基于决策树的GaN HEMT小信号行为建模

2019 IEEE 62nd International Midwest Symposium on Circuits and Systems (MWSCAS) Pub Date : 2019-08-01 DOI:10.1109/MWSCAS.2019.8885334

A. Khusro, M. Hashmi, A. Q. Ansari, Medet Auyenur

{"title":"基于决策树的GaN HEMT小信号行为建模","authors":"A. Khusro, M. Hashmi, A. Q. Ansari, Medet Auyenur","doi":"10.1109/MWSCAS.2019.8885334","DOIUrl":null,"url":null,"abstract":"The paper, for the first time, explores multivariable small signal modeling technique of GaN HEMT based on Decision tree. The proposed model presents a novel binary decision tree to model the GaN HEMT device for multi-biasing and broad frequency range. Bayesian algorithm has been used to find the optimal hyperparameters for better generalization capability and higher accuracy. An excellent agreement is found between the measured S-parameters and the proposed model for complete frequency range of 1GHz-18GHz.","PeriodicalId":287815,"journal":{"name":"2019 IEEE 62nd International Midwest Symposium on Circuits and Systems (MWSCAS)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"9","resultStr":"{\"title\":\"A new and Reliable Decision Tree Based Small-Signal Behavioral Modeling of GaN HEMT\",\"authors\":\"A. Khusro, M. Hashmi, A. Q. Ansari, Medet Auyenur\",\"doi\":\"10.1109/MWSCAS.2019.8885334\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"The paper, for the first time, explores multivariable small signal modeling technique of GaN HEMT based on Decision tree. The proposed model presents a novel binary decision tree to model the GaN HEMT device for multi-biasing and broad frequency range. Bayesian algorithm has been used to find the optimal hyperparameters for better generalization capability and higher accuracy. An excellent agreement is found between the measured S-parameters and the proposed model for complete frequency range of 1GHz-18GHz.\",\"PeriodicalId\":287815,\"journal\":{\"name\":\"2019 IEEE 62nd International Midwest Symposium on Circuits and Systems (MWSCAS)\",\"volume\":\"15 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2019-08-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"9\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2019 IEEE 62nd International Midwest Symposium on Circuits and Systems (MWSCAS)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/MWSCAS.2019.8885334\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2019 IEEE 62nd International Midwest Symposium on Circuits and Systems (MWSCAS)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/MWSCAS.2019.8885334","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 9

摘要

本文首次探索了基于决策树的GaN HEMT多变量小信号建模技术。该模型提出了一种新的二叉决策树，用于多偏置和宽频率范围的GaN HEMT器件的建模。采用贝叶斯算法寻找最优超参数，具有更好的泛化能力和更高的精度。在1GHz-18GHz的整个频率范围内，实测的s参数与所提出的模型非常吻合。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

A new and Reliable Decision Tree Based Small-Signal Behavioral Modeling of GaN HEMT

The paper, for the first time, explores multivariable small signal modeling technique of GaN HEMT based on Decision tree. The proposed model presents a novel binary decision tree to model the GaN HEMT device for multi-biasing and broad frequency range. Bayesian algorithm has been used to find the optimal hyperparameters for better generalization capability and higher accuracy. An excellent agreement is found between the measured S-parameters and the proposed model for complete frequency range of 1GHz-18GHz.

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

2019 IEEE 62nd International Midwest Symposium on Circuits and Systems (MWSCAS)

自引率

0.00%

发文量