Effects of IVIS touchscreen operation tasks on driver’s mental workload based on explainable CatBoost algorithm

Abstract

With the widespread adoption of touchscreen-based in-vehicle information systems (IVIS) in vehicles, a large amount of effective information is displayed on the system, resulting in a significant increase in the frequency of driver interaction with these systems. However, complex operational tasks can lead to elevated mental workload, thereby impacting driving safety. This study aims to investigate the effects of secondary tasks involving IVIS touchscreen operations on driver mental workload. Through driving simulation experiments and survey questionnaires, three car-following scenarios were designed at speed levels of 60, 40, and 20 km/h. A total of 36 participants completed the IVIS secondary task driving simulation tests. Using statistical analysis and interpretable machine learning methods, a driver mental workload prediction model based on the CatBoost algorithm was constructed. Shapley Additive exPlanations (SHAP), partial dependence plot (PDP), and individual conditional expectation (ICE) were used to comprehensively analyze the relationship between important driving behavior characteristics and mental workload. The results of the study indicate that as the number of manual operations of IVIS touchscreen secondary tasks increases, the driver’s mental workload, standard deviation of speed, standard deviation of Lateral offset distance, task completion time, and saccade number correspondingly significant increase (p < 0.05). With the increase of the driver’s mental workload, the speed of the following vehicle decreases (p < 0.01), along with a significant reduction in following distance (p < 0.05). When the number of IVIS secondary task manual operations exceeded 3, the probability of a high mental workload significantly increased. These findings provide a basis for designing safer IVIS, contributing to enhanced driving safety and improved driver experience, holding significant theoretical and practical application value.

Keywords

Traffic safety secondary driving tasks in-vehicle information systems driving behavior mental workload CatBoost

Get full access to this article

View all access options for this article.

References

Classen

Jeghers

Morgan-Daniel

, et al. Smart in-vehicle technologies and older drivers: a scoping review. OTJR Occup Particip Health 2019; 39(2): 97–107.

Krstačić

Žužić

Orehovački

Safety aspects of in-vehicle infotainment systems: a systematic literature review from 2012 to 2023. Electronics 2024; 13(13): 2563.

Yin

, et al. Support vector machines for the identification of real-time driving distraction using in-vehicle information systems. J Transp Saf Secur 2022; 14(2): 232–255.

Gong

Evaluation of driver distraction from in-vehicle information systems: a simulator study of interaction modes and secondary tasks classes on eight production cars. Int J Ind Ergon 2022; 92: 103380.

Quiñones

Rojas

Barraza

User experience heuristics for in-vehicle infotainment systems. Procedia Comput Sci 2024; 237: 725–732.

Xing

Zhong

Yan

, et al. A temporal analysis of crash injury severities in multivehicle crashes involving distracted and non-distracted driving on tollways. Accid Anal Prev 2023; 184: 107008.

Wang

Xue

Yang

, et al. Driving distraction evaluation model of in-vehicle infotainment systems based on driving performance and visual characteristics. Transp Res Rec 2024; 52: 03611981231224750.

Jiménez

Bergasa

Nuevo

, et al. Gaze fixation system for the evaluation of driver distractions induced by IVIS. IEEE Trans Intell Transp Syst 2012; 13(3): 1167–1178.

Charissis

Falah

Lagoo

, et al. Employing emerging technologies to develop and evaluate in-vehicle intelligent systems for driver support: infotainment AR HUD case study. Appl Sci 2021; 11(4): 1397.

10.

Ting

H-C

Chen

S-S

Labille

, et al. (eds.). Intelligent applications design in automotive infortainment systems. In: 2012 IEEE Asia Pacific conference on circuits and systems, 2012. New York: IEEE.

11.

Dingus

Guo

Lee

, et al. Driver crash risk factors and prevalence evaluation using naturalistic driving data. Proc Natl Acad Sci 2016; 113(10): 2636–2641.

12.

Oviedo-Trespalacios

Nandavar

Haworth

How do perceptions of risk and other psychological factors influence the use of in-vehicle information systems (IVIS)?

Transp Res F Traffic Psychol Behav 2019; 67: 113–122.

13.

Peng

Boyle

LN.

Driver’s adaptive glance behavior to in-vehicle information systems. Accid Anal Prev 2015; 85: 93–101.

14.

Liang

Yang

CC.

How are different sources of distraction associated with at-fault crashes among drivers of different age gender groups?

Accid Anal Prev 2022; 165: 106505.

15.

Zhao

, et al. Real-time multistep time-series prediction of driver’s head pose during IVIS secondary tasks for human–machine codriving and distraction warning systems. IEEE Sens J 2022; 22(24): 24364–24379.

16.

Nagy

Kovács

Földesi

, et al. Testing road vehicle user interfaces concerning the driver’s cognitive load. Infrastructures 2023; 8(3): 49.

17.

Chen

Sha

, et al. Effects of interface layout on the usability of in-vehicle information systems and driving safety. Displays 2017; 49: 124–132.

18.

Zhao

, et al. Distraction-level recognition based on stacking ensemble learning for IVIS secondary tasks. Expert Syst Appl 2024; 244: 122849.

19.

Reyes

Lee

JD.

Effects of cognitive load presence and duration on driver eye movements and event detection performance. Transp Res F Traffic Psychol Behav 2008; 11(6): 391–402.

20.

Huang

Peng

A multilayer stacking method base on RFE-SHAP feature selection strategy for recognition of driver’s mental load and emotional state. Expert Syst Appl 2024; 238: 121729.

21.

Causse

Parmentier

FBR

Mouratille

, et al. Busy and confused? High risk of missed alerts in the cockpit: an electrophysiological study. Brain Res 2022; 1793: 148035.

22.

Schirm

Gómez-Vargas

Perusquía-Hernández

, et al. Identification of language-induced mental load from eye behaviors in virtual reality. Sensors 2023; 23(15): 6667.

23.

Peng

Zhao

, et al. Mental workload assessments of aerial photography missions performed by novice unmanned aerial vehicle operators. Work 2023; 75(1): 181–193.

24.

Chi

Cheng

Shih

, et al. Learning rate and subjective mental workload in five truck driving tasks. Ergonomics 2019; 62(3): 391–405.

25.

Yang

Feng

Easa

, et al. Evaluation of mental load of drivers in long highway tunnel based on electroencephalograph. Front Psychol 2021; 12: 646406.

26.

Liang

Qin

Niu

, et al. Psychological load of drivers in entrance zone of road tunnel based on TOPSIS improved factor analysis method. Transp Res Rec 2024; 2678(6): 163–177.

27.

Miyaji

Kawanaka

Oguri

(eds.). Driver’s cognitive distraction detection using physiological features by the AdaBoost. In: 2009 12th international IEEE conference on intelligent transportation systems, 2009. New York: IEEE.

28.

Lyu

Deng

Xie

, et al. A field operational test in China: exploring the effect of an advanced driver assistance system on driving performance and braking behavior. Transp Res F Traffic Psychol Behav 2019; 65: 730–747.

29.

Zhao

Wan

, et al. Research on influence of emotion on novice drivers’ visual characteristics. China Saf Sci J 2022; 32(1): 34.

30.

Horswill

Taylor

Newnam

, et al. Even highly experienced drivers benefit from a brief hazard perception training intervention. Accid Anal Prev 2013; 52: 100–110.

31.

Smith

Horswill

Chambers

, et al. Hazard perception in novice and experienced drivers: the effects of sleepiness. Accid Anal Prev 2009; 41(4): 729–733.

32.

Dorogush

Ershov

Gulin

CatBoost: gradient boosting with categorical features support. arXiv preprint arXiv:1810.11363, 2018.

33.

Lundberg

Lee

S-I

. An unexpected unity among methods for interpreting model predictions. arXiv preprint arXiv:161107478, 2016.

34.

Friedman

JH.

Greedy function approximation: a gradient boosting machine. Ann Stat 2001; 25: 1189–1232.

35.

Goldstein

Kapelner

Bleich

, et al. Peeking inside the black box: visualizing statistical learning with plots of individual conditional expectation. J Comput Graph Stat 2015; 24(1): 44–65.

36.

Chawla

Bowyer

Hall

, et al. SMOTE: synthetic minority over-sampling technique. J Artif Intell Res 2002; 16: 321–357.

37.

Yang

H-H

Peng

Development of an errorable car-following driver model. Veh Syst Dyn 2010; 48(6): 751–773.

38.

Strayer

Cooper

Goethe

, et al. Assessing the visual and cognitive demands of in-vehicle information systems. Cogn Res Princip Implic 2019; 4: 1–22.

39.

Zhang

Liu

Zeng

, et al. Input modality matters: a comparison of touch, speech, and gesture based in-vehicle interaction. Appl Ergon 2023; 108: 103958.

40.

Grahn

Kujala

Impacts of touch screen size, user interface design, and subtask boundaries on in-car task’s visual demand and driver distraction. Int J Hum Comput Stud 2020; 142: 102467.

41.

, et al. Effects of in-vehicle navigation on perceptual responses and driving behaviours of drivers at tunnel entrances: a naturalistic driving study. J Adv Transp 2019; 2019(1): 9468451.

42.

Gong

Tan

, et al. Assessing the driving distraction effect of vehicle HMI displays using data mining techniques. Transp Res F Traffic Psychol Behav 2020; 69: 235–250.

43.

Kochi

Saito

Uchida

, et al. Task difficulty, risk feeling, and safety margin in the determination of driver behavior to prepare for traffic conflicts. Accid Anal Prev 2023; 192: 107284.

44.

Lee

Olsen

Simons-Morton

Eyeglance behavior of novice teen and experienced adult drivers. Transp Res Rec 2006; 1980(1): 57–64.

45.

McCartt

Hellinga

Bratiman

KA.

Cell phones and driving: review of research. Traffic Inj Prev 2006; 7(2): 89–106.