scholarly journals New Community Estimation Method in Bipartite Networks Based on Quality of Filtering Coefficient

2019 ◽  
Vol 2019 ◽  
pp. 1-12 ◽  
Author(s):  
Li Xiong ◽  
Guo-Zheng Wang ◽  
Hu-Chen Liu

Community detection is an important task in network analysis, in which we aim to find a network partitioning that groups together vertices with similar community-level connectivity patterns. Bipartite networks are a common type of network in which there are two types of vertices, and only vertices of different types can be connected. While there are a range of powerful and flexible methods for dividing a bipartite network into a specified number of communities, it is an open question how to determine exactly how many communities one should use, and estimating the numbers of pure-type communities in a bipartite network has not been completed. In our paper, we propose a method named as “biCNEQ” (bipartite network communities number estimation based on quality of filtering coefficient), which ensures that communities are all pure type, for estimating the number of communities in a bipartite network. This paper makes the following contributions: (1) we show how a unipartite weighted network, which we call similarity network, can be projected from a bipartite network using a measure of correlation; (2) we reveal the relation between the similarity correlation and community’s edges in the vertices of a unipartite network; (3) we design a measure of the filtering quality named QFC (quality of filtering coefficient) to filter the similarity network and construct a binary network, which we call approximation network; and (4) the number of communities in each type of unipartite networks is estimated using Riolo’s method with the approximation network as input. Finally, the proposed biCNEQ is demonstrated by both synthetic bipartite networks and a real-world network, and the results show that it can determine the correct number of communities and perform better than two classical one-mode projection methods.

Author(s):  
Antonios Garas ◽  
Céline Rozenblat ◽  
Frank Schweitzer

The chapter “Economic Specialization and the Nested Bipartite Network of City–Firm Relations” shows how the structure of the city–firm bipartite network has striking similarities with other types of bipartite networks found in ecology. There, nodes represent species, while links represent their interactions. In so-called antagonistic networks, such as food webs, the interaction between species is asymmetric, such as in host–parasite, predator–prey, and plant–herbivore interactions. In so-called mutualistic networks, on the other hand, the interaction between species is symmetric, that is, both species interact in a mutually beneficial way such as, for example, the way that plants interact with their pollinators. This chapter shows that ecological indicators can be used to identify the unbalanced deployment of economic activities; it also provides evidence that the network of city–firm relations contains information about the quality of life in cities.


2021 ◽  
pp. 0739456X2110067
Author(s):  
Siu Kei Wong ◽  
Kuang Kuang Deng

This study investigates how perceived school quality affects housing values, using a new estimation method. Our empirical design takes advantage of the mergers of school catchment zones initiated by the government to develop quasi-experiments. We find that, in zones that gained sudden access to higher ranked schools, housing prices increased by 1.3 to 4.1 percent. Larger and more expensive houses appreciated more in response to the improvement in perceived quality of available schools. The findings generate important policy implications regarding housing wealth redistribution and housing expenditures among different households. The study also enriches the literature on the capitalization effect of school quality.


2021 ◽  
Vol 26 (3-4) ◽  
pp. 291-301
Author(s):  
N.V. Stepanov ◽  

Operating quality of automated video control systems depends on optical specifications of video camera and peculiar features of video algorithm. Specified target function performance probability can serve as criterion of automated video control use efficiency. In this work, a new performance efficiency estimation method for automated equipment of target environment video control is suggested: to estimate the probability of target functions’ (object detection, capture, and auto tracking) performance. Theoretical prediction of target functions performance probability was built upon Johnson’s criterion and the use of optimal receiver model. The results of suggested method’s experimental verification have shown that target detection occurred when signal/noise ratio level was above 6. This level can be regarded as low value to ensure that object is detected with probability 0.9.


2017 ◽  
Vol 44 (5) ◽  
pp. 727-744
Author(s):  
Sujani Thrikawala ◽  
Stuart Locke ◽  
Krishna Reddy

Purpose The purpose of this paper is to examine the relationship between corporate governance (CG) and microfinance institution (MFI) performance, using a dynamic panel generalised method of moments (GMM) estimator to mitigate the serious issues with endogeneity. Design/methodology/approach Inconsistent findings and a general lack of empirical results for the microfinance industry leave an unclear message regarding the impacts of CG on MFI performance, especially in emerging economies. The authors use GMM estimation techniques to examine whether CG has an influence on MFI performance. Findings This study confirms that the MFIs’ contemporaneous performance and CG characteristics are statistically significantly positively linked with their past performance. This study finds statistically significant governance effects on MFI performance, including the presence of international directors and/or donor representatives on the board, client representatives on the board, percentage of non-executive directors and the quality of the national governance system. Practical implications These findings provide some insights for policy-makers and practitioners to develop suitable policies and guidelines to streamline MFIs’ operations in emerging countries. Moreover, national and international investors and donors may use these finding as a benchmark for their investment and funding decisions. Originality/value This paper is the first to estimate the CG and performance relationship of MFIs in a dynamic framework by applying the GMM estimation method. This approach improves upon traditional estimation methods by controlling the likely sources of endogeneity. Further, this paper examines whether quality of national-level governance characteristics is related to performance measures of profitability and outreach of MFIs.


2016 ◽  
Vol 5 ◽  
pp. 67-80 ◽  
Author(s):  
Nataly Zrazhevska

The most popular methods for dynamic risk measures – Value-at-Risk (VaR) and Conditional VaR (CVaR) estimating were analyzed, description and comparative analysis of the methods were fulfilled, recommendations on the use were given. Results of the research were presented in the form of a classification scheme of dynamic risk measures estimating that facilitates the choice of an estimation method. The GARCH-based models of dynamic risk measures VaR and CVaR evaluation for artificially generated series and two time series of log return on a daily basis of the most well-known Asian stock indexes Nikkey225 Stock Index and CSI30 were constructed to illustrate the effectiveness of the proposed scheme. A qualitative analysis of the proposed models was conducted. To analyze the quality of the dynamic VaR estimations the Cupets test and the Cristoffersen test were used. For CVaR estimations the V-test was used as quality test. The tests results confirm the high quality of obtained estimations. The proposed classification scheme of dynamic risk measures VaR and CVaR estimating may be useful for risk managers of different financial institutions.


2014 ◽  
Vol 4 (2) ◽  
pp. 195-206 ◽  
Author(s):  
Ruiting Xu ◽  
Zhigeng Fang ◽  
Jinyu Sun

Purpose – The purpose of this paper is to find out a scientific method to evaluate quality of complex products, whose quality is different from general products. Design/methodology/approach – Based on interval grey number theory, reliability analysis method and stochastic network theory, authors have established grey success tree analysis-graph evaluation and review technique (GSTA-GERT) model in this paper. Findings – Comparing complex products and general products, authors have found that complex products have two characters, i.e. quality of manufacture and quality of service. Furthermore, this paper has proved the GSTA-GERT model is a scientific and reasonable approach to estimate quality of complex products from the sight of manufacture-service network. Originality/value – This paper has established GSTA-GERT model, which surmounts the defect of traditional estimation method, such as lacking logic analysis in the method of analytic hierarchy process.


Author(s):  
Loreta Abakoka

Nora Ikstena’s “Mātes piens” (Mother’s Milk; published in English as Soviet Milk) is one of the novels in the book series “MĒS. Latvija, XX gadsimts” (We. Latvia. The 20th Century). It describes the difficulties that can arise in the mother-daughter relationship, describes the Soviet time’s environment and its impact on everyday life. The historical novel “Mātes piens” has been published in 25 countries, which means that this novel has been translated into many different cultures, which are less familiar with the mentality of the Latvian people and the USSR times in Latvia. Therefore, it is crucial how the text is translated or whether the style and the particular poetics of Nora Ikstena’s language in this novel are accurately reproduced. Therefore, the scientific research work “Quality of Translated Comparisons of Nora Ikstena’s “Soviet Milk” and “Молоко матери”” was developed. Comparisons requiring the translator to take into account both the content and the meaning of the words were analysed, as well as the aspect of language imagery and culture. The novel was translated into English by Margita Gailīts, and into Russian by Ludmila Nukņeviča. The events of the novel “Soviet Milk” take place from the end of the Second World War until the 1980s. The main character is a daughter, whose story is intertwined with the life stories of her mother and grandmother. The novel portrays the daughter’s struggle with her mother’s depression, which has deprived her of emotional intimacy with her mother since birth; the daughter continues to hope and gain her mother’s love, helping in times of crisis and ignoring several rejections. Although the translation process is very old, the question about the translation quality is still relevant. Using sources of information and gaining theoretical knowledge of the translation process, an error estimation method was developed that allows the word “quality” to be quantified. Literary translation is mostly separated from other translation types and put into a separate category, usually because the meaning of a literary work cannot be clarified in simple terms presented today. It is also difficult to analyse what the reader expects from the translation. Since there cannot be one right way of translating literature, the sense of the translator’s ethical duty to the author is the most important. However, this is very limited by how well the translator understands the author’s intentions and what is said and how much freedom the translator is given to change the text to find the most appropriate way to express the idea in the language. (Sager 1994) Four groups were divided by Juliane House’s theory (House 2014; House 2017) about overt errors. Text translation errors are divided into 2 categories – covert and overt. Covert errors are difficult to notice because, superficially, from a grammatical point of view, the sentence is correct, but its content is not logical or acceptable. The overt errors detected are obvious, constitute a systematic error. Overt errors are divided into 7 groups: 1 – not translated; 2 – a slight change in meaning; 3 – a significant change in meaning; 4 – distortion of meaning; 5 – breach of SL system; 6 – creative translation; 7 – cultural filtering. 64 comparisons in Latvian, 64 equivalents in Russian, and 55 equivalents in English were excerpted (9 comparisons were not translated). Translations of comparisons were divided into 4 groups: 1) accurately translated, 2) translations with minor changes, 3) culturally harmonized translations, 4) untranslated comparisons. Translations of comparisons that scored 5 points or more are considered qualitatively translated, given that there are no significant errors. There is no single fundamental criterion for the quality of a translation against which all translated texts can be judged. There are several definitions of quality translation, and quality is affected by many factors. The translations of comparisons in both foreign languages (English and Russian) are of high quality; they received high marks if they were analysed according to the error evaluation table because the maximum number of points that could be obtained was 6 points and no comparative translation was lower than 5 points. The Russian translation is more successful (comparative translations more often scored 6 points) than the English translation, which can be justified by the fact that the Russian language is historically and geographically a neighbor of the Latvian language, but the English language and culture are remote. Phraseological comparisons are translated literally and also more accurately into Russian; there are more of the same equivalents in the target culture. When evaluating comparisons that use the concepts of biblical story motifs or images of Greek mythology, they are mostly accurately translated into the target languages, as the target cultures are well acquainted with this religion and Greek mythology. One of the most important findings – not only literal translations are of high quality; it is much more important to express them in a way that is understandable to the target culture while maintaining the author’s writing style and the text’s main idea, paying attention to details.


Author(s):  
Kishlay Jha ◽  
Guangxu Xun ◽  
Aidong Zhang

Abstract Motivation Many real-world biomedical interactions such as ‘gene-disease’, ‘disease-symptom’ and ‘drug-target’ are modeled as a bipartite network structure. Learning meaningful representations for such networks is a fundamental problem in the research area of Network Representation Learning (NRL). NRL approaches aim to translate the network structure into low-dimensional vector representations that are useful to a variety of biomedical applications. Despite significant advances, the existing approaches still have certain limitations. First, a majority of these approaches do not model the unique topological properties of bipartite networks. Consequently, their straightforward application to the bipartite graphs yields unsatisfactory results. Second, the existing approaches typically learn representations from static networks. This is limiting for the biomedical bipartite networks that evolve at a rapid pace, and thus necessitate the development of approaches that can update the representations in an online fashion. Results In this research, we propose a novel representation learning approach that accurately preserves the intricate bipartite structure, and efficiently updates the node representations. Specifically, we design a customized autoencoder that captures the proximity relationship between nodes participating in the bipartite bicliques (2 × 2 sub-graph), while preserving both the global and local structures. Moreover, the proposed structure-preserving technique is carefully interleaved with the central tenets of continual machine learning to design an incremental learning strategy that updates the node representations in an online manner. Taken together, the proposed approach produces meaningful representations with high fidelity and computational efficiency. Extensive experiments conducted on several biomedical bipartite networks validate the effectiveness and rationality of the proposed approach.


2019 ◽  
Vol 29 (1) ◽  
pp. 1480-1495
Author(s):  
D. Khalandar Basha ◽  
T. Venkateswarlu

Abstract The image restoration (IR) technique is a part of image processing to improve the quality of an image that is affected by noise and blur. Thus, IR is required to attain a better quality of image. In this paper, IR is performed using linear regression-based support vector machine (LR-SVM). This LR-SVM has two steps: training and testing. The training and testing stages have a distinct windowing process for extracting blocks from the images. The LR-SVM is trained through a block-by-block training sequence. The extracted block-by-block values of images are used to enhance the classification process of IR. In training, the imperfections on the image are easily identified by setting the target vectors as the original images. Then, the noisy image is given at LR-SVM testing, based on the original image restored from the dictionary. Finally, the image block from the testing stage is enhanced using the hybrid Laplacian of Gaussian (HLOG) filter. The denoising of the HLOG filter provides enhanced results by using block-by-block values. This proposed approach is named as LR-SVM-HLOG. A dataset used in this LR-SVM-HLOG method is the Berkeley Segmentation Database. The performance of LR-SVM-HLOG was analyzed as peak signal-to-noise ratio (PSNR) and structural similarity index. The PSNR values of the house and pepper image (color image) are 40.82 and 36.56 dB, respectively, which are higher compared to the inter- and intra-block sparse estimation method and block matching and three-dimensional filtering for color images at 20% noise.


Sign in / Sign up

Export Citation Format

Share Document