GLORIA

GEOMAR Library Ocean Research Information Access

Your email was sent successfully. Check your inbox.

An error occurred while sending the email. Please try again.

Proceed reservation?

Export
  • 1
    In: Medical Image Analysis, Elsevier BV, Vol. 67 ( 2021-01), p. 101854-
    Type of Medium: Online Resource
    ISSN: 1361-8415
    Language: English
    Publisher: Elsevier BV
    Publication Date: 2021
    detail.hit.zdb_id: 1497450-2
    Location Call Number Limitation Availability
    BibTip Others were also interested in ...
  • 2
    Online Resource
    Online Resource
    Oxford University Press (OUP) ; 2023
    In:  Briefings in Bioinformatics Vol. 24, No. 1 ( 2023-01-19)
    In: Briefings in Bioinformatics, Oxford University Press (OUP), Vol. 24, No. 1 ( 2023-01-19)
    Abstract: The accurate prediction of cancer drug sensitivity according to the multiomics profiles of individual patients is crucial for precision cancer medicine. However, the development of prediction models has been challenged by the complex crosstalk of input features and the resistance-dominant drug response information contained in public databases. In this study, we propose a novel multidrug response prediction framework, response-aware multitask prediction (RAMP), via a Bayesian neural network and restrict it by soft-supervised contrastive regularization. To utilize network embedding vectors as representation learning features for heterogeneous networks, we harness response-aware negative sampling, which applies cell line–drug response information to the training of network embeddings. RAMP overcomes the prediction accuracy limitation induced by the imbalance of trained response data based on the comprehensive selection and utilization of drug response features. When trained on the Genomics of Drug Sensitivity in Cancer dataset, RAMP achieved an area under the receiver operating characteristic curve & gt; 89%, an area under the precision-recall curve & gt; 59% and an $\textrm{F}_1$ score & gt; 52% and outperformed previously developed methods on both balanced and imbalanced datasets. Furthermore, RAMP predicted many missing drug responses that were not included in the public databases. Our results showed that RAMP will be suitable for the high-throughput prediction of cancer drug sensitivity and will be useful for guiding cancer drug selection processes. The Python implementation for RAMP is available at https://github.com/hvcl/RAMP.
    Type of Medium: Online Resource
    ISSN: 1467-5463 , 1477-4054
    Language: English
    Publisher: Oxford University Press (OUP)
    Publication Date: 2023
    detail.hit.zdb_id: 2036055-1
    SSG: 12
    Location Call Number Limitation Availability
    BibTip Others were also interested in ...
  • 3
    Online Resource
    Online Resource
    Springer Science and Business Media LLC ; 2019
    In:  Scientific Reports Vol. 9, No. 1 ( 2019-11-15)
    In: Scientific Reports, Springer Science and Business Media LLC, Vol. 9, No. 1 ( 2019-11-15)
    Abstract: With recent advances in DNA sequencing technologies, fast acquisition of large-scale genomic data has become commonplace. For cancer studies, in particular, there is an increasing need for the classification of cancer type based on somatic alterations detected from sequencing analyses. However, the ever-increasing size and complexity of the data make the classification task extremely challenging. In this study, we evaluate the contributions of various input features, such as mutation profiles, mutation rates, mutation spectra and signatures, and somatic copy number alterations that can be derived from genomic data, and further utilize them for accurate cancer type classification. We introduce a novel ensemble of machine learning classifiers, called CPEM (Cancer Predictor using an Ensemble Model), which is tested on 7,002 samples representing over 31 different cancer types collected from The Cancer Genome Atlas (TCGA) database. We first systematically examined the impact of the input features. Features known to be associated with specific cancers had relatively high importance in our initial prediction model. We further investigated various machine learning classifiers and feature selection methods to derive the ensemble-based cancer type prediction model achieving up to 84% classification accuracy in the nested 10-fold cross-validation. Finally, we narrowed down the target cancers to the six most common types and achieved up to 94% accuracy.
    Type of Medium: Online Resource
    ISSN: 2045-2322
    Language: English
    Publisher: Springer Science and Business Media LLC
    Publication Date: 2019
    detail.hit.zdb_id: 2615211-3
    Location Call Number Limitation Availability
    BibTip Others were also interested in ...
  • 4
    Online Resource
    Online Resource
    Korean Association of Art History Education ; 2008
    In:  Journal of Korean Association of Art History Education , No. 22 ( 2008-08-31)
    In: Journal of Korean Association of Art History Education, Korean Association of Art History Education, , No. 22 ( 2008-08-31)
    Type of Medium: Online Resource
    ISSN: 1229-8433
    Language: English
    Publisher: Korean Association of Art History Education
    Publication Date: 2008
    Location Call Number Limitation Availability
    BibTip Others were also interested in ...
  • 5
    Online Resource
    Online Resource
    Institute of Electrical and Electronics Engineers (IEEE) ; 2021
    In:  IEEE Transactions on Medical Imaging Vol. 40, No. 11 ( 2021-11), p. 3238-3248
    In: IEEE Transactions on Medical Imaging, Institute of Electrical and Electronics Engineers (IEEE), Vol. 40, No. 11 ( 2021-11), p. 3238-3248
    Type of Medium: Online Resource
    ISSN: 0278-0062 , 1558-254X
    RVK:
    Language: Unknown
    Publisher: Institute of Electrical and Electronics Engineers (IEEE)
    Publication Date: 2021
    detail.hit.zdb_id: 2068206-2
    detail.hit.zdb_id: 622531-7
    SSG: 12
    Location Call Number Limitation Availability
    BibTip Others were also interested in ...
  • 6
    Online Resource
    Online Resource
    The Paek-San Society ; 2023
    In:  The Paek-San Society Vol. 125 ( 2023-04-30), p. 185-216
    In: The Paek-San Society, The Paek-San Society, Vol. 125 ( 2023-04-30), p. 185-216
    Abstract: Most of the king's ruling activities are held in a specific building or place in the Joseon Dynasty's Palace, and the king was carried in a palanquin or horse while moving from the king's residence to this building or place. In historical records, the king's movement is recorded as geodong擧動 and the movement path is recorded as munro門路. Governance activities are usually carried out in Jeongjeon正殿 and Pyeonjeon便殿, but there were many cases in which they were carried out in the Palace Garden. Gwageo科擧, Jeongang殿講, Mangbaerye望拜禮 and others were held at Chundangdae春塘臺 in Changdeokgung Palace and Gyeongmudae景武臺 in Gyeongbokgung Palace, and the king was carried in a palanquin or horse under the guard of his subjects to the rear garden後苑 far from the residential area大內. There were three paths to Chundangdae of Changdeokgung Palace. First, it is the eastern road from Geonyangmun Gate to Cheongyangmun Gate via Changgyeonggung Palace. Second, it is an western road that leaves Hyeopyangmun Gate, passes through Sookjangmun Gate and Jinseonmun Gate, and enters Jipseongmun Gate via Daebodan deep in the northwest of the palace. These two roads are a long way back by bypassing a large area inside the palace. Third, it is the way to enter Chuimimun Gate starting from Yeonyangmun Gate, passing through Guyeomun Gate next to Junghuidang Hall. This road is close to king's residence, and it also seems that it was a place that was reluctant to reveal to his subjects. There were four paths to Gyeongmudae of Gyeongbokgung Palace. First, after passing through the central areas of Gyeongbokgung Palace, Sajeongjeon Hall and Geunjeongjeon Hall to Heungryemun Gate, there were two roads: approaching Sinmumun Gate through Changhoemun Gate, and through Imsookmun Gate. Second, if exit the three gates of Sujeongjeon Hall, enter Yuhwamun Gate, and come back to Yongseongmun Gate through Heungryemun Gate, there are two ways to access Sinmumun Gate through Changhoemun Gate and through Imsookmun Gate. Third, there was a way to access Sinmumun Gate through Singeomun Gate and Yuhyeongmun Gate, starting from Daejaemun Gate in the west haenggak行閣 of the king's residence, leaving Mansimun Gate in the northeast of Gyeonghoeru Pavilion. Fourth, during the period when the king's residence was moved to Geoncheonggung Residence, the northernmost part of the palace, due to two fires in the residential area of Gyeongbokgung Palace, the road from Geonseonmun Gate to Sinmumun Gate was used. It should be revealed in a follow-up study the reason why the diversity of the geodong-munro, which was commonly identified in Changdeokgung Palace and Gyeongbokgung Palace, was formed.
    Type of Medium: Online Resource
    ISSN: 1225-7109
    Uniform Title: 高宗代 宮闕 後苑의 정치적 기능과 거둥 門路 연구
    URL: Issue
    Language: Unknown
    Publisher: The Paek-San Society
    Publication Date: 2023
    Location Call Number Limitation Availability
    BibTip Others were also interested in ...
  • 7
    Online Resource
    Online Resource
    MDPI AG ; 2022
    In:  Sensors Vol. 22, No. 11 ( 2022-06-02), p. 4255-
    In: Sensors, MDPI AG, Vol. 22, No. 11 ( 2022-06-02), p. 4255-
    Abstract: With the advent of unsupervised learning, efficient training of a deep network for image denoising without pairs of noisy and clean images has become feasible. Most current unsupervised denoising methods are built on self-supervised loss with the assumption of zero-mean noise under the signal-independent condition, which causes brightness-shifting artifacts on unconventional noise statistics (i.e., different from commonly used noise models). Moreover, most blind denoising methods require a random masking scheme for training to ensure the invariance of the denoising process. In this study, we propose a dilated convolutional network that satisfies an invariant property, allowing efficient kernel-based training without random masking. We also propose an adaptive self-supervision loss to increase the tolerance for unconventional noise, which is specifically effective in removing salt-and-pepper or hybrid noise where prior knowledge of noise statistics is not readily available. We demonstrate the efficacy of the proposed method by comparing it with state-of-the-art denoising methods using various examples.
    Type of Medium: Online Resource
    ISSN: 1424-8220
    Language: English
    Publisher: MDPI AG
    Publication Date: 2022
    detail.hit.zdb_id: 2052857-7
    Location Call Number Limitation Availability
    BibTip Others were also interested in ...
  • 8
    Online Resource
    Online Resource
    Korea Computer Graphics Society ; 2021
    In:  Journal of the Korea Computer Graphics Society Vol. 27, No. 5 ( 2021-11), p. 45-54
    In: Journal of the Korea Computer Graphics Society, Korea Computer Graphics Society, Vol. 27, No. 5 ( 2021-11), p. 45-54
    Type of Medium: Online Resource
    ISSN: 1975-7883 , 2383-529X
    Uniform Title: 비지도 학습 기반 영상 노이즈 제거 기술을위한 정규화 기법의 최적화
    Language: English
    Publisher: Korea Computer Graphics Society
    Publication Date: 2021
    Location Call Number Limitation Availability
    BibTip Others were also interested in ...
Close ⊗
This website uses cookies and the analysis tool Matomo. More information can be found here...