An adaptive beamforming approach using online learning neural network

2004 ◽  
Author(s):  
Xu-Bao Sun ◽  
Shun-Shi Zhong
Keyword(s):  
Neural Network ◽  
Online Learning ◽  
Adaptive Beamforming

Neural Network Adaptive Beamforming for Robust Multichannel Speech Recognition

2016 ◽  
Author(s):  
Bo Li ◽  
Tara N. Sainath ◽  
Ron J. Weiss ◽  
Kevin W. Wilson ◽  
Michiel Bacchiani
Keyword(s):  
Neural Network ◽  
Speech Recognition ◽  
Adaptive Beamforming

Convolutional neural network for 2D adaptive beamforming of phased array antennas with robustness to array imperfections

2021 ◽  
pp. 1-7
Author(s):  
Tarek Sallam ◽  
Ahmed M. Attiya
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Phased Array ◽  
Weight Vector ◽  
Adaptive Beamforming ◽  
Phased Array Antenna ◽  
Phased Array Antennas ◽  
Array Antennas ◽  
Optimum Weight ◽  
High Computational Complexity

Abstract Achieving robust and fast two-dimensional adaptive beamforming of phased array antennas is a challenging problem due to its high-computational complexity. To address this problem, a deep-learning-based beamforming method is presented in this paper. In particular, the optimum weight vector is computed by modeling the problem as a convolutional neural network (CNN), which is trained with I/O pairs obtained from the optimum Wiener solution. In order to exhibit the robustness of the new technique, it is applied on an 8 × 8 phased array antenna and compared with a shallow (non-deep) neural network namely, radial basis function neural network. The results reveal that the CNN leads to nearly optimal Wiener weights even in the presence of array imperfections.

scholarly journals A Novel Neuron in Kernel Domain

2013 ◽  
Vol 2013 ◽  
pp. 1-11 ◽  
Author(s):  
Zahra Khandan ◽  
Hadi Sadoghi Yazdi
Keyword(s):  
Neural Network ◽  
Online Learning ◽  
Mean Square ◽  
Least Mean Square ◽  
Backpropagation Neural Network ◽  
Adaptive Parameters ◽  
Kernel Parameter ◽  
Online Learning Algorithms ◽  
Adaptive Kernel ◽  
Kernel Least Mean Square

Kernel-based neural network (KNN) is proposed as a neuron that is applicable in online learning with adaptive parameters. This neuron with adaptive kernel parameter can classify data accurately instead of using a multilayer error backpropagation neural network. The proposed method, whose heart is kernel least-mean-square, can reduce memory requirement with sparsification technique, and the kernel can adaptively spread. Our experiments will reveal that this method is much faster and more accurate than previous online learning algorithms.

scholarly journals EVALUATION OF A NEURAL-NETWORK-BASED ADAPTIVE BEAMFORMING SCHEME WITH MAGNITUDE-ONLY CONSTRAINTS

2009 ◽  
Vol 11 ◽  
pp. 1-14 ◽  
Author(s):  
Giuseppe Castaldi ◽  
Vincenzo Galdi ◽  
Giampiero Gerini
Keyword(s):  
Neural Network ◽  
Adaptive Beamforming

scholarly journals Loss minimization DTC electric motor drive system based on adaptive ANN strategy

2020 ◽  
Vol 11 (2) ◽  
pp. 618
Author(s):  
Sim Sy Yi ◽  
Wahyu Mulyo Utomo ◽  
Goh Hui Hwang ◽  
Chien Siong Kai ◽  
Alvin John Lim Meng Siang ◽  
...  
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Online Learning ◽  
Electric Motor ◽  
Drive System ◽  
Motor Drive ◽  
Loss Minimization ◽  
Light Load ◽  
Flux Level ◽  
Electric Motor Drive

Electric motor drive systems (EMDS) have been recognized as one of the most promising motor systems recently due to their low energy consumption and reduced emissions. With only some exceptions, EMDS are the main source for the provision of mechanical energy in industry and accounts for about 60% of global industrial electricity consumption. Large energy efficiency potentials have been identified in EMDS with very short payback time and high-cost effectiveness. Typical, during operation at rated mode, the motor drive able to hold its good efficiencies. However, a motor usually operates out from rated mode in many applications, especially while under light load, it reduced the motor’s efficiency severely. Hence, it is necessary that a conventional drive system to embed with loss minimization strategy to optimize the drive system efficiency over all operation range. Conventionally, the flux value is keeping constantly over the range of operation, where it should be highlighted that for any operating point, the losses could be minimize with the proper adjustment of the flux level to a suitable value at that point. Hence, with the intention to generate an adaptive flux level corresponding to any operating point, especially at light load condition, an online learning Artificial Neural Network (ANN) controller was proposed in this study, to minimize the system losses. The entire proposed strategic drive system would be verified under the MATLAB/Simulink software environment. It is expected that with the proposed online learning Artificial Neural Network controller efficiency optimization algorithm can achieve better energy saving compared with traditional blended strategies.

scholarly journals A Cognitive Level Evaluation Method Based on a Deep Neural Network for Online Learning: From a Bloom’s Taxonomy of Cognition Objectives Perspective

2021 ◽  
Vol 12 ◽  
Author(s):  
Yan Cheng ◽  
Yingying Cai ◽  
Haomai Chen ◽  
Zhuang Cai ◽  
Gang Wu ◽  
...  
Keyword(s):  
Neural Network ◽  
Online Learning ◽  
Learning Strategies ◽  
Deep Neural Network ◽  
Evaluation Method ◽  
Bloom's Taxonomy ◽  
Automatic Evaluation ◽  
Cognitive Level ◽  
Text Data ◽  
Bloom’S Taxonomy

The evaluation of the learning process is an effective way to realize personalized online learning. Real-time evaluation of learners’ cognitive level during online learning helps to monitor learners’ cognitive state and adjust learning strategies to improve the quality of online learning. However, most of the existing cognitive level evaluation methods use manual coding or traditional machine learning methods, which are time-consuming and laborious. They cannot fully mine the implicit cognitive semantic information in unstructured text data, making the cognitive level evaluation inefficient. Therefore, this study proposed the bidirectional gated recurrent convolutional neural network combined with an attention mechanism (AM-BiGRU-CNN) deep neural network cognitive level evaluation method, and based on Bloom’s taxonomy of cognition objectives, taking the unstructured interactive text data released by 9167 learners in the massive open online course (MOOC) forum as an empirical study to support the method. The study found that the AM-BiGRU-CNN method has the best evaluation effect, with the overall accuracy of the evaluation of the six cognitive levels reaching 84.21%, of which the F1-Score at the creating level is 91.77%. The experimental results show that the deep neural network method can effectively identify the cognitive features implicit in the text and can be better applied to the automatic evaluation of the cognitive level of online learners. This study provides a technical reference for the evaluation of the cognitive level of the students in the online learning environment, and automatic evaluation in the realization of personalized learning strategies, teaching intervention, and resources recommended have higher application value.

Sign in / Sign up

Export Citation Format

Share Document