FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W1856180328> ?p ?o ?g. }

• W1856180328 abstract "In recent years, stroke has become an important issue to consider medically and socially since it poses high rate of human mortality and disability worldwidely. It typically results from impaired blood supply in the brain. Pathologically, it can be classified into two types: ischemic stroke and hemorrhagic stroke. While early treatment can effectively save lives, the treatment to each type are different and wrong treatment may deteriorate patients’ condition. Therefore, it is necessary to diagnose the type of stroke before any treatment is performed. Medfield Diagnostics proposed a solution for stroke diagnostics in pre-hospital scenarios where a medical instrument called Strokefinder can be used to diagnose stroke type. This instrument uses microwave antennas to transmit and receive response signals and acquire the data for each patient. After that, machine learning algorithms are used to process the data and perform classification. Earlier methods already show high classification accuracy for predicting the correct type of stroke. This thesis is a successive research based on earlier development from Medfield Diagnostics and aims to investigate whether new methods would further improve the performance of stroke classification. Specifically, a methodology named feature learning will be evaluated. One of the common feature learning algorithms is autoencoder, which is a reconstruction-based unsupervised learning algorithm with the purpose of dimensionality reduction. Since the data from stroke diagnostic instrument is massive and high-dimensional, applying autoencoder before a classifier will lower the dimension of acquired data and may possibly improve the classification performance. The thesis starts with basic theory of autoencoder and support vector machine (SVM) classifier, introduces the complete pipeline for classification which includes preprocessing, autoencoder, SVM and performance evaluation. In addition to normal autoencoder, the idea of class-specific autoencoder will be brought up and implemented. Essentially, the performance of three schemes are compared in detail, which covers SVM without autoencoder, SVM with normal autoencoder and SVM with class-specific autoencoder. The performance results contain classification Accuracy and AUC with various cross-validation methods by testing stroke datasets from lab simulation in Medfield Diagnostics and other external datasets such as CIFAR-10 and MNIST." @default.
• W1856180328 created "2016-06-24" @default.
• W1856180328 creator A5059326832 @default.
• W1856180328 date "2015-01-01" @default.
• W1856180328 modified "2023-09-27" @default.
• W1856180328 title "Performance evaluation of feature learning for stroke classification in a microwave-based medical diagnostic system" @default.
• W1856180328 cites W1498436455 @default.
• W1856180328 cites W1503398984 @default.
• W1856180328 cites W1554944419 @default.
• W1856180328 cites W1604591429 @default.
• W1856180328 cites W1680392829 @default.
• W1856180328 cites W2023279849 @default.
• W1856180328 cites W2066704854 @default.
• W1856180328 cites W2076063813 @default.
• W1856180328 cites W2098841537 @default.
• W1856180328 cites W2100495367 @default.
• W1856180328 cites W2102017903 @default.
• W1856180328 cites W2109943925 @default.
• W1856180328 cites W2110117066 @default.
• W1856180328 cites W2112796928 @default.
• W1856180328 cites W2138857742 @default.
• W1856180328 cites W2140190241 @default.
• W1856180328 cites W2150341604 @default.
• W1856180328 cites W2163922914 @default.
• W1856180328 cites W2186428165 @default.
• W1856180328 cites W2512536179 @default.
• W1856180328 cites W2768149277 @default.
• W1856180328 cites W3118608800 @default.
• W1856180328 cites W3120740533 @default.
• W1856180328 hasPublicationYear "2015" @default.
• W1856180328 type Work @default.
• W1856180328 sameAs 1856180328 @default.
• W1856180328 citedByCount "0" @default.
• W1856180328 crossrefType "dissertation" @default.
• W1856180328 hasAuthorship W1856180328A5059326832 @default.
• W1856180328 hasConcept C101738243 @default.
• W1856180328 hasConcept C108583219 @default.
• W1856180328 hasConcept C119857082 @default.
• W1856180328 hasConcept C127413603 @default.
• W1856180328 hasConcept C138885662 @default.
• W1856180328 hasConcept C153180895 @default.
• W1856180328 hasConcept C154945302 @default.
• W1856180328 hasConcept C2776401178 @default.
• W1856180328 hasConcept C2780645631 @default.
• W1856180328 hasConcept C41008148 @default.
• W1856180328 hasConcept C41895202 @default.
• W1856180328 hasConcept C70518039 @default.
• W1856180328 hasConcept C71924100 @default.
• W1856180328 hasConcept C78519656 @default.
• W1856180328 hasConcept C95623464 @default.
• W1856180328 hasConceptScore W1856180328C101738243 @default.
• W1856180328 hasConceptScore W1856180328C108583219 @default.
• W1856180328 hasConceptScore W1856180328C119857082 @default.
• W1856180328 hasConceptScore W1856180328C127413603 @default.
• W1856180328 hasConceptScore W1856180328C138885662 @default.
• W1856180328 hasConceptScore W1856180328C153180895 @default.
• W1856180328 hasConceptScore W1856180328C154945302 @default.
• W1856180328 hasConceptScore W1856180328C2776401178 @default.
• W1856180328 hasConceptScore W1856180328C2780645631 @default.
• W1856180328 hasConceptScore W1856180328C41008148 @default.
• W1856180328 hasConceptScore W1856180328C41895202 @default.
• W1856180328 hasConceptScore W1856180328C70518039 @default.
• W1856180328 hasConceptScore W1856180328C71924100 @default.
• W1856180328 hasConceptScore W1856180328C78519656 @default.
• W1856180328 hasConceptScore W1856180328C95623464 @default.
• W1856180328 hasLocation W18561803281 @default.
• W1856180328 hasOpenAccess W1856180328 @default.
• W1856180328 hasPrimaryLocation W18561803281 @default.
• W1856180328 hasRelatedWork W2775151852 @default.
• W1856180328 hasRelatedWork W2792628126 @default.
• W1856180328 hasRelatedWork W2801148351 @default.
• W1856180328 hasRelatedWork W2903099708 @default.
• W1856180328 hasRelatedWork W2911722481 @default.
• W1856180328 hasRelatedWork W2929547636 @default.
• W1856180328 hasRelatedWork W2980053795 @default.
• W1856180328 hasRelatedWork W3004897296 @default.
• W1856180328 hasRelatedWork W3047117862 @default.
• W1856180328 hasRelatedWork W3082190864 @default.
• W1856180328 hasRelatedWork W3115279029 @default.
• W1856180328 hasRelatedWork W3130398204 @default.
• W1856180328 hasRelatedWork W3157495772 @default.
• W1856180328 hasRelatedWork W3163537725 @default.
• W1856180328 hasRelatedWork W3187847994 @default.
• W1856180328 hasRelatedWork W3203333339 @default.
• W1856180328 hasRelatedWork W3206004033 @default.
• W1856180328 hasRelatedWork W3210804034 @default.
• W1856180328 hasRelatedWork W2184071663 @default.
• W1856180328 hasRelatedWork W2918156495 @default.
• W1856180328 isParatext "false" @default.
• W1856180328 isRetracted "false" @default.
• W1856180328 magId "1856180328" @default.
• W1856180328 workType "dissertation" @default.