We consider the problem of inference in a linear regression model in which the relative ordering of the input features and output labels is not known. Such datasets naturally arise from experiments in which the samples are shuffled or permuted during the protocol. In this work, we propose a framework that treats the unknown permutation as a latent variable. We maximize the likelihood of observa...

Data publishing techniques have led to breakthroughs in several areas. These tools provide a promising direction. However, when they are applied private or sensitive data such as patient medical records, the published may divulge critical information. In order address this issue, we propose differential method (SSKM_DP) based on SFLA-Kohonen network, which perturbs attributes maximum informatio...

The parameter identification problem can be modeled as a non-linear optimization problem. In this problem, some unknown parameters of a mathematical model presented by an ordinary differential equation using some experimental data must be estimated. This paper presents a shuffled frog leaping algorithm for solving parameter identification problem. An opposition-based initialization strategy is ...

This papers studies methods to improve the cryptographic quality of random or pseudorandom sequences by modifying the order of the original sequence. A new algorithm Cryshu is suggested, which produces its shuffled output data at the rate of the input data. 1 Cryptographic Aspects of Shuffling Random and Pseudorandom Sequences A deck of cards is shuffled to arrange the cards in a random sequenc...

Today using evolutionary programing for solving complex, nonlinear mathematical problems like optimum power flow is commonly in use. These types of problems are naturally nonlinear and the conventional mathematical methods aren’t powerful enough for achieving the desirable results. In this study an Optimum Power Flow problem solved by means of minimization of fuel costs for IEEE 30 buses test s...

SUMMARY Assessing the statistical significance of structured RNA predicted from multiple sequence alignments relies on the existence of a good null model. We present here a random shuffling algorithm, Multiperm, that preserves not only the gap and local conservation structure in alignments of arbitrarily many sequences, but also the approximate dinucleotide frequencies. No shuffling algorithm t...

Artificial Atom Algorithm is an optimization technique that developed inspired by nature. This algorithm used for both continues problems and discrete in previous studies. In this study, arrangement would increase the success of was envisaged. For purpose, ionic bond function has been improved benefiting algorithmic step Shuffled Frog Leaping Algorithm. As a result updates, search space narrowe...