近年來，生成對抗網路(Generative Adversarial Networks, GANs)的提出帶給人工智慧領域一個另類的思路，並已被驗證其能有效生成難以辨識真偽的虛擬假圖。基於GAN的架構，部分學者已開發適用於數值分析之生成網路(generator network, GN)與鑑別網路(discriminator network, DN)的對抗流程，以產生更佳的虛擬樣本。然而在許多領域中，如醫療與工業生產，常因個案數不足或成本高昂而有樣本取得困難之狀況。在此種小樣本的情形下，數值分析的DN並無法進行充分之學習，同時並無法完全判斷GN產生之樣本品質的良窳。因此，如何改善小樣本在DN網路的泛用性是一個值得探討的議題。本研究擬採用與GN網路不同之第三方的樣本產生方式，如整體趨勢擴張技術(mega-trend-diffusion, MTD)，增加訓練樣本之數量而達DN充分學習之結果，除避免DN因使用GN所產生之虛擬樣本進行訓練所導致的偏誤與過度配適之情形，亦期能改善DN之模型泛用性進而穩定GAN於數值樣本產生之結果。

Generative Adversarial Networks (GANs) are powerful generative models, but its capability is limited to the training sample size. The recently proposed Wasserstein GAN (WGAN) makes progress toward stable training of GANs but can still generate only low-quality samples or become “overfitted” when encountering the situation of small data set. To solve the problem of insufficient training data set, we proposed a method using virtual sample generation method to generate enough dataset before the training of WGAN network to enhance the training effectiveness. In our research, we randomly selected small-sample-sized samples from the population to simulate the situation of insufficient dataset. Then we used Mega-Trend-Diffusion method as the virtual sample generation method to generate samples and combined the virtual samples with small-data-sized real data as the input of the WGAN. Then we tested the output using classification model compare with the standard WGAN to see if there is progress in accuracy. The results showed that our proposed method performs better than standard WGAN when the data size is extremely small. We concluded that our method enhanced the capability of WGAN and improved the quality of the generated samples in the context of small data set.

Anthony, M., & Biggs, N. (1993). Computational learning theory for artificial neural networks. In North-Holland Mathematical Library (Vol. 51, pp. 25-62): Elsevier.
Arjovsky, M., Chintala, S., & Bottou, L. (2017). Wasserstein gan. arXiv preprint arXiv:1701.07875.
Chawla, N. V., Bowyer, K. W., Hall, L. O., & Kegelmeyer, W. P. (2002). SMOTE: synthetic minority over-sampling technique. Journal of artificial intelligence research, 16, 321-357.
Chongfu, H. (1997). Principle of information diffusion. Fuzzy sets and Systems, 91(1), 69-90.
Cover, T., & Hart, P. (1967). Nearest neighbor pattern classification. IEEE transactions on information theory, 13(1), 21-27.
Efron, B., & Tibshirani, R. J. (1994). An introduction to the bootstrap: CRC press.
Fiore, U., De Santis, A., Perla, F., Zanetti, P., & Palmieri, F. (2019). Using generative adversarial networks for improving classification effectiveness in credit card fraud detection. Information Sciences, 479, 448-455.
Frid-Adar, M., Diamant, I., Klang, E., Amitai, M., Goldberger, J., & Greenspan, H. (2018). GAN-based synthetic medical image augmentation for increased CNN performance in liver lesion classification. Neurocomputing, 321, 321-331.
I. Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde-Farley, S. Ozair, A. Courville, and Y. Bengio. (2014). Generative adversarial nets. Advances in Neural Information Processing Systems (NIPS), 2014-December, 2672–2680.
Gulrajani, I., Ahmed, F., Arjovsky, M., Dumoulin, V., & Courville, A. C. (2017). Improved training of wasserstein gans. Paper presented at the Advances in neural information processing systems.
Goyal, P., Dollár, P., Girshick, R., Noordhuis, P., Wesolowski, L., Kyrola, A., . . . He, K. (2017). Accurate, large minibatch sgd: Training imagenet in 1 hour. arXiv preprint arXiv:1706.02677.
Huang, C., & Moraga, C. (2004). A diffusion-neural-network for learning from small samples. International Journal of Approximate Reasoning, 35(2), 137-161.
Jang, J.-S. (1993). ANFIS: adaptive-network-based fuzzy inference system. IEEE transactions on systems, man, and cybernetics, 23(3), 665-685.
Karras, T., Laine, S., & Aila, T. (2019). A style-based generator architecture for generative adversarial networks. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2019-June, 4396-4405.
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017). Imagenet classification with deep convolutional neural networks. Communications of the ACM, 60(6), 84-90.
Li, D. C., Liu, C. W., & Hu, S. C. (2010). A learning method for the class imbalance problem with medical data sets. Comput Biol Med, 40(5), 509-518.
Li, D. C., Tsai, T. I., & Shi, S. (2008). A prediction of the dielectric constant of multi-layer ceramic capacitors using the mega-trend-diffusion technique in powder pilot runs: case study. International Journal of Production Research, 47(1), 51-69.
Li, D.-C., Chen, C.-C., Chang, C.-J., & Chen, W.-C. (2012). Employing box-and-whisker plots for learning more knowledge in TFT-LCD pilot runs. International Journal of Production Research, 50(6), 1539-1553.
Li, D.-C., Chen, C.-C., Chen, W.-C., & Chang, C.-J. (2012a). Employing dependent virtual samples to obtain more manufacturing information in pilot runs. International Journal of Production Research, 50(23), 6886-6903.
Li, D.-C., Chen, L.-S., & Lin, Y.-S. (2010). Using Functional Virtual Population as assistance to learn scheduling knowledge in dynamic manufacturing environments. International Journal of Production Research, 41(17), 4011-4024.
Li, D.-C., Hsu, H.-C., Tsai, T.-I., Lu, T.-J., & Hu, S. C. (2007). A new method to help diagnose cancers for small sample size. Expert Systems with Applications, 33(2), 420-424.
Li, D.-C., Huang, W.-T., Chen, C.-C., & Chang, C.-J. (2013). Employing virtual samples to build early high-dimensional manufacturing models. International Journal of Production Research, 51(11), 3206-3224.
Li, D.-C., & Lin, Y.-S. (2006). Using virtual sample generation to build up management knowledge in the early manufacturing stages. European Journal of Operational Research, 175(1), 413-434.
Li, D.-C., Wu, C., & Chang, F. M. (2005). Using data-fuzzification technology in small data set learning to improve FMS scheduling accuracy. The International Journal of Advanced Manufacturing Technology, 27(3-4), 321-328.
Li, D.-C., Wu, C.-S., Tsai, T.-I., & Lina, Y.-S. (2007a). Using mega-trend-diffusion and artificial samples in small data set learning for early flexible manufacturing system scheduling knowledge. Computers & Operations Research, 34(4), 966-982.
Liu, Y., Zhou, Y., Liu, X., Dong, F., Wang, C., & Wang, Z. (2019). Wasserstein GAN-Based Small-Sample Augmentation for New-Generation Artificial Intelligence: A Case Study of Cancer-Staging Data in Biology. Engineering, 5(1), 156-163.
Mirza, M., & Osindero, S. (2014). Conditional generative adversarial nets. arXiv preprint arXiv:1411.1784.
Niyogi, P., Girosi, F., & Poggio, T. (1998). Incorporating prior information in machine learning by creating virtual examples. Proceedings of the IEEE, 86(11), 2196-2209.
Papari, M. M., Yousefi, F., Moghadasi, J., Karimi, H., & Campo, A. (2011). Modeling thermal conductivity augmentation of nanofluids using diffusion neural networks. International Journal of Thermal Sciences, 50(1), 44-52.
Spanhol, F. A., Oliveira, L. S., Petitjean, C., & Heutte, L. (2016). Breast cancer histopathological image classification using convolutional neural networks. Paper presented at the 2016 international joint conference on neural networks (IJCNN).
Tian, C., Li, C., Zhang, G., & Lv, Y. (2019). Data Driven Parallel Prediction of Building Energy Consumption Using Generative Adversarial Nets. Energy and Buildings, 186, 230-243.
Tsai, T.-I., & Li, D.-C. (2008). Approximate modeling for high order non-linear functions using small sample sets. Expert Systems with Applications, 34(1), 564-569.
Wang, Q., Zhou, X., Wang, C., Liu, Z., Huang, J., Zhou, Y., . . . Cheng, J.-Z. (2019). WGAN-Based Synthetic Minority Over-Sampling Technique: Improving Semantic Fine-Grained Classification for Lung Nodules in CT Images. IEEE Access, 7, 18450-18463.
Wang, W., Wang, C., Cui, T., & Li, Y. (2020). Study of Restrained Network Structures for Wasserstein Generative Adversarial Networks (WGANs) on Numeric Data Augmentation. IEEE Access, 8, 89812-89821.
Yamashita, R., Nishio, M., Do, R. K. G., & Togashi, K. (2018). Convolutional neural networks: an overview and application in radiology. Insights into imaging, 9(4), 611-629.
Yang, Q., Yan, P., Zhang, Y., Yu, H., Shi, Y., Mou, X., . . . Wang, G. (2018). Low-Dose CT Image Denoising Using a Generative Adversarial Network With Wasserstein Distance and Perceptual Loss. IEEE Transactions on Medical Imaging, 37(6), 1348-1357.
Zhu, J., Zhang, J., Qiu, B., Liu, Y., Liu, X., & Chen, L. (2019). Comparison of the automatic segmentation of multiple organs at risk in CT images of lung cancer between deep convolutional neural network-based and atlas-based techniques. Acta Oncol, 58(2), 257-264.