Design of equiripple FIR filters using a feedback neural network

Bhattacharya, D.; Antoniou, A.

doi:10.1016/s0920-5489(99)90884-x

Cited by 8 publications

(19 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It requires 15 iterations to achieve convergence. It is clear that the proposed neural-based technique can implement the design of FIR Nyquist filters with good performance as compared to the previous neural-based method [23].…”

Section: Example 2 (Equiripple Design)mentioning

confidence: 87%

“…The proposed structure uses notably the same number of g neurons to implement the WLS design of FIR Nyquist filters. Comparing this to the methods presented by [22,23], the f neurons are replaced by the general blocks of multiplication and subtraction for the error function calculation. Therefore, the architecture of the proposed technique is much simpler and regular, and so it can reduce the computational complexity and hardware cost when implemented in real-time.…”

Section: Nyquist Filter Design Using Hopfield Neural Networkmentioning

confidence: 99%

“…Table 1 depicts the comparison of designed results with different algorithm. In such case, the previous neural-based method [23] does not result convergence problem and work well. It requires 15 iterations to achieve convergence.…”

Section: Example 2 (Equiripple Design)mentioning

confidence: 99%

“…Recently, neural networks [21][22][23] have been used for FIR filter design. Bhattacharya and Antoniou [22,23] introduced the design of FIR filters in real-time using feedback neural networks.…”

Section: Introductionmentioning

confidence: 99%

“…Bhattacharya and Antoniou [22,23] introduced the design of FIR filters in real-time using feedback neural networks. The disadvantage of this algorithm is the number of neurons required for the network is proportional to the sampling grid of frequency.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

WLS design of FIR Nyquist filter based on neural networks

Jou

Chen

2011

Digital Signal Processing

View full text Add to dashboard Cite

Section: Example 2 (Equiripple Design)mentioning

confidence: 87%

Section: Nyquist Filter Design Using Hopfield Neural Networkmentioning

confidence: 99%

Section: Example 2 (Equiripple Design)mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

WLS design of FIR Nyquist filter based on neural networks

Jou

Chen

2011

Digital Signal Processing

View full text Add to dashboard Cite

Neural network‐based design of 2‐channel quadrature mirror filter banks

Jou

Lin

Chen

2018

Circuit Theory & Apps

View full text Add to dashboard Cite

Two-channel quadrature mirror filter banks can be efficiently established by the combination of real-valued infinite impulse response all-pass filters without incurring aliasing and magnitude distortions. The design problem of filter banks is therefore to seek for the phase error minimization of the all-pass filter coefficients. In this paper, a neural network-based Lyapunov energy function is used to relate to the objective function of the designed all-pass filter coefficients. Based on the architecture of neural networks and suitable selection of Hopfield-related parameters, the all-pass filter coefficients are obtained when the networks reach convergence. By further using the suitable combination of the designed all-pass filters, the 2-channel quadrature mirror filter banks with perfect reconstruction can be efficiently accomplished. Simulation results indicate that the neural network-based approach has the advantage of satisfactory performance in magnitude and group delay responses in a parallelism manner.KEYWORDS all-pass filters, infinite impulse response, Lyapunov energy function, neural networks, quadrature mirror filter

show abstract