ログイン
Language:

WEKO3

  • トップ
  • ランキング
To
lat lon distance
To

Field does not validate



インデックスリンク

インデックスツリー

メールアドレスを入力してください。

WEKO

One fine body…

WEKO

One fine body…

アイテム

  1. 学位論文
  2. 学位論文

介護・高齢者ケア記録アプリケーションにおける文章サジェストの評価指標の開発

https://doi.org/10.18997/0002000945
https://doi.org/10.18997/0002000945
e44cea9d-e01e-464e-b41a-f69476ca9d58
名前 / ファイル ライセンス アクション
sei_k_487.pdf sei_k_487.pdf (1.4 MB)
アイテムタイプ 学位論文 = Thesis or Dissertation(1)
公開日 2024-09-03
資源タイプ
資源タイプ識別子 http://purl.org/coar/resource_type/c_db06
資源タイプ doctoral thesis
タイトル
タイトル The Development of Evaluation Metrics for Sentence Suggestion in Nursing and Elderly Care Record Application
言語 en
タイトル
タイトル 介護・高齢者ケア記録アプリケーションにおける文章サジェストの評価指標の開発
言語 ja
言語
言語 eng
著者 Defry Hamdhana,

× Defry Hamdhana,

en Defry Hamdhana,

Search repository
抄録
内容記述タイプ Abstract
内容記述 This thesis proposes a novel metrics evaluation framework for assessing the quality of sentence suggestions generated by a model in nursing care record applications. The objective is to introduce a systematic approach for evaluating the quality of generated sentence suggestions, allowing for assessments comparable to caregiver evaluations. Our proposed framework aims to provide a comprehensive and standardized method for evaluating the efficacy of sentence suggestions. By establishing a systematic evaluation process, we seek to bridge the gap between automated assessments and human evaluation, contributing to the development of more reliable and accurate models in the field of nursing care record applications.
During the initial phase of our study, we used a Markov model to generate sentence suggestions within the context of nursing care record applications. These suggestions were then compared systematically against ground truth care records, serving as a reference for accuracy and relevance. Furthermore, we conducted a human evaluation to obtain caregivers’ opinions and establish a ground truth for the assessment process. By comparing the model-generated suggestions with ground truth care records and expert evaluations, our study aims to assess the performance and applicability of the Markov model comprehensively.
Based on this foundation, our study evaluated the generated sentence suggestions using several existing metrics. The outcomes of these metrics were then systematically compared against human evaluations, and the results were meticulously observed. Given the unique characteristics of care records, we found that the current evaluation metrics fell short of delivering satisfactory assessments.
The intricacies of healthcare documentation necessitate a more nuanced approach to evaluation. Our findings underscore the need for customised metrics that can capture the specific intricacies and nuances of sentence suggestions within the context of care records.
In conclusion, our proposed evaluation metric outperforms several current evaluation methods in assessing sentence suggestion generation within care record applications. The meticulous comparison against existing metrics revealed the limitations of conventional approaches in adequately capturing the intricacies of healthcare documentation. By introducing a more tailored evaluation methodology, our study seeks to address these limitations and enhance the accuracy and relevance of assessments.
目次
内容記述タイプ TableOfContents
内容記述 1 Introduction| 2 Related Work| 3 EmbedHDP Method to Improved Evaluation Metrics| 4 Data Collection| 5 Evaluation| 6 Discusscion and Future Work| 7 Conclusion
備考
内容記述タイプ Other
内容記述 九州⼯業⼤学博⼠学位論⽂ 学位記番号:生工博甲第487号 学位授与年⽉⽇: 令和6年3⽉25⽇
学位授与番号
学位授与番号 甲第487号
学位名
学位名 博士(工学)
学位授与年月日
学位授与年月日 2024-03-25
学位授与機関
学位授与機関識別子Scheme kakenhi
学位授与機関識別子 17104
学位授与機関名 九州工業大学
言語 ja
学位授与年度
内容記述タイプ Other
内容記述 令和5年度
出版タイプ
出版タイプ VoR
出版タイプResource http://purl.org/coar/version/c_970fb48d4fbd8a85
アクセス権
アクセス権 open access
アクセス権URI http://purl.org/coar/access_right/c_abf2
ID登録
ID登録 10.18997/0002000945
ID登録タイプ JaLC
戻る
0
views
See details
Views

Versions

Ver.1 2024-09-03 06:16:42.188902
Show All versions

Share

Share
tweet

Cite as

Other

print

エクスポート

OAI-PMH
  • OAI-PMH JPCOAR 2.0
  • OAI-PMH JPCOAR 1.0
  • OAI-PMH DublinCore
  • OAI-PMH DDI
Other Formats
  • JSON
  • BIBTEX
  • ZIP

コミュニティ

確認

確認

確認


Powered by WEKO3


Powered by WEKO3