A Boxplot for Circular Data Buttarazzi, Davide; Pandolfo, Giuseppe; Porzio, Giovanni C.
Biometrics,
December 2018, Letnik:
74, Številka:
4
Journal Article
Recenzirano
The box-and-whiskers plot is an extraordinary graphical tool that provides a quick visual summary of an observed distribution. In spite of its many extensions, a really suitable boxplot to display ...circular data is not yet available. Thanks to its simplicity and strong visual impact, such a tool would be especially useful in all fields where circular measures arise: biometrics, astronomy, environmetrics, Earth sciences, to cite just a few. For this reason, in line with Tukey's original idea, a Tukey-like circular boxplot is introduced. Several simulated and real datasets arising in biology are used to illustrate the proposed graphical tool.
The γ decay of the elusive narrow, near-threshold proton resonance in 11B was investigated at Laboratori Nazionali di Legnaro (INFN) in a particle-γ coincidence experiment, using the 6Li(6Li,pγ) ...fusion-evaporation reaction and the GALILEO-GALTRACE setup. No clear signature was found for a possible E1 decay to the 1/21−, first-excited state of 11B, predicted by the Shell Model Embedded in the Continuum (SMEC) with a branching of 0.98−69+167×10−3 with respect to the dominant particle-decaying modes. The statistical analysis of the γ-ray spectrum provided an average upper limit of 2.37×10−3 for this γ-ray branching, with a global significance of 5σ. On the other hand, by imposing a global confidence level of 3σ, a significant excess of counts was observed for E=γ9300(20) keV, corresponding to a resonance energy of 11429(20) keV (namely 200(20) keV above the proton separation energy of 11B) and a γ-ray branching of 1.12(35)×10−3. This result is compatible with the SMEC calculations, potentially supporting the existence of a near-threshold proton resonance in 11B.
The excited states of N=44 ^{74}Zn were investigated via γ-ray spectroscopy following ^{74}Cu β decay. By exploiting γ-γ angular correlation analysis, the 2_{2}^{+}, 3_{1}^{+}, 0_{2}^{+}, and ...2_{3}^{+} states in ^{74}Zn were firmly established. The γ-ray branching and E2/M1 mixing ratios for transitions deexciting the 2_{2}^{+}, 3_{1}^{+}, and 2_{3}^{+} states were measured, allowing for the extraction of relative B(E2) values. In particular, the 2_{3}^{+}→0_{2}^{+} and 2_{3}^{+}→4_{1}^{+} transitions were observed for the first time. The results show excellent agreement with new microscopic large-scale shell-model calculations, and are discussed in terms of underlying shapes, as well as the role of neutron excitations across the N=40 gap. Enhanced axial shape asymmetry (triaxiality) is suggested to characterize ^{74}Zn in its ground state. Furthermore, an excited K=0 band with a significantly larger softness in its shape is identified. A shore of the N=40 "island of inversion" appears to manifest above Z=26, previously thought as its northern limit in the chart of the nuclides.
Distance-based depths for directional data PANDOLFO, Giuseppe; PAINDAVEINE, Davy; PORZIO, Giovanni C.
Canadian journal of statistics,
12/2018, Letnik:
46, Številka:
4
Journal Article
Recenzirano
Directional data are constrained to lie on the unit sphere of ℝq for some q ≥ 2. To address the lack of a natural ordering for such data, depth functions have been defined on spheres. However, the ...depths available either lack flexibility or are so computationally expensive that they can only be used for very small dimensions q. In this work, we improve on this by introducing a class of distance-based depths for directional data. Irrespective of the distance adopted, these depths can easily be computed in high dimensions too. We derive the main structural properties of the proposed depths and study how they depend on the distance used. We discuss the asymptotic and robustness properties of the corresponding deepest points. We show the practical relevance of the proposed depths in two applications, related to (i) spherical location estimation and (ii) supervised classification. For both problems, we show through simulation studies that distance-based depths have strong advantages over their competitors.
Les données directionnelles prennent leurs valeurs dans la sphère unité de ℝq pour un certain q ≥ 2. Pour pallier le manque d’ordre naturel de telles données, des fonctions de profondeur ont été définies sur la sphère. Cependant, les profondeurs disponibles manquent de flexibilité ou sont si coûteuses d’un point de vue calculatoire qu’elles ne peuvent être utilisées qu’en dimension très petite. Les auteurs améliorent la situation en introduisant une classe de fonctions de profondeur directionnelle fondées sur des distances. Indépendamment de la distance choisie, ces profondeurs peuvent être calculées aussi en grande dimension. Ils dérivent les principales propriétés structurelles des profondeurs proposées et étudient comment ces propriétés dépendent de la distance adoptée. Les auteurs considèrent également les propriétés asymptotiques et de robustesse des points correspondants les plus profonds. Ils montrent l’intérêt pratique des concepts introduits dans le cadre de deux applications liées (i) à l’estimation de la position sphérique et (ii) à la classification supervisée. Pour ces deux problèmes, les auteurs montrent à travers des simulations que les profondeurs fondées sur les distances ont des avantages importants par rapport à leurs compétiteurs.
Contaminated training sets can highly affect the performance of classification rules. For this reason, robust supervised classifiers have been introduced. Amongst the many, this work focuses on ...depth-based classifiers, a class of methods which have been proven to enjoy some robustness properties. However, no robustness studies are available for them within a directional data framework. Here, their performance under some directional contamination schemes is evaluated. A comparison with the directional Bayes rule is also provided. Different directional specific contamination scenarios are introduced and discussed: antipodality and orthogonality of the contaminated distribution mean, and the directional mean shift outlier model.
Photodynamic therapy (PDT) is a selective modality of killing targeted cells, mostly known for its application in neoplasms. PDT can be considered to be an alternative method for the elimination of ...periodontal bacteria from the pocket without harms for the resident tissues. Therefore, PDT may replace systemic antibiotics and enhance the effect of mechanical treatments of periodontal defects. This effort focused on the in vitro sensitization of periopathogens (Aggregatibacter actinomycetemcomitans, Porphyromonas gingivalis, Fusobacterium nucleatum and Prevotella intermedia) Toluidine Blue mediated and on the use of a Diode laser emitting source. The objective of this research was to evaluate the bactericidal in vitro effect of laser diodes 830 nm (as the light source) after photosensitization with Toluidine Blue (TBO) on the following periopathogenic bacteria: Aggregatibacter actinomycetemcomitans, Porphyromonas gingivalis, Fusobacterium nucleatum and Prevotella intermedia. After evaluating the effect on the single bacterial strain, the ability of Diode Laser to disrupt the structure of biofilms produced by A. actinomycetemcomitans after photosensitization with TBO was also analyzed. The study suggests that the association of TBO and diode laser light 830 nm is effective for the killing of bacteria strains and determines the photoinactivation of Aggregatibacter biofilms. In summary, photodynamic therapy has effectively shown its capabilities and, therefore, it can be considered a valid alternative approach to antimicrobial therapy of periodontitis.
The paper investigates the link between student relations and their performances at university. A social influence mechanism is hypothesized as individuals adjusting their own behaviors to those of ...others with whom they are connected. This contribution explores the effect of peers on a real network formed by a cohort of students enrolled at a graduate level in an Italian University. Specifically, by adopting a network effects model, the relation between interpersonal networks and university performance is evaluated assuming that student performance is related to the performance of the other students belonging to the same group. By controlling for individual covariates, the network results show informal contacts, based on mutual interests and goals, are related to performance, while formal groups formed temporarily by the instructor have no such effect.
The main goal of supervised learning is to construct a function from labeled training data which assigns arbitrary new data points to one of the labels. Classification tasks may be solved by using ...some measures of data point centrality with respect to the labeled groups considered. Such a measure of centrality is called data depth. In this paper, we investigate conditions under which depth-based classifiers for directional data are optimal. We show that such classifiers are equivalent to the Bayes (optimal) classifier when the considered distributions are rotationally symmetric, unimodal, differ only in location and have equal priors. The necessity of such assumptions is also discussed.