A Risk Prediction Framework Based on Self-Organizing Mapping and Just-in-Time-Learning Considering Usability and Interpretability

MA Xiaochi; LU Jian; HUO Zongxin; XIA Xiaohan

doi:10.7652/xjtuxb202405020

您当前的位置：

首页 >

文章列表页 >

A Risk Prediction Framework Based on Self-Organizing Mapping and Just-in-Time-Learning Considering Usability and Interpretability

更新时间：2025-07-28

- A Risk Prediction Framework Based on Self-Organizing Mapping and Just-in-Time-Learning Considering Usability and Interpretability
- Vol. 58, Issue 5, Pages: 212-220(2024)
- 作者机构：
  
  1. 东南大学江苏省城市智能交通重点实验室,南京,211189
  2. 东南大学现代城市交通技术江苏高校协同创新中心,南京,211189
  3. 东南大学交通学院,南京,211189
  4. 南洋理工大学土木与环境工程学院,新加坡,639798
- 作者简介：
- 基金信息：
- DOI：10.7652/xjtuxb202405020
  CLC： U491.3
- Online First：10 May 2024，
  
  Published：2024
- 稿件说明：
移动端阅览
MA Xiaochi, LU Jian, HUO Zongxin, et al. A Risk Prediction Framework Based on Self-Organizing Mapping and Just-in-Time-Learning Considering Usability and Interpretability[J]. 2024, 58(5): 212-220.
DOI：

MA Xiaochi, LU Jian, HUO Zongxin, et al. A Risk Prediction Framework Based on Self-Organizing Mapping and Just-in-Time-Learning Considering Usability and Interpretability[J]. 2024, 58(5): 212-220. DOI： 10.7652/xjtuxb202405020.

摘要

为提高风险预测系统的易用性和可解释性

提出基于自组织映射网络(SOM)改进的即时学习(JITL)风险预测框架。首先

应用SOM对数据样本进行聚类

并对聚类特征进行解释。进而

通过基于聚类结果的样本选择算法构建待测数据的相似样本集

在线上调用作为基学习器的支持向量机(SVM)进行建模并输出风险预测结果。最后

采用一个交通事故数据集对风险模型的性能进行测试

检验其精度、易用性和可解释性。结果表明:采用SOM-JITL策略的SVM模型

受试者工作状况曲线面积指标达到0.720

相比不使用该策略的传统SVM模型提高17.5%

精度较高; SOM-JITL模型构建所需参数调节工作少

具有较好的易用性; 此外

SOM聚类结果准确识别出处于交通拥堵等高风险场景

与现实场景一致

具有可解释性。综上

SOM-JITL策略能有效提高基学习器的性能

达到精度、可解释性和易用性的平衡

有助于以低成本大规模推广风险预测系统。

Abstract

To enhance the usability and interpretability of risk prediction system

a traffic risk prediction framework based on just-in-time learning(JITL)improved via self-organizing mapping(SOM)is proposed. Firstly

SOM is applied for clustering the data samples and interpreting the clustering features. Then

a sample selection algorithm based on clustering results is used to construct a similar sample set for the data to be tested

and the support vector machine(SVM)

which is the base learner

is invoked online to model and output the risk prediction results. Lastly

the model performance is tested using a traffic flow-crash dataset to evaluate interpretability and accuracy. The results show that the area under receiver operating characteristic curve of the SVM model using the SOM-JITL strategy reaches 0.720

which is 17.5% higher than that of the traditional SVM model without the strategy. The SOM-JITL requires less parameter adjustment

and has better usability. In addition

the clustering results of the SOM-JITL accurately identify high-risk scenarios

such as traffic congestion

which is consistent with realistic scenarios and has interpretability. In summary

the SOM-JITL can effectively enhance the performance of the base learner

and endow the model with balance among accuracy

interpretability and usability

facilitating the cost-effective and large-scale deployment of risk prediction systems.

关键词

Keywords

references

NADARAJAH R, YOUNSI T, ROMER E, et al. Prediction models for heart failure in the community: a systematic review and meta-analysis [J]. European Journal of Heart Failure, 2023, 25(10): 1724-1738.

ZELENKOV Y, FEDOROVA E, CHEKRIZOV D. Two-step classification method based on genetic algorithm for bankruptcy forecasting [J]. Expert Systems with Applications, 2017, 88: 393-401.

YU Le, DU Bowen, HU Xiao, et al. Deep spatio-temporal graph convolutional network for traffic accident prediction [J]. Neurocomputing, 2021, 423: 135-147.

HUO Xiaoyan, LENG Junqiang, LUO Lijun, et al. A mixed logit model with mean-variance heterogeneity to investigate factors of crash occurrence [J]. International Journal of Injury Control and Safety Promotion, 2021, 28(3): 301-308.

KAMEL A, SAYED T, FU Chuanyun. Real-time safety analysis using autonomous vehicle data: a Bayesian hierarchical extreme value model [J]. Transportmetrica: B Transport Dynamics, 2023, 11(1): 826-846.

CHEN T K, LIAO H H, CHEN Gengdao, et al. Bankruptcy prediction using machine learning models with the text-based communicative value of annual reports [J]. Expert Systems with Applications, 2023, 233: 120714.

BRITO M P, STEVENSON M, BRAVO C. Subjective machines: Probabilistic risk assessment based on deep learning of soft information [J]. Risk Analysis, 2023, 43(3): 516-529.

KRAFFT T D, ZWEIG K A, KÖNIG P D. How to regulate algorithmic decision-making: a framework of regulatory requirements for different applications [J]. Regulation Governance, 2022, 16(1): 119-136.

KHATTAK A, CHAN P W, CHEN Feng, et al. Interpretable ensemble imbalance learning strategies for the risk assessment of severe-low-level wind shear based on LiDAR and PIREPs [J/OL]. Risk Analysis, 2023[2023-07-12]. https://doi.org/10.1111/risa.14215.

BOSTROM A, DEMUTH J L, WIRZ C D, et al. Trust and trustworthy artificial intelligence: a research agenda for AI in the environmental sciences [J/OL]. Risk Analysis, 2023[2023-07-12]. https://doi.org/10.1111/risa.14245.

MANNERING F, BHAT C R, SHANKAR V, et al. Big data, traditional data and the tradeoffs between prediction and causality in highway-safety analysis [J]. Analytic Methods in Accident Research, 2020, 25: 100113.

GUTIERREZ-OSORIO C, PEDRAZA C. Modern data sources and techniques for analysis and forecast of road accidents: a review [J]. Journal of Traffic and Transportation Engineering(English Edition), 2020, 7(4): 432-446.

杨文臣, 周燕宁, 田毕江, 等. 基于聚类分析和SVM的二级公路交通事故严重度预测 [J]. 中国安全科学学报, 2022, 32(5): 163-169.

YANG Wenchen, ZHOU Yanning, TIAN Bijiang, et al. Traffic accident severity prediction for secondary highways based on cluster analysis and SVM model [J]. China Safety Science Journal, 2022, 32(5): 163-169.

QI Long, LIU Hui, XIONG Qian, et al. Just-in-time-learning based prediction model of BOF endpoint carbon content and temperature via vMF mixture model and weighted extreme learning machine [J]. Computers Chemical Engineering, 2021, 154: 107488.

ZHAO Dan, PAN Tianhong, SHENG Biqi. Just-in-time learning algorithm using the improved similarity index [C]//2016 35th Chinese Control Conference(CCC). Piscataway, NJ, USA: IEEE, 2016: 9065-9068.

WANG Ling, ABDEL-ATY M, LEE J, et al. Analysis of real-time crash risk for expressway ramps using traffic, geometric, trip generation, and socio-demographic predictors [J]. Accident Analysis Prevention, 2019, 122: 378-384.

PARSA A B, MOVAHEDI A, TAGHIPOUR H, et al. Toward safer highways, application of XGBoost and SHAP for real-time accident detection and feature analysis [J]. Accident Analysis Prevention, 2020, 136: 105405.

PARSA A B, TAGHIPOUR H, DERRIBLE S, et al. Real-time accident detection: coping with imbalanced data [J]. Accident Analysis Prevention, 2019, 129: 202-210.

LI Qianwen, YAO Handong, LI Xiaopeng. A matched case-control method to model car-following safety [J]. Transportmetrica: A Transport Science, 2023, 19(3): 2055198.

ZHOU Ping, CHEN Weiqi, YI Chengming, et al. Fast just-in-time-learning recursive multi-output LSSVR for quality prediction and control of multivariable dynamic systems [J]. Engineering Applications of Artificial Intelligence, 2021, 100: 104168.

ZHENG Qikang, XU Chengcheng, LIU Pan, et al. Investigating the predictability of crashes on different freeway segments using the real-time crash risk models [J]. Accident Analysis Prevention, 2021, 159: 106213.

SHI Qi, ABDEL-ATY M. Big data applications in real-time traffic operation and safety monitoring and improvement on urban expressways [J]. Transportation Research: Part C Emerging Technologies, 2015, 58, Part B: 380-394.

YU Rongjie, QUDDUS M, WANG Xuesong, et al. Impact of data aggregation approaches on the relationships between operating speed and traffic safety [J]. Accident Analysis Prevention, 2018, 120: 304-310.

YANG Kui, WANG Xuesong, YU Rongjie. A Bayesian dynamic updating approach for urban expressway real-time crash risk evaluation [J]. Transportation Research: Part C Emerging Technologies, 2018, 96: 192-207.

陈丰, 张婷, 黄雅迪, 等. 越江越海隧道入口段追尾事故风险预测模型研究 [J]. 交通运输系统工程与信息, 2021, 21(6): 167-175.

CHEN Feng, ZHANG Ting, HUANG Yadi, et al. Rear-end crash risk prediction model on entrance section of cross-river and cross-sea tunnels [J]. Journal of Transportation Systems Engineering and Information Technology, 2021, 21(6): 167-175.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Advances in the Application of Machine Learning to Boiling Heat Transfer

Machine Learning-Assisted Optimization of Generalized k-ω Turbulence Model for Transonic Compressor Rotors

Research on Adsorbents for CO2 Capture：From Traditional Design to Machine Learning

Study on the Interpretability of One-Dimensional Convolutional Neural Networks in Mechanical Fault Feature Extraction

Numerical Simulation of the Energy Conversion Process in Thermoacoustic Engines with Different Stack Materials

Related Author

PAVLENKO Alexander Nikolaevich

WANG Qiuwang

SURTAEV Anton Sergeevich

ZHOU Chenjie

BI Xiaolong

TANG Weifeng

CHU Wenxiao

ZHANG Xiawen

Related Institution

MOE Key Laboratory of Thermo-Fluid Science and Engineering，Xi’an Jiaotong University

Kutateladze Institute of Thermophysics，Siberian Branch of the Russian Academy of Sciences

School of Energy and Power Engineering, Xi'an Jiaotong University

西安交通大学能源与动力工程学院，710049，西安School of Energy and Power Engineering, Xi'an Jiaotong University, Xi'an 710049, China

中船（邯郸)派瑞特种气体股份有限公司，056000，河北邯郸Peric Special Gases Co., Ltd., Handan, Hebei 056000, China

⁰