Ordinal Distribution Research Articles

Ordinal distribution regression for gait-based age estimation

Computer vision researchers prefer to estimate age from face images because facial features provide useful information. However, estimating age from face images becomes challenging when people are distant from the camera or occluded. A person's gait is a unique biometric feature that can be perceived efficiently even at a distance. Thus, gait can be used to predict age when face images are not available. However, existing gait-based classification or regression methods ignore the ordinal relationship of different ages, which is an important clue for age estimation. This paper proposes an ordinal distribution regression with a global and local convolutional neural network for gait-based age estimation. Specifically, we decompose gait-based age regression into a series of binary classifications to incorporate the ordinal age information. Then, an ordinal distribution loss is proposed to consider the inner relationships among these classifications by penalizing the distribution discrepancy between the estimated value and the ground truth. In addition, our neural network comprises a global and three local sub-networks, and thus, is capable of learning the global structure and local details from the head, body, and feet. Experimental results indicate that the proposed approach outperforms state-of-the-art gait-based age estimation methods on the OULP-Age dataset.

Ordinal Pattern Based Entropies and the Kolmogorov-Sinai Entropy: An Update.

Different authors have shown strong relationships between ordinal pattern based entropies and the Kolmogorov–Sinai entropy, including equality of the latter one and the permutation entropy, the whole picture is however far from being complete. This paper is updating the picture by summarizing some results and discussing some mainly combinatorial aspects behind the dependence of Kolmogorov–Sinai entropy from ordinal pattern distributions on a theoretical level. The paper is more than a review paper. A new statement concerning the conditional permutation entropy will be given as well as a new proof for the fact that the permutation entropy is an upper bound for the Kolmogorov–Sinai entropy. As a main result, general conditions for the permutation entropy being a lower bound for the Kolmogorov–Sinai entropy will be stated. Additionally, a previously introduced method to analyze the relationship between permutation and Kolmogorov–Sinai entropies as well as its limitations will be investigated.

Characterization of the shape of height distribution of two-process profile

Two-process surfaces are more important than one-process topographies from the tribological point of view. However, most researchers understood the surface texture from a single-stratum viewpoint. Two-process topographies are more difficult to describe than one-process textures. The aim of this work was to select parameters characterizing the shape of the ordinate distribution of two-process profiles. A traditional description by the skewness Rsk and the kurtosis Rku used for one-process profiles is inadvisable for two-process profiles, since these parameters are strongly interrelated. Statistical dependencies among 17 non-dimensional parameters were analyzed on the basis of the linear coefficient of correlation. About 70 modeled and measured profiles were studied. The pair of ratios: Rp/Rz and Rq/Ra was selected. These parameters stable on typical surfaces are easy to calculate, the emptiness coefficient Rp/Rz is also tribologically important. It was also found that this pair of parameters could also describe the shape of the ordinate distribution of one-process profile. Especially the Rq/Ra ratio is a good alternative to the kurtosis Rku; these parameters are strongly inter-correlated, but the variation of the Rq/Ra ratio on typical surfaces is much lower.Sets of the following parameters: ypp–del and a–b from BETA distribution can also describe the shape of the ordinate distribution of two-process profiles.Extensions of the recommended parameters can be also used in the areal 3D analysis.

Can a single question about family members\u2019 sense of security during palliative care predict their well-being during bereavement? A longitudinal study during ongoing care and one year after the patient\u2019s death

BackgroundIt has been recognised that more evidence about important aspects of family members’ sense of security during palliative care is needed. The objectives of the study was: i) to discover what variables are associated with family members feeling secure during palliative care; ii) to develop a model of family members’ sense of security during palliative care, and iii) to evaluate if family members’ sense of security during ongoing palliative care predicts well-being during bereavement.MethodsBetween September 2009 and October 2010, 227 family members (of patients admitted to six Swedish palliative home care units) participated in the study (participation rate 75%) during ongoing care and 158 participated also 1 year after the patient’s death (70%). They answered a single question regarding the family members’ sense of security during the palliative care period. The question was constructed and validated by the researchers. Data were also collected using other questions and validated instruments and analysed stepwise with Generalized Linear Models (ordinal multinomial distribution and logit link).ResultsSixteen variables were positively related to family members’ sense of security during ongoing palliative care. The five variables with the highest importance were selected into the model (listed in decreasing importance): Family members’ mastery; nervousness and stress; self-efficacy; patient having gynaecological cancer; family members’ perceived quality of life. Moreover, the family members’ sense of security during ongoing palliative care predicted ten variables indicating their well-being 1 year after the patient’s death, e.g. psychological well-being, complicated grief symptoms, health related quality of life.ConclusionsThe findings reveal possibilities to identify family members at risk of negative adjustment to bereavement in clinical practice and may help to develop interventions to support family members during ongoing palliative care.

A financial hyperchaotic system with coexisting attractors: Dynamic investigation, entropy analysis, control and synchronization

Abstract This paper is concerned with dynamic and entropy analyses of a hyperchaotic financial system, as well as with its hyperchaos suppression and synchronization. The dynamic behaviour of the system is analyzed for several parameters and initial conditions making use of bifurcation diagrams, Lyapunov exponents and phase portraits. Moreover, entropy from resulting time series is also characterized by estimating ordinal pattern distributions. These analyses have been able to determine and locate accurately chaotic and periodic attractors in the system, thus enabling successful design of its control. In general, financial systems are not always completely synchronized; therefore, some robust synchronization technique should be considered. This study proposes a novel fuzzy disturbance-observer based integral terminal sliding mode control method for the hyperchaotic financial system. The presented control technique guarantees robustness against uncertainties, external disturbances and control input saturation. Fuzzy rules are employed to adaptively tune the gains of the proposed control scheme. Also, the fuzzy inference engine avoids the chattering problem in the system response. Simulation results illustrate the efficient performance of the proposed control technique in the presence of dynamic uncertainties, external disturbances and control input saturation.

On the Statistical Properties of Multiscale Permutation Entropy: Characterization of the Estimator's Variance.

Permutation Entropy (PE) and Multiscale Permutation Entropy (MPE) have been extensively used in the analysis of time series searching for regularities. Although PE has been explored and characterized, there is still a lack of theoretical background regarding MPE. Therefore, we expand the available MPE theory by developing an explicit expression for the estimator’s variance as a function of time scale and ordinal pattern distribution. We derived the MPE Cramér–Rao Lower Bound (CRLB) to test the efficiency of our theoretical result. We also tested our formulation against MPE variance measurements from simulated surrogate signals. We found the MPE variance symmetric around the point of equally probable patterns, showing clear maxima and minima. This implies that the MPE variance is directly linked to the MPE measurement itself, and there is a region where the variance is maximum. This effect arises directly from the pattern distribution, and it is unrelated to the time scale or the signal length. The MPE variance also increases linearly with time scale, except when the MPE measurement is close to its maximum, where the variance presents quadratic growth. The expression approaches the CRLB asymptotically, with fast convergence. The theoretical variance is close to the results from simulations, and appears consistently below the actual measurements. By knowing the MPE variance, it is possible to have a clear precision criterion for statistical comparison in real-life applications.

Plant functional indicators of vegetation response to climate change, past present and future: II. Modal plant functional types as response indicators for present and future climates

An assessment of plant functional indicators of vegetation response to climate change requires a science-based evaluation of functional linkages between plants and climate. This paper addresses the hypotheses outlined in the preceding paper: 1) A whole-plant system of modal plant functional types (PFTs) based on a core set of functional traits can provide an improved alternative to PFTs and traits used so far in models of vegetation response to climate change; 2) Modal PFTs are more efficient indicators of vegetation response to climate change than individual traits; 3) Improved plant functional selection criteria can lead to improved parameters in Earth System and Dynamic Global Vegetation Models. Present-day (1975 centred) plant–climate relationships were analyzed within a global climatic framework of 1327 (200 m2) sample sites covering all major biomes. Five regions were selected for their range of bioclimatic gradients (arctic-boreal; cool temperate-subtropical; humid equatorial; hot, cold deserts). Biophysical site data were recorded along gradient oriented transects (gradsects) using a standard protocol that included all vascular plant taxa and modal PFTs. Regression, ordination and species distribution modeling were used to assess plant–climate indicator values against ten bioclimatic variables including extremes of contemporary thermal, light (energy) and moisture availability and estimates for ‘present’ (1975) and year 2100 climate scenarios. Modal PFTs and individual traits were highly correlated in differing patterns with bioclimate in each of the five regions in both climate scenarios with PFTs being the best predictors. Each of the three hypotheses is supported by these results, indicating that preference should be given to modal assemblages rather than individual traits as response parameters in predictive vegetation models. The indicators identified here are but one element of the highly complex array of other factors that influence vegetation response to terrestrial environmental change such as resource use, species acclimation, invasive species and human population pressure.

Entropy measures for early detection of bearing faults

This paper investigates the performance of the 12 entropy-based features for the monitoring and detection of bearing faults. These entropy measures were proposed both in time, frequency and time–frequency domain. Probability mass function (PMF) was extracted from the time waveforms using four different methods: (i) via power spectral density, (ii) via ordinal pattern distribution, (iii) via wavelet packet tree and iv) ensemble empirical mode decomposition. Three different entropy measures were used in the article: (i) Shannon entropy, (ii) Rényi entropy and (iii) Jensen–Rényi divergence. A new bearing produces a vibration time series characterised by random noise without prominent periodic content. As soon as a fault develops, impulses are produced, what excites structural resonances generating a train of impulse responses. As defect grows, it becomes a distributed fault, and then no sharp impulses are generated but rather an amplitude modulated random noise signal. The proposed methodology has been applied to detect bearing faults by the analysis of two real bearing datasets, from run-to-failure experiments. Three bearings that presented different defects in the test (inner race fault, rolling elements fault and outer race fault) were analysed to validate the performance of the entropy-based features. The modified Z-score has been implemented and used as an index to detect changes of the entropy features. The results clearly demonstrate that the proposed approach represents a valuable non-parametric tool for early detection of anomalies in bearings vibration signals.

A mixed-effects location scale model for time-to-event data: A smoking behavior application

In general, mixed-effects location scale models (MELS) allow assessment of within-person and between-person variability with time-to-event data for outcomes that follow a normal or ordinal distribution. In this article, we extend the mixed-effects location scale model to time-to-event data in relation to smoking data. Better understanding of the time-graded within-person variability of factors involved in nicotine dependence can be helpful to researchers in their efforts to fine-tune smoking cessation programs. We illustrate the MELS model with data on time to first cigarette measured every day for 7 days in smokers randomized to two groups: a) those asked to keep smoking, or b) those asked to stop. Our results show that some individuals remain very stable in their time to first cigarette over the week, while others show variable patterns. The stable individuals smoked every day, did not smoke immediately upon waking, and were all in the group asked to keep smoking. Conversely, the variable individuals had at least one day during which they did not smoke, other days during which they smoked within the first 5 min of waking, and they were almost all in the group asked to quit smoking. These findings suggested that MELS have the potential to provide insights on how people try to stop smoking. More importantly, this model can be applied to other clinically important outcomes such as time to relapse in a range of cessation programs.

Calculation Possibilities of 3D Parameters for Surfaces with Irregular Roughness

Abstract In the scientific research, calculations of roughness parameters are carried out, with the aim of comparing measured values of roughness parameters with the calculated ones by normal random field equations. First of all, roughness measurement experiments for surfaces with irregular roughness are carried out to determine the roughness parameters and the ordinate distribution histograms using modern measuring equipment Taylor Hobson Talysurf Intra 50. Using the obtained experimental data, Pearson criterion calculations are made in order to check the compliance of surface ordinate distribution function to normal Gaussian distribution law. The obtained results showed that for all investigated samples the surface ordinate distribution function complies with normal Gaussian distribution law. The next step is the calculation of several 3D roughness parameters (from the standard ISO 25178-2). According to the obtained results it is concluded that the calculated values of surface roughness parameters Sa, Sp, Spc, Sdq, Sdr are quite close to the values obtained by measuring equipment Taylor Hobson. The acquired formulas may be applicable for determination of 3D roughness parameters.

Magnetic field of a radial tire after puncture caused by ferromagnetic elements

Tire, an element of wheel, is made in a sophisticated vulcanization process of many components and some of which such as: bead wire, belt and carcass exhibit ferromagnetic properties. Such components create variable in direction and intensity magnetic field, which expands around tire and the complete wheel. Since the layout of magnetic field is exceptional for every single wheel many of information might be obtained on the basis of it alteration. The reported since now application concentrates on rotational speed measurement, wheel rotations counting and therefore also vehicle linear speed and distance estimation. However up to the present the known solutions did not describe changes in magnetic field in case of damage induced by e.g. puncture caused by ferromagnetic elements. This paper’s aim is to test the thesis that it is possible to detect puncture in tire made by ferromagnetic element by using measurement and analysis of changes of magnetic flux density around tire. The tests were executed using original measuring device, designed especially for such experiments. It registers a magnetic profile, which consists of data series of magnetic flux density measured in this investigations 55 mm above tire’s tread and arranged along with rotation angle. Tire magnetic properties were assessed by using of circumferential magnetic profiles and parameters such as: minimum value (Mmin), maximum value (Mmax), peak to peak value (Mm), average value of ordinates of profile (Mb), skewness of ordinate distribution (Ms) and kurtosis of ordinate distribution (Mk). Magnetic profiles before after puncture were analysed as well as the parameters. Moreover differential signal caused by puncture were determined. It turned out that detected changes are directly related to tire damage and showing in rotation angle where puncture occurs.

Protocol for a prospective collaborative systematic review and meta-analysis of individual patient data from randomized controlled trials of vasoactive drugs in acute stroke: The Blood pressure in Acute Stroke Collaboration, stage-3.

Rationale Despite several large clinical trials assessing blood pressure lowering in acute stroke, equipoise remains particularly for ischemic stroke. The "Blood pressure in Acute Stroke Collaboration" commenced in the mid-1990s focussing on systematic reviews and meta-analysis of blood pressure lowering in acute stroke. From the start, Blood pressure in Acute Stroke Collaboration planned to assess safety and efficacy of blood pressure lowering in acute stroke using individual patient data. Aims To determine the optimal management of blood pressure in patients with acute stroke, including both intracerebral hemorrhage and ischemic stroke. Secondary aims are to assess which clinical and therapeutic factors may alter the optimal management of high blood pressure in patients with acute stroke and to assess the effect of vasoactive treatments on hemodynamic variables. Methods and design Individual patient data from randomized controlled trials of blood pressure management in participants with ischemic stroke and/or intracerebral hemorrhage enrolled during the ultra-acute (pre-hospital), hyper-acute (<6 h), acute (<48 h), and sub-acute (<168 h) phases of stroke. Study outcomes The primary effect variable will be functional outcome defined by the ordinal distribution of the modified Rankin Scale; analyses will also be carried out in pre-specified subgroups to assess the modifying effects of stroke-related and pre-stroke patient characteristics. Key secondary variables will include clinical, hemodynamic and neuroradiological variables; safety variables will comprise death and serious adverse events. Discussion Study questions will be addressed in stages, according to the protocol, before integrating these into a final overreaching analysis. We invite eligible trials to join the collaboration.

Predicting Aesthetic Score Distribution Through Cumulative Jensen-Shannon Divergence

Aesthetic quality prediction is a challenging task in the computer vision community because of the complex interplay with semantic contents and photographic technologies. Recent studies on the powerful deep learning based aesthetic quality assessment usually use a binary high-low label or a numerical score to represent the aesthetic quality. However the scalar representation cannot describe well the underlying varieties of the human perception of aesthetics. In this work, we propose to predict the aesthetic score distribution (i.e., a score distribution vector of the ordinal basic human ratings) using Deep Convolutional Neural Network (DCNN). Conventional DCNNs which aim to minimize the difference between the predicted scalar numbers or vectors and the ground truth cannot be directly used for the ordinal basic rating distribution. Thus, a novel CNN based on the Cumulative distribution with Jensen-Shannon divergence (CJS-CNN) is presented to predict the aesthetic score distribution of human ratings, with a new reliability-sensitive learning method based on the kurtosis of the score distribution, which eliminates the requirement of the original full data of human ratings (without normalization). Experimental results on large scale aesthetic dataset demonstrate the effectiveness of our introduced CJS-CNN in this task.

Reinstatement of the Southern Andean Genus Stenodraba (Brassicaceae) Based on Molecular Data and Insights from its Environmental and Geographic Distribution

Stenodraba (Brassicaceae) included a group of eight species distributed along the Andes of South-Central Argentina and Chile. All of its species are currently treated in Pennellia (Tribe Halimolobeae) and Weberbauera (Tribe Thelypodieae). However, the phylogeny of Stenodraba and its tribal placement were never analyzed usingmolecular data. The lack of such studies, as well as the paucity of herbarium collections suggesting that some species are vulnerable and/or endangered, prompted us to address the molecular phylogeny of Stenodraba. For this purpose, we generated comprehensive molecular phylogenies using nuclear (ITS) and plastid (trnL-F and trnH-psbA) data and conducted different niche comparisons in the environmental and geographic spaces using climate data processed both by ordination and species distribution modelling (SDM) techniques. Results from phylogenetic analyses demonstrated that Stenodraba belongs to the South American tribe Eudemeae and is related to the genera Aschersoniodoxa, Brayopsis, Dactylocardamum, and Eudema. Stenodraba species formed two strongly supported clades, and although molecular data did not recover monophyly of the genus, this hypothesis could not be rejected with our data. The main clades were differentiated in their climatic niches (both in the environmental and geographical spaces), and niche overlap was greater within than between clades. Systematic implications, including a key distinguishing Stenodraba from the remaining genera of Eudemeae and a synopsis of its species, are also provided. The new combination S. lagunae is proposed.

Model-based co-clustering for ordinal data

A model-based co-clustering algorithm for ordinal data is presented. This algorithm relies on the latent block model embedding a probability distribution specific to ordinal data (the so-called BOS or Binary Ordinal Search distribution). Model inference relies on a Stochastic EM algorithm coupled with a Gibbs sampler, and the ICL-BIC criterion is used for selecting the number of co-clusters (or blocks). The main advantage of this ordinal dedicated co-clustering model is its parsimony, the interpretability of the co-cluster parameters (mode, precision) and the possibility to take into account missing data. Numerical experiments on simulated data show the efficiency of the inference strategy, and real data analyses illustrate the interest of the proposed procedure.

Abstract TMP24: Alteplase-Tenecteplase Trial Evaluation for Stroke Thrombolysis (ATTEST 2)

Background: IV thrombolysis with alteplase, the only medical treatment currently approved for acute ischaemic stroke, significantly increases the probability of excellent recovery. A recent trial has demonstrated that the modified tissue plasminogen activator tenecteplase at a dose of 0.4mg/kg is of similar safety and efficacy to alteplase in acute stroke. In addition to having simpler administration, tenecteplase 0.25mg/kg is also potentially superior to alteplase with respect to efficacy, based on meta-analysis of small trials. More data are required to establish the true risk-benefit profile compared with alteplase. Objectives &amp; Methods: ATTEST-2 will establish whether tenecteplase is superior to alteplase by undertaking a prospective randomised open blinded end-point (PROBE) trial in patients eligible for IV thrombolysis based on non-contrast CT imaging. The study opened to recruitment in Dec 2016. 60 UK centres will recruit 1870 patients. Outcome: Primary outcome is the distribution of modified Rankin Scale (mRS) outcomes at day 90, determined by the Rankin Focused Assessment method, analysed by ordinal distribution ("shift") analysis of the of scores in intervention and control groups. Conclusion: An agent with superior risk:benefit ratio to alteplase would potentially extend thrombolytic treatment a greater proportion of patients than at present and reduce the need for mechanical thrombectomy. This trial will contribute to the optimisation of reperfusion strategies.

Generating Multivariate Ordinal Data via Entropy Principles.

When conducting robustness research where the focus of attention is on the impact of non-normality, the marginal skewness and kurtosis are often used to set the degree of non-normality. Monte Carlo methods are commonly applied to conduct this type of research by simulating data from distributions with skewness and kurtosis constrained to pre-specified values. Although several procedures have been proposed to simulate data from distributions with these constraints, no corresponding procedures have been applied for discrete distributions. In this paper, we present two procedures based on the principles of maximum entropy and minimum cross-entropy to estimate the multivariate observed ordinal distributions with constraints on skewness and kurtosis. For these procedures, the correlation matrix of the observed variables is not specified but depends on the relationships between the latent response variables. With the estimated distributions, researchers can study robustness not only focusing on the levels of non-normality but also on the variations in the distribution shapes. A simulation study demonstrates that these procedures yield excellent agreement between specified parameters and those of estimated distributions. A robustness study concerning the effect of distribution shape in the context of confirmatory factor analysis shows that shape can affect the robust [Formula: see text] and robust fit indices, especially when the sample size is small, the data are severely non-normal, and the fitted model is complex.

Encoder settings impact on intra-prediction-based descriptors for video retrieval

Intra-prediction modes (IPMs) of H.264/AVC, as visual feature components, are easily extracted from the compressed domain. However, in spite of their efficiency and effectiveness, they can be sensitive to encoder settings such as encoder-type and encoding-profile. In content-based video retrieval using different encoders between a video and its copy can affect performance. Similarly, applying different encoding-profiles can also have a negative impact. Experiments with different IPM-based descriptors, on a subset of the TRECVID/CCD 2011 collection with content-preserving visual distortions, compare the performance of four H.264/AVC encoding profiles (High10, High, Baseline and Main) and also investigate the impact of three encoders (FFmpeg, MediaCoder and JM). The research shows that ordinal pattern distribution of unified IPMs can improve their tolerance to changes in encoder settings. Furthermore, it is shown that a Correlogram rather than a Histogram of the IPMs is more robust with respect to the impact of encoding-profiles and encoder-types.

Random Walk Null Models for Time Series Data

Permutation entropy has become a standard tool for time series analysis that exploits the temporal and ordinal relationships within data. Motivated by a Kullback–Leibler divergence interpretation of permutation entropy as divergence from white noise, we extend pattern-based methods to the setting of random walk data. We analyze random walk null models for correlated time series and describe a method for determining the corresponding ordinal pattern distributions. These null models more accurately reflect the observed pattern distributions in some economic data. This leads us to define a measure of complexity using the deviation of a time series from an associated random walk null model. We demonstrate the applicability of our methods using empirical data drawn from a variety of fields, including to a variety of stock market closing prices.

Bayesian inference for health inequality and welfare using qualitative data

We show how to use Bayesian inference to compare two ordinal categorical distributions commonly occurring with data on self-reported health status. Procedures for computing probabilities for first and second order stochastic dominance and S-dominance are described, along with methodology for obtaining posterior densities for health inequality indexes. The techniques are applied to four years of data on Australian self-reported health status.