Institution
Beijing University of Posts and Telecommunications
Education•Beijing, Beijing, China•
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.
Papers published on a yearly basis
Papers
More filters
••
01 Aug 2012TL;DR: 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, which includes an improved local best first strategy based on mathematical analysis for candidate service selection, and a perturbing global best strategy along the global best particle.
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.
100 citations
••
TL;DR: In this article, the authors reviewed and discussed the application of data analysis methods for energy big data in intelligent energy networks and showed that existing methods for data analysis cannot fully meet the requirements for processing the big data produced by IENs, therefore more comprehensive data analysis method are needed to handle the increasing amount of data and to mine more valuable information.
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.
100 citations
••
TL;DR: A unified algorithm is presented for agents described by both discrete-time and continuous-time models through using the iterative learning approach to achieve the formation control for multi-agent systems.
100 citations
••
100 citations
••
01 Jul 2017TL;DR: This paper empirically verifies the superiority of the early softmax desaturation, and proposes Noisy Softmax to mitigating this early saturation issue by injecting annealed noise in softmax during each iteration and improves the generalization ability of CNN model by regularization.
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.
100 citations
Authors
Showing all 39925 results
Name | H-index | Papers | Citations |
---|---|---|---|
Jie Zhang | 178 | 4857 | 221720 |
Jian Li | 133 | 2863 | 87131 |
Ming Li | 103 | 1669 | 62672 |
Kang G. Shin | 98 | 885 | 38572 |
Lei Liu | 98 | 2041 | 51163 |
Muhammad Shoaib | 97 | 1333 | 47617 |
Stan Z. Li | 97 | 532 | 41793 |
Qi Tian | 96 | 1030 | 41010 |
Xiaodong Xu | 94 | 1122 | 50817 |
Qi-Kun Xue | 84 | 589 | 30908 |
Long Wang | 84 | 835 | 30926 |
Jing Zhou | 84 | 533 | 37101 |
Hao Yu | 81 | 981 | 27765 |
Mohsen Guizani | 79 | 1110 | 31282 |
Muhammad Iqbal | 77 | 961 | 23821 |