Zobrazeno 1 - 10
of 17
pro vyhledávání: '"Naoya YOSHIMURA"'
Autor:
Ryoma Otsuka, Naoya Yoshimura, Kei Tanigaki, Shiho Koyama, Yuichi Mizutani, Ken Yoda, Takuya Maekawa
Publikováno v:
Methods in Ecology and Evolution, Vol 15, Iss 4, Pp 716-731 (2024)
Abstract Machine learning‐based behaviour classification using acceleration data is a powerful tool in bio‐logging research. Deep learning architectures such as convolutional neural networks (CNN), long short‐term memory (LSTM) and self‐atten
Externí odkaz:
https://doaj.org/article/cb35496c9f3240b79c3757becf300e08
Publikováno v:
Nihon Kikai Gakkai ronbunshu, Vol 80, Iss 815, Pp SMM0193-SMM0193 (2014)
Fish eye failure that is unique fatigue fracture occurs in very long life region of high strength steel. The fatigue life of fish eye failure dominated ODA (Optically Dark Area) around the fracture origin. A granular looking area of ODA is visible cl
Externí odkaz:
https://doaj.org/article/dd76730ec9ef472ea195abe1201d033e
Predicting Performance Improvement of Human Activity Recognition Model by Additional Data Collection
Publikováno v:
Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies. 6:1-33
The development of a machine-learning-based human activity recognition (HAR) system using body-worn sensors is mainly composed of three phases: data collection, model training, and evaluation. During data collection, the HAR developer collects labele
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e363cad355ab3e6bfa87cb82c99f6e91
https://doi.org/10.1145/3550319
https://doi.org/10.1145/3550319
Publikováno v:
Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies. 6:1-39
This study presents a new neural network model for recognizing manual works using body-worn accelerometers in industrial settings, named Lightweight Ordered-work Segmentation Network (LOS-Net). In industrial domains, a human worker typically repetiti
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::65a8b7c7b2f35698735f7e901d05a087
https://doi.org/10.1145/3534572
https://doi.org/10.1145/3534572
Publikováno v:
2022 IEEE International Conference on Pervasive Computing and Communications (PerCom).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ddd91acaeb329f817368a010e3b77c2f
https://doi.org/10.1109/percom53586.2022.9762388
https://doi.org/10.1109/percom53586.2022.9762388
Publikováno v:
2022 17th ACM/IEEE International Conference on Human-Robot Interaction (HRI).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::7a3f5ebf2f8ea6a82bcf5b7407b78d39
https://doi.org/10.1109/hri53351.2022.9889410
https://doi.org/10.1109/hri53351.2022.9889410
Publikováno v:
Pervasive and Mobile Computing. 88:101735
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::5a53057275df5ff21c8495174b42db0c
https://doi.org/10.1016/j.pmcj.2022.101735
https://doi.org/10.1016/j.pmcj.2022.101735
Publikováno v:
IJCNN
Although deep learning-based activity recognition using wearable sensors has been actively studied to implement smart applications such as supporting elderly care, healthcare, and home automation, techniques for understanding the inside of activity r
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::aa6e22929efeefeefbbfcd08644a4b8d
https://doi.org/10.1109/ijcnn52387.2021.9533888
https://doi.org/10.1109/ijcnn52387.2021.9533888
Publikováno v:
ICMU
Owing to the growing demand for wearable context-aware applications, activity recognition technologies have attracted great attention. A neural network has been recently used as a recognition algorithm because of its discrimination and feature extrac
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e239595724f7e3803a0ef95bb79639bd
https://doi.org/10.23919/icmu48249.2019.9006643
https://doi.org/10.23919/icmu48249.2019.9006643
Publikováno v:
ICDCS
Inertial sensor data collected from wearable smart devices such as smartwatches are expected to be used in various smart applications such as video game controllers, hand drawing, hand writing, gestural input devices, human activity recognition, and
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::7e9221856634adaea8cebeb4d1979f75
https://doi.org/10.1109/icdcs.2019.00196
https://doi.org/10.1109/icdcs.2019.00196