A Machine Learning Study to Obtain an Optimal Processing Pulsed Frequency on Reactive Pulsed DC Sputtering of Aluminum Nitride Films (2024)

Tseng, X. L., Chen, Y. S., Chen, H. F., Lo, H. H., Wang, P. J., Dai, Y. M., Fuh, Y. K. (2024). A Machine Learning Study to Obtain an Optimal Processing Pulsed Frequency on Reactive Pulsed DC Sputtering of Aluminum Nitride Films. In C. Claeys, B. Zhang, B. Yu, R. Huang, X. Li, S. X. Liang, J. Tang, H.-L. Lung, L. Pang, W. Qian, X. Qu, X. Shi, & Y. Zhang (Eds.), 2024 Conference of Science and Technology for Integrated Circuits, CSTIC 2024 (2024 Conference of Science and Technology for Integrated Circuits, CSTIC 2024). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/CSTIC61820.2024.10532082

@inproceedings{54dfc84b06c04c57a2bbab2094c575fb,

title = "A Machine Learning Study to Obtain an Optimal Processing Pulsed Frequency on Reactive Pulsed DC Sputtering of Aluminum Nitride Films",

abstract = "The goal of this study was to investigate how changing the pulsed frequency affects the deposition process and correlates with AlN film properties. The resulting films were then characterized in terms of their crystallinity, microstructure, and surface roughness to identify any correlations with the pulsed frequency. This approach was used to determine the optimal pulsed conditions for film deposition. Each dataset spans the wavelength range of 190nm to 850nm, comprising 1,900 features. Following data collection, we employed traditional ensemble learning methods (Random Forest), tree-based gradient boosting (Categorical Boosting), and the improved gradient-boosted algorithm (Histogram Gradient Boosting), for predicting the quality of thin films. This analysis aimed to clarify which method excels in handling semiconductor process OES data to obtain an optimal processing pulsed frequency on reactive pulsed DC sputtering of aluminum nitride films.",

keywords = "aluminum nitride (AlN), Categorical Boosting (CatBoost), Histogram-Based Gradient Boosting (HGB), machine learning, optical emission spectroscopy (OES), pulsed frequency, Random Forest, Reactive pulsed DC magnetron sputtering",

author = "Tseng, {Xue Li} and Chen, {Yu Shin} and Chen, {Hsuan Fan} and Lo, {Hsiao Han} and Wang, {Peter J.} and Dai, {Yu Min} and Fuh, {Yiin Kuen} and Ting-Tung Li",

note = "Publisher Copyright: {\textcopyright} 2024 IEEE.; 2024 Conference of Science and Technology for Integrated Circuits, CSTIC 2024 ; Conference date: 17-03-2024 Through 18-03-2024",

year = "2024",

doi = "10.1109/CSTIC61820.2024.10532082",

language = "???core.languages.en_GB???",

series = "2024 Conference of Science and Technology for Integrated Circuits, CSTIC 2024",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

editor = "Cor Claeys and Beichao Zhang and Bin Yu and Ru Huang and Xiaowei Li and Liang, {Steve X.} and Jianshi Tang and Hsiang-Lan Lung and Linyong Pang and Weikang Qian and Xinping Qu and Xiaoping Shi and Ying Zhang",

booktitle = "2024 Conference of Science and Technology for Integrated Circuits, CSTIC 2024",

}

Tseng, XL, Chen, YS, Chen, HF, Lo, HH, Wang, PJ, Dai, YM, Fuh, YK 2024, A Machine Learning Study to Obtain an Optimal Processing Pulsed Frequency on Reactive Pulsed DC Sputtering of Aluminum Nitride Films. in C Claeys, B Zhang, B Yu, R Huang, X Li, SX Liang, J Tang, H-L Lung, L Pang, W Qian, X Qu, X Shi & Y Zhang (eds), 2024 Conference of Science and Technology for Integrated Circuits, CSTIC 2024. 2024 Conference of Science and Technology for Integrated Circuits, CSTIC 2024, Institute of Electrical and Electronics Engineers Inc., 2024 Conference of Science and Technology for Integrated Circuits, CSTIC 2024, Shanghai, China, 17/03/24. https://doi.org/10.1109/CSTIC61820.2024.10532082

A Machine Learning Study to Obtain an Optimal Processing Pulsed Frequency on Reactive Pulsed DC Sputtering of Aluminum Nitride Films. / Tseng, Xue Li; Chen, Yu Shin; Chen, Hsuan Fan et al.
2024 Conference of Science and Technology for Integrated Circuits, CSTIC 2024. ed. / Cor Claeys; Beichao Zhang; Bin Yu; Ru Huang; Xiaowei Li; Steve X. Liang; Jianshi Tang; Hsiang-Lan Lung; Linyong Pang; Weikang Qian; Xinping Qu; Xiaoping Shi; Ying Zhang. Institute of Electrical and Electronics Engineers Inc., 2024. (2024 Conference of Science and Technology for Integrated Circuits, CSTIC 2024).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - A Machine Learning Study to Obtain an Optimal Processing Pulsed Frequency on Reactive Pulsed DC Sputtering of Aluminum Nitride Films

AU - Tseng, Xue Li

AU - Chen, Yu Shin

AU - Chen, Hsuan Fan

AU - Lo, Hsiao Han

AU - Wang, Peter J.

AU - Dai, Yu Min

AU - Fuh, Yiin Kuen

AU - Li, Ting-Tung

N1 - Publisher Copyright:© 2024 IEEE.

PY - 2024

Y1 - 2024

N2 - The goal of this study was to investigate how changing the pulsed frequency affects the deposition process and correlates with AlN film properties. The resulting films were then characterized in terms of their crystallinity, microstructure, and surface roughness to identify any correlations with the pulsed frequency. This approach was used to determine the optimal pulsed conditions for film deposition. Each dataset spans the wavelength range of 190nm to 850nm, comprising 1,900 features. Following data collection, we employed traditional ensemble learning methods (Random Forest), tree-based gradient boosting (Categorical Boosting), and the improved gradient-boosted algorithm (Histogram Gradient Boosting), for predicting the quality of thin films. This analysis aimed to clarify which method excels in handling semiconductor process OES data to obtain an optimal processing pulsed frequency on reactive pulsed DC sputtering of aluminum nitride films.

AB - The goal of this study was to investigate how changing the pulsed frequency affects the deposition process and correlates with AlN film properties. The resulting films were then characterized in terms of their crystallinity, microstructure, and surface roughness to identify any correlations with the pulsed frequency. This approach was used to determine the optimal pulsed conditions for film deposition. Each dataset spans the wavelength range of 190nm to 850nm, comprising 1,900 features. Following data collection, we employed traditional ensemble learning methods (Random Forest), tree-based gradient boosting (Categorical Boosting), and the improved gradient-boosted algorithm (Histogram Gradient Boosting), for predicting the quality of thin films. This analysis aimed to clarify which method excels in handling semiconductor process OES data to obtain an optimal processing pulsed frequency on reactive pulsed DC sputtering of aluminum nitride films.

KW - aluminum nitride (AlN)

KW - Categorical Boosting (CatBoost)

KW - Histogram-Based Gradient Boosting (HGB)

KW - machine learning

KW - optical emission spectroscopy (OES)

KW - pulsed frequency

KW - Random Forest

KW - Reactive pulsed DC magnetron sputtering

UR - http://www.scopus.com/inward/record.url?scp=85195114697&partnerID=8YFLogxK

U2 - 10.1109/CSTIC61820.2024.10532082

DO - 10.1109/CSTIC61820.2024.10532082

M3 - 會議論文篇章

AN - SCOPUS:85195114697

T3 - 2024 Conference of Science and Technology for Integrated Circuits, CSTIC 2024

BT - 2024 Conference of Science and Technology for Integrated Circuits, CSTIC 2024

A2 - Claeys, Cor

A2 - Zhang, Beichao

A2 - Yu, Bin

A2 - Huang, Ru

A2 - Li, Xiaowei

A2 - Liang, Steve X.

A2 - Tang, Jianshi

A2 - Lung, Hsiang-Lan

A2 - Pang, Linyong

A2 - Qian, Weikang

A2 - Qu, Xinping

A2 - Shi, Xiaoping

A2 - Zhang, Ying

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2024 Conference of Science and Technology for Integrated Circuits, CSTIC 2024

Y2 - 17 March 2024 through 18 March 2024

ER -