FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4320712910> ?p ?o ?g. }

• W4320712910 endingPage "15448" @default.
• W4320712910 startingPage "15419" @default.
• W4320712910 abstract "The COVID-19 pandemic has severely affected various global markets, increasing the need for new forecasting models for the dry bulk market. Therefore, this study proposes deep neural network (abbreviated DNN) architectures to build a model for momentary forecasting that does not affect accuracy in the case of economic shocks (i.e., COVID-19) and elucidates the strategy for obtaining DNNs. First, since momentary and short-term forecastings are fundamentally different, they might use independent methods; as such, I apply DNN for the time series classification to momentary forecasting. Second, the proposed architecture is constructed by considering sparsity, because designing DNN architectures robust to any impacts is a type of overfitting prevention for deep neural networks. Finally, this study proposes indices for quantitatively evaluating the DNN architectures that represent the realized forecasting performance of various deep neural networks. Using these indices, I demonstrate that optimal architectures may need to have model sparsity in the DNN (i.e., sparsity independent of the input data). The importance of this issue has been demonstrated experimentally. As a result, the architectures achieved target performances of 88%, 91%, and 79% accuracy and had stability for Panamax, Supramax, and Capesize vessels, respectively from February 2016 to September 2021 (i.e., five years and eight months). It is difficult to identify a correlation between model performance and volatility. Furthermore, before and after the COVID-19 shock, the performance of the proposed models compared to the optimal one exceeds that of other four recent models, namely ”Facebook Prophet,” ”DARTS,” ”SKTIME,” and ”AutoTS." @default.
• W4320712910 created "2023-02-15" @default.
• W4320712910 creator A5083792107 @default.
• W4320712910 date "2023-01-01" @default.
• W4320712910 modified "2023-09-25" @default.
• W4320712910 title "Deep Neural Network Architectures for Momentary Forecasting in Dry Bulk Markets: Robustness to the Impact of COVID-19" @default.
• W4320712910 cites W1511501560 @default.
• W4320712910 cites W1832179792 @default.
• W4320712910 cites W1969412063 @default.
• W4320712910 cites W1971735090 @default.
• W4320712910 cites W1971916884 @default.
• W4320712910 cites W1981085262 @default.
• W4320712910 cites W1982584857 @default.
• W4320712910 cites W1983592571 @default.
• W4320712910 cites W1989102338 @default.
• W4320712910 cites W1991420284 @default.
• W4320712910 cites W2000322714 @default.
• W4320712910 cites W2011227258 @default.
• W4320712910 cites W2029527790 @default.
• W4320712910 cites W2037607963 @default.
• W4320712910 cites W2052996653 @default.
• W4320712910 cites W2053223966 @default.
• W4320712910 cites W2053244380 @default.
• W4320712910 cites W2055843842 @default.
• W4320712910 cites W2067718885 @default.
• W4320712910 cites W2072118886 @default.
• W4320712910 cites W2074741087 @default.
• W4320712910 cites W2096920123 @default.
• W4320712910 cites W2101285918 @default.
• W4320712910 cites W2103496339 @default.
• W4320712910 cites W2108537597 @default.
• W4320712910 cites W2123513648 @default.
• W4320712910 cites W2133783797 @default.
• W4320712910 cites W2146271801 @default.
• W4320712910 cites W2147360194 @default.
• W4320712910 cites W2147800946 @default.
• W4320712910 cites W2151554678 @default.
• W4320712910 cites W2154185090 @default.
• W4320712910 cites W2158241167 @default.
• W4320712910 cites W2158698691 @default.
• W4320712910 cites W2194775991 @default.
• W4320712910 cites W2423230295 @default.
• W4320712910 cites W2496717212 @default.
• W4320712910 cites W2544510896 @default.
• W4320712910 cites W2551393996 @default.
• W4320712910 cites W2606178078 @default.
• W4320712910 cites W2657631929 @default.
• W4320712910 cites W2747599906 @default.
• W4320712910 cites W2755520760 @default.
• W4320712910 cites W2781571649 @default.
• W4320712910 cites W2887286714 @default.
• W4320712910 cites W2890008621 @default.
• W4320712910 cites W2892035503 @default.
• W4320712910 cites W2910641113 @default.
• W4320712910 cites W2934059532 @default.
• W4320712910 cites W2937679722 @default.
• W4320712910 cites W2942231644 @default.
• W4320712910 cites W2944469930 @default.
• W4320712910 cites W2971791668 @default.
• W4320712910 cites W3011974631 @default.
• W4320712910 cites W3017042296 @default.
• W4320712910 cites W3046546941 @default.
• W4320712910 cites W3078821293 @default.
• W4320712910 cites W3081303655 @default.
• W4320712910 cites W3092201318 @default.
• W4320712910 cites W3092706105 @default.
• W4320712910 cites W3103113296 @default.
• W4320712910 cites W3109520983 @default.
• W4320712910 cites W3130777809 @default.
• W4320712910 cites W3147627103 @default.
• W4320712910 cites W3152792377 @default.
• W4320712910 cites W3168997536 @default.
• W4320712910 cites W3172942063 @default.
• W4320712910 cites W3179220440 @default.
• W4320712910 cites W3192181512 @default.
• W4320712910 cites W3194192744 @default.
• W4320712910 cites W4211006934 @default.
• W4320712910 cites W4224305133 @default.
• W4320712910 cites W4231109964 @default.
• W4320712910 cites W4238187298 @default.
• W4320712910 cites W4256596028 @default.
• W4320712910 cites W4281482594 @default.
• W4320712910 cites W4308793804 @default.
• W4320712910 doi "https://doi.org/10.1109/access.2023.3244680" @default.
• W4320712910 hasPublicationYear "2023" @default.
• W4320712910 type Work @default.
• W4320712910 citedByCount "1" @default.
• W4320712910 countsByYear W43207129102023 @default.
• W4320712910 crossrefType "journal-article" @default.
• W4320712910 hasAuthorship W4320712910A5083792107 @default.
• W4320712910 hasBestOaLocation W43207129101 @default.
• W4320712910 hasConcept C104317684 @default.
• W4320712910 hasConcept C119857082 @default.
• W4320712910 hasConcept C134306372 @default.
• W4320712910 hasConcept C142724271 @default.
• W4320712910 hasConcept C149782125 @default.
• W4320712910 hasConcept C154945302 @default.
• W4320712910 hasConcept C177148314 @default.

• next