Швыдун Сергей Владимирович

Superposition Principle for Tornado Prediction

2023 · CHAPTER · en

Constructing an Efficient Machine Learning Model for Tornado Prediction

2020 · ARTICLE · en

Tornado prediction variables are analyzed using machine learning and decision analysis techniques. A model based on several choice procedures and the superposition principle is applied for different methods of data analysis. The constructed model has been tested on a database of tornadic events. It is shown that the tornado prediction model developed herein is more efficient than a previous set of machine learning models, opening the way to more accurate decisions.

Power Distribution in the Networks of Terrorist Groups: 2001–2018

2020 · ARTICLE · en

Since 9/11, terrorism has become a global issue of the twenty-first century. Terrorist organizations become important actors of world politics as they gain influence on political process and decision-making. Some organizations compete with each other in order to gain more power and influence. We study the distribution of power among terrorist groups using network approach and applying classic and new centrality indices (Short-Range (SRIC) and Long-Range interactions indices (LRIC)). These indices allow to identify terrorist groups with direct and indirect influence on the terrorist network.

Power Distribution in the Networks of Terrorist Groups: 2001-2016

2019 · CHAPTER · en

Since 9/11, terrorism has become a global issue of the 21st century. Terrorist organizations become important actors of world politics as they gain influence on political process and decision-making. We study the distribution of power among terrorist groups using network approach.

From equality to diversity: Classifying Russian universities in a performance oriented system

2016 · ARTICLE · en

Over the last few decades, performance-based funding models of universities have been introduced and have made universities build and implement different strategies to enable them to compete and be viable in changing circumstances. In turn, national governments are focused on providing universities with more opportunities to run efficient programmes that advance higher education. This paper includes a detailed review of various taxonomies for structuring university. More importantly, it develops a typology of higher education institutions that is relevant for the Russian context. The Ward method is used to cluster universities on the basis of university distinctions in terms of the availability of resources, education, and research and development. This typology of universities is verified by assessing their efficiency score gained from modified Data Envelopment Analysis,incorporating universities' heterogeneity. Finally, the paper gives a decision tree for classifying universities bearing in mind their diversity. It might be expanded for abroader set of inputs and outputs, namely external projectbased research funding modes and cooperation between universities and industry to pursue the development of innovation. The results can be used for shaping targeted policies aimed at particular university groups

Construction of Universities' Typology via DEA

2016 · CHAPTER · en

In recent decades, increased economic pressure and growing societal expectations have led to the introduction of performance-based funding models for universities. In this respect, a great scholarly attention has paid to how to evaluate universities performance correctly. This allows national governments to design and apply various taxonomies to facilitate the development of efficient programmes for the advancement of higher education. The wide spread approach used for that purpose is DEA. This paper provides a review of different approaches how to take into account universities heterogeneity when applying DEA to construct the typologies of university by showing statistically their similarities and differences. The authors use the modified DEA proposed by Aleskerov & Petrushchenko (2013) to evaluate performance scores of Russian technical universities. This proposed typology divides universities into specific groups with a description taking into account their heterogeneity.

Centrality Measures in Large and Sparse Networks

2016 · CHAPTER · en

The problem of quick detection of central nodes in large networks is studied. There are many measures that allow to evaluate a topological importance of nodes of the network. Unfortunately, most of them cannot be applied to large networks due to their high computational complexity. However, if we narrow the initial network and apply these centrality measures to the sparse network, it is possible that the obtained set of central nodes will be similar to the set of central nodes in large networks. If these sets are similar, the centrality measures with a high computational complexity can be used for central nodes detection in large networks. To check the idea, several random networks were generated and different techniques of network reduction were considered. We also adapted some rules from social choice theory for the key nodes detection. As a result, we show how the initial network should be narrowed in order to apply centrality measures with a high computational complexity and maintain the set of key nodes of a large network.

Constructing an efficient machine learning model for tornado prediction

2016 · PREPRINT · en

Tornado prediction methods and main mechanisms of tornado genesis were analyzed. A model, based on the superposition principle, has been built. For efficiency evaluation, the constructed model has been tested on real-life data obtained from the University of Oklahoma (USA). It is shown that the constructed tornado prediction model is more efficient than all previous models.

Performance-Based Typology Of Universities: Evidence From Russia

2015 · PREPRINT · en

За последние десятилетия растущее экономическое давление и возросшие ожидания общества привели к внедрению системы государственного финансирования университетов, в основе которой лежат показатели результативности этих организаций. Адаптируясь к этим новым условиям финансирования, университеты начали развивать новые виды деятельности. В настоящее время национальные органы власти в разных странах занимаются разработкой и апробацией различных способов многоаспектной систематизации университетов в целях разработки эффективных программ для развития высшего образования. В статье подготовлен обзор литературы различных методов типологизации университетов, обсуждается выбор индикаторов и математического инструментария для группировки университетов с учетом их сходства и оценки эффективности университетов на основе классического и модифицированного методов оболочечного анализа данных (DEA). Мы предлагаем новую типологию университетов, принимая во внимание показатели их научной и образовательной деятельности, а также уровень эффективности. Предлагаемая типология, протестированная на российских данных, основана на кластеризации университетов с учетом их ресурсного обеспечения, научно-образовательного потенциала и показателей результативности. Созданная типология не только группирует университеты по типу, но и строит дерево решений для отнесения организации к тому или иному типу с учетом степени их неоднородности. Она может служить основой для содержательного анализа разнородной совокупности групп университетов и выработки адресных мер политики, адаптированных к специфике каждой из выделенных групп.

Типология российских вузов с учетом индикаторов научной и инновационной деятельности

2014 · CHAPTER · ru

Доклад подготовлен в рамках проекта «Формирование системы мониторинга экономики науки для оценки состояния сферы науки и технологий и демонстрации новых научных достижений» (государственный контракт Минобрнауки России от 26 сентября 2011 г. № 13.521.12.1011). Работа была частично поддержана Международной научно-учебной лабораторией анализа и выбора решений, Лабораторией экономики инноваций ИСИЭЗ и Институтом развития образования в рамках программы фундаментальных исследований НИУ ВШЭ в 2012 г.