Kinds Of Similarity Measures Research Articles

Locating the propagation source in complex networks with observers-based similarity measures and direction-induced search

Locating the propagation source is one of the most important strategies to control the harmful diffusion process on complex networks. Most existing methods only consider the infection time information of the observers, but the diffusion direction information of the observers is ignored, which is helpful to locate the source. In this paper, we consider both of the diffusion direction information and the infection time information to locate the source. We introduce a relaxed direction-induced search (DIS) to utilize the diffusion direction information of the observers to approximate the actual diffusion tree on a network. Based on the relaxed DIS, we further utilize the infection time information of the observers to define two kinds of observers-based similarity measures, including the Infection Time Similarity and the Infection Time Order Similarity. With the two kinds of similarity measures and the relaxed DIS, a novel source locating method is proposed. We validate the performance of the proposed method on a series of synthetic and real networks. The experimental results show that the proposed method is feasible and effective in accurately locating the propagation source.

Matching heterogeneous ontologies with adaptive evolutionary algorithm

An ontology provides a formal description on the domain concepts and their relationships. Due to the subjectivity of ontology engineers, one concept might be expressed in various ways, yielding the so-called ontology heterogeneity problem, and ontology matching is a ground method to address this problem. Ontology matching technique uses the similarity measure to determine the correspondences between two heterogeneous ontology entities. In order to improve the quality of ontology alignment, it is necessary to combine different kinds of similarity measures, and how to optimize the aggregating weights is called the ontology meta-matching problem. Tin this work, a heuristic evaluating metric on the ontology alignment is presented to evaluate the ontology alignment's quality, and a mathematical model on ontology meta-matching problem is constructed. Then, an Adaptive Evolutionary Algorithm (AEA) is proposed to effectively solve this problem. In particular, when the elite solution remains unchanged, AEA adaptively activates three independent exploring strategies, which, respectively use the adaptive selection, crossover and mutation operators based on the population diversity metric. In the experiment, we compare AEA among EA based matching technique and the state-of-the-art ontology matching technique, and the experimental results show its effectiveness.

Classification for Polsar image based on hölder divergences

(Dis)similarity measures play an important role in the interpretation of polarimetric synthetic aperture radar (PolSAR) images. Here, the authors introduce a kind of similarity measures for PolSAR images based on the concepts of Holder pseudo-divergence and Holder divergence. Authors’ similarity measures are more generalised as the derived formulas indicate that they contain several widely used measures, such as Bartlett or Bhattahcharyya distances and Chernoff distance. Also, their similarity measures are derived from the complex Wishart distribution, so these measures are good at quantifying the similarity between two covariance matrices and perform well while dealing with classification problems for PolSAR images. Experimental results on unsupervised and supervised classification of PolSAR images also verify the effectiveness of their measures.

Ranking of software developers based on expertise score for bug triaging

Existing bug triage approaches for developer recommendation systems are mainly based on machine learning (ML) techniques. These approaches have shown low prediction accuracy and high bug tossing length (BTL). The objective of this paper is to develop a robust algorithm for reducing BTL based on the concept of developer expertise score (DES). None of the existing approaches to the best of our knowledge have utilized metrics to build developer expertise score. The novel strategy of DES is consisted of two stages: Stage-I consisted of an offline process for detecting the developers based on DES which computes the score using priority, versatility and average fix-time for his individual contributions. The online system process consisted of finding the capable developers using three kinds of similarity measures (feature-based, cosine-similarity and Jaccard). Stage-II of the online process consisted of simply ranking the developers. Hit-ratio and reassignment accuracy were used for performance evaluation. We compared our system against the ML-based bug triaging approaches using three types of classifiers: Navies Bayes, Support Vector Machine and C4.5 paradigms. By adapting the five open source databases, namely: Mozilla, Eclipse, Netbeans, Firefox, and Freedesktop, covering 41,622 bug reports, our novel DES system yielded a mean accuracy, precision, recall rate and F-score of 89.49%, 89.53%, 89.42% and 89.49%, respectively, reduced BTLs of up to 88.55%. This demonstrates an improvement of up to 20% over existing strategies. This work presented a novel developer recommendation algorithm to rank the developers based on a metric-based integrated score for bug triaging. This integrated score was based on the developer's expertise with an objective to improve (i) bug assignment and (ii) reduce the bug tossing length. Such architecture has an application in software bug triaging frameworks.

Cleaning by clustering: methodology for addressing data quality issues in biomedical metadata

BackgroundThe ability to efficiently search and filter datasets depends on access to high quality metadata. While most biomedical repositories require data submitters to provide a minimal set of metadata, some such as the Gene Expression Omnibus (GEO) allows users to specify additional metadata in the form of textual key-value pairs (e.g. sex: female). However, since there is no structured vocabulary to guide the submitter regarding the metadata terms to use, consequently, the 44,000,000+ key-value pairs in GEO suffer from numerous quality issues including redundancy, heterogeneity, inconsistency, and incompleteness. Such issues hinder the ability of scientists to hone in on datasets that meet their requirements and point to a need for accurate, structured and complete description of the data.MethodsIn this study, we propose a clustering-based approach to address data quality issues in biomedical, specifically gene expression, metadata. First, we present three different kinds of similarity measures to compare metadata keys. Second, we design a scalable agglomerative clustering algorithm to cluster similar keys together.ResultsOur agglomerative cluster algorithm identified metadata keys that were similar, based on (i) name, (ii) core concept and (iii) value similarities, to each other and grouped them together. We evaluated our method using a manually created gold standard in which 359 keys were grouped into 27 clusters based on six types of characteristics: (i) age, (ii) cell line, (iii) disease, (iv) strain, (v) tissue and (vi) treatment. As a result, the algorithm generated 18 clusters containing 355 keys (four clusters with only one key were excluded). In the 18 clusters, there were keys that were identified correctly to be related to that cluster, but there were 13 keys which were not related to that cluster. We compared our approach with four other published methods. Our approach significantly outperformed them for most metadata keys and achieved the best average F-Score (0.63).ConclusionOur algorithm identified keys that were similar to each other and grouped them together. Our intuition that underpins cleaning by clustering is that, dividing keys into different clusters resolves the scalability issues for data observation and cleaning, and keys in the same cluster with duplicates and errors can easily be found. Our algorithm can also be applied to other biomedical data types.

Discriminating the reaction types of plant type III polyketide synthases.

MotivationFunctional prediction of paralogs is challenging in bioinformatics because of rapid functional diversification after gene duplication events combined with parallel acquisitions of similar functions by different paralogs. Plant type III polyketide synthases (PKSs), producing various secondary metabolites, represent a paralogous family that has undergone gene duplication and functional alteration. Currently, there is no computational method available for the functional prediction of type III PKSs.ResultsWe developed a plant type III PKS reaction predictor, pPAP, based on the recently proposed classification of type III PKSs. pPAP combines two kinds of similarity measures: one calculated by profile hidden Markov models (pHMMs) built from functionally and structurally important partial sequence regions, and the other based on mutual information between residue positions. pPAP targets PKSs acting on ring-type starter substrates, and classifies their functions into four reaction types. The pHMM approach discriminated two reaction types with high accuracy (97.5%, 39/40), but its accuracy decreased when discriminating three reaction types (87.8%, 43/49). When combined with a correlation-based approach, all 49 PKSs were correctly discriminated, and pPAP was still highly accurate (91.4%, 64/70) even after adding other reaction types. These results suggest pPAP, which is based on linear discriminant analyses of similarity measures, is effective for plant type III PKS function prediction.Availability and ImplementationpPAP is freely available at ftp://ftp.genome.jp/pub/tools/ppap/Supplementary information Supplementary data are available at Bioinformatics online.

Exploring information from the topology beneath the Gene Ontology terms to improve semantic similarity measures

Measuring the similarity between pairs of biological entities is important in molecular biology. The introduction of Gene Ontology (GO) provides us with a promising approach to quantifying the semantic similarity between two genes or gene products. This kind of similarity measure is closely associated with the GO terms annotated to biological entities under consideration and the structure of the GO graph. However, previous works in this field mainly focused on the upper part of the graph, and seldom concerned about the lower part. In this study, we aim to explore information from the lower part of the GO graph for better semantic similarity. We proposed a framework to quantify the similarity measure beneath a term pair, which takes into account both the information two ancestral terms share and the probability that they co-occur with their common descendants. The effectiveness of our approach was evaluated against seven typical measurements on public platform CESSM, protein–protein interaction and gene expression datasets. Experimental results consistently show that the similarity derived from the lower part contributes to better semantic similarity measure. The promising features of our approach are the following: (1) it provides a mirror model to characterize the information two ancestral terms share with respect to their common descendant; (2) it quantifies the probability that two terms co-occur with their common descendant in an efficient way; and (3) our framework can effectively capture the similarity measure beneath two terms, which can serve as an add-on to improve traditional semantic similarity measure between two GO terms. The algorithm was implemented in Matlab and is freely available from http://ejl.org.cn/bio/GOBeneath/.

A new clustering algorithm based on near neighbor influence

Clustering has been used in many areas. It is an unsupervised learning method which tries to find some distributions and patterns in unlabeled data sets. Although clustering algorithms have been studied for decades, none of them is all purpose. This paper presents a new clustering algorithm, Clustering based on Near Neighbor Influence (CNNI), an improved version in time cost of CNNI algorithm (ICNNI), and a variation of CNNI algorithm (VCNNI). They are inspired by the idea of near neighbors and the superposition principle of influence. In order to clearly describe the three algorithms, it lists three basic concepts (near neighbor point set, grid cell, and near neighbor grid cell set) and introduces two important concepts (near neighbor influence and a kind of similarity measure). In the simulations, four famous clustering algorithms (K-Means, FCM, AP, and DBSCAN) are used as comparative algorithms. From the simulated experiments of some artificial data sets and some real data sets, we observed that CNNI, ICNNI, and VCNNI can find those obvious clusters and get better (or similar) clustering results than (or with) K-Means, FCM, and AP for some data sets. We also observed that ICNNI is faster than CNNI with the same clustering results, CNNI and ICNNI are faster than AP with better or similar clustering quality, CNNI needs less space than VCNNI and DBSCAN, and VCNNI gets similar clustering results with DBSCAN. Especially, CNNI, ICNNI, and VCNNI can easily find some noises or isolates. At last, it gives several solid and insightful future research suggestions.

Some new approaches to constructing similarity measures

The purpose of this paper is threefold. Firstly, based on the concept of fuzzy equivalence given by Fodor and Roubens, we propose different methods for the construction of fuzzy equivalencies from biresiduations, automorphisms, fuzzy negations, t-norms and t-conorms. Secondly, we give two manners of generating similarity measures of P.Z. Wang from fuzzy equivalencies. Finally, some properties of the two kinds of similarity measures are discussed and compared.

A Terminological Search Algorithm for Ontology Matching

Most of the ontology alignment tools use terminological techniques as the initial step and then apply the structural techniques to refine the results. Since each terminological similarity measure considers some features of similarity, ontology alignment systems require exploiting different measures. While a great deal of effort has been devoted to developing various terminological similarity measures and also developing various ontology alignment systems, little attention has been paid to develop similarity search algorithms which exploit different similarity measures in order to gain benefits and avoid limitations. We propose a novel terminological search algorithm which tries to find an entity similar to an input search string in a given ontology. This algorithm extends the search string by creating a matrix from its synonym and hypernyms. The algorithm employs and combines different kind of similarity measures in different situations to achieve a higher performance, accuracy, and stability in comparison with previous methods which either use one measure or combine more measures in a naive ways such as averaging. We evaluated the algorithm using a subset of OAEI Bench mark data set. Results showed the superiority of proposed algorithm and effectiveness of different applied techniques such as word sense disambiguation and semantic filtering mechanism.

Context-Aware Service Selection with Uncertain Context Information

The current evolution of Service-Oriented Computing in ubiquitous systems is leading to the development of context-aware services. These are services whose description is enriched with context information related to the service execution environment and adaptation capabilities. This information is often used for discovery and adaptation purposes. However, in real-life systems context information is naturally dynamic, uncertain and incomplete, which represents an important issue when comparing service description and user requirements. Uncertainty of context information may lead to an inexact match between provided and required service capabilities, and consequently to the non-selection of services. In order to handle uncertain and incomplete context information, we propose a mechanism inspired by graph-comparison for matching contextual service descriptions using similarity measures that allow inexact matching. Service description and requirements are compared using two kinds of similarity measures: local measures, which compare individually required and provided properties, and global measures, which take into account the context description as a whole. We show how the proposed mechanism is integrated in MUSIC, an existing adaptation middleware, and how it enables more optimal adaptation decision making.

Appropriate similarity measures for author co‐citation analysis

AbstractWe provide in this article a number of new insights into the methodological discussion about author co‐citation analysis. We first argue that the use of the Pearson correlation for measuring the similarity between authors' co‐citation profiles is not very satisfactory. We then discuss what kind of similarity measures may be used as an alternative to the Pearson correlation. We consider three similarity measures in particular. One is the well‐known cosine. The other two similarity measures have not been used before in the bibliometric literature. We show by means of an example that the choice of an appropriate similarity measure has a high practical relevance. Finally, we discuss the use of similarity measures for statistical inference.

Shape-based time series similarity measure and pattern discovery algorithm

Pattern discovery from time series is of fundamental importance. Most of the algorithms of pattern discovery in time series capture the values of time series based on some kinds of similarity measures. Affected by the scale and baseline, value-based methods bring about problem when the objective is to capture the shape. Thus, a similarity measure based on shape, Sh measure, is originally proposed, and the properties of this similarity and corresponding proofs are given. Then a time series shape pattern discovery algorithm based on Sh measure is put forward. The proposed algorithm is terminated in finite iteration with given computational and storage complexity. Finally the experiments on synthetic datasets and sunspot datasets demonstrate that the time series shape pattern algorithm is valid.