Zobrazeno 1 - 10
of 59
pro vyhledávání: '"Yongfeng Dong"'
Publikováno v:
Applied Sciences, Vol 14, Iss 7, p 2759 (2024)
Due to the exceptional learning capabilities of deep neural networks (DNNs), they continue to struggle to handle label noise. To address this challenge, the pseudo-label approach has emerged as a preferred solution. Recent works have achieved signifi
Externí odkaz:
https://doaj.org/article/47a18e4ea42f418788ad0536c1cd5389
Publikováno v:
Biomimetics, Vol 9, Iss 2, p 92 (2024)
Inspired by the biological nervous system, deep neural networks (DNNs) are able to achieve remarkable performance in various tasks. However, they struggle to handle label noise, which can poison the memorization effects of DNNs. Co-teaching-based met
Externí odkaz:
https://doaj.org/article/8868402934e9452daa44fd99da2eda32
Deep learning methods may not outperform other machine learning methods on analyzing genomic studies
Publikováno v:
Frontiers in Genetics, Vol 13 (2022)
Deep Learning (DL) has been broadly applied to solve big data problems in biomedical fields, which is most successful in image processing. Recently, many DL methods have been applied to analyze genomic studies. However, genomic data usually has too s
Externí odkaz:
https://doaj.org/article/674708e961e34e039fbb59d310391934
Publikováno v:
IEEE Access, Vol 8, Pp 37014-37020 (2020)
Nowadays, capsule network model is widely used in image processing, whose feature engineering is not suitable for sentiment analysis based on texts obviously. In this paper, we propose a capsule network model with BiLSTM named caps-BiLSTM for sentime
Externí odkaz:
https://doaj.org/article/901c6798c4f0498d8274154ca35b3f42
Publikováno v:
IEEE Access, Vol 8, Pp 88259-88272 (2020)
Foreground-background separation of surveillance video, that models static background and extracts moving foreground simultaneously, attracts increasing attentions in building a smart city. Conventional techniques towards this always consider the bac
Externí odkaz:
https://doaj.org/article/37814cf9d2bb4eeaa924bc785a37757f
Publikováno v:
Journal of Electrical and Computer Engineering, Vol 2016 (2016)
HS-RAID (Hybrid Semi-RAID), a power-aware RAID, saves energy by grouping disks in the array. All of the write operations in HS-RAID are small write which degrade the storage system’s performance severely. In this paper, we propose a redundancy algo
Externí odkaz:
https://doaj.org/article/dc811489c09c45ad954960fa006ba87f
Publikováno v:
Journal of Intelligent & Fuzzy Systems. 43:7983-7994
Many real-world knowledge graphs are complex and keep evolving over time. Inferring missing facts in temporal knowledge graphs is a fundamental and challenging task. Previous studies focus on link prediction in static knowledge graphs which hardly ex
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::967bc656e3aa171c138a60756b7616d4
https://doi.org/10.3233/jifs-210943
https://doi.org/10.3233/jifs-210943
Publikováno v:
World Wide Web. 26:441-459
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::198737f249792d81ffbc7b8a5ba9e07f
https://doi.org/10.1007/s11280-022-01007-4
https://doi.org/10.1007/s11280-022-01007-4
Publikováno v:
Neurocomputing. 472:326-337
Imbalanced data can always be observed in our daily life and various practical tasks. A lot of well-constructed machine learning methodologies may produce ineffective performance, when conducted on this kind of data. This originates from the produced
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::1ae2f6ceeac08e607a676329598e777c
https://doi.org/10.1016/j.neucom.2021.04.135
https://doi.org/10.1016/j.neucom.2021.04.135
Publikováno v:
IEEE Transactions on Geoscience and Remote Sensing. 60:1-11
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::bad3da6b96ffa40f633c09db945040b9
https://doi.org/10.1109/tgrs.2022.3227626
https://doi.org/10.1109/tgrs.2022.3227626