Multidimensional Mahalanobis distance outperforms deep-learning baselines for sample-efficient rolling-window anomaly detection in clinical chemistry reaction curves
Clinica Chimica Acta
· Elsevier
Аннотация
Publication date: 15 February 2027 Source: Clinica Chimica Acta, Volume 595 Author(s): Terumichi Nakagawa, Shiori Tohma, Junpei Ueda, Saki Toyota, Shota Muramatsu, Emi Aoki, Akiko Sakai, Akemi Ohno, Tomoko Arai, Masatoshi Wakui, Hiromichi Matsushita
Читать у издателя →
Цитировать
Получайте новые статьи по теме «Медицинская биохимия»
Подписка, поиск по ключевым словам и избранное — в Telegram-боте Articlium.
Открыть в Telegram
Цитирование
✕
ГОСТ
APA
MLA
BibTeX
Multidimensional Mahalanobis distance outperforms deep-learning baselines for sample-efficient rolling-window anomaly detection in clinical chemistry reaction curves. // Clinica Chimica Acta. – URL: https://www.sciencedirect.com/science/article/pii/S0009898126021534?dgcid=rss_sd_all
Multidimensional Mahalanobis distance outperforms deep-learning baselines for sample-efficient rolling-window anomaly detection in clinical chemistry reaction curves. Clinica Chimica Acta. https://www.sciencedirect.com/science/article/pii/S0009898126021534?dgcid=rss_sd_all
“Multidimensional Mahalanobis distance outperforms deep-learning baselines for sample-efficient rolling-window anomaly detection in clinical chemistry reaction curves.” Clinica Chimica Acta.
@article{article99910,
title = {Multidimensional Mahalanobis distance outperforms deep-learning baselines for sample-efficient rolling-window anomaly detection in clinical chemistry reaction curves},
journal = {Clinica Chimica Acta},
url = {https://www.sciencedirect.com/science/article/pii/S0009898126021534?dgcid=rss_sd_all}
}