The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
The integration of the Smart Grid concept into the electric grid brings to the need for an active participation of small and medium players. This active participation can be achieved using decentralized decisions, in which the end consumer can manage loads regarding the Smart Grid needs. The management of loads must handle the users' preferences, wills and needs. However, the users' preferences, wills...
This paper deals with a 6-bar mechanism, which! finds its application in a precision deep drawing press. The approach for the kinematic simulation is based on loop closure analysis, which has been performed to derive expressions for slider displacement. The results are consolidated using Artificial Neural Network (ANN). Genetic Algorithm (GA) is used for optimizing the dimensions of the mechanism,...
In this paper, a High Precise Optimization Algorithm for manipulating multi-layered feed-forward neural network is studied. Its basic principle is: defining neural network average error as objective function, weights and thresholds as design variables, through design variables rationally sorted, objective function is dynamically formed. Compared the new method with BP, the optimum step-length can...
In this paper a hybrid approach is introduced to solve multiple response problems. In the proposed method signal to noise (SN) ratio is computed and then SN ratios for unexperimented treatments are estimated using artificial neural network. The SN ratios are converted into a process performance index by applying process capability ratio and VIKOR method, so the treatments can be ranked and the best...
Diversity improvement methods generally implement niching and fitness sharing schemes. In this work we propose a general principle based on using the inverse mapping from objective space to decision space that allows for the creation of diverse solutions in a direct manner. When analytical forms of objective functions are known, we propose a method of generating set-valued inverse maps, in functional...
In order to solve the problem of BP neural network (such as sensitive to the initial weights, easy to sink into local minimum, slow velocity of convergence and so on) in short-term stock prediction, a new stock predition method is created. Through optimizing initial weights of BP neural network by PSO of global stochastic optimization idea can the predition model which is based on the PSO and BP be...
The sigmoid function is a widely used, bounded activation function for feedforward neural networks (FFNNs). A problem with using bounded activation functions is that it necessitates scaling of the data to suit the fixed domain and range of the function. Alternatively the activation function itself can be adapted by learning the gradient and range of the function alongside the FFNN weights. The purpose...
Artificial Bee Colony or ABC is one of the newest additions to the class of population based Nature Inspired Algorithms (NIA). In the present study we suggest some modifications in the structure of basic ABC to further improve its performance. The corresponding algorithm proposed in the present study is named Intermediate ABC (I-ABC). In I-ABC, the potential food sources are generated by using the...
The choice of optimal topology of neural network (NN) is one of the most important factor for the success of any application. Generally the optimization of neural network (NN) has based on cross validation method which requires more learning and test procedures. This paper proposes the use of sophisticated methods, it is one of the pruning NN methods as: "Optimal Brain Damage" (OBD) and...
One of the important tasks of system operators in electricity network is Unit commitment. Considering development of electricity market restructuring in generation side, the Generating and Transition costs will be decreased in a high scale by right committing of this operation. This paper proposes to represent compromise improved TS and enhanced PSO in the sense of accuracy and speed of solution....
Fresh water and cold which are produced by desalination and cooling processes are simultaneously utilized in many factories and industries. Energy saving can be possible by integration of desalination and cooling systems. This paper contributes to a new integration scheme of the reverse osmosis (RO) and refrigeration systems. Compressor intercooler and condenser waste heat are recovered to increase...
In this study, a new artificial neuron network model called the meta-controlled Boltzmann machine is introduced. The meta-controlled Boltzmann machine model includes the McCulloch-Pitts model, the Hop field network, and also the Boltzmann machine. The proposed method are applied both diffusion processes and simulated annealing. The convergence proof of the proposed method is shows in this paper. Meta-controlled...
The essence of traditional ANN algorithm is to transfer the input-output problem of a group sample into a nonlinear programming problem. And it is a learning method to use iteration to work out weight problem along the negative gradient direction, but its convergence rate is slow and it is easy to fall into local minimum. Previously, there are many improved methods to solve the above-mentioned drawbacks...
This paper presents a neural circuit for solving linear programming problem (LPP). The objective is to minimize a first order cost function subject to linear constraints. The dynamic analog circuit, consisting of N identical units for N variable problem, can solve the general LPP and always converges to the optimal solution in constant time, irrespective of the initial conditions, which is of the...
Optimal Power Flow (OPF) is one of the most vital tools for power system operation analysis, which requires a complex mathematical formulation to find the best solution. Conventional methods such as Linear Programming, Newton-Raphson and Non-linear Programming were previously offered to tackle the complexity of the OPF. However, with the emergence of artificial intelligence, many novel techniques...
Premature convergence is the main obstacle to the application of genetic algorithm. This paper makes improvement on traditional genetic algorithm by linear scale transformation of fitness function, using self-adaptive crossover and mutation probability and adopting close relative breeding avoidance method. Simulation results show that the improved algorithm outperforms traditional genetic algorithm...
This paper proposes a systematic approach of determining the optimal amplitude taper for a shared aperture linear array that possesses true-time-delay (TTD) multiple beam functionality. Conventionally, uniform taper is used to achieve maximum gain, while Taylor taper is widely used in low side lobe applications. However, when multiple beams are generated across ultra-wideband frequencies, they seem...
In this paper, we investigate the use of a backpropagation neural network (BPNN) to estimate the mass and depth of buried radioactive materials, i.e., depleted uranium (DU). A Lanthanum bromide(LaBr) detector is employed to collect the data for buried targets with different mass and at different depths. Due to the sparseness and randomness of a gamma spectrum, spectral transformation methods are implemented...
We present a method of performing kernel space domain description of a dataset with incomplete entries without the need for imputation, allowing kernel features of a class of data with missing features to be rigorously described. This addresses the problem that absent data completion is usually required before kernel classifiers, such as support vector domain description (SVDD), can be applied; equally,...
We have examined the realization opportunity of the numerical weighed residuals method based on the approximate neuronet functions constructed on the computational nodes set with coordinates changing depending on the neuronet model local accuracy for the hydrodynamics equations solution.
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.