Hyperbolic Secant Distribution Research Articles

Hyperbolic Secant representation of the logistic function: Application to probabilistic Multiple Instance Learning for CT intracranial hemorrhage detection

Multiple Instance Learning (MIL) is a weakly supervised paradigm that has been successfully applied to many different scientific areas and is particularly well suited to medical imaging. Probabilistic MIL methods, and more specifically Gaussian Processes (GPs), have achieved excellent results due to their high expressiveness and uncertainty quantification capabilities. One of the most successful GP-based MIL methods, VGPMIL, resorts to a variational bound to handle the intractability of the logistic function. Here, we formulate VGPMIL using Pólya-Gamma random variables. This approach yields the same variational posterior approximations as the original VGPMIL, which is a consequence of the two representations that the Hyperbolic Secant distribution admits. This leads us to propose a general GP-based MIL method that takes different forms by simply leveraging distributions other than the Hyperbolic Secant one. Using the Gamma distribution we arrive at a new approach that obtains competitive or superior predictive performance and efficiency. This is validated in a comprehensive experimental study including one synthetic MIL dataset, two well-known MIL benchmarks, and a real-world medical problem. We expect that this work provides useful ideas beyond MIL that can foster further research in the field.

Volatility Forecasting Using Quasi-Score-Driven Models with an Application to the Coronavirus Pandemic Period

Abstract We study the statistical and volatility forecasting performances of the recent quasi-score-driven EGARCH (exponential generalized autoregressive conditional heteroscedasticity) models. We compare the quasi-score-driven EGARCH models with GARCH, asymmetric power ARCH (A-PARCH), and all relevant score-driven EGARCH models of the literature. For score-driven and quasi-score-driven EGARCH, we use the following seven score-driven probability distributions: Student’s t-distribution; general error distribution (GED); generalized t-distribution (Gen-t); skewed generalized t-distribution (Skew-Gen-t); exponential generalized beta distribution of the second kind (EGB2); normal-inverse Gaussian distribution (NIG); Meixner distribution (MXN). We use all combinations of those distributions for (i) the probability distribution of the dependent variable, and (ii) the probability distribution which defines the quasi-score function updating term of the quasi-score-driven filters. We use daily data for the Standard & Poor’s 500 (S&P 500) index. We find that both in-sample and out-of-sample, quasi-score-driven EGARCH is superior to GARCH, A-PARCH, and score-driven EGARCH. We report in-sample results for the period of January 2000 to December 2020, providing evidence in favor of the quasi-score-driven EGARCH model for the last two decades. We report out-of-sample volatility forecasting results for a period within the coronavirus disease 2019 (COVID-19) pandemic, providing evidence in favor of the quasi-score-driven EGARCH model for a crisis period.

Robust generalized hyperbolic secant algorithm for nonlinear active noise control

In nonlinear active noise control (ANC) system where the primary noise obeys non-Gaussian distribution, the traditional filter-s least mean square (FsLMS) algorithm is hardly satisfactory. In order to surmount this deficiency, a novel generalized hyperbolic secant function with lp norm (FsGHSFP) algorithm is proposed for nonlinear ANC system, which designs a robust optimization criterion utilizing the generalized hyperbolic secant distribution function. The FsGHSFP algorithm has robust noise attenuation capability for non-Gaussian noise, but suffers from the problem of tuning the parameter. To address this problem, an improved FsGHSFP (IFsGHSFP) algorithm is developed by taking advantage of the fact that continuous mixed norm does not need to adjust norm parameter. Moreover, in order to strike a balance between convergence and misalignment, thereby further enhancing the robustness of the ANC system, a convex combination algorithm of IFsGHSFP is suggested. The robustness mechanism of the proposed algorithms is analyzed, as well as stability conditions and computational complexity. It is verified by simulations that the proposed algorithms accelerate the convergence speed and improve the noise attenuation performance. In addition, the experimental results further validate the effectiveness of the proposed algorithms.

Unified quantum theory of electrochemical kinetics by coupled ion-electron transfer.

A general theory of coupled ion-electron transfer (CIET) is presented, which unifies Marcus kinetics of electron transfer (ET) with Butler-Volmer kinetics of ion transfer (IT). In the limit of large reorganization energy, the theory predicts normal Marcus kinetics of "electron-coupled ion transfer" (ECIT). In the limit of large ion transfer energies, the theory predicts Butler-Volmer kinetics of "ion-coupled electron transfer" (ICET), where the charge transfer coefficient and exchange current are connected to microscopic properties of the electrode/electrolyte interface. In the ICET regime, the reductive and oxidative branches of Tafel's law are predicted to hold over a wide range of overpotentials, bounded by the ion-transfer energies for oxidation and reduction, respectively. The probability distribution of transferring electron energies in CIET smoothly interpolates between a shifted Gaussian distribution for ECIT (as in the Gerischer-Marcus theory of ET) to an asymmetric, fat-tailed Meixner distribution centered at the Fermi level for ICET. The latter may help interpret asymmetric line shapes in x-ray photo-electron spectroscopy (XPS) and Auger electron spectroscopy (AES) for metal surfaces in terms of shake-up relaxation of the ionized atom and its image polaron by ICET. In the limit of large overpotentials, the theory predicts a transition to inverted Marcus ECIT, leading to a universal reaction-limited current for metal electrodes, dominated by barrierless quantum transitions. Uniformly valid, closed-form asymptotic approximations are derived that smoothly transition between the limiting rate expressions for ICET and ECIT for metal electrodes, using simple but accurate mathematical functions. The theory is applied to lithium intercalation in lithium iron phosphate (LFP) and found to provide a consistent description of the observed current dependence on overpotential, temperature and concentration. CIET theory thus provides a critical bridge between quantum electrochemistry and electrochemical engineering, which may find many other applications and extensions.

Astronomik bir veri kümesi uygulaması ile alfa çarpık hiperbolik sekant dağılımı

This work demonstrates the attractivity of the alpha-skew hyperbolic secant distribution, a new skewed distribution based on the alpha-skew technique and the hyperbolic secant distribution. In the first part, we determine its main features, including its cumulative distribution function, modality, non-central moments, skewness, kurtosis, moment generating function and characteristic function. The remaining part is devoted to the model applicability in a statistical context. As a first step, the parameters are estimated by maximum likelihood estimates. Then, we perform a data fitting experiment and compare the values of the Akaike and Bayesian information criteriawith those of some other similar distributions. By considering an astronomical dataset and valuable competitors also based on the alpha-skew technique, the alpha-skew hyperbolic secant distribution turns out to be the best.

TWO-SIDED GENERALIZED HYPERBOLIC SECANT DISTRIBUTION WITH REAL DATA APPLICATIONS AND MODEL COMPARISONS

In this paper, we use the structure of the standard two-sided power distribution to implement a new version of the hyperbolic secant distribution. This new distribution is more flexible than the hyperbolic secant distribution when it comes to interpreting data presenting an abrupt change in values. In the first part of the paper, we show some of its properties, such as the shape behavior of the probability density and hazard rate functions, and the analysis of moment-type measures. Then, the statistical side of the underlying model is explored. We provide the maximum likelihood estimates for the model parameters, as well as an efficient algorithm to calculate them. After this, to demonstrate the potential of the proposed modeling strategy, we present three real data applications. The beta-normal, power-normal, Kuramaswamy-normal and two-sided generalized normal distribution models are considered as competitors. The results are favorable to the proposed model.

Inverse stereographic hyperbolic secant distribution: a new symmetric circular model by rotated bilinear transformations

The inverse stereographic projection (ISP), or equivalently, bilinear transformation, is a method to produce a circular distribution based on an existing linear model. By the genesis of the ISP method, many important circular models have been provided by many researchers. In this study, we propose a new symmetric unimodal/bimodal circular distribution by the rotated ISP method considering the hyperbolic secant distribution as a baseline distribution. Rotation means that fixing the origin and rotating all other points the same amount counterclockwise. Considering the effect of rotation on the circular distribution to be obtained with the bilinear transformation, it is seen that it actually induces a location parameter in the obtained circular probability distribution. We analyze some of the stochastic properties of the proposed distribution. The methods for the parameter estimation of the new circular model and the simulation-based compare results of these estimators are extensively provided by the paper. Furthermore, we compare the fitting performance of the new model according to its well-known symmetric alternatives, such as Von-Misses, and wrapped Cauchy distributions, on a real data set. From the information obtained by the analysis on the real data, we say that the fitting performance of the new distribution is better than its alternatives according to the criteria frequently used in the literature.

Prediction accuracy of volatility using the score-driven Meixner distribution: an application to the Dow Jones

ABSTRACT The score-driven QAR-EGARCH-M (quasi-autoregressive, exponential generalized autoregressive conditional heteroscedasticity-in-mean) model using the Meixner distribution is introduced to improve the prediction accuracy of GARCH. QAR-EGARCH-M extends the recent EGARCH-M model in a statistically innovative way because a new score-driven filter is included in the risk premium. Volatility forecasts of QAR-EGARCH-M, EGARCH-M, and GARCH, all with leverage effects, are compared for the Dow Jones Industrial Average (DJIA). QAR-EGARCH-M is superior to EGARCH-M and GARCH, which is relevant for DJIA options investors at Chicago Mercantile Exchange Globex and Chicago Board Options Exchange.

The sum of two independent polynomially-modified hyperbolic secant random variables with application in computational finance

In this paper, by reshaping the hyperbolic secant distribution using Hermite polynomial, we devise a polynomially-modified hyperbolic secant distribution which is more flexible than secant distribution to capture the skewness, heavy-tailedness and kurtosis of data. As a portfolio possibly consists of multiple assets, the distribution of the sum of independent polynomially-modified hyperbolic secant random variables is derived. In exceptional cases, we evaluate risk measures such as value at risk and expected shortfall (ES) for the sum of two independent polynomially-modified hyperbolic secant random variables. Finally, using real datasets from four international computers stocks, such as Adobe Systems, Microsoft, Nvidia and Symantec Corporations, the effectiveness of the proposed model is shown by the goodness of Gram–Charlier-like expansion of hyperbolic secant law, for performance of value at risk and ES estimation, both in and out of the sample period.

The extended slash distribution of the sum of two independent logistic random variables

The concept of extended slash distribution is introduced. For the extended slash distribution of the sum of two independent logistic random variables, the characteristic function, moments, absolute moments and conditional tail expectation are obtained. It is shown that this distribution is related to the logistic and the generalized hyperbolic secant distributions by means of several distributional identities. The log-concavity of the distribution is studied. The self-decomposability of this distribution is also proved. Finally, an asymmetric distribution based on the extended slash distribution of the sum of two independent logistic random variables is introduced. Closed form expressions for the moments and for the conditional tail expectation of this skewed distribution are obtained. This distribution is a fairly flexible model for leptokurtic data as can be seen by fitting it to several datasets.

Generalized hyperbolic secant distribution: Properties, estimation, and applications

In this study, we define a generalized hyperbolic secant distribution. Poor fit to heavy tailed data sets is repeatedly obtained by existing three-parameter distributions. Only three parameters are considered in the proposed new distribution and it fits a heavy left- and right-tailed data better than various existing distributions. We study some properties of the new distribution, namely, mode, skewness, kurtosis, hazard function, moments, mean deviation, and Shannon entropy. Seven different frequentist methods for estimating the parameters are briefly described. A simulation study is also conducted to compare the performances of the proposed methods of estimation. The usefulness of the new model is demonstrated by applying it to fit two real-life data.

Mixture representations of noncentral distributions

With any symmetric distribution μ on the real line we may associate a parametric family of noncentral distributions as the distributions of where X is a random variable with distribution μ. The classical case arises if μ is the standard normal distribution, leading to the noncentral chi-squared distributions. It is well known that these may be written as Poisson mixtures of the central chi-squared distributions with odd degrees of freedom. We obtain such mixture representations for the logistic distribution and for the hyperbolic secant distribution. We also derive alternative representations for chi-squared distributions and relate these to representations of the Poisson family. While such questions originated in parametric statistics they also appear in the context of the generalized second Ray–Knight theorem, which connects Gaussian processes and local times of Markov processes.

3D-printed phononic crystal lens for elastic wave focusing and energy harvesting

We explore elastic wave focusing and enhanced energy harvesting by means of a 3D-printed Gradient-Index Phononic Crystal Lens (GRIN-PCL) bonded on a metallic host structure. The lens layer is fabricated by 3D printing a rectangular array of cylindrical nylon stubs with varying heights. The stub heights are designed to obtain a hyperbolic secant distribution of the refractive index to achieve the required phase velocity variation in space, hence the gradient-index lens behavior. Finite element simulations are performed on composite unit cells with various stub heights to obtain the lowest antisymmetric mode Lamb wave band diagrams, yielding a correlation between the stub height and refractive index. The elastic wave focusing performance of lenses with different design parameters (gradient coefficient and aperture size) is simulated numerically under plane wave excitation. It is observed that the focal points of the wider aperture lens designs have better consistency with the analytical beam trajectory results. Experiments are conducted using a PA2200 nylon lens bonded to an aluminum plate to demonstrate wave focusing and enhanced energy harvesting within the 3D-printed GRIN-PCL domain. The piezoelectric energy harvester at the focal region of the GRIN-PCL produces 3 times more power output than the baseline harvester at the same distance in the flat plate region. The results show that 3D printing can provide a simple and practical method for implementing phononic crystal concepts with minimal modification of the host structure.

A nonparametric Bayesian model for system identification based on a super‐Gaussian distribution

AbstractIn the acoustic signal processing applications of finite impulse response (FIR) system identification, it is important to develop the identification method that is robust to super‐Gaussian noises. Moreover, the identification method that estimates the FIR coefficients and the order of the unknown system is required, because the order of the unknown system is unavailable in advance. Therefore, in this paper, we propose a nonparametric Bayesian (NPB) model for FIR system identification using a super‐Gaussian likelihood and the beta‐Bernoulli process. In the proposed NPB model, we employ the hyperbolic secant distribution for the likelihood function. Then, we derive the inference algorithm to simultaneously estimate the FIR coefficients and the order of the unknown system. Our inference algorithm based on a hybrid inference approach combining the majorization‐minimization (MM) algorithm and the Gibbs sampler. The simulation results suggest that the proposed method outperforms the conventional identification algorithms in a super‐Gaussian noise environment.

Asymmetric generalizations of symmetric univariate probability distributions obtained through quantile splicing

Balakrishnan et al. proposed a two-piece skew logistic distribution by making use of the cumulative distribution function (CDF) of half distributions as the building block, to give rise to an asymmetric family of two-piece distributions, through the inclusion of a single shape parameter. This paper proposes the construction of asymmetric families of two-piece distributions by making use of quantile functions of symmetric distributions as building blocks. This proposition will enable the derivation of a general formula for the L-moments of two-piece distributions. Examples will be presented, where the logistic, normal, Student’s t(2) and hyperbolic secant distributions are considered.

Poisson type operators on the Fock space of type B

The main purpose of this paper is to propose an (α, q)-analogue of the Poisson operators on the Fock space of type B in the sense of Bożejko, Ejsmont, and Hasebe [J. Funct. Anal. 269, 1769–1795 (2015)] and to find a probability law of this operator. We shall show that the probability law is expressed by the q-Meixner distribution in the sense of Definition 3.2. Our results contain not only symmetric distributions as in Bożejko-Ejsmont-Hasebe but also the non-symmetric ones such as free Poisson, q and q2-deformations of Poisson, Pascal, Gamma, and Meixner distributions.

СООТНОШЕНИЯ ЭЛЕМЕНТОВ И ПОСЛЕДОВАТЕЛЬНОСТЕЙ В ЧИСЛОВОЙ ПРИЗМЕ

A numerical prism, previously introduced by the author as an ordered set regarding the research of a three-parameter probability distribution of the hyperbolic-cosine type, which is a generalization of the known two-parameter Meixner distribution, is being considered. In geometry-related terminology, elements of a numerical prism are the coefficients of moment-forming polynomials for the specified distribution, which are obtained with the use of both differential and algebraic recurrence correlations. Each one of the infinite number of elements depends on three indices determining its position in a prism. Fixation of one or two indices results in cross-sections of the prism, which are numerical triangles or sequences. Among them, there are such well-known cross-sections as the Stirling number triangle, number triangle of coefficients in the Bessel polynomials, sequences of tangent and secant numbers, and others. However, the majority of numerical sets in the prism’s cross-sections have never been described in literature before. Considering the structure and construction algorithm, cross-sections of the numerical prism turn out to be interconnected not only by the general construction formula but also by certain correlations. As a result, formulas of connection between various groups of elements are presented in the article. In particular, expansion of secant numbers for the sum of products grouped by the number of tangent numbers’ cofactors with specification of corresponding coefficients in the expansion, representation (automatic expression) of elements of a sequence of alternating secant and tangent number through the previous ones, as well as a number of other correlations for the sequences and particular elements is determined.

On the Infinitely Divisible of Meixner Distribution

The log-returns of most financial data show a significant leptokurtosis. For the better fit we showed a special levy process which is called the Meixner process. The Meixner distribution belongs to the class of infinitely divisible distribution chracterized by using characteristic function and it was proposed as a model for represented efficiently of the log-returns of financial data. The perfect fit of underlying Meixner distribution performing by using goodness of fit test.

Geometric dispersion models with real quadratic v-functions

Geometric dispersion models, characterized by their v-functions, are recently introduced arising from geometric sums of exponential dispersion models and they exhibit many potential applications. In this paper, we classify all the real quadratic v-functions. Up to affinity, there are only six types of such models with unbounded domain: asymmetric Laplace, geometric and the four remaining ones are obtained by the exponential mixtures of Poisson, gamma, negative binomial and generalized hyperbolic secant distributions. Further, we find the seventh one which is geometric hybrid distribution, purely a quadratic v-function on bounded domain and, classically steep as well as unbounded ones but not geometric-steep.

On Generating a New Family of Distributions Using the Tangent Function

In this paper, a method for generating a new family of univariate continuous distributions using the tangent function is proposed. Some general properties of this new family are discussed: hazard function, quantile function, Renyi and Shannon entropies, symmetry, and existence of the non-central n^th moment. Some new members as sub-families in the T-X family of distributions are provided. Three members of the new sub-families are defined and discussed: the five-parameter Normal-Generalized hyperbolic secant distribution (NGHS), the five-parameter Gumbel-Generalized hyperbolic secant distribution (GGHS), and the six-parameter Generalized Error-Generalized hyperbolic secant distribution (GEHS), the shapes of these distributions were found: skewed right, skewed left, or symmetric, and unimodal, bimodal, or trimodal. Finally, to demonstrate the usefulness and the capability of the distributions, two real data sets are used and the results are compared with other known distributions.