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.
In this paper, classification of audio sources is presented to supplement current work on existing system for localization of audio sources. The question of achieving the audio classification lies in the convenient discrimination of the feature vector in the feature vector space. Characteristics based on frequency analysis were chosen and used as feature vector. Artificial neural network was applied...
Kohonen's self-organizing map (SOM) is a competitive learning neural network that uses a neighborhood lateral interaction function to discover the topological structure hidden in the data set. In general, the SOM neural network is constructed as a learning algorithm for numerical data. However, except these numeric data, there are many other data types such as symbolic data. Thus, Yang et al. proposed...
In this paper, we consider a new periodic activation function for the multivalued neuron (MVN). The MVN is a neuron with complex-valued weights and inputs/output, which are located on the unit circle. Although the MVN outperforms many other neurons and MVN-based neural networks have shown their high potential, the MVN still has a limited capability of learning highly nonlinear functions. A periodic...
The paper proposes a novel neuron model termed as Generalized Power Mean Neuron model (GPMN). The paper focuses on illustrating the computational power and the generalization capability of this model. In this model, the aggregation function is based on generalized power mean of the inputs. The performance of the neural network using GPMN model is compared with traditional feed-forward neural network...
We present an attempt to separate between two kinds of events, using Genetic Algorithms. Events were produced by a Monte Carlo generator and characterized by the most discriminant variables. For the separation between events, two approaches are investigated. First, discriminant function parameters and neural network connection weights are optimized. In a multidimensional search approach, hyper-planes...
A classification method of video data using centroid neural network is proposed in this paper. The CNN algorithm is used for clustering the MPEG video data. In comparison with other conventional algorithms, The CNN requires neither a predetermined schedule for learning gain nor the total number of iterations for clustering. It always converges to sub-optimal solutions while conventional algorithms...
Magnetic resonance image (MRI) has been widely used for clinical applications in recent years. With the ability of scanning the same section by multiple frequencies, MRI makes it possible to generate several images on the same section. Despite of accessible abundant information, MRI also makes it more difficult to judge the location of every tissue. MRI will complicate the judgment due to strong noise...
In this paper, a neural network hardware implementation of pattern recognition using n-input neuron circuits is presented. Floating-gate MOS (FGMOS) based neuron model using four-quadrant analog multiplier with rail-to-rail linear input and FGMOS based differential comparator has been designed and simulated in HSPICE environment. Using the proposed low voltage neuron circuits a neural network was...
The classification for similar features classes is quite difficult task in many existing pattern-recognition systems. When the amount of samples is insufficient, neural networking training is hard. The dimension reduction, classification, clustering etc serial steps in recognition process takes such much time that the practical recognizing application is ease to meet the real time requirement. The...
Many of the widely used classifiers are time consuming and resource intensive, and hence not practical to be used in the emerging wireless networks. We present an efficient classifier, termed distributed hierarchical graph neuron (DHGN)-based classifier. Our proposed solution uses a new form of neural network, which consists of a hierarchical graph-based representation of input patterns, and adopts...
The classification on the dirty factor of the new and used banknotes is an important function of the note sorter. This paper proposes a classification method based on neural network with sine basis functions. The gray level histogram of banknote image is used as the characteristic vector to train the neural network. The classification effect is satisfying by this method.
With reference to the theory that only a part of signal from brain cells can reach pallium put forward by Raju Metherate, and the theory that axon signal strength is reduced with distance increment from main body of neural cells raised by Stephen R. Williams, axon signal theory-based clustering algorithm of neural network is presented in this paper. This algorithm processes equivalent to and even...
Classification is an important problem in data mining. This paper focuses on a method of optimizing classifiers of neural network by Genetic Algorithm based on principle of gene reconfiguration, and implement classification by training the weight. The paper uses shift reverse logic crossover operation and the improved genetic algorithm The article using the typical method for optimizing BP neural...
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.