Matches in SemOpenAlex for { <https://semopenalex.org/work/W3028190586> ?p ?o ?g. }
- W3028190586 endingPage "241" @default.
- W3028190586 startingPage "229" @default.
- W3028190586 abstract "In this article, novel gradient-based online learning algorithms are developed to investigate an important environmental application: real-time river pollution source identification, which aims at estimating the released mass, location, and time of a river pollution source based on downstream sensor data monitoring the pollution concentration. The pollution is assumed to be instantaneously released once. The problem can be formulated as a non-convex loss minimization problem in statistical learning, and our online algorithms have vectorized and adaptive step sizes to ensure high estimation accuracy in three dimensions which have different magnitudes. In order to keep the algorithm from sticking in the saddle points of non-convex loss, the “escaping from saddle points” module and multi-start setting are derived to further improve the estimation accuracy by searching for the global minimizer of the loss functions. This can be shown theoretically and experimentally as the O(N) local regret of the algorithms and the high probability cumulative regret bound O(N) under a particular error bound condition in loss functions. A real-life river pollution source identification example shows the superior performance of our algorithms compared with existing methods in terms of estimation accuracy. Managerial insights for the decision maker to use the algorithms are also provided." @default.
- W3028190586 created "2020-05-29" @default.
- W3028190586 creator A5057139422 @default.
- W3028190586 creator A5070019149 @default.
- W3028190586 creator A5076409244 @default.
- W3028190586 date "2022-06-13" @default.
- W3028190586 modified "2023-10-18" @default.
- W3028190586 title "Online non-convex learning for river pollution source identification" @default.
- W3028190586 cites W180788695 @default.
- W3028190586 cites W1969811075 @default.
- W3028190586 cites W1985996142 @default.
- W3028190586 cites W1991588358 @default.
- W3028190586 cites W2008715482 @default.
- W3028190586 cites W2037784954 @default.
- W3028190586 cites W2068484625 @default.
- W3028190586 cites W2069077479 @default.
- W3028190586 cites W2108531548 @default.
- W3028190586 cites W2118401377 @default.
- W3028190586 cites W2129566862 @default.
- W3028190586 cites W2132104902 @default.
- W3028190586 cites W2140821003 @default.
- W3028190586 cites W2144990451 @default.
- W3028190586 cites W2148813887 @default.
- W3028190586 cites W2155233957 @default.
- W3028190586 cites W2203059607 @default.
- W3028190586 cites W2259931409 @default.
- W3028190586 cites W2287294036 @default.
- W3028190586 cites W2291209874 @default.
- W3028190586 cites W2294011225 @default.
- W3028190586 cites W2320177191 @default.
- W3028190586 cites W2724044141 @default.
- W3028190586 cites W2791400650 @default.
- W3028190586 cites W2808043439 @default.
- W3028190586 cites W2945029112 @default.
- W3028190586 cites W3006428262 @default.
- W3028190586 cites W3106156334 @default.
- W3028190586 cites W4205841652 @default.
- W3028190586 cites W4292022450 @default.
- W3028190586 cites W924002907 @default.
- W3028190586 doi "https://doi.org/10.1080/24725854.2022.2068087" @default.
- W3028190586 hasPublicationYear "2022" @default.
- W3028190586 type Work @default.
- W3028190586 sameAs 3028190586 @default.
- W3028190586 citedByCount "0" @default.
- W3028190586 crossrefType "journal-article" @default.
- W3028190586 hasAuthorship W3028190586A5057139422 @default.
- W3028190586 hasAuthorship W3028190586A5070019149 @default.
- W3028190586 hasAuthorship W3028190586A5076409244 @default.
- W3028190586 hasBestOaLocation W30281905862 @default.
- W3028190586 hasConcept C112680207 @default.
- W3028190586 hasConcept C11413529 @default.
- W3028190586 hasConcept C116834253 @default.
- W3028190586 hasConcept C119857082 @default.
- W3028190586 hasConcept C126255220 @default.
- W3028190586 hasConcept C134306372 @default.
- W3028190586 hasConcept C157972887 @default.
- W3028190586 hasConcept C18903297 @default.
- W3028190586 hasConcept C2524010 @default.
- W3028190586 hasConcept C2681867 @default.
- W3028190586 hasConcept C2777127463 @default.
- W3028190586 hasConcept C33923547 @default.
- W3028190586 hasConcept C41008148 @default.
- W3028190586 hasConcept C50817715 @default.
- W3028190586 hasConcept C521259446 @default.
- W3028190586 hasConcept C59822182 @default.
- W3028190586 hasConcept C77553402 @default.
- W3028190586 hasConcept C86803240 @default.
- W3028190586 hasConceptScore W3028190586C112680207 @default.
- W3028190586 hasConceptScore W3028190586C11413529 @default.
- W3028190586 hasConceptScore W3028190586C116834253 @default.
- W3028190586 hasConceptScore W3028190586C119857082 @default.
- W3028190586 hasConceptScore W3028190586C126255220 @default.
- W3028190586 hasConceptScore W3028190586C134306372 @default.
- W3028190586 hasConceptScore W3028190586C157972887 @default.
- W3028190586 hasConceptScore W3028190586C18903297 @default.
- W3028190586 hasConceptScore W3028190586C2524010 @default.
- W3028190586 hasConceptScore W3028190586C2681867 @default.
- W3028190586 hasConceptScore W3028190586C2777127463 @default.
- W3028190586 hasConceptScore W3028190586C33923547 @default.
- W3028190586 hasConceptScore W3028190586C41008148 @default.
- W3028190586 hasConceptScore W3028190586C50817715 @default.
- W3028190586 hasConceptScore W3028190586C521259446 @default.
- W3028190586 hasConceptScore W3028190586C59822182 @default.
- W3028190586 hasConceptScore W3028190586C77553402 @default.
- W3028190586 hasConceptScore W3028190586C86803240 @default.
- W3028190586 hasFunder F4320321001 @default.
- W3028190586 hasIssue "3" @default.
- W3028190586 hasLocation W30281905861 @default.
- W3028190586 hasLocation W30281905862 @default.
- W3028190586 hasOpenAccess W3028190586 @default.
- W3028190586 hasPrimaryLocation W30281905861 @default.
- W3028190586 hasRelatedWork W2011746047 @default.
- W3028190586 hasRelatedWork W2352701666 @default.
- W3028190586 hasRelatedWork W2742141334 @default.
- W3028190586 hasRelatedWork W2963746283 @default.
- W3028190586 hasRelatedWork W2992295340 @default.
- W3028190586 hasRelatedWork W3173102712 @default.
- W3028190586 hasRelatedWork W4285050980 @default.