Serwis Infona wykorzystuje pliki cookies (ciasteczka). Są to wartości tekstowe, zapamiętywane przez przeglądarkę na urządzeniu użytkownika. Nasz serwis ma dostęp do tych wartości oraz wykorzystuje je do zapamiętania danych dotyczących użytkownika, takich jak np. ustawienia (typu widok ekranu, wybór języka interfejsu), zapamiętanie zalogowania. Korzystanie z serwisu Infona oznacza zgodę na zapis informacji i ich wykorzystanie dla celów korzytania z serwisu. Więcej informacji można znaleźć w Polityce prywatności oraz Regulaminie serwisu. Zamknięcie tego okienka potwierdza zapoznanie się z informacją o plikach cookies, akceptację polityki prywatności i regulaminu oraz sposobu wykorzystywania plików cookies w serwisie. Możesz zmienić ustawienia obsługi cookies w swojej przeglądarce.
It is known that the single genetic algorithm (SGA) has many disadvantages, and the paper presents an improved genetic algorithm, which with a new genetic algorithm based on the fitness values and group diversity to optimize the BP neural network. Experiment has shown that the improved genetic algorithm cannot only solve the problems of initializing the group fitness exception, but also can various...
This paper presents an algorithm for online adaptation of the kernel width parameter in information theoretic cost functions used for adaptive system training. Training algorithms which optimize information theoretic quantities like entropy involve choosing a kernel size for their sample estimators. The kernel size essentially dictates the nature of the performance surface of the cost function over...
As nanoscale devices such as OG-CNTFETs are under studies and may be used in a near futur, we choose to investigate in wich application domain such components may be of the most interest. In this paper we present how neural networks can be used to implement functions on nano-scale components. This method has been tested in the image processing application field.
This paper proposes the wavelet neural network (WNN) based on clonal selection algorithm (CLONALG) for using in fault diagnosis of marine diesel engine. CLONALG initializes the WNN's weights and biases, the ergodic weights and biases are used for further net-training. The fault diagnosis for marine diesel engine is conducted by using the well-trained wavelet network, in order to illustrate the performance...
BP neutral network is a method to fuse datas from several dissimilar sensors for more precise results, but its low convergence rate and easily falling into local minimum often decrease the fusion precision. In order to overcome this drawback, we combined BP neutral network with genetic algorithm, and optimized connection weights and threshold value of BP neutral network by genetic algorithm. Then...
ANN using BP is widely used in power load forecasting. But there are some existed problem of the BP algorithm: (1) Convergence speed is slow, usually convergence needs more than one thousand times; (2) Objective function is prone to getting into local minimum.. How to overcome the shortcoming that convergence speed is slow and network is prone to trapping in local minimum has not been resolved. Training...
In order to improve the performance of switched reluctance driving system, it is necessary to build an accurate switched reluctance motor (SRM) model. In this paper, a nonlinear flux-linkage model and a torque model of SRM are presented by using the measured accurate flux-linkage data, torque data and nonlinear mapping ability of BP neural network, which is based on fast self-configuring algorithm...
A method based on ant colony algorithm (ACA) is proposed to train weights and thresholds for Back-propagation (BP) neural network. BP algorithm has been widely used in training artificial neural network (ANN). This algorithm has many attractive features, such as adaptive learning, self-organism, and fault tolerant ability. All of them make BP one of the most successful algorithms in various fields...
The angle of break is a key factor that determines the mining damage extent of the surface in a mine, and it is also used to depict the characteristics of the mining subsidence basin. The geological and mining factors that influence the angle of break are fully analyzed. Based on the practical observational data from the ground movement monitoring stations of many mines in China, a neural network...
The production period of the crystalline aluminium chloride is considerably long. However, the offline assay of AlCl3??6H2O content has large time delay. Thus soft sensor modeling is needed to analyze its content, and estimate the value to improve the product quality. The conventional back-propagation (BP) neural network training is easily trapped to the local minimum, To overcome this embarrassment,...
To overcome the shortcomings of traditional Wavelet Neural Network (WNN), a WNN algorithm based on modified Unscented Kalman Filter (UKF) is proposed. The algorithm uses a UKF based on Spherical Simplex sigma-point (SSUKF) to estimate the WNN parameters, which can improve the learning capability of WNN. The aerodynamic force modeling experiment for flight vehicle indicate that, compared with BP, EKF...
Node deletion and node addition are two important types of structure mutations for evolutionary neural network (ENN). How to select mutation type and mutation node has a crucial impact on the performance of ENN. In order to improve the convergence speed and classification accuracy of ENN, a heuristic structure mutation operator (HSMO) based on sensitivity was proposed. The output sensitivity of ENN...
To address training of process neural networks based on the orthogonal basis expansion, a double chains quantum genetic algorithm based on the probability amplitudes of quantum bits is proposed. In this method, the probability amplitudes of each qubit are regarded as two paratactic genes, each chromosome contains two gene chains, and each of gene chains represents an optimization solution. The number...
A new particle swarm optimization algorithm with dynamically changing inertia weight and threshold value based on improved adaptive particle swarm optimization is proposed, in which the inertia weight of the particle is adjusted adaptively based on the premature convergence degree of the swarm and the fitness of the particle. The diversity of inertia weight makes a compromise between the global convergence...
Intrusion Detection Systems (IDS) are increasingly a key part of systems defense. Various approaches to Intrusion Detection are currently being used, but they are relatively in effective. Recently applying Artificial Intelligence, machine learning and data mining techniques to IDS are increasing. Artificial Intelligence plays a driving role in security services. An intrusion detection method based...
A type of optimized neural networks with limited precision weights (LPWNN) is presented in this paper. Such neural networks, which require less memory for storing the weights and less expensive floating point units in order to perform the computations involved, are better suited for embedded systems implementation than the real weight ones. Based on analyzing the learning capability of LPWNN, Quantize...
HMM-TTS synthesis is a popular approach toward flexible, low-footprint, data driven systems that produce highly intelligible speech. In spite of these strengths, speech generated by these systems exhibit some degradation in quality, attributable to an inadequacy in modeling the excitation signal that drives the parametric models of the vocal tract. This paper proposes a novel method for modeling the...
Neural Network is an effective tool in the field of pattern recognition. The neural network classifies the pattern from the training data and recognizes if the testing data holds that pattern. The classical Back propagation (BP) algorithm is generally used to train the neural network for its simplicity. The basic drawback of this algorithm is its uncertainty and long training time and it searches...
Within the statistical decision theory framework, This paper focuses on specific objectives in face recognition, and proposes the BP neural network classification methods which is under the Linex loss function, and proves that the convergence of BP neural network under the Linex loss function. The image recognition experiments with the ORL face database in Cambridge show that this method can effectively...
It is increasingly difficult for the traditional fault diagnosis technologies to meet the complex and automation requirements of electronic equipments, so the combination of artificial intelligence technology has become a development direction of fault diagnosis. In the fault diagnosis, BP neural network has also been widely used. As for the deficiency of BP network, the paper presented an improved...
Podaj zakres dat dla filtrowania wyświetlonych wyników. Możesz podać datę początkową, końcową lub obie daty. Daty możesz wpisać ręcznie lub wybrać za pomocą kalendarza.