臺灣博碩士論文加值系統

目的 : 本研究開發牛臉辨識演算法與建立一套自動化乳牛體溫量測系統，並彙整乳牛個體與環境參數分析影響乳牛體溫異常之重要因子，針對該定量參數建立乳牛體溫異常機率預測模型 (Abnormal body temperature probability, ABTP)，提供一套隨氣候變化的乳牛體溫預警模型，給予畜牧場早期發現早期治療之體溫預警措施。
材料與方法 : 在牛臉辨識演算法中比較三種YOLO模型 (YOLOV3、YOLOV3-tiny以及YOLOV5) 之辨識效率，共有3,150張乳牛影像納入本研究的影像辨識模型建立再以361張外部驗證影像作為評估與測試，透過五種影像辨識效能檢定工具 (IoU, AUC, Accuracy, Precision, F1-score) 進行模型評估；在第二部分彙整320筆乳牛個體與環境因子參數進行分析，所有入選因子包含: 溫度、濕度、環境溫溼度指數、年齡、泌乳天數、胎次、體重、乳量，因子萃取演算法採用最小絕對壓縮挑選運算子 (least absolute shrinkage and selection operator, LASSO) 作為影響體溫異常之重要因子挑選方法，並且建立四種 (Lyman Kutcher-Burman、Logistic、Schultheiss、Poisson) S型曲線之乳牛體溫異常機率預測模型 (ABTP)，預測模型效能檢定採用白氏得分、AIC模型評估準則 (Akaike's entropic information criterion)、AUC、Accuracy、Hosmer-Lemeshow test (H-L Test)、校準曲線作為模型評估方式。
結果 : 在乳牛個體 (ID) 辨識中YOLOV3、YOLOV3-tiny及YOLOV5模型之模型效能檢定分別為: IoU 0.846 / 0.841 / 0.944、AUC 0.813 / 0.813 / 0.873、Accuracy 90% / 90% / 93%、Precision 0.962 / 0.960 / 0.989、Recall 0.692 / 0.687 / 0.856、F1-score 0.805 / 0.801 / 0.918，並以YOLOV5整體影像辨識效能為最佳；四種ABTP模型建立參數分別為 (1) LKB模型 : TT50 = 75.07 (95% CI, 73.25 ~ 77.35), m = 0.12 (95% CI, 0.09 ~ 0.19)；(2) Logistic模型 : TT50 = 75.29 (95% CI, 73.12 ~ 77.49), γ50 = 3.36 (95% CI, 2.26 ~ 4.62)；(3) Schultheiss模型 : TT50 = 75.02 (95% CI, 72.85 ~ 77.24), k = 13.23 (95% CI, 8.81 ~ 18.19)；(4) Poisson模型 : TT50 = 74.44 (95% CI, 72.16 ~ 76.73), γ= 3.13 (95% CI, 2.16 ~ 4.10)；預測模型LKB、Logistic、Schultheiss、Poisson在效能檢定的表現分別為: 白式得分 0.180 / 0.214 / 0.133 / 0.204、AIC 361.28 / 361.60 / 361.56 / 362.22、AUC 0.809 / 0.809 / 0.809 / 0.807、Accuracy 0.713 / 0.713 / 0.713 / 0.706、H-L Test 0.502 / 0.511 / 0.503 / 0.481、校準曲線 0.897 / 0.897 / 0.896 / 0.891，效力評估顯示四種模型預測效能相當。
結論 : 自動化乳牛體溫量測系統提供牧場管理員快速及便利的體溫測量方案，在影像辨識效能的改良上可透過收集更多影像資料來進行優化，期望可以取代現有RFID的侵入性乳牛識別方案。在ABTP模型之成果定義當乳牛體溫 < 38.32°C 為正常體溫，38.32 ≤ 乳牛體溫 < 39.09°C 為待觀察牛隻，乳牛體溫 ≥ 39.09°C則為體溫異常訊息，若THI指數超過75則給予環境溫溼度警示通知，研究成果可提供牧場管理作為乳牛體溫與溫溼度指數管控之目標。

Purpose : In this research, we developed a cow face recognition algorithm and built an automated dairy cow body temperature measurement system. We collected cow and environmental parameters and analyzed factors that lead to abnormal body temperature of cows. Based on the quantitative parameters, a prediction model of abnormal body temperature probability (ABTP) of dairy cow was established. Provide a set of cow body temperature early warning model to provide early detection and early treatment of the body temperature early warning system for farms.
Materials and methods : Compare the recognition efficiency of three YOLO models (YOLOV3, YOLOV3-tiny and YOLOV5) in the cow face recognition algorithm. A total of 3,150 cow images were included in the image recognition model in this study, which was then evaluated and tested using 361 external validation images. Model evaluation is performed through five image recognition performance verification tools (IoU, AUC, Accuracy, Precision, F1-score). In the second part, 320 dairy cows and environmental factor parameters were collected for analysis. All selected factors included: temperature, humidity, temperature-humidity index (THI), age, lactation days, parity, weight, and milk production. The factor extraction algorithm used the least absolute shrinkage and selection operator (LASSO) as the factor selection method, and four types (Lyman Kutcher-Burman, Logistic, Schultheiss, Poisson) S-curve were established to predict the probability of abnormal body temperature in dairy cows. The performance test of the predictive model used Brier score, AIC (Akaike's entropic information criterion), AUC, Accuracy, Hosmer-Lemeshow test (H-L Test), and calibration curve as model evaluation methods.
Results : The model performance test of YOLOV3, YOLOV3-tiny and YOLOV5 models in cow individual (ID) identification : IoU 0.846 / 0.841 / 0.944, AUC 0.813 / 0.813 / 0.873, Accuracy 90% / 90% / 93%, Precision 0.962 / 0.960 / 0.989, Recall 0.692 / 0.687 / 0.856, F1-score 0.805 / 0.801 / 0.918, and the overall performance of YOLOV5 is the best model. The four ABTP model performance parameters : (1) LKB model: TT50 = 75.07 (95% CI, 73.25 ~ 77.35), m = 0.12 (95% CI, 0.09 ~ 0.19); (2) Logistic model: TT50 = 75.29 ( 95% CI, 73.12 ~ 77.49), γ50 = 3.36 (95% CI, 2.26 ~ 4.62); (3) Schultheiss model: TT50 = 75.02 (95% CI, 72.85 ~ 77.24), k = 13.23 (95% CI, 8.81) ~ 18.19); (4) Poisson model: TT50 = 74.44 (95% CI, 72.16 ~ 76.73), γ = 3.13 (95% CI, 2.16 ~ 4.10). The performance of the prediction models LKB, Logistic, Schultheiss, and Poisson in the performance test : Brier score 0.180 / 0.214 / 0.133 / 0.204, AIC 361.28 / 361.60 / 361.56 / 362.22, AUC 0.809 / 0.809 / 0.809 / 0.807, Accuracy 0.713 / 0.713 / 0.713 / 0.706, H-L Test 0.502 / 0.511 / 0.503 / 0.481, Calibration curve 0.897 / 0.897 / 0.896 / 0.891. The results show that the four models have the same predictive performance.
Conclusions : The automated cow body temperature measurement system provides a fast and convenient body temperature measurement solution for the farms. The improvement of image recognition performance can be optimized by collecting more image data, and it is expected to replace the existing RFID invasive cow identification solution. The results of the ABTP model define that the body temperature of cows < 38.32°C is normal body temperature, and the body temperature of 38.32 ≤ cows < 39.09°C is the cows to be observed. When the cow's body temperature is ≥ 39.09°C, it is abnormal body temperature. The research results can provide pasture management as the goal of cow body temperature and THI control.

摘要.....................................................i
Abstract...............................................iii
致謝....................................................vi
目錄...................................................vii
表目錄..................................................ix
圖目錄...................................................x
符號縮寫...............................................xii
符號說明..............................................xiii
第一章 緒論.............................................1
1.1動機..................................................1
1.2目的..................................................5
1.3相關文獻探討...........................................5
第二章 材料與方法........................................8
2.1前言..................................................8
2.2硬體設施..............................................10
2.2.1紅外線輻射與熱像儀...................................10
2.2.2熱像儀溫度準確度.....................................12
2.2.3自動化體溫量測步道設計...............................14
2.3資料彙整..............................................16
2.3.1影像資料............................................16
2.3.2體溫與環境資料.......................................16
2.4牛臉辨識..............................................18
2.4.1 YOLOV3及YOLOV3-tiny演算法..........................19
2.4.2 YOLOV5演算法.......................................25
2.5因子分析與模型建立.....................................27
2.5.1最小絕對壓縮挑選機制演算法 (LASSO)....................27
2.5.2乳牛體溫異常機率預測模型 (ABTP).......................28
2.5.3體溫異常之有效指數模型................................30
2.6模型效能評估...........................................32
2.6.1牛臉辨識模型評估.....................................32
2.6.2乳牛體溫異常機率預測模型 (ABTP) 評估..................33
第三章 結果.............................................35
3.1前言..................................................35
3.2牛臉辨識模型...........................................36
3.2.1資料前處理...........................................36
3.2.2 YOLOV3及YOLOV3-tiny模型訓練成果.....................38
3.2.3 YOLOV5模型訓練成果..................................40
3.3因子分析與模型建立成果..................................43
3.3.1最小絕對壓縮挑選機制演算法 (LASSO) 因子挑選結果........43
3.3.2乳牛體溫異常機率預測模型 (ABTP) 建立成果...............45
3.3.3體溫異常之有效指數模型建立成果.........................47
3.4模型效能...............................................48
3.5自動化體溫量測平台......................................50
第四章 討論..............................................51
4.1研究背景與需求分析......................................51
4.2牛臉辨識成果與問題討論..................................52
4.3 ABTP 預測模型建立與成果探討............................55
4.4 THI及乳牛體溫預警參數定義..............................58
4.5季節因素探討...........................................59
第五章 結論.............................................61
未來研究方向..............................................62
參考文獻..................................................63
List of publications.....................................74
專利: 手語翻譯系統........................................76
專利: 牛隻異常警示系統及方法...............................77
Turnitin論文原創性比對....................................78

[1]J. W. West, "Effects of heat-stress on production in dairy cattle," Journal of dairy science, vol. 86, pp. 2131-2144, 2003.
[2]J. West, B. Mullinix, and J. Bernard, "Effects of hot, humid weather on milk temperature, dry matter intake, and milk yield of lactating dairy cows," Journal of dairy science, vol. 86, pp. 232-242, 2003.
[3]G. Mazzullo, C. Rifici, G. Caccamo, M. Rizzo, and G. Piccione, "Effect of different environmental conditions on some haematological parameters in cow," Annals of Animal Science, vol. 14, p. 947, 2014.
[4]G. Yan, K. Liu, Z. Hao, Z. Shi, and H. Li, "The effects of cow-related factors on rectal temperature, respiration rate, and temperature-humidity index thresholds for lactating cows exposed to heat stress," Journal of Thermal Biology, vol. 100, p. 103041, 2021.
[5]J. Amundson, T. L. Mader, R. J. Rasby, and Q. Hu, "Environmental effects on pregnancy rate in beef cattle," Journal of animal science, vol. 84, pp. 3415-3420, 2006.
[6]N. St-Pierre, B. Cobanov, and G. Schnitkey, "Economic losses from heat stress by US livestock industries," Journal of dairy science, vol. 86, pp. E52-E77, 2003.
[7]A. Vitali, M. Segnalini, L. Bertocchi, U. Bernabucci, A. Nardone, and N. Lacetera, "Seasonal pattern of mortality and relationships between mortality and temperature-humidity index in dairy cows," Journal of dairy science, vol. 92, pp. 3781-3790, 2009.
[8]J. Allen, L. Hall, R. Collier, and J. Smith, "Effect of core body temperature, time of day, and climate conditions on behavioral patterns of lactating dairy cows experiencing mild to moderate heat stress," Journal of dairy science, vol. 98, pp. 118-127, 2015.
[9]謝欣哲, "自動化熱影像監控平台之乳牛體溫及環境參數對於產乳量影響分析," 國立高雄科技大學碩士論文, 2021.
[10]J. Liu, L. Li, X. Chen, Y. Lu, and D. Wang, "Effects of heat stress on body temperature, milk production, and reproduction in dairy cows: A novel idea for monitoring and evaluation of heat stress—A review," Asian-Australasian journal of animal sciences, vol. 32, p. 1332, 2019.
[11]S.-S. Guo, K.-H. Lee, L. Chang, C.-D. Tseng, S.-J. Sie, G.-Z. Lin, et al., "Development of an Automated Body Temperature Detection Platform for Face Recognition in Cattle with YOLO V3-Tiny Deep Learning and Infrared Thermal Imaging," Applied Sciences, vol. 12, p. 4036, 2022.
[12]T. T. Zin, C. N. Phyo, P. Tin, H. Hama, and I. Kobayashi, "Image technology based cow identification system using deep learning," in Proceedings of the International MultiConference of Engineers and Computer Scientists, 2018, pp. 236-247.
[13]S. Ansari and S. Salankar, "An Overview on Thermal Image Processing," RICE, pp. 117-120, 2017.
[14]C. McManus, C. B. Tanure, V. Peripolli, L. Seixas, V. Fischer, A. M. Gabbi, et al., "Infrared thermography in animal production: An overview," Computers and Electronics in Agriculture, vol. 123, pp. 10-16, 2016.
[15]C. Meola and G. M. Carlomagno, "Recent advances in the use of infrared thermography," Measurement science and technology, vol. 15, p. R27, 2004.
[16]Y.-C. Chou and L. Yao, "Automatic diagnostic system of electrical equipment using infrared thermography," in 2009 international conference of soft computing and pattern recognition, 2009, pp. 155-160.
[17]D. Vidal and R. Pitarma, "Infrared thermography applied to tree health assessment: A review," Agriculture, vol. 9, p. 156, 2019.
[18]S. Dikmen and P. Hansen, "Is the temperature-humidity index the best indicator of heat stress in lactating dairy cows in a subtropical environment?," Journal of dairy science, vol. 92, pp. 109-116, 2009.
[19]R. Zimbelman, R. Rhoads, M. Rhoads, G. Duff, L. Baumgard, and R. Collier, "A re-evaluation of the impact of temperature humidity index (THI) and black globe humidity index (BGHI) on milk production in high producing dairy cows," in Proceedings of the Southwest Nutrition Conference (ed. RJ Collier), 2009, pp. 158-169.
[20]李春芳, "熱緊迫下的乳牛飼養管理建議," 亞太糧肥與畜產試驗所, 2003.
[21]M. Frizzarin, I. Gormley, D. Berry, T. Murphy, A. Casa, A. Lynch, et al., "Predicting cow milk quality traits from routinely available milk spectra using statistical machine learning methods," Journal of Dairy Science, vol. 104, pp. 7438-7447, 2021.
[22]T.-F. Lee, M.-H. Liou, Y.-J. Huang, P.-J. Chao, H.-M. Ting, H.-Y. Lee, et al., "LASSO NTCP predictors for the incidence of xerostomia in patients with head and neck squamous cell carcinoma and nasopharyngeal carcinoma," Scientific reports, vol. 4, pp. 1-8, 2014.
[23]C. Kong, X.-z. Zhu, T.-F. Lee, P.-b. Feng, J.-h. Xu, P.-d. Qian, et al., "LASSO-based NTCP model for radiation-induced temporal lobe injury developing after intensity-modulated radiotherapy of nasopharyngeal carcinoma," Scientific reports, vol. 6, pp. 1-8, 2016.
[24]T.-F. Lee and E.-Y. Huang, "The different dose-volume effects of normal tissue complication probability using LASSO for acute small-bowel toxicity during radiotherapy in gynecological patients with or without prior abdominal surgery," BioMed Research International, vol. 2014, 2014.
[25]T.-F. Lee, P.-J. Chao, H.-M. Ting, L. Chang, Y.-J. Huang, J.-M. Wu, et al., "Using multivariate regression model with least absolute shrinkage and selection operator (LASSO) to predict the incidence of xerostomia after intensity-modulated radiotherapy for head and neck cancer," PloS one, vol. 9, p. e89700, 2014.
[26]C.-H. Liu, C.-S. Shieh, T.-L. Huang, C.-H. Lin, P.-J. Chao, Y.-J. Huang, et al., "Evaluating the Risk Factors of Post Inflammatory Hyperpigmentation Complications with Nd-YAG Laser Toning Using LASSO-Based Algorithm," Applied Sciences, vol. 10, p. 2049, 2020.
[27]T.-F. Lee, M.-H. Liou, H.-M. Ting, L. Chang, H.-Y. Lee, S. Wan Leung, et al., "Patient-and therapy-related factors associated with the incidence of xerostomia in nasopharyngeal carcinoma patients receiving parotid-sparing helical tomotherapy," Scientific Reports, vol. 5, pp. 1-13, 2015.
[28]A. Werker and K. Jaggard, "Modelling asymmetrical growth curves that rise and then fall: Applications to foliage dynamics of sugar beet (Beta vulgarisL.)," Annals of Botany, vol. 79, pp. 657-665, 1997.
[29]丁慧敏, 郭仕賢, 藍仁鴻, 李曉飛, 趙珮如, 黃郁傑, et al., "乳癌患者接受放射治療後發生放射性肺炎之萊曼正常組織併發症機率模型參數分析," 放射治療與腫瘤學, vol. 24, pp. 25-34, 2017.
[30]D. A. Ratkowsky, "Principles of nonlinear regression modeling," Journal of Industrial Microbiology, vol. 12, pp. 195-199, 1993.
[31]郭仕賢, "五種正常組織併發症機率模型之乳癌患者放射性肺炎劑量反應特性比較," 國立高雄應用科技大學電子工程系碩士論文, 2015.
[32]C. Pang, D. He, C. Li, C. Huang, and L. Zheng, "Method of traceability information acquisition and transmission for dairy cattle based on integrating of RFID and WSN," Transactions of the Chinese Society of Agricultural Engineering, vol. 27, pp. 147-152, 2011.
[33]H. Kou, Y. Zhao, K. Ren, X. Chen, Y. Lu, and D. Wang, "Automated measurement of cattle surface temperature and its correlation with rectal temperature," PLoS One, vol. 12, p. e0175377, 2017.
[34]J. Uddin, D. M. McNeill, A. T. Lisle, and C. J. Phillips, "A sampling strategy for the determination of infrared temperature of relevant external body surfaces of dairy cows," International Journal of Biometeorology, pp. 1-10, 2020.
[35]H. A. Alwzwazy, H. M. Albehadili, Y. S. Alwan, and N. E. Islam, "Handwritten digit recognition using convolutional neural networks," International Journal of Innovative Research in Computer and Communication Engineering, vol. 4, pp. 1101-1106, 2016.
[36]B. Jiang, Q. Wu, X. Yin, D. Wu, H. Song, and D. He, "FLYOLOv3 deep learning for key parts of dairy cow body detection," Computers and Electronics in Agriculture, vol. 166, p. 104982, 2019.
[37]C. Y. Kuan, Y. C. Tsai, J. T. Hsu, S. T. Ding, and T. Te Lin, "An imaging system based on deep learning for monitoring the feeding behavior of dairy cows," in 2019 ASABE Annual International Meeting, 2019, p. 1.
[38]F. Sultana, A. Sufian, and P. Dutta, "A review of object detection models based on convolutional neural network," Intelligent computing: image processing based applications, pp. 1-16, 2020.
[39]P. Jiang, D. Ergu, F. Liu, Y. Cai, and B. Ma, "A Review of Yolo Algorithm Developments," Procedia Computer Science, vol. 199, pp. 1066-1073, 2022.
[40]Y.-Y. Qin, J.-T. Cao, and X.-F. Ji, "Fire detection method based on depthwise separable convolution and yolov3," International Journal of Automation and Computing, vol. 18, pp. 300-310, 2021.
[41]Y. Liu, X. Ji, S. Pei, Z. Ma, G. Zhang, Y. Lin, et al., "Research on automatic location and recognition of insulators in substation based on YOLOv3," High Voltage, vol. 5, pp. 62-68, 2020.
[42]P. Li and H. Li, "Research on fod detection for airport runway based on yolov3," in 2020 39th Chinese Control Conference (CCC), 2020, pp. 7096-7099.
[43]L. Zhang, Y. Li, H. Chen, W. Wu, K. Chen, and S. Wang, "Anchor-free YOLOv3 for mass detection in mammogram," Expert systems with applications, vol. 191, p. 116273, 2022.
[44]K. Cai, X. Miao, W. Wang, H. Pang, Y. Liu, and J. Song, "A modified YOLOv3 model for fish detection based on MobileNetv1 as backbone," Aquacultural Engineering, vol. 91, p. 102117, 2020.
[45]X. Zhang and X. Zhu, "Vehicle Detection in the aerial infrared images via an improved YOLOv3 network," in 2019 IEEE 4th International Conference on Signal and Image Processing (ICSIP), 2019, pp. 372-376.
[46]J. Redmon and A. Farhadi, "Yolov3: An incremental improvement," arXiv preprint arXiv:1804.02767, 2018.
[47]G. Hoffmann, M. Schmidt, C. Ammon, S. Rose-Meierhöfer, O. Burfeind, W. Heuwieser, et al., "Monitoring the body temperature of cows and calves using video recordings from an infrared thermography camera," Veterinary research communications, vol. 37, pp. 91-99, 2013.
[48]M. A. Jaddoa, A. Al-Jumaily, L. Gonzalez, and H. Cuthbertson, "Automatic eyes localization in thermal images for temperature measurement in cattle," in 2017 12th International Conference on Intelligent Systems and Knowledge Engineering (ISKE), 2017, pp. 1-6.
[49]陳怡璇, 陳宜鴻, and 蕭方君, "乳牛健康一把罩-紅外線體溫感測," 科學發展智慧養牛科技, pp. 16-21, 2007.
[50]J. Uddin, D. M. McNeill, A. T. Lisle, and C. J. Phillips, "A sampling strategy for the determination of infrared temperature of relevant external body surfaces of dairy cows," International Journal of Biometeorology, vol. 64, pp. 1583-1592, 2020.
[51]M. Stewart, K. Stafford, S. Dowling, A. Schaefer, and J. Webster, "Eye temperature and heart rate variability of calves disbudded with or without local anaesthetic," Physiology & Behavior, vol. 93, pp. 789-797, 2008.
[52]M. Stewart, J. Webster, G. Verkerk, A. Schaefer, J. Colyn, and K. Stafford, "Non-invasive measurement of stress in dairy cows using infrared thermography," Physiology & behavior, vol. 92, pp. 520-525, 2007.
[53]J. Gloster, K. Ebert, S. Gubbins, J. Bashiruddin, and D. J. Paton, "Normal variation in thermal radiated temperature in cattle: implications for foot-and-mouth disease detection," BMC veterinary research, vol. 7, p. 73, 2011.
[54]V. Poikalainen, J. Praks, I. Veermae, and E. Kokin, "Infrared temperature patterns of cow’s body as an indicator for health control at precision cattle farming," Agronomy Research Biosystem Engineering Special, vol. 10, pp. 187-194, 2012.
[55]S. Talukder, K. Kerrisk, L. Ingenhoff, P. Thomson, S. Garcia, and P. Celi, "Infrared technology for estrus detection and as a predictor of time of ovulation in dairy cows in a pasture-based system," Theriogenology, vol. 81, pp. 925-935, 2014.
[56]B. Xu, W. Wang, L. Guo, G. Chen, Y. Wang, W. Zhang, et al., "Evaluation of Deep Learning for Automatic Multi-View Face Detection in Cattle," Agriculture, vol. 11, p. 1062, 2021.
[57]W. Shen, H. Hu, B. Dai, X. Wei, J. Sun, L. Jiang, et al., "Individual identification of dairy cows based on convolutional neural networks," Multimedia Tools and Applications, vol. 79, pp. 14711-14724, 2020.
[58]M. R. Jose and H. Kaakinen, "An object detection application approach to analyze cattle under camera surveillance."
[59]W. Wu, H. Liu, L. Li, Y. Long, X. Wang, Z. Wang, et al., "Application of local fully Convolutional Neural Network combined with YOLO v5 algorithm in small target detection of remote sensing image," PloS one, vol. 16, p. e0259283, 2021.
[60]R. H. Dicke, P. J. E. Peebles, P. G. Roll, and D. T. Wilkinson, "Cosmic black-body radiation," The Astrophysical Journal, vol. 142, pp. 414-419, 1965.
[61]G. Ranganath, "Black-body radiation," Resonance, vol. 13, pp. 115-133, 2008.
[62]A. K. Sood, R. Richwine, Y. R. Puri, N. K. Dhar, D. L. Polla, and P. S. Wijewarnasuriya, "Multispectral EO/IR sensor model for evaluating UV, visible, SWIR, MWIR and LWIR system performance," in Infrared Imaging Systems: Design, Analysis, Modeling, and Testing XX, 2009, pp. 158-169.
[63]R. Breiter, J. Wendler, H. Lutz, S. Rutzinger, K. Hofmann, and J. Ziegler, "IR-detection modules from SWIR to VLWIR: performance and applications," in Infrared Technology and Applications XXXV, 2009, pp. 668-679.
[64]M.-D. Yang, T.-C. Su, and H.-Y. Lin, "Fusion of infrared thermal image and visible image for 3D thermal model reconstruction using smartphone sensors," Sensors, vol. 18, p. 2003, 2018.
[65]D. Bulanon, T. Burks, and V. Alchanatis, "Image fusion of visible and thermal images for fruit detection," Biosystems engineering, vol. 103, pp. 12-22, 2009.
[66]dronegenuity, "What are SWIR, MWIR, and LWIR – And what do they mean?," 2020.
[67]B. H. Kim, M. Y. Kim, and Y. S. Chae, "Scene-Based Adaptive Noise Filtering and evaluating technique for LWIR/MWIR imaging sensor systems."
[68]李財福, 郭仕賢, 謝欣哲, 李國華, 葉亦馨, 陳志毅, et al., "牛隻異常警示系統及方法," 中華民國 Patent I766747, 2022.
[69]J. Bohmanova, I. Misztal, and J. Cole, "Temperature-humidity indices as indicators of milk production losses due to heat stress," Journal of dairy science, vol. 90, pp. 1947-1956, 2007.
[70]N. Council, "A guide to environmental research on animals: National Academies," 1971.
[71]L. Fu, Y. Feng, J. Wu, Z. Liu, F. Gao, Y. Majeed, et al., "Fast and accurate detection of kiwifruit in orchard using improved YOLOv3-tiny model," Precision Agriculture, pp. 1-23, 2020.
[72]Q. Wang, S. Bi, M. Sun, Y. Wang, D. Wang, and S. Yang, "Deep learning approach to peripheral leukocyte recognition," PloS one, vol. 14, p. e0218808, 2019.
[73]S. Ioffe and C. Szegedy, "Batch normalization: Accelerating deep network training by reducing internal covariate shift," in International conference on machine learning, 2015, pp. 448-456.
[74]J. Xu, Z. Li, B. Du, M. Zhang, and J. Liu, "Reluplex made more practical: Leaky ReLU," in 2020 IEEE Symposium on Computers and communications (ISCC), 2020, pp. 1-7.
[75]U. Nepal and H. Eslamiat, "Comparing YOLOv3, YOLOv4 and YOLOv5 for autonomous landing spot detection in faulty UAVs," Sensors, vol. 22, p. 464, 2022.
[76]B. Yan, P. Fan, X. Lei, Z. Liu, and F. Yang, "A real-time apple targets detection method for picking robot based on improved YOLOv5," Remote Sensing, vol. 13, p. 1619, 2021.
[77]F. Zhou, H. Zhao, and Z. Nie, "Safety helmet detection based on YOLOv5," in 2021 IEEE International Conference on Power Electronics, Computer Applications (ICPECA), 2021, pp. 6-11.
[78]R. Tibshirani, "Regression shrinkage and selection via the lasso," Journal of the Royal Statistical Society. Series B (Methodological), pp. 267-288, 1996.
[79]R. Tibshirani, M. Saunders, S. Rosset, J. Zhu, and K. Knight, "Sparsity and smoothness via the fused lasso," Journal of the Royal Statistical Society: Series B (Statistical Methodology), vol. 67, pp. 91-108, 2005.
[80]H. Zou and T. Hastie, "Regularization and variable selection via the elastic net," Journal of the Royal Statistical Society: Series B (Statistical Methodology), vol. 67, pp. 301-320, 2005.
[81]T.-F. Lee, P.-J. Chao, L. Chang, H.-M. Ting, and Y.-J. Huang, "Developing multivariable normal tissue complication probability model to predict the incidence of symptomatic radiation pneumonitis among breast cancer patients," PloS one, vol. 10, p. e0131736, 2015.
[82]C.-C. Huang, P.-J. Chao, S.-S. Guo, C.-J. Wang, H.-L. Luo, Y.-L. Su, et al., "Developing a multivariable normal tissue complication probability model to predict late rectal bleeding following intensity-modulated radiation therapy," Journal of Cancer, vol. 10, p. 2588, 2019.
[83]P.-J. Chao, H.-F. Lee, J.-H. Lan, S.-S. Guo, H.-M. Ting, Y.-J. Huang, et al., "Propensity-score-matched evaluation of the incidence of radiation pneumonitis and secondary cancer risk for breast cancer patients treated with IMRT/VMAT," Scientific reports, vol. 7, pp. 1-9, 2017.
[84]C.-C. Huang, P.-J. Chao, S.-S. Guo, C.-J. Wang, H.-L. Luo, Y.-L. Su, et al., "LASSO-based Multivariable NTCP Model for Late Rectal Bleeding in Prostate Cancer Patients after IMRT," Risk, vol. 19, p. 0.99, 2018.
[85]K. Sung, H. Ting, P. Chao, S. Guo, C. Tran, Y. Huang, et al., "Predicting grade 2 acute radiation-induced dermatitis after hybrid intensity modulation radiotherapy for breast cancer using a logistic regression normal tissue complication probability model," European Journal of Cancer, vol. 60, p. e4, 2016.
[86]T. Dijkema, C. P. Raaijmakers, R. K. Ten Haken, J. M. Roesink, P. M. Braam, A. C. Houweling, et al., "Parotid gland function after radiotherapy: the combined Michigan and Utrecht experience," International Journal of Radiation Oncology, Biology, Physics, vol. 78, pp. 449-453, 2010.
[87]J. T. Lyman and A. B. Wolbarst, "Optimization of radiation therapy, III: A method of assessing complication probabilities from dose-volume histograms," International Journal of Radiation Oncology, Biology, Physics, vol. 13, pp. 103-109, 1987.
[88]G. Kutcher, C. Burman, L. Brewster, M. Goitein, and R. Mohan, "Histogram reduction method for calculating complication probabilities for three-dimensional treatment planning evaluations," International Journal of Radiation Oncology, Biology, Physics, vol. 21, pp. 137-146, 1991.
[89]T. E. Schultheiss, C. G. Orton, and R. Peck, "Models in radiotherapy: volume effects," Medical physics, vol. 10, pp. 410-415, 1983.
[90]P. Källman, A. Ågren, and A. Brahme, "Tumour and normal tissue responses to fractionated non-uniform dose delivery," International Journal of Radiation Biology, vol. 62, pp. 249-262, 1992.
[91]L. Le Cam, "Maximum likelihood: an introduction," International Statistical Review/Revue Internationale de Statistique, pp. 153-171, 1990.
[92]S. J. Hasstedt, "A mixed-model likelihood approximation on large pedigrees," Computers and biomedical research, vol. 15, pp. 295-307, 1982.
[93]J. T. Lyman, "Complication probability as assessed from dose-volume histograms," Radiation Research, vol. 104, pp. S13-S19, 1985.
[94]G. Luxton, P. J. Keall, and C. R. King, "A new formula for normal tissue complication probability (NTCP) as a function of equivalent uniform dose (EUD)," Physics in Medicine and Biology, vol. 53, pp. 23-36, 2008.
[95]T.-F. Lee, S.-A. Yeh, P.-J. Chao, L. Chang, C.-L. Chiu, H.-M. Ting, et al., "Normal tissue complication probability modeling for cochlea constraints to avoid causing tinnitus after head-and-neck intensity-modulated radiation therapy," Radiation Oncology, vol. 10, p. 194, 2015.
[96]I. Beetz, C. Schilstra, A. van der Schaaf, E. R. van den Heuvel, P. Doornaert, P. van Luijk, et al., "NTCP models for patient-rated xerostomia and sticky saliva after treatment with intensity modulated radiotherapy for head and neck cancer: the role of dosimetric and clinical factors," Radiotherapy and Oncology, vol. 105, pp. 101-106, 2012.
[97]R. G. Congalton, "A review of assessing the accuracy of classifications of remotely sensed data," Remote Sensing of Environment, vol. 37, pp. 35-46, 1991.
[98]M.-T. Pham, L. Courtrai, C. Friguet, S. Lefèvre, and A. Baussard, "YOLO-Fine: One-stage detector of small objects under various backgrounds in remote sensing images," Remote Sensing, vol. 12, p. 2501, 2020.
[99]G. Meyfroidt, F. Güiza, D. Cottem, W. De Becker, K. Van Loon, J.-M. Aerts, et al., "Computerized prediction of intensive care unit discharge after cardiac surgery: development and validation of a Gaussian processes model," BMC Medical Informatics and Decision Making, vol. 11, p. 64, 2011.
[100]E. W. Steyerberg, Clinical prediction models: a practical approach to development, validation, and updating: Springer Science & Business Media, 2008.
[101]E. W. Steyerberg, A. J. Vickers, N. R. Cook, T. Gerds, M. Gonen, N. Obuchowski, et al., "Assessing the performance of prediction models: a framework for some traditional and novel measures," Epidemiology (Cambridge, Mass.), vol. 21, p. 128, 2010.
[102]H. Bozdogan, "Model selection and Akaike's information criterion (AIC): The general theory and its analytical extensions," Psychometrika, vol. 52, pp. 345-370, 1987.
[103]B. Miladinovic, R. Mhaskar, A. Kumar, S. Kim, R. Schonwetter, and B. Djulbegovic, "External validation of a web-based prognostic tool for predicting survival for patients in hospice care," Journal of Palliative Care, vol. 29, pp. 140-146, 2013.
[104]G. Tripepi, K. J. Jager, F. W. Dekker, and C. Zoccali, "Statistical methods for the assessment of prognostic biomarkers (part II): calibration and re-classification," Nephrology Dialysis Transplantation, vol. 25, pp. 1402-1405, 2010.
[105]E. W. Steyerberg, F. E. Harrell, G. J. Borsboom, M. Eijkemans, Y. Vergouwe, and J. D. F. Habbema, "Internal validation of predictive models: efficiency of some procedures for logistic regression analysis," Journal of Clinical Epidemiology, vol. 54, pp. 774-781, 2001.
[106]D. R. Cox, "Two further applications of a model for binary regression," Biometrika, pp. 562-565, 1958.
[107]H.-W. Luo, C.-S. Zhang, F.-C. Pan, and X.-M. Ju, "Contextual-YOLOV3: implement better small object detection based deep learning," in 2019 International Conference on Machine Learning, Big Data and Business Intelligence (MLBDBI), 2019, pp. 134-141.
[108]J. Gaughan, T. L. Mader, S. Holt, and A. Lisle, "A new heat load index for feedlot cattle," Journal of Animal Science, vol. 86, pp. 226-234, 2008.
[109]R. Ingraham, D. Gillette, and W. Wagner, "Relationship of temperature and humidity to conception rate of Holstein cows in subtropical climate," Journal of Dairy Science, vol. 57, pp. 476-481, 1974.
[110]B. Xue, Z. Wang, S. Li, L. Wang, and Z. Wang, "Temperature-humidity index on performance of cows," China Anim Husb Vet Med, vol. 37, pp. 153-7, 2010.
[111]李國華, 陳志毅, 葉亦馨, and 林宗毅, "紅外線熱像儀可以偵測乳牛發燒嗎?," 農業知識網, 2022.
[112]D. Peng, S. Chen, G. Li, J. Chen, J. Wang, and X. Gu, "Infrared thermography measured body surface temperature and its relationship with rectal temperature in dairy cows under different temperature-humidity indexes," International Journal of Biometeorology, vol. 63, pp. 327-336, 2019.
[113]陳怡璇, 陳宜鴻, and 蕭方君, "智慧養牛科技：乳牛健康一把罩─紅外線體溫感測," 科技大觀園, 2017.
[114]N. Cook, R. Mentink, T. Bennett, and K. Burgi, "The effect of heat stress and lameness on time budgets of lactating dairy cows," Journal of dairy science, vol. 90, pp. 1674-1682, 2007.
[115]C. B. Tucker, A. R. Rogers, and K. E. Schütz, "Effect of solar radiation on dairy cattle behaviour, use of shade and body temperature in a pasture-based system," Applied Animal Behaviour Science, vol. 109, pp. 141-154, 2008.
[116]M. Rhoads, R. Rhoads, M. VanBaale, R. Collier, S. Sanders, W. Weber, et al., "Effects of heat stress and plane of nutrition on lactating Holstein cows: I. Production, metabolism, and aspects of circulating somatotropin," Journal of dairy science, vol. 92, pp. 1986-1997, 2009.
[117]M. Igono, B. Steevens, M. Shanklin, and H. Johnson, "Spray cooling effects on milk production, milk, and rectal temperatures of cows during a moderate temperate summer season," Journal of dairy science, vol. 68, pp. 979-985, 1985.
[118]M. Zähner, L. Schrader, R. Hauser, M. Keck, W. Langhans, and B. Wechsler, "The influence of climatic conditions on physiological and behavioural parameters in dairy cows kept in open stables," Animal Science, vol. 78, pp. 139-147, 2004.
[119]方煒, "畜舍環控技術—草食動物產業," 台大生物產業機電工程學系, 2010.