FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2892035503> ?p ?o ?g. }

• W2892035503 endingPage "963" @default.
• W2892035503 startingPage "917" @default.
• W2892035503 abstract "Time Series Classification (TSC) is an important and challenging problem in data mining. With the increase of time series data availability, hundreds of TSC algorithms have been proposed. Among these methods, only a few have considered Deep Neural Networks (DNNs) to perform this task. This is surprising as deep learning has seen very successful applications in the last years. DNNs have indeed revolutionized the field of computer vision especially with the advent of novel deeper architectures such as Residual and Convolutional Neural Networks. Apart from images, sequential data such as text and audio can also be processed with DNNs to reach state-of-the-art performance for document classification and speech recognition. In this article, we study the current state-of-the-art performance of deep learning algorithms for TSC by presenting an empirical study of the most recent DNN architectures for TSC. We give an overview of the most successful deep learning applications in various time series domains under a unified taxonomy of DNNs for TSC. We also provide an open source deep learning framework to the TSC community where we implemented each of the compared approaches and evaluated them on a univariate TSC benchmark (the UCR/UEA archive) and 12 multivariate time series datasets. By training 8,730 deep learning models on 97 time series datasets, we propose the most exhaustive study of DNNs for TSC to date." @default.
• W2892035503 created "2018-09-27" @default.
• W2892035503 creator A5014963512 @default.
• W2892035503 creator A5030958578 @default.
• W2892035503 creator A5032791589 @default.
• W2892035503 creator A5044378917 @default.
• W2892035503 creator A5077151661 @default.
• W2892035503 date "2019-03-02" @default.
• W2892035503 modified "2023-10-16" @default.
• W2892035503 title "Deep learning for time series classification: a review" @default.
• W2892035503 cites W119403003 @default.
• W2892035503 cites W1469859527 @default.
• W2892035503 cites W1677182931 @default.
• W2892035503 cites W1705374184 @default.
• W2892035503 cites W1732493212 @default.
• W2892035503 cites W1832693441 @default.
• W2892035503 cites W1850325679 @default.
• W2892035503 cites W1900747440 @default.
• W2892035503 cites W1968354112 @default.
• W2892035503 cites W1970861901 @default.
• W2892035503 cites W1975257359 @default.
• W2892035503 cites W1978371851 @default.
• W2892035503 cites W1984674851 @default.
• W2892035503 cites W2014307680 @default.
• W2892035503 cites W2014725748 @default.
• W2892035503 cites W2016944307 @default.
• W2892035503 cites W2026430219 @default.
• W2892035503 cites W2030863907 @default.
• W2892035503 cites W2050493487 @default.
• W2892035503 cites W2068194158 @default.
• W2892035503 cites W2070808135 @default.
• W2892035503 cites W2081028405 @default.
• W2892035503 cites W2084536656 @default.
• W2892035503 cites W2097117768 @default.
• W2892035503 cites W2111473877 @default.
• W2892035503 cites W2112739286 @default.
• W2892035503 cites W2112796928 @default.
• W2892035503 cites W2117539524 @default.
• W2892035503 cites W2118706537 @default.
• W2892035503 cites W2160815625 @default.
• W2892035503 cites W2165698076 @default.
• W2892035503 cites W2166547175 @default.
• W2892035503 cites W2194775991 @default.
• W2892035503 cites W2270470215 @default.
• W2892035503 cites W2295107390 @default.
• W2892035503 cites W2440222035 @default.
• W2892035503 cites W2510380565 @default.
• W2892035503 cites W2510434276 @default.
• W2892035503 cites W2524083015 @default.
• W2892035503 cites W2550848904 @default.
• W2892035503 cites W2551393996 @default.
• W2892035503 cites W2555077524 @default.
• W2892035503 cites W2578445924 @default.
• W2892035503 cites W2585354796 @default.
• W2892035503 cites W2598525681 @default.
• W2892035503 cites W2616619856 @default.
• W2892035503 cites W2736191430 @default.
• W2892035503 cites W2759690896 @default.
• W2892035503 cites W2763079654 @default.
• W2892035503 cites W2765911928 @default.
• W2892035503 cites W2772740820 @default.
• W2892035503 cites W2773554974 @default.
• W2892035503 cites W2773583505 @default.
• W2892035503 cites W2773662615 @default.
• W2892035503 cites W2775133808 @default.
• W2892035503 cites W2786161686 @default.
• W2892035503 cites W2787600432 @default.
• W2892035503 cites W2791900323 @default.
• W2892035503 cites W2792071264 @default.
• W2892035503 cites W2792740245 @default.
• W2892035503 cites W2794787390 @default.
• W2892035503 cites W2795342689 @default.
• W2892035503 cites W2797694788 @default.
• W2892035503 cites W2805586107 @default.
• W2892035503 cites W2808392264 @default.
• W2892035503 cites W2808955427 @default.
• W2892035503 cites W2897647030 @default.
• W2892035503 cites W2898843852 @default.
• W2892035503 cites W2902760701 @default.
• W2892035503 cites W2919115771 @default.
• W2892035503 cites W2963034797 @default.
• W2892035503 cites W2963042536 @default.
• W2892035503 cites W2963599029 @default.
• W2892035503 cites W2988244882 @default.
• W2892035503 cites W3098949126 @default.
• W2892035503 cites W3103507112 @default.
• W2892035503 cites W4236619680 @default.
• W2892035503 cites W4238404964 @default.
• W2892035503 cites W4246262524 @default.
• W2892035503 cites W4246354968 @default.
• W2892035503 cites W4252684946 @default.
• W2892035503 cites W67158865 @default.
• W2892035503 cites W848133049 @default.
• W2892035503 cites W98192633 @default.
• W2892035503 doi "https://doi.org/10.1007/s10618-019-00619-1" @default.
• W2892035503 hasPublicationYear "2019" @default.
• W2892035503 type Work @default.
• W2892035503 sameAs 2892035503 @default.

• next