Ranking Distance Research Articles

Alternative Ranking Distance Metrics for Fault-Focused Clustering in Parallel Fault Localization

Alternative Ranking Distance Metrics for Fault-Focused Clustering in Parallel Fault Localization

Relationships between opponent ranking and locomotor activity in international field hockey

No research has investigated the effect of opponent world ranking (WR) on locomotor activity within modern (post-2015) international men's hockey. A retrospective analysis of 71 matches (vs. 24 opponents, WR# 12 ± 11, WR# 1–86) investigated the relationships between opponent ranking at team and positional levels, on locomotor activity. Data were analysed using linear mixed modelling to; (1) explore relationships between opponent ranking and locomotor activity and (2) to compare between predefined ranking groups (WR# 1–8 ‘HIGHER’ [ n = 8], WR# 9–17 ‘SIMILAR’ [ n = 8] and WR >#18 ‘LOWER’ [ n = 8]), relative to the reference team (WR# 11). Significant relationships were found between opponent world ranking and total distance ( β = −6.11; p = 0.003), high-speed running ([HSR], β = −4.87, p < 0.001), sprint distance ([SD], β = −2.41, p < 0.001), sprint efforts ([SE], β = −0.10, p < 0.001) and average speed ( β = −0.19, p < 0.001), but not low-speed running ( β = −0.94, p = 0.57). When analysed by ranking groups, HSR, SD and SE increased against HIGHER (+12%–14% vs. grand mean, p < 0.05) and reduced against LOWER teams (−15%–18% vs. grand mean, p < 0.05). The largest differences in SD were observed in forwards (HIGHER +14% and LOWER −19%) and defenders (HIGHER +20% and LOWER −18%). In international hockey, average speed is greatest when facing higher-ranked rather than similarly ranked opponents. Furthermore, high-speed but not low-speed activity, is modulated by opponent ranking.

An Adaptive Two-Stage Kriging-Based Infilling Strategy for Efficient Multi-Objective Global Optimization

Abstract Most practical multi-objective optimization problems are often characterized by two or more expensive and conflicting objectives, which require time-consuming simulations. Commonly used algorithms construct a surrogate model of each objective function from a few high-fidelity solutions. In order to further decrease the computational burden, adaptive infilling strategies for multi-objective problems are developed to guide the next infilling design for expensive evaluation and update the surrogate model as well as the Pareto front in an iterative manner. In this paper, a multi-objective infilling strategy integrating the Kriging model with a two-stage infilling framework is proposed, termed as ATKIS. This method allows exploitation and exploration alternately to pinpoint the infilling solution for improving the Pareto set and avoiding local over-exploitation simultaneously. At the local exploitation stage, Kriging-based prediction and uncertainty estimation are combined with Non-dominant Ranking and Minimum Relative Distance theories for determining a new design solution, which has maximum improvement relative to the current Pareto set. At the global exploration stage, Voronoi tessellation theory is employed to search for the sparsest position in the design space for a new evaluation. The proposed method is compared with five recent infilling strategies to investigate the performance of infilling ability using several numerical benchmarks. The experimental results show that the proposed method outperforms the other three strategies in improving both effectiveness and robustness using the improvement of hypervolume as the evaluating indicator. In addition, a lightweight optimization design of hoist sheaves shows that the proposed method can deal with real engineering problems, while significantly reducing the computational time and the number of expensive simulations of samples.

Novel multiobjective particle swarm optimization based on ranking and cyclic distance strategy

To effectively improve the convergence and diversity of the multiobjective particle swarm optimization (MOPSO), we proposed a novel MOPSO based on ranking and cyclic distance (RCDMOPSO) that comprehensively considers the spatial target and congestion information of particles. RCDMOPSO introduced a method namely global proportional ranking (GPR) which differs from nondominated ranking under the Pareto framework, and designed a novel external archive maintenance and the global selection strategies of learning sample by combining GPR with cyclic distance. In this paper, RCDMOPSO together with eight classic and state-of-the-art algorithms were examined on ZDT, UF, and DTLZ series to test functions. The results show that RCDMOPSO is highly competitive in achieving the objectives of both convergence and diversity. RCDMOPSO outperformed other popular algorithms such as MOPSOs and multiobjective genetic algorithms based on comprehensive performance evaluation indicators inverted generational distance and hypervolume, thus supporting that RCDMOPSO is an effective approach to tackle multiobjective optimization problems.

Knowledge derivation from Likert scale using Z-numbers

The Likert scale is an extensively used psychometric scale in questionnaire-based research. It is the most widely used approach for measuring responses in survey research. The data collected using the Likert scale is somewhat ambiguous in terms of data quality and latent variable assessment. Besides, there are numerous debates about the Likert scale regarding the accuracy of the data collected, the ranking order and distance between the scale options, the use of multiple scales for different questionnaires, the ability to combine scale options, the possibility of performing mathematical operations on the data collected using the Likert scale, and quantification of respondents’ negation choices. How to extract useful information from the Likert scale and resolve the aforementioned debates has been an interesting and open topic of discussion in recent years. To address this open issue, we deploy the Z-number in conjunction with the Likert scale since the former is a useful tool for generating information from objective and subjective data. A case study with numerical examples is provided to demonstrate the proposed technique. Additionally, the case study illustrates how Z-numbers might be used to resolve protracted disagreements on the usage of the Likert scale. One critical component of the proposed study is that it does not offer a new variety of scale but rather attempts to resolve long-standing controversies and issues using the conventional, regular Likert scale with Z-numbers.

Aggregation as Unsupervised Learning and its Evaluation

Regression uses supervised machine learning to find a model that combines several independent variables to predict a dependent variable based on ground truth (labeled) data, i.e., tuples of independent and dependent variables (labels). Similarly, aggregation also combines several independent variables to a dependent variable. The dependent variable should preserve properties of the independent variables, e.g., the ranking or relative distance of the independent variable tuples, and/or represent a latent ground truth that is a function of these independent variables. However, ground truth data is not available for finding the aggregation model. Consequently, aggregation models are data agnostic or can only be derived with unsupervised machine learning approaches. We introduce a novel unsupervised aggregation approach based on intrinsic properties of unlabeled training data, such as the cumulative probability distributions of the single independent variables and their mutual dependencies. We present an empirical evaluation framework that allows assessing the proposed approach against other aggregation approaches from two perspectives: (i) how well the aggregation output represents properties of the input tuples, and (ii) how well can aggregated output predict a latent ground truth. To this end, we use data sets for assessing supervised regression approaches that contain explicit ground truth labels. However, the ground truth is not used for deriving the aggregation models, but it allows for the assessment from a perspective (ii). More specifically, we use regression data sets from the UCI machine learning repository and benchmark several data-agnostic and unsupervised approaches for aggregation against ours. The benchmark results indicate that our approach outperforms the other data-agnostic and unsupervised aggregation approaches. It is almost on par with linear regression.

A novel flow routing algorithm based on non-dominated ranking and crowd distance sorting to improve the performance in SDN

A novel flow routing algorithm based on non-dominated ranking and crowd distance sorting to improve the performance in SDN

Team Standing’s Influence on Throwback and Current Team Apparel Purchase Intentions: The Moderating Role of Power Distance Belief

Despite the popularity of throwback apparel, few extant studies have investigated factors that differentially affect throwback and current apparel preferences. In this study, we suggest that the negative effects of poor team performance are especially relevant to low power distance belief fans and that throwback apparel is more resilient to these negative effects due to its nostalgic nature. Thus, the current study investigated the interplay between sport team ranking and power distance belief in shaping NBA fans’ preferences for current and throwback apparel. This study utilized a moderated moderation analysis of team ranking, product type (throwback vs. current team apparel), and power distance belief on purchase intentions. Data was collected from 401 NBA fans via Amazon Mechanical Turk. Findings suggest that, first, team ranking significantly influenced fans’ purchase intentions in general (i.e. both throwback and current apparel). Second, there was a significant interaction effect between team ranking and product type such that lower team rankings negatively influenced only current apparel and not throwback apparel. Third, high power distance belief was positively associated with purchase intentions of both throwback and current apparel. Finally, the three-way interaction effect was significant. Specifically, the two-way interaction between team ranking and product type was found to be significant only for low power distance belief fans and not high power distance belief fans.

Prediction of unconfined compressive strength of cement stabilized pavement materials

This paper evaluated and justified suitable prediction equations for unconfined compressive strength (UCS) of cement stabilized pavement materials. Equations by multiple linear regression analysis were also proposed. Data including pavement recycling base and subbase layers were collected from the Bureau of Material, Analysis, and Inspection, Department of Highways, Thailand. Multiple linear regression was conducted using the SPSS software. Three equations obtained from multiple linear regression and past researches were compared. Two criteria were considered in the selection of equations in order to check the accuracy and precision of each equation. First criterion was based on the predicted UCS vs. actual UCS graph. The slope and interception values of each graph were evaluated. Second criterion used two indices: ranking distance (RD) and ranking index (RI). For a good correlation, both these indices shall approach zero. By considering the statistical analysis outputs from the two criteria, a relationship between UCS and California Bearing Ratio – water cement ratio [CBR/(w/c)] proposed by Sunitsakul in 2012 was justified as a suitable equation to predict the UCS of cement stabilized pavement materials. The study also confirmed that the relationship proposed by Sawangsuriya in 2016 for fine-grained soil with plasticity index was not appropriate for the prediction of UCS because the majority of the samples were non-plastic.

Image retrieval via learning content-based deep quality model towards big data

Image retrieval aims to search specific image from large-scale datasets. Traditional text-based and content-based image retrieval approaches have shown competitive performance. However, both of which are limited by semantic gap, i.e., they cannot reflect human perception of images. To narrow semantic gap in image retrieval, this paper proposes a deep neural network (DNN) based image retrieval method, where saliency map is derived to form human gaze shifting paths by constraint metrics. More specifically, we first design a DNN-based image saliency prediction. Subsequently, we leverage image quality assessment (IQA) algorithm to select high-quality salient regions, which will be concatenated in sequence by using proposed constraint metrics to mimic human visual perception. Afterwards, we leverage the CNN-based architecture for deep representation acquisition of each images, where spatial structure among salient regions can be well preserved. Subsequently, based on the quality score of the query image, a series of candidate images whose quality scores are similar to that of the query image are derived. Finally, we engineer a ranking distance metric to refine the candidate images to achieve image retrieval. Extend experiments demonstrate that our method outperforms several state-of-the-art algorithms.

Comparison of Shear Wave Velocity Prediction Models to Yangtze River Deltaic Sediments Based on Piezocone Test Data

Seismic piezocone (SCPTu) data compiled from 37 sites in the southern Yangtze delta, China, are used to evaluate several existing empirical correlations in predicting the shear wave velocity of deltaic sediments. Four indices were employed in the assessment: the ratio of the estimated values to the measured Vs values, the root-mean-square error, the ranking index, and the ranking distance. It is shown that all the considered prediction models are biased, generally over-estimating the observed shear wave velocity of the predominant intermediate soils in the Yangtze delta. The results also reveal that the overall best correlation for the mixed deltaic soils is given by Robertson [Can Geotech J 46(11):1337–1355, 2009]. It is hypothesized that the unique depositional environment of the considered soils is the primary source of the observed prediction bias. Further statistical analysis indicates that partial drainage effects during cone penetration in deltaic intermediate sediments should be taken into careful consideration to derive reliable Vs values from CPTu data when applying correlations from the literature. More suitable site-specific shear wave velocity prediction correlations should be introduced, according to the recent findings on the Yangtze delta SCPTu database.

A Ranking Distance Analysis for Performance Assessment of UCS Versus SPT-N Correlations

It is important to know the reliability of the correlations unconfined compressive strength (UCS) versus blow count of standard penetration test (SPT-N) available in the literature for foundation design of constructions. However, selection of best performed equation verified with local data always becomes a primary issue for the site of interest foundation constructed. Thus, this paper investigates the performances of some UCS versus SPT-N correlations for the applicability to fine-grained soils in an interested area. A novel ranking measure called ranking distance (RD) that accounts equal weighting to the accuracy and precision of estimation has been used for the performance assessment of the equations, in comparison with alternative measures. The RD index is a comprehensive ranking measure for performing the dependability of an empirical equation with regard to the accuracy and precision, using the ratios of estimated and measured UCS. Dependent upon the analysis results in the study, the performances of equations have been ranked high, moderate, low and unacceptable (the worst equations). The equations have also been categorized whether they influence more weighting to precise or accuracy, or equal accuracy and precise during the estimations of UCS. From the results, it is concluded that the best performed estimation based on the RD is proposed by the equation of low plastic clay (Sivrikaya and Togrol, in: 5th international congress on advances in civil engineering, Istanbul, Turkey, pp 943–952, 2002; Eng Geol 86:52–69, 2006). Consequently, the study has successfully demonstrated the use of RD for assessing the best equation by confirming its results with the alternative methodologies compared. This could be beneficial for the experimenters in practice to attempt the validations of different empirical equations with different parameter through a good ranking procedure.

Review of shear-wave velocity prediction equations based on piezocone penetration test data: example from Yangtze River floodplain deposits at Nanjing, Jiangsu Province, China

Small-strain parameters of soils play an important role in modern engineering geology. A research database of seismic piezocone test (SCPTu) results has been collected to develop empirical correlations for shear-wave velocity ( V s ) prediction of recent floodplain deposits at Nanjing in the lower reaches of the Yangtze River. First, several existing cone penetration test (CPT)– V s or CPTu– V s correlations for general soils have been investigated. Four indices were used in the assessment, including the ratio of the estimated to measured V s values, the root mean square error, the ranking index and the ranking distance. It is observed that all the selected correlations are biased towards overestimation or underestimation of V s values for such floodplain deposits, demonstrating the need for a site-specific V s prediction model. Then, new correlations for Yangtze floodplain deposits were developed through multiple linear regression, the performance of which has been assessed through comparisons of predicted and observed V s values. The recommended correlation is entirely based directly on CPT data ( q c , f s and z ). The verification and calibration of this newly developed correlation for floodplain deposits constitute a useful contribution to the practice of geologists and engineers not only in the Yangtze delta region, but also in other similar depositional environments worldwide.

A novel ranking distance measure combining Cayley and Spearman footrule metrics

AbstractDefining the appropriate ranking distance measures among rankings is a classic area of study. The goal of our work is to identify a combination of methodologies, which is proven to be capable for the determination of a proper ranking system. In our study, we used 3 well‐established metrics: Kendall tau, Spearman footrule, and Cayley distance and a novel metric created by the combination of Cayley and Spearman footrule metrics. The results of the newly introduced metric depend on how fast we can trade a permutation of items to the reference permutation according to the Spearman footrule. On the other hand, the distance also depends on the number of cycles and the inversions in the cycle. Two case studies—chemometric data of phytonutrients of tomato varieties and sensometric data of orange juices—were used to test the performance of the studied ranking distance metrics. The properties of the new metric were compared to the traditional metrics regarding the normality of their distributions, significant number of differences between the rating objects, and the quality of the rankings. Results were validated by leave‐one‐out cross‐validation and significant differences by Wilcoxon matched pairs test.

Investigating the effects of subconcussion on functional connectivity using mass-univariate and multivariate approaches.

There are concerns about the effects of subconcussive head impacts in sport, but the effects of subconcussion on brain connectivity are not well understood. We hypothesized that college football players experience changes in brain functional connectivity not found in athletes competing in lower impact sports or healthy controls. These changes may be spatially heterogeneous across participants, requiring analysis methods that go beyond mass-univariate approaches commonly used in functional MRI (fMRI). To test this hypothesis, we analyzed resting-state fMRI data from college football (n = 15), soccer (n = 12), and lacrosse players (n = 16), and controls (n = 29) collected at preseason and postseason time points. Regional homogeneity (ReHo) and degree centrality (DC) were calculated as measures of local and long-range functional connectivity, respectively. Standard voxel-wise analysis and paired support vector machine (SVM) classification studied subconcussion's effects on local and global functional connectivity. Voxel-wise analyses yielded minimal findings, but SVM classification had high accuracy for college football's ReHo (87%, p = 0.009) and no other group. The findings suggest subconcussion results in spatially heterogeneous changes in local functional connectivity that may only be detectible with multivariate analyses. To determine if voxel-wise and SVM analyses had similar spatial patterns, region-average t-statistic and SVM weight values were compared using a measure of ranking distance. T-statistic and SVM weight rankings exhibited significantly low ranking distance values for all groups and metrics, demonstrating that the analyses converged on a similar underlying effect. Overall, this research suggests that subconcussion in football may produce local functional connectivity changes similar to concussion.

Use of ranking measure for performance assessment of correlations for the compression index

In order to provide a fast and cost-effective solution, particularly for preliminary evaluations in many design situations of constructions, a number of numerous empirical equations for estimation of compression index simply established with soil index properties are intensively used for consolidation settlement. However, they may not be appropriate when considered for different regions dependent upon local site conditions. Thus, it is important to know the performances of the empirical equations with local data. This paper investigates the performances of some of the empirical equations for estimation of compression index for fine-grained soils of Baghdad City along the Tigris River. Four criteria including error and ranking measurement were employed as bases of evaluation: root mean square error, the ratio of estimated to measured (laboratory) compression index, ranking index and ranking distance (RD). The last two (ranking index and RD), a relatively new approach of ranking measurement, involve with the accuracy and precision of estimated result with actual data. The assessment ultimately has been done regarding the RD, since it is a comprehensive statistical parameter that gives equal weight to the accuracy (mean) and precise (standard deviation) of estimation, as compared with others. It is found from the analysis results that the overall best estimation of compression index for the data of Baghdad was obtained by the empirical equations established with liquid limit proposed by Cozzolino and Azzouz, Krizek, and Corotis. The results indicate that the most reliable equation correlates compression index with liquid limit.

Assessment of empirical equations for the compression index of fine-grained soils in Missouri

The use of correlations and empirical relationships in geotechnical engineering provides a fast, cost-effective means of predicting the value of a parameter based on the values of certain other, possibly more easily determined, parameters. The correlation between two or more soil properties has been found to be dependent in varying degrees on soil type, the testing method used to obtain the numerical value of the parameter itself and the homogeneity of the soil. Many empirical correlations among soil properties have been published. These correlations, based on widely sourced data, may not be appropriate for local situations. Hence, there is a need for correlations that are based on local data. This paper evaluated the validity of published empirical equations for the index of fine-grained soils in Missouri, USA. Four indices were used in the assessment including the root mean square error, the ratio of the estimated to laboratory-determined compression index, the ranking index and the ranking distance. Results reveal the overall best correlations for the Southeast Region and "Other Regions" of Missouri are given by Azzouz et al. (Soils Found 16:19–29, 1976).

A multi-stage learning framework for intelligent system

As information technologies advance and user-friendly interfaces develop, the interaction between humans and computers, information devices, and new consumer electronics is increasingly gaining attention. One example that most people can relate to is Apple's innovation in human-computer interaction which has been used on many products such as iPod and iPhone. Siri, the intelligent personal assistant, is a typical application of machine-learning human-computer interaction. Algorithms in machine learning have been employed in many disciplines, including gesture recognition, speaker recognition, and product recommendation systems. While the existing learning algorithms compute and learn from a large quantity of data, this study proposes an improved learning to rank algorithm named MultiStageBoost. In addition to ranking data through multiple stages, the MultiStageBoost algorithm significantly improves the existing algorithms in two ways. Firstly, it classifies and filters data to small quantities and applies the Boosting algorithm to achieve faster ranking performance. Secondly, it enhances the original binary classification by using the reciprocal of fuzzily weighted membership as the ranking distance. The importance of data is revealed in their ranked positions. Usually data ranked in the front are given more attention than those ranked in the middle. For example, after ranking 10,000 pieces of data, the top 10, or at most 100, are the most important and relevant. Whether the data after the top ones are ranked precisely does not really matter. Due to this reason, this study has made improvement on the conventional methods of the pair-wise ranking approach. Not only are data classified and ranked binarily, they are also given different weights depending on whether they are concordant or discordant. Incorporating the concept of weighting into the ranking distance allows us to increase the precision of ranking. Results from experiments demonstrate that our proposed algorithm outperforms the conventional methods in three evaluation measures: [email protected], MAP, and NDCG. MultiStageBoost was then applied to speech recognition. However, we do not aim to improve the technology of speech recognition, but simply hope to provide evidences that MultiStageBoost can be used in the classification and ranking in speech recognition. Experiments show that the recognition optimization procedures established by this study are able to increase the recognition rate to over 95% in the personal computing device and industrial personal computer. It is expected that in the future this voice management system will accurately and effectively identify speakers answering the voice response questionnaire and will successfully carry out the functions in the choice of answers, paying the way for the formation of a virtual customer service person.

Affiliative relationships and reciprocity among adult male bonnet macaques (Macaca radiata) at Arunachala Hill, India

In captivity, male bonnet macaques (Macaca radiata) frequently express "friendship" toward one another, including affiliative behavior such as huddling, grooming, coalitionary support, and sitting in close proximity. The purpose of this study was to determine whether wild adult male bonnet macaques also express "friendship" by investigating whether or not (1) adult male bonnet macaques have affiliative social relationships with other males, (2) the strength of social relationships varies among dyads, (3) there is time-matched reciprocity in allogrooming among dyads, and if so, whether the level of reciprocity occurs within a bout of grooming, a day, or over 2 months (the limit of this study), and (4) a correlation exists between the strength of social relationships and dominance ranks among adult males. Focal samples totaling 150 hr on all seven adult males in one study group were conducted to record both agonistic and affiliative interactions. Agonistic interactions were used to construct a dominance hierarchy, whereas affiliative interactions (sitting in proximity to within 1 m with and without grooming) were used to quantify the existence and strength of social bonds within dyads. Results show that adult male bonnet macaques had differentiated affiliative relationships with other males in their group. There was little reciprocity of grooming within a bout of grooming or within a day, but greater reciprocity over the study period of 2 months. There was no correlation between dominance ranking distance and the strength of affiliative relationship within dyads; however, within dyads lower-ranking males groomed higher-ranking males more than vice versa. This study suggests that friendships in male bonnet macaques are characterized not by immediate tit-for-tat reciprocal altruism, but by reciprocity over a longer time span, and that affiliative social relationships may be less constrained by agonistic relationships than is the case in more despotic species of macaques.

Bayesian Visual Reranking

Visual reranking has been proven effective to refine text-based video and image search results. It utilizes visual information to recover “true” ranking list from the noisy one generated by text-based search, by incorporating both textual and visual information. In this paper, we model the textual and visual information from the probabilistic perspective and formulate visual reranking as an optimization problem in the Bayesian framework, termed Bayesian visual reranking. In this method, the textual information is modeled as a likelihood, to reflect the disagreement between reranked results and text-based search results which is called ranking distance. The visual information is modeled as a conditional prior, to indicate the ranking score consistency among visually similar samples which is called visual consistency. Bayesian visual reranking derives the best reranking results by maximizing visual consistency while minimizing ranking distance. To model the ranking distance more precisely, we propose a novel pair-wise method which measure the ranking distance based on the disagreement in terms of pair-wise orders. For visual consistency, we study three different regularizers to mine the best way for its modeling. We conduct extensive experiments on both video and image search datasets. Experimental results demonstrate the effectiveness of our proposed Bayesian visual reranking.