Top

International Journal of Machine Learning and Cybernetics

Published in:

27-04-2023 | Original Article

Irregular convolution strategy based tensorized type-2 single layer feedforward network

Authors: Jie Li, Guoliang Zhao, Sharina Huang, Zhi Weng

Published in: International Journal of Machine Learning and Cybernetics | Issue 9/2023

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

search-config

AI-assisted search

Off

Abstract

Tensorized type-2 single layer feedforward network extends the single layer feedforward network with tensorized type-2 fuzzy structure. In the tensorized type-2 single layer feedforward network, type-2 fuzzy sets are used to generate tensor with lower membership function, principal membership function and upper membership function. Other compositions of the single layer feedforward network, such as defuzzification results, weighted averaged results and different type reduction results could also be formed by the tensorized fuzzy construction method. In thus doing, the type-reduction or defuzzification approach is the unimportance procedure in the fuzzy network operation and construction. To deeply unveil the implicit information hidden in the type-2 fuzzy sets, cross-shaped convolution with irregular convolution kernel is used to form the tensor. The named irregular convolution kernel based tensorized type-2 single layer feedforward network adopts an iterative tensor equation solving algorithm with tensor inequality constraint (Huang and Ma in Linear Multilinear Algebra, 1–24, 2021, https://doi.org/10.1080/03081087.2021.1954140). Finally, the effectiveness of different convolution kernels for irregular convolution strategy based tensorized type-2 single layer feedforward network are tested. Comparisons are carried out on several benchmark datasets, and five different type-reduction methods for the irregular convolution strategy based tensorized type-2 single layer feedforward network are compared. Results show that the proposed learning method could be improved with this new information extraction strategy.

previous article An attention-based automatic vulnerability detection approach with GGNN

next article BenchMetrics Prob: benchmarking of probabilistic error/loss performance evaluation instruments for binary classification problems

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

ATZelectronics worldwide

ATZlectronics worldwide is up-to-speed on new trends and developments in automotive electronics on a scientific level with a high depth of information.

Order your 30-days-trial for free and without any commitment.

inform now

ATZelektronik

Die Fachzeitschrift ATZelektronik bietet für Entwickler und Entscheider in der Automobil- und Zulieferindustrie qualitativ hochwertige und fundierte Informationen aus dem gesamten Spektrum der Pkw- und Nutzfahrzeug-Elektronik.

Lassen Sie sich jetzt unverbindlich 2 kostenlose Ausgabe zusenden.

inform now

Huang BH, Ma CF (2021) The iterative solution of a class of tensor equations via Einstein product with a tensor inequality constraint. Linear Multilinear Algebra. 70:6321–6344. https://doi.org/10.1080/03081087.2021.1954140

Husmeier D (1999) Random vector functional link (RVFL) networks. Neural networks for conditional probability estimation. Perspectives in neural computing. Springer, London, pp 87–97. https://doi.org/10.1007/978-1-4471-0847-4_6CrossRef

Huang G-B, Zhu Q-Y, Siew C-K (2004) Extreme learning machine: a new learning scheme of feedforward neural networks. In: 2004 IEEE international joint conference on neural networks (IEEE Cat. No.04CH37541), vol 2, pp 985–990. https://doi.org/10.1109/IJCNN.2004.1380068

Huang SRN, Zhao GL, Chen MH (2019) Tensor extreme learning design via generalized Moore-Penrose inverse and triangular type-2 fuzzy sets. Neural Comput Appl 31(9):5641–5651. https://doi.org/10.1007/s00521-018-3385-5CrossRef

Zhao GL, Wu W (2019) Tensor-based type-2 random vector functional link network. In: 2019 Chinese control and decision conference (CCDC), pp 3278–3285. https://doi.org/10.1109/CCDC.2019.8833161

Ahuja B, Vishwakarma VP (2021) Deterministic multi-kernel based extreme learning machine for pattern classification. Expert Syst Appl 183:115308. https://doi.org/10.1016/j.eswa.2021.115308CrossRef

Dhar S, Kundu MK (2020) Interval type-2 fuzzy set and theory of weak continuity constraints for accurate multiclass image segmentation. IEEE Trans Fuzzy Syst 28(9):2151–2163. https://doi.org/10.1109/TFUZZ.2019.2930932CrossRef

Greenfield S, Chiclana F (2018) Type-reduced set structure and the truncated type-2 fuzzy set. Fuzzy Sets Syst 352:119–141. https://doi.org/10.1016/j.fss.2018.02.012MathSciNetCrossRefMATH

Liu XL, Wan SP (2020) Combinatorial iterative algorithms for computing the centroid of an interval type-2 fuzzy set. IEEE Trans Fuzzy Syst 28(4):607–617. https://doi.org/10.1109/TFUZZ.2019.2911918CrossRef

10.

Wang HD, Yao JL, Yan J, Dong MG (2019) An extended TOPSIS method based on gaussian interval type-2 fuzzy set. Int J Fuzzy Syst 21(6):1831–1843. https://doi.org/10.1007/s40815-019-00670-6CrossRef

11.

Wu Q, Zhou LG, Chen Y, Chen HY (2019) An integrated approach to green supplier selection based on the interval type-2 fuzzy best-worst and extended VIKOR methods. Inf Sci 502:394–417. https://doi.org/10.1016/j.ins.2019.06.049CrossRef

12.

Deng L, Li GQ, Han S, Shi LP, Xie Y (2020) Model compression and hardware acceleration for neural networks: a comprehensive survey. Proc IEEE 108(4):485–532. https://doi.org/10.1109/JPROC.2020.2976475CrossRef

13.

Choudhary T, Mishra V, Goswami A, Sarangapani J (2020) A comprehensive survey on model compression and acceleration. Artif Intell Rev 53(7):5113–5155. https://doi.org/10.1007/s10462-020-09816-7CrossRef

14.

Negi S, Rauthan MMS, Vaisla KS, Panwar N (2021) CMODLB: an efficient load balancing approach in cloud computing environment. J Supercomput. https://doi.org/10.1007/s11227-020-03601-7CrossRef

15.

Cai H, Lin J, Lin YJ, Liu ZJ, Wang K, Wang TZ, Zhu LG, Han Song (2020) AutoML for architecting efficient and specialized neural networks. IEEE Micro 40(1):75–82. https://doi.org/10.1109/MM.2019.2953153CrossRef

16.

Qin HT, Gong RH, Liu XL, Bai X, Song JK, Sebe N (2020) Binary neural networks: a survey. Pattern Recogn 105:107281. https://doi.org/10.1016/j.patcog.2020.107281CrossRef

17.

Dhar S, Kundu MK (2018) A novel method for image thresholding using interval type-2 fuzzy set and bat algorithm. Appl Soft Comput 63:154–166. https://doi.org/10.1016/j.asoc.2017.11.032CrossRef

18.

Bora DJ, Thakur RS (2018) An efficient technique for medical image enhancement based on interval type-2 fuzzy set logic. Progress in computing, analytics and networking. Springer Singapore, Singapore, pp 667–678. https://doi.org/10.1007/978-981-10-7871-2_64CrossRef

19.

Alipouri Y, Poshtan J (2017) Robust minimum variance lower bound estimation by uncertainty modeling using interval type-2 fuzzy set. Asian J Control 19(1):47–56. https://doi.org/10.1002/asjc.1307MathSciNetCrossRefMATH

20.

Pal SS, Kar S (2019) A hybridized forecasting method based on weight adjustment of neural network using generalized type-2 fuzzy set. Int J Fuzzy Syst 21(1):308–320. https://doi.org/10.1007/s40815-018-0534-zCrossRef

21.

Dan S, Kar MB, Majumder S, Roy B, Kar S, Pamucar D (2019) Intuitionistic type-2 fuzzy set and its properties. Symmetry 11(6):808. https://doi.org/10.3390/sym11060808CrossRef

22.

Bustince H, Barrenechea E, Pagola M, Fernandez J, Xu ZS, Bedregal B, Montero J, Hagras H, Herrera F, Baets BD (2016) A historical account of types of fuzzy sets and their relationships. IEEE Trans Fuzzy Syst 24(1):179–194. https://doi.org/10.1109/TFUZZ.2015.2451692CrossRef

23.

Mohammadzadeh A, Sabzalian MH, Zhang WD (2020) An interval type-3 fuzzy system and a new online fractional-order learning algorithm: theory and practice. IEEE Trans Fuzzy Syst 28(9):1940–1950. https://doi.org/10.1109/TFUZZ.2019.2928509CrossRef

24.

Ma C, Mohammadzadeh A, Turabieh H, Mafarja M, Band SS, Mosavi A (2020) Optimal type-3 fuzzy system for solving singular multi-pantograph equations. EEE Acess 8:225692–225702. https://doi.org/10.1109/ACCESS.2020.3044548CrossRef

25.

Qasem SN, Ahmadian A, Mohammadzadeh A, Rathinasamy S, Pahlevanzadeh B (2021) A type-3 logic fuzzy system: optimized by a correntropy based Kalman filter with adaptive fuzzy kernel size. Inf Sci 572:424–443. https://doi.org/10.1016/j.ins.2021.05.031MathSciNetCrossRef

26.

Nabipour N, Qasem SN, Jermsittiparsert K (2020) Type-3 fuzzy voltage management in PV/hydrogen fuel cell/battery hybrid systems. Int J Hydrogen Energy 45(56):32478–32492. https://doi.org/10.1016/j.ijhydene.2020.08.261CrossRef

27.

Vafaie RH, Mohammadzadeh A, Piran MJ (2021) A new type-3 fuzzy predictive controller for MEMS gyroscopes. Nonlinear Dyn. https://doi.org/10.1007/s11071-021-06830-4CrossRef

28.

Cao Y, Raise A, Mohammadzadeh A, Rathinasamy S, Band SS, Mosavi A (2021) Deep learned recurrent type-3 fuzzy system: application for renewable energy modeling/prediction. Energy Rep. https://doi.org/10.1016/j.egyr.2021.07.004CrossRef

29.

Mohammadzadeh A, Castillo O, Band SS, Mosavi A (2021) A novel fractional-order multiple-model type-3 fuzzy control for nonlinear systems with unmodeled dynamics. Int J Fuzzy Syst. https://doi.org/10.1007/s40815-021-01058-1CrossRef

30.

Gheisarnejad M, Mohammadzadeh A, Farsizadeh H, Khooban MH (2021) Stabilization of 5G telecom converter-based deep type-3 fuzzy machine learning control for telecom applications. IEEE Trans Circuits Syst II Express Briefs. https://doi.org/10.1109/TCSII.2021.3102282CrossRef

31.

Ye JM, Li GX, Chen D, Yang HQ, Zhe SD, Xu ZL (2020) Block-term tensor neural networks. Neural Netw 130:11–21. https://doi.org/10.1016/j.neunet.2020.05.034CrossRef

32.

Wu BJ, Wang DH, Zhao GS, Deng L, Li GQ (2020) Hybrid tensor decomposition in neural network compression. Neural Netw 132:309–320. https://doi.org/10.1016/j.neunet.2020.09.006CrossRefMATH

33.

Chang Nie, Wang H (2022) Tensor neural networks via circulant convolution. Neurocomputing 483:22–31. https://doi.org/10.1016/j.neucom.2022.01.010CrossRef

34.

Li J, Hu JL, Zhao GL, Huang SRN, Liu Y (2022) Tensor based stacked fuzzy neural network for efficient data regression. Soft Comput. https://doi.org/10.1007/s00500-022-07402-3CrossRef

35.

Wang XZ, Che ML, Wei YM (2020) Tensor neural network models for tensor singular value decompositions. Comput Optim Appl 75(3):753–777. https://doi.org/10.1007/s10589-020-00167-1MathSciNetCrossRefMATH

36.

Lv R, Wang DH, Zheng JB, Xie YF, Yang ZX (2022) Realistic acceleration of neural networks with fine-grained tensor decomposition. Neurocomputing 512:52–68. https://doi.org/10.1016/j.neucom.2022.09.057CrossRef

37.

Duan MX, Li KL, Li KQ, Tian Q (2021) A novel multi-task tensor correlation neural network for facial attribute prediction. ACM Trans Intell Syst Technol 12(1):1–22. https://doi.org/10.1145/3418285CrossRef

38.

Zhao XS, Dai Q, Wu J, Peng H, Liu MS, Bai X, Tan JL, Wang SZ, Yu PS (2022) Multi-view tensor graph neural networks through reinforced aggregation. IEEE Trans Knowl Data Eng. https://doi.org/10.1109/tkde.2022.3142179CrossRef

39.

Mendel JM, John RI, Liu FL (2006) Interval type-2 fuzzy logic systems made simple. IEEE Trans Fuzzy Syst 14(6):808–821. https://doi.org/10.1109/TFUZZ.2006.879986CrossRef

40.

Liu GZ, Zhang K, Lv MB (2021) ASKs: convolution with any-shape kernels for efficient neural networks. Neurocomputing 446:32–49. https://doi.org/10.1016/j.neucom.2021.03.039CrossRef

41.

Runkler TA, Coupland S, John R, Chen C (2018) Interval type-2 defuzzification using uncertainty weights. Frontiers in computational intelligence. Springer, Berlin, pp 47–59. https://doi.org/10.1007/978-3-319-67789-7_4CrossRef

42.

Huang SRN, Zhao GL, Weng Z, Ma SY (2022) Trapezoidal type-2 fuzzy inference system with tensor unfolding structure learning method. Neurocomputing 473:54–67. https://doi.org/10.1016/j.neucom.2021.12.011CrossRef

43.

Rong HJ, Huang GB, Sundararajan N, Saratchandran P (2009) Online sequential fuzzy extreme learning machine for function approximation and classification problems. IEEE Trans Syst Man Cybern Part B (Cybern) 39(4):1067–1072. https://doi.org/10.1109/TSMCB.2008.2010506CrossRef

44.

Juang CF, Huang RB, Cheng WY (2010) An interval type-2 fuzzy-neural network with support-vector regression for noisy regression problems. IEEE Trans Fuzzy Syst 18(4):686–699. https://doi.org/10.1109/TFUZZ.2010.2046904CrossRef

45.

Ho DWC, Zhang PA, Xu JH (2001) Fuzzy wavelet networks for function learning. IEEE Trans Fuzzy Syst 9(1):200–211. https://doi.org/10.1109/91.917126CrossRef

46.

Zhang PB, Yang ZX (2020) A new learning paradigm for random vector functional-link network:RVFL+. Neural Netw 122:94–105. https://doi.org/10.1016/j.neunet.2019.09.039CrossRef

47.

Lai J, Wang XD, Li R, Song YF, Lei L (2020) BD-ELM: a regularized extreme learning machine using biased DropConnect and biased dropout. Math Probl Eng 2020:1–7. https://doi.org/10.1155/2020/3604579CrossRef

48.

Fedesoriano (2021) Heart failure prediction dataset. Retrieved [Date Retrieved] from https://www.kaggle.com/fedesoriano/heart-failure-prediction

49.

Wu D, Nie M (2011) Comparison and practical implementation of type-reduction algorithms for type-2 fuzzy sets and systems. In: 2011 IEEE international conference on fuzzy systems, pp 2131–2138. https://doi.org/10.1109/FUZZY.2011.6007317

50.

Wu DR, Mendel JM (2009) Enhanced Karnik–Mendel algorithms. IEEE Trans Fuzzy Syst 17(4):923–934. https://doi.org/10.1109/TFUZZ.2008.924329CrossRef

51.

Hu HZ, Wang Y, Cai YL (2012) Advantages of the enhanced opposite direction searching algorithm for computing the centroid of an interval type-2 fuzzy set. Asian J Control 14(5):1422–1430. https://doi.org/10.1002/asjc.477MathSciNetCrossRefMATH

52.

Duran K, Bernal H, Melgarejo M (2008) Improved iterative algorithm for computing the generalized centroid of an interval type-2 fuzzy set. In: NAFIPS 2008–2008 annual meeting of the North American Fuzzy Information Processing Society, pp 1–5. https://doi.org/10.1109/NAFIPS.2008.4531244

53.

Rezaie-Balf M, Attar NF, Mohammadzadeh A, Murti MA, Ahmed AN, Fai CM, Nabipour N, Alaghmand S, El-Shafie A (2020) Physicochemical parameters data assimilation for efficient improvement of water quality index prediction: comparative assessment of a noise suppression hybridization approach. J Clean Prod 271:122576. https://doi.org/10.1016/j.jclepro.2020.122576CrossRef

54.

Sakthivel R, Kavikumar R, Mohammadzadeh A, Kwon OM, Kaviarasan B (2021) Fault estimation for mode-dependent IT2 fuzzy systems with quantized output signals. IEEE Trans Fuzzy Syst 29(2):298–309. https://doi.org/10.1109/tfuzz.2020.3018509CrossRef

Title: Irregular convolution strategy based tensorized type-2 single layer feedforward network
Authors: Jie Li
Guoliang Zhao
Sharina Huang
Zhi Weng
Publication date: 27-04-2023
Publisher: Springer Berlin Heidelberg
Published in: International Journal of Machine Learning and Cybernetics / Issue 9/2023
Print ISSN: 1868-8071
Electronic ISSN: 1868-808X
DOI: https://doi.org/10.1007/s13042-023-01825-6

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"

ATZelectronics worldwide

ATZelektronik

Other articles of this Issue 9/2023

Robust unsupervised feature selection via dual space latent representation learning and adaptive structure learning

CatSight, a direct path to proper multi-variate time series change detection: perceiving a concept drift through common spatial pattern

Deep hashing via multi-scale and multi-directional pooling for image retrieval

AANet: adaptive attention network for rolling bearing fault diagnosis under varying loads

Link prediction for heterogeneous information networks based on enhanced meta-path aggregation and attention mechanism

An attention-based automatic vulnerability detection approach with GGNN