首页> 外文期刊>Neurocomputing >Designing and modeling of ultra low voltage and ultra low power LNA using ANN and ANFIS for Bluetooth applications
【24h】

Designing and modeling of ultra low voltage and ultra low power LNA using ANN and ANFIS for Bluetooth applications

机译:使用ANN和ANFIS为蓝牙应用设计和设计超低压和超低功耗LNA

获取原文
获取原文并翻译 | 示例
           

摘要

This paper reports the design of an ultra low voltage and ultra low power RF CMOS LNA using a two-stage common source-common gate topology with source inductive degeneration. The proposed structure reduced the supply voltage and power consumption. Considering the complexity of the analysis, it is necessary to simulate a neural model with high speed and accuracy. The proposed LNA is accurately modeled using ANN (MLP and RBF) and ANFIS. The model accuracy is evaluated for all the input-output parameters in the Bluetooth frequency range. A model of low voltage and low power LNA using ANN for Bluetooth applications is developed. The results show the average errors of 0.106%, 0.093% and 7.18 × 10~(-5)% using MLP, RBF and ANFIS, respectively. It is observed that the ANFIS model is better than ANN for developing the model and increasing the input parameters.
机译:本文报告了一种采用两级共源-共栅拓扑结构和源极电感退化的超低压和超低功耗RF CMOS LNA设计。所提出的结构降低了电源电压和功耗。考虑到分析的复杂性,有必要以高速和准确的方式模拟神经模型。使用ANN(MLP和RBF)和ANFIS对所提出的LNA进行精确建模。针对蓝牙频率范围内的所有输入输出参数评估模型的准确性。针对蓝牙应用,开发了使用ANN的低压低功耗LNA模型。结果表明,使用MLP,RBF和ANFIS的平均误差分别为0.106%,0.093%和7.18×10〜(-5)%。可以看出,在开发模型和增加输入参数方面,ANFIS模型优于ANN。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号