This article proposes an algorithm to recommend apposite ID photos for users by judging the photo of which the facial expression is apposite or not as the ID photo. Microsoft’s Kinect sensor is used for taking photos. Parts of the face, such as eyes, nose, and mouth, are analyzed as explanatory variables for judging face expression. Some body coordinate information such as head and shoulders is used to trim the photos. Neural networks and support vector machines are employed and compared to our proposed method. To achieve accurate results, ten examinees including specialized staff are selected for taking ID photo used for training models. A series of experiments are conducted to examine the validity. As a result, the accuracy of neural networks is better than that of the support vector machine. Furthermore, we analyze and discuss the difference between system results and specialized staffs’ opinions.
Roadworks take place frequently on existing roads in New Zealand. The adverse effects of poor road conditions and reduced road width due to the presence of a work zone on the safety of road users and workers at the work zone have been a matter of concern. Several studies have been conducted to examine the risk factors contributing to the occurrence of road crashes in work zones in different countries. Slow-moving and stopped vehicles near work zones have been found to be the primary cause of crashes and casualties in the work zones. Excessive speed of passing traffic has also been recognized as a crucial factor contributing to work zone related crashes in New Zealand. This study examined the effect of possible risk factors contributing to severe injury and fatality in work zone related crashes in New Zealand. A multinomial logistic regression model was established to determine the association between crash severity and factors such as road environment, vehicle attributes, driver behavior, and crash circumstances, based on the information available on 453 road crashes during the period from 2008 to 2013. The results indicated that the time period, vehicle involvement, and presence of vulnerable road users were the factors that determined the crash severity in work zones. This implies that improvements are required in traffic control and management measures in work zones to enhance road safety in the long run. 相似文献
This paper empirically examines the influences of strategic interdependence and resource complementarity on operational performance and relational performance of Chinese suppliers based on the resource-based view and resource dependence theory. In particular, it analyses the mediating effects of interfirm business process integration and joint teamwork. We apply structural equation modeling to analyze the survey data collected from logistics and supply chain managers, and derive the best model with theoretical foundation and statistical significance. As a result, our work has identified the mediating effects of interfirm business process integration and joint teamwork, and validated the assertion that strategic interdependence and resource complementarity as supply chain resources are fundamental to firm performance. It is stressed that resource capitalization requires interfirm business process integration and joint teamwork to realize the value of supply chain resources. The findings not only contribute to research on interfirm resources and performance, but also have practical implications for operations and supply chain management. 相似文献