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, a focused time lagged recurrent neural network (FTLRNN) model with gamma memory is developed for multi step ahead (k=1,5,10.20,50,100) prediction of typical Duffing Chaotic time series. It is popularized in Neural network field due to its richness in chaotic behavior. It is observed that duffing time series exhibit a rich chaotic behavior. This paper compares the performance of two...
A new approach to ANN-based real time voltage stability monitoring and reactive power management in a power system has been proposed in this paper. In this approach a separate ANN has been trained for each of the vulnerable load buses in the system from the voltage stability point of view. The vulnerable load buses of the system are identified by modal analysis of the system reduced Jacobian (of Q-V...
This paper presents an artificial neural network (ANN) controller for automatic generation control of a two area hydro-electric power system. A hierarchical architecture of three layer feed forward neural network (NN) is proposed for controller design, two networks are used, one for identifying the system and other for control respectively, trained based on back propagation algorithm (BPA). The regulator...
This paper presents a new approach to equalization of communication channels using artificial neural networks (ANNs). A novel method of training the ANNs using Tabu based back propagation (TBBP) algorithm is described. The algorithm uses the Tabu search (TS) to improve the performance of the equalizer as it searches for global minima which is many a time escaped while back propagation (BP) algorithm...
In this paper, we demonstrate the complementary nature of audio-specific excitation source (subsegmental) information present in the linear prediction (LP) residual, to the information derived using spectral (segmental) features, for audio clip classification. Classes considered for study are advertisement, cricket, cartoon, football and news, and the data is collected from TV broadcast with large...
Proximity sensing is required for a wide range of military applications, especially for weapon fuzing. In this paper, wavelet video processing is discussed which is used for proximity sensing of objects through their time dependent Doppler shift. A continuous wavelet transform is performed on the Doppler signal, after subjecting it to a time varying window, the signal features are extracted from resulting...
Electroencephalograms (EEG) are the brain signals that provide us the valuable information about the normal or epileptic state of the brain. In this paper the EEG signals were characterized by wavelet, sample and spectral entropy approach and the recurrent neural network classifier is used for the automated detection of epileptic seizures.
The shortest path planning in optical networks is an integer linear programming problem (ILP). Since, this problem is NP hard therefore; a simplified scheme is required for real time solution. To counteract the problem, a simplified artificial neural network architecture is proposed which utilizes the information of the optical network for the initialization of neural networks weight parameter. In...
This paper introduces a new method to detect out-of-step condition in power system based on an energy equilibrium criterion in the time domain directly. The proposed criterion is obtained using the concepts of equal area criterion in power angle domain but eliminates the need for numerical computations required in the earlier algorithm. The proposed algorithm uses power-time curve for computing the...
A new hybrid technique using support vector machines (SVM) and artificial neural networks (ANN) to forecast the next dasia24psila hours load is proposed in this paper. The forecasted load for the next dasia24psila hours is obtained by using four modules consisting of the basic SVM, Peak and Valley ANN, averager and forecaster and adaptive combiner. These modules try to extract the various components...
In this paper, we present an optical neural network based face detection system. Unlike similar systems which are limited to detecting upright, frontal faces, this system detects faces at any degree of rotation in the image plane. The system employs multiple networks; the first is an orientation network which processes each input window to determine its orientation and then uses this information to...
This paper presents dynamic voltage collapse prediction on an actual power system using support vector machines. Dynamic voltage collapse prediction is first determined based on the PTSI calculated from information in dynamic simulation output. Simulations were carried out on a practical 87 bus test system by considering load increase as the contingency. The data collected from the time domain simulation...
The radial basis function (RBF) based neural networks have been successfully used to solve many non-linear problems, including that of adaptive channel equalization. In this paper, we present three different adaptive fuzzy/neuro-fuzzy channel equalizers that closely fit into the broad framework of RBF neural network based systems. We consider the type-2 fuzzy adaptive filter (FAF) based channel equalizer...
This paper presents modeling, controller design, and simulation study of a grid connected Photovoltaic (GCPV) distributed generation (DG) system. The overall configuration of the grid connected photovoltaic DG system are present. The dynamic models for the GCPV power plant and its power electronic interfacing are described. Controller design methodologies for the control of power flow from the photovoltaic...
The preprocessing of numerals includes bounding them for translation invariance followed by normalization for scale invariance. We achieve translation and scale invariance using simple geometric moments. Higher order Zernike moments are used as shape descriptors. Due to rotation invariance and orthogonal properties of Zernike moments, they are found to perform better in terms of computational complexity...
This paper presents Wavelet based back propagation algorithm for classifying the power system faults, which is quite reliable, fast and computationally efficient. The proposed technique consists of a preprocessing unit based on discrete wavelet transform (DWT) in combination with an artificial neural network (ANN). The DWT acts as extractor of distinctive features in the input current signal which...
Short term load forecasting is essential to the operation of electricity companies. It enhances the energy-efficient and reliable operation of power system. Neural networks (NNs) have powerful nonlinear mapping capabilities. Therefore, they have been used to deal with predicting, in which the conventional methods fail to give satisfactory results. A novel recurrent neural network (RNN) is proposed...
In a smart hospital that uses RFID technology the location and status of the entities inside the hospital are continuously tracked and are captured into the hospital database. Such a database stores enormous amount of spatial as well as temporal data. Transforming this huge data into actionable information is highly complex. Knowledge discovery in such databases is highly desirable and can be applied...
This paper evaluates the reliability of the use of muscle activation during unuttered (silent) vowel by an individual and reports the study of repeating of the experiments over several days. Surface electromyogram has been used as an indicator of muscle activity and independent component analysis (ICA) has been used to separate the electrical activity from different muscles. The results demonstrate...
This paper presents the critical issues of optical network design and performance evaluation. The performance evaluation of the networks is measured in terms of packet loss probability or throughput with least amount of propagation time (delay). But as the network size grows it becomes cumbersome and hence some mechanism is required to handle stringent requirements of networks. This has been shown...
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.