The Training of Feedforward Neural Network Using The Unscented Kalman Filter for Voice Classification Application

被引：0

作者：

Darojah, Zaqiatud ^{[1
]}

Ningrum, Endah Suryawati ^{[1
]}

Purnomo, Didik Setyo ^{[1
]}

机构：

[1] Politekn Elekt Negeri Surabaya, Dept Mechatron, Surabaya, Indonesia

来源：

2017 INTERNATIONAL ELECTRONICS SYMPOSIUM ON KNOWLEDGE CREATION AND INTELLIGENT COMPUTING (IES-KCIC) | 2017年

关键词：

Neural Network; Extended Kalman Filter; Unsented Kalman Filter; Voice Classification;

D O I：

暂无

中图分类号：

TP301 [理论、方法];

学科分类号：

081202 ;

摘要：

In the previous study, we have investigated that the Extended Kalman Filter (EKF) has the excellennt performance and very fast learning as the training of Feedforward Neural Network (FNN). In the expansion of Kalman filter algorithm for nonlinear estimation, the Unscented Kalman Filter (UKF) was proposed. Enlightened the UKF is superior to EKF, in this study, we investigate the UKF algorithm as the training of FNN for voice classification application. Simulation results show that the UKF has also very excellence performance. The training process need only 2 epochs with the average performance rates in training data is 100% and the average performance rates in the testing data is 94.49%. These results are the same as the EKF-based FNN and the Levenberg-Marquardt Backpropagation but differ in the required training epoch.

引用

页码：21 / 25

页数：5

共 50 条

[41] A full bi-tensor neural tractography algorithm using the unscented Kalman filter
Stefan Lienhard
James G Malcolm
Carl-Frederik Westin
Yogesh Rathi
EURASIP Journal on Advances in Signal Processing, 2011
[42] Issues in training set selection and refinement for classification by a feedforward neural network
Foody, GM
IGARSS '98 - 1998 INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM, PROCEEDINGS VOLS 1-5: SENSING AND MANAGING THE ENVIRONMENT, 1998, : 409 - 411
[43] Unscented Kalman filter for urban network travel time estimation
Hage, Re-Mi
Betaille, David
Peyret, Francois
Meizel, Dominique
PROCEEDINGS OF EWGT 2012 - 15TH MEETING OF THE EURO WORKING GROUP ON TRANSPORTATION, 2012, 54 : 1047 - 1057
[44] The significance of border training patterns in classification by a feedforward neural network using back propagation learning
Foody, GM
INTERNATIONAL JOURNAL OF REMOTE SENSING, 1999, 20 (18) : 3549 - 3562
[45] Nerual Network Assisted Adaptive Unscented Kalman Filter for AUV
Chen, Xu
Wu, Shuyi
Zhang, Xin
Mu, Xiaokai
Yan, Tianhong
He, Bo
GLOBAL OCEANS 2020: SINGAPORE - U.S. GULF COAST, 2020,
[46] Recurrent neural network training with the Kalman Filter-based techniques
Trebaticky, P
NEURAL NETWORK WORLD, 2005, 15 (05) : 471 - 488
[47] On the Efficiency of SLAM Using Adaptive Unscented Kalman Filter
Bahraini, Masoud Sotoodeh
IRANIAN JOURNAL OF SCIENCE AND TECHNOLOGY-TRANSACTIONS OF MECHANICAL ENGINEERING, 2020, 44 (03) : 727 - 735
[48] Ballistic missile tracking using unscented Kalman filter
Park, Sanghyuk
Yun, Joongsup
Ryoo, Chang-Kyung
Journal of Institute of Control, Robotics and Systems, 2008, 14 (09) : 898 - 903
[49] Wheelset states estimation using unscented Kalman filter
Yang, Z.
Lu, Z. G.
Wang, X. C.
Huang, Q.
DYNAMICS OF VEHICLES ON ROADS AND TRACKS, VOL 2, 2018, : 1071 - 1076
[50] Acoustic Tomography of the Atmosphere Using Unscented Kalman Filter
Kolouri, Soheil
Azimi-Sadjadi, Mahmood R.
Ziemann, Astrid
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2014, 52 (04): : 2159 - 2171

← 1 2 3 4 5 →