Zobrazeno 1 - 10
of 35
pro vyhledávání: '"Kazuma Kondo"'
Publikováno v:
IEEE Access, Vol 10, Pp 20547-20558 (2022)
The feature extraction of human activity recognition (HAR) based on sensor data has been studied as a hand-crafted method. The significant feature extraction ability is a key factor in improving the accuracy of HAR. Recently, deep learning methods ha
Externí odkaz:
https://doaj.org/article/f66c9f2bed5b49bdb146d9fcc247d783
Autor:
Katsunori Ryoke, Kana Ishizuka, Yuzo Yasui, Kazuma Kondo, Noriko Suzuki-Kemuriyama, Tatsuya Maekawa, Katsuhiro Miyajima
Publikováno v:
Fundamental Toxicological Sciences; 2024, Vol. 11 Issue 4, p159-168, 10p
Autor:
Kazuma Kondo1,2 kazuma.kondo@jt.com, Naohito Yamada1, Yusuke Suzuki1, Tatsuji Hashimoto1, Kaoru Toyoda1, Tadakazu Takahashi1, Akio Kobayashi1, Shoichiro Sugai1, Kouichi Yoshinari2
Publikováno v:
Journal of Toxicological Sciences. 2020, Vol. 45 Issue 5, p245-260. 16p.
Autor:
Kazuma Kondo, Tatsuhito Hasegawa
Publikováno v:
IEEE Sensors Letters. 6:1-4
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::3fe885f4a06f0863fea8ecbe569f0f41
https://doi.org/10.1109/lsens.2022.3206472
https://doi.org/10.1109/lsens.2022.3206472
Autor:
Kazuma Kondo, Tatsuhito Hasegawa
Publikováno v:
Sensors, Vol 21, Iss 22, p 7743 (2021)
In sensor-based human activity recognition, many methods based on convolutional neural networks (CNNs) have been proposed. In the typical CNN-based activity recognition model, each class is treated independently of others. However, actual activity cl
Externí odkaz:
https://doaj.org/article/046a63cd506442e79e4b9e3760ba9eab
Autor:
Hideaki Yokoyama, Taku Masuyama, Yuki Tanaka, Iori Tsubakihara, Kazuma Kondo, Kouichi Yoshinari
Publikováno v:
The Journal of Toxicological Sciences. 47:19-30
Acyl-CoAdiacylglycerol acyltransferase 1 (DGAT1) is a key enzyme in the fat absorption step in enterocytes. We previously reported that the pharmacological inhibition of DGAT1 increased plasma alanine aminotransferase (ALT) and aspartate aminotransfe
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d39c05abaf322d41931d4f6da9dc07a5
https://doi.org/10.2131/jts.47.19
https://doi.org/10.2131/jts.47.19
Autor:
YUSUKE SUZUKI, KAZUMA KONDO, KAORU TOYODA, YUKI TANAKA, AKIO KOBAYASHI, DAIGO YOKOYAMA, HIROYUKI SAKAKIBARA
Publikováno v:
In Vivo
Background/Aim: The habitual consumption of excessive fructose is associated with the onset and progression of lifestyle-related diseases, such as nonalcoholic fatty liver disease (NAFLD). In this study, we investigated the physiological changes obse
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0557522a0ed0191fc4e663ac9fc38976
https://pubmed.ncbi.nlm.nih.gov/36593010
https://pubmed.ncbi.nlm.nih.gov/36593010
Autor:
YUSUKE SUZUKI, DAIGO YOKOYAMA, CHIZURU MATSUURA, KAZUMA KONDO, TAISHI SHIMAZAKI, KATSUNORI RYOKE, AKIO KOBAYASHI, HIROYUKI SAKAKIBARA
Publikováno v:
In Vivo; Sep/Oct2023, Vol. 37 Issue 5, p1967-1974, 8p
Autor:
Tatsuhito Hasegawa, Kazuma Kondo
Sensor-based human activity recognition (HAR) is a paramount technology in the Internet of Things services. HAR using representation learning, which automatically learns a feature representation from raw data, is the mainstream method because it is d
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5ceef76b2d8a8fccd2e91cc1d00c482a
http://arxiv.org/abs/2203.04153
http://arxiv.org/abs/2203.04153
Autor:
YUSUKE SUZUKI, KAZUMA KONDO, KAORU TOYODA, YUKI TANAKA, AKIO KOBAYASHI, DAIGO YOKOYAMA, HIROYUKI SAKAKIBARA
Publikováno v:
In Vivo; Jan/Feb2023, Vol. 37 Issue 1, p173-181, 9p