FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2185707977> ?p ?o ?g. }

• W2185707977 abstract "This paper explores the use of Support Vector Machine (SVM) as a predictive engine for natural hazards forecasting. It particularly discusses the issues of incorporating this classification method into a decision-support system for operational use in avalanche forecasting. The recent developments concerned with semi-supervised and transductive SVM-based learning targeted at applications in natural hazards forecasting on geomanifolds are presented. The real case study on spatio-temporal avalanche forecasting deals with the development of a predictive engine for the decision support system used at the avalanche- prone site of Ben Nevis, Lochaber region in Scotland. Amongst different natural hazards the events like snow avalanches are of particular interest. These events can be characterized by relatively low frequency, complex non-linear relationships with meteorological conditions, geomorphology and a large variety of other factors including human activity on the site. In terms of data-driven modeling, the avalanche forecasting can be considered as a classification problem, where one needs to find a decision boundary in the feature space of factors which discriminate the safe and dangerous conditions. In this paper we explore the use of Support Vector Machine (SVM), a method from the field of Machine Learning, as a predictive engine for natural hazard forecasting. We discuss the issues of incorporating the developed model into a decision-support system for operational use in avalanche forecasting, and present the recent achievements. The real case study on the application of SVM is devoted to temporal and spatio-temporal avalanche forecasting at the avalanche-prone site of Ben Nevis, Lochaber region in Scotland, where avalanche forecasts are produced daily in winter months. The paper is organized as follows. First, in the next section, we introduce the data-driven classification as an approach to decision support. We present there the basic features of a particular machine learning classification method, SVM, including the probabilistic interpretation of its outputs. Next, in Section 3, we motivate the use of semi-supervised and transductive learning in environmental data-driven modelling and describe the related contemporary approaches. We finally review the recent results on the application of SVMs for decision support in avalanche forecasting and provide the preliminary results on the use of semi-supervised and transductive SVM learning (Section 4). The paper is summarized with directions to the further developments and the conclusions in Section 5." @default.
• W2185707977 created "2016-06-24" @default.
• W2185707977 creator A5048171501 @default.
• W2185707977 creator A5068472081 @default.
• W2185707977 creator A5080785648 @default.
• W2185707977 date "2008-01-01" @default.
• W2185707977 modified "2023-09-26" @default.
• W2185707977 title "Semi-Supervised Support Vector Machine for Natural Hazards Forecasting. Case Study: Snow Avalanches" @default.
• W2185707977 cites W1421216920 @default.
• W2185707977 cites W1479807131 @default.
• W2185707977 cites W1551558534 @default.
• W2185707977 cites W1560724230 @default.
• W2185707977 cites W1607624180 @default.
• W2185707977 cites W1618905105 @default.
• W2185707977 cites W1652382999 @default.
• W2185707977 cites W1989857949 @default.
• W2185707977 cites W2033131288 @default.
• W2185707977 cites W2084336510 @default.
• W2185707977 cites W2142114717 @default.
• W2185707977 cites W2148603752 @default.
• W2185707977 cites W2153529786 @default.
• W2185707977 cites W2174601942 @default.
• W2185707977 hasPublicationYear "2008" @default.
• W2185707977 type Work @default.
• W2185707977 sameAs 2185707977 @default.
• W2185707977 citedByCount "0" @default.
• W2185707977 crossrefType "journal-article" @default.
• W2185707977 hasAuthorship W2185707977A5048171501 @default.
• W2185707977 hasAuthorship W2185707977A5068472081 @default.
• W2185707977 hasAuthorship W2185707977A5080785648 @default.
• W2185707977 hasConcept C107327155 @default.
• W2185707977 hasConcept C119857082 @default.
• W2185707977 hasConcept C12267149 @default.
• W2185707977 hasConcept C124101348 @default.
• W2185707977 hasConcept C138885662 @default.
• W2185707977 hasConcept C153294291 @default.
• W2185707977 hasConcept C154945302 @default.
• W2185707977 hasConcept C178790620 @default.
• W2185707977 hasConcept C185592680 @default.
• W2185707977 hasConcept C205649164 @default.
• W2185707977 hasConcept C2776401178 @default.
• W2185707977 hasConcept C39410599 @default.
• W2185707977 hasConcept C41008148 @default.
• W2185707977 hasConcept C41895202 @default.
• W2185707977 hasConcept C42023084 @default.
• W2185707977 hasConcept C49261128 @default.
• W2185707977 hasConceptScore W2185707977C107327155 @default.
• W2185707977 hasConceptScore W2185707977C119857082 @default.
• W2185707977 hasConceptScore W2185707977C12267149 @default.
• W2185707977 hasConceptScore W2185707977C124101348 @default.
• W2185707977 hasConceptScore W2185707977C138885662 @default.
• W2185707977 hasConceptScore W2185707977C153294291 @default.
• W2185707977 hasConceptScore W2185707977C154945302 @default.
• W2185707977 hasConceptScore W2185707977C178790620 @default.
• W2185707977 hasConceptScore W2185707977C185592680 @default.
• W2185707977 hasConceptScore W2185707977C205649164 @default.
• W2185707977 hasConceptScore W2185707977C2776401178 @default.
• W2185707977 hasConceptScore W2185707977C39410599 @default.
• W2185707977 hasConceptScore W2185707977C41008148 @default.
• W2185707977 hasConceptScore W2185707977C41895202 @default.
• W2185707977 hasConceptScore W2185707977C42023084 @default.
• W2185707977 hasConceptScore W2185707977C49261128 @default.
• W2185707977 hasLocation W21857079771 @default.
• W2185707977 hasOpenAccess W2185707977 @default.
• W2185707977 hasPrimaryLocation W21857079771 @default.
• W2185707977 hasRelatedWork W1933394711 @default.
• W2185707977 hasRelatedWork W2284097410 @default.
• W2185707977 hasRelatedWork W2289869083 @default.
• W2185707977 hasRelatedWork W2589392130 @default.
• W2185707977 hasRelatedWork W2759797999 @default.
• W2185707977 hasRelatedWork W2768369945 @default.
• W2185707977 hasRelatedWork W2777691585 @default.
• W2185707977 hasRelatedWork W2807138771 @default.
• W2185707977 hasRelatedWork W2899619587 @default.
• W2185707977 hasRelatedWork W2914463281 @default.
• W2185707977 hasRelatedWork W2991364382 @default.
• W2185707977 hasRelatedWork W2995734456 @default.
• W2185707977 hasRelatedWork W2997411708 @default.
• W2185707977 hasRelatedWork W3006260484 @default.
• W2185707977 hasRelatedWork W3011215211 @default.
• W2185707977 hasRelatedWork W3033008316 @default.
• W2185707977 hasRelatedWork W3190838952 @default.
• W2185707977 hasRelatedWork W3203662702 @default.
• W2185707977 hasRelatedWork W2879350879 @default.
• W2185707977 hasRelatedWork W3111105136 @default.
• W2185707977 isParatext "false" @default.
• W2185707977 isRetracted "false" @default.
• W2185707977 magId "2185707977" @default.
• W2185707977 workType "article" @default.