Jiapeng Xiu

Learn More
Cloud computing environment for the efficient resources allocation is an important issue in the field of cloud computing. The resources in Cloud computing application platform are distributed widely and with great diversity. User demands of real-time dynamic change are very difficult to predict accurately. The heuristic ant colony algorithm could be used to(More)
Service Oriented Architecture (SOA) is a business-centric IT architectural approach that promoted integrated and reusable business processes or services. Business Process Execution Language (BPEL) provides an ideal way to composite services within SOA into complete business processes. However, the distributed, heterogeneous and highly volatile nature of web(More)
It is significant to make a short-term power output forecast for the solar photovoltaic power station. On the one hand it helps guarantee power grid security, on the other hand it can increase the efficiency of power generation. This paper designs a high concentrated photovoltaic output power prediction model based on the Fuzzy Clustering and Radial Basis(More)
Inadequate crawling behavior of the crawler will have a very serious impact on the site, so anti crawling mechanism is an important function for the website. Most of the existing anti crawling methods are non real time detection, and the recognition accuracy is low. By analyzing the characteristics of Crawler, a real-time crawler detection method based on(More)
Based on the research of the 863 program “Generation and Applications of Global Products of Essential Land Variable”, the paper proposes an ontology-based production model of parameter products of satellite remote sensing data, which describes the design of satellite ontology, remote sensing data ontology and parameter products ontology. And(More)
In this paper, a face detection algorithm based on AdaBoost algorithm combined with Haar classifier depth cascade about OpenCV is proposed. In order to solve the problem that the training depth of AdaBoost algorithm is not enough and the Haar classifier is not accurate because of the lack of depth cascade classification. Before the face feature extraction,(More)
The power generation of solar power station has close relationship with the weather and environmental factors such as temperature, humidity, irradiation, etc. so prediction of power generation is very important for the intelligent power control. BP neural network is an effective tool to predict task, but too many parameters will cause the BP network(More)
The research in the field of web information extraction technology has made some progress in the past few years, but the extraction performance of the system still needs a lot of improvement. To solve this problem, a new intelligent framework for web information extraction is proposed in this paper. The framework provides a mechanism for automatic(More)
The paper presents an effective method to predict the movie box-office by Neural network algorithm. The core idea is to use past performance of the similar movie to predict a coming movie. Based on the analysis on Chinese film market, we extracted the elements of a movie like actors, director, screenplay, film genre, technical specs, etc. Some elements were(More)
The paper present a framework for video playing and video storage based on Hadoop. Our framework consist of 3 layers. CDN for receiving clinets' requests; CCN for connecting clients and sending data; Hadoop cluster for data storage. This kind of structure helps to provide high availablility services, which could support high concurrent access and play(More)