• 研究課題をさがす
  • 研究者をさがす
  • KAKENの使い方
  1. 課題ページに戻る

2021 年度 実施状況報告書

Healthcare Risk Prediction on Data Streams Employing Cross Ensemble Deep Learning

研究課題

研究課題/領域番号 20K11955
研究機関岩手県立大学

研究代表者

藤田 ハミド  岩手県立大学, 公私立大学の部局等, 特命教授 (30244990)

研究期間 (年度) 2020-04-01 – 2023-03-31
キーワード知能情報学関連 / Machine Learning / Health Care System / Deep Learning
研究実績の概要

We have used ensemble deep learning techniques by constructing Deep Neural Networks (DNNs) based on assembled CNN in architecture of two GPUs in
cross layered connection. Also, we have one GUP system, running as backup for training experiments using large scale data for comparison purpose. I
could achieve good research results using zero short learning on multivariate data. Also I have trained the deep-learning architecture on dynamic data, and image data. The results was promising and therefore we publish three journal articles. We also, implemented Multi-task Learning-based Attentional
Feature Fusion Network for Scene Text Image Super-resolution, with good results.

Although we achieved good results using our reported algorithms (as shown in the list of publications), however, the accuracy for some healthcare data analytics need to be enhanced. The year 2021 was hard due to the pandemic as traveling and moving around was tight, also materials become expensive than usual. Nevertheless, the results achieved is good, as evident from the publication enlisted in journals.

現在までの達成度 (区分)
現在までの達成度 (区分)

3: やや遅れている

理由

The experimental results provided high accuracy outcome, by testing it on the learning system, however due to the pandemic traveling
restrictions, it was rather not easy to expand the results with European collaborators that I contribute with in terms of the innovative idea in
Deep learning using semi-supervised learning methods. Some researchers that I collaborate are looking to test the machine learning developed
model on Parkinson’s Disease: as in the joint publication: A. Butt, E. Rovini, Hamido Fujita, C. Maremmani, F. Cavallo, “Data-Driven Models
for Objective Grading Improvement of Parkinson’s Disease”, Annals of Biomedical Engineering (2020) 48, p.2976-2987
https://doi.org/10.1007/s10439-020-02628-4. This is currently to be test for more accuracy on our system, also for Alzheimer.

今後の研究の推進方策

For the year 2022: testing data to revise the built architecture for learning. Still some multivariate health care data, are not providing
high quality prediction, maybe this is related to data noise (we need to check this issue). it needs extract further features to refine the training mechanism.
Also to test multi view learning by my joint work Consensus Multi-view Clustering Model for Predicting Alzheimer’s Disease Progression"
Computer Methods and Programs in Biomedicine, V.199, Feb. 2021, 105895. These new results are to be expanded and be used to detect other health
issues like my work: "Application of mechanical trigger for unobtrusive detection of respiratory disorders from body recoil micro-movements" Computer Methods and Programs in Biomedicine, Volume 207, August 2021, 106149

次年度使用額が生じた理由

(1) 新型コロナウイルスの影響で海外出張が中止になったため
(1) Due to the pandemic the traveling for conference and meeting with other research collaborator was not possible,
(2) Some development was delayed due to traveling restrictions.

  • 研究成果

    (20件)

すべて 2022 2021 その他

すべて 国際共同研究 (2件) 雑誌論文 (12件) (うち国際共著 12件、 査読あり 12件) 学会発表 (4件) (うち国際学会 4件) 図書 (2件)

  • [国際共同研究] University of Hradec Kralove/Faculty of Science/Rokitanskeho 62, Hradec Kralove 50003(チェコ)

    • 国名
      チェコ
    • 外国機関名
      University of Hradec Kralove/Faculty of Science/Rokitanskeho 62, Hradec Kralove 50003
  • [国際共同研究] OLIMPIA Projec/The BioRobotics Institute/Viale Rinaldo Piaggio, 34 Pontedera(イタリア)

    • 国名
      イタリア
    • 外国機関名
      OLIMPIA Projec/The BioRobotics Institute/Viale Rinaldo Piaggio, 34 Pontedera
  • [雑誌論文] Aspect-level sentiment analysis with aspect-specific context position information2022

    • 著者名/発表者名
      Huang Bo、Guo Ruyan、Zhu Yimin、Fang Zhijun、Zeng Guohui、Liu Jin、Wang Yini、Fujita Hamido、Shi Zhicai
    • 雑誌名

      Knowledge-Based Systems

      巻: 243 ページ: 108473~108473

    • DOI

      10.1016/j.knosys.2022.108473

    • 査読あり / 国際共著
  • [雑誌論文] BERT syntactic transfer: A computational experiment on Italian, French and English languages2022

    • 著者名/発表者名
      Guarasci Raffaele、Silvestri Stefano、De Pietro Giuseppe、Fujita Hamido、Esposito Massimo
    • 雑誌名

      Computer Speech & Language

      巻: 71 ページ: 101261~101261

    • DOI

      10.1016/j.csl.2021.101261

    • 査読あり / 国際共著
  • [雑誌論文] Deep learning network for medical volume data segmentation based on multi axial plane fusion2021

    • 著者名/発表者名
      Huang Bo、Wei Ziran、Tang Xianhua、Fujita Hamido、Cai Qingping、Gao Yongbin、Wu Tao、Zhou Liang
    • 雑誌名

      Computer Methods and Programs in Biomedicine

      巻: 212 ページ: 106480~106480

    • DOI

      10.1016/j.cmpb.2021.106480

    • 査読あり / 国際共著
  • [雑誌論文] Multilingual evaluation of pre-processing for BERT-based sentiment analysis of tweets2021

    • 著者名/発表者名
      Pota Marco、Ventura Mirko、Fujita Hamido、Esposito Massimo
    • 雑誌名

      Expert Systems with Applications

      巻: 181 ページ: 115119~115119

    • DOI

      10.1016/j.eswa.2021.115119

    • 査読あり / 国際共著
  • [雑誌論文] Multiple-objective optimization applied in extracting multiple-choice tests2021

    • 著者名/発表者名
      Nguyen Tram、Bui Toan、Fujita Hamido、Hong Tzung-Pei、Loc Ho Dac、Snasel Vaclav、Vo Bay
    • 雑誌名

      Engineering Applications of Artificial Intelligence

      巻: 105 ページ: 104439~104439

    • DOI

      10.1016/j.engappai.2021.104439

    • 査読あり / 国際共著
  • [雑誌論文] Assessing BERT’s ability to learn Italian syntax: a study on null-subject and agreement phenomena2021

    • 著者名/発表者名
      Guarasci Raffaele、Silvestri Stefano、De Pietro Giuseppe、Fujita Hamido、Esposito Massimo
    • 雑誌名

      Journal of Ambient Intelligence and Humanized Computing

      巻: in press ページ: in press

    • DOI

      10.1007/s12652-021-03297-4

    • 査読あり / 国際共著
  • [雑誌論文] A dynamic feedback mechanism with attitudinal consensus threshold for minimum adjustment cost in group decision making2021

    • 著者名/発表者名
      Sun Qi、Wu Jian、Chiclana Francisco、Fujita Hamido、Herrera-Viedma Enrique
    • 雑誌名

      IEEE Transactions on Fuzzy Systems

      巻: in press ページ: 1~1

    • DOI

      10.1109/TFUZZ.2021.3057705

    • 査読あり / 国際共著
  • [雑誌論文] Application of mechanical trigger for unobtrusive detection of respiratory disorders from body recoil micro-movements2021

    • 著者名/発表者名
      Cimr Dalibor、Studnicka Filip、Fujita Hamido、Cimler Richard、Slegr Jan
    • 雑誌名

      Computer Methods and Programs in Biomedicine

      巻: 207 ページ: 106149~106149

    • DOI

      10.1016/j.cmpb.2021.106149

    • 査読あり / 国際共著
  • [雑誌論文] Less complexity one-class classification approach using construction error of convolutional image transformation network2021

    • 著者名/発表者名
      Hayashi Toshitaka、Fujita Hamido、Hernandez-Matamoros Andres
    • 雑誌名

      Information Sciences

      巻: 560 ページ: 217~234

    • DOI

      10.1016/j.ins.2021.01.069

    • 査読あり / 国際共著
  • [雑誌論文] Multi-class financial distress prediction based on support vector machines integrated with the decomposition and fusion methods2021

    • 著者名/発表者名
      Sun Jie、Fujita Hamido、Zheng Yujiao、Ai Wenguo
    • 雑誌名

      Information Sciences

      巻: 559 ページ: 153~170

    • DOI

      10.1016/j.ins.2021.01.059

    • 査読あり / 国際共著
  • [雑誌論文] A Novel COVID-19 Data Set and an Effective Deep Learning Approach for the De-Identification of Italian Medical Records2021

    • 著者名/発表者名
      Catelli Rosario、Gargiulo Francesco、Casola Valentina、De Pietro Giuseppe、Fujita Hamido、Esposito Massimo
    • 雑誌名

      IEEE Access

      巻: 9 ページ: 19097~19110

    • DOI

      10.1109/ACCESS.2021.3054479

    • 査読あり / 国際共著
  • [雑誌論文] Combining contextualized word representation and sub-document level analysis through Bi-LSTM+CRF architecture for clinical de-identification2021

    • 著者名/発表者名
      Catelli Rosario、Casola Valentina、De Pietro Giuseppe、Fujita Hamido、Esposito Massimo
    • 雑誌名

      Knowledge-Based Systems

      巻: 213 ページ: 106649~106649

    • DOI

      10.1016/j.knosys.2020.106649

    • 査読あり / 国際共著
  • [学会発表] One-Class Classification Approach Using Feature-Slide Prediction Subtask for Feature Data2021

    • 著者名/発表者名
      Toshitaka Hayashi, Hamido Fujita
    • 学会等名
      The 34th International Conference on Industrial, Engineering & Other Applications of Applied Intelligent Systems
    • 国際学会
  • [学会発表] Combining Siamese Network and Correlation Filter for Complementary Object Tracking2021

    • 著者名/発表者名
      Kosuke Honda, Hamido Fujita
    • 学会等名
      The 34th International Conference on Industrial, Engineering & Other Applications of Applied Intelligent Systems
    • 国際学会
  • [学会発表] Experiment of OCITN: Considering Appropriate Goal Images and Metric for One-Class Image Transformation Network2021

    • 著者名/発表者名
      Toshitaka Hayashi, Hamido Fujita
    • 学会等名
      The 20th International Conference on Intelligent Software Methodologies Tools and Techniques
    • 国際学会
  • [学会発表] Kosuke Honda, Hamido Fujita2021

    • 著者名/発表者名
      Complementary Object Tracking Using Average Peak-to-Correlation Energy
    • 学会等名
      The 20th International Conference on Intelligent Software Methodologies Tools and Techniques
    • 国際学会
  • [図書] New Trends in Intelligent Software Methodologies, Tools and Techniques2021

    • 著者名/発表者名
      Hamido Fujita, Hector Perez-Meana
    • 総ページ数
      800
    • 出版者
      IOS Press
    • ISBN
      978-1-64368-194-8
  • [図書] Advances and Trends in Artificial Intelligence. From Theory to Practice2021

    • 著者名/発表者名
      Hamido Fujita, Ali Selamat, Jerry Chun-Wei Lin, Moonis Ali
    • 総ページ数
      900
    • 出版者
      Springer
    • ISBN
      978-3-030-79462-0

URL: 

公開日: 2022-12-28  

サービス概要 検索マニュアル よくある質問 お知らせ 利用規程 科研費による研究の帰属

Powered by NII kakenhi