Results 61 to 70 of about 3,433,600 (309)
Time Series Classification with Shapelet and Canonical Features
Applied Sciences, 2022 Shapelet-based time series classification methods are widely adopted models for time series classification tasks. However, the high computational cost greatly limits the practicability of the Shapelet-based methods. What is more, traditional Shapelet can
Hai-Yang Liu +3 more
doaj +1 more source
Physica D: Nonlinear Phenomena, 2000 28 pages, 23 figures, software at http://www.mpipks-dresden.mpg.de ...
Schreiber, Thomas, Schmitz, Andreas
openaire +3 more sources
The UCR time series archive [PDF]
IEEE/CAA Journal of Automatica Sinica, 2019 The UCR Time Series Archive - introduced in 2002, has become an important resource in the time series data mining community, with at least one thousand published papers making use of at least one data set from the archive. The original incarnation of the archive had sixteen data sets but since that time, it has gone through periodic expansions.
Dau, Hoang Anh +7 more
openaire +3 more sources
Pediatric Blood &Cancer, EarlyView.ABSTRACT Hemophilic arthropathy remains the leading morbidity in hemophilia despite modern prophylaxis, and early joint damage may be missed by routine exams. This study explored T2* MRI as a noninvasive biomarker of hemosiderin deposition in pediatric hemophilia.
Jessica Garcia +6 more
wiley +1 more source
A Green AI Methodology Based on Persistent Homology for Compressing BERT
Applied SciencesLarge Language Models (LLMs) like BERT have gained significant prominence due to their remarkable performance in various natural language processing tasks. However, they come with substantial computational and memory costs.
Luis Balderas +2 more
doaj +1 more source
Eddies: Fluid Dynamical Niches or Transporters?–A Case Study in the Western Baltic Sea
Frontiers in Marine Science, 2019 Fluid flows in the ocean have a strong impact on the growth and distribution of planktonic communities. In this case study, we applied a Lagrangian eddy detection and tracking tool and a transfer operator approach to data from a coupled hydrodynamical ...
Rahel Vortmeyer-Kley +5 more
doaj +1 more source
A combined robust fuzzy time series method for prediction of time series [PDF]
Neurocomputing, 2017 Outlier(s) have an adverse impact on the performance of fuzzy time series models.We proposed a combined robust fuzzy time series model (C-R-FTSM).C-R-FTSM uses fuzzy inputs composed of membership values as well as the crisp data.Training process of C-R-FTSM is performed by PSO in a single optimization process.Huber's loss function based on M estimator ...
Ozge Cagcag Yolcu, Hak-Keung Lam
openaire +5 more sources
Pediatric Blood &Cancer, EarlyView.ABSTRACT Purpose Despite 5‐year survival rates of over 90% among children and adolescents/young adults (CAYAs) with classic Hodgkin lymphoma (cHL), 15%–20% relapse after frontline therapy. Prior analysis of frontline Children's Oncology Group (COG) clinical trials demonstrated that, despite similar rates of relapse, non‐Hispanic Black (NHB) and ...
Mallorie B. Heneghan +14 more
wiley +1 more source
Optimizing Convolutional Neural Network Architectures
MathematicsConvolutional neural networks (CNNs) are commonly employed for demanding applications, such as speech recognition, natural language processing, and computer vision.
Luis Balderas +2 more
doaj +1 more source
Pediatric Blood &Cancer, EarlyView.ABSTRACT Introduction Anthracycline‐related cardiac remodeling precedes heart failure in childhood cancer survivors. The objectives of this study were to determine the relationships between patient‐specific factors, moderate‐to‐vigorous physical activity (MVPA), and cardiac remodeling.
Hari K. Narayan +15 more
wiley +1 more source