本論文針對高中生提出一個深度學習視覺分類機器人平台與一套基於資料驅動學習的人工智慧機器人課程，讓其可以在高中職階段實施和推廣人工智慧機器人的基礎教育。主要有三個部分：(1) 深度學習視覺分類機器人平台、(2) 人工智慧機器人課程、以及(3) 資料驅動學習。在深度學習視覺分類機器人平台方面，本論文使用低價位的邊緣運算裝置來設計一台具深度學習能力之小型移動機器人，使其具有價格合理、軟硬體彈性高、場地模組化、以及擴充性高的特色。此外，搭配本論文提出之輕量型卷積神經網路模型，使其可在一般規格之電腦上有理想的訓練速度，且訓練後的神經網絡在邊緣運算裝置上也有不錯的推論準確度與執行速度。在人工智慧機器人課程方面，本論文設計一套24小時動手做課程，包含了人工智慧觀念、影像處理演算法、深度學習神經網路、以及機器人控制等四個單元，使其具有概念學習、動手操作、以及錯誤釐清的特色。在資料驅動學習方面，本論文設計一個自駕車的場地與情境。在路牌辨識之實際操作過程中，讓學生可以瞭解所蒐集之照片資料的品質與數量對於神經網路在學習上的影響。從分析與訪談的結果可知，本論文所提出之平台與課程確實可以在高中職教學現場成功地實施，並且可以提高學生的學習效果以及建立正確之人工智慧與機器人控制的概念。

In the dissertation, a deep learning visual classification robotics platform and an artificial intelligence robotics curriculum based on data-driven learning are proposed for high school students so that the basic education of artificial intelligence robots can be implemented and promoted in high school. There are three main parts: (1) deep learning visual classification robotics platform, (2) artificial intelligence robotics curriculum, and (3) data driven learning. In deep learning visual classification robotics platform, some low-cost edge computing devices (Raspberry Pi SBC and Intel NCS compute stick) are used to design a small-sized mobile robot with deep learning capability so that it has the characteristics of reasonable price, high flexibility of hardware and software, modularity of venue, and high expandability of functions. In addition, a lightweight convolutional neural network model is proposed so that this network model can be fast trained on ordinary computers and the trained neural network can also have a pretty good inference accuracy and execution speed on this edge computing device with limited performance. In artificial intelligence robotics curriculum, a 24-hour hands-on curriculum is designed. It includes four units: artificial intelligence concepts, image processing algorithms, deep learning neural networks, and robot control so that it has the characteristics of concept learning, hands-on operation, and misunderstanding clarification. In data driven learning, a venue and a scenario of a self-driving car are designed. During the actual operation of neural network training for the recognition of road signs, students can understand that the quality and quantity of the collected photo data have a great influence on the learning of neural networks. From the results of analysis and interviews, it can see that the platform and the curriculum proposed in this dissertation can be successfully implemented in the teaching site of high school, and can improve the learning effect of students and establish the correct concept of artificial intelligence and robot control.

致謝	I
中文摘要	II
英文摘要	IV
目錄	V
圖目錄	X
表目錄	XII
第一章	緒論	1
1.1 研究背景與動機	1
1.2 研究目的	6
1.3 研究範圍與限制	7
1.3.1研究範圍	7
1.3.2研究限制	8
1.4 名詞釋義	9
1.4.1資料驅動學習	9
1.4.2人工智慧機器人課程	9
1.4.3深度學習視覺分類機器人平台	9
1.4.4資料品質	10
第二章	文獻探討	12
2.1我國之資訊科技教學現況	12
2.2 STEAM教育與圖形化程式語言發展沿革	13
2.2.1 Logo圖形化程式語言	14
2.2.2 Scratch	15
2.2.3 MIT App Inventor	16
2.3相關學習理論	17
2.3.1建構式學習	17
2.3.2情境學習	19
2.3.3發現式學習	21
2.4可用於深度學習之單板電腦	23
2.4.1 Raspberry Pi	24
2.4.2 Google Coral TPU Edge	24
2.4.3 NVIDIA Jetson Nano	25
2.4.4 Aaeon UpBoard	25
2.4.5 ASUS Tinker Edge T	26
2.5相關視覺機器人平台教學系統	27
2.5.1 Duckietown	28
2.5.2 Donkey Car	28
2.5.3 MIT Racecar	29
2.5.4 AWS Deepracer	30
第三章	系統架構與功能	33
3.1設計理念	33
3.2課程架構	34
3.3 深度學習視覺分類機器人平台	36
3.3.1硬體配置	38
3.3.2軟體框架	40
3.3.3系統執行架構	46
3.4學習內容	47
3.5錯誤觀念	49
第四章	研究方法	51
4.1 實驗對象	52
4.2 實驗設計	52
4.3 實驗工具	54
4.3.1 資料驅動學習之人工智慧機器人課程	54
4.3.2 學習成效測驗	55
4.3.3 錯誤概念分析測驗	61
4.3.4 資料驅動學習之學習環境	62
4.3.5 學習行為編碼方案	63
4.3.6 態度問卷	64
4.4 實驗程序	65
第五章	結果與討論	68
5.1 學習成效分析	68
5.2 錯誤觀念導正成果分析	71
5.2.1錯誤觀念分析	73
5.3 態度問卷結果分析	75
5.4 課堂觀察與討論	76
第六章	結論與未來展望	77
6.1 結論	78
6.2 未來展望	78
參考文獻	80
附錄	88
附錄一  前測問卷	88
附錄二  後測問卷	91
附錄三  錯誤觀念分析問卷	94
附錄四  態度問卷	95

圖目錄
圖2.1、Logo程式語言	15
圖2.2、Resnick所提出之創意螺旋	16
圖2.3、MIT App Inventor 系統架構圖	17
圖2.4、Raspberry Pi B+ 單板電腦	24
圖2.5、Google Coral TPU Edge：(a) 開發板與(b) USB加速模組	25
圖2.6、NVIDIA Jetson Nano開發板	25
圖2.7、Aaeon UpBoard開發板	26
圖2.8、ASUS Tinker Edge T開發板	26
圖2.9、DuckieBot機器人平台	28
圖2.10、Donkey Car機器學習自駕車	29
圖2.11、MIT Racecar自駕車平台	30
圖2.12、AWS DeepRacer機器人平台	30
圖3.1、資料驅動人工智慧機器人課程之學習活動階段	34
圖3.2、Raspberry Pi單板電腦結合Intel Movidius神經運算模組	36
圖3.3、深度學習視覺分類機器人平台：(a) 2019版與(b) 2020版	36
圖3.4、本論文所實現之深度學習視覺分類機器人平台的四大特色	37
圖3.5、深度學習視覺分類機器人平台的主要硬體元件	38
圖3.6、深度學習視覺分類機器人平台的硬體配線圖	38
圖3.7、本論文所提出之簡化版卷積神經網路的網路模型架構	41
圖3.8、簡化版卷積神經網路之訓練過程的執行畫面	42
圖3.9、不同網路參數之準確度與損失收斂的比較	44
圖3.10、深度學習視覺分類機器人平台的執行流程	47
圖3.11、實驗操作過程	49
圖4.1、實驗程序	66
圖4.2、使用三種路牌之路線示意圖	67
圖4.3、使用六種路牌之路線示意圖	67
圖5.1、實驗組與對照組錯誤觀念改正成功率比較	74
圖5.2、態度問卷結果分析	76

表目錄
表1.1、影像品質說明	11
表2.1、六款單板電腦的規格比較	27
表2.2、五款視覺機器人平台的規格比較	32
表3.1、本論文所實現之兩款平台的比較	37
表3.2、深度學習視覺分類機器人平台之硬體名稱、功能說明與數量	39
表3.3、本論文所使用之二款卷積神經網路版本的比較	45
表3.4、五款神經網路之訓練時間與推論時間的比較	46
表3.5、各單元概念學習內容	48
表3.6、本論文之四個教學領域常見之錯誤觀念	50
表4.1、四所學校之實驗組與對照組的人數	52
表4.2、本論文之變項說明	53
表4.3、實驗設計架構	54
表4.4、資料驅動學習之人工智慧機器人課程內容課程	55
表4.5、前測試題與概念主題對應表	57
表4.6、後測試題與概念主題對應表	59
表4.7、前後測各單元題目對照一覽表	61
表4.8、資料驅動學習之AI機器人學習行為編碼方案	64
表4.9、態度問卷題目內容分布	65
表5.1、本教學之學習成效測驗前後測的分數摘要表	69
表5.2、本教學之學習成效測驗迴歸係數同質性檢定表	69
表5.3、本教學之學習成效測驗共變數分析檢定表	70
表5.4、學習成效測驗之統計分析結果	71
表5.5、學習成效測驗前、後測的錯誤觀念個數摘要表	72
表5.6、學習成效測驗的迴歸係數同質性考驗摘要表	73
表5.7、錯誤觀念測驗的迴歸係數同質性考驗摘要表	73
表5.8、前測後測錯誤觀念分析	75

[1]	陳宇姍，國中學生對資訊科技融入生活科技教學之學習態度研究。國立高雄師範大學工業科技教育學系碩士論文(指導教授：朱耀明)，2017。
[2]	王盈琪、王美芬，利用 POE 教學模式探討國小三年級學童光錯誤觀念及其概念改變之成效。中華民國第二十二屆科學教育學術研討會，國立台灣師範大學，2006。
[3]	李賢哲、樊琳、張蘭友，國小學童「電池」概念之診斷—以兩段式選擇題為例，科學教育學刊，13 (3), 263-288，2005。
[4]	V. L. Akerson, L. B. Flick, and N. G. Lederman, “The influence of young children's ideas in science on teaching practice,” Journal of Research in Science Teaching, vol. 37, no, 4, pp. 363-385, 2000.
[5]	黃福坤，資訊素養與教學─以物理教學示範實驗室輔助教學網站為例。圖書館學與資訊科學，25 (2)，53-62，1999。
[6]	林淑慧，問題導向學習法在遠距教學環境的應用－理論探討與實例說明，技術及職業教育雙月刊，74，50-54，2003。
[7]	邱美虹，概念改變研究的省思與啟示。科學教育學刊，8 (1)，1-34，2000。
[8]	洪妤如，應用視覺化與操作之模擬軟體在電子學上的學習效果，國立台灣師範大學資訊教育學系碩士論文(指導教授：張國恩、宋曜廷、方瓊瑤)，2005。
[9]	計惠卿、張杏妃。全方位的學習策略－問題導向學習的教學設計模式，教學科技與媒體，55，58-71，2001。
[10]	高頌洲，問題導向學習(PBL)導入生活科技教學活動之初探，生活科技教育，35 (8)，12-19，2002。
[11]	許永賢，兒童數學科「問題解決」的指導與發展，臺灣教育，416，27-29，1985。    
[12]	V. Bar, B. Zinn, and E. Rubin, “Children's ideas about action at a distance,” International Journal of Science Education, vol. 19, no. 10, pp. 1137-1157, 1997.
[13]	Naps et al., “Exploring the role of visualization and engagement in computer science education,” ACM SIGCSE Bulletin, vol. 35, no.2, pp. 131-152, 2003.
[14]	K.E. Chang, Y.L. Chen, H.Y. Lin, and Y.T. Sung, “Effects of learning support in simulation-based physics learning,” Computers & Education, vol. 51, no. 4, pp. 1486-1498, 2008.
[15]	J. Zhang, Q. Chen, Y. Sun, and D.J. Reid, “Triple scheme of learning support design for scientific discovery learning based on computer simulation: Experimental research,” Journal of computer Assisted Learning, vol. 20, no. 4, pp. 269-282, 2004.
[16]	N. L. Gage, “Hard gains in the soft sciences: The case of pedagogy,” Phi Delta Kappa, 1986.
[17]	O. Geban, P. Askar, and I. Ozkan, “Effects of computer simulations and problems solving approaches on high school students,” Journal of Educational Research, vol. 86, no. 1, pp. 5-10, 1992.
[18]	M.M. Mulopo and H. S. Fowler, “Effects of traditional and discovery instruction approaches on learning outcomes for learners of different intellectual development. A study of chemistry students in Zambia,” Journal of Research in Science Teaching, vol. 24, no. 3, pp. 217-227, 1987.
[19]	D. J. Ton and W. R. Van Joolingen, “Scientific discovery learning with computer simulations of conceptual domains,” Review of Educational Research, vol. 68, no. 2, pp. 179-201, 1998.
[20]	“行政院環境保護署空氣指標預報” URL: http://opendata2.epa.gov.tw/AQI.json
[21]	M. Ronen and M. Eliahu, “Simulation- A bridge between theory and reality: The case of electric circuits,” Journal of Computer Assisted Learning, vol. 16, no. 1, pp. 14-26, 2000.
[22]	J.W. Belcher and S. Olbert, “Field line motion in classical electromagnetism,” American Journal of Physics, vol. 71, no. 3, pp. 220-228, 2003.
[23]	M. Reiner, J.D. Slotta, T.H. Chi, and L.B. Resnick, “Naïve physics reasoning: A commitment to substance-based conceptions,” Cognition and Instruction, vol. 18, no. 1, pp. 1-34, 2000.
[24]	H. Pfundt and R. Duit, Bibliography: Students’ Alternative Frameworks and Science Education, ERIC Clearinghouse, 1988.
[25]	P. Sengupta and U. Wilensky, “Learning electricity with NIELS: Thinking with electrons and thinking in levels,” International Journal of Computers for Mathematical Learning, vol. 14, no. 1, pp. 21-50, 2009.
[26]	T. Jaakkola and S. Nurmi, Academic impact of learning objectives: The case of electric circuits, Online Submission, 2004.
[27]	A. Eryilmaz, “Effects of conceptual assignments and conceptual change discussions on students' misconceptions and achievement regarding force and motion,” Journal of Research in Science Teaching, vol. 39, no. 10, pp. 1001-1015, 2002.
[28]	R. Tytler, “Teaching for understanding in science: Constructivist/ conceptual change teaching approaches,” Australian Science Teachers’ Journal, vol. 48, no. 4, pp. 30, 2002.
[29]	S. Vosniadou, “On the nature of naive physics,” Reconsidering conceptual change: Issues in theory and practice, pp. 61-76, 2002.
[30]	J. Piaget, “Le point de vue de Piaget,” International Journal of Psychology, vol. 3, no. 4, pp. 281-299, 1968.
[31]	G. J. Posner, K.A. Strike, P.W. Hewson, and W.A. Gertzog, “Accommodation of a scientific conception: Toward a theory of conceptual change,” Science Education, vol. 66, no. 2, pp. 211-227, 1982.
[32]	K.E. Chang, Y.L. Chen, H.Y. Lin, and Y.T. Sung, “Effects of learning support in simulation-based physics learning,” Computers & Education, vol. 51, no. 4, pp. 1486-1498, 2008.
[33]	“Computer Science for All Initiative” URL:  https://obamawhitehouse.archives.gov/blog/2016/01/30/computer-science-all.
[34]	“十二年國民基本教育課程綱要國民中小學暨普通型高級中等學校科技領域”  URL: https://www.naer.edu.tw/files/15-1000-15281,c639-1.php?Lang=zh-tw.
[35]	任鍵忠，十二年國民基本教育「科技領域-資訊科技科」課程學習表現應具備能力指標研究，朝陽科技大學資訊管理系碩士論文(指導教授：陳榮昌)，2018。
[36]	D.M. Kurland and R.D. Pea, “Children's mental models of recursive LOGO programs,” Journal of Educational Computing Research, vol. 1, no. 2, pp. 235-243, 1985.
[37]	I. Lee, F. Martin, J. Denner, B. Coulter, W. Allan, J. Erickson, J. Malyn-Smith, and L. Werner, “Computational thinking for youth in practice,” ACM Inroads, vol. 2, no. 1, pp. 32-37, 2011.
[38]	S. Papert, Mindstorms: Children, Computers, and Powerful Ideas, Basic Books, 1980.
[39]	“Logo Programming Language” URL: https://el.media.mit.edu/logo-foundation/what_is_logo/logo_programming.html.
[40]	M. Resnick, J. Maloney, A. Monroy-Hernández, N. Rusk, E. Eastmond, K. Brennan, A. Millner, E. Rosenbaum, J. Silver, B. Silverman and Y. Kafai, “Scratch: Programming for all,” Communications of the ACM, vol. 52, no. 11, pp. 60-67, 2009.
[41]	M. Resnick, “All I really need to know (about creative thinking) I learned (by studying how children learn) in kindergarten,” In Proceedings of the 6th ACM SIGCHI conference on Creativity & cognition, pp. 1-6, 2007.
[42]	D. Wolber, H. Abelson, E. Spertus, and L. Looney, App Inventor: Create Your Own Android Apps, O'Reilly Media, Inc., 2011.
[43]	S. Papadakis and V. Orfanakis, “Comparing novice programing environments for use in secondary education: App Inventor for Android vs. Alice,” International Journal of Technology Enhanced Learning, vol. 10, no. 1-2, pp. 44-72, 2018.
[44]	“MIT App Inventor” URL: https://appinventor.mit.edu/.
[45]	T.D. Jong and W.R.V. Joolingen, “Scientific discovery learning with computer simulations of conceptual domains,” Review of Educational Research, vol. 68, no. 22, pp. 179-201, 1998.
[46]	B. J. Wadsworth, Piaget's Theory of Cognitive and Affective Development: Foundations of Constructivism, Longman Publishing, 1996. 
[47]	L.P. Steffe and J.E. Gale, Constructivism in Education, Lawrence Erlbaum, 1995.
[48]	E. Ackermann, “Piaget’s constructivism, Papert’s constructionism: What’s the difference,” Future of learning group publication, vol. 5, no. 3, pp. 438, 2001.
[49]	J. A. Jaramillo, “Vygotsky's sociocultural theory and contributions to the development of constructivist curricula,” Education, vol. 117, no. 1, pp. 133-141, 1996.
[50]	A. Csizmadia, B. Standl, and J. Waite, “Integrating the constructionist learning theory with computational thinking classroom activities,” Informatics in Education, vol. 18, no. 1, pp. 41-67, 2019.
[51]	E. Von Glasersfeld, Radical Constructivism, Routledge, 2013.
[52]	D. Jonassen, M. Davidson, M. Collins, J. Campbell, and B.B. Haag, “Constructivism and computer-mediated communication in distance education,” American Journal of Distance Education, vol. 9, no. 2, pp. 7-26, 1995.
[53]	G. K. W. Wong, and H. Y. Cheung, “Exploring children’s perceptions of developing twenty-first century skills through computational thinking and programming,” Interactive Learning Environments, vol. 28, no. 4, pp. 438-450, 2020.
[54]	L. A. Suchman, Plans and Situated Action: The Problem of Human-Machine Communication, Cambridge University Press, 1987.
[55]	簡頌沛，從情境認知師徒制的觀點，探討科學實習教師的信念、知識與實務之轉變。國立臺灣師範大學科學教育學系碩士論文(指導教授：吳心楷)，2007。
[56]	J. Lave, and E. Wenger, Situated Learning: Legitimate Peripheral Participation, Cambridge University Press, 1991.
[57]	H. McLellan, “Situated learning in focus: Instruction to special issue,” Educational Technology, vol. 33, no.3, pp. 5-9, 1993.
[58]	M. F. Young and J. M. Kulikowich, “Anchored instruction and anchored assessment: An ecological approach to measuring situated learning,” Paper presented at the Annual Meeting of the American Educational Research Association, pp. 1-21, 1992.
[59]	D. J. Ton and W. R. Van Joolingen, “An extended dual search space model of scientific discovery learning,” Instructional Science, vol. 25, no. 5, pp. 307-346, 1997.
[60]	R. E. Simamora, and S. Saragih, “Improving students' mathematical problem solving ability and self-efficacy through guided discovery learning in local culture context,” International Electronic Journal of Mathematics Education, vol. 14, no. 1, pp. 61-72, 2019.
[61]	J. Zhang, Q. Chen, Y. Sun, and D. J. Reid, “Triple scheme of learning support design for scientific discovery learning based on computer simulation: experimental research,” Journal of Computer Assisted Learning, vol. 20, no. 4, pp. 269-282, 2004.
[62]	張春興，教育心理學－三化取向的理論與實踐。重修二版，東華書局，2013。
[63]	J.S. Bruner, “The course of cognitive growth,” American Psychologist, vol. 19, no. 1, pp. 1-15, 1964.
[64]	“Teach, Learn, and Make with Raspberry Pi – Raspberry Pi” URL: https://www.raspberrypi.org/.
[65]	J. Sobota, R. PiŜl, P. Balda and M. Schlegel, “Raspberry Pi and Arduino boards in control education,” IFAC Proceedings Volumes, vol. 46, no. 17, pp.  7-12, 2013.
[66]	R. G. Babu, P. Karthika, and V. A. Rajan, “Secure IoT systems using raspberry Pi machine learning artificial intelligence,” In International Conference on Computer Networks and Inventive Communication Technologies, pp. 797-805. Springer, Cham, 2019.
[67]	X. Wang, Y. Han, C. Wang, Q. Zhao, X. Chen, and M. Chen, “In-edge AI: Intelligentizing mobile edge computing, caching and communication by federated learning,” IEEE Network, vol. 33, no. 5, pp. 156-165, 2019.
[68]	S. Cass, “Taking AI to the edge: Google's TPU now comes in a maker-friendly package,” IEEE Spectrum, vol. 56, no. 5, pp. 16-17, 2019.
[69]	“Coral.ai” URL: https://coral.ai/.
[70]	S. Cass, “Nvidia makes it easy to embed AI: The Jetson nano packs a lot of machine-learning power into DIY projects-[Hands on],” IEEE Spectrum, vol. 57, no. 7, pp. 14-16, 2020.
[71]	“NVIDIA Jetson Nano Developer Kit” URL:  https://developer.nvidia.com/embedded/jetson-nano-developer-kit. 
[72]	“UP Board” URL:  https://up-board.org.
[73]	“ASUS Tinker Edge T” URL:  https://www.asus.com/tw/AIoT-Industrial-Solutions/Tinker-Edge-T/.
[74]	L. Paull, J. Tani, H. Ahn, J. Alonso-Mora, L. Carlone, M. Cap and D. Hoehener, “Duckietown: An open, inexpensive and flexible platform for autonomy education and research,” 2017 IEEE International Conference on Robotics and Automation (ICRA), pp. 1497-1504, 2017.
[75]	G. Karalekas, S. Vologiannidis, and J. Kalomiros, “EUROPA: A case study for teaching sensors, data acquisition and robotics via a ROS-based educational robot,” Sensors, vol. 20, no. 9, pp. 2469, 2020.
[76]	“Duckietown – A playful way to learn robotics” URL: https://www.duckietown.org/.
[77]	“Donkey® Car - Home” URL: https://www.donkeycar.com. 
[78]	“The MIT RACECAR” URL: https://mit-racecar.github.io.
[79]	J. Betz, A. Wischnewski, A. Heilmeier, F. Nobis, T. Stahl, L.  Hermansdorfer, and M. Lienkamp, “A software architecture for an autonomous racecar,” In 2019 IEEE 89th Vehicular Technology Conference (VTC2019-Spring), pp. 1-6, 2019.
[80]	“MIT Racecar” URL: https://mit-racecar.github.io/.
[81]	R. Suenaga, and K. Morioka, “Development of a Web-Based Education System for Deep Reinforcement Learning-Based Autonomous Mobile Robot Navigation in Real World,” In 2020 IEEE/SICE International Symposium on System Integration (SII), pp. 1040-1045, IEEE, 2020.
[82]	“AWS DeepRacer” URL: https://aws.amazon.com/deepracer/.
[83]	A. Pester, and M. Schrittesser, “Object detection with raspberry Pi3 and movidius neural network stick,” In 2019 5th Experiment International Conference (exp. at'19), pp. 326-330, IEEE, 2019.
[84]	J. Hochstetler, R. Padidela, Q. Chen, Q. Yang, and S. Fu, “Embedded deep learning for vehicular edge computing,” In 2018 IEEE/ACM Symposium on Edge Computing (SEC), pp. 341-343, 2018.
[85]	A. Khan, A. Sohail, U. Zahoora, and A. S. Qureshi, “A survey of the recent architectures of deep convolutional neural networks,” Artificial Intelligence Review, pp. 1-62, 2020.
[86]	S. Kornblith, J. Shlens, and Q. V. Le, “Do better imagenet models transfer better?” In Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 2661-2671, 2019.
[87]	A. G. Howard, M. Zhu, B. Chen, D. Kalenichenko, W. Wang, T. Weyand, M. Andreetto, and H. Adam, “Mobilenets: Efficient convolutional neural networks for mobile vision applications,” arXiv preprint arXiv:1704.04861, 2017
[88]	H. Li, K. Ota, and M. Dong, “Learning IoT in edge: Deep learning for the Internet of Things with edge computing,” IEEE network, vol. 32, no. 1, pp. 96-101, 2018.
[89]	L. C. Chen, Y. Zhu, G. Papandreou, F. Schroff, and H. Adam, “Encoder-decoder with atrous separable convolution for semantic image segmentation,” In Proceedings of the European conference on computer vision (ECCV), pp. 801-818, 2018.
[90]	F. Haslam, and D. F. Treagust, “Diagnosing secondary students’ misconceptions of photosynthesis and respiration in plants using a two-tier multiple choice instrument,” Journal of Biological Education, vol. 21, no. 3, pp. 203-211, 1987.
[91]	陳裕隆，融入問題引導策略的模擬式學習環境之應用成效與學習歷程研究。國立臺灣師範大學資訊教育研究所博士論文(指導教授：張國恩，宋曜廷)，2014。