Probability Density Function Analysis Based on Logistic Regression Model

The data fitting level in probability density function analysis has great influence on the analysis results, so it is of great significance to improve the data fitting level. Therefore, a probability density function analysis method based on logistic regression model is proposed. The logistic regression model with kernel function is established, and the optimal window width and mean square integral error are selected to limit the solution accuracy of probability density function. Using the real probability density function, the probability density function with the smallest error is obtained. The estimated probability density function is analyzed from two aspects of consistency and convergence speed. The experimental results show that compared with the traditional probability density function analysis method, the probability density function analysis method based on logistics regression model has a higher fitting level, which is more suitable for practical research projects.

Variability Assessment of the Compressive and Tensile Strength of Fibred Earthen Composites

Earthen composites (rammed earth, cob, adobe, daub, CEB...) are experiencing renewed interest from builders due to the many advantages of these building materials, and in particular their eco-friendliness. Nevertheless, the widespreading of these materials, as certified materials and conforming to construction standards, comes against the lack of data concerning their mechanical properties. Indeed, the literature generally gives the average values of the properties without indicating the number of specimens tested neither the distribution of the data. Yet, the mean value of the compressive strength is not enough to assess the reliability of a given earthen composite to build a wall and it would be better to indicate the value of a defined percentile (characteristic value just like with concrete composites). The aim of this paper is to analyze the data about the mechanical properties (tensile and compressive strength) obtained on different formulations of cob including natural fibres or not. The tests performed allowed to determine the probability density function and the average values, the standard deviation and the percentiles, for the various properties.

Manifold-adaptive dimension estimation revisited

Data dimensionality informs us about data complexity and sets limit on the structure of successful signal processing pipelines. In this work we revisit and improve the manifold adaptive Farahmand-Szepesvári-Audibert (FSA) dimension estimator, making it one of the best nearest neighbor-based dimension estimators available. We compute the probability density function of local FSA estimates, if the local manifold density is uniform. Based on the probability density function, we propose to use the median of local estimates as a basic global measure of intrinsic dimensionality, and we demonstrate the advantages of this asymptotically unbiased estimator over the previously proposed statistics: the mode and the mean. Additionally, from the probability density function, we derive the maximum likelihood formula for global intrinsic dimensionality, if i.i.d. holds. We tackle edge and finite-sample effects with an exponential correction formula, calibrated on hypercube datasets. We compare the performance of the corrected median-FSA estimator with kNN estimators: maximum likelihood (Levina-Bickel), the 2NN and two implementations of DANCo (R and MATLAB). We show that corrected median-FSA estimator beats the maximum likelihood estimator and it is on equal footing with DANCo for standard synthetic benchmarks according to mean percentage error and error rate metrics. With the median-FSA algorithm, we reveal diverse changes in the neural dynamics while resting state and during epileptic seizures. We identify brain areas with lower-dimensional dynamics that are possible causal sources and candidates for being seizure onset zones.

Generalized fractal Jensen and Jensen–Mercer inequalities for harmonic convex function with applications

In this paper, we present a generalized Jensen-type inequality for generalized harmonically convex function on the fractal sets, and a generalized Jensen–Mercer inequality involving local fractional integrals is obtained. Moreover, we establish some generalized Jensen–Mercer-type local fractional integral inequalities for harmonically convex function. Also, we obtain some generalized related results using these inequalities on the fractal space. Finally, we give applications of generalized means and probability density function.

Local Asymptotic Normality Complexity Arising in a Parametric Statistical Lévy Model

We consider statistical experiments associated with a Lévy process X = X t t ≥ 0 observed along a deterministic scheme i u n , 1 ≤ i ≤ n . We assume that under a probability ℙ θ , the r.v. X t , t > 0 , has a probability density function > o , which is regular enough relative to a parameter θ ∈ 0 , ∞ . We prove that the sequence of the associated statistical models has the LAN property at each θ , and we investigate the case when X is the product of an unknown parameter θ by another Lévy process Y with known characteristics. We illustrate the last results by the case where Y is attracted by a stable process.

Probability Density Functions for Prediction Using Normal and Exponential Distribution

When data are found to be realizations of a specific distribution, constructing the probability density function based on this distribution may not lead to the best prediction result. In this study, numerical simulations are conducted using data that follow a normal distribution, and we examine whether probability density functions that have shapes different from that of the normal distribution can yield larger log-likelihoods than the normal distribution in the light of future data. The results indicate that fitting realizations of the normal distribution to a different probability density function produces better results from the perspective of predictive ability. Similarly, a set of simulations using the exponential distribution shows that better predictions are obtained when the corresponding realizations are fitted to a probability density function that is slightly different from the exponential distribution. These observations demonstrate that when the form of the probability density function that generates the data is known, the use of another form of the probability density function may achieve more desirable results from the standpoint of prediction.

Hypothetical Control of Fatal Quarrel Variability

Wars, terrorist attacks, as well as natural catastrophes typically result in a large number of casualties, whose distributions have been shown to belong to the class of Pareto’s inverse power laws (IPLs). The number of deaths resulting from terrorist attacks are herein fit by a double Pareto probability density function (PDF). We use the fractional probability calculus to frame our arguments and to parameterize a hypothetical control process to temper a Lévy process through a collective-induced potential. Thus, the PDF is shown to be a consequence of the complexity of the underlying social network. The analytic steady-state solution to the fractional Fokker-Planck equation (FFPE) is fit to a forty-year fatal quarrel (FQ) dataset.

Flexible Power-Normal Models with Applications

The main object of this paper is to propose a new asymmetric model more flexible than the generalized Gaussian model. The probability density function of the new model can assume bimodal or unimodal shapes, and one of the parameters controls the skewness of the model. Three simulation studies are reported and two real data applications illustrate the flexibility of the model compared with traditional proposals in the literature.

Bifurcation Analysis of an Energy Harvesting System with Fractional Order Damping Driven by Colored Noise

Vibration energy harvester, which can convert mechanical energy to electrical energy so as to achieve self-powered micro-electromechanical systems (MEMS), has received extensive attention. In order to improve the efficiency of vibration energy harvesters, many approaches, including the use of advanced materials and stochastic loading, have been adopted. As the viscoelastic property of advanced materials can be well described by fractional calculus, it is necessary to further discuss the dynamical behavior of the fractional-order vibration energy harvester. In this paper, the stochastic P-bifurcation of a fractional-order vibration energy harvester subjected to colored noise is investigated. Variable transformation is utilized to obtain the approximate equivalent system. Probability density function for the amplitude of the system response is derived via the stochastic averaging method. Numerical results are presented to verify the proposed method. Critical conditions for stochastic P-bifurcation are provided according to the change of the peak number for the probability density function. Then bifurcation diagrams in the parameter planes are analyzed. The influences of parameters in the system on the mean harvested power are discussed. It is found that the mean harvested power increases with the enhancement of the noise intensity, while it decreases with the increase of the fractional order and the correlation time.