在電子封裝結構中，例如異質封裝、系統級封裝、扇出封裝和晶圓級封裝（WLP），有許多設計參數會影響其可靠性性能，通常是實驗、加速熱循環測試（ ATCT），用於獲得可靠性結果，但是優化設計參數需要大量的時間和巨大的成本。為了克服上述問題，基於有限元的仿真設計（DoS）技術已被許多研究人員廣泛用於電子封裝的可靠性評估，以減少耗時的實驗次數。DoS 技術可以有效縮短設計週期，降低成本，優化封裝結構。 因此，DOS 技術在各個包裝行業都比實驗更具競爭力。然而，仿真分析結果與仿真工作的執行者高度相關，而且結果往往因人而異。 為了始終如一地提供可靠的模擬結果來評估新設計的電子封裝的可靠性壽命，需要具有廣泛領域知識、對基礎/應用力學理論和有限元方法有深刻理解的研究人員。 人工智能（AI）可以幫助研究人員避免這些人為因素的缺點。本研究以 WLP 為例說明 AI 輔助仿真設計 (DoS) 技術，重點回顧人工智能與仿真技術相結合預測晶圓級封裝 (WLP) 可靠性的解決方案，並解釋如何 將人工智能算法與仿真技術相結合，實現可靠性預測。模擬是實驗，如果它的結果能夠與實驗結果在一個準確的範圍內保持一致，人們可以使用經過驗證的模擬程序來創建用於 AI 訓練的龐大數據庫，以獲得用於可靠性預測的小而準確的 AI 模型。本研究實現了K近鄰（KNN）、核嶺回歸（KRR）、高斯過程回歸（GPR）、多項式回歸（PR）、高斯混合模型-KMean-Passive Aggressive Regression 等幾種機器學習回歸模型（ GMM-KMean-PAR）通過調整 WLP 數據庫來預測可靠性壽命。一旦回歸模型建立並驗證後，可以簡單地輸入影響WLP 的參數如芯片厚度、上焊盤直徑、下焊盤直徑和緩衝層厚度，然後藉助上述機器學習立即獲得WLP 的可靠性壽命 回歸模型。此外，本研究還成功建立了針對上述機器學習回歸算法的有限元模擬生成的500到9000不同訓練數據集的誤差分析和CPU時間分析。KNN、KRR、GPR、PR 和 GMM-KMean-PAR 測試數據的最佳準確度（平均絕對誤差）小於 10%，本研究討論了 KNN、KRR、PR 和 GMM 的 CPU 時間分析 -WLP 結構可靠性壽命預測的KMean-PAR 模型。 此外，本研究利用芯片厚度、上焊盤直徑、下焊盤直徑、應力緩衝層厚度和PCB 厚度等五個影響參數生成5000個訓練數據集，用於構建AI 訓練模型並估計WLP 結構的可靠性壽命。對於 5000 個訓練數據集的 5 個有影響力的特徵，所有 AI 模型的測試數據的 MAE 均小於 10%，並且還討論了上述 AI 模型所需的 CPU 時間。 同時，本工作還將上述算法的結果與有限元法和實驗結果進行了比較。

In electronic packaging structure, e.g., heterogeneous packaging, system-in-packaging, fan-out packaging and wafer level packaging (WLP), there are many design parameters that will affects its reliability performance, conventionally, the experiment, accelerated thermal cycling test (ATCT), is used to obtain the reliability result, however, it will take a lot of time and huge amount of cost to optimize the design parameters. To overcome the above-mentioned problems, the finite element based design-on-simulation (DoS) technology has been widely adopted by many researchers for the reliability assessment of electronic packaging to reduce the number of time consuming experiments. DoS technology can effectively shorten the design cycle, reduce costs and optimize the packaging structure. So, DOS technology has been more competitive in the each and every packaging industry instead of experiment. However, the simulation analysis results are related to who performed the simulation work, and the results are usually inconsistent with different people. In order to consistently provide reliable simulation results to evaluate the reliability life of newly designed electronic packaging, researchers with extensive domain knowledge, a deep understanding of basic/applied mechanics theory, and finite element methods are required. Artificial intelligence (AI) can help researchers to avoid these shortcomings of human factor. This study takes WLP as an example to illustrate the AI-assisted Design on Simulation (DoS) technology, focusing on reviewing the solutions which combination of artificial intelligence and simulation technology to predict the reliability of WLP, and explains how to combine AI algorithms with simulation technology to achieve a reliability prediction. Simulation is experiment if its results can consistently match with experiment result in an accurate range, one can have used a validated simulation procedure to create huge database for AI training to get a small and accurate AI model for reliability prediction. This study has implemented several machine learning regression model such as K-nearest neighbor (KNN), kernel ridge regression (KRR), Gaussian Process regression (GPR), Polynomial regression (PR), and Gaussian Mixture model-KMean-Passive Aggressive Regression (GMM-KMean-PAR) to predict the reliability life by tuning WLP database. Once the regression model is established and validated, the influential parameters of WLP such as chip thickness, upper pad diameter, lower pad diameter, buffer layer thickness and PCB thickness can be simply entered and then immediately obtained reliability life of WLP by the help of the above machine learning regression model. In addition, this study has also successfully established the error analysis and CPU time analysis for different training dataset which is from 500 to 9000 generated by FEM simulation for the above machine learning regression algorithms. The best accuracy (Mean Absolute Error) of testing data for KNN, KRR, GPR, PR, and GMM-KMean-PAR is less than 10% and this study has discussed about the CPU time analysis for KNN, KRR, PR, and GMM-KMean-PAR model for the reliability life prediction of WLP structure. Furthermore, this study has used five influential parameters such as chip thickness, upper pad diameter, lower pad diameter, stress buffer layer thickness and PCB thickness to generate 5000 training datasets to build AI training models and estimate the reliability life of WLP structure. For five influential features with 5000 training datasets, the MAE of testing data for all the AI models are less than 10% and CPU time required for above AI models are also discussed. Meanwhile, this work has also compared the result of above algorithms with FEM and experiment result.

Study on AI-Assisted Design-On-Simulation Technology for Reliability Life Prediction of Wafer Level Package i
ABSTRACT ii
TABLE OF CONTENTS iv
LIST OF TABLES viii
LIST OF FIGURES xiii
CHAPTER 1 INTRODUCTION 1
1.1 Introduction to electronic package 1
1.2 Introduction to AI 3
1.3 Research Motivation 6
1.4 Literature Survey 8
1.4.1 Reliability analysis of electronic package 9
1.4.2 literature of machine learning algorithms: 11
1.5 Research Goal 15
CHAPTER 2 FUNDAMENTAL THEORIES 16
2.1 Finite Element Theory 16
2.1.1 Linear-Elastic Finite Element Theory 17
2.1.2 Material Non-linear Theory 22
2.2 Hardening Rule 25
2.2.1 Isotropic Hardening Rule 25
2.2.2 Kinematic Hardening Rule 26
2.2.3 Chaboche Kinematic Hardening Rule 27
2.3 Garofalo-Arrhenius Creep Theory 29
2.4 Numerical Method and Convergence Criteria 30
2.5 Fatigue Model of Solder Joint 32
2.5.1 Coffin-Manson Strain Method 33
2.5.2 Darveaux Energy Density Method 33
2.6 Machine learning 34
2.6.1 Why Machine Learning 36
2.6.2 Supervised Learning 37
2.6.3 Unsupervised Learning 39
2.6.4 Generalization, Overfitting, and Underfitting 41
2.6.5 Training Methodology: 42
2.6.6 ANN Algorithm 51
2.6.7 The Gradient Descent Algorithm 57
2.6.8 The Backpropagation Algorithm 59
2.6.9 KNN Algorithm 63
2.6.10 KRR Algorithm 69
2.6.11 Mercer’s theorem 77
2.6.12 GPR Algorithm 80
2.6.13 GPR model 83
2.6.14 Marginal likelihood 92
2.6.15 Polynomial Regression Algorithm 94
2.6.16 K-Means Clustering Algorithm 100
2.6.17 GMM Algorithm 104
2.6.18 PAR Algorithm 111
2.6.19 Different types of Error method in machine learning 117
2.6.20 Why Python Programming language 119
2.6.21 Scikit-learn library 120
CHAPTER 3 Finite Element Method for WLP Structure and Verification 121
3.1 Information of five test vehicle of WLP structure 121
3.1.1 Size and specification of test vehicles. 123
3.1.2 JEDEC Standard for Thermal Cyclic Load 124
3.1.3 Accelerated thermal cyclic test 126
3.2 Finite Element Simulation for WLP Structure 127
3.2.1 Finite Element Method (FEM) 127
3.2.2 Material Properties 129
3.2.3 Finite element model for test vehicles 131
3.2.4 Boundary Conditions 133
3.2.5 Life prediction Model 133
3.2.6 Life prediction Result with equivalent plastic strain 134
CHAPTER 4 AI Model Implementation for WLP Reliability Prediction Result 138
4.1 Establishment of Training and Testing Dataset 139
4.2 KNN Result and Discussion 148
4.2.1 KNN Model Parameter 149
4.2.2 KNN Preprocessing Methods 152
4.2.3 KNN model Performance for different Training Dataset 153
4.2.4 Error and CPU Time analysis between KNN and FEM Model. 165
4.3 KRR Result and Discussion 170
4.3.1 KRR Model Parameter 170
4.3.2 KRR Preprocessing Methods 174
4.3.3 KRR model performance for different Training Dataset 175
4.3.4 Error and CPU Time analysis between KRR and FEM Model. 186
4.4 GPR Result and Discussion 192
4.4.1 GPR Model Parameter 193
4.4.2 GPR Preprocessing Methods 197
4.4.3 GPR model performance for different Training Dataset 198
4.4.4 Error and CPU Time analysis between GPR and FEM Model. 210
4.5 Polynomial Regression (PR) Result and Discussion 217
4.5.1 PR Model Parameter 218
4.5.2 PR Preprocessing Methods 221
4.5.3 PR Model Performance for different Training Dataset 222
4.5.4 Error and CPU Time analysis between PR and FEM Model. 234
4.6 GMM-Kmean-PAR Model Result and Discussion 240
4.6.1 GMM-KMean-PAR Model Parameter 241
4.6.2 GMM-KMean-PAR Preprocessing Methods 246
4.6.3 PAR Model Performance for different Training Dataset 247
4.6.4 KMean-PAR Model Performance for different Training Dataset 252
4.6.5 GMM-PAR Model Performance for different Training Dataset 257
4.6.6 GMM-KMean-PAR Model Performance for Training Datasets. 262
4.6.7 Error and CPU Time for GMM-KMean-PAR and FEM Model. 269
4.7 Performance comparison between different type of AI Models. 276
CHAPTER 5 Conclusion and Future Work 286
5.1 Conclusion 286
5.2 Suggest Future Works 288
REFERENCE 289

[1] Y. Andriani et al., "Effect of Boron Nitride Nanosheets on Properties of a Commercial Epoxy Molding Compound Used in Fan-Out Wafer-Level Packaging," IEEE Transactions on Components, Packaging and Manufacturing Technology, vol. 10, no. 6, pp. 990-999, 2020.
[2] H.-C. Cheng, C.-H. Chung, and W.-H. Chen, "Die shift assessment of reconstituted wafer for fan-out wafer-level packaging," IEEE Transactions on Device and Materials Reliability, vol. 20, no. 1, pp. 136-145, 2020.
[3] H. Dong, J. Chen, D. Hou, Y. Xiang, and W. Hong, "A low-loss fan-out wafer-level package with a novel redistribution layer pattern and its measurement methodology for millimeter-wave application," IEEE Transactions on Components, Packaging and Manufacturing Technology, vol. 10, no. 7, pp. 1073-1078, 2020.
[4] J. H. Lau et al., "Design, materials, process, fabrication, and reliability of fan-out wafer-level packaging," IEEE Transactions on Components, Packaging and Manufacturing Technology, vol. 8, no. 6, pp. 991-1002, 2018.
[5] J. H. Lau et al., "Fan-out wafer-level packaging for heterogeneous integration," IEEE Transactions on Components, Packaging and Manufacturing Technology, vol. 8, no. 9, pp. 1544-1560, 2018.
[6] T.-K. Lee, W. Xie, M. Tsai, and M. D. Sheikh, "Impact of Microstructure Evolution on the Long-Term Reliability of Wafer-Level Chip-Scale Package Sn–Ag–Cu Solder Interconnects," IEEE Transactions on Components, Packaging and Manufacturing Technology, vol. 10, no. 10, pp. 1594-1603, 2020.
[7] K.-C. Wu and K.-N. Chiang, "Investigation of solder creep behavior on wafer level CSP under thermal cycling loading," in 2014 International Conference on Electronics Packaging (ICEP), Toyama, Japan., 2014: IEEE, pp. 498-501.
[8] D.-H. Kim, P. Elenius, and S. Barrett, "Solder joint reliability and characteristics of deformation and crack growth of Sn-Ag-Cu versus eutectic Sn-Pb on a WLP in a thermal cycling test," IEEE Transactions on Electronics Packaging Manufacturing, vol. 25, no. 2, pp. 84-90, 2002.
[9] E.-H. Wong, S. Seah, and V. Shim, "A review of board level solder joints for mobile applications," Microelectronics Reliability, vol. 48, no. 11-12, pp. 1747-1758, 2008.
[10] K.-N. Chiang and C.-A. Yuan, "An overview of solder bump shape prediction algorithms with validations," IEEE transactions on advanced packaging, vol. 24, no. 2, pp. 158-162, 2001.
[11] S.-H. Dai and M.-O. Wang, "Reliability Analysis in Engineering Applications”–Van Nostrand Reinhold Company," New York–1992, 1992.
[12] J. H. Lau and Y.-H. Pao, Solder joint reliability of BGA, CSP, flip chip, and fine pitch SMT assemblies. McGraw-Hill Professional Publishing, USA., 1997.
[13] C. Qin, Y. Li, and H. Mao, "Effect of Different PBO-Based RDL Structures on Chip-Package Interaction Reliability of Wafer Level Package," IEEE Transactions on Device and Materials Reliability, vol. 20, no. 3, pp. 524-529, 2020.
[14] P.-H. Wang, Y.-W. Huang, and K.-N. Chiang, "Reliability Evaluation of Fan-Out Type 3D Packaging-On-Packaging," Micromachines, vol. 12, no. 3, p. 295, 2021.
[15] C. Yang, Y. Su, S. Y. Liang, and K. Chiang, "Simulation of wire bonding process using explicit FEM with ALE remeshing technology," Journal of Mechanics, vol. 36, no. 1, pp. 47-54, 2020.
[16] M.-K. Yeh, K.-N. Chiang, and J.-A. Su, "Thermal stress analysis of thermally-enhanced plastic ball grid array electronic packaging," Journal of Mechanics, vol. 18, no. 1, pp. 9-16, 2002.
[17] R.-S. Chen, C.-H. Huang, and Y.-Z. Xie, "Application of optimal design on twin die stacked package by reliability indicator of average SED concept," Journal of Mechanics, vol. 28, no. 1, pp. 135-142, 2012.
[18] C.-M. Liu, C.-C. Lee, and K.-N. Chiang, "Enhancing the reliability of wafer level packaging by using solder joints layout design," IEEE Transactions on Components and Packaging Technologies, vol. 29, no. 4, pp. 877-885, 2006.
[19] K.-N. Chiang, W.-H. Chen, and H.-C. Cheng, "Large-scale three-dimensional area array electronic packaging analysis," CMSE- Computer Modeling and Simulation in Engineering, vol. 4, no. 1, pp. 4-11, 1999.
[20] C. Tsou, T. Chang, K. Wu, P. Wu, and K. Chiang, "Reliability assessment using modified energy based model for WLCSP solder joints," in 2017 International Conference on Electronics Packaging (ICEP), 2017: IEEE, pp. 7-15.
[21] R. Darveaux and K. Banerji, "Fatigue analysis of flip chip assemblies using thermal stress simulations and a Coffin-Manson relation," in 1991 Proceedings 41st Electronic Components & Technology Conference, Atlanta, GA, USA.,1991: IEEE, pp. 797-805.
[22] R. Darveaux, K. Banerji, A. Mawer, G. Dody, and J. Lau, "Reliability of plastic ball grid array assembly," in Ball grid array technology, vol. 13: McGraw-Hill New York, 1995, pp. 379-442.
[23] R. Darveaux, "Effect of simulation methodology on solder joint crack growth correlation and fatigue life prediction," J. Electron. Packag., vol. 124, no. 3, pp. 147-154, 2002.
[24] A. Mertol, "Optimization of high pin count cavity-up enhanced plastic ball grid array (EPBGA) packages for robust design," IEEE Transactions on Components, Packaging, and Manufacturing Technology: Part B, vol. 20, no. 4, pp. 376-388, 1997.
[25] J. H. Lau, S.-W. R. Lee, and C. Chang, "Solder joint reliability of wafer level chip scale packages (WLCSP): A time-temperature-dependent creep analysis," J. Electron. Packag., vol. 122, no. 4, pp. 311-316, 2000.
[26] X. Shi, Z. Wang, W. Zhou, H. Pang, and Q. Yang, "A new creep constitutive model for eutectic solder alloy," J. Electron. Packag., vol. 124, no. 2, pp. 85-90, 2002.
[27] S.-J. Ham and S.-B. Lee, "Measurement of creep and relaxation behaviors of wafer-level CSP assembly using moiré interferometry," J. Electron. Packag., vol. 125, no. 2, pp. 282-288, 2003.
[28] L. Zhang, V. Patwardhan, L. Nguyen, N. Kelkar, and R. Sitaraman, "Solder joint reliability model with modified Darveaux's equations for the micro SMD wafer level-chip scale package family," in Electronic Components and Technology Conference, 2003: Citeseer, pp. 572-577.
[29] L. Zhang, V. Arora, L. Nguyen, and N. Kelkar, "Numerical and experimental analysis of large passivation opening for solder joint reliability improvement of micro SMD packages," Microelectronics Reliability, vol. 44, no. 3, pp. 533-541, 2004.
[30] E. Alpaydin, "Introduction to machine learning. 2004," Cover, Copyright Page, Table of Contents for, MIT Press, USA., pp. 1-327, 2014.
[31] S. Gupta, S. Al-Obaidi, and L. Ferrara, "Meta-Analysis and Machine Learning Models to Optimize the Efficiency of Self-Healing Capacity of Cementitious Material," Materials, vol. 14, no. 16, p. 4437, 2021.
[32] S. Jianliang, S. Mengqian, G. Hesong, P. Yan, J. Jiang, and X. Lipu, "Research on Edge Surface Warping Defect Diagnosis Based on Fusion Dimension Reduction Layer DBN and Contribution Plot Method," Journal of Mechanics, vol. 36, no. 6, pp. 889-899, 2020.
[33] S. Kuschmitz, T. P. Ring, H. Watschke, S. C. Langer, and T. Vietor, "Design and additive manufacturing of porous sound absorbers—A machine-learning approach," Materials, vol. 14, no. 7, p. 1747, 2021.
[34] H. Song, A. Ahmad, K. A. Ostrowski, and M. Dudek, "Analyzing the compressive strength of ceramic waste-based concrete using experiment and artificial neural network (ANN) approach," Materials, vol. 14, no. 16, p. 4518, 2021.
[35] F. Farooq et al., "A comparative study for the prediction of the compressive strength of self-compacting concrete modified with fly ash," Materials, vol. 14, no. 17, p. 4934, 2021.
[36] X. Huang, M. Wasouf, J. Sresakoolchai, and S. Kaewunruen, "Prediction of healing performance of autogenous healing concrete using machine learning," Materials, vol. 14, no. 15, p. 4068, 2021.
[37] A. Salazar and F. Xiao, "Design of Hybrid Reconstruction Scheme for Compressible Flow Using Data-Driven Methods," Journal of Mechanics, vol. 36, no. 5, pp. 675-689, 2020.
[38] S.-H. Song, "A Comparison Study of Constitutive Equation, Neural Networks, and Support Vector Regression for Modeling Hot Deformation of 316L Stainless Steel," Materials, vol. 13, no. 17, p. 3766, 2020.
[39] W. S. McCulloch and W. Pitts, "A logical calculus of the ideas immanent in nervous activity," The bulletin of mathematical biophysics, vol. 5, no. 4, pp. 115-133, 1943.
[40] T. Denoeux, "A neural network classifier based on Dempster-Shafer theory," IEEE Transactions on Systems, Man, and Cybernetics-Part A: Systems and Humans, vol. 30, no. 2, pp. 131-150, 2000.
[41] G. S. Tandel et al., "A review on a deep learning perspective in brain cancer classification," Cancers, vol. 11, no. 1, p. 111, 2019.
[42] J. Schmidhuber, "Deep learning in neural networks: An overview," Neural networks, vol. 61, pp. 85-117, 2015.
[43] S. Hochreiter and J. Schmidhuber, "Long short-term memory," Neural computation, vol. 9, no. 8, pp. 1735-1780, 1997.
[44] A. Kulawik, J. Wróbel, and A. M. Ikonnikov, "Model of the Austenite Decomposition during Cooling of the Medium Carbon Steel Using LSTM Recurrent Neural Network," Materials, vol. 14, no. 16, p. 4492, 2021.
[45] C. C. Yuan, J. Fan, and X. Fan, "Deep machine learning of the spectral power distribution of the LED system with multiple degradation mechanisms," Journal of Mechanics, vol. 37, pp. 172-183, 2021.
[46] C. Cortes and V. Vapnik, "Support-vector networks," Machine learning, vol. 20, no. 3, pp. 273-297, 1995.
[47] A. C. Braun, U. Weidner, and S. Hinz, "Classification in high-dimensional feature spaces—Assessment using SVM, IVM and RVM with focus on simulated EnMAP data," IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 5, no. 2, pp. 436-443, 2012.
[48] K. A. A. Al-Sodani et al., "Experimental and modelling of alkali-activated mortar compressive strength using hybrid support vector regression and genetic algorithm," Materials, vol. 14, no. 11, p. 3049, 2021.
[49] T. Benkedjouh, K. Medjaher, N. Zerhouni, and S. Rechak, "Health assessment and life prediction of cutting tools based on support vector regression," Journal of intelligent manufacturing, vol. 26, no. 2, pp. 213-223, 2015.
[50] P. Dhanalakshmi and T. Kanimozhi, "Automatic segmentation of brain tumor using K-Means clustering and its area calculation," International Journal of advanced electrical and Electronics Engineering, vol. 2, no. 2, pp. 130-134, 2013.
[51] P. Drineas, M. W. Mahoney, and N. Cristianini, "On the Nyström Method for Approximating a Gram Matrix for Improved Kernel-Based Learning," journal of machine learning research, vol. 6, no. 12, 2005.
[52] S. K. Panigrahy and K.-N. Chiang, "Study on an Artificial Intelligence Based Kernel Ridge Regression Algorithm for Wafer Level Package Reliability Prediction," in 2021 IEEE 71st Electronic Components and Technology Conference (ECTC), San Diego, CA, USA., 2021: IEEE, pp. 1435-1441.
[53] Y. Hamed, A. I. Alzahrani, Z. Mustaffa, M. C. Ismail, and K. K. Eng, "Two steps hybrid calibration algorithm of support vector regression and K-nearest neighbors," Alexandria Engineering Journal, vol. 59, no. 3, pp. 1181-1190, 2020.
[54] S. Tan, "An effective refinement strategy for KNN text classifier," Expert Systems with Applications, vol. 30, no. 2, pp. 290-298, 2006.
[55] W. Ho and F. Yu, "Chiller system optimization using k nearest neighbour regression," Journal of Cleaner Production, vol. 303, p. 127050, 2021.
[56] J. Xia, J. Zhang, Y. Wang, L. Han, and H. Yan, "WC-KNNG-PC: Watershed clustering based on k-nearest-neighbor graph and Pauta Criterion," Pattern Recognition, vol. 121, p. 108177, 2022.
[57] L. Breiman, "Random forests," Machine learning, vol. 45, no. 1, pp. 5-32, 2001.
[58] H. Hsiao and K. Chiang, "AI-assisted reliability life prediction model for wafer-level packaging using the random forest method," Journal of Mechanics, vol. 37, pp. 28-36, 2021.
[59] H. Santiago and M. Dias, "Automated detection of anomalies in electrocardiograms using Empirical Mode Decomposition," Revista Gestão & Tecnologia, vol. 22, no. 1, pp. 51-75, 2022.
[60] C. E. Rasmussen and C. Williams, "Gaussian processes for machine learning, vol. 1," ed: MIT press Cambridge MA, 2006.
[61] A. Wilson and R. Adams, "Gaussian process kernels for pattern discovery and extrapolation," in International conference on machine learning, Atlanta, Georgia, USA., 2013: PMLR, pp. 1067-1075.
[62] A. Krizhevsky, I. Sutskever, and G. E. Hinton, "Imagenet classification with deep convolutional neural networks," Advances in neural information processing systems, vol. 25, 2012.
[63] G. Ortac and G. Ozcan, "Comparative study of hyperspectral image classification by multidimensional Convolutional Neural Network approaches to improve accuracy," Expert Systems with Applications, vol. 182, p. 115280, 2021.
[64] G. Petneházi, "Quantile convolutional neural networks for Value at Risk forecasting," Machine Learning with Applications, vol. 6, p. 100096, 2021.
[65] P. Sinha, "Multivariate polynomial regression in data mining: methodology, problems and solutions," International Journal of Scientific and Engineering Research, vol. 4, no. 12, pp. 962-965, 2013.
[66] M. Su, Q. Zhong, and H. Peng, "Regularized multivariate polynomial regression analysis of the compressive strength of slag-metakaolin geopolymer pastes based on experimental data," Construction and Building Materials, vol. 303, p. 124529, 2021.
[67] J. M. Pena, J. A. Lozano, and P. Larranaga, "An empirical comparison of four initialization methods for the k-means algorithm," Pattern recognition letters, vol. 20, no. 10, pp. 1027-1040, 1999.
[68] S. A. Abbas, A. Aslam, A. U. Rehman, W. A. Abbasi, S. Arif, and S. Z. H. Kazmi, "K-Means and K-Medoids: cluster analysis on birth data collected in City Muzaffarabad, Kashmir," IEEE Access, vol. 8, pp. 151847-151855, 2020.
[69] D. Steinley, "K‐means clustering: a half‐century synthesis," British Journal of Mathematical and Statistical Psychology, vol. 59, no. 1, pp. 1-34, 2006.
[70] A. Gupta, S. Kumar, and M. Pattanaik, "Coverage hole detection using social spider optimized Gaussian Mixture Model," Journal of King Saud University-Computer and Information Sciences, 2021.
[71] B. Zhang, X. Yan, G. Liu, and K. Fan, "Multi-source fault diagnosis of chiller plant sensors based on an improved ensemble empirical mode decomposition Gaussian mixture model," Energy Reports, vol. 8, pp. 2831-2842, 2022.
[72] K. Crammer, O. Dekel, J. Keshet, S. Shalev-Shwartz, and Y. Singer, "Online passive aggressive algorithms," Journal of Machine Learning research, vol. 7, pp. 551-585, 2006.
[73] K.-J. Bathe, Finite element procedures. Prentice Hall, Pearson Education, Klaus-Jurgen Bathe, USA., 2006.
[74] S. Timoshenko, Theory of elastic stability 2e. Tata McGraw-Hill Education, New york, USA., 1970.
[75] W. N. Findley and F. A. Davis, Creep and relaxation of nonlinear viscoelastic materials. Courier corporation, 2013.
[76] A. Schubert, R. Dudek, E. Auerswald, A. Gollhardt, B. Michel, and H. Reichl, "Fatigue life models for SnAgCu and SnPb solder joints evaluated by experiments and simulation," in Electronic components and technology conference, 2003: IEEE; 1999, pp. 603-610.
[77] J. Chakrabarty, Theory of plasticity. Elsevier, Amsterdam, Boston, Oxford, UK., 2012.
[78] N. E. Dowling, Mechanical behavior of materials: engineering methods for deformation, fracture, and fatigue. Prentice Hall international, New York, USA., 1993.
[79] G. Wang, Z. Cheng, K. Becker, and J. Wilde, "Applying Anand model to represent the viscoplastic deformation behavior of solder alloys," J. Electron. Packag., vol. 123, no. 3, pp. 247-253, 2001.
[80] J.-L. Chaboche, "Constitutive equations for cyclic plasticity and cyclic viscoplasticity," International journal of plasticity, vol. 5, no. 3, pp. 247-302, 1989.
[81] J.-L. Chaboche, "On some modifications of kinematic hardening to improve the description of ratchetting effects," International journal of plasticity, vol. 7, no. 7, pp. 661-678, 1991.
[82] J.-C. Lin, H.-C. Cheng, and K.-N. Chiang, "Design and analysis of wafer-level CSP with a double-pad structure," IEEE Transactions on Components and Packaging Technologies, vol. 28, no. 1, pp. 117-126, 2005.
[83] R. D. Cook, Concepts and applications of finite element analysis. John wiley & sons, USA., 2007.
[84] Y. Gu and T. Nakamura, "Interfacial delamination and fatigue life estimation of 3D solder bumps in flip-chip packages," Microelectronics Reliability, vol. 44, no. 3, pp. 471-483, 2004.
[85] A. C. Müller and S. Guido, Introduction to machine learning with Python: a guide for data scientists. " O'Reilly Media, Inc.", North Sebastopol, CA, USA., 2016.
[86] F. Pedregosa et al., "Scikit-learn: Machine learning in Python," the Journal of machine Learning research, vol. 12, pp. 2825-2830, 2011.
[87] C. Gershenson, "Artificial neural networks for beginners," arXiv preprint cs/0308031, 2003.
[88] P. Chou, K. Chiang, and S. Y. Liang, "Reliability assessment of wafer level package using artificial neural network regression model," Journal of Mechanics, vol. 35, no. 6, pp. 829-837, 2019.
[89] C. Nwankpa, W. Ijomah, A. Gachagan, and S. Marshall, "Activation functions: Comparison of trends in practice and research for deep learning," arXiv preprint arXiv:1811.03378, 2018.
[90] S. Ruder, "An overview of gradient descent optimization algorithms," arXiv preprint arXiv:1609.04747, 2016.
[91] Y. Hamed, Z. B. Mustaffa, and N. R. B. Idris, "Comparative Calibration of Corrosion Measurements Using K-Nearest Neighbour Based Techniques," in MATEC Web of Conferences, 2016, vol. 52: EDP Sciences, p. 02001.
[92] G. K. Michelon, "Web application for generation of thematic maps and determination of proximal sensor placement locations for use in precision agriculture," Universidade Tecnológica Federal do Paraná, 2018.
[93] W. Härdle and O. Linton, "Applied nonparametric methods," Handbook of econometrics, Elsevier, vol. 4, pp. 2295-2339, 1994.
[94] C. G. Atkeson, A. W. Moore, and S. Schaal, "Locally weighted learning for control. Lazy learning," pp. 75-113, 1997.
[95] M. Welling, "Kernel ridge regression," Max Welling’s classnotes in machine learning, pp. 1-3, 2013.
[96] M. Hofmann, "Support vector machines-kernels and the kernel trick," Notes, vol. 26, no. 3, pp. 1-16, 2006.
[97] G. Gordon and R. Tibshirani, "Karush-kuhn-tucker conditions," Optimization, vol. 10, no. 725/36, p. 725, 2012.
[98] J. Rui, H. Zhang, D. Zhang, F. Han, and Q. Guo, "Total organic carbon content prediction based on support-vector-regression machine with particle swarm optimization," Journal of petroleum science and engineering, vol. 180, pp. 699-706, 2019.
[99] C. Rasmussen, "CKI Williams Gaussian processes for machine learning," ed: MIT Press Cambridge, MA, USA:, 2006.
[100] D. Yang, X. Zhang, R. Pan, Y. Wang, and Z. Chen, "A novel Gaussian process regression model for state-of-health estimation of lithium-ion battery using charging curve," Journal of Power Sources, vol. 384, pp. 387-395, 2018.
[101] E. Ostertagová, "Modelling using polynomial regression," Procedia Engineering, vol. 48, pp. 500-506, 2012.
[102] D. G. Kleinbaum, L. L. Kupper, A. Nizam, and E. S. Rosenberg, Applied regression analysis and other multivariable methods. Cengage Learning, Boston, USA., 2013.
[103] Y.-L. Cheng, The dimensionality of cognitive structure: A MIRT approach and the use of subscores. Michigan State University, USA., 2016.
[104] P. J. Rousseeuw, "Silhouettes: a graphical aid to the interpretation and validation of cluster analysis," Journal of computational and applied mathematics, vol. 20, pp. 53-65, 1987.
[105] M. Ay and O. Kisi, "Modelling of chemical oxygen demand by using ANNs, ANFIS and k-means clustering techniques," Journal of Hydrology, vol. 511, pp. 279-289, 2014.
[106] R. M. Adnan, P. Khosravinia, B. Karimi, and O. Kisi, "Prediction of hydraulics performance in drain envelopes using Kmeans based multivariate adaptive regression spline," Applied Soft Computing, vol. 100, p. 107008, 2021.
[107] S. Cao, Z. Hu, X. Luo, and H. Wang, "Research on fault diagnosis technology of centrifugal pump blade crack based on PCA and GMM," Measurement, vol. 173, p. 108558, 2021.
[108] Y. Wu et al., "Dynamic Gaussian mixture based deep generative model for robust forecasting on sparse multivariate time series," arXiv preprint arXiv:2103.02164, 2021.
[109] S.-J. Qiao, K. Jin, N. Han, C.-J. Tang, and G. Gesangduoji, "Trajectory prediction algorithm based on Gaussian mixture model," Journal of software, vol. 26, no. 5, pp. 1048-1063, 2015.
[110] Y. Guo and H. Chen, "Fault diagnosis of VRF air-conditioning system based on improved Gaussian mixture model with PCA approach," International journal of refrigeration, vol. 118, pp. 1-11, 2020.
[111] D. A. Reynolds, "Gaussian mixture models," Encyclopedia of biometrics, vol. 741, no. 659-663, 2009.
[112] M.-C. Hsieh and S.-L. Tzeng, "Solder joint fatigue life prediction in large size and low cost wafer-level chip scale packages," in 2014 15th International Conference on Electronic Packaging Technology, Chengdu, China., 2014: IEEE, pp. 496-501.
[113] M.-C. Hsieh, "Modeling correlation for solder joint fatigue life estimation in wafer-level chip scale packages," in 2015 10th International Microsystems, Packaging, Assembly and Circuits Technology Conference (IMPACT), 2015: IEEE, pp. 65-68.
[114] B. Rogers and C. Scanlan, "Improving WLCSP reliability through solder joint geometry optimization," in International Symposium on Microelectronics, 2013, vol. 2013, no. 1: International Microelectronics Assembly and Packaging Society, pp. 000546-000550.
[115] J. S. S. T. Association, "JEDEC Standard JESD22-A104D, Temperature Cycling," Jedec. Org, vol. 11, p. 2009, 2005.
[116] J. Chang, L. Wang, J. Dirk, and X. Xie, "Finite element modeling predicts the effects of voids on thermal shock reliability and thermal resistance of power device," Welding journal, vol. 85, no. 3, pp. 63s-70s, 2006.
[117] L. F. Coffin Jr, "A study of the effects of cyclic thermal stresses on a ductile metal," Transactions of the American Society of Mechanical Engineers, New York, vol. 76, pp. 931-950, 1954.
[118] V. Ramachandran, K. Wu, and K. Chiang, "Overview study of solder joint reliablity due to creep deformation," Journal of Mechanics, vol. 34, no. 5, pp. 637-643, 2018.
[119] C.-H. Lee, K.-C. Wu, and K.-N. Chiang, "A novel acceleration-factor equation for packaging-solder joint reliability assessment at different thermal cyclic loading rates," Journal of Mechanics, vol. 33, no. 1, pp. 35-40, 2017.
[120] X. Yanjun, W. Liquan, W. Fengshun, X. Weisheng, and L. Hui, "Effect of interface structure on fatigue life under thermal cycle with SAC305 solder joints," in 2013 14th International Conference on Electronic Packaging Technology, 2013: IEEE, pp. 959-964.
[121] Y. Huang and K. Chiang, "Study of shear locking effect on 3D solder joint reliability analysis," Journal of Mechanics, vol. 38, pp. 176-184, 2022.
[122] P. Wang, Y. Lee, C. Lee, H. Chang, and K. Chiang, "Solder Joint Reliability Assessment and Pad Size Studies of FO-WLP with Glass Substrate," IEEE Transactions on Device and Materials Reliability, vol. 21, no. 1, pp. 96-101, 2021.
[123] Q.-H. Su and K.-N. Chiang, "Predicting Wafer-Level Package Reliability Life Using Mixed Supervised and Unsupervised Machine Learning Algorithms," Materials, vol. 15, no. 11, p. 3897, 2022.
[124] S. C. Chaparala et al., "Effect of geometry and temperature cycle on the reliability of WLCSP solder joints," IEEE transactions on components and packaging technologies, vol. 28, no. 3, pp. 441-448, 2005.
[125] L. F. Atherton and R. W. Atherton, Wafer fabrication: Factory performance and analysis. Springer Science & Business Media, Massachusetts, USA., 1995.
[126] B. N. Muthuraman and B. Canete, "Board Level Reliability assessment of Wafer Level Chip Scale Packages for SACQ, a lead-free solder with a novel life prediction model," in 2018 7th Electronic System-Integration Technology Conference (ESTC), Dresden, Germany., 2018: IEEE, pp. 1-5.
[127] C.-C. Lee, S.-M. Chang, and K.-N. Chiang, "Sensitivity design of DL-WLCSP using DOE with factorial analysis technology," IEEE transactions on advanced packaging, vol. 30, no. 1, pp. 44-55, 2007.
[128] S. Liu, S. Panigrahy, and K. Chiang, "Prediction of fan-out panel level warpage using neural network model with edge detection enhancement," in 2020 IEEE 70th Electronic Components and Technology Conference (ECTC), Orlando, FL, USA., 2020: IEEE, pp. 1626-1631.
[129] T. He et al., "Deep neural networks and kernel regression achieve comparable accuracies for functional connectivity prediction of behavior and demographics," NeuroImage, vol. 206, p. 116276, 2020.
[130] V. Vovk, "Kernel ridge regression," in Empirical inference: Springer, Berlin, Germany., 2013, pp. 105-116.