Traditional practical teaching has problems on low reusability, high cost and low collaboration ability. To solve these problems, this paper proposes a solution that is to build and use a novel practical teaching plat...Traditional practical teaching has problems on low reusability, high cost and low collaboration ability. To solve these problems, this paper proposes a solution that is to build and use a novel practical teaching platform based on cloud computing. By utilizing advanced information technology, for example, cloud computing, this solution can present a unified service system providing practical teaching resource management, innovation resource management and knowledge management both inside and outside class. Moreover, an instance implementing the cloud-based practical teaching unified services system, Yun Hai, would be detailedly discussed in this paper. The system deployment, resource configuration and matched practice teaching mode will be presented. Yun Hai is independently developed by State Key Laboratory of Networking and Switching Technology and has been deployed and employed in many institutions. To verify the effectiveness of this teaching platform, we take Data Mining, a representative course of computer science, as an example, and analyze how the system would perform when applied to such course which contains cross-disciplinary knowledges. The practice indicates that this teaching system and practical teaching mode can improve convenience and flexibility on practical teaching resource. This kind of one-stop service can contribute to the overall teaching quality improvement.展开更多
Real-time Fraud Detection has always been a challenging task, especially in financial, insurance, and telecom industries. There are mainly three methods, which are rule set, outlier detection and classification to sol...Real-time Fraud Detection has always been a challenging task, especially in financial, insurance, and telecom industries. There are mainly three methods, which are rule set, outlier detection and classification to solve the problem. But those methods have some drawbacks respectively. To overcome these limitations, we propose a new algorithm UAF (Usage Amount Forecast).Firstly, Manhattan distance is used to measure the similarity between fraudulent instances and normal ones. Secondly, UAF gives real-time score which detects the fraud early and reduces as much economic loss as possible. Experiments on various real-world datasets demonstrate the high potential of UAF for processing real-time data and predicting fraudulent users.展开更多
基金supported by the Projects on International Scientific and Technological Cooperation under the National Key R&D Program(NKP)(No.2016YFE0204500)the National Natural Science Foundation of China under Grants(No.61671081,No.61720106007)+1 种基金the Beijing Natural Science Foundation under Grant(No.4172042)the Fundamental Research Funds for the Central Universities,Beijing University of Posts and Telecommunications 2017 Education and Teaching Reform Project (No.2017JY31)
文摘Traditional practical teaching has problems on low reusability, high cost and low collaboration ability. To solve these problems, this paper proposes a solution that is to build and use a novel practical teaching platform based on cloud computing. By utilizing advanced information technology, for example, cloud computing, this solution can present a unified service system providing practical teaching resource management, innovation resource management and knowledge management both inside and outside class. Moreover, an instance implementing the cloud-based practical teaching unified services system, Yun Hai, would be detailedly discussed in this paper. The system deployment, resource configuration and matched practice teaching mode will be presented. Yun Hai is independently developed by State Key Laboratory of Networking and Switching Technology and has been deployed and employed in many institutions. To verify the effectiveness of this teaching platform, we take Data Mining, a representative course of computer science, as an example, and analyze how the system would perform when applied to such course which contains cross-disciplinary knowledges. The practice indicates that this teaching system and practical teaching mode can improve convenience and flexibility on practical teaching resource. This kind of one-stop service can contribute to the overall teaching quality improvement.
基金This paper is supported by the National Natural Science Foundation of China (61272515), and National Science & Technology Pillar Program (2015BAH03F02).
文摘Real-time Fraud Detection has always been a challenging task, especially in financial, insurance, and telecom industries. There are mainly three methods, which are rule set, outlier detection and classification to solve the problem. But those methods have some drawbacks respectively. To overcome these limitations, we propose a new algorithm UAF (Usage Amount Forecast).Firstly, Manhattan distance is used to measure the similarity between fraudulent instances and normal ones. Secondly, UAF gives real-time score which detects the fraud early and reduces as much economic loss as possible. Experiments on various real-world datasets demonstrate the high potential of UAF for processing real-time data and predicting fraudulent users.
