基于支持向量機的濾波器設計及硬件實現(xiàn)
發(fā)布時間：2018-10-10 11:49
【摘要】：濾波器是電子設備中的常見模塊,經(jīng)典的濾波器設計方法有窗函數(shù)法,頻率抽取法等。自機器學習的理論出現(xiàn)后,神經(jīng)網(wǎng)絡等算法廣泛應用到FIR濾波器的設計中。本文針對傳統(tǒng)FIR濾波器設計方法及神經(jīng)網(wǎng)絡設計方法的不足,在改進使用支持向量機(SVM)設計FIR濾波器方法的基礎上,提出了 SVM設計FIR濾波器的硬件實現(xiàn)方法,將由SVM設計的濾波器移植到硬件上。使用SVM構造FIR濾波器,得到的濾波器可更新,并且使用的訓練樣本較少,本文中使用理想濾波器的幅值響應訓練SVM。在建立SVM模型的過程中,本文引入針對訓練集輸出值的放大參數(shù),該參數(shù)將數(shù)據(jù)集分離,并影響最終的幅頻響應。SVM模型中訓練參數(shù)較多,如訓練組數(shù)、懲罰參數(shù)、核函數(shù)參數(shù)等,本文進行多次測試,將結果進行比較得到最優(yōu)訓練參數(shù),據(jù)此構建基于SVM的FIR濾波器模型。相對于窗函數(shù),使用S VM設計的濾波器具有良好的幅頻特性,邊界控制較為精確,通帶較為平緩,阻帶波動次數(shù)較少,衰減較多。為了保證濾波器的可更改性和便于其移植到其他系統(tǒng)里,利用生成的FIR濾波器模型構建一個位于FPGA上的嵌入式系統(tǒng)。FIR濾波器嵌入式系統(tǒng)主要由SVM構成,對SVM算法中頻繁出現(xiàn)的核函數(shù)計算以及浮點數(shù)乘法加法運算進行硬件實現(xiàn),對SVM算法中的訓練部分和分類部分進行軟件框架實現(xiàn)。本文對核函數(shù)的硬件實現(xiàn)進行優(yōu)化,針對RBF核函數(shù),進行算法上的改進,加速運算,同時使用流水線、向量分割等方法加速硬件系統(tǒng),并平衡速度與資源。最終系統(tǒng)中單次分類測試向量的時間約為20us,濾波準確率可達到98.41%。
[Abstract]:Filter is a common module in electronic equipment. The classical filter design methods include window function method, frequency decimation method and so on. Since the emergence of the theory of machine learning, neural networks and other algorithms are widely used in the design of FIR filters. Aiming at the shortcomings of the traditional FIR filter design method and the neural network design method, this paper proposes a hardware implementation method of SVM design FIR filter based on improving the FIR filter design method using support vector machine (SVM). The filter designed by SVM is transplanted to hardware. Using SVM to construct FIR filter, the filter can be updated and less training samples are used. In this paper, the amplitude response of ideal filter is used to train SVM.. In the process of establishing the SVM model, this paper introduces the amplification parameter for the output value of the training set, which separates the data set and affects the final amplitude-frequency response. There are many training parameters in the SVM model, such as the number of training groups and the penalty parameter. The kernel function parameters are tested several times in this paper, and the optimal training parameters are obtained by comparing the results, and then the FIR filter model based on SVM is constructed. Compared with the window function, the filter designed by S VM has good amplitude-frequency characteristic, the boundary control is more accurate, the passband is more gentle, the frequency of stopband fluctuation is less, and the attenuation is more. In order to ensure the modifiability of the filter and to transplant it to other systems, an embedded system. Fir filter embedded system based on FPGA is constructed by using the generated FIR filter model. The embedded system is mainly composed of SVM. The kernel function calculation and floating-point multiplication addition in SVM algorithm are implemented by hardware, and the training part and classification part of SVM algorithm are implemented by software framework. In this paper, the hardware implementation of kernel function is optimized. For RBF kernel function, the algorithm is improved and the operation is accelerated. At the same time, pipeline and vector partition are used to accelerate the hardware system, and the speed and resources are balanced. In the final system, the time of single classification test vector is about 20us, and the filtering accuracy can reach 98.41%.
【學位授予單位】：浙江大學
【學位級別】：碩士
【學位授予年份】：2017
【分類號】：TN713
本文編號：2261651
[Abstract]:Filter is a common module in electronic equipment. The classical filter design methods include window function method, frequency decimation method and so on. Since the emergence of the theory of machine learning, neural networks and other algorithms are widely used in the design of FIR filters. Aiming at the shortcomings of the traditional FIR filter design method and the neural network design method, this paper proposes a hardware implementation method of SVM design FIR filter based on improving the FIR filter design method using support vector machine (SVM). The filter designed by SVM is transplanted to hardware. Using SVM to construct FIR filter, the filter can be updated and less training samples are used. In this paper, the amplitude response of ideal filter is used to train SVM.. In the process of establishing the SVM model, this paper introduces the amplification parameter for the output value of the training set, which separates the data set and affects the final amplitude-frequency response. There are many training parameters in the SVM model, such as the number of training groups and the penalty parameter. The kernel function parameters are tested several times in this paper, and the optimal training parameters are obtained by comparing the results, and then the FIR filter model based on SVM is constructed. Compared with the window function, the filter designed by S VM has good amplitude-frequency characteristic, the boundary control is more accurate, the passband is more gentle, the frequency of stopband fluctuation is less, and the attenuation is more. In order to ensure the modifiability of the filter and to transplant it to other systems, an embedded system. Fir filter embedded system based on FPGA is constructed by using the generated FIR filter model. The embedded system is mainly composed of SVM. The kernel function calculation and floating-point multiplication addition in SVM algorithm are implemented by hardware, and the training part and classification part of SVM algorithm are implemented by software framework. In this paper, the hardware implementation of kernel function is optimized. For RBF kernel function, the algorithm is improved and the operation is accelerated. At the same time, pipeline and vector partition are used to accelerate the hardware system, and the speed and resources are balanced. In the final system, the time of single classification test vector is about 20us, and the filtering accuracy can reach 98.41%.
【學位授予單位】：浙江大學
【學位級別】：碩士
【學位授予年份】：2017
【分類號】：TN713
【參考文獻】
相關期刊論文 前4條
1 吉立新;魏開容;劉冰洋;聶智良;;基于組合-移位的指數(shù)運算FPGA實現(xiàn)方法[J];信息工程大學學報;2011年05期
2 孫豐闊;席斌;;基于支持向量回歸(SVR)的線性相位FIR濾波器設計[J];福州大學學報(自然科學版);2008年S1期
3 陳楊生;顏鋼鋒;;硬件實現(xiàn)基于BP神經(jīng)網(wǎng)絡設計的帶阻FIR濾波器[J];浙江大學學報(工學版);2006年07期
4 周衛(wèi)東,李英遠;基于神經(jīng)網(wǎng)絡的FIR濾波器設計與應用[J];山東大學學報(工學版);2003年01期
，本文編號：2261651
本文鏈接：http://www.lk138.cn/kejilunwen/dianzigongchenglunwen/2261651.html
教材專著
