FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2803727098> ?p ?o ?g. }

• W2803727098 endingPage "460" @default.
• W2803727098 startingPage "446" @default.
• W2803727098 abstract "Objective assessment of multimedia quality using machine learning (ML) has been gaining popularity especially in the context of both traditional (e.g., terrestrial and satellite broadcast) and advance (such as over-the-top media services, IPTV) broadcast services. Being data-driven, these methods obviously rely on training to find the optimal model parameters. Therefore, to statistically compare and validate such ML-based quality predictors, the current approach randomly splits the given data into training and test sets and obtains a performance measure (for instance mean squared error, correlation coefficient etc.). The process is repeated a large number of times and parametric tests (e.g., ${t}$ test) are then employed to statistically compare mean (or median) prediction accuracies. However, the current approach suffers from a few limitations (related to the qualitative aspects of training and testing data, the use of improper sample size for statistical testing, possibly dependent sample observations, and a lack of focus on quantifying the learning ability of the ML-based objective quality predictor) which have not been addressed in literature. Therefore, the main goal of this paper is to shed light on the said limitations both from practical and theoretical perspectives wherever applicable, and in the process propose an alternate approach to overcome some of them. As a major advantage, the proposed guidelines not only help in a theoretically more grounded statistical comparison but also provide useful insights into how well the ML-based objective quality predictors exploit data structure for learning. We demonstrate the added value of the proposed set of guidelines on standard datasets by comparing the performance of few existing ML-based quality estimators. A software implementation of the presented guidelines is also made publicly available to enable researchers and developers to test and compare different models in a repeatable manner." @default.
• W2803727098 created "2018-06-01" @default.
• W2803727098 creator A5055646370 @default.
• W2803727098 date "2018-06-01" @default.
• W2803727098 modified "2023-09-27" @default.
• W2803727098 title "Toward Better Statistical Validation of Machine Learning-Based Multimedia Quality Estimators" @default.
• W2803727098 cites W1507985183 @default.
• W2803727098 cites W1880384040 @default.
• W2803727098 cites W1966528181 @default.
• W2803727098 cites W1968495153 @default.
• W2803727098 cites W1972859666 @default.
• W2803727098 cites W1977246677 @default.
• W2803727098 cites W1982471090 @default.
• W2803727098 cites W1984486655 @default.
• W2803727098 cites W1990534247 @default.
• W2803727098 cites W2022295273 @default.
• W2803727098 cites W2023140507 @default.
• W2803727098 cites W2035126508 @default.
• W2803727098 cites W2038911825 @default.
• W2803727098 cites W2043067815 @default.
• W2803727098 cites W2049222570 @default.
• W2803727098 cites W2059823394 @default.
• W2803727098 cites W2065221444 @default.
• W2803727098 cites W2091528887 @default.
• W2803727098 cites W2102817897 @default.
• W2803727098 cites W2107026277 @default.
• W2803727098 cites W2137139046 @default.
• W2803727098 cites W2139498473 @default.
• W2803727098 cites W2154516913 @default.
• W2803727098 cites W2155982020 @default.
• W2803727098 cites W2157825442 @default.
• W2803727098 cites W2158698691 @default.
• W2803727098 cites W2159976914 @default.
• W2803727098 cites W2205039763 @default.
• W2803727098 cites W2293006825 @default.
• W2803727098 cites W2303076655 @default.
• W2803727098 cites W2343109543 @default.
• W2803727098 cites W2472413205 @default.
• W2803727098 cites W2560703252 @default.
• W2803727098 cites W2604764451 @default.
• W2803727098 cites W2949121461 @default.
• W2803727098 cites W4235051201 @default.
• W2803727098 cites W4298872162 @default.
• W2803727098 doi "https://doi.org/10.1109/tbc.2018.2832441" @default.
• W2803727098 hasPublicationYear "2018" @default.
• W2803727098 type Work @default.
• W2803727098 sameAs 2803727098 @default.
• W2803727098 citedByCount "7" @default.
• W2803727098 countsByYear W28037270982018 @default.
• W2803727098 countsByYear W28037270982019 @default.
• W2803727098 countsByYear W28037270982021 @default.
• W2803727098 crossrefType "journal-article" @default.
• W2803727098 hasAuthorship W2803727098A5055646370 @default.
• W2803727098 hasConcept C105795698 @default.
• W2803727098 hasConcept C111472728 @default.
• W2803727098 hasConcept C119857082 @default.
• W2803727098 hasConcept C138885662 @default.
• W2803727098 hasConcept C154945302 @default.
• W2803727098 hasConcept C185429906 @default.
• W2803727098 hasConcept C2779530757 @default.
• W2803727098 hasConcept C2982736386 @default.
• W2803727098 hasConcept C2986587452 @default.
• W2803727098 hasConcept C33923547 @default.
• W2803727098 hasConcept C41008148 @default.
• W2803727098 hasConcept C49774154 @default.
• W2803727098 hasConceptScore W2803727098C105795698 @default.
• W2803727098 hasConceptScore W2803727098C111472728 @default.
• W2803727098 hasConceptScore W2803727098C119857082 @default.
• W2803727098 hasConceptScore W2803727098C138885662 @default.
• W2803727098 hasConceptScore W2803727098C154945302 @default.
• W2803727098 hasConceptScore W2803727098C185429906 @default.
• W2803727098 hasConceptScore W2803727098C2779530757 @default.
• W2803727098 hasConceptScore W2803727098C2982736386 @default.
• W2803727098 hasConceptScore W2803727098C2986587452 @default.
• W2803727098 hasConceptScore W2803727098C33923547 @default.
• W2803727098 hasConceptScore W2803727098C41008148 @default.
• W2803727098 hasConceptScore W2803727098C49774154 @default.
• W2803727098 hasIssue "2" @default.
• W2803727098 hasLocation W28037270981 @default.
• W2803727098 hasOpenAccess W2803727098 @default.
• W2803727098 hasPrimaryLocation W28037270981 @default.
• W2803727098 hasRelatedWork W2030250808 @default.
• W2803727098 hasRelatedWork W2143244606 @default.
• W2803727098 hasRelatedWork W2355862304 @default.
• W2803727098 hasRelatedWork W2356108042 @default.
• W2803727098 hasRelatedWork W2376796979 @default.
• W2803727098 hasRelatedWork W2379418341 @default.
• W2803727098 hasRelatedWork W2961085424 @default.
• W2803727098 hasRelatedWork W4287166790 @default.
• W2803727098 hasRelatedWork W4306674287 @default.
• W2803727098 hasRelatedWork W4224009465 @default.
• W2803727098 hasVolume "64" @default.
• W2803727098 isParatext "false" @default.
• W2803727098 isRetracted "false" @default.
• W2803727098 magId "2803727098" @default.
• W2803727098 workType "article" @default.