電力網路的穩定與變壓器的健康狀況息息相關。乾式電力變壓器在電力系統中扮演至關重要的腳色。當發生各種型態的變壓器故障，將會降低電力系統的供應與韌性，並且容易引起重大事故和嚴重的經濟損失。對電力變壓器運行狀態下的各種過熱故障進行檢測是設法避免電力系統停擺的必要條件。到目前為止，已經提出了許多診斷方法來監測變壓器的運行。這些方法大多無法在線檢測診斷，容易受到噪訊干擾，維護成本高，對變壓器的實時監控系統造成障礙。
在本文中，基於紅外線熱圖像的模鑄型乾式變壓器過熱故障的監測系統之相關實驗設置，透過系統來擷取模鑄型乾式變壓器之不同負載下正常運轉的熱圖像。鑒於故障圖像在實際運轉中不易獲得，本研究引用故障痕跡方法，透過製作不同型態及不同溫度的故障痕跡，將之與正常狀態熱圖像合成以蒐集為 9 種不同故障型態的數據集，應用於本研究所提出的異常狀態檢測模型與故障分類辨識模型的相關實驗，
在異常狀態檢測模型方面，其目的為透過異常狀態檢測模型與逐像素 (Pixel-wise) 異常檢測算法能夠檢測模鑄型乾式變壓器的運轉狀態是否正常。首先，獲取變壓器的正常狀態熱圖像並收集用於訓練和測試數據集。接下來，訓練基於變分自動編碼器的生成對抗網路以生成具有從重負載到輕負載的不同運行條件的正常圖像。通過原始圖像和重建圖像之間的像素級餘弦差異，獲得具有錯誤特徵的殘差圖像。最後，我們在正常和異常測試圖像上評估訓練模型和異常檢測方法，以證明所提出工作的有效性和性能。
另外在故障分類辨識方面，目的為透過設計故障分類辨識模型能夠學習對模鑄型乾式變壓器的故障型態執行分類辨識任務，首先分別進行重建模型與分類模型的模型訓練評估分析，接著模型的測試結果評估並與其他不同分類方法相互比對結果。與現有的深度學習算法相比，實驗結果證明了所提模型的巨大優勢，可以獲得輕量級、存儲量小、推理時間快和診斷準確率足夠的綜合性能。

The stability of the power network is closely related to the health of the transformers. Cast resin dry-type transformers are quite critical equipment in power systems. When various types of transformer failures occur, the supply and resilience of the power system will be reduced, and it is easy to cause major accidents and serious economic losses. Accurately identifying different types of cast resin transformer overheating faults in operation is an important measure to prevent power system collapse. To date, many diagnostic methods have been proposed in the literature to monitor the operation of transformers. Most of these methods can only be detected and diagnosed offline, are easily affected by noise, and have high maintenance costs, which hinder the development of real-time monitoring systems for transformers.
In this work, the related experimental settings of the propsed system for overheating faults of cast-resin dry-type transformers based on infrared thermal images are used to capture the thermal images of normal operation of the transformers under different loading. In view of the fact that fault images are not easy to obtain in actual operation, the fault trace method is used in this study. By producing fault traces of different types and different temperatures, they are synthesized with normal state thermal images for collecting the dataset with 9 different fault types, which applied to the experiments of the proposed fault classification identification model and anomalydetection model in this study,
The purpose of the proposed abnomaly detection model is to detect whether the operation state of the cast-resin transformer is normal after computing by the pixel-wise abnormal detection algorithm. First, get normal state thermal images of the transformer and collect these for model learning. Next, a variational autoencoder generator with adversarial learing is trained to reconstruct normal pictures with different loading. The residual image with fault trace features is calculated by pixel-level difference between the real image and the regenerated image. Finally, the trained model and anomaly detection method are estimated by using normal and anomalous test images under some evaluation modes to manifest the benefits and efficacy of our proposed approach.
In addition, the goal of the proposed fault classification and identification is to perform classification and identification tasks on the fault types of cast-resin dry-type transformers. Firstly, the training and analysis of the reconstruction model and the classification model are carried out respectively, and then the test results of the model are evaluated and compared with other different classification methods. Compared with existing deep learning approaches, the testing results demonstrate the great achievement of the proposed model, which can accomplish the leading advantages of less weight numbers and storage size, quickly inference and satisfied diagnostic accuracy.

參考文獻

[1] Chen, P.; Huang, Y.; Zeng, F.; Jin, Y.; Zhao, X.; Wang, J. Review on insulation and reliability of dry-type transformer. In Proceedings of the 2019 IEEE Sustainable Power and Energy Conference (iSPEC), Beijing, China, 20–24 November 2019.
[2] Mafra, R.; Magalhães, E.; Anselmo, B.; Belchior, F.; e Silva, S.L. Winding hottest-spot temperature analysis in dry-type trans-former using numerical simulation. Energies 2018, 12, 68.
[3] Duan, X.; Zhao, T.; Liu, J.; Zhang, L.; Zou, L. Analysis of Winding Vibration Characteristics of Power Transformers Based on the Finite-Element Method. Energies 2018, 11, 2404, doi:10.3390/en11092404.
[4] Liu, Y.; Li, X.; Li, H.; Fan, X. Global Temperature Sensing for an Operating Power Transformer Based on Raman Scattering. Sensors 2020, 20, 4903. https://doi.org/10.3390/s20174903.
[5] Sen, P. Application guidelines for dry-type distribution power transformers. In Proceedings of the IEEE Technical Conference on Industrial and Commercial Power Systems, St. Louis, MO, USA, 4–8 May 2003. https://doi.org/10.1109/icps.2003.1201495.
[6] Rajpurohit, B.S.; Savla, G.; Ali, N.; Panda, P.K.; Kaul, S.K.; Mishra, H. A case study of moisture and dust induced failure of dry type transformer in power supply distribution. Water Energy Int. 2017, 60, 43–47.
[7] Senobari, R.K.; Sadeh, J.; Borsi, H. Frequency response analysis (FRA) of transformers as a tool for fault detection and location: A review. Electric. Power Syst. Res. 2018, 155, 172–183.
[8] Zhang, Z, Z.; Gao, W.; Kari, T.; Lin, H. Identification of Power Transformer Winding Fault Types by a Hierarchical Dimension Reduction Classifier. Energies 2018, 11, 2434, doi:10.3390 /en11092434.
[9] Li, E.; Wang, L.; Song, B.; Jian, S. Improved Fuzzy C-Means Clustering for Transformer Fault Diagnosis Using Dissolved Gas Analysis Data. Energies 2018, 11, 2344, doi:10.3390/en11092344.
[10] Bagheri, M.; Zollanvari, A.; Nezhivenko, S. Transformer fault condition prognosis using vibration signals over cloud envi-ronment. IEEE Access 2018, 6, 9862–9874.
[11] Tang, S.; Hale, C.; Thaker, H. Reliability modeling of power transformers with maintenance outage. Syst. Sci. Control Eng. 2014, 2, 316–324.
[12] Tenbohlen, S.; Vahidi, F.; Jagers, J. A Worldwide Transformer Reliability Survey. In Proceedings of the VDE High Voltage Technology 2016, ETG-Symposium, Berlin, Germany, 14–16 November 2016; pp. 1–6.
[13] Murugan, R; Ramasamy, R. Understanding the power transformer component failures for health index-based maintenance planning in electric utilities. Eng Fail Anal. 2019;96:274–88.
[14] Alonso, P.E.B.; Meana-Fernández, A.; Oro, J.M.F. Thermal response and failure mode evaluation of a dry-type transformer. Appl. Therm. Eng. 2017, 120, 763–771.
[15] Cremasco, A.; Wu, W.; Blaszczyk, A.; Cranganu-Cretu, B. Network modelling of dry-type transformer cooling systems. COMPEL Int. J. Comput. Math. Electr. Electron. Eng. 2018, 37, 1039–1053. https:// doi.org/10.1108/compel-12-2016-0534.
[16] Islam, M.; Lee, G.; Hettiwatte, S.N. A review of condition monitoring techniques and diagnostic tests for lifetime estimation of power transformers. Electr. Eng. 2018, 100, 581–605. https://doi.org/10. 1007/s00202-017-0532-4.
[17] Athikessavan, S.C.; Jeyasankar, E.; Manohar, S.S.; Panda, S.K. Inter-Turn Fault Detection of Dry-Type Transformers Using Core-Leakage Fluxes. IEEE Trans. Power Deliv. 2019, 34, 1230–1241. https://doi.org /10.1109/tpwrd.2018.2878460.
[18] Liu, Y.; Yin, J.; Tian, Y.; Fan, X. Design and Performance Test of Transformer Winding Optical Fibre Composite Wire Based on Raman Scattering. Sensors 2019, 19, 2171. https://doi.org/10.3390/s19092171.
[19] Zhang, X.; Gockenbach, E. Asset-Management of Transformers Based on Condition Monitoring and Standard Diagnosis. IEEE Electr. Insul. Mag. 2008, 24, 26–40. https://doi.org/10.1109/mei.2008.4581371.
[20] Ward, S.; El-Faraskoury, A.; Badawi, M.; Ibrahim, S.; Mahmoud, K.; Lehtonen, M.; Darwish, M. Towards Precise Interpretation of Oil Transformers via Novel Combined Techniques Based on DGA and Partial Discharge Sensors. Sensors 2021, 21, 2223. https://doi.org/10. 3390/s21062223.
[21] He, Y.; Zhou, Q.; Lin, S.; Zhao, L. Validity Evaluation Method Based on Data Driving for On-Line Monitoring Data of Trans-former under DC-Bias. Sensors 2020, 20, 4321. https://doi.org/10.3390/s20154321.
[22] Zhang, C.; He, Y.; Du, B.; Yuan, L.; Li, B.; Jiang, S. Transformer fault diagnosis method using IoT based monitoring system and ensemble machine learning. Futur. Gener. Comput. Syst. 2020, 108, 533–545. https://doi.org/10.1016/j.future.2020.03.008.
[23] Sun, Y.; Hua, Y.; Wang, E.; Li, N.; Ma, S.; Zhang, L.; Hu, Y. A temperature-based fault pre-warning method for the dry-type transformer in the offshore oil platform. Int. J. Electr. Power Energy Syst. 2020, 123, 106218.
[24] Chen, M.-K.; Chen, J.-M.; Cheng, C.-Y. Partial discharge detection in 11.4 kV cast resin power transformer. IEEE Trans. Dielectr. Electr. Insul. 2016, 23, 2223–2231, doi:10.1109/TDEI.2016.7556498.
[25] Gockenbach, E.; Werle, P.; Borsi, H. Monitoring and diagnostic systems for dry type transformers. In Proceedings of the ICSD’01 2001 IEEE 7th International Conference on Solid Dielectrics (Cat. No.01CH37117), Eindhoven, The Netherlands, 25–29 June 2001; doi:10.1109/ICSD.2001.955628.
[26] Lee, C.-T.; Horng, S.-C. Abnormality detection of cast-resin transformers using the fuzzy logic clustering decision tree. Energies 2020, 13, 2546.
[27] Muttillo, M.; Nardi, I.; Stornelli, V.; De Rubeis, T.; Pasqualoni, G.; Ambrosini, D. On Field Infrared Thermography Sensing for PV System Efficiency Assessment: Results and Comparison with Electrical Models. Sensors 2020, 20, 1055. https://doi.org/10.3390 /s20041055.
[28] Osornio-Rios, R.A.; Antonino-Daviu, J.A.; de Jesus Romero-Troncoso, R. Recent Industrial Applications of Infrared Thermography: A Review. IEEE Trans. Ind. Inform. 2019, 15, 615–625, doi:10.1109/TII.2018.2884738.
[29] Zou, H.; Huang, F. A novel intelligent fault diagnosis method for electrical equipment using infrared thermography. Infrared Phys. Technol. 2015, 73, 29–35.
[30] Laib dit Leksir, Y.; Mansour, M.; Moussaoui, A. Localization of thermal anomalies in electrical equipment using Infrared Thermography and support vector machine. Infrared Phys. Technol. 2018, 89, 120–128. https://doi.org/10.1016/j.infrared.2017.12.015.
[31] López-Pérez, D.; Antonino-Daviu, J. Application of Infrared Thermography to Failure Detection in Industrial Induction Motors: Case Stories. IEEE Trans. Ind. Appl. 2017, 53, 1901–1908, doi:10.1109/TIA.2017.2655008.
[32] Duan, L.; Yao, M.; Wang, J.; Bai, T.; Zhang, L. Segmented infrared image analysis for rotating machinery fault diagnosis. Infrared Phys. Technol. 2016, 77, 267–276. https://doi.org/10.1016/j.infrared. 2016.06.011.
[33] Ioannidou, A.; Chatzilari, E.; Nikolopoulos, S.; Kompatsiaris, I. Deep Learning Advances in Computer Vision with 3D Data: A Survey. ACM Comput. Surv. 2018, 50, 1–38. https://doi.org/10.1145/3042064.
[34] Yang, J.; Xu, R.; Qi, Z.; Shi, Y. Visual Anomaly Detection for Images: A Survey. arXiv 2021, arXiv:2109.13157.
[35] Nomura, Y. A Review on Anomaly Detection Techniques Using Deep Learning. J. Soc. Mater. Sci. Jpn. 2020, 69, 650–656. https://doi.org/10.2472/jsms.69.650.
[36] Thudumu, S.; Branch, P.; Jin, J.; Singh, J. A comprehensive survey of anomaly detection techniques for high dimensional big data. J. Big Data 2020, 7, 42. https://doi.org/10.1186/s40537-020-00320-x.
[37] Alloqmani, A.; Abushark, Y.B.; Irshad, A.; Alsolami, F. Deep Learning based Anomaly Detection in Images: Insights, Chal-lenges and Recommendations. Int. J. Adv. Comput. Sci. Appl. 2021, 12(4). http://dx.doi.org/10.14569/IJACSA.2021.0120428
[38] Pang, G.; Shen, C.; Cao, L.; Hengel, A.V.D. Deep Learning for Anomaly Detection: A Review. ACM Comput. Surv. 2021, 54, 1–38. https://doi.org/10.1145/3439950.
[39] Mitiche, I.; McGrail, T.; Boreham, P.; Nesbitt, A.; Morison, G. Data-Driven Anomaly Detection in High-Voltage Transformer Bushings with LSTM Auto-Encoder. Sensors 2021, 21, 7426. https://doi.org/10. 3390/s21217426.
[40] Liang, X.; Wang, Y.; Li, H.; He, Y.; Zhao, Y. Power Transformer Abnormal State Recognition Model Based on Improved K-Means Clustering. In Proceedings of the 2018 IEEE Electrical Insulation Conference (EIC), San Antonio, TX, USA, 17–20 June 2018; pp. 327–330.
[41] Tang, K.; Liu, T.; Xi, X.; Lin, Y.; Zhao, J. Power Transformer Anomaly Detection Based on Adaptive Kernel Fuzzy C-Means Clustering and Kernel Principal Component Analysis. In Proceedings of the 2018 Australian & New Zealand Control Conference (ANZCC), Melbourne, VIC, Australia, 7–8 December 2018. https://doi.org/10.1109/ANZCC. 2018.8606615.
[42] Bergmann, P.; Löwe, S.; Fauser, M.; Sattlegger, D.; Steger, C. Improving Unsupervised Defect Segmentation by Applying Structural Similarity to Autoencoders. In Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications; Scitepress, 2019, volume 5: VISAPP,pages 372–380, Setubal.
[43] Schlegl, T.; Seeböck, P.; Waldstein, S.M.; Schmidt-Erfurth, U.; Langs, G. Unsupervised anomaly detection with generative adversarial networks to guide marker discovery. In Proceedings of the International Conference on Information Processing in Medical Imaging, Boone, NC, USA, 25–30 June 2017; pp. 146–157.
[44] Schlegl, T.; Seeböck, P.; Waldstein, S.M.; Langs, G.; Schmidt-Erfurth, U. f-AnoGAN: Fast unsupervised anomaly detection with generative adversarial networks. Med. Image Anal. 2019, 54, 30–44. https://doi.org/10.1016/j.media.2019.01.010.
[45] Akcay, S.; Atapour-Abarghouei, A.; Breckon, T.P. GANomaly: Semi-Supervised Anomaly Detection via Adversarial Training. In Computer Vision–ACCV 2018; Springer International Publishing: Cham, Switzerland, 2019; pp. 622–637.
[46] Vu, H.S.; Ueta, D.; Hashimoto, K.; Maeno, K.; Pranata, S.; Shen, S.M. Anomaly Detection with Adversarial Dual Autoencoders. arXiv 2019, arXiv:1902.06924.
[47] Lai, C.-H.; Zou, D.; Lerman, G. Robust Subspace Recovery Layer for Unsupervised Anomaly Detection. arXiv 2019., arXiv:1904.00152v2.
[48] Wang, L.; Zhang, D.; Guo, J.; Han, Y. Image Anomaly Detection Using Normal Data Only by Latent Space Resampling. Appl. Sci. 2020, 10, 8660. https://doi.org/10.3390/app10238660.
[49] Tang, T.-W.; Kuo, W.-H.; Lan, J.-H.; Ding, C.-F.; Hsu, H.; Young, H.-T. Anomaly Detection Neural Network with Dual Au-to-Encoders GAN and Its Industrial Inspection Applications. Sensors 2020, 20, 3336. https://doi.org/10.3390/s20123336.
[50] Siddiqui, Z.A.; Park, U.; Lee, S.-W.; Jung, N.-J.; Choi, M.; Lim, C.; Seo, J.-H. Robust Powerline Equipment Inspection System Based on a Convolutional Neural Network. Sensors 2018, 18, 3837, doi: 10.3390/s18113837.
[51] Duan, J.; He, Y.; Du, B.; Ghandour, R.M.R.; Wu, W.; Zhang, H. Intelligent Localization of Transformer Internal Degradations Combining Deep Convolutional Neural Networks and Image Segmentation. IEEE Access 2019, 7, 62705–62720, doi:10.1109/ ACCESS.2019.2916461.
[52] Janssens, O.; Loccufier, M.; van Hoecke, S. Thermal Imaging and Vibration-Based Multisensor Fault Detection for Rotating Machinery. IEEE Trans. Ind. Inform. 2019, 15, 434–444, doi:10.1109/TII.2018. 2873175.
[53] Matuszewski,J; Pietrow, D. Recognition of electromagnetic sources with the use of deep neural networks. In: Kaniewski P, editor. XII Conference on Reconnaissance and Electronic Warfare Systems. SPIE; 2019.
[54] Ma, S.; Cai, W.; Liu, W.; Shang, Z.; Liu, G. A lighted deep convolutional neural network based fault diagnosis of rotating machinery. Sensors 2019, 19, 2381.
[55] Kang, Q.; Zhao, H.; Yang, D.; Ahmed, H.S.; Ma, J. Lightweight convolutional neural network for vehicle recognition in thermal infrared images. Infrared Phys. Technol. 2020, 104, 103120, doi:10.3390/s19102381.
[56] Iandola, F.N.; Han, S.; Moskewicz, M.W.; Ashraf, K.; Dally, W.J.; Keutzer, K. SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size, CoRR, arXiv 2016, arXiv:abs/1602.07360.
[57] Biswas, D.; Su, H.; Wang, C.; Stevanovic, A.; Wang, W. An automatic traffic density estimation using Single Shot Detection (SSD) and MobileNet-SSD. Phys. Chem. Earth 2019, 110, 176–184, doi:10.1016 /j.pce.2018.12.001.
[58] Zhang, X.; Zhou, X.; Lin, M.; Sun, J. ShuffleNet: An extremely efficient convolutional neural network for mobile devices. In Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA, 18–23 June 2018; doi:10.1109/CVPR.2018.00716.
[59] Masci, J.; Meier, U.; Cireşan, D.; Schmidhuber, J. Stacked convolutional auto-encoders for hierarchical feature extraction. In Lecture Notes in Computer Science; Springer: Berlin/Heidelberg, Germany, 2011; pp. 52–59.
[60] Kingma, D.P.; Welling, M. Auto-Encoding Variational Bayes. arXiv 2013, arXiv:1312.6114v10
[61] Goodfellow, I.; Pouget-Abadie, J.; Mirza, M.; Xu, B.; Warde-Farley, D.; Ozair, S.; Courville, A.; Bengio, Y. Generative adver-sarial nets. In Proceedings of the Advances in Neural Information Processing Systems, Montreal, QC, Canada, 8–13 December 2014; pp. 2672–2680.
[62] Wiatrak, M.; Albrecht, S.V.; Nystrom, A. Stabilizing Generative Adversarial Networks: A Survey. arXiv 2020, arXiv:1910.00927v2. Available online: https://arxiv.org/pdf/1910.00927.pdf (accessed on).
[63] Wang, Z.; She, Q.; Ward, T.E. Generative adversarial networks in computer vision: A survey and taxonomy. ACM Comput. Surv. 2021, 54, 1–38.
[64] Arjovsky, M.; Bottou, L. Towards principled methods for training generative adversarial networks. arXiv 2017, arXiv:1701.04862. Available online: https://arxiv.org/abs/1701.04862 (accessed on 12 May 2021).
[65] Salimans, T.; Goodfellow, I.; Zaremba, W.; Cheung, V.; Radford, A.; Chen, X. Improved techniques for training GANs. In Proceedings of the 30th International Conference on Neural Information Processing Systems, Barcelona, Spain, 5–10 December 2016; pp. 2234–2242.
[66] Arjovsky, M.; Chintala, S.; Bottou, L. Wasserstein Generative Adversarial Networks. In Proceedings of the 34th International Conference on Machine Learning, Sydney, Australia, 6–11 August 2017; Volume 70, pp. 214–223.
[67] Wang, Z.; Chen, J.; Hoi, S.C.H. Deep learning for image super-resolution: A survey. IEEE Trans. Pattern Anal. Mach. Intell. 2020, 1-1.
[68] Borji, A. Pros and cons of GAN evaluation measures. Comput. Vis. Image Underst. 2019, 179, 41–65.
[69] Szegedy, Christian, Vincent Vanhoucke, Sergey Ioffe, Jon Shlens, and Zbigniew Wojna. 2016. “Rethinking the Inception Architecture for Computer Vision.” In 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE.
[70] Han, J.; Moraga, C. The influence of the sigmoid function parameters on the speed of backpropagation learning. In Lecture Notes in Computer Science; Springer: Berlin/Heidelberg, Germany, 1995; pp. 195–201.
[71] Agarap, A.F. Deep Learning using Rectified Linear Units (ReLU). arXiv 2018, arXiv:1803.08375. Available online: https://arxiv.org/abs/1803. 08375 .
[72] Chollet, F. Xception: Deep learning with depthwise separable convolutions. In Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA, 21–26 July 2017.
[73] Yao, D.; Liu, H.; Yang, J.; Li, X. A lightweight neural network with strong robustness for bearing fault diagnosis. Measurement 2020, 159, 107756, doi:10.1016/j.measurement.2020.107756.
[74] Gong, W.; Chen, H.; Zhang, Z.; Zhang, M.; Wang, R.; Guan, C.; Wang, Q. A novel deep learning method for intelligent fault diagnosis of rotating machinery based on improved CNN-SVM and multichannel data fusion. Sensors 2019, 19, 1693.
[75] 余丞皓，"具深度學習之紅外線熱影像於設備故障診斷之應用"，國立臺灣科技大學，碩士論文，2020年 。
[76] 楊鈞佑，"應用深度學習及紅外線熱影像於設備溫度預測系統之研製"，國立臺灣科技大學，碩士論文，2020年。
[77] FLIR, "FLIR camera adjustments boson," FLIR Application Note, September 2018.
[78] 郭政謙，黃彥植，中華民國專利公報公告編號：M595226，「電力設備故障之智慧檢測設備」，2020 年5月。
[79] Yuan, X.; Liu, Q.; Long, J.; Hu, L.; Wang, Y. Deep Image Similarity Measurement Based on the Improved Triplet Network with Spatial Pyramid Pooling. Information 2019, 10, 129. https://doi.org/10.3390/info10040129.
[80] X. Zhang, S. Karaman and S. -F. Chang, "Detecting and Simulating Artifacts in GAN Fake Images," 2019 IEEE International Workshop on Information Forensics and Security (WIFS), 2019, pp. 1-6, doi: 10.1109/WIFS47025.2019.9035107.
[81] Isola, P.; Zhu, J.-Y.; Zhou, T.; Efros, A.A. Image-to-image translation with conditional adversarial networks. In Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA, 21–26 July 2017.
[82] Kingma, Diederik P., and Jimmy Ba. "Adam: A method for stochastic optimization." arXiv preprint arXiv:1412.6980 (2014).
[83] Schmidt-Hieber, J. Nonparametric regression using deep neural networks with ReLU activation function. Ann. Stat. 2020, 48, 1875–1897. https://doi.org/10.1214/19-aos1875.
[84] Weller-Fahy, D.J.; Borghetti, B.J.; Sodemann, A.A. A Survey of Distance and Similarity Measures Used Within Network In-trusion Anomaly Detection. IEEE Commun. Surv. Tutorials 2014, 17, 70–91. https://doi.org/10.1109/comst.2014.2336610.
[85] Mercioni, M.A.; Holban, S. A Survey of Distance Metrics in Clustering Data Mining Techniques. In Proceedings of the 2019 3rd International Conference on Graphics and Signal Processing, New York, NY, USA, 1–3 June 2019. https://doi.org/10.1145/3338472. 3338490.
[86] Hossain MK, Abufardeh S. A new method of calculating squared euclidean distance (SED) using PTreE technology and its performance analysis. In Lee G, Jin Y, editors, Proceedings of 34th International Conference on Computers and Their Applications, CATA 2019. The International Society for Computers and Their Applications (ISCA). 2019. p. 45-54. (Proceedings of 34th International Conference on Computers and Their Applications, CATA 2019).
[87] LeCun, Y. LeNet-5, convolutional neural networks. 2015. Available online: http://yann.lecun.com/exdb/lenet (accessed on 12 May 2021).
[88] He, K.; Zhang, X.; Ren, S.; Sun, J. Deep residual learning for image recognition. In Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NE, USA, 26 June–1 July 2016.
[89] Simonyan, K.; Zisserman, A. Very deep convolutional networks for large-scale image recognition. arXiv 2014, arXiv:1409.1556v6. Available online: https://arxiv.org/abs/1409.1556 .
[90] Krizhevsky, A.; Sutskever, I.; Hinton, G.E. ImageNet classification with deep convolutional neural networks. Commun. ACM 2017, 60, 84–90.
[91] He, H.; Garcia, E.A. Learning from imbalanced data. IEEE Trans. Knowl. Data Eng. 2009, 21, 1263–1284.