Matches in SemOpenAlex for { <https://semopenalex.org/work/W4200528093> ?p ?o ?g. }
- W4200528093 endingPage "108286" @default.
- W4200528093 startingPage "108286" @default.
- W4200528093 abstract "Non-linear regression is the primary tool for estimating kinetic models of chemical reactions. The default approach of minimizing the sum of squared residuals tends to underperform in the presence of systematic errors, non-normal distribution of residuals or identifiability issues such as a high correlation between parameters. Therefore, we argue for a careful choice of the fit criteria and propose new, concave loss functions. Together with regularization, they form a robust objective for the regression procedure. Discussion of the rationale behind the proposed approach and its effects is illustrated by laboratory data on the transesterification of palm oil. A dedicated simulation study complements qualitative examples. All of the top-performing methods use regularization. Concave loss functions were among the best in 6–7 out of 8 test cases, compared to 2–3 for the classical square loss confirming both statistical and practical usefulness of the novel fit criteria. This result holds for a variety of modern optimizers. In 76% of our simulations, we obtained results not significantly worse than the best, whereas methods currently used in the literature provide 38% for the relative and 0% for the square loss." @default.
- W4200528093 created "2021-12-31" @default.
- W4200528093 creator A5008298191 @default.
- W4200528093 creator A5058101576 @default.
- W4200528093 date "2022-02-01" @default.
- W4200528093 modified "2023-09-27" @default.
- W4200528093 title "Regularization and concave loss functions for estimation of chemical kinetic models" @default.
- W4200528093 cites W130017914 @default.
- W4200528093 cites W133927138 @default.
- W4200528093 cites W1531931873 @default.
- W4200528093 cites W1557800628 @default.
- W4200528093 cites W1595159159 @default.
- W4200528093 cites W1916786071 @default.
- W4200528093 cites W1966388004 @default.
- W4200528093 cites W1967069631 @default.
- W4200528093 cites W1982652137 @default.
- W4200528093 cites W1983306148 @default.
- W4200528093 cites W1988091883 @default.
- W4200528093 cites W1991710340 @default.
- W4200528093 cites W1993019513 @default.
- W4200528093 cites W1995100052 @default.
- W4200528093 cites W1998667631 @default.
- W4200528093 cites W1998885514 @default.
- W4200528093 cites W2003765237 @default.
- W4200528093 cites W2014925878 @default.
- W4200528093 cites W2016003664 @default.
- W4200528093 cites W2024282948 @default.
- W4200528093 cites W2025852341 @default.
- W4200528093 cites W2029624031 @default.
- W4200528093 cites W2030077105 @default.
- W4200528093 cites W2033414977 @default.
- W4200528093 cites W2034915480 @default.
- W4200528093 cites W2035832119 @default.
- W4200528093 cites W2037511628 @default.
- W4200528093 cites W2040807954 @default.
- W4200528093 cites W2041891835 @default.
- W4200528093 cites W2043408670 @default.
- W4200528093 cites W2045428453 @default.
- W4200528093 cites W2048483321 @default.
- W4200528093 cites W2054452209 @default.
- W4200528093 cites W2057472231 @default.
- W4200528093 cites W2062142739 @default.
- W4200528093 cites W2063796860 @default.
- W4200528093 cites W2067849750 @default.
- W4200528093 cites W2074674183 @default.
- W4200528093 cites W2074890618 @default.
- W4200528093 cites W2077002011 @default.
- W4200528093 cites W2086302085 @default.
- W4200528093 cites W2096518690 @default.
- W4200528093 cites W2119862467 @default.
- W4200528093 cites W2122825543 @default.
- W4200528093 cites W2124822779 @default.
- W4200528093 cites W2129862066 @default.
- W4200528093 cites W2131043603 @default.
- W4200528093 cites W2138244219 @default.
- W4200528093 cites W2143834662 @default.
- W4200528093 cites W2154197216 @default.
- W4200528093 cites W2168648059 @default.
- W4200528093 cites W2321259193 @default.
- W4200528093 cites W2511119176 @default.
- W4200528093 cites W2544737478 @default.
- W4200528093 cites W2550044583 @default.
- W4200528093 cites W2594647661 @default.
- W4200528093 cites W2751846886 @default.
- W4200528093 cites W2770188460 @default.
- W4200528093 cites W2784027534 @default.
- W4200528093 cites W2784257505 @default.
- W4200528093 cites W2790389815 @default.
- W4200528093 cites W2806110455 @default.
- W4200528093 cites W2897969757 @default.
- W4200528093 cites W2908367847 @default.
- W4200528093 cites W2912504921 @default.
- W4200528093 cites W2926551842 @default.
- W4200528093 cites W2946085841 @default.
- W4200528093 cites W2952056515 @default.
- W4200528093 cites W2969454052 @default.
- W4200528093 cites W2981898809 @default.
- W4200528093 cites W2986844658 @default.
- W4200528093 cites W2991415853 @default.
- W4200528093 cites W2991996856 @default.
- W4200528093 cites W2998203113 @default.
- W4200528093 cites W3021414821 @default.
- W4200528093 cites W3025544282 @default.
- W4200528093 cites W3049703060 @default.
- W4200528093 cites W3124413522 @default.
- W4200528093 cites W3150815575 @default.
- W4200528093 cites W4234698323 @default.
- W4200528093 doi "https://doi.org/10.1016/j.asoc.2021.108286" @default.
- W4200528093 hasPublicationYear "2022" @default.
- W4200528093 type Work @default.
- W4200528093 citedByCount "3" @default.
- W4200528093 countsByYear W42005280932022 @default.
- W4200528093 countsByYear W42005280932023 @default.
- W4200528093 crossrefType "journal-article" @default.
- W4200528093 hasAuthorship W4200528093A5008298191 @default.
- W4200528093 hasAuthorship W4200528093A5058101576 @default.
- W4200528093 hasConcept C105795698 @default.
- W4200528093 hasConcept C11413529 @default.