# Prediction of Run-Off Road Crash Severity in South Korea’s Highway through Tree Augmented Naïve Bayes Learning

^{1}

^{2}

^{3}

^{4}

^{*}

## Abstract

**:**

## 1. Introduction

## 2. Related Work

## 3. Data Preparation

#### 3.1. Target of Data Collection

#### 3.2. Road Segmentation for Data Collection

#### 3.3. Data Collection Method

#### 3.3.1. Traffic Accident Data

- Fatal accident: Death within 30 days of the accident
- Serious accident: Injuries that require treatment for more than three weeks due to a traffic accident
- Slight accident: Injuries that require treatment for the period between five days or longer and less than three weeks due to a traffic accident

#### 3.3.2. Data on Fixed Objects and Road Geometry

#### 3.3.3. Traffic Condition Data

## 4. Methodology for Model Construction

#### 4.1. Type of Learning Method Based on a Baysian Network

_{1}, …, X

_{n}in the data set, whereas the arcs indicate direct dependencies between the variables. The graph G then encodes the independence relationships in the domain under investigation. The first task when learning a Bayesian network is to find the structure G of the network. G is estimated through iterative structural design learning. The second part, D, represents the probability distribution. In the probability distribution, ${x}_{i}$, the value of the variable ${X}_{i}$, which indicates the parameter in the form of ${D}_{{X}_{i}}|={P}_{B}\left({x}_{i}{\displaystyle \prod}{X}_{i}\right)$, can be given when the combination of the variable ${X}_{i}$ and the direct parameter variable $\prod}{X}_{i$ is given, where $\prod}{X}_{i$ represents the set of direct parents of the variable ${X}_{i}$ in G. Thus, a joint distribution is obtained as follows:

#### 4.2. TAN Learning Method for RORC Severity Prediction

#### 4.2.1. Reasons for TAN Learning Application

#### 4.2.2. TAN Learning Procedure

_{j}provides about X

_{i}(and vice versa) when the value of C is known:

- (i)
- Compute ${I}_{P}$ between each pair of severity impact variables.
- (ii)
- Create a maximum weighted spanning tree.
- (iii)
- The resulting undirected tree is transformed to a directed tree by choosing a root variable from the attribute variables and setting the direction of all edges to be outward from it.
- (iv)
- Construct a TAN model by adding a vertex labeled by the class variable C and adding an arc from C to each ${X}_{i}$.
- (v)
- Estimate the conditional probability of each variable/node through a gradient descent approach [22].

## 5. Results and Verification

#### 5.1. Model Structure

#### 5.2. Modeling Result

#### 5.3. Model Verification

#### 5.3.1. Validation through Comparison between Measured Values and Predicted Values Using the Confusion Matrix

#### 5.3.2. Exploration of Prediction Power Using Receiver Operating Characteristic (ROC) Curve

## 6. Discussion

#### 6.1. Calculation of RORC Severity Change Threshold

#### 6.2. Result of Threshold Calculation

#### 6.2.1. Road Geometry

#### 6.2.2. Curve Type of Road Variable

- (1)
- In the schematic diagram of the TAN structure, the compound curve is linked as a variable that is correlated with the radius of the curve and the vertical slope.
- (2)
- The effect of the vertical slope is greater than that of the radius of the curve.
- (3)
- The roads with compound curves involve a high proportion of serious accidents.
- (4)
- Because the reverse and continuous curves are greatly affected by the radius of the curve, a result similar to the threshold calculation result of the radius of the curve is obtained.
- (5)
- Most sections with reverse and continuous curves have a small radius of the curve, which reduces the driving speed. This subsequently causes a decrease in the probability of fatal accidents and affects only serious accidents.

#### 6.2.3. Roadside Fixed Object Variable

## 7. Conclusions and Outlook

## Author Contributions

## Funding

## Institutional Review Board Statement

## Informed Consent Statement

## Data Availability Statement

## Conflicts of Interest

## References

- LeRoy, A.A.; Morse, M.L.; Iatrogen, L.L.C. Multiple Medications and Vehicle Crashes: Analysis of Databases; National Highway Traffic Safety Administration: Washington, DC, USA, 2008; pp. 117–129.
- Liu, C.; Subramanian, R. Factors Related to Fatal Single-Vehicle Run-Off-Road Crashes; National Highway Traffic Safety Administration: Washington, DC, USA, 2008; pp. 71–80.
- Alruwaished, A.F. Characteristics of Drivers Who Cause Run-Off-Road-Crashes on Ohio Roadways. Ph.D. Thesis, University of Dayton, Dayton, OH, USA, August 2013. [Google Scholar]
- Chen, F.; Chen, S. Injury severities of truck drivers in single- and multivehicle accidents on rural highways. Accid. Anal. Prev.
**2011**, 43, 1677–1688. [Google Scholar] [CrossRef] [PubMed] - Xie, Y.C.; Zhao, K.G.; Huynh, N. Analysis of driver injury severity in rural single-vehicle crashes. Accid. Anal. Prev.
**2012**, 47, 36–44. [Google Scholar] [CrossRef] - Roque, C.; Jalayer, M. Improving roadside design policies for safety enhancement using hazard-based duration modeling. Accid. Anal. Prev.
**2018**, 120, 165–173. [Google Scholar] [CrossRef] - Shaheed, M.S.; Gkritza, K. A latent class analysis of single-vehicle motorcycle crash severity outcomes. Anal. Method Accid.
**2014**, 2, 30–38. [Google Scholar] [CrossRef] - McLaughlin, S.B.; Hankey, J.M.; Klauer, S.G.; Dingus, T.A. Contributing Factors to Run-Off-Road Crashes and Near-Crashes; National Highway Traffic Safety: Washington, DC, USA, 2009; pp. 59–71.
- Lord, D.; Brewer, M.A.; Fitzpatrick, K. Analysis of Roadway Departure Crashes on Two Lane Rural Roads in Texas; Texas Transportation Institute: College Station, TX, USA, 2011; pp. 143–150.
- Roque, C.; Moura, F.; Cardoso, J.L. Detecting unforgiving roadside contributors through the severity analysis of ran-off-road crashes. Accid. Anal. Prev.
**2015**, 80, 262–273. [Google Scholar] [CrossRef] - Hussein, M.H.A.; Sayed, T.; Ismail, K.; Espen, A.V. Calibrating road design guides using risk-based reliability analysis. J. Transp. Eng.
**2013**, 140, 04014041. [Google Scholar] [CrossRef] - Li, H.; Pang, F.; Chen, H.; Du, Y. Vibration analysis of functionally graded porous cylindrical shell with arbitrary boundary restraints by using a semi analytical method. Compos. Part B Eng.
**2019**, 164, 249–264. [Google Scholar] [CrossRef] - Amiria, A.M.; Sadrib, A.; Nadimic, N.; Shamsd, M. A comparison between Artificial Neural Network and Hybrid Intelligent Genetic Algorithm in predicting the severity of fixed object crashes among elderly drivers. Accid. Anal. Prev.
**2020**, 138, 105468. [Google Scholar] [CrossRef] - Good, M.C.; Fox, J.C.; Joubert, P.N. An in-depth study of accidents involving collisions with utility poles. Accid. Anal. Prev.
**1987**, 19, 397–413. [Google Scholar] [CrossRef] - Ju, M.Y. Probit and ordered probit analysis and its application. J. Gov. Stud.
**2000**, 6, 24–49. [Google Scholar] - Park, J.H.; Yun, D.G. Analysis of road cross section component affecting traffic accident severity on national highway. J. Korean Soc. Saf.
**2017**, 32, 143–149. [Google Scholar] - Hamdar, S.H.; Mahmassani, H.S.; Chen, R.B. Aggressiveness propensity index for driving behavior at signalized intersectiions. Accid. Anal. Prev.
**2008**, 50, 315–326. [Google Scholar] [CrossRef] [PubMed] - Rundmo, T.; Hale, A.R. Manager’s attitudes towards safety and accident prevention. Saf. Sci.
**2003**, 41, 557–574. [Google Scholar] [CrossRef] - De Oña, J.; Mujalli, R.O.; Mujalli, R.O.; Calvo, F.J. Analysis of traffic accident injury severity on Spanish rural highways using Bayesian networks. Accid. Anal. Prev.
**2011**, 43, 402–411. [Google Scholar] [CrossRef] [PubMed] - Cong, C.; Guohui, Z.; Tarefder, R.; Jianming, M.; Heng, W.; Hongzhi, G. A multinomial logit model-Bayesian network hybrid approach for driver injury severity analyses in rear-end crashes. Accid. Anal. Prev.
**2015**, 80, 76–88. [Google Scholar] - Hänninen, M. Bayesian networks for maritime traffic accident prevention: Benefits and challenges. Accid. Anal. Prev.
**2014**, 73, 305–312. [Google Scholar] [CrossRef] - Yang, Z.S.; Yang, Z.L.; Yin, J. Realising advanced risk-based port state control inspection using data-driven Bayesian networks. Transp. Res. Part A Pol. Pract.
**2018**, 110, 38–56. [Google Scholar] [CrossRef] - Castaldo, F.; Palmieri, F.A.N.; Regazzoni, C.S. Bayesian analysis of behaviors and interactions for situation awareness in transportation systems. IEEE Trans. Intell. Transp. Syst.
**2016**, 17, 313–322. [Google Scholar] [CrossRef] - Fan, S.; Blanco-Davis, E.; Yang, Z.; Zhang, J.; Yan, X. Incorporation of human factors into maritime accident analysis using a data-driven Bayesian network. Reliab. Eng. Syst. Saf.
**2020**, 203, 107070. [Google Scholar] [CrossRef] - Kim, J.M.; Kim, D.S.; Ahn, J.H. Research on the Establishment of Reinforcement Plans for Vehicle Protection Fences on National Roads; Ministry of Land, Infrastructure, and Transport: Sejong, Korea, 2014; pp. 151–170.
- Park, M.; Lee, D. A random parameter negative binomial model for signalized intersection accidents in Seoul, Korea. Int. J. Inj. Control. Saf. Promot.
**2021**, 28, 201–207. [Google Scholar] [CrossRef] - Lee, J.; Mannering, F. Impact of roadside features on the frequency and severity of run-off-roadway accidents: An empirical analysis. Accid. Anal. Prev.
**2002**, 34, 149–161. [Google Scholar] [CrossRef] - Al-Bdairi, N.S.S.; Hernandez, S. Comparison of contributing factors for injury severity of large truck drivers in run-off-road crashes on rural and urban roadways: Accounting for unobserved heterogeneity. Int. J. Transp. Sci. Technol.
**2020**, 9, 116–127. [Google Scholar] [CrossRef] - Ghadi, M.; Török, Á. A comparative analysis of black spot identification methods and road accident segmentation methods. Accid. Anal. Prev.
**2019**, 128, 1–7. [Google Scholar] [CrossRef] - Cafiso, S.; D’Agostino, C.; Persaud, B. Investigating the influence of segmentation in estimating safety performance functions for roadway sections. In Proceedings of the TRB 92nd Annual Meeting, Washington, DC, USA, 13–17 January 2013; Volume 15. [Google Scholar]
- Koorey, G. Road data aggregation and sectioning considerations for crash analysis. J. Transp. Res. Board
**2009**, 2103, 61–68. [Google Scholar] [CrossRef][Green Version] - Misra, R.; Das, A. Identification of Homogeneous Sections from Road Data. Int. J. Pavement Eng.
**2003**, 4, 229–233. [Google Scholar] [CrossRef] - Cafiso, S.; Graziano, A.D.; Silvestro, G.D.; Cava, G.L.; Persaud, B. Development of comprehensive accident models for two-lane rural highways using exposure, geometry, consistency and context variables. Accid. Anal. Prev.
**2010**, 42, 1072–1079. [Google Scholar] [CrossRef] - Depaire, B.; Wets, G.; Vanhoof, K. Traffic accident segmentation by means of latent class clustering. Accid. Anal. Prev.
**2008**, 40, 1257–1266. [Google Scholar] [CrossRef][Green Version] - Luca, M.R.; Mauro, R.; Lamberti, R.; Dell’Acqua, G. Road safety management using bayesian and cluster analysis. Procedia Soc. Behav. Sci.
**2012**, 54, 1260–1269. [Google Scholar] [CrossRef][Green Version] - Ghadi, M.; Török, Á.; Tánczos, K. Integration of probability and clustering based approaches in the field of black spot identification. Period. Polytech. Civ. Eng.
**2019**, 63, 46–52. [Google Scholar] [CrossRef] - Ministry of Land, Infrastructure, and Transport, Intersection Design Guidelines; MOLIT: Sejong, Korea, 2015; pp. 37–38.
- Baesens, B.G. Bayesian Network Classifiers for Identifying the Slope of the Customer Life Cycle of Longlife Customers. Eur. J. Oper. Res.
**2004**, 156, 508–523. [Google Scholar] [CrossRef][Green Version] - Cheng, J. Comparing bayesian network classifiers. In Proceedings of the 15th Conference on Uncertainty in Artificial Intelligence, Stockholm, Sweden, 30 July–1 August 1999; Morgan Kaufmann Publishers: Burlington, VT, USA, 1999; pp. 101–107. [Google Scholar]
- Langley, P.; Iba, W.; Thompson, K. An analysis of bayesian classifiers. In Proceedings of the Tenth National Conference on Artificial Intelligence, San Jose, CA, USA, 12–16 July 1992; Volume 92, pp. 223–228. [Google Scholar]
- Salzberg, S.L. C4.5: Programs for Machine Learning by J. Ross Quinlan; Morgan Kaufmann Publishers: Baltimore, MD, USA, 1994; pp. 235–240. [Google Scholar]
- Wang, L.K.; Yang, Z.L. Bayesian network modelling and analysis of accident severity in waterborne transportation: A case study in China. Reliab. Eng. Syst. Saf.
**2018**, 180, 277–289. [Google Scholar] [CrossRef] - Friedman, N.; Geiger, D.; Goldszmitd, M. Bayesian network classifiers. Mach. Learn.
**1997**, 29, 131–163. [Google Scholar] [CrossRef][Green Version] - Chow, C.K.; Liu, C.N. Approximating discrete probability distributions with dependence trees. IEEE Trans. Inf. Theory
**1968**, 14, 462–467. [Google Scholar] [CrossRef][Green Version] - Yang, Z.; Yang, Z.; Smith, J.; Robert, B.A.P. Risk analysis of bicycle accidents: A Bayesian approach. Reliab. Eng. Syst. Saf.
**2021**, 209, 107460. [Google Scholar] [CrossRef] - Wegman, F. Analyzing road design risk factors for run-off-road crashes in the Netherlands with crash prediction models. J. Saf. Res.
**2014**, 49, 121.e1-127. [Google Scholar] - Martinez, P.; Mohamed, E.; Mohsen, O.; Mohamed, Y. Comparative study of data mining models for prediction of bridge future conditions. J. Perform. Constr. Facil.
**2020**, 34, 04019108. [Google Scholar] [CrossRef] - Huang, Y.; Pepe, M.S. A parametric ROC model-based approach for evaluating the predictiveness of continuous markers in case-control studies. Biometrics
**2009**, 65, 1133–1144. [Google Scholar] [CrossRef][Green Version] - Hwaton, K.; Heeringen, K. The International Handbook of Suicide and Attempted Suicide; Wiley Online Library: Somerset, NJ, USA, 2000; pp. 335–412. [Google Scholar]
- Kjaerulff, U.B.; Madsen, A.L. Bayesian Networks and Influence Diagrams: A Guide to Construction and Analysis; Springer: New York, NY, USA, 2008; pp. 107–139. [Google Scholar]
- Park, H.C.; Kim, D.K.; Kho, S.Y. Bayesian Network for Freeway Traffic State Prediction. Transp. Res. Rec.
**2018**, 2672, 124–135. [Google Scholar] [CrossRef] - Zegeer, C.V.; Council, F.M. Safety relationships associated with cross-sectional roadway elements. Transp. Res. Rec.
**1995**, 1512, 29–36. [Google Scholar] - Zegeer, C.V.; Michael, J.C. Determination of cost-effective roadway treatments for utility pole accidents. Transp. Res. Rec.
**1982**, 970, 52–64. [Google Scholar] - Ivey, D.; Zegeer, C.V. Utilities and Roadside Safety; Transportation Research Board: Washington, DC, USA, 2012; pp. 1–81. [Google Scholar]
- TAAS. Traffic Accident Analysis System. Available online: http://taas.koroad.co.kr (accessed on 13 January 2022).
- Elmarakbi, A.; Sennah, K.; Samaan, M.; Siriya, P. Crashworthiness of motor vehicle and traffic light pole in frontal collisions. J. Transp. Eng.
**2006**, 132, 722–733. [Google Scholar] [CrossRef]

Category | Average |
---|---|

RORC severity ratio | slight: 41.3%, serious: 43.9%, fatal: 14.8% |

Point of collision ratio | left: 19.7%, right: 80.3% |

Horizontal alignment ratio | straight: 54.7%, curved: 45.3% |

Radius of curve | 116.14 m |

Vertical alignment ration | flat: 69.5%, others: 30.5% |

Vertical slope (absolute value) | 0.93% |

Reverse curve ratio | yes: 4.5%, no: 95.5% |

Continuous curve ratio | yes: 1.8%, no: 98.2% |

Compound curve ratio | yes: 15.2%, no: 84.8% |

Design speed | 62.1 km/h |

Number of entrance/exists (no.) | 1.27 |

Type of fixed objects ration | streetlight: 13.90%, pier: 9.90%, traffic light: 10.30%, utility pole: 23.30%, road sign: 13.00%, others: 29.6% |

Distance between the roadway and the fixed object of collision | 6.14 m |

Density of roadside fixed objects (no./10 m) | 1.29 |

AADT (5-year average) | 17,217.2 vehicle/day |

Road surface condition | dry0: 72.6%, damp: 27.4% |

Daytime/nighttime | nighttime: 48.0%, daytime: 52.0% |

Weekends/weekdays | weekdays: 65.0%, weekends: 35.0% |

Compliance status of minimum radius of curve standard | Compliance: 86.1%, not compliance: 13.9% |

Category | Estimated Probability | Predicted Accident | Actual Accident | ||
---|---|---|---|---|---|

Slight Accident | Serious Accident | Fatal Accident | |||

1 | 48.3% | 40.0% | 11.7% | slight accident | slight accident |

2 | 39.4% | 56.7% | 3.9% | serious accident | serious accident |

3 | 42.2% | 30.3% | 27.5% | serious accident | slight accident |

4 | 43.0% | 55.8% | 1.2% | serious accident | serious accident |

5 | 47.5% | 36.4% | 16.1% | slight accident | slight accident |

6 | 42.2% | 30.3% | 27.5% | slight accident | slight accident |

7 | 42.8% | 47.4% | 9.9% | serious accident | serious accident |

⋮ | ⋮ | ⋮ | ⋮ | ⋮ | ⋮ |

392 | 47.5% | 36.4% | 16.1% | slight accident | slight accident |

393 | 46.8% | 46.4% | 6.8% | slight accident | slight accident |

394 | 35.1% | 50.7% | 14.2% | serious accident | serious accident |

395 | 39.4% | 56.7% | 3.9% | serious accident | serious accident |

396 | 46.8% | 46.4% | 6.8% | slight accident | slight accident |

397 | 48.4% | 48.4% | 3.2% | serious accident | serious accident |

398 | 46.8% | 46.4% | 6.8% | slight accident | slight accident |

399 | 8.3% | 84.5% | 7.2% | serious accident | serious accident |

400 | 48.4% | 45.5% | 60.1% | fatal accident | fatal accident |

401 | 3.2% | 27.8% | 69.0% | fatal accident | fatal accident |

402 | 51.7% | 47.1% | 1.2% | serious accident | slight accident |

403 | 39.2% | 46.5% | 14.3% | serious accident | serious accident |

Prediction | Slight | Serious | Fatal | Total | |
---|---|---|---|---|---|

Measurement | |||||

slight | 13 | 0 | 1 | 14 | |

serious | 1 | 16 | 1 | 18 | |

fatal | 1 | 0 | 7 | 8 | |

Total | 15 | 16 | 9 | 40 |

Prediction | 1 | 0 | Total | |
---|---|---|---|---|

Measurement | ||||

1 | a | c | a + c | |

0 | b | d | b + d | |

Total | a + b | c + d | ||

Prediction power | Sensitivity: a/(a + c) Specificity: d/(b + d) |

Category | Slight | Serious | Fatal | |
---|---|---|---|---|

Vertical slope | ≥4% | −63.8 | 135.7 | 79.1 |

2–4% | 48.6 | −13.4 | −22.5 | |

<2% | 78.5 | −51.1 | −10.2 | |

None | 2.0 | −1.8 | −0.2 | |

Total | 65.3 | 69.4 | 46.2 | |

Average (class = 12) | (65.3 + 69.4 + 46.2)/12 = 15.1 | |||

Radius of curve | ≥500 m | −5.9 | 5.9 | 1.1 |

250–500 m | −4.1 | −11.5 | 20.4 | |

<250 m | 2.0 | 23.0 | −15.2 | |

None | 4.6 | −5.7 | 2.7 | |

Total | −3.4 | 11.7 | 9.1 | |

Average (class = 12) | (−3.4 + 11.7 + 9.1)/12 = 1.5 | |||

Compliance status of minimum radius of curve design criteria | NC | 1.5 | 16.9 | −12.4 |

C | −0.6 | −4.3 | 5.4 | |

Total | 1.0 | 12.6 | −7.0 | |

Average (class = 6) | (1.0 + 12.6 − 7.0)/6 = 1.1 |

Category | Slight | Serious | Fatal | |
---|---|---|---|---|

Compound curve | Y | −20.2 | 20.7 | 2.1 |

N | 7.7 | −7.1 | −0.3 | |

Total | −12.5 | 13.6 | 1.9 | |

Average (class = 6) | (−12.5 + 13.6 + 1.9)/6 = 0.5 | |||

Reverse curve | Y | 1.8 | 21.5 | −14.5 |

N | −0.1 | −1.2 | 1.4 | |

Total | 1.7 | 20.3 | −13.1 | |

Average (class = 6) | (1.7 + 20.3 − 13.1)/6 = 1.5 | |||

Continuous curve | Y | 1.9 | 22.4 | −14.9 |

N | −0.1 | −0.5 | 0.6 | |

Total | 1.9 | 21.9 | −14.4 | |

Average (class = 6) | (1.9 + 21.9 − 14.4)/6 = 1.6 |

Category | Slight | Serious | Fatal | |
---|---|---|---|---|

Distance between the roadway and the fixed object | <3 m | −1.1 | −71.1 | 112.1 |

3–5 m | 14.7 | −23.3 | 11.3 | |

≥5 m | −6.7 | 64.3 | −34.3 | |

Total | 7.0 | −30.1 | 89.1 | |

Average (class = 6) | (7.0 − 30.1 + 89.1)/9 = 7.3 | |||

Density of fixed objects | N > 2 | −53.2 | 2.2 | 75.6 |

1 < N ≤ 2 | −7.7 | −11.7 | 21.6 | |

N ≤ 1 | 38.8 | 23.2 | −36.9 | |

Total | −22.0 | 13.7 | 60.3 | |

Average (class = 6) | (−22.0 + 13.7 + 60.3)/9 = 5.8 | |||

Type of fixed objects | Streetlight | −0.4 | 4.0 | −3.1 |

Pier | −0.3 | 0.5 | −0.2 | |

Traffic light | −0.3 | 1.0 | −0.6 | |

Utility pole | 0.1 | −3.6 | 4.0 | |

Road sign | 0.2 | 1.6 | −1.7 | |

Tree | 0.3 | 0.2 | −0.5 | |

Total | −0.9 | 1.9 | 0.0 | |

Average (class = 18) | (−0.9 + 1.9 − 0.0)/18 = 0.1 |

Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. |

© 2022 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).

## Share and Cite

**MDPI and ACS Style**

Kim, H.; Kim, J.-T.; Shin, S.; Lee, H.; Lim, J.
Prediction of Run-Off Road Crash Severity in South Korea’s Highway through Tree Augmented Naïve Bayes Learning. *Appl. Sci.* **2022**, *12*, 1120.
https://doi.org/10.3390/app12031120

**AMA Style**

Kim H, Kim J-T, Shin S, Lee H, Lim J.
Prediction of Run-Off Road Crash Severity in South Korea’s Highway through Tree Augmented Naïve Bayes Learning. *Applied Sciences*. 2022; 12(3):1120.
https://doi.org/10.3390/app12031120

**Chicago/Turabian Style**

Kim, Hyungkyu, Jin-Tae Kim, Somyoung Shin, Hyerin Lee, and Joonbeom Lim.
2022. "Prediction of Run-Off Road Crash Severity in South Korea’s Highway through Tree Augmented Naïve Bayes Learning" *Applied Sciences* 12, no. 3: 1120.
https://doi.org/10.3390/app12031120