Skip to main content
SpringerLink
Log in

Risk prediction model and classification of various hazards in automobile industry using HAO based deep CNN

  • Published:
Sādhanā Aims and scope Submit manuscript

Abstract

The automobile industries and the manufacturing revolution leads to a large extend of risk and hazards to automobile workers. The modern automobile industries are complicated because of various breakthroughs in technological innovations and based on the nature of operation with hazards of assorted degrees at every stage. This paper aims in identifying the hazards to evaluate and compare the rate of risk. The proposed framework comprises three diverse levels such as the data collection phase, data processing phase and risk prediction phase. In the data collection phase, the data gathered from the automobile manufacturing industry located in Tamil Nadu region is taken for investigation. In the data processing phase, raw data obtained from cameras and sensors are processed and the features are then extracted and selected for prediction purposes. In the risk prediction phase, the risk is predicted and classified into four levels namely level 1 (Extreme risk level), level 2 (High risk level), level 3 (Medium risk level), and level 4 (Low risk level) using deep convolutional neural network-hybrid Aquila optimizer (DCNN-HAO) approach. Regarding the evaluation of the proposed model, few performance measures namely area of under curve (AUC), area under receiving operation characteristics (ROC), false positive rate (FPR) and true positive rate (TPR) are evaluated. The experimental investigations are performed and graphical evaluation revealed that the proposed technique achieves better performances than other techniques. This confirms that the superiority and feasibility of the proposed DCNN-HAO approach that accurately predicts the risk.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Figure 1
Figure 2
Figure 3
Figure 4
Figure 5
Figure 6
Figure 7
Figure 8
Figure 9
Figure 10
Figure 11
Figure 12

Similar content being viewed by others

Abbreviations

N :

aggregate convolution layers count

\(C_{Q}\) :

Qth conv layer

\(\left( {{\rm O}_{D}^{Q} } \right)_{I,J}\) :

conv output

\(\left( {\beta_{D}^{Q} } \right)_{I,J}\) :

bias function

\(\left( {{\rm H}_{D,\,P}^{Q} } \right)_{I,J}\) :

conv layer weight

\(K_{1}^{E\, - \,1}\) :

previous layer features

\(*\) :

convolution operator

\(F\,\left( {} \right)\) :

activation function with respect to Qth layer

\(R_{P}^{Q}\) :

output of the FC layer

\(W_{D,\,E,\,I,\,J}^{Q}\) :

weight associated with I and J of Pth feature map in Q-1th layer

\(Z\) :

current candidate solution

\(Z_{J}\) :

position of decision variables

D and N :

dimension size and total number of candidate solution

\(U_{K}^{B} \,and\,\,L_{K}^{B}\) :

upper and lower boundaries

\(Z_{1} (t + 1)\) :

solution of succeeding iteration t generated by first searching technique \(Z_{1}\)

\(Z_{best} (t)\) :

best solution

\(\Re\) :

random number ranges from 0,1

t and T :

current and total iterations

\(Z_{Mean} (t)\) :

mean value of the current solution

\(Z_{2} (t + 1)\) :

succeeding iteration t generated by the second searching technique \(Z_{2}\)

\(Z_{\Re } (t)\) :

random solution ranging from 1 to N

\(L(d)\) :

levy distribution function

\(\alpha\) :

constant with a fixed value of 1.5

\(I_{1}\) :

integer number and for a certain number of search cycles

\(P\) :

size of the population

\(\psi\) :

control strategy

\(N_{G}^{J}\) :

new solution generated in the second step

\(T_{P}\) :

true positive

\(T_{N}\) :

true negative

\(F_{P}\) :

false positive

\(F_{N}\) :

false negative

References

  1. Liu R, Liu Z, Liu H C and Shi H 2021 An improved alternative queuing method for occupational health and safety risk assessment and its application to construction excavation. Automation in Construction 126: 103672

    Article  Google Scholar 

  2. Lin S S, Shen S L, Zhou A and Xu Y S 2021 Novel model for risk identification during karst excavation. Reliability Engineering & System Safety 209: 107435

    Article  Google Scholar 

  3. Wang S, Li L P, Cheng S, Hu H, Jin H and Gao S, 2020 Dynamic risk assessment method of tunnel collapse based on attribute interval assessment model and application. Polish Journal of Environmental Studies 29(5): 3853–3864

    Article  Google Scholar 

  4. Wang X, Li S, Xu Z, Hu J, Pan D and Xue Y 2019 Risk assessment of water inrush in karst tunnels excavation based on normal cloud model. Bulletin of Engineering Geology and the Environment 78(5): 3783–3798

    Article  Google Scholar 

  5. Wu J H, Wei W, Zhang L, Wang J, Damaševičius R, Li J and Wang M et al. 2019 Risk assessment of hypertension in steel workers based on LVQ and Fisher-SVM deep excavation. Ieee Access 7: 23109–23119

    Article  Google Scholar 

  6. Cui Y, Quddus N and Mashuga C V 2020 Bayesian network and game theory risk assessment model for third-party damage to oil and gas pipelines. Process Safety and Environmental Protection 134: 178–188

    Article  Google Scholar 

  7. Lee P C, Zheng L L, Lo T P and Long D B 2020 A risk management system for deep excavation based on BIM-3DGIS framework and optimized grey Verhulst model. KSCE Journal of Civil Engineering 24(3): 715–726

    Article  Google Scholar 

  8. McQuillan A, Canbulat I, Payne D and Oh J 2018 New risk assessment methodology for coal mine excavated slopes. International Journal of Mining Science and Technology 28(4): 583–592

    Article  Google Scholar 

  9. Valipour A, Yahaya N, Md Noor N, Antuchevičienė J and Tamošaitienė J 2017 Hybrid SWARA-COPRAS method for risk assessment in deep foundation excavation project: An Iranian case study. Journal of Civil Engineering and Management 23(4): 524–532

    Article  Google Scholar 

  10. Sundararaj V and Selvi M 2021 Opposition grasshopper optimizer based multimedia data distribution using user evaluation strategy. Multimedia Tools and Applications 80(19): 29875–29891

    Article  Google Scholar 

  11. Vinu S, Anoop V, Dixit P, Arjaria A, Chourasia U, Bhambri P, MR R and Sundararaj R, 2020 CCGPA-MPPT: Cauchy preferential crossover-based global pollination algorithm for MPPT in photovoltaic system. Progress in Photovoltaics: Research and Applications 28(11): 1128–1145

    Article  Google Scholar 

  12. Momeni E, Poormoosavian M, Tehrani H S and Fakher A 2021 Reliability analysis and risk assessment of deep excavations using random-set finite element method and event tree technique. Transportation Geotechnics 29: 100560

    Article  Google Scholar 

  13. Liang X, Qi T, Jin Z, Qin S and Chen P 2020 Risk Assessment System Based on Fuzzy Composite Evaluation and a Backpropagation Neural Network for a Shield Tunnel Crossing under a River. Advances in Civil Engineering 2020

  14. Pham B T, Khosravi K and Prakash I 2017 Application and comparison of decision tree-based machine learning methods in landside susceptibility assessment at Pauri Garhwal Area, Uttarakhand, India. Environmental Processes 4(3): 711–730

    Article  Google Scholar 

  15. Kuo Y C and Lu S T 2013 Using fuzzy multiple criteria decision making approach to enhance risk assessment for metropolitan automobile projects. International Journal of Project Management 31(4): 602–614

    Article  Google Scholar 

  16. Lin S S, Shen S L, Zhou A and Xu Y S 2021 Risk assessment and management of excavation system based on fuzzy set theory and machine learning methods. Automation in Construction 122: 103490

    Article  Google Scholar 

  17. Zhou Y, Si L, Zhou C and Luo H 2019 Intelligent approach based on random forest for safety risk prediction of deep foundation pit in subway stations. Journal of Computing in Civil Engineering 33(1): 05018004

    Article  Google Scholar 

  18. Krechowicz M and Krechowicz A 2021 Risk Assessment in Energy Infrastructure Installations by Horizontal Directional Drilling Using Machine Learning. Energies 14(2): 289

    Article  Google Scholar 

  19. Ou G Z, Jiao Y Y, Zhang G H, Zou J P, Tan F and Zhang W S Collapse risk assessment of deep-buried tunnel during construction and its application. Tunnelling and Underground Space Technology. 115: 104019

  20. Sohail A, Khan A, Wahab N, Zameer A and Khan S 2021 A multi-phase deep CNN based mitosis detection framework for breast cancer histopathological images. Scientific Reports 11(1): 1–18

    Article  Google Scholar 

  21. Jha K K and Dutta H S 2019 Mutual information based hybrid model and deep learning for acute lymphocytic leukemia detection in single cell blood smear images. Computer methods and programs in biomedicine 179: 104987

    Article  Google Scholar 

  22. Abualigah L, Yousri D, Abd Elaziz M, Ewees A A, Al-qaness M A and Gandomi A H 2021 Aquila Optimizer: A novel meta-heuristic optimization Algorithm. Computers & Industrial Engineering 157: 107250

    Article  Google Scholar 

  23. Liu Y, Shi Y, Chen H, Heidari A A, Gui W, Wang M, Chen H and Li C 2021 Chaos-assisted multi-population Salp swarm algorithms: Framework and case studies. Expert Systems with Applications 168: 114369

    Article  Google Scholar 

  24. Dey P, Chaulya S K and Kumar S 2021 Hybrid CNN-LSTM and IoT-based coal mine hazards monitoring and prediction system. Process Safety and Environmental Protection

  25. Unnikrishnan P, Kumar D K, PoosapadiArjunan S, Kumar H, Mitchell P and Kawasaki R 2016 Development of health parameter model for risk prediction of CVD using SVM. Computational and mathematical methods in medicine 2016

Download references

Author information

Authors and Affiliations

  1. Department of Mechanical Engineering, Sri Eshwar College of Engineering, Coimbatore, India

    Anbarasu Jaganathan & Karthikeyan Mathesan

Authors
  1. Anbarasu Jaganathan
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Karthikeyan Mathesan
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Anbarasu Jaganathan.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Jaganathan, A., Mathesan, K. Risk prediction model and classification of various hazards in automobile industry using HAO based deep CNN. Sādhanā 47, 165 (2022). https://doi.org/10.1007/s12046-022-01928-w

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s12046-022-01928-w

Keywords

Search

Navigation