Göz takibi ve sanal gerçeklik teknolojileri ile şantiyelerde tehlike farketme yeteneği ölçümü.


Tezin Türü: Yüksek Lisans

Tezin Yürütüldüğü Kurum: Orta Doğu Teknik Üniversitesi, Türkiye

Tezin Onay Tarihi: 2019

Öğrenci: Bekir Enes Özel

Danışman: MEHMET KORAY PEKERİÇLİ

Özet:

Hazard recognition is considered as one of the major elements of construction site safety; however, empirical studies about hazard recognition capabilities of construction workers are limited due to nature of construction sites and difficulty of measuring this skill. This study suggests usage of immersive virtual reality systems, eye tracking, and game technologies to overcome this difficulty. In this scope; a virtual construction site with hazardous situations was designed and used in experiments, via these technologies. In these experiments, effects of levels of formal education and work experience on hazard recognition rate and speed were tested. The results show that level of education has a significant effect on hazard recognition performance. Both recognition rate (p=0.000058) and speed (p=0.021) are significantly better for more educated group of workers. Moreover, the difference in recognition rate is mostly caused by the hazards which were seen but unrecognized by the subjects. On the other hand, experience does not affect hazard recognition performance. Neither recognition rate nor recognition speed is different among the groups. However, the ratio of the unseen hazards is significantly higher (p=0.004) for more experienced group of workers. Additionally, results are also analyzed according to each hazard individually. The contributions of this study are on two fronts: Firstly, the results obtained would broaden the knowledge on hazard recognition behavior and they could help developing better and more personalized safety management and training strategies. Secondly, the methodology suggested in this study provides a practical, ethical, and feasible way of conducting safety research.