FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2945229969> ?p ?o ?g. }

• W2945229969 endingPage "38" @default.
• W2945229969 startingPage "27" @default.
• W2945229969 abstract "Purpose: To evaluate and enhance the generalization performance of machine learning physical activity intensity prediction models developed with raw acceleration data on populations monitored by different activity monitors. Method: Five datasets from four studies, each containing only hipor wrist-based raw acceleration data (two hipand three wrist-based) were extracted. The five datasets were then used to develop and validate artificial neural networks (ANN) in three setups to classify activity intensity categories (sedentary behavior, light, and moderate-to-vigorous). To examine generalizability, the ANN models were developed using within dataset (leave-one-subject-out) cross validation, and then cross tested to other datasets with different accelerometers. To enhance the models' generalizability, a combination of four of the five datasets was used for training and the fifth dataset for validation. Finally, all the five datasets were merged to develop a single model that is generalizable across the datasets (50% of the subjects from each dataset for training, the remaining for validation). Results: The datasets showed high performance in within dataset cross validation (accuracy 71.9-95.4%, Kappa K = 0.63-0.94). The performance of the within dataset validated models decreased when applied to datasets with different accelerometers (41.2-59.9%, K = 0.21-0.48). The trained models on merged datasets consisting hip and wrist data predicted the left-out dataset with acceptable performance (65.9-83.7%, K = 0.61-0.79). The model trained with all five datasets performed with acceptable performance across the datasets (80.4-90.7%, K = 0.68-0.89). Conclusions: Integrating heterogeneous datasets in training sets seems a viable approach for enhancing the generalization performance of the models. Instead, within dataset validation is not sufficient to understand the models' performance on other populations with different accelerometers." @default.
• W2945229969 created "2019-05-29" @default.
• W2945229969 creator A5010979597 @default.
• W2945229969 creator A5047366834 @default.
• W2945229969 creator A5053956008 @default.
• W2945229969 creator A5057877217 @default.
• W2945229969 creator A5061434942 @default.
• W2945229969 creator A5065061546 @default.
• W2945229969 date "2020-01-01" @default.
• W2945229969 modified "2023-10-18" @default.
• W2945229969 title "Evaluating and Enhancing the Generalization Performance of Machine Learning Models for Physical Activity Intensity Prediction From Raw Acceleration Data" @default.
• W2945229969 cites W1976451292 @default.
• W2945229969 cites W1998879590 @default.
• W2945229969 cites W2002353621 @default.
• W2945229969 cites W2019076211 @default.
• W2945229969 cites W2019098172 @default.
• W2945229969 cites W2026297770 @default.
• W2945229969 cites W2030401894 @default.
• W2945229969 cites W2035855116 @default.
• W2945229969 cites W2037789405 @default.
• W2945229969 cites W2039665130 @default.
• W2945229969 cites W2048606477 @default.
• W2945229969 cites W2050998072 @default.
• W2945229969 cites W2060699725 @default.
• W2945229969 cites W2074276081 @default.
• W2945229969 cites W2084779848 @default.
• W2945229969 cites W2096653978 @default.
• W2945229969 cites W2098450425 @default.
• W2945229969 cites W2123504417 @default.
• W2945229969 cites W2125212922 @default.
• W2945229969 cites W2146199357 @default.
• W2945229969 cites W2152195551 @default.
• W2945229969 cites W2164365672 @default.
• W2945229969 cites W2164777277 @default.
• W2945229969 cites W2200539030 @default.
• W2945229969 cites W2279300874 @default.
• W2945229969 cites W2295454405 @default.
• W2945229969 cites W2314289569 @default.
• W2945229969 cites W2315380544 @default.
• W2945229969 cites W2317306538 @default.
• W2945229969 cites W2325534066 @default.
• W2945229969 cites W2327453846 @default.
• W2945229969 cites W2329483624 @default.
• W2945229969 cites W2400273852 @default.
• W2945229969 cites W2465778425 @default.
• W2945229969 cites W2548437830 @default.
• W2945229969 cites W2618096841 @default.
• W2945229969 cites W2625557646 @default.
• W2945229969 cites W2664062929 @default.
• W2945229969 cites W2760233617 @default.
• W2945229969 cites W2765422955 @default.
• W2945229969 cites W2778426046 @default.
• W2945229969 cites W2778618555 @default.
• W2945229969 cites W2785176356 @default.
• W2945229969 cites W2903150444 @default.
• W2945229969 doi "https://doi.org/10.1109/jbhi.2019.2917565" @default.
• W2945229969 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/31107668" @default.
• W2945229969 hasPublicationYear "2020" @default.
• W2945229969 type Work @default.
• W2945229969 sameAs 2945229969 @default.
• W2945229969 citedByCount "11" @default.
• W2945229969 countsByYear W29452299692020 @default.
• W2945229969 countsByYear W29452299692021 @default.
• W2945229969 countsByYear W29452299692022 @default.
• W2945229969 countsByYear W29452299692023 @default.
• W2945229969 crossrefType "journal-article" @default.
• W2945229969 hasAuthorship W2945229969A5010979597 @default.
• W2945229969 hasAuthorship W2945229969A5047366834 @default.
• W2945229969 hasAuthorship W2945229969A5053956008 @default.
• W2945229969 hasAuthorship W2945229969A5057877217 @default.
• W2945229969 hasAuthorship W2945229969A5061434942 @default.
• W2945229969 hasAuthorship W2945229969A5065061546 @default.
• W2945229969 hasBestOaLocation W29452299691 @default.
• W2945229969 hasConcept C105795698 @default.
• W2945229969 hasConcept C111919701 @default.
• W2945229969 hasConcept C119857082 @default.
• W2945229969 hasConcept C12267149 @default.
• W2945229969 hasConcept C124101348 @default.
• W2945229969 hasConcept C132964779 @default.
• W2945229969 hasConcept C134306372 @default.
• W2945229969 hasConcept C153180895 @default.
• W2945229969 hasConcept C154945302 @default.
• W2945229969 hasConcept C173633133 @default.
• W2945229969 hasConcept C177148314 @default.
• W2945229969 hasConcept C199360897 @default.
• W2945229969 hasConcept C27158222 @default.
• W2945229969 hasConcept C27181475 @default.
• W2945229969 hasConcept C33923547 @default.
• W2945229969 hasConcept C41008148 @default.
• W2945229969 hasConcept C45804977 @default.
• W2945229969 hasConcept C50644808 @default.
• W2945229969 hasConcept C89805583 @default.
• W2945229969 hasConceptScore W2945229969C105795698 @default.
• W2945229969 hasConceptScore W2945229969C111919701 @default.
• W2945229969 hasConceptScore W2945229969C119857082 @default.
• W2945229969 hasConceptScore W2945229969C12267149 @default.
• W2945229969 hasConceptScore W2945229969C124101348 @default.
• W2945229969 hasConceptScore W2945229969C132964779 @default.

• next