Zobrazeno 1 - 10
of 67
pro vyhledávání: '"Nianbin Wang"'
Publikováno v:
Frontiers in Neurorobotics, Vol 18 (2024)
IntroductionThe meta-learning methods have been widely used to solve the problem of few-shot learning. Generally, meta-learners are trained on a variety of tasks and then generalized to novel tasks.MethodsHowever, existing meta-learning methods do no
Externí odkaz:
https://doaj.org/article/4aeaf6688aa74af5805514d0ca7cf86b
Publikováno v:
IEEE Access, Vol 8, Pp 75303-75312 (2020)
Formal concept analysis (FCA) gets into good graces by increasing big data scientists due to its unique advantages. Concept similarity measurement is the key to the FCA-based application. Most of the previous methods are based on set theory and less
Externí odkaz:
https://doaj.org/article/fa875ad7115c422caacd2e2798cf44c0
Publikováno v:
IEEE Access, Vol 8, Pp 81320-81330 (2020)
Relation extraction (RE) aims to mine semantic relations between entity pairs from plain texts, which plays an important role in various natural language processing (NLP) tasks. However, the existing methods in distant supervision (DS) are sensitive
Externí odkaz:
https://doaj.org/article/e6bbfcfe0f6c47fd94442da6a2338dc7
Publikováno v:
IEEE Access, Vol 8, Pp 146300-146307 (2020)
In complex underwater environments, the single mode of a single sensor cannot meet the precision requirement of object identification, and multisource fusion is currently the mainstream research approach. Deep canonical correlation analysis is an eff
Externí odkaz:
https://doaj.org/article/f87f78e4860f4df78833ab6809b45c7e
Publikováno v:
Machines, Vol 10, Iss 11, p 998 (2022)
With the development of IoT technology, the digital twin has been applied in many fields. It is the key to realizing the integration of physical information space and an effective means for intelligent upgrading of products, providing a novel idea fo
Externí odkaz:
https://doaj.org/article/b8319e92d5ee4b3d9035ee33af0571ca
Publikováno v:
Tehnički Vjesnik, Vol 25, Iss 3, Pp 748-758 (2018)
To solve the inefficiency of the existing keyword search methods in large databases, this paper proposes TCU-based query, an offline query method based on topic cluster units. First, topic cluster units (TCUs) are constructed through vertical groupin
Externí odkaz:
https://doaj.org/article/c8276160e1e64fcda4f2e09ee7407a52
Publikováno v:
IEEE Access, Vol 6, Pp 44698-44706 (2018)
The goal of unsupervised domain adaptation aims to utilize labeled data from source domain to annotate the target-domain data, which has none of the labels. Existing work uses Siamese network-based models to minimize the domain discrepancy to learn a
Externí odkaz:
https://doaj.org/article/f798ae817032450ca25bb33842058de7
Publikováno v:
Aquaculture and Fisheries, Vol 2, Iss 1, Pp 10-17 (2017)
Aquatic animals are susceptible to sudden changes of their living environment but they adopt strategies to cope with adverse environmental challenges. Contamination by suspended solids, often associated with a dramatic change in the concentrations of
Externí odkaz:
https://doaj.org/article/2d3d18a64012470f951d0ec9ea3a3596
Publikováno v:
Information, Vol 11, Iss 6, p 288 (2020)
High-dimensional time series classification is a serious problem. A similarity measure based on distance is one of the methods for time series classification. This paper proposes a metric learning-based univariate time series classification method (M
Externí odkaz:
https://doaj.org/article/dadf540e13ff442abb4e21348547d1cf
Publikováno v:
Multimedia Tools and Applications. 82:7267-7292
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::8e3d15c6d16f82420a72c288bb605782
https://doi.org/10.1007/s11042-022-13640-2
https://doi.org/10.1007/s11042-022-13640-2