Traffic identification method based on multiple probabilistic neural network model

Neural Computing and Applications - Traffic identification is currently an important challenge for network management and security. In this paper, we propose a novel application identification...     

广义频率响应函数的鲁棒建模新方法

针对基于非线性谱分析的故障诊断技术的需要,研究了非线性系统的广义频率响应函数的鲁棒在线建模方 法。首先将次元分析算法应用于Volterra级数模型的辨识,并通过对此算法的修正,得到了一种改进的Volterra系统的鲁 棒辨识算法。对其鲁棒性能进行的分析表明,改进算法的鲁棒抗噪性能被明显提高。在此基础上,提出了一种广义频率响 应函数的两步鲁棒建模新方法。仿真实验表明,该方法具有良好的鲁棒收敛性能,能够有效解决GFRF的在线建模问题。     

Proactive replication for rare objects in unstructured peer-to-peer networks

Unstructured peer-to-peer (P2P) networks have become a very popular architecture for content distribution in large-scale and dynamic environments. The search efficiency problem in unstructured P2P networks has not been adequately addressed so far, especially concerning search for rare objects. In this paper, we propose a proactive replication strategy to improve search efficiency for rare objects. It uses an object-probing technique for peers to decide whether or not to establish replications for their objects when they join the network. This strategy can effectively increase the popularity of rare objects in order to enhance search efficiency. We also present a rare object search algorithm to reduce the overhead caused by the replication strategy. When a peer forwards a search request, the forward probability is calculated according to its neighbors' degrees and the number of neighbors' objects. Therefore, the search request is forwarded to the peers more likely containing target objects. Simulations show that our proactive replication strategy greatly improves search efficiency for rare objects with moderate communication overhead. The rare object search algorithm not only improves search efficiency for rare objects, but also achieves load balance in search.     

并联电容器频繁发热缺陷分析及处理

针对某220 kV变电站并联电容器组发热问题频发的情况,对其进行全面检查及统计分析,发现导致该问题的主要原因是电容器连接线与接头连接处线轨较浅,导致接触不良,从而导致发热现象.后期对接触面进行工艺处理,在检修及消缺应用过程中取得了良好的效果.     

Optimizing ranking method using social annotations based on language model

Recent research has shown that more and more web users utilize social annotations to manage and organize their interested resources. Therefore, with the growing popularity of social annotations, it is becoming more and more important to utilize such social annotations to achieve effective web search. However, using a statistical model, there are no previous studies that examine the relationships between queries and social annotations. Motivated by this observation, we use social annotations to re-rank search results. We intend to optimize retrieval ranking method by using the ranking strategy of integrating the query-annotation similarity into query-document similarity. Specifically, we calculate the query-annotation similarity by using a statistical language model, which in a shorter form we call simply a language model. Then the initial search results are re-ranked according to the computational weighted score of the query-document similarity score and the query-annotation similarity score. Experimental results show that the proposed method can improve the NDCG score by 8.13%. We further conduct an empirical evaluation of the method by using a query set including about 300 popular social annotations and constructed phrases. More generally, the optimized results with social annotations based on a language model can be of significant benefit to web search.     

一种基于深度谱空网络的高光谱图像聚类方法

通常无监督算法在对高光谱数据进行聚类时仅使用光谱信息,忽略了空间信息,使得聚类准确率较低.针对上述问题提出一种基于深度谱空网络和无监督判别极限学习的高光谱图像聚类算法.利用深度谱空网络对高光谱数据进行光谱特征和空间特征的分层交叉学习,通过反复学习获得深度空谱特征,为后续无监督聚类提供方便.在三种高光谱图像上进行实验,结果表明,该算法获得的聚类效果优于其他基于极限学习机的方法和其他无监督方法.     

A model based transformation paradigm for cross-language collaborations

Online collaboration is a big challenge in the field of international product development in a cross-language environment. It serves two purposes: cross-language translation and design requirement clarification. Though many approaches and tools are developed for each of the purposes, not a solution serves both of them well. Especially, the traditional statistical methods for cross-language translation cannot preserve the whole semantic information, which intend to incur misunderstanding and ineffective collaboration. This results in potential problems in clarifying the design requirements. In this paper, we proposed a method to online collaboration, named Cross-Language Transformation based on Recursive Object Model (CLT-ROM). The proposed method consists of two steps. Firstly, a natural language sentence is transformed into a source ROM diagram. Secondly, a corresponding target ROM diagram is generated by a transformation algorithm. The proposed method is a model-based communication tool which facilitates collaborations. Since the ROM has been proven effective in requirements clarification, some examples are given to illustrate that the CLT-ROM has a good capability of semantic preserving in requirement engineering for product development.