Beijing University of Posts and Telecommunications

About: Beijing University of Posts and Telecommunications is a education organization based out in Beijing, Beijing, China. It is known for research contribution in the topics: MIMO & Quality of service. The organization has 39576 authors who have published 41525 publications receiving 403759 citations. The organization is also known as: BUPT.

An improved discrete immune optimization algorithm based on PSO for QoS-driven web service composition

Abstract: An improved discrete immune optimization algorithm based on particle swarm optimization (IDIPSO) is proposed for Quality of Service (QoS)-driven web service composition with global QoS constraints. A series of effective strategies are presented for this problem, which include an improved local best first strategy based on mathematical analysis for candidate service selection, a perturbing global best strategy along the global best particle. The improved local best first strategy has equivalent effects on the local fitness of a candidate service and the fitness of a composite web service. Empirical comparisons with recently proposed algorithms on various scales of composite web service instances with global QoS constraints indicate that IDIPSO is highly competitive in terms of powerful searching capability, high stability and well trade-off between population diversity and selection pressure, especially when the size of the composite web service problem is large.

The Role of Data Analysis in the Development of Intelligent Energy Networks

Abstract: Data analysis plays an important role in the development of intelligent energy networks (IENs). This article reviews and discusses the application of data analysis methods for energy big data. The installation of smart energy meters has provided a huge volume of data at different time resolutions, suggesting data analysis is required for clustering, demand forecasting, energy generation optimization, energy pricing, monitoring and diagnostics. The currently adopted data analysis technologies for IENs include pattern recognition, machine learning, data mining, statistics methods, and so on. However, existing methods for data analysis cannot fully meet the requirements for processing the big data produced by IENs, therefore more comprehensive data analysis methods are needed to handle the increasing amount of data and to mine more valuable information.

Noisy Softmax: Improving the Generalization Ability of DCNN via Postponing the Early Softmax Saturation

Abstract: Over the past few years, softmax and SGD have become a commonly used component and the default training strategy in CNN frameworks, respectively. However, when optimizing CNNs with SGD, the saturation behavior behind softmax always gives us an illusion of training well and then is omitted. In this paper, we first emphasize that the early saturation behavior of softmax will impede the exploration of SGD, which sometimes is a reason for model converging at a bad local-minima, then propose Noisy Softmax to mitigating this early saturation issue by injecting annealed noise in softmax during each iteration. This operation based on noise injection aims at postponing the early saturation and further bringing continuous gradients propagation so as to significantly encourage SGD solver to be more exploratory and help to find a better local-minima. This paper empirically verifies the superiority of the early softmax desaturation, and our method indeed improves the generalization ability of CNN model by regularization. We experimentally find that this early desaturation helps optimization in many tasks, yielding state-of-the-art or competitive results on several popular benchmark datasets.