Nearest Neighbor Classification Rule for Mixtures of Discrete and Continuous Random Variables

In this paper very simple nonparametric classification rule for mixtures of discrete and continuous random variables is described. It is based on the method of nearest neighbor proposed by Cover and Hart (1967). The bounds on the limit of the nearest neighbor rule risks are given. Both lower and upper bound depend on the Bayes risk and the loss function. Finally the method is compared with other existing methods on some practical data set.     

Attention improves information flow between neuronal populations without changing the communication subspace

1. Download : Download high-res image (142KB)
2. Download : Download full-size image

     

The Social Environment of an Aggregating, Ant-Attended Treehopper (Hemiptera: Membracidae: Vanduzea arquata)

Many membracid treehoppers are attended by honeydew-harvesting ants. Ant mutualism often favors group living, which will in turn influence social interactios and communication. I investigated aspects of life history that underlie the social behavior of an aggregating, ant-attended treehopper. The number of adults, and their patterns of distribution, changes dramatically over the course of a season. Despite the relatively low vagility and high persistence in the same clump of host plants, individuals encounter a wide range of social environments. This aggregating species differs from solitary species in the clumped distribution of females, and possibly in the intensity of acoustic competition among males, but both aggregating and solitary species exhibit large temporal changes in density. A high degree of temporal and spatial variation in the social environment is probably characteristic of many insects and may be an important source of selection on insect communication.     

Analysis of Multiply Matched Retrospective Studies When Risk Factor Under Study is Discrete,With Two or More Levels

The odds ratio is known to closely approximate the relative risk when the disease is rare. Logistic regression models are often used to estimate such odds ratios, but here a different model is used which avoids the assumptions implicit in logistic modelling; it also has the advantage of providing a test of homogeneity for odds rat os in situations where the logistic model cannot.     

The International Atomic Energy Agency action plan on radiation protection of patients and staff in interventional procedures: Achieving change in practice

IntroductionThe International Atomic Energy Agency (IAEA) organized the 3rd international conference on radiation protection (RP) of patients in December 2017. This paper presents the conclusions on the interventional procedures (IP) session.Material and methodsThe IAEA conference was conducted as a series of plenary sessions followed by various thematic sessions. “Radiation protection of patients and staff in interventional procedures” session keynote speakers presented information on: 1) Risk management of skin injuries, 2) Occupational radiation risks and 3) RP for paediatric patients. Then, a summary of the session-related papers was presented by a rapporteur, followed by an open question-and-answer discussion.ResultsSixty-seven percent (67%) of papers came from Europe. Forty-four percent (44%) were patient studies, 44% were occupational and 12% were combined studies. Occupational studies were mostly on eye lens dosimetry. The rest were on scattered radiation measurements and dose tracking. The majority of patient studies related to patient exposure with only one study on paediatric patients. Automatic patient dose reporting is considered as a first step for dose optimization. Despite efforts, paediatric IP radiation dose data are still scarce. The keynote speakers outlined recent achievements but also challenges in the field. Forecasting technology, task-specific targeted education from educators familiar with the clinical situation, more accurate estimation of lens doses and improved identification of high-risk professional groups are some of the areas they focused on.ConclusionsManufacturers play an important role in making patients safer. Low dose technologies are still expensive and manufacturers should make these affordable in less resourced countries. Automatic patient dose reporting and real-time skin dose map are important for dose optimization. Clinical audit and better QA processes together with more studies on the impact of lens opacities in clinical practice and on paediatric patients are needed.     

Confidence Intervals for the Risk Ratio in Cohort Studies under Inverse Sampling

Three simple interval estimates for the risk ratio in inverse sampling are considered. The first two interval estimates are derived on the basis of Fieller's Theorem and the delta method with the logarithmic transformation, respectively. The third interval estimate is derived on the basis of an F-test statistic proposed by BENNETT (1981) for testing equal probabilities of a disease between two comparison groups when the disease is rare. To evaluate the performance of these three methods, a Monte Carlo simulation is used to compare the actual coverage probability with the nominal confidence level for each method and to estimate the expected length of the corresponding confidence interval in a variety of situations. On the basis of the results found in the simulation, we have concluded that the method with the logarithmic transformation is either equivalent to or better than the other two methods for all situations considered here.     

Fairy wrasses perceive and respond to their deep red fluorescent coloration

Fluorescence enables the display of wavelengths that are absent in the natural environment, offering the potential to generate conspicuous colour contrasts. The marine fairy wrasse Cirrhilabrus solorensis displays prominent fluorescence in the deep red range (650–700 nm). This is remarkable because marine fishes are generally assumed to have poor sensitivity in this part of the visual spectrum. Here, we investigated whether C. solorensis males can perceive the fluorescence featured in this species by testing whether the presence or absence of red fluorescence affects male–male interactions under exclusive blue illumination. Given that males respond aggressively towards mirror-image stimuli, we quantified agonistic behaviour against mirrors covered with filters that did or did not absorb long (i.e. red) wavelengths. Males showed significantly fewer agonistic responses when their fluorescent signal was masked, independent of brightness differences. Our results unequivocally show that C. solorensis can see its deep red fluorescent coloration and that this pattern affects male–male interactions. This is the first study to demonstrate that deep red fluorescent body coloration can be perceived and has behavioural significance in a reef fish.     

SOCIAL SELECTION AND THE EVOLUTION OF ANIMAL SIGNALS

Social selection is presented here as a parallel theory to sexual selection and is defined as a selective force that occurs when individuals change their own social behaviors, responding to signals sent by conspecifics in a way to influence the other individuals' fitness. I analyze the joint evolution of a social signal and behavioral responsiveness to the signal by a quantitative-genetic model. The equilibria of average phenotypes maintained by a balance of social selection and natural selection and their stability are examined for two alternative assumptions on behavioral responsiveness, neutral and adaptive. When behavioral responsiveness is neutral on fitness, a rapid evolution by runaway selection occurs only with enough genetic covariance between the signal and responsiveness. The condition for rapid evolution also depends on natural selection and the number of interacting individuals. When signals convey some information on signalers (e.g., fighting ability), behavioral responsiveness is adaptive such that a receiver's fitness is also influenced by the signal. Here there is a single point of equilibrium. The equilibrium point and its stability do not depend on the genetic correlation. The condition needed for evolution is that the signal is beneficial for receivers, which results from reliability of the signal. Frequency-dependent selection on responsiveness has almost no influence on the equilibrium and the rate of evolution.