Artificial intelligence and wireless communications

Wang, Jun; Li, Rong; Wang, Jian; Ge, Yiqun; Zhang, Qi-fan; Shi, Wuxian

doi:10.1631/fitee.1900527

Cited by 16 publications

(6 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Generally speaking, source number estimation is a prerequisite for signal-related parameter estimation and has an important position in array signal processing. The earliest proposed method of source number estimation is the hypothesis testing method [ 2 ], which performs a characteristic decomposition of the received signal covariance matrix. Theoretically, the first few larger eigenvalues are equal in number to sources and correspond to the signal eigenvalues, while the remaining eigenvalues correspond to the noise eigenvalues, which are usually divided according to empirically set thresholds.…”

Section: Introductionmentioning

confidence: 99%

Research on Underdetermined DOA Estimation Method with Unknown Number of Sources Based on Improved CNN

Zhao

Zhou

et al. 2023

Sensors

View full text Add to dashboard Cite

This paper proposes a joint estimation method for source number and DOA based on an improved convolutional neural network for unknown source number and undetermined DOA estimation. By analyzing the signal model, the paper designs a convolutional neural network model based on the existence of a mapping relationship between the covariance matrix and both the source number and DOA estimation. The model, which discards the pooling layer to avoid data loss and introduces the dropout method to improve generalization, takes the signal covariance matrix as input and the two branches of source number estimation and DOA estimation as outputs, and achieves the unfixed number of DOA estimation by filling in invalid values. Simulation experiments and analysis of the results show that the algorithm can effectively achieve the joint estimation of source number and DOA. Under the conditions of high SNR and a large snapshot number, both the proposed algorithm and the traditional algorithm have high estimation accuracy, while under the conditions of low SNR and a small snapshot, the algorithm is better than the traditional algorithm, and under the underdetermined conditions, where the traditional algorithm often fails, the algorithm can still achieve the joint estimation.

show abstract

Section: Introductionmentioning

confidence: 99%

Research on Underdetermined DOA Estimation Method with Unknown Number of Sources Based on Improved CNN

Zhao

Zhou

et al. 2023

Sensors

View full text Add to dashboard Cite

show abstract

“…Digital signal processing (DSP) system is an important part of modern electronic systems [1]- [3]. Recently, with the rapid development of modern electronic systems such as communications [4] [5] and testing [6] [7], the requirement for DSP is also increased. For example, mobile communication system requires that the DSP system should have faster data transmission rate and better stability [8] [9].…”

Section: Introductionmentioning

confidence: 99%

Optimal design of digital FIR filters based on back propagation neural network

Yang

et al. 2023

IEICE Electron. Express

View full text Add to dashboard Cite

In the traditional digital finite impulse response (FIR) filter design, there exist some limitations. For instance, unwanted signals cannot be filtered out by using these FIR filters. Therefore, to break these limitations, this paper proposes an optimization method for designing digital FIR filters based on the back propagation neural network (BPNN) algorithm. Firstly, an amplitude response model has been established based on the linear properties of the digital FIR filters. Then, the BPNN algorithm has been used to minimize the estimation error between the ideal and the actual amplitude response such that the optimal coefficients of the digital FIR filter can be obtained. Finally, several design examples are used to verify the performance of our proposed optimal design based on BPNN. The simulation results show that, compared with the optimal designs based on the sequential and rectangular window, our proposed optimal design based on BPNN can achieve better filtering effectiveness but at the cost of larger computational complexity.

show abstract

“…At the same time, it was not necessary to specify a fixed set of lagged inputs [17][18][19]. LSTM could resolve the long-term dependency issue as it memorized the information for more extended periods, unlike some other linear time series forecast algorithms (such as ARIMA and its various extensions) that were affected by the unnecessary fluctuations occurring in the series [19][20][21][22]. This is then projected to all forecasted results.…”

Section: Introductionmentioning

confidence: 99%

Dynamic Learning Framework for Smooth-Aided Machine-Learning-Based Backbone Traffic Forecasts

Hamdi

Hamam

2022

Sensors

View full text Add to dashboard Cite

Recently, there has been an increasing need for new applications and services such as big data, blockchains, vehicle-to-everything (V2X), the Internet of things, 5G, and beyond. Therefore, to maintain quality of service (QoS), accurate network resource planning and forecasting are essential steps for resource allocation. This study proposes a reliable hybrid dynamic bandwidth slice forecasting framework that combines the long short-term memory (LSTM) neural network and local smoothing methods to improve the network forecasting model. Moreover, the proposed framework can dynamically react to all the changes occurring in the data series. Backbone traffic was used to validate the proposed method. As a result, the forecasting accuracy improved significantly with the proposed framework and with minimal data loss from the smoothing process. The results showed that the hybrid moving average LSTM (MLSTM) achieved the most remarkable improvement in the training and testing forecasts, with 28% and 24% for long-term evolution (LTE) time series and with 35% and 32% for the multiprotocol label switching (MPLS) time series, respectively, while robust locally weighted scatter plot smoothing and LSTM (RLWLSTM) achieved the most significant improvement for upstream traffic with 45%; moreover, the dynamic learning framework achieved improvement percentages that can reach up to 100%.

show abstract

Artificial intelligence and wireless communications

Cited by 16 publications

References 33 publications

Research on Underdetermined DOA Estimation Method with Unknown Number of Sources Based on Improved CNN

Research on Underdetermined DOA Estimation Method with Unknown Number of Sources Based on Improved CNN

Optimal design of digital FIR filters based on back propagation neural network

Dynamic Learning Framework for Smooth-Aided Machine-Learning-Based Backbone Traffic Forecasts

Contact Info

Product

Resources

About