A method for identification of mechanical parameters of an asynchronous motor is presented in this paper. The identification method is based on the use of our knowledge of the system. This paper clarifies the method by using the example identifying of mechanical parameters of the three-phase squirrel-cage asynchronous motor.A model of mechanical subsystem of the motor is presented as well as results of simulation. The special neural network is used as an identification model and its adaptation is based on the gradient descent method.The parameters of mechanical subsystem are derived from the values of synaptic weights of the neural identification model after its adaptation. Deviation of identified mechanical parameters in the case of moment inertia was up to 0.03% and in the case of load torque was 1.45% of real values.
This paper presents a new model to perform a supervised image segmentation task. The proposed model is called segmentation and classification with receptive fields (SCRF) which is based on the concept of receptive fields that analyzes pieces of an image considering not only a pixel or a group of pixels, but also the relationship between them and their neighbors. In order to work with the SCRF model, we propose a new artificial neural network, called I-PyraNet, which is a hybrid implementation of the recently described PyraNet and the nonclassical receptive fields inhibition. Furthermore, the model and the neural network are combined to accomplish a satellite image segmentation task.
A boundary vector generator is a data barrier amplifier that improves the distribution model of the samples to increase the classification accuracy of the feed-forward neural network. It generates new forms of samples, one for amplifying the barrier of their class (fundamental multi-class outpost vectors) and the other for increasing the barrier of the nearest class (additional multi-class outpost vectors). However, these sets of boundary vectors are enormous. The reduced boundary vector generators proposed three boundary vector reduction techniques that scale down fundamental multi-class outpost vectors and additional multi-class outpost vectors. Nevertheless, these techniques do not consider the interval of the attributes, causing some attributes to suppress over the other attributes on the Euclidean distance calculation. The motivation of this study is to explore whether six normalization techniques; min-max, Z-score, mean and mean absolute deviation, median and median absolute deviation, modified hyperbolic tangent, and hyperbolic tangent estimator, can improve the classification performance of the boundary vector generator and the reduced boundary vector generators for maximizing class boundary. Each normalization technique pre-processes the original training set before the boundary vector generator or each of the three reduced boundary vector generators will begin. The experimental results on the real-world datasets generally confirmed that (1) the final training set having only FF-AA reduced boundary vectors can be integrated with one of the normalization techniques effectively when the accuracy and precision are prioritized, (2) the final training set having only the boundary vectors can be integrated with one of the normalization techniques effectively when the recall and F1-score are prioritized, (3) the Z-score normalization can generally improve the accuracy and precision of all types of training sets, (4) the modified hyperbolic tangent normalization can generally improve the recall of all types of training sets, (5) the min-max normalization can generally improve the accuracy and F1-score of all types of training sets, and (6) the selection of the normalization techniques and the training set types depends on the key performance measure for the dataset.
In this article we use a combination of neural networks with other techniques for the analysis of orthophotos. Our goal is to obtain results that can serve as a useful groundwork for interactive exploration of the terrain in detail. In our approach we split an aerial photo into a regular grid of segments and for each segment we detect a set of features. These features depict the segment from the viewpoint of a general image analysis (color, tint, etc.) as well as from the viewpoint of the shapes in the segment. We perform clustering based on the Formal Concept Analysis (FCA) and Non-negative Matrix Factorization (NMF) methods and project the results using effective visualization techniques back to the aerial photo. The FCA as a tool allows users to be involved in the exploration of particular clusters by navigation in the space of clusters. In this article we also present two of our own computer systems that support the process of the validation of extracted features using a neural network and also the process of navigation in clusters. Despite the fact that in our approach we use only general properties of images, the results of our experiments demonstrate the usefulness of our approach and the potential for further development.
Text categorization is based on the idea of content-based texts clustering. An Artificial Neural Network (ANN) or simply Neural Network (NN) classifier for Arabic texts categorization is proposed. The Singular Value Decomposition (SVD) is used as preprocessor with the aim of further reducing data in terms of both size and dimensionality. Indeed, the use of SVD makes data more amenable to classification and the convergence training process faster. Specifically, the effectiveness of the Multilayer Perceptron (MLP) and the Radial Basis Function (RBF) classifiers are implemented. Experiments are conducted using an in-house corpus of Arabic texts. Precision, recall and F-measure are used to quantify categorization effectiveness. The results show that the proposed SVD-Supported MLP/RBF ANN classifier is able to achieve high effectiveness. Experimental results also show that the MLP classifier outperforms the RBF classifier and that the SVD-supported NN classifier is better than the basic NN, as far as Arabic text categorization is concerned.
Biological systems are able to switch their neural systems into inhibitory states and it is therefore important to build mathematical models that can explain such phenomena. If we interpret such inhibitory modes as `positive' or `negative' steady states of neural networks, then we will need to find the corresponding fixed points. This paper shows positive fixed point theorems for a particular class of cellular neural networks whose neuron units are placed at the vertices of a regular polygon. The derivation is based on elementary analysis. However, it is hoped that our easy fixed point theorems have potential applications in exploring stationary states of similar biological network models.
learning machine (ELM), as a new learning mechanism for single hidden layer feedforward neural networks (SLFNs), has shown its advantages, such as fast computation speed and good generalization performance. However, the weak robustness of ELM is an unavoidable defect for image classification. To address the problem, we propose a novel ensemble method which combines rotation forest and selective ensemble model in this paper. Firstly, ELM and rotation forest are integrated to construct an ensemble classifier (RF-ELM), which combines the advantages of both rotation forest and ELM. The purpose of rotation forest here is to enhance the diversity of each base classifier which can improve the performance generalization. Then several ELMs are removed from the ensemble pool by using genetic algorithm (GA) based selective ensemble model to further enhance the robustness. Finally, the remaining ELMs are grouped as a selected ensemble classifier (RFSEN-ELM) for image classification. The performance is analyzed and compared with several existing methods on benchmark datasets and the experimental results demonstrate that the proposed algorithm substantially improves the accuracy and robustness of classification at an acceptable level of training cost.
The language EpsiloNN allows a high-level specification of arbitrary
neural network structures. It is especially designed for the automatic generation of simulation code, which can run efficiently on different parallel Computer architectures. In this páper soine applications of EpsiloNN are presented. First, the basic syntactical and semantical aspects of the language are described briefly. Then the EpsiloNN specifications of a popular multilayer perceptron (MLP) and of a more complex hybrid LVQ/FfBF neural network architecture are presented. Further features of the language are explained by example.
In this paper, we consider a three-unit delayed neural network system, investigate the linear stability, and obtain some sufficient conditions ensuring the absolute synchronization of the system by the Lyapunov function. Numerical simulations show that the theoretically predicted results are in excellent agreement with the numerically observed behavior.
Applications of artificial intelligence in engineering disciplines have become widespread and have provided alternative solutions to engineering problems. Image processing technology (IPT) and artificial neural networks (ANNs) are types of artificial intelligence methods. However, IPT and ANN have been used together in extremely few studies. In this study, these two methods were used to deter- mine the compressive strength of concrete, a complex material whose mechanical features are difficult to predict. Sixty cube-shaped specimens were manufactured, and images of specific features of the specimens were taken before they were tested to determine their compressive strengths. An ANN model was constituted as a result of the process of digitizing the images. In this way, the two different artificial intelligence methods were used together to carry out the analysis. The compressive strength values of the concrete obtained via analytical modeling were compared with the test results. The results of the comparison (R² = 0:9837-0:9961) indicate that the combination of these two artificial intelligence methods is highly capable of predicting the compressive strengths of the specimens. The model's predictive capability was also evaluated in terms of several statistical parameters using a set of statistical methods during the digitization of the images constituting the artificial neural network.