Abstract
In view of the nonlinearity and uncertainty of safety accident risk assessment, firstly, based on the deep neural network, the training criterion of the network is changed, and the triplet convolutional neural network with the similarity measure as the cost function is proposed. The inactive multi-scale set features are extracted from them, so that the semantic features obtained by learning are suitable for security risk image retrieval. In the image retrieval application, the training samples of the retrieved data set are not enough to train a large network, and the innovative application of migration learning to security risk image retrieval proposes to train the network with data sets similar to the retrieved data sets. Then based on the traditional nearest neighbor algorithm, this paper proposes a case similarity calculation method based on two-dimensional structure of structural similarity and attribute similarity, input the characteristic attribute value of the current emergency event, and conduct similar case retrieval. The final calculation returns the historical case and its solution that the user is most similar to the currently entered incident feature. The experiment proves that the maximum relative error between the output of the network and the expected output value is 5.17%, and the minimum relative error is 1.38%, which has high accuracy.
Similar content being viewed by others
References
Silva C, Vasconcelos G, Barros H et al (2015 ) Case-based reasoning combined with neural networks for credit risk analysis. International Joint Conference on Neural Networks
Sharma R, Aiken A (2016) From invariant checking to invariant inference using randomized search. Formal Methods in System Design 48(3):235–256
Yu Q, Tang H, Tan KC, Yu H (2014) A brain-inspired spiking neural network model with temporal encoding and learning. Neurocomputing 138(11):3–13
Gharavian D, Bejani M, Sheikhan M (2017) Audio-visual emotion recognition using FCBF feature selection method and particle swarm optimization for fuzzy ARTMAP neural networks. Multimed Tools Appl 76(2):2331–2352
Hamm RM, Beasley WH, Johnson WJ (2014) A balance beam aid for instruction in clinical diagnostic reasoning. Medical Decision Making An International Journal of the Society for Medical Decision Making 34(7):854–862
Hahn GJ, Sens T, Decouttere C, Vandaele NJ (2016) A multi-criteria approach to robust outsourcing decision-making in stochastic manufacturing systems. Comput Ind Eng 98:275–288
Viduto V, Maple C, Huang W et al (2012) A multi-objective genetic algorithm for minimising network security risk and cost. International Conference on High Performance Computing & Simulation. IEEE
Xinlan Z X Z, Zhifang H Z H, Guangfu W G W et al (2011) Information security risk assessment methodology research: group decision making and analytic hierarchy process. Second World Congress on Software Engineering. IEEE
Rees LP, Deane JK, Rakes TR, Baker WH (2011) Decision support for cybersecurity risk planning[J]. Decis Support Syst 51(3):493–505
Mandal M (2014) Risk analysis using FMEA: fuzzy similarity value and possibility theory based approach. Expert Syst Appl 41(7):3527–3537
Pham C, Estrada Z, Cao P et al (2014) Reliability and security monitoring of virtual machines using hardware architectural invariants. IEEE/IFIP International Conference on Dependable Systems & Networks
Long NC, Meesad P, Unger H (2015) A highly accurate firefly based algorithm for heart disease prediction[J]. Expert Syst Appl 42(21):8221–8231
Chai J, Liu JNK (2014) A novel believable rough set approach for supplier selection. Expert Syst Appl 41(1):92–104
Wang P, Wu Q, Shen C et al (2015) Explicit knowledge-based reasoning for visual question answering. Comput Therm Sci
Papatheou E, Manson G, Barthorpe RJ, Worden K (2014) The use of pseudo-faults for damage location in SHM: an experimental investigation on a Piper Tomahawk aircraft wing. J Sound Vib 333(3):971–990
Kulkarni SU, Shetty BS (2015) Data mining using modified GFMM neural network. Int J Comput Appl 116(15):18–22
Lu W, Wang X, Yang C et al (2015) A novel feature extraction method using deep neural network for rolling bearing fault diagnosis. Control & Decision Conference
Thanda A, Venkatesan SM (2016) Audio visual speech recognition using deep recurrent neural networks. Iapr Workshop on Multimodal Pattern Recognition of Social Signals in Human-Computer Interaction
Woo S, Lee C (2017) Feature extraction for deep neural networks based on decision boundaries. Spie Defense + Security
Yadav P (2015) Case retrieval algorithm using similarity measure and adaptive fractional brain storm optimization for health Informaticians[J]. Arab J Sci Eng 41(3):1–12
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Hu, J., Fang, J., Du, Y. et al. A security risk plan search assistant decision algorithm using deep neural network combined with two-stage similarity calculation. Pers Ubiquit Comput 23, 541–552 (2019). https://doi.org/10.1007/s00779-019-01236-x
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00779-019-01236-x