IDEAS home Printed from https://ideas.repec.org/a/eee/chsofr/v157y2022ics0960077922001977.html
   My bibliography  Save this article

Analysis and visualization of accidents severity based on LightGBM-TPE

Author

Listed:
  • Li, Kun
  • Xu, Haocheng
  • Liu, Xiao

Abstract

In recent years, road traffic accidents, as a leading cause of accidental deaths, have been attracting more and more attention across several disciplines. Notably, the feature study on accidents severity can help exactly identify causality between different risk factors and road accidents, thereby substantially improving road traffic safety. Meanwhile, the application of data visualization to traffic safety investigations is still lacking. Motivated by this, we incorporate the visualization method into machine learning to analyze the traffic accidents data of the UK in 2017. A hybrid algorithm, namely Light Gradient Boosting Machine-Tree-structured Parzen Estimator (LightGBM-TPE) is proposed. Compared with other typical machine learning algorithms, it performs better in terms of the metrics f1,accuracy, recall and precision. Using LightGBM-TPE to calculate the SHAP value of each feature, we find that “Longitude”, “Latitude”, “Hour” and “Day_of_Week” are four risk factors most closely related with accident severity. Visualization for the data further verifies this conclusion. Overall, our research tries to explore an innovative way to understand and evaluate feature importance of road traffic accidents, which can help suggest effective solutions to improve traffic safety.

Suggested Citation

  • Li, Kun & Xu, Haocheng & Liu, Xiao, 2022. "Analysis and visualization of accidents severity based on LightGBM-TPE," Chaos, Solitons & Fractals, Elsevier, vol. 157(C).
    • Handle: RePEc:eee:chsofr:v:157:y:2022:i:c:s0960077922001977
    DOI: 10.1016/j.chaos.2022.111987
    as

    Download full text from publisher

    File URL: http://www.sciencedirect.com/science/article/pii/S0960077922001977
    Download Restriction: Full text for ScienceDirect subscribers only
    File URL: https://libkey.io/10.1016/j.chaos.2022.111987?utm_source=ideas
    LibKey link: if access is restricted and if your library uses this service, LibKey will redirect you to where you can use your library subscription to access this item
    ---><---

    As the access to this document is restricted, you may want to search for a different version of it.

    References listed on IDEAS

    as
    1. Wang, Xiaofeng & Perc, Matjaž, 2021. "Emergence of cooperation in spatial social dilemmas with expulsion," Applied Mathematics and Computation, Elsevier, vol. 402(C).
    2. Szolnoki, Attila & Chen, Xiaojie, 2022. "Tactical cooperation of defectors in a multi-stage public goods game," Chaos, Solitons & Fractals, Elsevier, vol. 155(C).
    3. Shi, Zhenyu & Wei, Wei & Perc, Matjaž & Li, Baifeng & Zheng, Zhiming, 2022. "Coupling group selection and network reciprocity in social dilemmas through multilayer networks," Applied Mathematics and Computation, Elsevier, vol. 418(C).
    4. David G. Rand & Joshua D. Greene & Martin A. Nowak, 2012. "Spontaneous giving and calculated greed," Nature, Nature, vol. 489(7416), pages 427-430, September.
    5. Ji Ang & David Levinson, 2020. "Injury severity prediction from two-vehicle crash mechanisms with machine learning and ensemble models," Working Papers 2022-01, University of Minnesota: Nexus Research Group.
    6. He, Nanrong & Chen, Xiaojie & Szolnoki, Attila, 2019. "Central governance based on monitoring and reporting solves the collective-risk social dilemma," Applied Mathematics and Computation, Elsevier, vol. 347(C), pages 334-341.
    7. Zhen Wang & Marko Jusup & Lei Shi & Joung-Hun Lee & Yoh Iwasa & Stefano Boccaletti, 2018. "Exploiting a cognitive bias promotes cooperation in social dilemma experiments," Nature Communications, Nature, vol. 9(1), pages 1-7, December.
    8. Karl Sigmund & Hannelore De Silva & Arne Traulsen & Christoph Hauert, 2010. "Social learning promotes institutions for governing the commons," Nature, Nature, vol. 466(7308), pages 861-863, August.
    Full references (including those not matched with items on IDEAS)

    Citations

    Citations are extracted by the CitEc Project, subscribe to its RSS feed for this item.
    as


    Cited by:

    1. Ahmed, Abdulaziz & Topuz, Kazim & Moqbel, Murad & Abdulrashid, Ismail, 2024. "What makes accidents severe! explainable analytics framework with parameter optimization," European Journal of Operational Research, Elsevier, vol. 317(2), pages 425-436.
    2. Feng, Fenling & Zhang, Jiaqi & Liu, Chengguang, 2023. "Integrated pricing mechanism of China Railway Express whole-process logistics based on the Stackelberg game," Physica A: Statistical Mechanics and its Applications, Elsevier, vol. 609(C).
    3. Hua Xin & Shiqi Zhang & Yuhlong Lio & Tzong-Ru Tsai, 2024. "Predicting Pump Inspection Cycles for Oil Wells Based on Stacking Ensemble Models," Mathematics, MDPI, vol. 12(14), pages 1-18, July.
    4. Elena Butsenko, 2022. "How Data Mining Can Improve Road Safety in Cities," Social Sciences, MDPI, vol. 11(3), pages 1-11, March.
    5. Shahriari, Zahra & Nazarimehr, Fahimeh & Rajagopal, Karthikeyan & Jafari, Sajad & Perc, Matjaž & Svetec, Milan, 2022. "Cryptocurrency price analysis with ordinal partition networks," Applied Mathematics and Computation, Elsevier, vol. 430(C).
    6. Pérez-Sala, Luis & Curado, Manuel & Tortosa, Leandro & Vicent, Jose F., 2023. "Deep learning model of convolutional neural networks powered by a genetic algorithm for prevention of traffic accidents severity," Chaos, Solitons & Fractals, Elsevier, vol. 169(C).
    7. Mireille Megnidio-Tchoukouegno & Jacob Adedayo Adedeji, 2023. "Machine Learning for Road Traffic Accident Improvement and Environmental Resource Management in the Transportation Sector," Sustainability, MDPI, vol. 15(3), pages 1-19, January.

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Li, Kun & Sun, Xiaodi, 2024. "Study on taxi mode selection dynamics based on evolutionary game theory," Chaos, Solitons & Fractals, Elsevier, vol. 180(C).
    2. Li, Kun & Chen, Zhiyu & Cong, Rui & Zhang, Jianlei & Wei, Zhenlin, 2024. "Simulated dynamics of virus spreading on social networks with various topologies," Applied Mathematics and Computation, Elsevier, vol. 470(C).
    3. Zhang, Boyu & An, Xinmiao & Dong, Yali, 2021. "Conditional cooperator enhances institutional punishment in public goods game," Applied Mathematics and Computation, Elsevier, vol. 390(C).
    4. Wang, Jianwei & Xu, Wenshu & Yu, Fengyuan & He, Jialu & Chen, Wei & Dai, Wenhui, 2024. "Evolution of cooperation under corrupt institutions," Chaos, Solitons & Fractals, Elsevier, vol. 184(C).
    5. Dehghani, Sedigheh & Nazarimehr, Fahimeh & Jafari, Sajad, 2021. "How can cultural conditions affect society’s decisions?," Physica A: Statistical Mechanics and its Applications, Elsevier, vol. 582(C).
    6. Cheng, Yuan & Xue, Yanbo & Chang, Meng, 2020. "Career choice as an extended spatial evolutionary public goods game," Chaos, Solitons & Fractals, Elsevier, vol. 137(C).
    7. Huo, Liang’an & Gu, Jiafeng, 2023. "The influence of individual emotions on the coupled model of unconfirmed information propagation and epidemic spreading in multilayer networks," Physica A: Statistical Mechanics and its Applications, Elsevier, vol. 609(C).
    8. Deng, Zheng-Hong & Wang, Zi-Ren & Wang, Huan-Bo & Huang, Yijie, 2021. "Impact of informers on the evolution of cooperation in prisoner's dilemma game," Chaos, Solitons & Fractals, Elsevier, vol. 149(C).
    9. Ding, Rui & Wang, Xianjia & Zhao, Jinhua & Gu, Cuiling & Wang, Tao, 2023. "The evolution of cooperation in spatial public goods games under a risk-transfer mechanism," Chaos, Solitons & Fractals, Elsevier, vol. 169(C).
    10. Hu, Liwen & He, Nanrong & Weng, Qifeng & Chen, Xiaojie & Perc, Matjaž, 2020. "Rewarding endowments lead to a win-win in the evolution of public cooperation and the accumulation of common resources," Chaos, Solitons & Fractals, Elsevier, vol. 134(C).
    11. Chaoqian Wang & Matjaž Perc & Attila Szolnoki, 2024. "Evolutionary dynamics of any multiplayer game on regular graphs," Nature Communications, Nature, vol. 15(1), pages 1-15, December.
    12. Wu, Yu’e & Zhang, Zhipeng & Yang, Guoli & Liu, Haixin & Zhang, Qingfeng, 2022. "Evolution of cooperation driven by diversity on a double-layer square lattice," Chaos, Solitons & Fractals, Elsevier, vol. 162(C).
    13. Su, Ran & Fang, Zhi-Ming & Hao, Qing-Yi & Sheng, Chun & Fu, Yuan-Jiao, 2024. "The evolution of cooperation affected by unidirectional acceptability mechanism on interdependent networks," Chaos, Solitons & Fractals, Elsevier, vol. 184(C).
    14. Liu, Linjie & Chen, Xiaojie, 2022. "Effects of interconnections among corruption, institutional punishment, and economic factors on the evolution of cooperation," Applied Mathematics and Computation, Elsevier, vol. 425(C).
    15. Luo-Luo Jiang & Matjaž Perc & Attila Szolnoki, 2013. "If Cooperation Is Likely Punish Mildly: Insights from Economic Experiments Based on the Snowdrift Game," PLOS ONE, Public Library of Science, vol. 8(5), pages 1-7, May.
    16. Yang, Han-Xin & Sun, Lei, 2020. "Heterogeneous donation game in geographical small-world networks," Physica A: Statistical Mechanics and its Applications, Elsevier, vol. 540(C).
    17. Li, Dandan & Zhou, Kai & Sun, Mei & Han, Dun, 2023. "Investigating the effectiveness of individuals’ historical memory for the evolution of the prisoner’s dilemma game," Chaos, Solitons & Fractals, Elsevier, vol. 170(C).
    18. Li, Wen-Jing & Chen, Zhi & Jin, Ke-Zhong & Wang, Jun & Yuan, Lin & Gu, Changgui & Jiang, Luo-Luo & Perc, Matjaž, 2022. "Options for mobility and network reciprocity to jointly yield robust cooperation in social dilemmas," Applied Mathematics and Computation, Elsevier, vol. 435(C).
    19. Gao, Liyan & Pan, Qiuhui & He, Mingfeng, 2023. "Impact of peer pressure on the evolution of cooperation in prisoner’s dilemma game," Chaos, Solitons & Fractals, Elsevier, vol. 174(C).
    20. Quan, Ji & Yang, Wenjun & Li, Xia & Wang, Xianjia & Yang, Jian-Bo, 2020. "Social exclusion with dynamic cost on the evolution of cooperation in spatial public goods games," Applied Mathematics and Computation, Elsevier, vol. 372(C).

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:eee:chsofr:v:157:y:2022:i:c:s0960077922001977. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: Thayer, Thomas R. (email available below). General contact details of provider: https://www.journals.elsevier.com/chaos-solitons-and-fractals .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.