基于聚类算法实现信号盲分类

本文解决了信号处理、工业控制等领域存在的非平稳信号盲分类问题。在聚类中广泛应用的K-Means算法及其它基于中心的聚类算法有两个共同的缺陷-需要预先确定类数目且随机初始化中心引起性能不稳定。本文提出的算法较好地解决了这两个问题，提高了算法稳定性，实现了非平稳信号盲分类。提取非平稳信号的小波系数作为聚类的样本空间，分析聚类结果的统计偏差以估计类的数目，采用调和均值准则进行分类。最后给出的仿真结果表明本文提出的方法较传统的K-Means算法明显降低分类错误率。     

A fuzzy clustering algorithm enhancing local model interpretability

In this work, simple modifications on the cost index of particular local-model fuzzy clustering algorithms are proposed in order to improve the readability of the resulting models. The final goal is simultaneously providing local linear models (reasonably close to the plant’s Jacobian) and clustering in the input space so that desirable characteristics (regarding final model accuracy, and convexity and smoothness of the cluster membership functions) are improved with respect to other proposals in literature. Some examples illustrate the proposed approach.     

Information systems effectiveness: research designs for causal inference

Abstract. This paper examines the capacity of the research designs of 37 empirical studies of information systems (IS) effectiveness to provide a basis for the development of theories about behaviour related to IS effectiveness. The power of each study to support causal inference was evaluated in terms of (a) its handling of the time dimension, (b) its ability to weigh differences and (c) its resistance to internal validity threats that pose alternative explanations for its reported findings. Of the reviewed studies, 29.7% could account for the time dimension, 32.4% employed a comparison group and 16.2% were not susceptible to any internal validity threats. Only 13.5% of the studies combined an accounting for the time dimension with the use of a comparison group. Of these, however, only 5.4% were also invulnerable to internal validity threats. The research designs of nearly 95% of these published studies were deficient in supporting causal inference. In those studies, suggestions that one variable was causally related to another variable could not be substantiated. Encouragement for the future capacity of IS effectiveness research to support causal inference was found in a trend towards the use of quasiexperimental designs. Recommendations are made regarding ways to increase the inferential capacity of research designs employed in the study of IS effectiveness.     

Software for dynamic reconfigurable order picking systems

This paper describes an approach, conceptual framework, and software architecture for dynamic reconfiguration of the order picking system. The research and development project was sponsored by the Material Handling Research Center (MHRC), a National Science Foundation sponsored Cooperative Industry/University Research Center. The storage configuration is assumed to be an in-the-aisle order picking system in which stockkeeping units (SKUs) can occupy variable capacity storage locations and stock-splitting is allowed among zones (clusters). The product mix may include multiple product families with different life cycles, correlated demand within families and commonality of demand across families.     

Non-redundant data clustering

Data clustering is a popular approach for automatically finding classes, concepts, or groups of patterns. In practice, this discovery process should avoid redundancies with existing knowledge about class structures or groupings, and reveal novel, previously unknown aspects of the data. In order to deal with this problem, we present an extension of the information bottleneck framework, called coordinated conditional information bottleneck, which takes negative relevance information into account by maximizing a conditional mutual information score subject to constraints. Algorithmically, one can apply an alternating optimization scheme that can be used in conjunction with different types of numeric and non-numeric attributes. We discuss extensions of the technique to the tasks of semi-supervised classification and enumeration of successive non-redundant clusterings. We present experimental results for applications in text mining and computer vision.     

Reliability and Validity of the Revised Children's Manifest Anxiety Scale in a French-Canadian Sample.

The aim of this study was to examine the reliability and validity of a French version of the Revised Children's Manifest Anxiety Scale (RCMAS). A sample of 2,666 school-age French-Canadian children completed the questionnaire. With regard to factor structure, the 5-factor model found in U.S. normative samples was confirmed. The internal consistency of the 5 scales and of the 2 global scales was good to excellent. Test-retest reliabilities after a 6-month period were also similar to those of the original version. Finally, the concurrent validity, assessed by a correlation with the State-Trait Anxiety Inventory for Children, was also found to be good. Results of the present study show that the French version of the RCMAS is a good instrument to assess anxiety in children. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Recent Development of Cognitive and Neuropsychological Assessment in Asian Countries.

There is a growing trend of research in neuropsychological assessment in Asia: The mean number of published studies increased from 1.8 in the 1980s to 16.0 in 2 recent years. About 40% of the studies reviewed concerned test development or adaptation, with the latter greatly outnumbering the former. To facilitate the test selection for clinical use, 36 clinical measures were evaluated based on some statistical criteria. The results showed that only 8 neuropsychological tests (5 Chinese. 2 Korean, and 1 Japanese) met the criteria. Given that Asian and Western populations differ on certain cognitive processes, future development of neuropsychological assessment measures in Asia should move from the adaptation of Western tests toward the construction of original tests with better ecological validity. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

一种应用于二次布局的有效划分方法

提出了一种基于二次布局的结合MFFC结群和hMETIS划分的算法.实验表明:这种方法能得到很好的布局结果,但是运行消耗的时间比较长.为了缩短划分在二次布局中运行的时间,提出了一种改进的结群算法IMFFC,用它在二次布局中做划分.与前者相比较,这种方法虽然布局质量稍差,但速度更快.     

模糊聚类在三维地震参数处理中的应用

三维地震参数是一个庞大的三维数据体，能从不同侧面反映储集层的特征。通过对三维地震参数的分析，可以评估油藏表征的参数（沉积相、构造、生长历史、流体饱和度等）。针对传统的聚类方法不能很好地综合考虑各个参数之间的相似程度，提出了用模糊C-均值聚类（fuzzy c-means clustering，简称FCM）对三维地震参数进行处理。从三维地震参数和油藏表征参数之间的关系出发，采用模糊C-均值聚类方法对三维地震参数进行处理，依此评估油藏表征的参数。测试结果表明，模糊C-均值聚类方法能够对三维地震参数进行较为准确的分类，并为储集层的研究提供了很好的依据。