Abstract
Deep neural network (DNN), being an important member of machine learning family, has been employed to serve a wide range of applications in the area of signal and image processing like pattern recognition, speech recognition, language processing, image segmentation, etc. To this aim, this paper concentrates on the design of a narrow transition-band finite impulse response (FIR) filter with the aid of back-propagation-based deep learning approach. The proposed deep learning-based approach offers a unified design framework for a variety of FIR filters. Convergence behaviour of the proposed algorithm has been proved analytically in situations when weights between adjacent layers are updated continuously. Simulation results have shown the frequency response characteristics of several FIR filters with narrow transition-band, designed with the help of proposed approach. Advantage of our design strategy has also been established in terms of magnitude response over a number of state-of-the-art techniques of recent interest. Simulation results have shown noticeable improvement in terms of transition bandwidth when compared with few existing works. Designed filter is subsequently implemented on Altera’s Cyclone IV field programmable gate array (FPGA) chip, and hardware efficiency of the suggested design has strongly been established by correlating its hardware cost with many of the state-of-the-art FIR filters.
Similar content being viewed by others
References
Awad AM, Adaptive window method of fir filter design, in 2010 IEEE Conference on Open Systems (ICOS 2010), (2010), pp. 57–62. https://doi.org/10.1109/ICOS.2010.5720064
J.W. Adams, J.L. Sullivan, Peak-constrained least-squares optimization. IEEE Trans. Signal Process. 46(2), 306–321 (1998)
D.A. Alwahab, D.R. Zaghar, S. Laki, Fir filter design based neural network, in 2018 11th International Symposium on Communication Systems, Networks & Digital Signal Processing (CSNDSP). (IEEE, 2018), pp. 1–4
Anshul Rathi, K., Comparison of various window techniques for design fir digital filter, in 2017 IEEE International Conference on Power, Control, Signals and Instrumentation Engineering (ICPCSI), (2017), pp. 428–432. https://doi.org/10.1109/ICPCSI.2017.8392331
K. Ben, P. Van der Smagt, An introduction to neural networks (University of Amsterdam, Amsterdam, 1996)
A. Chandra, A. Kumar, S. Roy, Design of fir filter isota with the aid of genetic algorithm. Integration 79, 107–115 (2021)
W. Chen, M. Huang, X. Lou, Sparse fir filter design based on interpolation technique, in 2018 IEEE 23rd International Conference on Digital Signal Processing (DSP). (IEEE, 2018), pp. 1–5
S. Dhabu, A.P. Vinod, Design and fpga implementation of reconfigurable linear-phase digital filter with wide cutoff frequency range and narrow transition bandwidth. IEEE Trans. Circuits Syst. 63(2), 181–185 (2016)
A.K. Dwivedi, S. Ghosh, N.D. Londhe, Modified artificial bee colony optimisation based fir filter design with experimental validation using field-programmable gate array. IET Signal Process. 10(8), 955–964 (2016)
A.K. Dwivedi, S. Ghosh, N.D. Londhe, Review and analysis of evolutionary optimization-based techniques for fir filter design. Circuits, Syst., Signal Process. 37(10), 4409–4430 (2018)
A.A. Eleti, A.R. Zerek, Fir digital filter design by using windows method with matlab, in 14th International Conference on Sciences and Techniques of Automatic Control Computer Engineering - STA’2013. (2013), pp. 282–287. https://doi.org/10.1109/STA.2013.6783144
A. Ghosh, S. Roy, A. Chandra, Prefilter-equalizer based structure: A new design strategy for narrow-band fir filters, in 2018 IEEE Applied Signal Processing Conference (ASPCON). (IEEE, 2018), pp. 229–233
A.L. Goldberger, L.A.N. Amaral, L. Glass, J.M. Hausdorff, P.C. Ivanov, R.G. Mark, J.E. Mietus, G.B. Moody, C.K. Peng, H.E. Stanley, PhysioBank, PhysioToolkit, and PhysioNet: Components of a new research resource for complex physiologic signals. Circulation 101(23), e215–e220 (2000 (June 13)). Circulation Electronic Pages: http://circ.ahajournals.org/content/101/23/e215.full PMID:1085218; https://doi.org/10.1161/01.CIR.101.23.e215
N. Haridas, E. Elias, Reconfigurable farrow structure-based frm filters for wireless communication systems. Circuits, Syst., Signal Process. 36(1), 315–338 (2017)
N. Haridas, E. Elias, Reconfigurable farrow structure-based frm filters for wireless communication systems. Circuits, Syst., Signal Process. 36(1), 315–338 (2017). https://doi.org/10.1007/s00034-016-0309-4
A. Jiang, H.K. Kwan, Y. Tang, Y. Zhu, Efficient design of sparse fir filters with optimized filter length, in 2014 IEEE International Symposium on Circuits and Systems (ISCAS). (IEEE, 2014), pp. 966–969
A. Jiang, H.K. Kwan, Y. Zhu, X. Liu, N. Xu, X. Yao, Peak-error-constrained sparse fir filter design using iterative l 1 optimization, in 2016 24th European Signal Processing Conference (EUSIPCO). (IEEE, 2016), pp. 180–184
W. Jiang, P. Liu, F. Wen, An improved vector quantization method using deep neural network. AEU-Int. J. Electron. Commun. 72, 178–183 (2017)
Y.D. Jou, Design of real fir filters with arbitrary magnitude and phase specifications using a neural-based approach. IEEE Trans. Circuits Syst. II: Expr. Briefs 53(10), 1068–1072 (2006)
Y.D. Jou, F.K. Chen, On the use of lyapunov functions for the design of complex fir digital filters, in Circuits and Systems, 2006. APCCAS 2006. IEEE Asia Pacific Conference on. (IEEE, 2006), pp. 740–743
Y.D. Jou, F.K. Chen, Least-squares design of fir filters based on a compacted feedback neural network. IEEE Trans. Circuits Syst. II: Expr. Briefs 54(5), 427–431 (2007)
J. Ke, X. Liu, Empirical analysis of optimal hidden neurons in neural network modeling for stock prediction, in 2008 IEEE Pacific-Asia Workshop on Computational Intelligence and Industrial Application, vol. 2. (2008), pp. 828–832. https://doi.org/10.1109/PACIIA.2008.363
A. Konar, Computational intelligence: principles, techniques and applications (Springer Science & Business Media, New York, 2006)
W. Lee, V. Rehbock, K.L. Teo, L. Caccetta, A weighted least-square-based approach to fir filter design using the frequency-response masking technique. IEEE Signal Process. Lett. 11(7), 593–596 (2004)
W.R. Lee, L. Caccetta, K.L. Teo, V. Rehbock, A weighted least squares approach to the design of fir filters synthesized using the modified frequency response masking structure. IEEE Trans. Circuits Syst. II: Expr. Briefs 53(5), 379–383 (2006)
Y.C. Lim, Y. Lian, The optimum design of one-and two-dimensional fir filters using the frequency response masking technique. IEEE Trans. Circuits Syst. II: Analog Digital Signal Process. 40(2), 88–95 (1993)
W.S. Lu, T. Hinamoto, Optimal design of frequency-response-masking filters using semidefinite programming. IEEE Trans. Circuits Syst. I: Fundamental Theory Appl. 50(4), 557–568 (2003)
W.S. Lu, T. Hinamoto, A unified approach to the design of interpolated and frequency-response-masking fir filters. IEEE Trans. Circuits Syst. I: Regular Papers 63(12), 2257–2266 (2016)
T. Ma, Y. Wei, X. Ma, A new method for designing farrow filters based on cosine basis neural network, in Digital Signal Processing (DSP), 2016 IEEE International Conference on. (IEEE, 2016), pp. 154–158
S. Mitra, S. Mitra, Digital Signal Processing: A Computer-based Approach. Connect, learn, succeed. (McGraw-Hill, 2011). URL https://books.google.co.in/books?id=QyuNQgAACAAJ
G. Montavon, W. Samek, K.R. Müller, Methods for interpreting and understanding deep neural networks. Digital Signal Processing (2017)
Z. Naghibi, S.A. Sadrossadat, S. Safari, Time-domain modeling of nonlinear circuits using deep recurrent neural network technique. AEU-Int. J. Electron. Commun. 35, 125 (2018)
K. Pachori, A. Mishra, Design of fir digital filters using adaline neural network, in Computational Intelligence and Communication Networks (CICN), 2012 Fourth International Conference on. (IEEE, 2012), pp. 800–803
K. Rana, V. Kumar, S.S. Nair, Efficient fir filter designs using constrained genetic algorithms based optimization, in Communication Control and Intelligent Systems (CCIS), 2016 2nd International Conference on. (IEEE, 2016), pp. 131–135
J. Rodrigues, K. Pai, New approach to the synthesis of sharp transition fir digital filter, in Proceedings of the IEEE International Symposium on Industrial Electronics, 2005. ISIE 2005., vol. 3. (IEEE, 2005), pp. 1171–1173
S. Roy, A. Chandra, A new design strategy of sharp cut-off fir filter with powers-of-two coefficients, in 2018 International Conference on Wireless Communications, Signal Processing and Networking (WiSPNET). (2018), pp. 1–6. https://doi.org/10.1109/WiSPNET.2018.8538605
S. Roy, A. Chandra, Design of narrow transition band digital filter: An analytical approach. Integration 68, 38–49 (2019). https://doi.org/10.1016/j.vlsi.2019.06.002. URL http://www.sciencedirect.com/science/article/pii/S0167926019300707
S. Roy, A. Chandra, Interpolated band-pass method based narrow-band fir filter: A prospective candidate in filtered-ofdm technique for the 5g cellular network, in TENCON 2019-2019 IEEE Region 10 Conference (TENCON). (IEEE, 2019), pp. 311–315
S. Roy, A. Chandra, On the order minimization of interpolated bandpass method based narrow transition band fir filter design. IEEE Trans. Circuits Syst. I: Regular Papers 66(11), 4287–4295 (2019). https://doi.org/10.1109/TCSI.2019.2928052
S. Roy, A. Chandra, A study on the optimum selection of interpolation factor for the design of narrow transition band fir filter using ibm, in International Conference on Computers and Devices for Communication. (Springer, 2019), pp. 465–475
S. Roy, A. Chandra, Design of narrow transition band variable bandwidth digital filter. IET Circuits, Devices Syst. 14(6), 750–757 (2020)
S. Roy, A. Chandra, A survey of fir filter design techniques: low-complexity, narrow transition-band and variable bandwidth. Integration 77, 193–204 (2021)
T.K. Roy, M. Morshed, Performance analysis of low pass fir filters design using kaiser, gaussian and tukey window function methods, in 2013 2nd International Conference on Advances in Electrical Engineering (ICAEE). (2013), pp. 1–6. https://doi.org/10.1109/ICAEE.2013.6750294
T. Saramaki, T. Neuvo, S.K. Mitra, Design of computationally efficient interpolated fir filters. IEEE Trans. Circuits Syst. 35(1), 70–88 (1988)
K.G. Sheela, S.N. Deepa, Review on methods to fix number of hidden neurons in neural networks. Math. Probl. Eng. 20, 453 (2013)
P. Vaidyanathan, Optimal design of linear phase fir digital filters with very flat passbands and equiripple stopbands. IEEE Trans. Circuits Syst. 32(9), 904–917 (1985)
X. Wang, Y. He, Y. Peng, J. Xiong, A neural networks approach for designing fir notch filters, in Signal Processing, 2006 8th International Conference on, vol. 1. (IEEE, 2006)
X. Wang, X. Meng, Y. He, A novel neural networks-based approach for designing fir filters, in Intelligent Control and Automation, 2006. WCICA 2006. The Sixth World Congress on, vol. 1. (IEEE, 2006), pp. 4029–4032
X.H. Wang, Y.G. He, A neural network approach to fir filter design using frequency-response masking technique. Signal Process. 88(12), 2917–2926 (2008)
X.H. Wang, Y.G. He, T.Z. Li, Neural network algorithm for designing fir filters utilizing frequency-response masking technique. J. Computer Sci. Technol. 24(3), 463–471 (2009)
Y. Wei, S. Huang, X. Ma, A novel approach to design low-cost two-stage frequency-response masking filters. IEEE Trans. Circuits Syst. II: Expr. Briefs 62(10), 982–986 (2015)
Y. Wei, D. Liu, Improved design of frequency-response masking filters using band-edge shaping filter with non-periodical frequency response. IEEE Trans. Signal Process. 61(13), 3269–3278 (2013)
T. Xue, Design of fir digital filter based on improved neural network, in 2021 International Symposium on Computer Technology and Information Science (ISCTIS). (IEEE, 2021), pp. 406–410
Z. Zeng, Y. Zhang, Y. Wang, Optimal design of the high order fir multi-band-stop filters, in Intelligent Control and Automation, 2006. WCICA 2006. The Sixth World Congress on, vol. 1. (IEEE), pp. 4279–4283
Z.Z. Zeng, Y. Chen, Y.N. Wang, Optimal design study of high-order fir digital filters based on neural-network algorithm, in 2006 International Conference on Machine Learning and Cybernetics. (IEEE, 2006), pp. 3157–3161
A.X. Zhao, X.J. Tang, Z.H. Zhang, J.H. Liu, The optimal design method of fir filter using the improved genetic algorithm, in Industrial Electronics and Applications (ICIEA), 2014 IEEE 9th Conference on. (IEEE, 2014), pp. 452–455
Z. Zhe-zhao, W. Hui, Optimal design study of three-type fir high-order digital filters based on sine basis functions neural-network algorithm, in Communications and Information Technology, 2005. ISCIT 2005. IEEE International Symposium on, vol. 2. (IEEE, 2005), pp. 921–924
Funding
This research work is funded by Science and Engineering Research Board (SERB), Department of Science and Technology, Govt. of India, vide sanction order no. ECR/2017/000440.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have no conflicts of interest/competing interests.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Appendices
Appendix A
Define a Lyapunov function:
According to Eqs. (27) and (28), we can write
In order to let the algorithm be convergent, \(\varDelta V_{k}<0\) (i.e. \(\delta _{r}^2(H_{q})^2>0\)). Therefore, we have
As, learning rate \(\eta _{1}~>0\), therefore we have
When \(\eta _{1}\) satisfies Eq. (31), \(\varDelta V_{k}<0\), the proposed deep neural network is stable and the given algorithm is convergent to its global minimum; hence, the theorem is proved completely.
Appendix B
Define a Lyapunov function:
According to Eqs. (32) and (33), we can write
In order to let the algorithm be convergent, \(\varDelta V_{k}<0\) (i.e. \(H_{p}^2\sum _{\forall i \in \mathscr {Q}}\delta _{i}^2W_{ir}^2(H_{i}(1-H_{i}))^2>0\)). Therefore, we have
As, learning rate \(\eta _{2}~>0\), therefore we get
When \(\eta _{2}\) satisfies Eq. (36), \(\varDelta V_{k}<0\), the proposed deep neural network is stable and the algorithm converges towards its global minimum.
Appendix C
Define a Lyapunov function:
According to Eqs. (37) and (38), we can write
In order to let the algorithm be convergent, \(\varDelta V_{k}<0\) (i.e. \(H_{n}^2\sum _{\forall i \in \mathscr {Q}}\delta _{i}^2W_{ir}^2(H_{i}(1-H_{i}))^2\sum _{\forall j \in \mathscr {P}}W_{jq}^2(H_{j}(1-H_{j}))^2>0\)). Therefore, we get
As, learning rate \(\eta _{3}~>0\), therefore we get
When \(\eta _{3}\) satisfies Eq. (41), \(\varDelta V_{k}<0\), the proposed deep neural network is stable and the algorithm is convergent to its global minimum.
Rights and permissions
About this article
Cite this article
Roy, S., Chandra, A. A Deep Learning Approach for the Design of Narrow Transition-Band FIR Filter. Circuits Syst Signal Process 41, 5578–5613 (2022). https://doi.org/10.1007/s00034-022-02036-0
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00034-022-02036-0