跳到主要內容

臺灣博碩士論文加值系統

(18.97.14.80) 您好!臺灣時間:2025/01/25 20:57
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果 :::

詳目顯示

我願授權國圖
: 
twitterline
研究生:李鎮宇
研究生(外文):Chen-Yu Li
論文名稱:應用於雙波段紅外線之乳癌檢測盲源分離演算法
論文名稱(外文):Application of Blind Source Separation Algorithms on Dual-band IR Spectrogram for Breast Cancer Detection
指導教授:陳少傑陳少傑引用關係
指導教授(外文):Sao-Jie Chen
口試委員:陳中平游竹林伯星
口試委員(外文):Chung-Ping ChenYu ChuBor-Shing Lin
口試日期:2016-06-25
學位類別:碩士
校院名稱:國立臺灣大學
系所名稱:電子工程學研究所
學門:工程學門
學類:電資工程學類
論文種類:學術論文
論文出版年:2016
畢業學年度:104
語文別:英文
論文頁數:46
中文關鍵詞:雙波段紅外線影像盲源分離演算法
外文關鍵詞:Dual-band IR SpectrogramBlind Source Separation Algorithm
相關次數:
  • 被引用被引用:0
  • 點閱點閱:164
  • 評分評分:
  • 下載下載:0
  • 收藏至我的研究室書目清單書目收藏:0
本論文提出一個針對雙波段紅外線頻譜(Dual-band IR Spectrogram),應用改良的盲源分離演算法(Blind Source Separation Algorithm)進行分析,來判定追蹤乳癌的長期化療之成效。本文採用雙波段紅外線頻譜的原始資料(RAW Data)為輸入檔,進行演算法分析,並針對盲源分離演算法的特性,在過程中運用資料分析進行改良,最後將該演算法加載至本實驗室開發的醫療控管處理器設計進行整合,提供我們一個更便利的管道來體現雙波段紅外線頻譜分析應用於醫療的成果。在標定率方面,該改良演算法設計比其他演算法平均高15%,在癌細胞判斷的正確率方面,該演算法設計比其他演算法平均高10%。

This work presents an application of Blind Source Separation (BSS) Algorithms on Dual-band IR Spectrogram for breast cancer detection, which is used to trace the effect of long-term chemotherapy for breast-cancer patients. We take Dual-band IR Spectrogram’s RAW Data as an input to the BSS algorithms. Also, we plan to integrate this analytical algorithm into the back-end processor of our designed Dual-band IR Sensor and Readout Circuit Platform. This work will provide a more convenient medical application of our Improved Neighbor-based BSS algorithm on Dual-band IR Spectrogram for breast cancer detection. For Demarcating Degree, our Improved Neighbor-based BSS algorithm is approximately 15% better than other algorithms. For Correctness Rate, our improved algorithm approximately increases 10% compared with other algorithms.

ABSTRACT i
TABLE OF CONTENTS iii
LIST OF FIGURES v
LIST OF TABLES vii
CHAPTER 1 INTRODUCTION 1
1.1 Motivation 1
1.2 Thesis Organization 2
CHAPTER 2 BACKGROUND 3
2.1 Dual-band IR Spectrogram 3
2.2 Blind Source Separation Algorithms 5
2.2.1 Single Pixel Blind Source Separation Algorithm 5
2.2.2 Neighbor-based Blind Source Separation Algorithm 7
2.3 Machine Learning Models 8
2.3.1 Supervised Learning and Unsupervised Learning 8
2.3.2 Linear Regression Model and Non-linear Regression Model 9
2.4 Breast Cancer Detection 11
2.4.1 Thermal Phenomena of Symptom 11
2.4.2 Critical Temperature and Gradient Temperature 12
2.4.3 Risk Level of Breast Cancer 13
CHAPTER 3 BLIND SOURCE SEPERATION ALGORITHMS 15
3.1 Single Pixel Blind Separation Algorithm 15
3.1.1 Principle of Single Pixel BSS 15
3.1.2 Application of Single Pixel BSS 16
3.1.3 Challenge in Single Pixel Blind Separation Algorithm 16 
3.2 Neighbor-based Blind Separation Algorithm 17
3.2.1 Principle of Neighbor-based BSS 17
3.2.2 Application of Neighbor-based BSS 20
3.2.3 Challenge in Neighbor-based Blind Separation Algorithm 21
3.3 Machine Learning Analysis Algorithms 21
3.3.1 Linear Regression Model 21
3.3.2 Augmented Regression Model 22
3.4 Experiment Procedures 23
3.4.1 Specification of SC4000 FLIR Camera 23
3.4.2 Dual-band IR Platform 25
CHAPTER 4 SIMULATION AND EXPERIMENT RESULTS 29
4.1 RAW Data Pre-Processing 29
4.1.1 Histogram Equalization 29
4.1.2 Binary Occupied Histogram Projection 30
4.1.3 Result of Compression 30
4.2 Experimental Results 31
4.2.1 Algorithms used in our Experiments 31
4.2.2 Demarcating Degree 37
4.2.3 Correctness Rate and Error Rate 39
CHAPTER 5 CONCLUSIONS 43
REFERENCE 45

[1] Szu, Harold, L. Miao, and H. Qi, "Thermodynamic Free-energy Minimization for Unsupervised Fusion of Dual-color Infrared Breast Images," Defense and Security Symposium. International Society for Optics and Photonics, pp.6-11, April 2006.
[2] H.-Y. Hsieh, "Evaluation and Implementation of Dual-Spectrum IR Spectrogram Diagnostic System on Breast Cancer Detection," Master Thesis, National Taiwan University, July 2008.
[3] C.-Y. Lee, "Evaluation of Dual-spectrum IR Spectrogram System on Invasive Ductal Carcinoma (IDC) Breast Cancer," Biomedical Engineering: Applications, Basis and Communications, pp.427-433, June, 2011.
[4] A. Belouchrani, K. Abed-Meraim, J.-F. Cardoso, and E. Moulines, "A Blind Source Separation Technique Using Second-order Statistics," IEEE Transactions on Signal Processing, vol.45, no.2, pp.434-444, February 1997.
[5] J. Friedman, T. Hastie, and R. Tibshirani, The Elements of Statistical Learning: Data Mining, Inference, and Prediction, Springer, 2011.
[6] A.-C. Rencher, Multivariate Statistical Inference and Applications, Wiley-Interscience, 1998.
[7] http://web.ntpu.edu.tw/~ccw/statmath/M_group_1.pdf
[8] http://web.ntpu.edu.tw/~ccw/statmath/M_group_2.pdf
[9] http://web.ntpu.edu.tw/~ccw/statmath/M_group_3.pdf
[10] http://web.ntpu.edu.tw/~ccw/statmath/M_group_4.pdf
[11] http://www.fda.gov/RegulatoryInformation/Guidances/ucm126420.htm
[12] https://wwssllabcd.github.io/blog/2013/01/31/how-to-setup-raspberry-pi/
[13] W. Herschel, "Experiments on the Refrangibility of the Invisible Rays of the Sun," Philosophical Transactions of the Royal Society of London, vol. 90, pp. 284-292, 1800.
[14] S.-Y. Yin, "Design of a Dual-band Quantum-well IR Spectrogram Readout Circuit," Master Thesis, National Taiwan University, July 2014.
[15] C.-C. Wang, "A Practical Infrared Image Contrast Enhancement Method," Master Thesis, National Chiao Tung University, June 2004.


QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top