Abstract
We present an exploratory study to improve the performance of a knowledge push system in product design. We focus on the domain of knowledge matching, where traditional matching algorithms need repeated calculations that result in a long response time and where accuracy needs to be improved. The goal of our approach is to meet designers’ knowledge demands with a quick response and quality service in the knowledge push system. To improve the previous work, two methods are investigated to augment the limited training set in practical operations, namely, oscillating the feature weight and revising the case feature in the case feature vectors. In addition, we propose a multi-classification radial basis function neural network that can match the knowledge from the knowledge base once and ensure the accuracy of pushing results. We apply our approach using the training set in the design of guides by computer numerical control machine tools for training and testing, and the results demonstrate the benefit of the augmented training set. Moreover, experimental results reveal that our approach outperforms other matching approaches.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Bahramian Z, Abbaspour RA, Claramunt C, 2017. A cold start context-aware recommender system for tour planning using artificial neural network and case based reasoning. Mob Inform Syst, 2017:9364903. https://doi.org/10.1155/2017/9364903
Chen S, Yang ZY, Sun LY, et al., 2015. Research on design knowledge analytical method during sketching—combining acoustic energy feature and creative segment theory. J Zhejiang Univ Eng Sci, 49(11):2073–2082 (in Chinese).
Devi MKK, Samy RT, Kumar SV, et al., 2010. Probabilistic neural network approach to alleviate sparsity and cold start problems in collaborative recommender systems. Proc IEEE Int Conf on Computational Intelligence and Computing Research, p.1–4. https://doi.org/10.1109/ICCIC.2010.5705777
Dong SY, Xu JX, Wang KQ, et al., 2013. Active push model of manufacturing process knowledge in CAD platform based on immune process. Comput Integr Manuf Syst, 19(7):1520–1531 (in Chinese). https://doi.org/10.13196/jxims.2013.07.82.dongsy.016
Fan ZP, Feng Y, Sun YH, et al., 2005. A framework on compound knowledge push system oriented to organizational employees. Proc 1st Int Workshop on Internet and Network Economics, p.622–630. https://doi.org/10.1007/11600930_62
Feng YX, Zhang SY, Gao YC, et al., 2016. Intelligent push method of CNC design knowledge based on feature semantic analysis. Comput Integr Manuf Syst, 22(1):189–201 (in Chinese). https://doi.org/10.13196/j.cims.2016.01.018
Gabrani G, Sabharwal S, Singh VK, 2017. Artificial intelligence based recommender systems: a survey. Proc 1st Int Conf on Advances in Computing and Data Sciences, p.50–59. https://doi.org/10.1007/978-981-10-5427-3_6
Guo Y, Yin CX, Li MF, et al., 2018. Mobile e-commerce recommendation system based on multi-source information fusion for sustainable e-business. Sustainability, 10(1):147. https://doi.org/10.3390/su10010147
Gupta A, Tripathy BK, 2014. A generic hybrid recommender system based on neural networks. Proc IEEE Int Advance Computing Conf, p.1248–1252. https://doi.org/10.1109/IAdCC.2014.6779506
Ji X, Gu XJ, Dai F, et al., 2013. Technology for product design knowledge push based on ontology and rough sets. Comput Integr Manuf Syst, 19(1):7–20 (in Chinese). https://doi.org/10.13196/j.cims.2013.01.9.jix.008
Jiang H, Yin P, Guo L, et al., 2017. Knowledge push based on design flow and user capacity model. Proc MATEC Web Conf, Article 12.
Karayiannis NB, 1999. Reformulated radial basis neural networks trained by gradient descent. IEEE Trans Neur Netw, 10(3):657–671. https://doi.org/10.1109/72.761725
Le CY, Dai F, Ji X, et al., 2010. Domain knowledge actively pushing system driven by process. Comput Integr Manuf Syst, 16(12):2720–2727 (in Chinese). https://doi.org/10.13196/j.cims.2010.12.178.yuechy.018
Li XR, Yu SH, Chu JJ, et al., 2017. Double push strategy of knowledge for product design based on complex network theory. Discr Dynam Nat Soc, Article 2 078 626. https://doi.org/10.1155/2017/2078626
Liang Y, Zhang S, Liu X, et al., 2015. Product design knowledge dynamic push technology based on variable-weight layered spreading activation model. Comput Integr Manuf Syst, 21(12):3107–3118 (in Chinese). https://doi.org/10.13196/j.cims.2015.12.002
Liu HM, Wang HQ, Li X, 2009. A study on data normalization for target recognition based on RPROP algorithm. Mod Radar, 31(5):55–60. https://doi.org/10.3969/j.issn.1004-7859.2009.05.014
Liu TY, Wang HF, He Y, 2016. Intelligent knowledge recommending approach for new product development based on workflow context matching. Concurr Eng, 24(4):318–329. https://doi.org/10.1177/1063293X16640319
Paradarami TK, Bastian ND, Wightman JL, 2017. A hybrid recommender system using artificial neural networks. Expert Syst Appl, 83:300–313. https://doi.org/10.1016/j.eswa.2017.04.046
Pushpa CN, Ashvini P, Thriveni J, et al., 2013. Web page recommendations using radial basis neural network technique. Proc 8th Int Conf on Industrial and Information Systems, p.501–506. https://doi.org/10.1109/ICIInfS.2013.6732035
Schreiber AT, Schreiber G, Akkermans H, et al., 2000. Knowledge engineering and management: the common KADS methodology. MIT Press, Cambridge, MA, USA.
Sunhem W, Pasupa K, 2016. An approach to face shape classification for hairstyle recommendation. Proc 8th Int Conf on Advanced Computational Intelligence, p.390–394. https://doi.org/10.1109/ICACI.2016.7449857
Twardowski B, 2016. Modelling contextual information in session-aware recommender systems with neural networks. Proc 10th ACM Conf on Recommender Systems, p.273–276. https://doi.org/10.1145/2959100.2959162
van Rijsbergen CJ, 1979. Information Retrieval (2nd Ed.). Butterworth, London, UK.
Wang ZS, Tian L, Wu YH, et al., 2016. Personalized knowledge push system based on design intent and user interest. Proc Inst Mech Eng Part C, 230(11):1757–1772. https://doi.org/10.1177/0954406215584395
Wu H, Zhang ZX, Yue K, et al., 2018. Dual-regularized matrix factorization with deep neural networks for recommender systems. Knowl-Based Syst, 145:46–58. https://doi.org/10.1016/j.knosys.2018.01.003
Wu LJ, Gou BC, Wen CG, 2018. Research on knowledge-push driven by workflow and knowledge points. Comput Eng Appl, 54(4):231–236 (in Chinese). https://doi.org/10.3778/j.issn.1002-8331.1609-0014
Xiao Y, Lou CQ, Liu G, 2010. Personalized knowledge push service based on semantic web. Int Conf on E-Business and E-Government, p.1872–1875. https://doi.org/10.1109/ICEE.2010.473
Xu YH, Yin GF, Nie Y, et al., 2013. Research on an active knowledge push service based on collaborative intent capture. J Netw Comput Appl, 36(6):1418–1430. https://doi.org/10.1016/j.jnca.2013.04.010
Xue HJ, Dai XY, Zhang JB, et al., 2017. Deep matrix factorization models for recommender systems. Proc 26th Int Joint Conf on Artificial Intelligence, p.3203–3209. https://doi.org/10.24963/ijcai.2017/447
Yan Y, Yang N, Hao J, et al., 2016. A context modeling method of knowledge recommendation for designers. Proc Int Conf on Information System and Artificial Intelligence, p.492–496. https://doi.org/10.1109/ISAI.2016.0111
Yang XH, Huang JF, Wang JW, et al., 2007. Estimation of vegetation biophysical parameters by remote sensing using radial basis function neural network. J Zhejiang Univ-Sci A (Appl Phys Eng), 8(6):883–859. https://doi.org/10.1631/jzus.2007.A0883
Zhang C, Zhou GH, Bai QD, et al., 2018. HEKM: a high-end equipment knowledge management system for supporting knowledge-driven decision-making in new product development. Proc ASME Int Design Engineering Technical Conf and Computers and Information in Engineering Conf, Article V0 1BT 02A 014. https://doi.org/10.1115/DETC2018-85151
Zhang FP, Li L, 2016. Research on knowledge push method for business process based on multidimensional hierarchical context model. Proc IEEE Int Conf on Industrial Engineering and Engineering Management, p.656–660. https://doi.org/10.1109/IEEM.2016.7797957
Zhang FP, Li L, 2017. Research on knowledge push method for business process based on multidimensional hierarchical context model. J Comput-Aided Des Comput Graph, 29(4):751–758 (in Chinese). https://doi.org/10.3969/j.issn.1003-9775.2017.04.021
Zhang K, Zhao W, Wang J, et al., 2019. Knowledge push technology based on quality function knowledge deployment. Proc Inst Mech Eng Part C, 233(4):1119–1138. https://doi.org/10.1177/0954406218768843
Zhang LL, Nie GL, Zhang YJ, et al., 2009. A way to implement intelligent knowledge push in knowledge management system. Proc Int Joint Conf on Computational Sciences and Optimization, 1:746–749. https://doi.org/10.1109/CSO.2009.102
Zhang SY, Gu Y, Liu X, et al., 2018. A knowledge push technology based on applicable probability matching and multidimensional context driving. Front Inform Technol Electron Eng, 19(2):235–245. https://doi.org/10.1631/FITEE.1700763
Zhang SY, Gu Y, Yi GD, 2019. A hybrid knowledge push method based on trust-aware and item-cluster oriented to product design. New Gener Comput, 37:339–357. https://doi.org/10.1007/s00354-019-00053-3
Zuo Y, Zeng J, Gong M, et al., 2016. Tag-aware recommender systems based on deep neural networks. Neurocomputing, 204:51–60. https://doi.org/10.1016/j.neucom.2015.10.134
Author information
Authors and Affiliations
Contributions
Shu-you ZHANG guided the research. Ye GU designed the research and drafted the manuscript. Shu-you ZHANG and Guo-dong YI helped organize and revise the manuscript. Zi-li WANG finalized the paper.
Corresponding author
Ethics declarations
Shu-you ZHANG, Ye GU, Guo-dong YI, and Zi-li WANG declare that they have no conflict of interest.
Additional information
Project supported by the National Key R&D Project of China (No. 2018YFB1700700) and the National Natural Science Foundation of China (No. 51675478)
Rights and permissions
About this article
Cite this article
Zhang, Sy., Gu, Y., Yi, Gd. et al. A knowledge matching approach based on multi-classification radial basis function neural network for knowledge push system. Front Inform Technol Electron Eng 21, 981–994 (2020). https://doi.org/10.1631/FITEE.1900057
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1631/FITEE.1900057
Key words
- Product design
- Knowledge push system
- Augmented training set
- Multi-classification neural network
- Knowledge matching