政大機構典藏-National Chengchi University Institutional Repository(NCCUR):Item 140.119/152415
English  |  正體中文  |  简体中文  |  Post-Print筆數 : 27 |  全文笔数/总笔数 : 113160/144130 (79%)
造访人次 : 50753821      在线人数 : 705
RC Version 6.0 © Powered By DSPACE, MIT. Enhanced by NTU Library IR team.
搜寻范围 查询小技巧:
  • 您可在西文检索词汇前后加上"双引号",以获取较精准的检索结果
  • 若欲以作者姓名搜寻,建议至进阶搜寻限定作者字段,可获得较完整数据
  • 进阶搜寻
    政大機構典藏 > 商學院 > 資訊管理學系 > 學位論文 >  Item 140.119/152415


    请使用永久网址来引用或连结此文件: https://nccur.lib.nccu.edu.tw/handle/140.119/152415


    题名: 使用LIME建構防跌倒系統並評估對信任度的影響
    Building XAI for Fall Prevention System: An Evaluation of LIME’s Potential in Bridging Trust Gap
    作者: 侯允禔
    Hou, Yun-Ti
    贡献者: 張欣綠
    Chang, Hsin-Lu
    侯允禔
    Hou, Yun-Ti
    关键词: 可解釋AI
    使用者信任
    預防跌倒系統
    模型可解釋性
    XAI
    User Trust
    Fall Prevention System
    Model Interpretability
    日期: 2024
    上传时间: 2024-08-05 12:07:45 (UTC+8)
    摘要: 近年來,人工智慧(AI)成為相當熱門的研究課題,並迅速在醫療領域開始發展。儘管 AI 變得越來越強大且多功能,但其「黑箱」問題導致了 AI 與用戶之間的信任鴻溝。這一鴻溝可能會阻礙 AI 方法的採用,並減緩 AI 在醫療領域的發展。可解釋人工智慧(XAI)的出現為這一問題提供了潛在的解決方案,通過對模型的預測結果提供解釋,從而可能增加用戶對這些模型的信任。本研究將 XAI 演算法 LIME 和 SHAP 整合到基於 AI 的預防跌倒系統中。我們設計了一項實驗,以觀察 XAI 整合到預防跌倒系統中對三個指標的影響:用戶信任、解釋滿意度和解釋全面性,以及評估這些效果在不同準確度模型中的差異。我們的研究結果表明,提高解釋的質量和簡單性,以及在實施 XAI 前優先考慮系統準確性,對建立用戶信任至關重要。此外,以用戶為中心的設計和對解釋影響的持續評估,對於在醫療環境中有效部署 XAI 至關重要。
    In recent years, AI has become a quite popular research topic and has rapidly started to develop in the medical field. Despite AI becoming increasingly powerful and multifunctional, it has led to the problem of the 'black box', creating a trust gap between AI and its users. This gap could hinder the adoption of AI methods and decrease the development of AI in the medical sector. The emergence of XAI (Explainable AI) offers a potential solution by providing explanations for the predictive results of models, which may increase users' trust in these models. This study integrates the XAI algorithm LIME and SHAP into an AI based fall prevention system. We designed an experiment to observe how the integration of XAI into fall prevention system impacts three metrics: user trust, explanation satisfaction and explanation comprehensiveness, as well as to assess how these effects might differ across models with varying accuracy levels. Our findings indicate that enhancing the quality and simplicity of explanations, along with prioritizing system accuracy before implementing XAI, is crucial for building user trust. Furthermore, user-centric design and continuous evaluation of explanation impacts are essential for effectively deploying XAI in healthcare contexts.
    參考文獻: Adhikari, K., Bouchachia, H., & Nait-Charif, H. (2017, May). Activity recognition for indoor fall detection using convolutional neural network. In 2017 Fifteenth IAPR International Conference on Machine Vision Applications (MVA) (pp. 81-84). IEEE.
    Arenas, M., Barceló, P., Bertossi, L., & Monet, M. (2023). On the complexity of SHAP-score-based explanations: Tractability via knowledge compilation and non-approximability results. Journal of Machine Learning Research, 24(63), 1-58.
    Biau, G., Scornet, E., & Welbl, J. (2019). Neural random forests. Sankhya A, 81(2), 347-386.
    Carlier, A., Peyramaure, P., Favre, K., & Pressigout, M. (2020, July). Fall detector adapted to nursing home needs through an optical-flow based CNN. In 2020 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC) (pp. 5741-5744). IEEE.
    Doshi-Velez, F., & Kim, B. (2017). Towards a rigorous science of interpretable machine learning. arXiv preprint arXiv:1702.08608.
    Farsi, M. (2021). Application of ensemble RNN deep neural network to the fall detection through IoT environment. Alexandria Engineering Journal, 60(1), 199-211.
    Feng, Q., Gao, C., Wang, L., Zhao, Y., Song, T., & Li, Q. (2020). Spatio-temporal fall event detection in complex scenes using attention guided LSTM. Pattern Recognition Letters, 130, 242-249.
    Gille, F., Jobin, A., & Ienca, M. (2020). What we talk about when we talk about trust: theory of trust for AI in healthcare. Intelligence-Based Medicine, 1, 100001.
    Gutiérrez, J., Rodríguez, V., & Martin, S. (2021). Comprehensive review of vision-based fall detection systems. Sensors, 21(3), 947.
    Hagras, H. (2018). Toward human-understandable, explainable AI. Computer, 51(9), 28-36.
    Hailesilassie, T. (2016). Rule extraction algorithm for deep neural networks: A review. arXiv preprint arXiv:1610.05267.
    Han, Q., Zhao, H., Min, W., Cui, H., Zhou, X., Zuo, K., & Liu, R. (2020). A two-stream approach to fall detection with MobileVGG. IEEE Access, 8, 17556-17566.
    Hoffman, R. R., Mueller, S. T., Klein, G., & Litman, J. (2023). Measures for explainable AI: Explanation goodness, user satisfaction, mental models, curiosity, trust, and human-AI performance. Frontiers in Computer Science, 5, 1096257.
    Igual, R., Medrano, C., & Plaza, I. (2013). Challenges, issues and trends in fall detection systems. Biomedical engineering online, 12(1), 66.
    Jeong, S., Kang, S., & Chun, I. (2019, June). Human-skeleton based fall-detection method using LSTM for manufacturing industries. In 2019 34th International Technical Conference on Circuits/Systems, Computers and Communications (ITC-CSCC) (pp. 1-4). IEEE.
    Kong, Y., Huang, J., Huang, S., Wei, Z., & Wang, S. (2019). Learning spatiotemporal representations for human fall detection in surveillance video. Journal of Visual Communication and Image Representation, 59, 215-230.
    Li, H., Shrestha, A., Heidari, H., Le Kernec, J., & Fioranelli, F. (2019). Bi-LSTM network for multimodal continuous human activity recognition and fall detection. IEEE Sensors Journal, 20(3), 1191-1201.
    Li, X., Pang, T., Liu, W., & Wang, T. (2017, October). Fall detection for elderly person care using convolutional neural networks. In 2017 10th international congress on image and signal processing, biomedical engineering and informatics (CISP-BMEI) (pp. 1-6). IEEE.
    Loyola-Gonzalez, O. (2019). Black-box vs. white-box: Understanding their advantages and weaknesses from a practical point of view. IEEE Access, 7, 154096-154113.
    Lugaresi, C., Tang, J., Nash, H., McClanahan, C., Uboweja, E., Hays, M., Zhang, F., Chang, C.-L., Yong, M. G., & Lee, J. (2019). Mediapipe: A framework for building perception pipelines. arXiv preprint arXiv:1906.08172.
    Lundberg, S. M., & Lee, S.-I. (2017). A unified approach to interpreting model predictions. Advances in neural information processing systems, 30.
    Madsen, A., Reddy, S., & Chandar, S. (2022). Post-hoc interpretability for neural nlp: A survey. ACM Computing Surveys, 55(8), 1-42.
    Miller, T. (2019). Explanation in artificial intelligence: Insights from the social sciences. Artificial intelligence, 267, 1-38.
    Mubashir, M., Shao, L., & Seed, L. (2013). A survey on fall detection: Principles and approaches. Neurocomputing, 100, 144-152.
    Pawar, U., O'Shea, D., Rea, S., & O'Reilly, R. (2020, December). Incorporating Explainable Artificial Intelligence (XAI) to aid the Understanding of Machine Learning in the Healthcare Domain. In Aics (pp. 169-180).
    Perry, J. T., Kellog, S., Vaidya, S. M., Youn, J. H., Ali, H., & Sharif, H. (2009, December). Survey and evaluation of real-time fall detection approaches. In 2009 6th International Symposium on High Capacity Optical Networks and Enabling Technologies (HONET) (pp. 158-164). IEEE.
    Queralta, J. P., Gia, T. N., Tenhunen, H., & Westerlund, T. (2019, July). Edge-AI in LoRa-based health monitoring: Fall detection system with fog computing and LSTM recurrent neural networks. In 2019 42nd international conference on telecommunications and signal processing (TSP) (pp. 601-604). IEEE.
    Ribeiro, M. T., Singh, S., & Guestrin, C. (2016, August). " Why should i trust you?" Explaining the predictions of any classifier. In Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining (pp. 1135-1144).
    Rota Bulo, S., & Kontschieder, P. (2014). Neural decision forests for semantic image labelling. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 81-88).
    Rougier, C., Meunier, J., St-Arnaud, A., & Rousseau, J. (2011). Robust video surveillance for fall detection based on human shape deformation. IEEE Transactions on circuits and systems for video Technology, 21(5), 611-622.
    Srinivasu, P. N., Sandhya, N., Jhaveri, R. H., & Raut, R. (2022). From blackbox to explainable AI in healthcare: existing tools and case studies. Mobile Information Systems, 2022, 1-20.
    World Health Organization. (2021). Falls. Retrieved Oct 20, 2023 from https://www.who.int/news-room/fact-sheets/detail/falls
    Wu, Y., Zhang, L., Bhatti, U. A., & Huang, M. (2023). Interpretable Machine Learning for Personalized Medical Recommendations: A LIME-Based Approach. Diagnostics, 13(16), 2681.
    Yang, Y., Morillo, I. G., & Hospedales, T. M. (2018). Deep neural decision trees. arXiv preprint arXiv:1806.06988.
    Zhuang, X.-Y. (2019). Black Box or White Box? A Hybrid Approach for Predicting and Interpreting Customer Demands in SCM https://hdl.handle.net/11296/9639td
    Zilke, J. R., Loza Mencía, E., & Janssen, F. (2016). Deepred–rule extraction from deep neural networks. In Discovery Science: 19th International Conference, DS 2016, Bari, Italy, October 19–21, 2016, Proceedings 19 (pp. 457-473). Springer International Publishing.
    描述: 碩士
    國立政治大學
    資訊管理學系
    111356040
    資料來源: http://thesis.lib.nccu.edu.tw/record/#G0111356040
    数据类型: thesis
    显示于类别:[資訊管理學系] 學位論文

    文件中的档案:

    档案 描述 大小格式浏览次数
    604001.pdf7560KbAdobe PDF0检视/开启


    在政大典藏中所有的数据项都受到原著作权保护.


    社群 sharing

    著作權政策宣告 Copyright Announcement
    1.本網站之數位內容為國立政治大學所收錄之機構典藏,無償提供學術研究與公眾教育等公益性使用,惟仍請適度,合理使用本網站之內容,以尊重著作權人之權益。商業上之利用,則請先取得著作權人之授權。
    The digital content of this website is part of National Chengchi University Institutional Repository. It provides free access to academic research and public education for non-commercial use. Please utilize it in a proper and reasonable manner and respect the rights of copyright owners. For commercial use, please obtain authorization from the copyright owner in advance.

    2.本網站之製作,已盡力防止侵害著作權人之權益,如仍發現本網站之數位內容有侵害著作權人權益情事者,請權利人通知本網站維護人員(nccur@nccu.edu.tw),維護人員將立即採取移除該數位著作等補救措施。
    NCCU Institutional Repository is made to protect the interests of copyright owners. If you believe that any material on the website infringes copyright, please contact our staff(nccur@nccu.edu.tw). We will remove the work from the repository and investigate your claim.
    DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library IR team Copyright ©   - 回馈