The problem of Bi-level programming is to reduce or maximize the function of the target by having another target function within the constraints. This problem has received a great deal of attention in the programming community due to the proliferation of applications and the use of evolutionary algorithms in addressing this kind of problem. Two non-linear bi-level programming methods are used in this paper. The goal is to achieve the optimal solution through the simulation method using the Monte Carlo method using different small and large sample sizes. The research reached the Branch Bound algorithm was preferred in solving the problem of non-linear two-level programming this is because the results were better.

A three-stage learning algorithm for deep multilayer perceptron (DMLP) with effective weight initialisation based on sparse auto-encoder is proposed in this paper, which aims to overcome difficulties in training deep neural networks with limited training data in high-dimensional feature space. At the first stage, unsupervised learning is adopted using sparse auto-encoder to obtain the initial weights of the feature extraction layers of the DMLP. At the second stage, error back-propagation is used to train the DMLP by fixing the weights obtained at the first stage for its feature extraction layers. At the third stage, all the weights of the DMLP obtained at the second stage are refined by error back-propagation. Network structures an

Authors in this work design efficient neural networks, which are based on the modified Levenberg - Marquardt (LM) training algorithms to solve non-linear fourth - order three -dimensional partial differential equations in the two kinds in the periodic and in the non-periodic - Periodic. Software reliability growth models are essential tools for monitoring and evaluating the evolution of software reliability. Software defect detection events that occur during testing and operation are often treated as counting processes in many current models. However, when working with large software systems, the error detection process should be viewed as a random process with a continuous state space, since the number of faults found during testin

In this research velocity of moving airplane from its recorded digital sound is introduced. The data of sound file is sliced into several frames using overlapping partitions. Then the array of each frame is transformed from time domain to frequency domain using Fourier Transform (FT). To determine the characteristic frequency of the sound, a moving window mechanics is used, the size of that window is made linearly proportional with the value of the tracked frequency. This proportionality is due to the existing linear relationship between the frequency and its Doppler shift. An algorithm was introduced to select the characteristic frequencies, this algorithm allocates the frequencies which satisfy the Doppler relation, beside that the tra

In this paper, a compact genetic algorithm (CGA) is enhanced by integrating its selection strategy with a steepest descent algorithm (SDA) as a local search method to give I-CGA-SDA. This system is an attempt to avoid the large CPU time and computational complexity of the standard genetic algorithm. Here, CGA dramatically reduces the number of bits required to store the population and has a faster convergence. Consequently, this integrated system is used to optimize the maximum likelihood function lnL(φ1, θ1) of the mixed model. Simulation results based on MSE were compared with those obtained from the SDA and showed that the hybrid genetic algorithm (HGA) and I-CGA-SDA can give a good estimator of (φ1, θ1) for the ARMA(1,1) model. Anot

The consensus algorithm is the core mechanism of blockchain and is used to ensure data consistency among blockchain nodes. The PBFT consensus algorithm is widely used in alliance chains because it is resistant to Byzantine errors. However, the present PBFT (Practical Byzantine Fault Tolerance) still has issues with master node selection that is random and complicated communication. The IBFT consensus technique, which is enhanced, is proposed in this study and is based on node trust value and BLS (Boneh-Lynn-Shacham) aggregate signature. In IBFT, multi-level indicators are used to calculate the trust value of each node, and some nodes are selected to take part in network consensus as a result of this calculation. The master node is chosen

BP algorithm is the most widely used supervised training algorithms for multi-layered feedforward neural net works. However, BP takes long time to converge and quite sensitive to the initial weights of a network. In this paper, a modified cuckoo search algorithm is used to get the optimal set of initial weights that will be used by BP algorithm. And changing the value of BP learning rate to improve the error convergence. The performance of the proposed hybrid algorithm is compared with the stan dard BP using simple data sets. The simulation result show that the proposed algorithm has improved the BP training in terms of quick convergence of the solution depending on the slope of the error graph.