東華大學圖書館 |

語系: 繁體中文

說明(常見問題)

回圖書館首頁

手機版館藏查詢

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

FindBook

Google Book

Amazon

博客來

Application Studies of Machine Learning in Breast Cancer Prevention Assessment and Deep Learning in Natural Language Processing.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Application Studies of Machine Learning in Breast Cancer Prevention Assessment and Deep Learning in Natural Language Processing./
作者:	Han, Qing.
面頁冊數:	1 online resource (72 pages)
附註:	Source: Dissertations Abstracts International, Volume: 84-05, Section: B.
Contained By:	Dissertations Abstracts International84-05B.
標題:	Statistics. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=29252552click for full text (PQDT)
ISBN:	9798357571014

Application Studies of Machine Learning in Breast Cancer Prevention Assessment and Deep Learning in Natural Language Processing.
Han, Qing.

Application Studies of Machine Learning in Breast Cancer Prevention Assessment and Deep Learning in Natural Language Processing. - 1 online resource (72 pages)

Source: Dissertations Abstracts International, Volume: 84-05, Section: B.

Thesis (Ph.D.)--The Florida State University, 2022.

Includes bibliographical references

With the rapid development of Artificial Intelligence, Machine Learning technologies have entered a fast-evolving era. This dissertation covers application studies of various algorithms ranging from traditional machine learning methods to deep neural networks. In the first study, we predicted Female Breast Cancer Incidence Rates using prevailing machine learning techniques for 1,754 US counties with a female population over 10,000. Outlier counties with unexpectedly high or low FBC IRs were identified by controlling the non-modifiable factors (demographics and socioeconomics). Geographic clusters of outlier counties as well as impacts of modifiable factors (lifestyle, healthcare accessibility, and environment) were also mapped. Our study pioneers the county-level assessment, which takes both individual and population risk factors into consideration across 6 state-of-art machine learning algorithms. Moreover, the framework we developed can be applied to studies of other types of cancer. Diving deep into deep learning in particular, we investigated text mining models of biomedical Named Entity Recognition and Relation Extraction on both social media texts and scientific publications. For social media texts, we developed a PubMedBERT-based classifier trained with a combination of multiple data augmentation approaches. Our study explored the effects of various data augmentation strategies on extremely imbalanced data, which has not been experimented thoroughly before. It has achieved an F1 score of 0.762, which is substantially higher than the mean of all submissions (0.696). For scientific articles, we design and train two NLP systems that effectively extract biomedical entities and relations information. As a result, our methods achieved Top 4 in BioCreative VII track 3 and Top 1 in LitCoin NLP challenges.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2023

Mode of access: World Wide Web

ISBN: 9798357571014Subjects--Topical Terms:

517247
Statistics.
Subjects--Index Terms:

Text mining modelsIndex Terms--Genre/Form:

542853
Electronic books.

Application Studies of Machine Learning in Breast Cancer Prevention Assessment and Deep Learning in Natural Language Processing.
LDR:03156nmm a2200349K 4500 001 2356440
005 20230612110823.5
006 m o d
007 cr mn ---uuuuu
008 241011s2022 xx obm 000 0 eng d
020 $a 9798357571014
035 $a (MiAaPQ)AAI29252552
035 $a AAI29252552
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Han, Qing. $3 728340
245 1 0 $a Application Studies of Machine Learning in Breast Cancer Prevention Assessment and Deep Learning in Natural Language Processing.
264 0 $c 2022
300 $a 1 online resource (72 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Dissertations Abstracts International, Volume: 84-05, Section: B.
500 $a Advisor: Zhang, Jinfeng.
502 $a Thesis (Ph.D.)--The Florida State University, 2022.
504 $a Includes bibliographical references
520 $a With the rapid development of Artificial Intelligence, Machine Learning technologies have entered a fast-evolving era. This dissertation covers application studies of various algorithms ranging from traditional machine learning methods to deep neural networks. In the first study, we predicted Female Breast Cancer Incidence Rates using prevailing machine learning techniques for 1,754 US counties with a female population over 10,000. Outlier counties with unexpectedly high or low FBC IRs were identified by controlling the non-modifiable factors (demographics and socioeconomics). Geographic clusters of outlier counties as well as impacts of modifiable factors (lifestyle, healthcare accessibility, and environment) were also mapped. Our study pioneers the county-level assessment, which takes both individual and population risk factors into consideration across 6 state-of-art machine learning algorithms. Moreover, the framework we developed can be applied to studies of other types of cancer. Diving deep into deep learning in particular, we investigated text mining models of biomedical Named Entity Recognition and Relation Extraction on both social media texts and scientific publications. For social media texts, we developed a PubMedBERT-based classifier trained with a combination of multiple data augmentation approaches. Our study explored the effects of various data augmentation strategies on extremely imbalanced data, which has not been experimented thoroughly before. It has achieved an F1 score of 0.762, which is substantially higher than the mean of all submissions (0.696). For scientific articles, we design and train two NLP systems that effectively extract biomedical entities and relations information. As a result, our methods achieved Top 4 in BioCreative VII track 3 and Top 1 in LitCoin NLP challenges.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2023
538 $a Mode of access: World Wide Web
650 4 $a Statistics. $3 517247
653 $a Text mining models
653 $a Machine learning methods
655 7 $a Electronic books. $2 lcsh $3 542853
690 $a 0463
690 $a 0800
710 2 $a ProQuest Information and Learning Co. $3 783688
710 2 $a The Florida State University. $b Statistics. $3 3185231
773 0 $t Dissertations Abstracts International $g 84-05B.
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=29252552 $z click for full text (PQDT)