在國內的「教育4.0」政策的實施之際，藉由科技輔助學習來達成自我學習的現象日漸普遍。而電子電路實驗就非電機電子領域之學習者而言，並非容易入門之領域，而就電機電子本科系之師生而言，電子電路實驗之時間與人力上的負擔則較為沉重，複雜的實驗於評分階段並無法輕易完成，往往教師的評分便會由實驗能否運作作為評分之依據，造成分數非0即100之現象，因此該門學科常出現學生不易學習且教師不易審評之棘手問題。
得益於近幾年電腦視覺系統發展之勢，本研究之方法旨在利用電腦視覺系統改善電子電路實驗學習及審評不易之現況，利用Yolo即時影像辨識系統完成各種元件辨識及定位接著透過一連串演算法比對出學習者所操作之實驗評分，並且針對環境之雜訊進行影像之正規化，將電路板之影像進行分割與映射，於充滿各種元件的實驗環境依舊可以進行辨識、比對等流程。
於方法中亦利用語意之嵌入以及LSTM之深度神經網路對電子實驗種類進行分類，在教學雙方無法於當下取得實驗精簡電路圖之情況下利用電子實驗之元件種類及數量分辨出實驗項目，並進一步對其進行評分，以及向使用者告知元件有無缺失，是否該補上或移除缺少或多餘之元件。利用電腦視覺系統、深度神經網路以及一系列演算法達成科技輔助教育之目的。

With the implementation of the "Education 4.0" policy in Taiwan, it is becoming increasingly common to use technology to assist learning to achieve self-learning. For non-electrical and electronic students, electronic circuit experiments are not an easy field to enter, and for electrical and electronic faculty and students, the time and labor burden of electronic circuit experiments is relatively heavy. The subject is often difficult for students to learn and teachers to evaluate.
This study aims to improve the learning and evaluation of electronic circuit experiments by using computer vision systems, which have been developed in recent years. The image of the circuit board is divided and mapped, and the process of recognition and comparison can still be performed in an experimental environment full of various components.
The method also uses semantic embedding and deep neural networks of LSTM to classify the types of electronic experiments, and to distinguish the types and numbers of components of electronic experiments, and to further score them, and to inform the user whether there are missing components, and whether to replace or remove missing or redundant components. Computer vision systems, deep neural networks, and a series of algorithms are used to achieve the goal of technology-assisted education.

[1] B. Means, “Using technology to support education reform,” 1993.
[2] E. Cloete, “Electronic education system model,” Computers & education, vol. 36, no. 2, pp. 171–182, 2001.
[3] B. Smith, “Ontology,” in The furniture of the world, pp. 47–68, Brill, 2012.
[4] C. López, L. M. Cysneiros, and H. Astudillo, “Ndr ontology: Sharing and reusing nfr and design rationale knowledge,” in 2008 First International Workshop on Managing Requirements Knowledge, pp. 1–10, 2008.
[5] S. R. Safavian and D. Landgrebe, “A survey of decision tree classifier methodology,” IEEE transactions on systems, man, and cybernetics, vol. 21, no. 3, pp. 660–674, 1991.
[6] H. Zhuge and L. Zheng, “Ranking semantic-linked network.,” WWW (Posters), vol. 121, 2003.
[7] S. Wang, Y. Sun, H. Zhang, X. Yu, and R. Bie, “Advances of the semantic link network,” in 2012 Eighth International Conference on Semantics, Knowledge and Grids, pp. 120– 127, 2012.
[8] P. P.-S. Chen, “The entity-relationship model—toward a unified view of data,” ACM transactions on database systems (TODS), vol. 1, no. 1, pp. 9–36, 1976.
[9] C. W. Bachman, “The programmer as navigator,” in Readings in Artificial Intelligence and Databases, pp. 52–59, Elsevier, 1989.
[10] C. W. Bachman, “Software for random access processing,” Datamation, vol. 11, no. 4, pp. 36–41, 1965.
[11] C. W. Bachman, “Data structure diagrams,” ACM SIGMIS Database: The DATABASE for Advances in Information Systems, vol. 1, no. 2, pp. 4–10, 1969.
[12] R. W. Engles, “An analysis of the april 1971 data base task group report,” in Proceedings of the 1971 ACM SIGFIDET (now SIGMOD) Workshop on Data Description, Access and Control, pp. 69–91, 1971.
[13] Z. Hai and L. Zheng, “Ranking semantic-linked network,” in Proceedings of the 12th International Conference on World Wide Web, pp. 114–117, 2003.
[14] C. Manning, I. Introduction. ISEAS Publishing, 1988.
[15] Y. Zhang, R. Jin, and Z.-H. Zhou, “Understanding bag-of-words model: a statistical framework,” International Journal of Machine Learning and Cybernetics, vol. 1, no. 1- 4, pp. 43–52, 2010.
[16] Y. Bengio, R. Ducharme, P. Vincent, and C. Janvin, “A neural probabilistic language model,” The journal of machine learning research, vol. 3, pp. 1137–1155, 2003. 46
[17] J. Turian, L. Ratinov, and Y. Bengio, “Word representations: a simple and general method for semi-supervised learning,” in Proceedings of the 48th annual meeting of the association for computational linguistics, pp. 384–394, 2010.
[18] A. Mnih and G. Hinton, “Three new graphical models for statistical language modelling,” in Proceedings of the 24th international conference on Machine learning, pp. 641–648, 2007.
[19] A. Mnih and K. Kavukcuoglu, “Learning word embeddings efficiently with noisecontrastive estimation,” in Advances in neural information processing systems, pp. 2265–2273, 2013.
[20] T. Mikolov, M. Karafiát, L. Burget, J. Černockỳ, and S. Khudanpur, “Recurrent neural network based language model,” in Eleventh annual conference of the international speech communication association, 2010.
[21] T. Mikolov, K. Chen, G. Corrado, and J. Dean, “Efficient estimation of word representations in vector space,” arXiv preprint arXiv:1301.3781, 2013.
[22] T. Mikolov, I. Sutskever, K. Chen, G. S. Corrado, and J. Dean, “Distributed representations of words and phrases and their compositionality,” in Advances in neural information processing systems, pp. 3111–3119, 2013.
[23] A. Conneau, D. Kiela, H. Schwenk, L. Barrault, and A. Bordes, “Supervised learning of universal sentence representations from natural language inference data,” arXiv preprint arXiv:1705.02364, 2017.
[24] A. Talman, A. Yli-Jyrä, and J. Tiedemann, “Natural language inference with hierarchical bilstm max pooling architecture,” arXiv preprint arXiv:1808.08762, 2018.
[25] T. Chung, B. Xu, Y. Liu, C. Ouyang, S. Li, and L. Luo, “Empirical study on character level neural network classifier for chinese text,” Engineering Applications of Artificial Intelligence, vol. 80, pp. 1–7, 2019.
[26] J. R. Martinez-Rico, J. Martinez-Romo, and L. Araujo, “Can deep learning techniques improve classification performance of vandalism detection in wikipedia?,” Engineering Applications of Artificial Intelligence, vol. 78, pp. 248–259, 2019.
[27] L. Yao, Y. Zhang, Q. Chen, H. Qian, B. Wei, and Z. Hu, “Mining coherent topics in documents using word embeddings and large-scale text data,” Engineering Applications of Artificial Intelligence, vol. 64, pp. 432–439, 2017.
[28] Y. LeCun, Y. Bengio, and G. Hinton, “Deep learning,” nature, vol. 521, no. 7553, pp. 436–444, 2015.
[29] Y. A. LeCun, L. Bottou, G. B. Orr, and K.-R. Müller, “Efficient backprop,” in Neural networks: Tricks of the trade, pp. 9–48, Springer, 2012.
[30] Y. LeCun, K. Kavukcuoglu, and C. Farabet, “Convolutional networks and applications in vision,” in Proceedings of 2010 IEEE international symposium on circuits and systems, pp. 253–256, IEEE, 2010. 47
[31] D. Eigen, C. Puhrsch, and R. Fergus, “Depth map prediction from a single image using a multi-scale deep network,” arXiv preprint arXiv:1406.2283, 2014.
[32] Y. LeCun, L. Bottou, Y. Bengio, and P. Haffner, “Gradient-based learning applied to document recognition,” Proceedings of the IEEE, vol. 86, no. 11, pp. 2278–2324, 1998.
[33] Y. LeCun, Y. Bengio, et al., “Convolutional networks for images, speech, and time series,” The handbook of brain theory and neural networks, vol. 3361, no. 10, p. 1995, 1995.
[34] W. C. Gartner, “Image formation process,” Journal of travel & tourism marketing, vol. 2, no. 2-3, pp. 191–216, 1994.
[35] C. Torras, Computer vision: theory and industrial applications. Springer Science & Business Media, 2012.
[36] G. J. Agin, “Computer vision systems for industrial inspection and assembly,” Computer, vol. 13, no. 05, pp. 11–20, 1980.
[37] M. Aldalil, “A new method for measuring leveling heights using computer vision techniques,” in 2020 International Conference on Computer, Control, Electrical, and Electronics Engineering (ICCCEEE), pp. 1–6, 2021.
[38] X. Wang, “Moving window-based double haar wavelet transform for image processing,” IEEE Transactions on Image Processing, vol. 15, no. 9, pp. 2771–2779, 2006.
[39] C.-C. Chang, J.-Y. Hsiao, and C.-P. Hsieh, “An adaptive median filter for image denoising,” in 2008 Second International Symposium on Intelligent Information Technology Application, vol. 2, pp. 346–350, 2008.
[40] T. Chen, K.-K. Ma, and L.-H. Chen, “Tri-state median filter for image denoising,” IEEE Transactions on Image processing, vol. 8, no. 12, pp. 1834–1838, 1999.
[41] N. Otsu, “A threshold selection method from gray-level histograms,” IEEE transactions on systems, man, and cybernetics, vol. 9, no. 1, pp. 62–66, 1979.
[42] L. Lin and S. Yang, “Weighted two-dimensional otsu threshold approached for image segmentation,” in 2019 IEEE Symposium Series on Computational Intelligence (SSCI), pp. 1002–1006, 2019.
[43] J. F. Canny, “Finding edges and lines in images.,” tech. rep., MASSACHUSETTS INST OF TECH CAMBRIDGE ARTIFICIAL INTELLIGENCE LAB, 1983.
[44] G. Hao, L. Min, and H. Feng, “Improved self-adaptive edge detection method based on canny,” in 2013 5th International Conference on Intelligent Human-Machine Systems and Cybernetics, vol. 2, pp. 527–530, 2013.
[45] H. Lu and J. Yan, “Window frame obstacle edge detection based on improved canny operator,” in 2019 3rd International Conference on Electronic Information Technology and Computer Engineering (EITCE), pp. 493–496, 2019.
[46] J. Fu, J. Wang, Y. Rui, X.-J. Wang, T. Mei, and H. Lu, “Image tag refinement with view-dependent concept representations,” IEEE Transactions on Circuits and Systems for Video Technology, vol. 25, no. 8, pp. 1409–1422, 2014. 48
[47] K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” in Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 770–778, 2016.
[48] J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, “You only look once: Unified, realtime object detection,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2016.
[49] J. Redmon and A. Farhadi, “Yolo9000: better, faster, stronger,” in Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 7263–7271, 2017.
[50] J. Redmon and A. Farhadi, “Yolov3: An incremental improvement,” arXiv preprint arXiv:1804.02767, 2018.
[51] A. Bochkovskiy, C.-Y. Wang, and H.-Y. M. Liao, “Yolov4: Optimal speed and accuracy of object detection,” arXiv preprint arXiv:2004.10934, 2020.
[52] C. L. Liu, A study in machine-aided learning. PhD thesis, Massachusetts Institute of Technology, 1960.
[53] S. A. Papert, “Uses of technology to enhance education,” 1973.
[54] M. Minsky, “Form and content in computer science (1970 acm turing lecture),” Journal of the ACM (JACM), vol. 17, no. 2, pp. 197–215, 1970.
[55] Z. Qinfei, “Effective combination between e-learning and km in higher education: By the support of information technology,” in 2010 2nd IEEE International Conference on Information Management and Engineering, pp. 533–536, 2010.
[56] Z. Wang, J. Liu, and R. Dong, “Intelligent auto-grading system,” in 2018 5th IEEE International Conference on Cloud Computing and Intelligence Systems (CCIS), pp. 430– 435, 2018.
[57] X. Li, T. Yue, X. Huang, Z. Yang, and G. Xu, “Bags: an automatic homework grading system using the pictures taken by smart phones,” arXiv preprint arXiv:1906.03767, 2019.
[58] 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.
[59] Ö. Demir, A. Soysal, A. Arslan, B. Yürekli, and Ö. Yılmazel, “Automatic grading system for programming homework,” Computer Science Education: Innovation and Technology, CSEIT, 2010.
[60] D. M. Rao, “Experiences with auto-grading in a systems course,” in 2019 IEEE Frontiers in Education Conference (FIE), pp. 1–8, 2019.
[61] Z.-y. Wen, L.-m. Shen, H.-p. Jing, and K. Fang, “Color and shape grading of citrus fruit based on machine vision with fractal dimension,” in 2010 3rd International Congress on Image and Signal Processing, vol. 2, pp. 898–903, 2010.
[62] J. Li, J. Gu, Z. Huang, and J. Wen, “Application research of improved yolo v3 algorithm in pcb electronic component detection,” Applied Sciences, vol. 9, no. 18, p. 3750, 2019. 49
[63] 戴琬諭et al., Scratch 圖像導引式教學法對認知負荷與學習成效影響之探討. PhD thesis, 2014.
[64] L. Deng, “The mnist database of handwritten digit images for machine learning research [best of the web],” IEEE Signal Processing Magazine, vol. 29, no. 6, pp. 141–142, 2012.