Russia Florent Domenach Akita International University, Japan Alexey Drutsa Lomonosov Moscow State University & Yandex,
Russia Julia Efremova Eindhoven University of Technology, The Netherlands Natalia Efremova Moscow State Lomonosov University, Russia Maria Eskevich Radboud University Nijmegen, the Netherlands Myasnikov Evgeny Samara National Research University, Russia Stefano Faralli University of Mannheim, Germany Victor Fedoseev Image Processing Systems Institute of Russian Academy of Sciences & Samara National Research
University, Russia Michael Figurnov Skolkovo Institute of Science and Technology, Russia Elena Filatova New York City College of Technology, USA Mark Fishel University of Tartu, Estonia Thomas Francois Universite catholique de Louvain, Belgium Oleksandr Frei Schlumberger, Norway Binyam Gebrekidan Gebre Max Planck Institute for Psycholinguistics, The
Netherlands Natalia Grabar STL CNRS Universite Lille 3, France Dmitry Granovsky Yandex, Russia Mena Habib Maastricht University, The Netherlands Dmitry Ilvovsky National Research University Higher School of Economics, Russia Vladimir Ivanov Kazan Federal University, Russia Dmitry Kan SemanticAnalyzer, Finland Nikolay Karpov National Research University Higher School of Economics, Russia Egor Kashkin Vinogradov Russian Language Institute of Russian
Academy of Sciences, Russia Yury Katkov Ecole Polytechnique Federale de Lausanne, Switzerland
Yelena Mejova Benjamin Milde Olga Mitrofanova Andrea Moro Hubert Naets
Sobolev Institute of Mathematics of Siberian Branch of Russian Academy of Sciences, Russia Moscow Aviation Institute, Russia Lomonosov Moscow State University, Russia Moscow State Institute of Electronics and Mathematics, Russia University of Cambridge, UK National Research University Higher School of Economics, Russia National Research University Higher School of Economics, Russia AltexSoft, Ukraine University of Wolverhampton, UK Tula State University, Russia Itseez & Lobachevsky State University of Nizhni Novgorod, Russia ScrapingHub, Russia Institute for System Programming of Russian Academy of Sciences, Russia Vyatka State University, Russia Tula State University, Russia Vytautas Magnus University, Lithuania National Research University Higher School of Economics, Russia University of Oslo, Norway Samara National Research University, Russia National Research University Higher School of Economics, Russia Ariel University, Israel National Research University Higher School of Economics, Russia Lomonosov Moscow State University, Russia National Research University Higher School of Economics & Vinogradov Russian Language Institute of Russian Academy of Sciences, Russia University of Amsterdam, The Netherlands Carnegie Mellon University, USA and(University of Lisbon, Portugal University of Aveiro, Portugal Qatar Computing Research Institute, Qatar Technische Universitat Darmstadt, Germany St. Petersburg State University, Russia Sapienza, Universita di Roma, Italy Universite Catholique de Louvain, Belgium Vassilina Nikoulina Xerox Research Center Europe, France Damien Nouvel Institut National des Langues et Civilisations Orientales, France Dimitri Nowicki Institute of Cybernetics of Ukraine National
Academy of Science, Ukraine Alexander Panchenko Universite catholique de Louvain, Belgium Georgios Petasis National Center for Scienti c Research Demokritos,
Greece Andrey Philippovich Bauman Moscow State Technical University,
Moscow Lidia Pivovarova University of Helsinki, Finland Vladimir Pleshko RCO, Russia Jonas Poelmans Bigdatarobots, Cyprus Alexander Porshnev National Research University Higher School of Economics, Russia Surya Prasath University of Missouri-Columbia, USA Delhibabu Radhakrishnan Kazan Federal University, Russia Carlos Ramisch Aix Marseille University, France Evgeniy Riabenko Moscow Institute of Physics and Technology, Russia Martin Riedl Technische Universitat Darmstadt, Germany Alexandra Roshchina Institute of Technology Tallaght, Ireland Eugen Ruppert Technische Universitat Darmstadt, Germany Mohammed Abdel-Mgeed Ain Shams University, Egypt M. Salem Grigory Sapunov Stepic, Russia Sheikh Muhammad Sarwar University of Dhaka, Bangladesh & University of
Massachusetts Amherst, USA Andrey Savchenko National Research University Higher School of Economics, Russia Carsten Schnober Deutsches Institut fur Internationale Padagogische
Forschung, Germany Marijn Schraagen Utrecht University, The Netherlands Alexander Semenov National Research University Higher School of Economics, Russia Oleg Seredin Tula State University, Russia Andrey Shcherbakov Intel, Russia Jan Snajder University of Zagreb, Croatia Evgeny Sokolov Lomonosov Moscow State University, Germany Christian Stab Technische Universitat Darmstadt, Germany Vadim Strijov Dorodnicyn Computing Centre of Russian Academy of Sciences, Russia Maria Sukhareva Goethe University Frankfurt, Germany Marina Suvorova Lomonosov Moscow State University, Russia Irina Temnikova Qatar Computing Research Institute, Qatar Christos Tryfonopoulos University of Peloponnese, Greece
xii
Natalia Vassilieva Dmitry Vetrov Ekaterina Vylomova Patrick Watrin Rostislav Yavorskiy
Vladimir M. Chernov Samuel Daylis Svyatoslav Elizarov Yuri Kan Alexander Minkin Paraskevi Raftopoulou Ivan Sterligov Natali Vaganova
Bronze sponsor: Institute for System Programming of Russian Academy of Sciences, Russia HP Labs, Russia HP Labs, Russia Lomonosov Moscow State University, Russia University of Melbourne, Australia Universite catholique de Louvain, Belgium National Research University Higher School of Economics, Russia Technische Universitat Darmstadt, Germany Saarland University, Germany Ural Federal University, Russia
Silvio Ricardo Cordeiro Anna Denisova Denis Fedyanin Benjamin Milde Andrey Naumov Oleg Slavin Dmitry Ustalov Diliara Valeeva Lefteris Zervakis
IT Centre
The Structure of an Investment Portfolio in Two-step Problem of Optimal Investment with One Risky Asset Via the Probability Criterion :
Alexei Ignatov Evolution of Advanced Technology Studies: Searching for a Communication Core : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : :
Alina Kadyrova and Konstantin Fursov Evolvable Semantic Platform for Facilitating Knowledge Exchange : : : : : :
Nikolay Karpov, Eduard Babkin and Alexander Demidovskij Lazy Learning of Classi cation Rules for Complex Structure Data : : : : : : :
Yury Kashnitsky The Corpus of Syntactic Co-occurences: the First Glance : : : : : : : : : : : : : : Edward Klyshinsky, Petr Ermakov, Natalia Lukashevich and Olesya Karpik 1 10 21 27 42 51 62 73 85 Determination of an Unmanned Mobile Object Orientation by Natural Landmarks : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : Anton Korsakov, Ivan Fomin, Dmitry Gromoshinsky, Aleksandr Bakhshiev, Dmitrii Stepanov and Ekaterina Smirnova 91 Using Ontology-Driven Methods to Develop Frameworks for Tackling NLP Problems : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : 102
Taisiya Kostareva, Svetlana Chuprina and Alexandr Nam Detection and Tracking of the Objects in Real Time Applied to the Problem of the Log Volume Estimation : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : 114
Artem Kruglov and Yurii Chiryshev Checking the Topological Consistency of Maps of Di erent Scales : : : : : : : 124
Kirill Kuptsov, Sergey Eremeev and Dmitry Andrianov The 360 Around View System for Large Vehicles, the Methods of Calibration and Removal of Barrel Distortion for Omnidirectional Cameras 182
Aleksey S. Makarov and Marina V. Bolsunovskaya Smoothing Voronoi-Based Path with Minimized Length and Visibility Using Composite Bezier Curves : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : 191
Ilya Makarov and Pavel Polyakov Multi-class Learning in Big Data : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : 203
Anton Malenichev, Olga Krasotkina, Vadim Mottl and Oleg Seredin Automatic Detection of Bone Contours in X-Ray Images : : : : : : : : : : : : : : : 212
Alexey Mikhaylichenko, Yana Demyanenko and Elena Grushko Program Tools for Dynamic Investigation of Social Networks : : : : : : : : : : : 224
Alexander Mikov, Elena Zamyatina and Daria Germanova Classi cation of E-commerce Websites by Product Categories : : : : : : : : : : : 237
George Moiseev The Study of Applicability of the Decision Tree Method for Contouring of the Left Ventricle Area in Echographic Video Data : : : : : : : : : : : : : : : : : : 248 Andrey Mukhtarov, Sergey Porshnev, Vasiliy Zuzin, Anastasia Bobkova and Vladimir Bobkov Extracting Functional Job Roles from Professional Social Networking Site Pro les : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : 258
Anastasiia Nesterenko On Road Defects Detection and Classi cation : : : : : : : : : : : : : : : : : : : : : : : : 264 Thu Huong Nguyen, Aleksei Zhukov and The Long Nguyen