Akira Yoshizawa

Evaluation Model of Cognitive Distraction State Based on Eye Tracking Data Using Neural Networks

Eye tracking reveals a persons state of mind. Thus, representing personal cognitive states using eye tracking leads to objective evaluations of these states, and this can be applied to various fields. In this paper, we propose a model that evaluates the degree of personal distraction based on eye tracking. Moreover, we apply the proposed model to eye tracking for a person driving a car.

Evaluation model of cognitive distraction state based on eye-tracking data using neural networks

Eye tracking reveals a persons state of mind. Thus, representing personal cognitive states using eye tracking leads to objective evaluations of these states, and this can be applied to various fields. In this paper, we propose a model that evaluates the degree of personal distraction based on eye tracking. Moreover, we apply the proposed model to eye tracking for a person driving a car.

Designing a Car-Driver's Cognitive Process Model for considering Degree of Distraction

A distracted state of a driver affects car driving state. The eye tracking can reveal an individuals psychological state. In this paper, we design a drivers cognitive process model by clearly indicating the relations between cognitive states, such as perception and memory, in the process to produce the driving action using the eye tracking data. It is important to consider degree of distraction. Therefore, we consider a cognitive distraction expressed both serially and quantitatively in the model. In this modeling, we utilize a production system framework, and the cognitive distracted state is managed by a module in the production system.

SS3: A design of the cognitive process model for a car driver considering quantitatively expressed distraction

Eye tracking can reveal an individuals state of mind. In this paper, taking into consideration that cognitive distraction that may be expressed both serially and quantitatively, we designed the Drivers Cognitive Process Model by expressing the relationships between cognitive states, such as perception and memory, from eye tracking which we utilized as an input to the driving action which we considered as an output. It is expected that driving state can be expressed accurately by analyzing distraction.

Detecting Cognitive Distraction using Random Forest by Considering Eye Movement Type

Detecting distracted states can be applied to various problems such as danger prevention when driving a car. A cognitive distracted state is one example of a distracted state. It is known that eye movements express cognitive distraction. Eye movements can be classified into several types. In this paper, the authors detect a cognitive distraction using classified eye movement types when applying the Random Forest machine learning algorithm, which uses decision trees. They show the effectiveness of considering eye movement types for detecting cognitive distraction when applying Random Forest. The authors use visual experiments with still images for the detection.

Detecting driver's visual attention area by using vehicle-mounted device

When a car moves on the road, the driver must monitor the driving environment whenever there is a takeover request (TOR), even if automated driving is activated. We examined ways to determine the drivers visual attention area in order to judge whether or not the driver has confirmed safety. We observed the gaze of the subject during driving, tracking not only the head, but also the eye. Considering the drivers load, it is undesirable to use a device attached to the driver to estimate the drivers gaze. When sensing the drivers gaze using equipment installed in the vehicle, there is much noise caused by the equipment vibration. We proposed a new method to estimate the visual attention area and summarized the effect and the problem.

Common-sense approach to avoiding near-miss incidents of pedestrians suddenly crossing narrow roads

This study focused on pedestrians suddenly crossing narrow roads. In order to avoid a near-miss incident while walking, we have used a common-sense reasoning approach to eliminate the risk of pedestrian behavior. We believe that common-sense knowledge is an important approach to safely driving on narrow roads in Japan. There are three types of near-miss incidents based upon past observations. We have demonstrated a new type of support system on an iPhone as a guide to safe driving.

Considering eye movement type when applying random forest to detect cognitive distraction

Eye movements are well known to express cognitive distraction. Detecting cognitive distraction can help to prevent work-related accidents; thus, it is very useful to detect cognitive distraction using eye movements. Eye movements can be classified into various types. In this paper, we apply an identification-based machine learning algorithm considering eye movement types. We apply Random Forest as the machine learning algorithm. We show the effectiveness of considering eye movement types when applying Random Forest to detect cognitive distraction.