Matches in SemOpenAlex for { <https://semopenalex.org/work/W3135524347> ?p ?o ?g. }
- W3135524347 endingPage "36619" @default.
- W3135524347 startingPage "36589" @default.
- W3135524347 abstract "In navigation, deep learning for inertial odometry (IO) has recently been investigated using data from a low-cost IMU only. The measurement of noise, bias, and some errors from which IO suffers is estimated with a deep neural network (DNN) to achieve more accurate pose estimation. While numerous studies on the subject highlighted the performances of their approach, the behavior of data-driven IO with DNN has not been clarified. Therefore, this paper presents a quantitative analysis of kinematics-mimicking DNN-based IO from various aspects. First, the new network architecture is designed to mimic the kinematics and ensure comprehensive analyses. Next, the hyper-parameters of neural networks that are highly correlated to IO are identified. Besides, their role in the performances is investigated. In the evaluation, the analyses were conducted with publicly-available IO datasets for vehicles and drones. The results are introduced to highlight the remaining problems in IO and are considered a guideline to promote further research." @default.
- W3135524347 created "2021-03-15" @default.
- W3135524347 creator A5046837505 @default.
- W3135524347 creator A5056015857 @default.
- W3135524347 creator A5056399333 @default.
- W3135524347 date "2021-01-01" @default.
- W3135524347 modified "2023-10-12" @default.
- W3135524347 title "Understanding the Behavior of Data-Driven Inertial Odometry With Kinematics-Mimicking Deep Neural Network" @default.
- W3135524347 cites W1564768010 @default.
- W3135524347 cites W1599888605 @default.
- W3135524347 cites W1896503986 @default.
- W3135524347 cites W1993523669 @default.
- W3135524347 cites W1993793087 @default.
- W3135524347 cites W2011224697 @default.
- W3135524347 cites W2016053056 @default.
- W3135524347 cites W2027444023 @default.
- W3135524347 cites W2048312361 @default.
- W3135524347 cites W2091782715 @default.
- W3135524347 cites W2115579991 @default.
- W3135524347 cites W2118223742 @default.
- W3135524347 cites W2131420149 @default.
- W3135524347 cites W2137303024 @default.
- W3135524347 cites W2140658564 @default.
- W3135524347 cites W2142558335 @default.
- W3135524347 cites W2149128480 @default.
- W3135524347 cites W2160626949 @default.
- W3135524347 cites W2184410429 @default.
- W3135524347 cites W2194775991 @default.
- W3135524347 cites W2240067561 @default.
- W3135524347 cites W2263270788 @default.
- W3135524347 cites W2331577291 @default.
- W3135524347 cites W2396274919 @default.
- W3135524347 cites W2745859992 @default.
- W3135524347 cites W2765512007 @default.
- W3135524347 cites W2776443693 @default.
- W3135524347 cites W2800254930 @default.
- W3135524347 cites W2805594094 @default.
- W3135524347 cites W2806294667 @default.
- W3135524347 cites W2883735935 @default.
- W3135524347 cites W2887149528 @default.
- W3135524347 cites W2895879514 @default.
- W3135524347 cites W2919115771 @default.
- W3135524347 cites W2922243907 @default.
- W3135524347 cites W2936887342 @default.
- W3135524347 cites W2945668765 @default.
- W3135524347 cites W2955453892 @default.
- W3135524347 cites W2962994355 @default.
- W3135524347 cites W2963887447 @default.
- W3135524347 cites W2967242391 @default.
- W3135524347 cites W2971141820 @default.
- W3135524347 cites W2978556704 @default.
- W3135524347 cites W2984573846 @default.
- W3135524347 cites W2994617216 @default.
- W3135524347 cites W2998370018 @default.
- W3135524347 cites W2998677710 @default.
- W3135524347 cites W3032120116 @default.
- W3135524347 cites W3101037136 @default.
- W3135524347 cites W3104978629 @default.
- W3135524347 cites W4234782453 @default.
- W3135524347 cites W4243425824 @default.
- W3135524347 cites W4246614213 @default.
- W3135524347 doi "https://doi.org/10.1109/access.2021.3062817" @default.
- W3135524347 hasPublicationYear "2021" @default.
- W3135524347 type Work @default.
- W3135524347 sameAs 3135524347 @default.
- W3135524347 citedByCount "2" @default.
- W3135524347 countsByYear W31355243472021 @default.
- W3135524347 crossrefType "journal-article" @default.
- W3135524347 hasAuthorship W3135524347A5046837505 @default.
- W3135524347 hasAuthorship W3135524347A5056015857 @default.
- W3135524347 hasAuthorship W3135524347A5056399333 @default.
- W3135524347 hasBestOaLocation W31355243471 @default.
- W3135524347 hasConcept C108583219 @default.
- W3135524347 hasConcept C115961682 @default.
- W3135524347 hasConcept C121332964 @default.
- W3135524347 hasConcept C154945302 @default.
- W3135524347 hasConcept C173386949 @default.
- W3135524347 hasConcept C19966478 @default.
- W3135524347 hasConcept C2984842247 @default.
- W3135524347 hasConcept C31972630 @default.
- W3135524347 hasConcept C39920418 @default.
- W3135524347 hasConcept C41008148 @default.
- W3135524347 hasConcept C49441653 @default.
- W3135524347 hasConcept C50644808 @default.
- W3135524347 hasConcept C62520636 @default.
- W3135524347 hasConcept C74650414 @default.
- W3135524347 hasConcept C79061980 @default.
- W3135524347 hasConcept C90509273 @default.
- W3135524347 hasConcept C99498987 @default.
- W3135524347 hasConceptScore W3135524347C108583219 @default.
- W3135524347 hasConceptScore W3135524347C115961682 @default.
- W3135524347 hasConceptScore W3135524347C121332964 @default.
- W3135524347 hasConceptScore W3135524347C154945302 @default.
- W3135524347 hasConceptScore W3135524347C173386949 @default.
- W3135524347 hasConceptScore W3135524347C19966478 @default.
- W3135524347 hasConceptScore W3135524347C2984842247 @default.
- W3135524347 hasConceptScore W3135524347C31972630 @default.
- W3135524347 hasConceptScore W3135524347C39920418 @default.