請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/103607完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 曾宇鳳 | zh_TW |
| dc.contributor.advisor | Yufeng Jane Tseng | en |
| dc.contributor.author | 許漢強 | zh_TW |
| dc.contributor.author | Dwayne Reinaldy | en |
| dc.date.accessioned | 2026-08-18T17:12:35Z | - |
| dc.date.available | 2026-08-19 | - |
| dc.date.copyright | 2026-08-18 | - |
| dc.date.issued | 2026 | - |
| dc.date.submitted | 2026-07-30 00:00:00 | - |
| dc.identifier.citation | O. Waln and J. Jankovic. An update on tardive dyskinesia: From phenomenology to treatment. Tremor and Other Hyperkinetic Movements, 3, 2013.
E. M. Cornett, M. Novitch, A. D. Kaye, V. O. Kata, and A. M. Kaye. Medication-induced tardive dyskinesia: A review and update. Ochsner Journal, 17(2):162–174, 2017. R. Bhidayasiri, O. Jitkritsadakul, J. H. Friedman, and S. Fahn. Updating the recommendations for the treatment of tardive dyskinesia: A systematic review. Journal of the Neurological Sciences, 387:119–130, 2018. A. Faurbye, P. J. Rasch, P. B. Petersen, G. Brandborg, and H. Pakkenberg. Neurological symptoms in pharmacotherapy of psychosis. Acta Psychiatrica Scandinavica, 40(1):10–27, 1964. J. Lieberman, S. Pollack, M. Lesser, and J. Kane. Pharmacologic characterization of tardive dyskinesia. Journal of Clinical Psychopharmacology, 8(4):254–260, 1988. N. R. Schooler and J. M. Kane. Research diagnoses for tardive dyskinesia. Archives of General Psychiatry, 39(4):486–487, 1982. D. E. Casey. Tardive dyskinesia. The Western Journal of Medicine, 153(5):535–541, 1990. D. V. Jeste and M. P. Caligiuri. Tardive Dyskinesia. Schizophrenia Bulletin, 19(2):303–315, 1993. W. M. Glazer. Expected incidence of tardive dyskinesia associated with atypical antipsychotics. The Journal of Clinical Psychiatry, 61(Suppl. 4):21–26, 2000. M. R. Munetz and S. Benjamin. The abnormal involuntary movement scale (aims) and the evaluation of tardive dyskinesia. Psychopharmacology Bulletin, 24(3):425–428, 1988. S. Hawthorne et al. Tardive dyskinesia: A review of the literature and clinical practice considerations. Neuropsychiatric Disease and Treatment, 14:177–192, 2018. J. M. Kane, C. U. Correll, M. Sajatovic, et al. Revisiting the use of the abnormal involuntary movement scale in tardive dyskinesia: Consensus perspectives on clinical use and limitations. The Journal of Clinical Psychiatry, 2021. K. Griffiths, Y. Won, Z. Lee, L. Wang, C. U. Correll, and R. Patel. Identifying the diagnostic gap of tardive dyskinesia: An analysis of semi-structured electronic health record data. BMC Psychiatry, 25(1):407, 2025. R. A. Hauser, S. A. Factor, S. R. Marder, M. A. Knesevich, P. M. Ramirez, R. Jimenez, J. Burke, G. S. Liang, and C. F. O'Brien. Kinect 3: a phase 3 randomized, double-blind, placebo-controlled trial of valbenazine for tardive dyskinesia. American Journal of Psychiatry, 174(5):476–484, 2017. K. E. Anderson, D. Stamler, M. D. Davis, S. A. Factor, R. A. Hauser, J. Isojarvi, and J. Jimenez-Shahed. Deutetrabenazine for tardive dyskinesia: a randomized, double-blind, placebo-controlled, 12-week trial. The Lancet Neurology, 16(6):443–452, 2017. B. R. Gerratt, C. G. Goetz, and R. S. Fisher. Speech abnormalities in tardive dyskinesia: timing and phonatory disruption. Journal of Speech and Hearing Disorders, 49, 1984. M. Laporta, D. Archambault, A. Ross-Chouinard, and G. Chouinard. Articulatory impairment associated with tardive dyskinesia. Journal of Nervous and Mental Disease, 178(10):660–662, 1990. A. Khan et al. Speech impairment in tardive dyskinesia and its relationship to clinical severity. Movement Disorders, 9, 1994. T. H. Ngo, M. A. Hossain, X. Pu, and T. Ngo. Machine learning applications for diagnosing parkinson's disease via speech, language, and voice changes: A systematic review. Digital Health Informatics, 10(4):48–62, 2026. B. E. Sakar, M. E. Isenkul, C. O. Sakar, A. Sertbas, F. Gurgen, S. Delil, H. Astepi, and O. Kursun. Collection and analysis of a parkinson's disease speech dataset using multiple types of sound recordings. IEEE Journal of Biomedical and Health Informatics, 23(1):324–334, 2019. J. C. Suarez-Escudero, A. Martinez, I. Torres, and R. Smith. Dysarthria and speech characteristics as digital biomarkers in amyotrophic lateral sclerosis: A systematic scoping review. Neurología (English Edition), 36(8):612–621, 2021. Z. Wang, W. Zhi, Y. Lin, X. Chen, and Y. Liu. Speech digital biomarker combined with fluid biomarkers predict cognitive impairment through machine learning. Alzheimer's Research & Therapy, 17(1):1–14, 2025. Y. Wang and D. Askounis. Machine learning approaches for speech-based alzheimer's detection: A comprehensive survey. Computational Intelligence Review, 14(2):36–55, 2024. A. A. Sterns, J. W. Hughes, B. Grimm, L. Larsen, F. Ma, R. Ranjan, C. MacMillan, B. H. Talbot, J. H. Friedman, and O. S. Muir. Detecting tardive dyskinesia using video-based artificial intelligence. Journal of Clinical Psychiatry, 86(3):25m15792, 2025. T. L. Liu, K. A. Lee, Q. Wang, and H. Li. Disentangling voice and content with self-supervision for speaker recognition. In Proceedings of the 37th International Conference on Neural Information Processing Systems (NeurIPS), 2023. G. Retsinas, P. P. Filntisis, R. Danecek, V. F. Abrevaya, A. Roussos, T. Bolkart, and P. Maragos. 3d facial expressions through analysis-by-neural-synthesis. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024. W. Guy. Abnormal involuntary movement scale (aims). In ECDEU Assessment Manual for Psychopharmacology, pages 534–537. National Institute of Mental Health, 1976. A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, Ł. Kaiser, and I. Polosukhin. Attention is all you need. Advances in Neural Information Processing Systems, 30:5998–6008, 2017. M. A. Little, P. E. McSharry, E. J. Hunter, J. Spielman, and L. O. Ramig. Suitability of dysphonia measurements for telemonitoring of Parkinson's disease. IEEE Transactions on Biomedical Engineering, 56(4):1015–1022, 2009. A. Tsanas, M. A. Little, P. E. McSharry, and L. O. Ramig. Nonlinear speech analysis algorithms mapped to a standard metric achieve clinically useful quantification of average Parkinson's disease symptom severity. Journal of The Royal Society Interface, 8(59):842–855, 2011. N. Cummins, S. Scherer, J. Krajewski, S. Schnieder, J. Epps, and T. F. Quatieri. A review of depression and suicide risk assessment using speech analysis. Speech Communication, 71:10–49, 2015. K. Kaczmarek-Majer, M. Dominiak, A. Z. Antosik, et al. Acoustic features from speech as markers of depressive and manic symptoms in bipolar disorder: A prospective study. Acta Psychiatrica Scandinavica, 151(3):358–374, 2025. P. Boersma and D. Weenink. Praat, a system for doing phonetics by computer. Glot International, 5(9/10):341–345, 2001. F. Eyben, M. Wöllmer, and B. Schuller. opensmile: the munich versatile and fast open-source audio feature extractor. In Proceedings of the 18th ACM International Conference on Multimedia, pages 1459–1462, 2010. B. McFee, C. Raffel, D. Liang, D. P. W. Ellis, M. McVicar, E. Battenberg, and O. Nieto. librosa: Audio and music signal analysis in python. In Proceedings of the 14th Python in Science Conference, volume 8, pages 18–25, 2015. J. C. Vásquez-Correa, J. Fritsch, J. R. Orozco-Arroyave, E. Nöth, and M. Magimai-Doss. On modeling glottal source information for phonation assessment in parkinson's disease. In Interspeech 2021, pages 26–30, 2021. S. Hawi, J. Alhozami, R. AlQahtani, D. AlSafran, M. Alqarni, and L. El Sahmarany. Automatic parkinson's disease detection based on the combination of long-term acoustic features and mel frequency cepstral coefficients (mfcc). Biomedical Signal Processing and Control, 78:104013, 2022. A. Suppa, G. Costantini, F. Asci, P. Di Leo, M. S. Al-Wardat, G. Di Lazzaro, S. Scalise, A. Pisani, and G. Saggio. Voice in parkinson's disease: A machine learning study. Frontiers in Neurology, 13:831428, 2022. H. Choi, J. Park, S. Kim, and H. Lee. Detecting parkinson's disease using multiscale features from short-duration speech segments. In Proceedings of the Annual Conference of the International Speech Communication Association (Interspeech), pages 5278–5282, 2025. J. C. Vásquez-Correa, J. R. Orozco-Arroyave, and E. Nöth. Effect of acoustic conditions on algorithms to detect parkinson's disease from speech. In 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pages 5065–5069, 2017. L. Jeancolas, D. Petrovska-Delacrétaz, B. E. Benkelfat, G. Mangone, J. C. Corvol, M. Vidailhet, and A. L. Fowler. Comparison of five different front-end systems for automatic parkinson's disease detection through voice. In Proceedings of the Annual Conference of the International Speech Communication Association (Interspeech), pages 4300–4304, 2019. M. Hireš, M. Gazda, and P. Drotár. Convolutional neural network ensemble for parkinson's disease detection from voice recordings. Computers in Biology and Medicine, 141:105021, 2022. K. Bhatt, M. Chandra, and R. K. Jaiswal. High-resolution superlet transform based techniques for parkinson's disease detection using speech signal. Applied Acoustics, 214:109657, 2023. M. B. Er, E. Işık, and I. Isik. Parkinson's detection based on combined cnn and lstm using enhanced speech signals with variational mode decomposition. Biomedical Signal Processing and Control, 70:103006, 2021. A. Dosovitskiy, L. Beyer, A. Kolesnikov, D. Weissenborn, X. Zhai, T. Unterthiner, M. Dehghani, M. Minderer, G. Heigold, S. Gelly, J. Uszkoreit, and N. Houlsby. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929, 2020. K. He, C. Gan, Z. Li, I. Rekik, Z. Yin, W. Ji, Y. Gao, Q. Wang, J. Zhang, and D. Shen. Transformers in medical image analysis: A review. arXiv preprint arXiv:2202.12165, 2022. C. Lugaresi, J. Tang, H. Nash, C. McClanahan, E. Uboweja, M. Somani, C. T. Zhang, M. Ground, V. Vezhnevets, V. Bazarevsky, J. Wang, and M. Grundmann. MediaPipe: A framework for building perception pipelines. arXiv preprint arXiv:1910.10088, 2019. Z. Cao, G. Hidalgo, T. Simon, S. E. Wei, and Y. Sheikh. OpenPose: Realtime multiperson 2D pose estimation using Part Affinity Fields. IEEE Transactions on Pattern Analysis and Machine Intelligence, 43(1):172–186, 2019. D. E. King. Dlib-ml: A machine learning toolkit. Journal of Machine Learning Research, 10:1755–1758, 2009. V. Blanz and T. Vetter. A morphable model for the synthesis of 3D faces. In Proceedings of the 26th Annual Conference on Computer Graphics and Interactive Techniques, pages 187–194, 1999. P. Paysan, R. Knothe, B. Amberg, S. Romdhani, and T. Vetter. A 3D face model for pose and illumination invariant face recognition. In IEEE International Conference on Advanced Video and Signal Based Surveillance, pages 296–301, 2009. Y. Feng, H. Feng, M. J. Black, and T. Bolkart. Learning an animatable detailed 3D face model from in-the-wild images. In ACM Transactions on Graphics (TOG), volume 40, pages 1–13, 2021. R. Daněček, M. J. Black, and T. Bolkart. EMOCA: Emotion driven monocular face capture and animation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 20311–20322, 2022. G. Song, J. Wang, S. Tripathy, and J. F. Cohn. Quantitative evaluation of facial palsy using local binary patterns and landmark kinematics. IEEE Transactions on Biomedical Engineering, 62(4):1092–1101, 2015. A. Bandini, J. R. Green, J. Wang, T. F. Campbell, and Y. Yunusova. Analysis of facial kinematics in Amyotrophic Lateral Sclerosis during speech and non-speech tasks. Journal of Speech, Language, and Hearing Research, 60(6):1512–1525, 2017. J. Wu, G. M. Schulz, S. Golaszewski, C. McRae, and J. Lightfoot. Facial kinematics in Parkinson's disease: A longitudinal assessment of expressive changes. Neurology and Clinical Neurophysiology, 14(2):85–94, 2014. T. Baltrušaitis, C. Ahuja, and L. P. Morency. Multimodal machine learning: A survey and taxonomy. IEEE Transactions on Pattern Analysis and Machine Intelligence, 41(2):423–443, 2018. D. Ramachandram and M. Scarloff. Deep multimodal learning: A survey on recent advances and trends. IEEE Signal Processing Magazine, 34(6):96–108, 2017. Y. H. H. Tsai, S. Bai, P. P. Liang, J. Z. Kolter, and L. P. Morency. Multimodal Transformer for unaligned multimodal language sequences. In Proceedings of the ACL Conference on Empirical Methods in Natural Language Processing, pages 6558–6569, 2019. T. Afouras, J. S. Chung, A. Senior, O. Vinyals, and A. Zisserman. Deep audio-visual speech recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 44(12):8717–8827, 2018. Y. Guo. A multimodal audiovisual deep learning framework for early detection of Parkinson's disease. Electronics, 13(9):1904, 2024. E. Tjoa and C. Guan. A survey on explainable artificial intelligence (XAI): Toward medical applications. IEEE Transactions on Neural Networks and Learning Systems, 32(11):4793–4813, 2020. Mukund Sundararajan, Ankur Taly, and Qiqi Yan. Axiomatic attribution for deep networks. In Proceedings of the 34th International Conference on Machine Learning, volume 70, pages 3319–3328. PMLR, 2017. F. M. Nilsson, B. L. Hansen, C. Büchel, W. F. Gattaz, and J. Gerlach. Digital movement analysis, a new objective method of measuring tardive dyskinesia and drug-induced parkinsonian tremor: acceptability, reliability and validity. European Archives of Psychiatry and Clinical Neuroscience, 246(2):71–77, 1996. H. Sedigh Malekroodi, B. I. Lee, and M. Yi. Voice-based detection of parkinson's disease using machine and deep learning approaches: A systematic review. Bioengineering, 12(11):1279, 2025. YouTube LLC. Youtube video repository. https://www.youtube.com, 2026. Journal of Clinical Psychiatry. Patients living with tardive dyskinesia: Expert-led video series. https://www.psychiatrist.com/jcp/patients/, 2024. A. Zhou, S. Li, P. Sriram, X. Li, J. Dong, A. Sharma, Y. Zhong, S. Luo, M. Jaromin, V. Kindratenko, G. Heintz, C. Zallek, and Y. X. Wang. Youtubepd: A multimodal benchmark for parkinson's disease analysis. In Proceedings of the 37th Conference on Neural Information Processing Systems (NeurIPS), 2023. S. Rouard, F. Massa, and A. Défossez. Hybrid transformers for music source separation. In Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2023. A. Défossez. Hybrid spectrogram and waveform source separation. In Proceedings of the ISMIR 2021 Workshop on Music Source Separation, 2021. E. Vincent, R. Gribonval, and C. Févotte. Performance measurement in blind audio source separation. IEEE Transactions on Audio, Speech, and Language Processing, 14(4):1462–1469, 2006. S. S. Stevens, J. Volkmann, and E. B. Newman. A scale for the measurement of the psychological magnitude pitch. The Journal of the Acoustical Society of America, 8(3):185–190, 1937. D. O'Shaughnessy. Speech communication: human and machine. Addison-Wesley, 1987. G. Jocher, J. Qiu, and A. Chaurasia. Ultralytics yolo. https://github.com/ultralytics/ultralytics, 2023. Y. He, C. Zhu, J. Wang, M. Savvides, and X. Zhang. Bounding box regression with uncertainty for accurate object detection. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 2888–2897, 2019. G. Deuschl, P. Bain, and M. Brin. Consensus statement of the movement disorder society on tremor. Movement Disorders, 13(S3):2–23, 1998. A. Howard, M. Sandler, G. Chu, L. C. Chen, B. Chen, M. Tan, W. Wang, Y. Zhu, R. Pang, V. Vasudevan, Q. V. Le, and H. Adam. Searching for mobilenetv3. arXiv preprint arXiv:1905.02244, 2019. O. Russakovsky, J. Deng, H. M. Su, J. Krause, S. Satheesh, S. Ma, Z. Huang, A. Karpathy, A. Khosla, M. Bernstein, A. C. Berg, and L. Fei-Fei. ImageNet Large Scale Visual Recognition Challenge. International Journal of Computer Vision (IJCV), 115(3):211–252, 2015. I. Loshchilov and F. Hutter. Decoupled weight decay regularization. In International Conference on Learning Representations (ICLR), 2019. A. K. Ho, R. Iansek, C. Maragliano, J. L. Bradshaw, and J. G. Phillips. Speech impairment in a large sample of patients with parkinson's disease. Behavioral Neurology, 11(3):131–137, 1998. S. Skodda, W. Grönheit, and U. Schlegel. Impairment of speech rate and rhythm in parkinson's disease. Journal of Neural Transmission, 118:1499–1507, 2011. R. B. Postuma, D. Berg, M. Stern, W. Poewe, C. W. Olanow, W. Oertel, J. Obeso, K. Marek, I. Litvan, A. E. Lang, et al. Mds clinical diagnostic criteria for parkinson's disease. Movement Disorders, 30(12):1591–1601, 2015. | - |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/103607 | - |
| dc.description.abstract | 遲發性運動障礙(Tardive Dyskinesia, TD)是一種由藥物引起的運動障礙,估計影響20%至30%接受長期抗精神病藥物治療的患者,但在臨床實踐中仍普遍存在診斷不足的問題。TD患者的言語障礙已被臨床記錄超過三十年,但目前尚無自動化系統用於分析TD患者的言語特徵。本論文提出了一種多模態機器學習框架,透過整合來自簡短、真實場景視訊錄製中的語音和面部分析,實現TD的自動化篩檢。該框架結合了基於解耦機制的音訊模組與3D面部運動學分析模組,並透過跨模態注意力機制將兩者連接,使兩種模態能夠動態互動。我們在包含80名受試者的資料集上評估了該框架,受試者分為三類:TD、帕金森病(Parkinson's Disease)和健康對照組,並採用受試者獨立的交叉驗證方法。該多模態模型在健康對照組與TD的二分類任務中取得了0.93的AUROC值,在三分類任務中取得了0.89的AUROC值,在所有任務中均持續優於僅使用面部或僅使用音訊的基線模型。我們還採用了可解釋人工智慧(Explainable AI, XAI)方法,以提供可解釋的預測結果,將模型的注意力機制與已知TD言語障礙相關的語音片段聯繫起來。總體而言,我們的研究填補了一個持續三十餘年的診斷空白,並朝著在真實臨床環境中實現客觀TD篩檢邁出了重要一步。 | zh_TW |
| dc.description.abstract | Tardive Dyskinesia (TD) is a medication-induced movement disorder affecting an estimated 20-30% of patients on long-term antipsychotic treatment, yet remains widely underdiagnosed in clinical practice. Speech impairment in TD has been clinically documented for over three decades, yet no automated system has been used for analyzing speech in TD. This thesis presents a multimodal machine learning framework for automated TD screening by integrating voice and facial analysis from brief, in-the-wild video recordings. The proposed framework combines a disentanglement mechanism-based audio module with a 3D facial kinematic analysis module connected via cross-modal attention, enabling the two modalities to interact dynamically. We evaluated this framework on a dataset of 80 subjects across three classes: TD, Parkinson's Disease, and healthy controls under subject-independent cross-validation. The multimodal model achieved an AUROC of 0.93 for healthy control versus TD discrimination and 0.89 for the three-class classification task, consistently outperforming the face and audio only baseline across all tasks. We also employed Explainable AI (XAI) to provide interpretable predictions, linking model attention to speech segments consistent with known speech impairments in TD. Overall, our work addresses a diagnostic gap that has persisted for over three decades and represents a step toward objective TD screening in real-world clinical settings. | en |
| dc.description.provenance | Submitted by admin ntu (admin@lib.ntu.edu.tw) on 2026-08-18T17:12:35Z No. of bitstreams: 0 | en |
| dc.description.provenance | Made available in DSpace on 2026-08-18T17:12:35Z (GMT). No. of bitstreams: 0 | en |
| dc.description.tableofcontents | Acknowledgements i
摘要 iii Abstract iv Contents vii List of Figures xi List of Tables xiii Denotation xiv Chapter 1 Introduction 1 Chapter 2 Literature Review 5 2.1 Clinical Assessment of TD 5 2.2 Clinical Background of Speech in Movement Disorders 7 2.2.1 Speech Impairment in TD 7 2.2.2 Speech as a Biomarker in Neurological Conditions 8 2.3 Automated Speech Analysis for Neurological Disorders 9 2.3.1 Handcrafted Acoustic Features 9 2.3.2 CNN-Based Approaches 10 2.3.3 Transformer-Based Approaches 11 2.3.4 Speaker Disentanglement for Pathological Speech Analysis 12 2.4 Automated Facial Movement Analysis 12 2.5 Multimodal Learning 14 2.6 Explainable AI (XAI) 15 2.7 Automated TD Detection 16 2.8 Summary and Research Gap 18 Chapter 3 Materials and Methods 20 3.1 Study Design and Data Sources 20 3.1.1 Overview of Dataset 20 3.1.2 Self-Curated TD Dataset 20 3.1.3 Benchmark Data (PD & HC) 21 3.1.4 Dataset Distribution and Statistics 22 3.1.5 Clinician-Verified TD Subset 22 3.2 Data Preprocessing 23 3.2.1 Audio Preprocessing 24 3.2.1.1 Acoustic Source Separation and Vocal Signal Isolation 24 3.2.1.2 Temporal Windowing and Multi-Resolution Short-Time Fourier Transform 25 3.2.1.3 Perceptual Mel Scaling and Compression 27 3.2.2 Video Preprocessing 29 3.2.2.1 Object Detection and ROI Tracking 30 3.2.2.2 Spatio-Temporal Normalization 31 3.3 Model Architecture 32 3.3.1 Audio Feature Extraction 33 3.3.1.1 Backbone Feature Extraction 33 3.3.1.2 Disentanglement Mechanism 36 3.3.1.3 Integration of the Audio Outputs 40 3.3.2 Visual Feature Extraction 41 3.3.2.1 SMIRK Model for 3D Face Reconstruction 41 3.3.2.2 Anatomical Region Selection and Kinematic Feature Engineering 42 3.3.2.3 Visual Projection Head 45 3.3.3 Cross-Attention Interaction 46 3.3.4 Fusion and Classification 47 Chapter 4 Results 49 4.1 Experimental Setup 49 4.1.1 Training Environment and Framework 49 4.1.2 Subject-Independent Cross Validation 49 4.1.3 Optimization and Hyperparameters 50 4.2 Evaluation Metrics 51 4.3 Results and Discussions 54 4.3.1 Multimodal Performance and Task-Specific Evaluation 54 4.3.2 Comparative Analysis of Unimodal and Multimodal Diagnostic Performance 55 4.3.3 Explainable AI (XAI): Integrated Gradients 61 4.3.4 Supplementary Analysis: Clinician-Verified TD Subset 62 4.3.5 Comparison to Sterns et al. (2025) 66 4.4 Limitations and Future Direction of Our Work 68 4.4.1 Limitations 68 4.4.2 Future Work 69 Chapter 5 Conclusion 71 References 73 Appendices 85 1.1 Self-Curated Dataset Resource Mapping 85 | - |
| dc.language.iso | en | - |
| dc.subject | 遲發性運動障礙 | - |
| dc.subject | 自動化篩查 | - |
| dc.subject | 語音生物標記 | - |
| dc.subject | 多模態機器學習 | - |
| dc.subject | 三維臉部分析 | - |
| dc.subject | 說話者解纏 | - |
| dc.subject | 可解釋人工智慧 | - |
| dc.subject | Tardive Dyskinesia | - |
| dc.subject | Automated Screening | - |
| dc.subject | Speech Biomarker | - |
| dc.subject | Multimodal Machine Learning | - |
| dc.subject | 3D Facial Analysis | - |
| dc.subject | Speaker Disentanglement | - |
| dc.subject | Explainable AI | - |
| dc.title | 遲發性運動障礙辨識之多模態機器學習框架：基於語 音與臉部動作分析 | zh_TW |
| dc.title | A Multimodal Machine Learning Framework for Distinguishing Tardive Dyskinesia via Voice and Facial Movement Analysis | en |
| dc.type | Thesis | - |
| dc.date.schoolyear | 114-2 | - |
| dc.description.degree | 碩士 | - |
| dc.contributor.oralexamcommittee | 郭昇翰;黃名琪;劉智民;施吉昇 | zh_TW |
| dc.contributor.oralexamcommittee | Sheng-Han Kuo;Ming-Chyi Huang;Chih-Min Liu;Chi-Sheng Shih | en |
| dc.subject.keyword | 遲發性運動障礙; 自動化篩查; 語音生物標記; 多模態機器學習; 三維臉部分析; 說話者解纏; 可解釋人工智慧 | zh_TW |
| dc.subject.keyword | Tardive Dyskinesia; Automated Screening; Speech Biomarker; Multimodal Machine Learning; 3D Facial Analysis; Speaker Disentanglement; Explainable AI | en |
| dc.relation.page | 86 | - |
| dc.identifier.doi | 10.6342/NTU202602120 | - |
| dc.rights.note | 同意授權(全球公開) | - |
| dc.date.accepted | 2026-08-03 | - |
| dc.contributor.author-college | 共同教育中心 | - |
| dc.contributor.author-dept | 智慧醫療與健康資訊碩士學位學程 | - |
| dc.date.embargo-lift | 2026-08-19 | - |
| 顯示於系所單位： | 智慧醫療與健康資訊碩士學位學程 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| ntu-114-2.pdf | 5.17 MB | Adobe PDF | 檢視/開啟 |
系統中的文件，除了特別指名其著作權條款之外，均受到著作權保護，並且保留所有的權利。