請用此 Handle URI 來引用此文件:
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/91161
完整後設資料紀錄
DC 欄位 | 值 | 語言 |
---|---|---|
dc.contributor.advisor | 宋孔彬 | zh_TW |
dc.contributor.advisor | Kung-Bin Sung | en |
dc.contributor.author | 孫欽鉉 | zh_TW |
dc.contributor.author | Chin-Hsuan Sun | en |
dc.date.accessioned | 2023-11-20T16:12:25Z | - |
dc.date.available | 2023-11-21 | - |
dc.date.copyright | 2023-11-20 | - |
dc.date.issued | 2023 | - |
dc.date.submitted | 2023-10-17 | - |
dc.identifier.citation | [1] Philip Bickler and Kevin K Tremper. The pulse oximeter is amazing, but not perfect, 2022.
[2] Yitzhak Mendelson. Pulse oximetry: theory and applications for noninvasive monitoring. Clinical chemistry, 38(9):1601–1607, 1992. [3] BART G Denys and BARRY F Uretsky. Anatomical variations of internal jugular vein location: impact on central venous access. Critical care medicine, 19(12):1516, 1519, 1991. [4] NinoStocchetti, Alessandro Paparella, Franca Bridelli, Marisa Bacchi, Paolo Piazza, and Paolo Zuccoli. Cerebral venous oxygen saturation studied with bilateral samples in the internal jugular veins. Neurosurgery, 34(1):38–44, 1994. [5] RohitSLoomba,JacquelineRausa,DanielleSheikholeslami, AaronEDyson,JuanS Farias, Enrique G Villarreal, Saul Flores, and Ronald A Bronicki. Correlation of near-infrared spectroscopy oximetry and corresponding venous oxygen saturations in children with congenital heart disease. Pediatric cardiology, 43(1):197–206, 2022. [6] Chetana Shanmukhappa and Srivatsa Lokeshwaran. Venous oxygen saturation. 2020. [7] Jaromir Richter, Peter Sklienka, Nilay Chatterjee, Jan Maca, Roman Zahorec, and Michal Burda. Elevated jugular venous oxygen saturation after cardiac arrest. Resuscitation, 169:214–219, 2021. [8] David C. McGee and Michael K. Gould. Preventing complications of central venous catheterization. New England Journal of Medicine, 348(12):1123–1133, 2003. PMID: 12646670. [9] Zsolt Molnar, Andreas Umgelter, Ildiko Toth, David Livingstone, Andreas Weyland, Samir G Sakka, and Andreas Meier-Hellmann. Continuous monitoring of scvo2 by a new fibre-optic technology compared with blood gas oximetry in critically ill patients: a multicentre study. Intensive care medicine, 33:1767 1770, 2007. [10] Philip Tan, Shreya Tamma, Sarnab Bhattacharya, James Tunnell, and Nanshu Lu. Wearable optical e-tattoo for deep neck hemodynamic monitoring. In 2022 IEEE/ACM Conference on Connected Health: Applications, Systems and Engineering Technologies (CHASE), pages 118–122. IEEE, 2022. [11] Mark AHBMvanderHoeven,WielJMaertzdorf, and Carlos E Blanco. Continuous central venous oxygen saturation (scvo2) measurement using a fibre optic catheter in newborn infants. Archives of Disease in Childhood-Fetal and Neonatal Edition, 74(3):F177–F181, 1996. [12] Ingemar Fredriksson, Marcus Larsson, and Tomas Strömberg. Machine learning for direct oxygen saturation and hemoglobin concentration assessment using diffuse reflectance spectroscopy. Journal of Biomedical Optics, 25(11):112905–112905, 2020. [13] Taweevat Assavapokee and Kunlawat Thadanipon. Examination of the neck veins. NewEngland Journal of Medicine, 383(24):e132, 2020. PMID: 33296562. [14] 高子佳. 以連續波近紅外光譜與三維模型定量人體腦部光學參數. Master’s thesis, 國立臺灣大學,Jan 2021. [15] Alex Bielajew. Fundamentals of the monte carlo method for neutral and charged particle transport. 10 2001. [16] Lihong Wang, Steven L. Jacques, and Liqiong Zheng. Mcml—monte carlo modeling of light transport in multi-layered tissues. Computer Methods and Programs in Biomedicine, 47(2):131–146, 1995. [17] B. C. Wilson and G. Adam. A Monte Carlo model for the absorption and flux distributions of light in tissue. Med Phys, 10(6):824–830, 1983. [18] Sri Lanka, Pranav Lanka, Lin Yang, David Orive-Miguel, Joshua Deepak V, Susanna Tagliabue, Aleh Sudakou, Saeed Samaei, MarioForcione, Zuzana Kovacsova, Anurag Behera, Thomas Gladytz, Dirk Grosenick, Lionel Hervé, Giuseppe Presti, Lorenzo Cortese, Turgut Durduran, Karolina Bejm, Magdalena Morawiec, and Antonio Pifferi. A multi-laboratory comparison of photon migration instruments and their performances–the bitmap exercise. page 11, 03 2021. [19] D. F. Swinehart. The beer-lambert law. Journal of Chemical Education, 39(7):333, 1962. [20] Julien Nou, Rémi Chauvin, Stéphane Thil, and Stéphane Grieu. A new approach to the real-time assessment of the clear-sky direct normal irradiance. Applied Mathematical Modelling, 40, 03 2016. [21] T Binzoni, T S Leung, A H Gandjbakhche, D Rüfenacht, and D T Delpy. The use of the henyey–greenstein phase function in monte carlo simulations in biomedical optics. Physics in Medicine Biology, 51(17):N313, aug 2006. [22] Valery Tuchin. Light interaction with biological tissues: overview. Proceedings of SPIE- The International Society for Optical Engineering, 07 1993. [23] QianqianFangandDavidA.Boas. Monte carlo simulation of photon migration in 3d turbid media accelerated by graphics processing units. Opt. Express, 17(22):20178 20190, Oct 2009. [24] R. Graaff, M. H. Koelink, F. F. M. de Mul, W. G. Zijlstra, A. C. M. Dassel, and J. G. Aarnoudse. Condensedmontecarlosimulations for the description of light transport. Appl. Opt., 32(4):426–434, Feb 1993. [25] Antonio Pifferi, Paola Taroni, Gianluca Valentini, and Stefan Andersson-Engels. Real-time method for fitting time-resolved reflectance and transmittance measurements with a monte carlo model. Applied optics, 37(13):2774–2780, 1998. [26] Antonio Pifferi, Roger Berg, Paola Taroni, and Stefan Andersson-Engels. Fitting of time-resolved reflectance curves with a monte carlo model. In Advances in optical imaging and photon migration, page RIA311. Optica Publishing Group, 1996. [27] Erik Alerstam, Stefan Andersson-Engels, and Tomas Svensson. White monte carlo for time-resolved photon migration. Journal of biomedical optics, 13(4):041304 041304, 2008. [28] Erik Alerstam, Tomas Svensson, and Stefan Andersson-Engels. Parallel computing with graphics processing units for high-speed monte carlo simulation of photon migration. Journal of biomedical optics, 13(6):060504–060504, 2008. [29] Felix Gremse, Andreas Höfter, Lars Ole Schwen, Fabian Kiessling, and Uwe Nau mann. Gpu-accelerated sparse matrix-matrix multiplication by iterative row merging. SIAM Journal on Scientific Computing, 37(1):C54–C71, 2015. [30] AayushShah, RushikeshBedagkar, andAmitJoshi. Cupy: Abriefoverview. Jaypee University of Engineering and Technology, Raghogarh, Guna (MP), page 8. [31] Rukshan Pramoditha. The concept of artificial neurons (perceptrons) in neural networks. https://towardsdatascience.com/the-concept-of-artificial-neurons-perceptrons-in-neural-networks-fab22249cbfc. [32] KarishmaGupta. Opengenusiq: Computingexpertise legacy-hiddenlayers. https://iq.opengenus.org/hidden-layers/. [33] Crypto1. How does the gradient descent algorithm work in machine learning? https://www.analyticsvidhya.com/blog/2020/10/how-does-the-gradient-descent-algorithm-work-in-machine-learning/. [34] Yu-Chiang Frank Wang and Hung-Yi Lee. NTU course: Deep Learning for Computer Vision (COMME5052). [35] 10 程式中. [day 26] 交叉驗證k-fold cross-validation. https://ithelp.ithome.com.tw/articles/10279240. [36] Hao Tong, Changwu Huang, Leandro L Minku, and Xin Yao. Surrogate models in evolutionary single-objective optimization: A new taxonomy and experimental study. Information Sciences, 562:414–437, 2021. [37] ShivaNejati, LevSorokin, DamirSafin, FedericoFormica, MohammadMahdiMah boob, and Claudio Menghi. Reflections on surrogate-assisted search-based testing: Ataxonomy and two replication studies based on industrial adas and simulink models. Information and Software Technology, page 107286, 2023. [38] Claudio Menghi, Shiva Nejati, Lionel Briand, and Yago Isasi Parache. Approximation-refinement testing of compute-intensive cyber-physical models: An approach based on system identification. In Proceedings of the ACM/IEEE 42nd International Conference on Software Engineering, pages 372–384, 2020. [39] Chiao-Yi Wang, Tzu-Chia Kao, Yin-Fu Chen, Wen-Wei Su, Hsin-Jou Shen, and Kung-Bin Sung. Validation of an inverse fitting method of diffuse reflectance spectroscopy to quantify multi-layered skin optical properties. In Photonics, volume 6, page 61. MDPI, 2019. [40] Tzu-Chia Kao and Kung-Bin Sung. Quantifying tissue optical properties of human heads in vivo using continuous-wave near-infrared spectroscopy and subject specific three-dimensional monte carlo models. Journal of Biomedical Optics, 27(8):083021–083021, 2022. [41] QingLan,KarthikVishwanath,etal. Neuralnetwork-basedinversemodelfordiffuse reflectance spectroscopy. 2023. [42] MahmutOzanGökkanandMehmetEngin. Artificial neural networks based estimation of optical parameters by diffuse reflectance imaging under in vitro conditions. Journal of Innovative Optical Health Sciences, 10(01):1650027, 2017. [43] Hung-Yi Lee. NTU Lecture : Maching Learning. [44] 陳胤甫. 內頸靜脈血氧飽和度可攜式量測系統的開發與建立. Master’sthesis, 國立臺灣大學,Jan2020. [45] 詹朝舜. 以逆向白蒙地卡羅法分析模擬資料及人體大腦實驗尋找功能性近紅外線光譜技術之最佳化波長組合.Master’sthesis,國立臺灣大學,Jan2018. [46] Scott A Prahl, Martin JC van Gemert, and Ashley J Welch. Determining the optical properties of turbid media by using the adding–doubling method. Applied optics, 32(4):559–568, 1993. [47] Qianqian Fang and David A Boas. Monte carlo simulation of photon migration in 3d turbid media accelerated by graphics processing units. Optics express, 17(22):20178–20190, 2009. [48] Li-Da Huang, Tzu-Chia Kao, Kung-Bin Sung, and Jacob A Abraham. Simulation study on the optimization of photon energy delivered to the prefrontal cortex in low level-light therapy using red to near-infrared light. IEEE Journal of Selected Topics in Quantum Electronics, 27(4):1–10, 2021. [49] 謝昕原. 以近紅外光譜及類神經網路定量內頸靜脈血氧飽和度變化量. Master’s thesis, 國立臺灣大學, Aug 2022. [50] Emmanuel Boss, Marc Picheral, Thomas Leeuw, Alison Chase, Eric Karsenti, Gabriel Gorsky, L. Taylor, Wayne Slade, Joséphine Ras, and Hervé Claustre. The characteristics of particulate absorption, scattering and attenuation coefficients in the surface ocean; contribution of the tara oceans expedition. Methods in Oceanography, 7:52–62, 09 2013. [51] Andreas M Brandmaier, Elisabeth Wenger, Nils C Bodammer, Simone Kühn, Naftali Raz, and Ulman Lindenberger. Assessing reliability in neuroimaging research through intra-class effect decomposition(iced). Elife, 7:e35718, 2018. | - |
dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/91161 | - |
dc.description.abstract | 本研究的主要目標在於透過近紅外光譜量測技術,以非侵入式的方式定量人體內頸靜脈血氧飽和度變化量,首先透過基於類神經網路的代理模型對傳統組織光學模擬所使用的蒙地卡羅法進行加速,接著應用類神經網路建立血氧飽和度變化量預測模型,其輸入為經由公式萃取出光譜特徵的特徵光譜,輸出為血氧飽和度變化量。
在實體量測系統上,本研究使用20個波長點根據血液的吸收光譜特徵設立,波長範圍介在700nm~850nm之間,並且建立雙通道系統,短通道的部分,光源與偵測器的距離為10mm,長通道的部分,光源與偵測器的距離為20mm,透過這樣的設計能夠有效降地淺層組織的影響並且放大深層組織及內頸靜脈所在的區域的訊號。在模擬測試時是基於受試者的頸部超音波影像建立的三維數值模型,讓模擬結果能與現實更加貼近,得到更加準確的模擬資料。 本研究所建立的預測模型根據模擬結果,預測出內頸靜脈的血氧飽和度變化量其RMSE<1.5%。模型效能的評估上,本研究對人體呼吸造成內頸靜脈管徑大小與深度改變、周遭組織血氧變化、量測訊號產生的誤差等等,對於預測模型產生的影響進行了實驗與調查,結果顯示呼吸造成的影響最大可能造成3%~4%的方均根誤差(root-mean-square error, RMSE)的上升,而周遭組織血氧的變化對於預測模型的預測效能影響並不顯著,最多只會有1%的RMSE上升,而若是量測到的訊號受到誤差影響,則會造成1%~2%的RMSE上升。 模型泛用化上,本研究透過遷移學習的方式進行模擬實驗,經由實驗觀察發現,使用與原先資料相比僅佔千分之一的資料集透過遷移學習的方式能夠得到RMSE=3.5% 的結果,而若是不使用遷移學習單純使用千分之一的資料集則會得到RMSE=7%的結果。 在活體實驗上,將活體量測到的漫反射光譜,根據本實驗所設計的公式萃取出其光譜特徵後經由適當的標準化後,輸入至預測模型進行血氧飽和度變化量的預測,其預測結果與活體光譜觀察到的現象有一致性。 | zh_TW |
dc.description.abstract | The primary objective of this study is to quantitatively measure changes in internal jugular vein oxygen saturation non-invasively using near-infrared spectroscopy. Initially, a surrogate model based on neural networks is employed to accelerate the Monte Carlo method which is traditionally used to simulate photon transport in tissue. Subsequently, another neural network is applied to establish a predictive model for oxygen saturation changes. The input to this model consists of spectral features extracted using formulas same as modified Beer-Lambert law, while the output represents oxygen saturation changes.
As for the measurement system, the study utilizes 20 wavelength points based on the absorption spectra of blood, within the wavelength range of 700 nm to 850 nm. A dual channel system is set up, with the short channel having a distance of 10 mm between the light source and detector, and the long channel having a distance of 20 mm. This design effectively minimizes the impact of superficial tissues and enhances the signal from deeper tissues including the internal jugular vein area. During simulation, a three-dimensional numerical model is constructed based on ultrasound images of each subject’s neck, ensuring that simulation results closely resemble reality, thus providing more accurate simulated data. To evaluate the prediction model’s performance, the study investigates the impacts of factors such as human respiration, changes in oxygen levels in surrounding tissues, and measurement noise on the predictive model. The results indicate that the effects of respiration may lead to a maximum increase of 3% to 4% in root-mean-square error (RMSE). Changes in oxygen levels in surrounding tissues have a less significant impact, with a maximum RMSE increase of only 1%. Measurement signal errors can cause an RMSE increase of 1% to 2%. For model generalization, the study conducts simulated experiments using transfer learning. Through experimentation, it is observed that by using a thousandth of the original dataset and employing transfer learning, an RMSE of 3.5% can be achieved, while without transfer learning and using only a thousandth of the dataset, an RMSE of 7% is obtained. Based on the simulation results, the prediction model established in this study predicts changes in internal jugular vein oxygen saturation with an RMSE of less than 1.5%. In vivo experiments involve measuring diffuse reflectance spectra from living subjects, extracting spectral features using the formulas designed in this study, and inputting them into the prediction model after appropriate normalization. The prediction results are consistent with expected physiological response and spectral features in the measured data. | en |
dc.description.provenance | Submitted by admin ntu (admin@lib.ntu.edu.tw) on 2023-11-20T16:12:25Z No. of bitstreams: 0 | en |
dc.description.provenance | Made available in DSpace on 2023-11-20T16:12:25Z (GMT). No. of bitstreams: 0 | en |
dc.description.tableofcontents | 目錄
Page 口試委員審定書i 致謝iii 摘要v Abstract vii 目錄xi 圖目錄xv 表目錄xix 第一章緒論1 1.1研究背景. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1 1.2研究動機. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 4 1.3研究問題. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 5 1.3.1利用神經網路建立可靠的預測模型. . . . . . . . . . . . . . . . 6 1.3.2代理模型產生大量光譜資料. . . . . . . . . . . . . . . . . . . . 6 1.3.3預測模型泛用化. . . . . . . . . . . . . . . . . . . . . . . . . . . 6 第二章文獻回顧與理論介紹9 2.1頸部組織結構. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 9 2.2漫反射光譜. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 11 2.3蒙地卡羅演算法. . . . . . . . . . . . . . . . . . . . . . . . . . . . . 13 2.3.1蒙地卡羅模擬在光學中之應用. . . . . . . . . . . . . . . . . . . 14 2.3.1.1光子路徑長. . . . . . . . . . . . . . . . . . . . . . . 15 2.3.1.2光子行進方向. . . . . . . . . . . . . . . . . . . . . . 17 2.3.1.3光子能量. . . . . . . . . . . . . . . . . . . . . . . . 20 2.3.2白蒙地卡羅模擬. . . . . . . . . . . . . . . . . . . . . . . . . . . 22 2.4人工類神經網路. . . . . . . . . . . . . . . . . . . . . . . . . . . . . 25 2.4.1基本原理. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 25 2.4.2損失函數與梯度下降法. . . . . . . . . . . . . . . . . . . . . . . 27 2.4.3嵌套交叉驗證. . . . . . . . . . . . . . . . . . . . . . . . . . . . 28 2.4.4本研究之應用一:代理模型. . . . . . . . . . . . . . . . . . . . . 30 2.4.5本研究之應用二:預測模型. . . . . . . . . . . . . . . . . . . . . 32 2.5遷移學習. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 33 2.5.1基本原理. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 33 2.5.2本研究之應用. . . . . . . . . . . . . . . . . . . . . . . . . . . . 34 第三章研究方法設計37 3.1光學系統設計. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 37 3.2仿體校正. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 40 3.3漫反射光譜模擬工具. . . . . . . . . . . . . . . . . . . . . . . . . . 44 3.3.1模擬光源與偵測器. . . . . . . . . . . . . . . . . . . . . . . . . . 44 3.3.2建立組織模型. . . . . . . . . . . . . . . . . . . . . . . . . . . . 45 3.3.3光學參數設定. . . . . . . . . . . . . . . . . . . . . . . . . . . . 48 3.3.4代理模型產生光譜. . . . . . . . . . . . . . . . . . . . . . . . . . 49 3.4血氧預測模型. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 51 3.4.1訓練資料. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 52 3.4.1.1散射係數. . . . . . . . . . . . . . . . . . . . . . . . 52 3.4.1.2吸收係數. . . . . . . . . . . . . . . . . . . . . . . . 54 3.4.2光譜特徵萃取. . . . . . . . . . . . . . . . . . . . . . . . . . . . 56 第四章實驗結果與討論59 4.1代理模型驗證. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 59 4.1.1訓練資料穩定之分析. . . . . . . . . . . . . . . . . . . . . . . . 59 4.1.2代理模型表現之分析. . . . . . . . . . . . . . . . . . . . . . . . 60 4.2血氧預測模型驗證. . . . . . . . . . . . . . . . . . . . . . . . . . . . 62 4.2.1嵌套交叉驗證. . . . . . . . . . . . . . . . . . . . . . . . . . . . 62 4.2.2血氧預測模型表現之分析. . . . . . . . . . . . . . . . . . . . . . 64 4.2.3光譜特徵萃取分析. . . . . . . . . . . . . . . . . . . . . . . . . . 67 4.2.4光譜誤差影響. . . . . . . . . . . . . . . . . . . . . . . . . . . . 72 4.2.5肌肉血氧變化影響. . . . . . . . . . . . . . . . . . . . . . . . . . 74 4.2.6幾何結構變化影響. . . . . . . . . . . . . . . . . . . . . . . . . . 75 4.2.6.1內頸靜脈深度變化. . . . . . . . . . . . . . . . . . . 78 4.2.6.2內頸靜脈管徑變化. . . . . . . . . . . . . . . . . . . 79 4.2.7模型泛用化. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 80 4.3活體光譜分析. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 82 4.3.1實驗光譜前處理. . . . . . . . . . . . . . . . . . . . . . . . . . . 82 4.3.2過度換氣實驗. . . . . . . . . . . . . . . . . . . . . . . . . . . . 87 第五章結論與未來展望93 5.1結論. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 93 5.1.1代理模型加速. . . . . . . . . . . . . . . . . . . . . . . . . . . . 93 5.1.2預測模型模擬驗證. . . . . . . . . . . . . . . . . . . . . . . . . . 93 5.1.3活體實驗. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 94 5.2未來展望. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 94 5.2.1優化光譜特徵萃取方法. . . . . . . . . . . . . . . . . . . . . . . 94 5.2.2提升模擬資料的精準度. . . . . . . . . . . . . . . . . . . . . . . 95 5.2.3組織模型之改良. . . . . . . . . . . . . . . . . . . . . . . . . . . 95 5.2.4仿體實驗. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 96 參考文獻97 附錄A—模型參數表105 A.1代理模型. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 105 A.2相對血氧預測模型. . . . . . . . . . . . . . . . . . . . . . . . . . . . 105 | - |
dc.language.iso | zh_TW | - |
dc.title | 代理模型加速蒙地卡羅模擬及類神經網路定量內頸靜脈血氧變化量 | zh_TW |
dc.title | Accelerate Monte Carlo Simulation Based on Surrogate Model and Quantify Internal Jugular Vein by Using Artificial Neural Network | en |
dc.type | Thesis | - |
dc.date.schoolyear | 112-1 | - |
dc.description.degree | 碩士 | - |
dc.contributor.oralexamcommittee | 吳峻宇;許富舜 | zh_TW |
dc.contributor.oralexamcommittee | Chun-Yu Wu;Fu-Shun Hsu | en |
dc.subject.keyword | 漫反射光譜,內頸靜脈,血氧飽和度,蒙地卡羅演算法,代理模型,遷移學習,類神經網路, | zh_TW |
dc.subject.keyword | Diffuse Reflectance Spectroscopy,Internal Jugular Vein,Oxygen Saturation,Monte Carlo Algorithm,Surrogate Model,Transfer Learning,Artificial Neural Network, | en |
dc.relation.page | 105 | - |
dc.identifier.doi | 10.6342/NTU202304336 | - |
dc.rights.note | 同意授權(限校園內公開) | - |
dc.date.accepted | 2023-10-18 | - |
dc.contributor.author-college | 電機資訊學院 | - |
dc.contributor.author-dept | 生醫電子與資訊學研究所 | - |
顯示於系所單位: | 生醫電子與資訊學研究所 |
文件中的檔案:
檔案 | 大小 | 格式 | |
---|---|---|---|
ntu-112-1.pdf 目前未授權公開取用 | 39.52 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。