FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4214726431> ?p ?o ?g. }

• W4214726431 endingPage "1373" @default.
• W4214726431 startingPage "1373" @default.
• W4214726431 abstract "Human activity recognition (HAR) using wearable sensors is an increasingly active research topic in machine learning, aided in part by the ready availability of detailed motion capture data from smartphones, fitness trackers, and smartwatches. The goal of HAR is to use such devices to assist users in their daily lives in application areas such as healthcare, physical therapy, and fitness. One of the main challenges for HAR, particularly when using supervised learning methods, is obtaining balanced data for algorithm optimisation and testing. As people perform some activities more than others (e.g., walk more than run), HAR datasets are typically imbalanced. The lack of dataset representation from minority classes hinders the ability of HAR classifiers to sufficiently capture new instances of those activities. We introduce three novel hybrid sampling strategies to generate more diverse synthetic samples to overcome the class imbalance problem. The first strategy, which we call the distance-based method (DBM), combines Synthetic Minority Oversampling Techniques (SMOTE) with Random_SMOTE, both of which are built around the k-nearest neighbors (KNN). The second technique, referred to as the noise detection-based method (NDBM), combines SMOTE Tomek links (SMOTE_Tomeklinks) and the modified synthetic minority oversampling technique (MSMOTE). The third approach, which we call the cluster-based method (CBM), combines Cluster-Based Synthetic Oversampling (CBSO) and Proximity Weighted Synthetic Oversampling Technique (ProWSyn). We compare the performance of the proposed hybrid methods to the individual constituent methods and baseline using accelerometer data from three commonly used benchmark datasets. We show that DBM, NDBM, and CBM reduce the impact of class imbalance and enhance F1 scores by a range of 9–20 percentage point compared to their constituent sampling methods. CBM performs significantly better than the others under a Friedman test, however, DBM has lower computational requirements." @default.
• W4214726431 created "2022-03-02" @default.
• W4214726431 creator A5041863006 @default.
• W4214726431 creator A5041915757 @default.
• W4214726431 creator A5089445707 @default.
• W4214726431 date "2022-02-11" @default.
• W4214726431 modified "2023-09-30" @default.
• W4214726431 title "Comparing Sampling Strategies for Tackling Imbalanced Data in Human Activity Recognition" @default.
• W4214726431 cites W1527911497 @default.
• W4214726431 cites W175634338 @default.
• W4214726431 cites W1993220166 @default.
• W4214726431 cites W2023302299 @default.
• W4214726431 cites W2034841618 @default.
• W4214726431 cites W2054780155 @default.
• W4214726431 cites W2073401630 @default.
• W4214726431 cites W2107138773 @default.
• W4214726431 cites W2118978333 @default.
• W4214726431 cites W2120336810 @default.
• W4214726431 cites W2132603770 @default.
• W4214726431 cites W2134524950 @default.
• W4214726431 cites W2136744557 @default.
• W4214726431 cites W2148143831 @default.
• W4214726431 cites W2166712377 @default.
• W4214726431 cites W2167460663 @default.
• W4214726431 cites W2170505850 @default.
• W4214726431 cites W2270470215 @default.
• W4214726431 cites W2304267454 @default.
• W4214726431 cites W2342667915 @default.
• W4214726431 cites W2544836728 @default.
• W4214726431 cites W2562319768 @default.
• W4214726431 cites W2594116048 @default.
• W4214726431 cites W2795342689 @default.
• W4214726431 cites W2803294438 @default.
• W4214726431 cites W2890264806 @default.
• W4214726431 cites W2963563124 @default.
• W4214726431 cites W2969674096 @default.
• W4214726431 cites W2971644666 @default.
• W4214726431 cites W2972393330 @default.
• W4214726431 cites W3015351929 @default.
• W4214726431 cites W3083323811 @default.
• W4214726431 cites W3084255915 @default.
• W4214726431 cites W3106983564 @default.
• W4214726431 cites W3134064484 @default.
• W4214726431 doi "https://doi.org/10.3390/s22041373" @default.
• W4214726431 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/35214275" @default.
• W4214726431 hasPublicationYear "2022" @default.
• W4214726431 type Work @default.
• W4214726431 citedByCount "6" @default.
• W4214726431 countsByYear W42147264312022 @default.
• W4214726431 countsByYear W42147264312023 @default.
• W4214726431 crossrefType "journal-article" @default.
• W4214726431 hasAuthorship W4214726431A5041863006 @default.
• W4214726431 hasAuthorship W4214726431A5041915757 @default.
• W4214726431 hasAuthorship W4214726431A5089445707 @default.
• W4214726431 hasBestOaLocation W42147264311 @default.
• W4214726431 hasConcept C119857082 @default.
• W4214726431 hasConcept C121687571 @default.
• W4214726431 hasConcept C124101348 @default.
• W4214726431 hasConcept C13280743 @default.
• W4214726431 hasConcept C149635348 @default.
• W4214726431 hasConcept C150594956 @default.
• W4214726431 hasConcept C154945302 @default.
• W4214726431 hasConcept C169258074 @default.
• W4214726431 hasConcept C185798385 @default.
• W4214726431 hasConcept C197323446 @default.
• W4214726431 hasConcept C205649164 @default.
• W4214726431 hasConcept C2776257435 @default.
• W4214726431 hasConcept C31258907 @default.
• W4214726431 hasConcept C41008148 @default.
• W4214726431 hasConceptScore W4214726431C119857082 @default.
• W4214726431 hasConceptScore W4214726431C121687571 @default.
• W4214726431 hasConceptScore W4214726431C124101348 @default.
• W4214726431 hasConceptScore W4214726431C13280743 @default.
• W4214726431 hasConceptScore W4214726431C149635348 @default.
• W4214726431 hasConceptScore W4214726431C150594956 @default.
• W4214726431 hasConceptScore W4214726431C154945302 @default.
• W4214726431 hasConceptScore W4214726431C169258074 @default.
• W4214726431 hasConceptScore W4214726431C185798385 @default.
• W4214726431 hasConceptScore W4214726431C197323446 @default.
• W4214726431 hasConceptScore W4214726431C205649164 @default.
• W4214726431 hasConceptScore W4214726431C2776257435 @default.
• W4214726431 hasConceptScore W4214726431C31258907 @default.
• W4214726431 hasConceptScore W4214726431C41008148 @default.
• W4214726431 hasIssue "4" @default.
• W4214726431 hasLocation W42147264311 @default.
• W4214726431 hasLocation W42147264312 @default.
• W4214726431 hasLocation W42147264313 @default.
• W4214726431 hasLocation W42147264314 @default.
• W4214726431 hasLocation W42147264315 @default.
• W4214726431 hasOpenAccess W4214726431 @default.
• W4214726431 hasPrimaryLocation W42147264311 @default.
• W4214726431 hasRelatedWork W2145343602 @default.
• W4214726431 hasRelatedWork W2811014843 @default.
• W4214726431 hasRelatedWork W2911455822 @default.
• W4214726431 hasRelatedWork W3176807344 @default.
• W4214726431 hasRelatedWork W3209425741 @default.
• W4214726431 hasRelatedWork W4206325870 @default.
• W4214726431 hasRelatedWork W4296783273 @default.

• next