Queuing Network-Model Human Processor Research Articles

Modeling distracted driving behavior considering cognitive processes

The modeling of distracted driving behavior has been studied for many years, however, there remain many distraction phenomena that can not be fully modeled. This study proposes a new method that establishes the model using the queuing network model human processor (QN-MHP) framework. Unlike previous models that only consider distracted-driving-related human factors from a mathematical perspective, the proposed method reflects the information processing in the human brain, and simulates the distracted driver’s cognitive processes based on a model structure supported by physiological and cognitive research evidence. Firstly, a cumulative activation effect model for external stimuli is adopted to mimic the phenomenon that a driver responds only to stimuli above a certain threshold. Then, dual-task queuing and switching mechanisms are modeled to reflect the cognitive resource allocation under distraction. Finally, the driver's action is modeled by the Intelligent Driver Model (IDM). The model is developed for visual distraction auditory distraction separately. 773 distracted car-following events from the Shanghai Naturalistic Driving Study data were used to calibrate and verify the model. Results show that the model parameters are more uniform and reasonable. Meanwhile, the model accuracy has improved by 57% and 66% compared to the two baseline models respectively. Moreover, the model demonstrates its ability to generate critical pre-crash scenarios and estimate the crash rate of distracted driving. The proposed model is expected to contribute to safety research regarding new vehicle technologies and traffic safety analysis.

A Computational Cognitive Model of Driver Response Time for Scheduled Freeway Exiting Takeovers in Conditionally Automated Vehicles.

This study develops a computational model to predict drivers' response time and understand the underlying cognitive mechanism for freeway exiting takeovers in conditionally automated vehicles (AVs). Previous research has modeled drivers' takeover response time in emergency scenarios that demand a quick response. However, existing models may not be applicable for scheduled, non-time-critical takeovers as drivers take longer to resume control when there is no time pressure. A model of driver response time in non-time-critical takeovers is lacking. A computational cognitive model of driver takeover response time is developed based on Queuing Network-Model Human Processor (QN-MHP) architecture. The model quantifies gaze redirection in response to takeover request (ToR), task prioritization, driver situation awareness, and driver trust to address the complexities of drivers' takeover strategies when sufficient time budget exists. Experimental data of a preliminary driving simulator study were used to validate the model. The model accounted for 97% of the experimental takeover response time for freeway exiting. The current model can successfully predict drivers' response time for scheduled, non-time-critical freeway exiting takeovers in conditionally AVs. This model can be applied to the human-machine interface design with respect to ToR lead time for enhancing safe freeway exiting takeovers in conditionally AVs. It also provides a foundation for future modeling work towards an integrated driver model of freeway exiting takeover performance.

Modeling the effects of perceived intuitiveness and urgency of various auditory warnings on driver takeover performance in automated vehicles

Existing driver models mainly account for drivers’ responses to visual cues in manually controlled vehicles. The present study is one of the few attempts to model drivers’ responses to auditory cues in automated vehicles. It developed a mathematical model to quantify the effects of characteristics of auditory cues on drivers’ response to takeover requests in automated vehicles. The current study enhanced queuing network-model human processor (QN-MHP) by modeling the effects of different auditory warnings, including speech, spearcon, and earcon. Different levels of intuitiveness and urgency of each sound were used to estimate the psychological parameters, such as perceived trust and urgency. The model predictions of takeover time were validated via an experimental study using driving simulation with resultant R squares of 0.925 and root-mean-square-error of 73 ms. The developed mathematical model can contribute to modeling the effects of auditory cues and providing design guidelines for standard takeover request warnings for automated vehicles.

Effects of Non-Speech Auditory Cues on Control Transition Behaviors in Semi-Automated Vehicles: Empirical Study, Modeling, and Validation

ABSTRACT In semi-automated vehicles, non-speech sounds have been prevalently used as auditory displays for control transitions since these sounds convey urgency well. However, there are no standards of specifications for warning sounds so that diverse non-speech sounds are being employed. To shed light on this, the effects of different non-speech auditory warnings on driver performance were investigated and quantified through the experimental study and human performance modeling approaches. Twenty-four young drivers drove in the driving simulator and experienced both handover and takeover transitions between manual and automated modes while performing a secondary task. The reaction times for handover and takeover, mental workload, and subjective responses were reported. Overall, a traditional warning sound with many repetitions and an indicator sound with decreasing polarity outperformed and were preferred. Additionally, a mathematical model, using the Queuing Network-Model Human Processor (QN-MHP) framework, was applied to quantify the effects of auditory warnings’ acoustic characteristics on drivers’ reaction times in response to takeover request displays. The acoustic characteristics, including the fundamental frequency, the number of repetitions, and the range of dominant frequencies were utilized in modeling. The model was able to explain 99.7% of the experimental data with a root mean square error (RMSE) of 0.148. The present study can contribute to establishing standards and design guidelines for takeover request displays in semi-automated vehicles.

A computer-aided usability testing tool for in-vehicle infotainment systems

This paper describes the development of a computer-aided engineering (CAE) software toolkit for designers of in-vehicle infotainment systems to predict and benchmark the system usability, such as task completion time, eye glance behaviors, and mental workload. A digital driver model was developed based on the task-independent cognitive architecture of QN-MHP (Queuing Network-Model Human Processor). At the front end of the software a graphical user interface (GUI) was developed that allows designers to create digital mockups of the designs and simulate drivers performing secondary tasks while steering a vehicle. To validate the software outputs, an experiment using human drivers was conducted on a fix-based driving simulator with a radio-tuning task as a test case. Three typical in-vehicle infotainment systems that have the function of radio tuning were investigated (a touch screen, physical buttons, and a knob). The results show that the software was able to generate task completion time, total eyes-off-road time, and mental workload estimates that were similar to the empirical data. The software toolkit has the potential to be a supplemental tool for designers to explore a larger design space and address usability issues at the early design stages with lower cost in time and manpower.

Computational Modeling of Finger Swipe Gestures on Touchscreen

Although swiping (also called flicking) is one of the commonly used touchscreen gestures, few modeling studies have been conducted. In this paper, a computational model that focuses on touchscreen swipe gestures was developed by extending the QN-MHP (Queuing Network-Model Human Processor) architecture. The model assumed that the swiped-route follows a three-dimensional path. To model the finger swipe gesture, an operator (i.e., “ Swipe-with-finger”) for the Queuing Network Cognitive Architecture was developed using an existing regression equation for predicting the finger movement time in 3D space (Cha and Myung, 2013). The model was validated with two corresponding experimental results in the literature. As a result, the swiping times generated by the model were well fit with the human subject data.

Integrating Human Behavior Modeling and Data Mining Techniques to Predict Human Errors in Numerical Typing

Numerical typing errors can lead to serious consequences, but various causes of human errors and the lack of contextual clues in numerical typing make their prediction difficult. Human behavior modeling can predict the general tendency in making errors, while data mining can recognize neurophysiological feedback in detecting cognitive abnormality on a trial-by-trial basis. This study suggests integrating human behavior modeling and data mining to predict human errors because it utilizes both 1) top-down inference to transform interactions between task characteristics and conditions into a general inclination of an average operator to make errors and 2) bottom-up analysis in parsing psychophysiological measurements into an individual's likelihood of making errors on a trial-by-trial basis. Real-time electroencephalograph (EEG) features collected in a numerical typing experiment and modeling features produced by an enhanced human behavior model (queuing network model human processor) were combined to improve error classification performance by a linear discriminant analysis (LDA) classifier. Integrating EEG and modeling features improved the results of LDA classification by 28.3% in keenness (d') and by 10.7% in the area under ROC curve (AUC) from that of using EEG only; it also outperformed the other three benchmarking scenarios: using behaviors only, using apparent task features, and using task features plus trial information. The AUC was significantly increased from using EEG along only if EEG + Model features were used.

Modeling the Effect of Loudness and Semantics of Speech Warnings on Human Performances

The quantitative prediction and understanding of human performances in the responses to speech warnings is an essential component to improve warning effectiveness. Queuing network-model human processor (QN-MHP), as a computational architecture, enables researchers to model dual-task information processing. The current study enhanced QN-MHP by modelling the effect of loudness and semantics on human responses to speech warning messages. The model predictions of crash rate were validated with two empirical studies in collision warning systems with resultant R squares of 0.73 and 0.77, respectively. The developed mathematical model could be further utilized in optimizing the design of speech warnings to achieve most safety benefits.

Computer-Aided Usability Evaluation of In-Vehicle Infotainment Systems

This paper reports the development of a computer-aided engineering (CAE) software for human machine interface (HMI) designers to predict and benchmark the usability of in-vehicle infotainment systems. At the front end of the software a graphic user interface (GUI) was developed that allows HMI designers to create digital mockups of designs and setup the tasks for simulation. At the back end a digital driver was created for simulating the driver cognition and performance based on the cognitive architecture of QN-MHP (Queuing Network-Model Human Processor). The software is able to simulate a driver performing in-vehicle secondary tasks (e.g., tuning radios) while steering a vehicle, make quantitative predictions of the driver’s task performance and workload. To validate the software outputs, an experiment was conducted on a driving simulator with two typical in-vehicle infotainment systems (a physical panel and a touch screen), and a radio tuning task was used as a test case. The results show that the software is able to generate task performance and workload estimates that are similar to the empirical data from human participants.

Integrating Behavior Modeling with Data Mining to Improve Human Error Prediction in Numerical Data Entry

Human errors in numerical data entry can lead to serious consequence but it is difficult to predict those errors because mechanisms of human errors vary and no contextual clues are available. This study suggests integrating human behavior modeling and data mining as an advanced method to predict human errors. Human behavior modeling utilized top-down inference to transform interactions between task characteristics and conditions into general inclination of an average operator to make errors, while data mining parsed psychophysiological measurements into individual’s likeliness of making errors on a trial-by-trial basis through bottom-up analysis. Specifically, an enhanced Queuing Network-Model Human Processor (QN-MHP) generated modeling features to be combined with real-time EEG features that were collected in a realistic numerical typing experiment, and potential errors were predicted by detecting error-associated features by linear discriminant analysis (LDA) classifiers before responses. The detection could be made as early as 300 milliseconds beforehand, and the results showed that integration improved the LDA classifiers’ performance by 31.7% in keenness ( d') and by 12.5 % in area under ROC curve (AUC) from that of using EEG only. The integration may help implement future adaptive augmented system to prevent cognitive breakdown by determining appropriate automation/augmentation levels.

Mathematically modelling the effects of pacing, finger strategies and urgency on numerical typing performance with queuing network model human processor

Numerical typing is an important perceptual-motor task whose performance may vary with different pacing, finger strategies and urgency of situations. Queuing network-model human processor (QN-MHP), a computational architecture, allows performance of perceptual-motor tasks to be modelled mathematically. The current study enhanced QN-MHP with a top-down control mechanism, a close-loop movement control and a finger-related motor control mechanism to account for task interference, endpoint reduction, and force deficit, respectively. The model also incorporated neuromotor noise theory to quantify endpoint variability in typing. The model predictions of typing speed and accuracy were validated with Lin and Wu's (2011) experimental results. The resultant root-mean-squared errors were 3.68% with a correlation of 95.55% for response time, and 35.10% with a correlation of 96.52% for typing accuracy. The model can be applied to provide optimal speech rates for voice synthesis and keyboard designs in different numerical typing situations. Practitioner Summary: An enhanced QN-MHP model was proposed in the study to mathematically account for the effects of pacing, finger strategies and internalised urgency on numerical typing performance. The model can be used to provide optimal pacing for voice synthesise systems and suggested optimal numerical keyboard designs under urgency.

Mathematical Modeling of Average Driver Speed Control with the Integration of Queuing Network-Model Human Processor and Rule-Based Decision Field Theory

Quantitative prediction and understanding of driver speed control is important to prevent speeding behavior and design vehicle systems. Speed control is a complex behavior of driver longitudinal vehicle control, involving speed perception, decision making (setting a target speed), motor control (foot movement for pedal control), and vehicle mechanics. However, few of existing models is able to cover all of these important aspects together. To address this problem, the current work built a new mathematical driver speed control model with analytical solutions based on rigorous understanding of human cognitive mechanisms in driving, integrated Queuing Network-Model Human Processor (QN-MHP, which already modeled driver lateral control) structure and Rule-Based Decision Field Theory (RDFT), and offered a relatively complete picture of driver speed control in free-flow driving settings. This new model can provide predictions with regard to driving speed, pedal angle and acceleration for average driver.

Queuing Network Modeling of Transcription Typing

Transcription typing is one of the basic and common activities in human-machine interaction and 34 transcription typing phenomena have been discovered involving many aspects of human performance including interkey time, typing units and spans, typing errors, concurrent task performance, eye movements, and skill effects. Based on the queuing network theory of human performance [Liu 1996; 1997] and current discoveries in cognitive and neural science, this article extends and applies the Queuing Network-Model Human Processor (QN-MHP [Liu et al. 2006]) to model 32 transcription typing phenomena. The queuing network model of transcription typing offers new insights into the mechanisms of cognition and human-computer interaction. Its value in proactive ergonomics design of user interfaces is illustrated and discussed.

Development of an Adaptive Workload Management System using the Queueing Network-Model Human Processor

Drivers overloaded with information from in-vehicle systems significantly increase the chance of vehicle collisions. Developing adaptive workload management systems (AWMS) to dynamically control the rate of messages from these in-vehicle systems is one of the solutions to this problem. However, existing AWMS do not use driver models to estimate workload, and only suppress or redirect messages without changing the rate of messages from the in-vehicle systems. In this work, we propose a prototype of a new adaptive workload management system, the Queuing Network-Model Human Processor (QN-MHP) AWMS, which includes a model of driver workload based on the queueing network theory of human performance that estimates driver workload in different driving situations and a message controller that dynamically controls the rate of messages presented to drivers. Corresponding experimental studies were conducted to validate the potential effectiveness of this system in reducing driver workload and improving driver performance.

The Queuing Network Model Human Processor (QNMHP): An Engineering Approach for Modeling Cognitive Performance

Human performance modeling approaches (HPMAs) that are comprehensive and computational are particularly useful for system development. Current comprehensive approaches have strengths in modeling a person's actions, but lack mathematical foundations that inherently yield information about the time and capacity related performance of the human in the system. This paper proposes a complementary approach called the Queuing Network Model Human Processor (QNMHP) that combines elements of the GOMS/Model Human Processor approach with the mathematical concept of queuing networks. A general queuing network representing the human and methodology for using this network are discussed in light of current efforts to model a steering task.