No abstract

Vehicle detection and classification are very important for analysis of vehicle behavior in intelligent transportation system, urban computing, etc. In this paper, an approach based on convolutional neural networks (CNNs) has been applied for vehicle classification. In order to achieve a more accurate classification, we removed the unrelated background as much as possible based on a trained object detection model. In addition, an unsupervised pretraining approach has been introduced to better initialize CNNs parameters to enhance the classification performance. Through the data enhancement on manual labeled images, we got 2000 labeled images in each category of motorcycle, transporter, passenger, and others, with 1400 samples for training and 600 samples for testing. Then, we got 17395 unlabeled images for layer-wise unsupervised pretraining convolutional layers. A remarkable accuracy of 93.50% is obtained, demonstrating the high classification potential of our approach.

Abstract. Quality (QOS) prediction is one of the most important research topics of workflow management system. In this paper, we propose the SWQ approach to analytically evaluate QOS of workflow systems based on QWF-net, which extends traditional WF-net by associating tasks with exponential response time and exponential TTF (time-tofailure). The comparison between simulative and analytical results in the case study indicates that the SWQ approach achieves satisfactory accuracy. The paper concludes with a comparison between the SWQ approach and other related work.

No abstract