Big data analysis has important applications in many areas such as sensor networks and connected healthcare. High volume and velocity of big data bring many challenges to data analysis. One possible solution is to summarize the data and provides a manageable data structure to hold a scalable summarization of data for efficient and effective analysis. This research extends our previous work on developing an effective technique to create, organize, access, and maintain summarization of big data and develops algorithms for Bayes classification and entropy discretization of large data sets using the multi-resolution data summarization structure. Bayes classification and data discretization play essential roles in many learning algorithms such a

Contents IJPAM: Volume 116, No. 3 (2017)

This article studied some linear and nonlinear optical characteristics of different pH solutions from anthocyanin dye extract at 180 oC from red cabbage. First, the linear spectral characteristics, including absorption and transmittance in the range 400-800 nm for anthocyanin solution 5% v/v with different pHs, were achieved utilizing a UV/VIS spectrophotometer. The experimental results reveal a shift in the absorption toward the longer wavelength direction as pH values increment. Then, the nonlinear features were measured using the Z-scan technique with a CW 532 nm laser to measure the nonlinear absorption coefficient through an open aperture. A close aperture (diameter 2 mm) calculates the nonlinear refractive index. The open Z-scan sh

The estimation of the parameters of linear regression is based on the usual Least Square method, as this method is based on the estimation of several basic assumptions. Therefore, the accuracy of estimating the parameters of the model depends on the validity of these hypotheses. The most successful technique was the robust estimation method which is minimizing maximum likelihood estimator (MM-estimator) that proved its efficiency in this purpose. However, the use of the model becomes unrealistic and one of these assumptions is the uniformity of the variance and the normal distribution of the error. These assumptions are not achievable in the case of studying a specific problem that may include complex data of more than one model. To

The main intention of this study was to investigate the development of a new optimization technique based on the differential evolution (DE) algorithm, for the purpose of linear frequency modulation radar signal de-noising. As the standard DE algorithm is a fixed length optimizer, it is not suitable for solving signal de-noising problems that call for variability. A modified crossover scheme called rand-length crossover was designed to fit the proposed variable-length DE, and the new DE algorithm is referred to as the random variable-length crossover differential evolution (rvlx-DE) algorithm. The measurement results demonstrate a highly efficient capability for target detection in terms of frequency response and peak forming that was isola

In this paper, a subspace identification method for bilinear systems is used . Wherein a " three-block " and " four-block " subspace algorithms are used. In this algorithms the input signal to the system does not have to be white . Simulation of these algorithms shows that the " four-block " gives fast convergence and the dimensions of the matrices involved are significantly smaller so that the computational complexity is lower as a comparison with " three-block " algorithm .