Top

Neural Processing Letters

Published in:

22-07-2021

Study on Neural Network Integration Method Based on Morphological Associative Memory Framework

Authors: Naiqin Feng, Xiuqin Geng, Bin Sun

Published in: Neural Processing Letters | Issue 6/2021

Activate our intelligent search to find suitable subject content or patents.

search-config

AI-assisted search

Off

Abstract

In traditional neural network integration, people adopt Boosting, Bagging and other methods to integrate traditional neural networks. The integration is complex, time-consuming and laborious, difficult to popularize and apply. This paper is not a continuation of this method, but another integration which is called by us morphological neural network integration (MNNI) or morphological associative memory integration (MAMI). These networks used in MAMI are a network family, with 10 family members, unified in the morphological associative memory framework. Various morphological associative memory networks can be directly used as individual networks to learn and work separately, and then synthesize to draw conclusions. The results of some experiments show that this method is not only feasible in theory, but also effective in practice. It can avoid the complexity of traditional integration method, make the integration structure simple and clear, easy to operate, save time, and therefore is a method of neural network integration with research and application value. The contribution of this paper lies in that: (1) it proposed the concept and method of MNNI and, (2) verified the effectiveness of MNNI through experiments and, (3) it has the characteristics of simplicity, saving time and labor and cost, with a good application prospect and, (4) thus promoting the development of morphological neural networks in theory and practice.

previous article Correlation Projection for Analytic Learning of a Classification Network

next article New Results on Global Exponential Stability of Genetic Regulatory Networks with Diffusion Effect and Time-Varying Hybrid Delays

Dont have a licence yet? Then find out more about our products and how to get one now:

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!

inform now

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!

inform now

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!

inform now

Hansen LK, Salamon P (1990) Neural network ensembles. IEEE Trans Pattern Anal Mach Intell 12(10):993–1001. https://doi.org/10.1109/34.58871CrossRef

Zhou ZH, Chen SF (2002) Neural network ensemble. Chin J Comput 25(1):1–8. https://doi.org/10.3321/j.issn:0254-4164.2002.01.001 (in Chinese with abstract in English)MathSciNetCrossRef

Zhou ZH, Wu JX, Wei T (2002) Ensembling neural networks: many could be better than all. Artif Intell 137:239–267. https://doi.org/10.1016/S0004-3702(02)00190-XMathSciNetCrossRefMATH

Yu HL, Liu DY, Chen GF (2010) A neural network ensemble method for precision fertilization modeling. Math Comput Model 51:1375–1382. https://doi.org/10.1016/j.mcm.2009.10.028CrossRef

Bologna G (2004) Is it worth generating rules from neural network ensembles? J Appl Log 2:325–348. https://doi.org/10.1016/j.jal.2004.03.004MathSciNetCrossRefMATH

Oyewole SA, Olugbara OO (2018) Product image classification using Eigen color feature with ensemble machine learning. Egypt Inform J 19:83–100. https://doi.org/10.1016/j.eij.2017.10.002CrossRef

Cárdenas-Gallo I, Sarmiento CA, Morales GA et al (2017) An ensemble classifier to predict track geometry degradation. Reliab Eng Syst Saf 161:53–60. https://doi.org/10.1016/j.ress.2016.12.012CrossRef

Li H, Wang XS, Ding SF (2016) Research of multi-sided multi-granular neural network ensemble optimization method. Neurocomputing 197:78–85. https://doi.org/10.1016/j.neucom.2016.02.013CrossRef

González M, Dominguez D, Sánchez Á et al (2017) Increase attractor capacity using an ensembled neural network. Expert Syst Appl 71:206–215. https://doi.org/10.1016/j.eswa.2016.11.035CrossRef

10.

Zhao ZS, Feng X, Lin YY et al (2015) Evolved neural network ensemble by multiple heterogeneous swarm intelligence. Neurocomputing 49:29–38. https://doi.org/10.1016/j.neucom.2013.12.062CrossRef

11.

Yin XC, Huang K, Yang C, Hao HW (2014) Convex ensemble learning with sparsity and diversity. Inf Fusion 20(1):49–59. https://doi.org/10.1016/j.inffus.2013.11.003CrossRef

12.

Yang J, Zeng X, Zhong S, Wu S (2013) Effective neural network ensemble approach for improving generalization performance. IEEE Trans Neural Net Learn Syst 24(6):878–887. https://doi.org/10.1109/TNNLS.2013.2246578CrossRef

13.

Li H, Wang X, Ding S (2018) Research and development of neural network ensembles: a survey. Artif Intell Rev 49:455–479. https://doi.org/10.1007/s10462-016-9535-1CrossRef

14.

Mohamad M, Makhtar M, Rahman MNA (2017) The reconstructed heterogeneity to enhance ensemble neural network for large data. In: Herawan T, Ghazali R, Nawi N, Deris M (eds) Recent advances on soft computing and data mining. SCDM 2016. Advances in intelligent systems and computing, vol 549. Springer, Cham, pp 447–455. https://doi.org/10.1007/978-3-319-51281-5_45CrossRef

15.

Nanni L, Ghidoni S, Brahnam S (2018) Ensemble of convolutional neural networks for bioimage classification. Appl Comput Inform. https://doi.org/10.1016/j.aci.2018.06.002 ((In Press))CrossRef

16.

Chen YT, Chang HB, Meng J, Zhang DX (2019) Ensemble Neural Networks (ENN): a stochastic method. Neural Netw 110:170–185. https://doi.org/10.1016/j.neunet.2018.11.009CrossRef

17.

Kumar I, Bhadauria HS, Jitendra V, Shruti T (2017) A classification framework for prediction of breast density using an ensemble of neural network classifiers. Biocybern Biomed Eng 37:217–228. https://doi.org/10.1016/j.bbe.2017.01.001CrossRef

18.

Wang R, Li W, Zhang L (2019) Blur image identification with ensemble convolution neural networks. Signal Process 155:73–82. https://doi.org/10.1016/j.sigpro.2018.09.027CrossRef

19.

Asakura T, Date Y, Kikuchi J (2018) Application of ensemble deep neural network to metabolomics studies. Anal Chim Acta 1037:230–236. https://doi.org/10.1016/j.aca.2018.02.045CrossRef

20.

Zhang L, Yu GX, Xia DW, Wang J (2019) Protein–protein interactions prediction based on ensemble deep neural networks. Neurocomputing 324:10–19. https://doi.org/10.1016/j.neucom.2018.02.097CrossRef

21.

Kaveh K, Bui MD, Rutschmann P (2019) Integration of artificial neural networks into TELEMAC-MASCARET system, new concepts for hydromorphodynamic modeling. Adv Eng Softw 132:18–28. https://doi.org/10.1016/j.advengsoft.2019.03.011CrossRef

22.

Geng ZQ, Shang DR, Han YM, Zhong YH (2019) Early warning modeling and analysis based on a deep radial basis function neural network integrating an analytic hierarchy process: a case study for food safety. Food Control 96:329–342. https://doi.org/10.1016/j.foodcont.2018.09.027CrossRef

23.

Ge L, Ge LJ, Hu J (2019) Feature extraction and classification of hand movements surface electromyogram signals based on multi-method integration. Neural Process Lett 49(3):1179–1188. https://doi.org/10.1007/s11063-018-9862-0CrossRef

24.

Li J, Yu ZL, Gu Z et al (2019) MMAN: multi-modality aggregation network for brain segmentation from MR images. Neurocomputing 358:10–19. https://doi.org/10.1016/j.neucom.2019.05.025?CrossRef

25.

Verikas A, Lipnickas A (2002) Fusing neural networks through space partitioning and fuzzy integration. Neural Process Lett 16(1):53–65. https://doi.org/10.1023/A:1019703911322CrossRefMATH

26.

Davidson JL, Ritter GX (1990) Theory of morphological neural networks. In: Proceedings of the SPIE. Digital Optical Computing II. Los Angeles, CA, USA, vol 1215, pp 378-388.https://doi.org/10.1117/12.18085

27.

Feng NQ, Sun B (2018) On simulating one-trial learning using morphological neural networks. Cogn Syst Res 53:61–70. https://doi.org/10.1016/j.cogsys.2018.05.003CrossRef

28.

Ritter GX, Sussner P, Diaz-de-Leon JL (1998) Morphological associative memories. IEEE Trans Neural Netw 9(2):281–293. https://doi.org/10.1109/72.661123CrossRef

29.

Wang M, Wang ST, Wu XJ (2003) Initial results of fuzzy morphological associative memories. Acta Electronica Cinica 31(5):690–693 (in Chinese with abstract in English)MathSciNet

30.

Wang M, Chen SC (2005) Enhanced FMAM based on empirical kernel map. IEEE Trans Neural Netw 16(3):557–564CrossRef

31.

Feng NQ, Liu CH, Zhang CP et al (2010) Research on the framework of morphological associative memories. Chin J Comput 33(1):157–166. https://doi.org/10.3724/SP.J.1016.2010.00157 (in Chinese with abstract in English)CrossRef

32.

Feng NQ, Tian Y, Wang XF et al (2015) Logarithmic and exponential morphological associative memories. Ruan Jian Xue Bao/J Softw 26(7):1662–1674 (in Chinese with abstract in English)MathSciNet

33.

Feng NQ, Wang XF, Mao WT, Ao LH (2013) Heteroassociative morphological memories based on four-dimensional storage. Neurocomputing 116:76–86. https://doi.org/10.1016/j.neucom.2012.01.043CrossRef

34.

Feng NQ, Yao YL (2016) No rounding reverse fuzzy morphological associative memories. Neural Netw World 6:571–587CrossRef

35.

Valdiviezo-N JC, Urcid G, Lechuga E (2016) Digital restoration of damaged color documents based on hyperspectral imaging and lattice associative memories. Signal Image Video Process. https://doi.org/10.1007/s11760-016-1042-yCrossRef

36.

Graña M, Chyzhyk D (2015) Image understanding applications of lattice autoassociative memories. IEEE Trans Neural Netw Learn Syst 27(9):1920–1932. https://doi.org/10.1109/TNNLS.2015.2461451MathSciNetCrossRef

37.

Sussner P, Schuster T (2018) Interval-valued fuzzy morphological associative memories: some theoretical aspects and applications. Inf Sci 438:127–144. https://doi.org/10.1016/j.ins.2018.01.042MathSciNetCrossRefMATH

38.

Acevedo ME, Martınez JA, Acevedo MA et al (2014) Morphological associative memories for gray-scale image encryption. Appl. Math. Inf. Sci. 8(1):127–134MathSciNetCrossRef

39.

Sossa H, Guevara E (2014) Efficient training for dendrite morphological neural networks. Neurocomputing 131:132–142. https://doi.org/10.1016/j.neucom.2013.10.031CrossRef

40.

He H, Garcia EA (2009) Learning from imbalanced data. IEEE Trans Knowl Data Eng 21(9):1263–1284CrossRef

41.

Li J, Yu ZL, Gu Z et al (2019) Spatial-temporal discriminative restricted boltzmann machine for event-related potential detection and analysis. IEEE Trans Neural Syst Rehabil Eng 27(2):139–151CrossRef

42.

Wu W, Chen Z, Gao X et al (2014) Probabilistic common spatial patterns for multichannel EEG analysis. IEEE Trans Pattern Anal Mach Intell 37(3):639–653. https://doi.org/10.1109/TPAMI.2014.2330598CrossRef

43.

Li J, Yu ZL, Gu Z et al (2018) A hybrid network for ERP detection and analysis based on restricted Boltzmann machine. IEEE Trans Neural Syst Rehabil Eng 26(3):563–572. https://doi.org/10.1109/TNSRE.2018.2803066CrossRef

44.

Qi F, Li Y, Wu W (2015) RSTFC: a novel algorithm for spatio-temporal filtering and classification of single-trial EEG. IEEE Trans Neural Netw Learn Syst 26(12):3070–3082. https://doi.org/10.1109/TNNLS.2015.2402694MathSciNetCrossRef

45.

Bradley AP (1997) The use of the area under the ROC curve in the evaluation of machine learning algorithms. Pattern Recognit 30(7):1145–1159CrossRef

46.

Liu Y, Qin Z, Lu J, Shi Z (2005) Multimodal particle swarm optimization for neural network ensemble. J Comput Res Dev 42(9):1519–1526 (in Chinese with abstract in English)CrossRef

47.

Li K, Huang HK (2006) Study of a neural network ensemble algorithm for small data sets. J Comput Res Dev 43(7):1161–1166CrossRef

48.

Gupta Y (2018) Selection of important features and predicting wine quality using machine learning techniques. Procedia Comput Sci 125:305–312. https://doi.org/10.1016/j.procs.2017.12.041CrossRef

49.

Vazquez RA, Sossa H (2011) Behavioral study of median associative memory under true color image patterns. Neurocomputing 74(17):2985–2997CrossRef

Title: Study on Neural Network Integration Method Based on Morphological Associative Memory Framework
Authors: Naiqin Feng
Xiuqin Geng
Bin Sun
Publication date: 22-07-2021
Publisher: Springer US
Published in: Neural Processing Letters / Issue 6/2021
Print ISSN: 1370-4621
Electronic ISSN: 1573-773X
DOI: https://doi.org/10.1007/s11063-021-10569-9

Springer Professional

Abstract

Please log in to get access to your license.

Dont have a licence yet? Then find out more about our products and how to get one now:

Springer Professional "Wirtschaft+Technik"

Springer Professional "Technik"

Springer Professional "Wirtschaft"

Other articles of this Issue 6/2021

Correction to: An Energy-Aware Trust and Opportunity Based Routing Algorithm in Wireless Sensor Networks Using Multipath Routes Technique

Residual Spatiotemporal Autoencoder with Skip Connected and Memory Guided Network for Detecting Video Anomalies

Fuzzy Coefficient of Impulsive Intensity in a Nonlinear Impulsive Control System

New Results on Global Exponential Stability of Genetic Regulatory Networks with Diffusion Effect and Time-Varying Hybrid Delays

BSS Method Based on Wavelet Transform and Improved EASI Algorithm and Its Application in EMI

Identification of Influential Nodes for Drone Swarm Based on Graph Neural Networks