In many worksites, there are some tasks that each worker's location will affect the work efficiency, the safety of work, the frequency of mistakes, the physical and mental workload, etc. The relationships between the location of people and the efficiency of the work, etc. have been investigated using personal trajectory data. The data is obtained by people tracking methods. Although the tracking methods have been developed by many researchers over the decades, several issues remain. One of the biggest issues is the lack of capability of individual recognition. Another of the biggest issues is to protect the privacy of the people involved in the tracking. In this paper, first, the existing methods of people tracking are surveyed and the necessary requirements for tracking the people are shown. And then, a new people tracking method using invisible visual markers made of a near infrared LED is proposed. We attempt to recognize multiple people by our method. It is shown that two peoples can be successfully tracked separately in our laboratory, and the privacy of the person is protected.

No abstract

This research applies network structuring theories to the aviation domain and predicts aviation network growth, considering a flight connection between airports as a link between nodes. Our link prediction approach is based on network structure information, and to improve prediction accuracy, it is necessary to estimate the mechanism of aviation network growth. This research critically evaluates the prediction accuracy of two methods: the receiver operating characteristic curve method (ROC) and the logistic regression method. We propose a four-step method to evaluate the relative predictive accuracy among different link prediction methods. A case study of US aviation networks indicated that the ROC method provided better prediction accuracy compared with the logistic regression method. This result suggests that tuning of the prediction distribution and the regression model coefficients can further improve the accuracy of the logistic regression method.

Although mobile eye-trackers have wide measurement range of gaze, and high flexibility, it is difficult to judge what a subject is actually looking at based only on obtained coordinates, due to the influence of head movement. In this paper, a method to compensate for head movements while seeing the large screen with mobile eye-tracker is proposed, through the use of NIR-LED markers embedded on the screen. The head movements are compensated by performing template matching on the images of view camera to detect the actual eye position on the screen. As a result of the experiment, the detection rate of template matching was 98.6%, the average distance between the actual eye position and the corrected eye position was approximately 16 pixels for the projected image (1920 x 1080).