A fuzzy measure identification method by diamond pairwise comparisons and $${\phi_s}$$ transformation

We propose an identification method of fuzzy measures by diamond pairwise comparisons. Right and left side of the diamond means ordinal weights’ comparison and up and down means interaction degrees. From the comparisons, we estimate a hierarchy diagram with interaction degrees and weights of evaluation items using the agglomerative hierarchical clustering method. From the diagram, to identify the fuzzy measure, conversion method is proposed.     

军用飞机任务保障规划方案效率分析

针对军用飞机再次出动保障任务规划方案的效率分析缺乏有效的解决方法的问题,构建了基于灰色聚类算法与熵权法相结合的任务保障规划方案效率分析模型。该模型首先利用灰色聚类对保障方案的人员利用率的有效参数进行计算并确定。其后利用熵权法对保障方案的人员数量时间分布进行计算。在此基础上根据任务规划工期、人员利用率、人员数量时间分布三个参数的权重得到任务保障规划方案效率。文中通过实例对构建的效率分析模型进行了验证。结果表明：所构建的效率分析模型能够有效的对军用飞机任务保障规划方案效率分析,且具有较高的可靠性和很好的工程应用价值。     

On finding a large number of 3D points with a small diameter

Given a set S of n points in R³, we wish to decide whether S has a subset of size at least k with Euclidean diameter at most r. It is unknown whether this decision problem is NP-hard. The two closely related optimization problems, (i) finding a largest subset of diameter at most r, and (ii) finding a subset of the smallest diameter of size at least k, were recently considered by Afshani and Chan. For maximizing the size, they presented several polynomial-time algorithms with constant approximation factors, the best of which has a factor of . For maximizing the diameter, they presented a polynomial-time approximation scheme. In this paper, we present improved approximation algorithms for both optimization problems. For maximizing the size, we present two algorithms: the first one improves the approximation factor to 2.5 and the running time by an O(n) factor; the second one improves the approximation factor to 2 and the running time by an O(n²) factor. For minimizing the diameter, we improve the running time of the PTAS from O(nlogn+2^O(1/ε3)n) to O(nlogn+2^{O(1/(ε1.5logε))}n).     

一种主扫描图象的二进制特征向量动态聚类方法

不同类型的地物,由于辐射光谱分布不同,在多维光谱空间中构成不同的特征向量,这些向量可以用二进制数码表征。本文介绍的动态聚类方法便是一种基于二进制特征向量的非监督分类方法。此方法成功地用于主扫描图象分类.     

复杂产品碳足迹结构元规划方法研究*

日益增长的环境压力对复杂产品供应链碳足迹优化提出了更高的要求。为了降低优化过程动态性及不确定性,在综合评述产品拆卸建模分析研究方法的基础上,依据约束关系和装配结构,通过构建规则,设计多目标复杂产品碳足迹结构元拆卸混合图模型,确立模型约束关系矩阵,利用迭代分层思想设计驱动式递归聚类搜索算法,规划各层次碳足迹结构元模块。经液晶显示器实例证明,该规划方法可有效剖析复杂产品碳足迹结构基本元及模块单元。     

Community detection in social networks based on improved Label Propagation Algorithm and balanced link density

Nowadays, community detection has been raised as one of the key research areas in the online social networks mining. One of the most common algorithms in this field is label propagation algorithm (LPA). Even though the LPA method has advantages such as simplicity in understanding and implementation, as well as linear time complexity, it has an important disadvantage of the uncertainty and instability in outcomes, that is, the algorithm detects and reports different combinations of communities in each run. This problem originates from the nature of random selection in the LPA method. In this paper, a novel method is proposed based on the LPA method and the inherent structure, that is, link density feature, of the input network. The proposed method uses a sensitivity parameter (balance parameter); by choosing the appropriate values for it, the desired qualities of the identified communities can be achieved. The proposed method is called Balanced Link Density-based Label Propagation (BLDLP). In comparison with the basic LPA, the proposed method has an advantage of certainty and stability in the output results, whereas its time complexity is still comparable with the basic LPA and of course lowers than many other approaches. The proposed method has been evaluated on real-world known datasets, such as the Facebook social network and American football clubs, and by comparing it with the basic LPA, the effectiveness of the proposed method in terms of the quality of the communities found and the time complexity has been shown.     

Unsupervised classification of slip events for planetary exploration rovers

This paper introduces an unsupervised method for the classification of discrete rovers’ slip events based on proprioceptive signals. In particular, the method is able to automatically discover and track various degrees of slip (i.e. low slip, moderate slip, high slip). The proposed method is based on aggregating the data over time, since high level concepts, such as high and low slip, are concepts that are dependent on longer time perspectives. Different features and subsets of the data have been identified leading to a proper clustering, interpreting those clusters as initial models of the prospective concepts. Bayesian tracking has been used in order to continuously improve the parameters of these models, based on the new data. Two real datasets are used to validate the proposed approach in comparison to other known unsupervised and supervised machine learning methods. The first dataset is collected by a single-wheel testbed available at MIT. The second dataset was collected by means of a planetary exploration rover in real off-road conditions. Experiments prove that the proposed method is more accurate (up to 86% of accuracy vs. 80% for K-means) in discovering various levels of slip while being fully unsupervised (no need for hand-labeled data for training).     

ProSeg: a database of local structures of protein segments

Integration of knowledge on the sequence-structure correlation of proteins provides a basis for the structural design of artificial novel proteins. As one of strategies, it is effective to consider a short segment, whose size is in between an amino acid and a domain, as a correlation unit for exploring the structure-to-sequence relationship. Here we report the development of a database called ProSeg, which consists of two sub-databases, Segment DB and Cluster DB. Segment DB contains tens of thousands of segments that were prepared by dividing the primary sequences of 370 proteins using a sliding L-residue window (L = 5, 9, 11, 15). These segments were classified into several thousands of clusters according to their three-dimensional structural resemblance. Cluster DB contains much cluster-related information, which includes image, rank, frequency, secondary structure assignment, sequence profile, etc. Users can search for a suitable cluster by inputting an appropriate parameter (i.e., PDB ID, dihedral angles, or DSSP symbols), which identifies the backbone structure of a query segment. Analogous to a language, ProSeg could be regarded as a ‘structure-sequence dictionary’ that contains over 10,000 ‘protein words’. ProSeg is freely accessible through the Internet ().     

聚类分析在入侵检测中的应用

在对现有的入侵检测技术研究的基础上,着重对数据挖掘技术中的聚类分析方法在入侵检测领域中的应用进行了研究。通过分析网络中数据的特点,提出了一种基于改进的k-means算法的无监督二次聚类算法,并用入侵检测权威数据集KDD Cup1999作为实验数据将其实现,实验表明,该算法具有较高的检测率和较低的误检率。     

面向稀疏数据集的聚类算法

在聚类过程中数据可能呈现稀疏性,如果仍用传统的欧式距离作为聚类指标,则聚类的质量和效率将会受到严重的影响。受到信息论中KL(Kullback-Leibler)散度的启发,采用基于KL散度的相似性度量方法,先描述数据的整体分布,进而对数据进行聚类。研究结果表明,最后通过实验验证本算法的有效性。这种方法可以利用簇中元素提供的信息来度量不同簇之间的相互关系,克传统欧式距离的缺点,提升算法准确度。