nach oben

The Journal of Supercomputing

Erschienen in:

22.01.2023

Cycle sampling neural network algorithms and applications

verfasst von: Gang Cai, Lingyan Wu

Erschienen in: The Journal of Supercomputing | Ausgabe 9/2023

Einloggen

Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.

search-config

KI-gestützte Suche

Aus

Abstract

Two improved sampling neural network (SNN) algorithms, Cycle SNN (CSNN) and Rolling-Cycle SNN (RSNN), are proposed and optimized in this study, to improve the accuracy of basic SNN (BSNN). Experiments show that the improved algorithms achieve significant improvements in both accuracy and training efficiency. This study also perfects the SNN theoretical system and unifies the vector form of these SNN algorithms. Based on the theoretical analysis, this can be achieved by effectively reducing the high-frequency component and aliasing distortion through cycle extension and rolling. These efforts have made useful contributions to explore the potential and prospects of SNN applications. The SNN networks with a new structure and SNN error diffusion (SNN-ED) convergence method provide a new idea for the development of neural networks.

Vorheriger Artikel Implementation of a motion estimation algorithm for Intel FPGAs using OpenCL

Nächster Artikel Parallel border tracking in binary images for multicore computers

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

über 67.000 Bücher
über 340 Zeitschriften

aus folgenden Fachgebieten:

Bauwesen + Immobilien
Business IT + Informatik
Finance + Banking
Management + Führung
Marketing + Vertrieb
Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Jetzt informieren

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

über 67.000 Bücher
über 390 Zeitschriften

aus folgenden Fachgebieten:

Automobil + Motoren
Bauwesen + Immobilien
Business IT + Informatik
Elektrotechnik + Elektronik
Energie + Nachhaltigkeit
Maschinenbau + Werkstoffe

Jetzt Wissensvorsprung sichern!

Jetzt informieren

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

über 102.000 Bücher
über 537 Zeitschriften

aus folgenden Fachgebieten:

Automobil + Motoren
Bauwesen + Immobilien
Business IT + Informatik
Elektrotechnik + Elektronik
Energie + Nachhaltigkeit
Finance + Banking
Management + Führung
Marketing + Vertrieb
Maschinenbau + Werkstoffe
Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Jetzt informieren

Sani S, Shermeh HE (2022) A novel algorithm for detection of COVID-19 by analysis of chest CT images using Hopfield neural network. Expert Syst Appl 197:116740. https://doi.org/10.1016/j.eswa.2022.116740CrossRef

Bilal DK, Unel M, Tunc LT et al (2022) Development of a vision based pose estimation system for robotic machining and improving its accuracy using LSTM neural networks and sparse regression. Robot Computer-Integrated Manufact 74:456. https://doi.org/10.1016/j.rcim.2021.102262CrossRef

Emami SA, Castaldi P, Banazadeh A (2022) Neural network-based flight control systems: present and future. Annu Rev Control 53:97–137. https://doi.org/10.1016/j.arcontrol.2022.04.006CrossRefMathSciNet

Larestani A, Mousavi SP, Hadavimoghaddam F et al (2022) Predicting the surfactant-polymer flooding performance in chemical enhanced oil recovery: cascade neural network and gradient boosting decision tree. Alex Eng J 61:7715–7731. https://doi.org/10.1016/j.aej.2022.01.023CrossRef

Zhang L, Zhu L, Hua C et al (2021) Adaptive neural network control for a class of interconnected pure-feedback time-delay nonlinear systems with full-state constraints and unknown measurement sensitivities. Neurocomputing 461:147–161. https://doi.org/10.1016/j.neucom.2021.07.043CrossRef

Yang F, Zhang H, Tao S (2021) Travel order quantity prediction via attention-based bidirectional LSTM networks. J Supercomput 78:4398–4420. https://doi.org/10.1007/s11227-021-04032-8CrossRef

Cai G, Wu L, Li M (2021) The circuit fault diagnosis method based on spectrum analyses and ELM. In: 2021 IEEE 16th Conference on Industrial Electronics and Applications (ICIEA), pp 475–479

Rumelhart DE, Hinton GE, Williams RJ (1986) Learning representations by back-propagating errors. Nature 323:533–536CrossRefMATH

Zhang R, Huang G-B, Sundararajan N et al (2007) Improved GAP-RBF network for classification problems. Neurocomputing 70:3011–3018. https://doi.org/10.1016/j.neucom.2006.07.016CrossRef

10.

Zhou Y, Li C, Wang H (2018) Stability analysis on state-dependent impulsive Hopfield neural networks via fixed-time impulsive comparison system method. Neurocomputing 316:20–29. https://doi.org/10.1016/j.neucom.2018.07.047CrossRef

11.

Huang G-B, Wang D (2011) Advances in extreme learning machines (ELM2010). Neurocomputing 74:2411–2412. https://doi.org/10.1016/j.neucom.2011.03.030CrossRef

12.

Chi Z, Yuan G, Ming L (2021) A review of development and application of artificial neural network models. Comput Eng Appl 56:1–15. https://doi.org/10.3778/j.issn.1002-8331.2102-0256CrossRef

13.

Li X, Wang L, Sung E (2008) AdaBoost with SVM-based component classifiers. Eng Appl Artif Intell 21:785–795. https://doi.org/10.1016/j.engappai.2007.07.001CrossRef

14.

Huang GB, Zhou H, Ding X et al (2012) Extreme learning machine for regression and multiclass classification. IEEE Trans Syst Man Cybern B Cybern 42:513–529. https://doi.org/10.1109/TSMCB.2011.2168604CrossRef

15.

Rathod N, Wankhade S (2022) Optimizing neural network based on cuckoo search and invasive weed optimization using extreme learning machine approach. Neuroscience Informatics. https://doi.org/10.1016/j.neuri.2022.100075CrossRef

16.

Rong H-J, Ong Y-S, Tan A-H et al (2008) A fast pruned-extreme learning machine for classification problem. Neurocomputing 72:359–366. https://doi.org/10.1016/j.neucom.2008.01.005CrossRef

17.

Chen Z, Yang C, Qiao J (2021) The optimal design and application of LSTM neural network based on the hybrid coding PSO algorithm. J Supercomput 78:7227–7259. https://doi.org/10.1007/s11227-021-04142-3CrossRef

18.

Lindemann B, Maschler B, Sahlab N et al (2021) A survey on anomaly detection for technical systems using LSTM networks. Comput Industry 131:103498. https://doi.org/10.1016/j.compind.2021.103498CrossRef

19.

Etxegarai G, López A, Aginako N et al (2022) An analysis of different deep learning neural networks for intra-hour solar irradiation forecasting to compute solar photovoltaic generators’ energy production. Energy Sustain Dev 68:1–17. https://doi.org/10.1016/j.esd.2022.02.002CrossRef

20.

Wambugu N, Chen Y, Xiao Z et al (2021) Hyperspectral image classification on insufficient-sample and feature learning using deep neural networks: a review. Int J Appl Earth Observ Geoinform 105:102603. https://doi.org/10.1016/j.jag.2021.102603CrossRef

21.

Hadsell R, Rao D, Rusu AA et al (2020) Embracing change: continual learning in deep neural networks. Trends Cogn Sci 24:1028–1040. https://doi.org/10.1016/j.tics.2020.09.004CrossRef

22.

Bouwmans T, Javed S, Sultana M et al (2019) Deep neural network concepts for background subtraction: a systematic review and comparative evaluation. Neural Netw 117:8–66. https://doi.org/10.1016/j.neunet.2019.04.024CrossRef

23.

Habib G, Qureshi S (2020) Optimization and acceleration of convolutional neural networks: a survey. J King Saud Univ Comput Inform Sci. https://doi.org/10.1016/j.jksuci.2020.10.004CrossRef

24.

Wang H, Wang Y, Wang X et al (2022) A novel deep-learning model for RDTS signal denoising based on down-sampling and convolutional neural network. J Lightwave Technol 40:3647–3653. https://doi.org/10.1109/jlt.2022.3149400CrossRef

25.

Liu X, Qi D-Y, Li W-L et al (2021) Exploring the Internet of Things sequence-structure detection and supertask network generation of temporal-spatial-based graph convolutional neural network. J Supercomput 78:5029–5049. https://doi.org/10.1007/s11227-021-04041-7CrossRef

26.

Cai G, Wu L (2021) Sampling neural network: a novel neural network based on sampling theorem. In: 2021 6th International Symposium on Computer and Information Processing Technology (ISCIPT). p 717–720.

27.

Shannon CE (1949) Communication in the presence of noise. Proc IRE 37:10–21CrossRefMathSciNet

28.

Huo H, Sun W (2015) Average sampling theorem. Sci Sinica Math 45:1403–1422. https://doi.org/10.1360/n012015-00026CrossRefMATH

29.

Zhang J, Wang G, Wang H (2017) Improvement of wind-induced vibration analysis in time domain based on Shannon sampling theorem. Noise Vib Control 3:131–136. https://doi.org/10.3969/j.issn.1006-1355.2017.02.027CrossRef

30.

JL Zheng, W.L.Y., Y. Ying Q, 2009 Introduction to signals and systems. Higher Education Press, Beijing

31.

Av O, As W, Sh N (2015) Signals and systems(Second Edition). Publishing House of Electronics Industry, Beijing

32.

Cheng PQ (2013) Digital signal processing tutorial. Tsinghua University Press, Beijing

33.

Luo X, Zhang Z (2021) Data recovery with sub-Nyquist sampling: fundamental limit and a detection algorithm. Front Inform Technol Electron Eng 22:232–243. https://doi.org/10.1631/fitee.1900320CrossRef

34.

Butzer PL, Engels W, Scheben U (1982) Magnitude of the truncation error in sampling expansions of bandlimited signals. IEEE Trans Acoust Speech Signal Process 30:906–912CrossRefMATH

35.

Jagerman D (1966) Bounds for truncation error of the sampling expansion. SIAM J Appl Math 14:714–723CrossRefMATHMathSciNet

36.

Fj B (1976) On the truncation error of the cardinal sampling expansion. IEEE Trans Inform Theory 22(5):568–73CrossRefMathSciNet

37.

Cambanis S, Masry E (1982) Truncation error bounds for the cardinal sampling expansion of bandlimited signals. IEEE Trans Inform Theory 28:605–612CrossRefMATHMathSciNet

38.

Y Hu (2008) Truncation error bounds for the cardinal sampling expansion of bandlimited signals. J Graduate School Chin Acad Sci 25:460–466

39.

Erling G, Zhiqiang S, Yadong L (2015) From the Fourier transform of non-periodic signals to the Fourier series of periodic signals. J Electric Electron Educ 37:42–44

40.

Zhou K, Kang Y (2005) Neural network model and its MATLAB simulation program design. Tsinghua University Press, Beijing

41.

Zhang D (2010) MATLAB numerical calculation method. China Machine Press, Beijing

42.

Suykens JAK, Gestel TV, Brabanter JD et al. Least squares support vector machines https://www.esat.kuleuven.be/stadius/lssvmlab/toolbox.html.

43.

Huang GB Extreme learning machine https://www.ntu.edu.sg/eee/icis/cv/egbhuang.html.

44.

Huang G, Zhu Q, Siew C (2004) Extreme learning machine: a new learning scheme of feedforward neural networks. In: Proceedings of 2004 IEEE International Joint Conference on Neural Networks. Budapest, pp 985–990

45.

Anonymous NTC thermo-sensitive semiconductor resistors of Sinochip Electronics CO. LTD http://www.sinochip.net/list/?107_1.html.

Titel: Cycle sampling neural network algorithms and applications
verfasst von: Gang Cai
Lingyan Wu
Publikationsdatum: 22.01.2023
Verlag: Springer US
Erschienen in: The Journal of Supercomputing / Ausgabe 9/2023
Print ISSN: 0920-8542
Elektronische ISSN: 1573-0484
DOI: https://doi.org/10.1007/s11227-022-05019-9

Springer Professional

Abstract

Bitte loggen Sie sich ein, um Zugang zu Ihrer Lizenz zu erhalten.

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft"

Springer Professional "Technik"

Springer Professional "Wirtschaft+Technik"

Weitere Artikel der Ausgabe 9/2023

PAARes: an efficient process allocation based on the available resources of cluster nodes

LSTM-SN: complex text classifying with LSTM fusion social network

A machine learning model for improving virtual machine migration in cloud computing

Kemeny ranking aggregation meets the GPU

TDMBBO: a novel three-dimensional migration model of biogeography-based optimization (case study: facility planning and benchmark problems)

A proposed cloud‑based platform for facilitating donation services in support to needy-students

Premium Partner