Showing 35 results for Neural Network
A Ayatollahi, N Jafarnia Dabanloo, Dc McLernon, V Johari Majd, H Zhang,
Volume 1, Issue 2 (4-2005)
Abstract
Developing a mathematical model for the artificial generation of
electrocardiogram (ECG) signals is a subject that has been widely investigated. One of its
uses is for the assessment of diagnostic ECG signal processing devices. So the model
should have the capability of producing a wide range of ECG signals, with all the nuances
that reflect the sickness to which humans are prone, and this would necessarily include
variations in heart rate variability (HRV). In this paper we present a comprehensive model
for generating such artificial ECG signals. We incorporate into our model the effects of
respiratory sinus arrhythmia, Mayer waves and the important very low frequency
component in the power spectrum of HRV. We use the new modified Zeeman model for
generating the time series for HRV, and a single cycle of ECG is produced using a radial
basis function neural network.
M. Hariri, S. B. Shokouhi, N. Mozayani,
Volume 4, Issue 3 (10-2008)
Abstract
Dealing with uncertainty is one of the most critical problems in complicated
pattern recognition subjects. In this paper, we modify the structure of a useful Unsupervised
Fuzzy Neural Network (UFNN) of Kwan and Cai, and compose a new FNN with 6 types of
fuzzy neurons and its associated self organizing supervised learning algorithm. This
improved five-layer feed forward Supervised Fuzzy Neural Network (SFNN) is used for
classification and identification of shifted and distorted training patterns. It is generally
useful for those flexible patterns which are not certainly identifiable upon their features. To
show the identification capability of our proposed network, we used fingerprint, as the most
flexible and varied pattern. After feature extraction of different shapes of fingerprints, the
pattern of these features, “feature-map”, is applied to the network. The network first
fuzzifies the pattern and then computes its similarities to all of the learned pattern classes.
The network eventually selects the learned pattern of highest similarity and returns its
specific class as a non fuzzy output. To test our FNN, we applied the standard (NIST
database) and our databases (with 176×224 dimensions). The feature-maps of these
fingerprints contain two types of minutiae and three types of singular points, each of them
is represented by 22×28 pixels, which is less than real size and suitable for real time
applications. The feature maps are applied to the FNN as training patterns. Upon its setting
parameters, the network discriminates 3 to 7 subclasses for each main classes assigned to
one of the subjects.
M. R. Aghamohammadi,
Volume 4, Issue 3 (10-2008)
Abstract
This paper proposes a novel approach for generation scheduling using sensitivity
characteristic of a Security Analyzer Neural Network (SANN) for improving static security
of power system. In this paper, the potential overloading at the post contingency steadystate
associated with each line outage is proposed as a security index which is used for
evaluation and enhancement of system static security. A multilayer feed forward neural
network is trained as SANN for both evaluation and enhancement of system security. The
input of SANN is load/generation pattern. By using sensitivity characteristic of SANN,
sensitivity of security indices with respect to generation pattern is used as a guide line for
generation rescheduling aimed to enhance security. Economic characteristic of generation
pattern is also considered in the process of rescheduling to find an optimum generation
pattern satisfying both security and economic aspects of power system. One interesting
feature of the proposed approach is its ability for flexible handling of system security into
generation rescheduling and compromising with the economic feature with any degree of
coordination. By using SANN, several generation patterns with different level of security
and cost could be evaluated which constitute the Pareto solution of the multi-objective
problem. A compromised generation pattern could be found from Pareto solution with any
degree of coordination between security and cost. The effectiveness of the proposed
approach is studied on the IEEE 30 bus system with promising results.
M. H. Sedaaghi,
Volume 5, Issue 1 (3-2009)
Abstract
Accurate gender classification is useful in speech and speaker recognition as
well as speech emotion classification, because a better performance has been reported when
separate acoustic models are employed for males and females. Gender classification is also
apparent in face recognition, video summarization, human-robot interaction, etc. Although
gender classification is rather mature in applications dealing with images, it is still in its
infancy in speech processing. Age classification, on the other hand, is also concerned as a
useful tool in different applications, like issuing different permission levels for different
aging groups. This paper concentrates on a comparative study of gender and age
classification algorithms applied to speech signal. Experimental results are reported for the
Danish Emotional Speech database (DES) and English Language Speech Database for
Speaker Recognition (ELSDSR). The Bayes classifier using sequential floating forward
selection (SFFS) for feature selection, probabilistic Neural Networks (PNNs), support
vector machines (SVMs), the K nearest neighbor (K-NN) and Gaussian mixture model
(GMM), as different classifiers, are empirically compared in order to determine the best
classifier for gender and age classification when speech signal is processed. It is proven that
gender classification can be performed with an accuracy of 95% approximately using
speech signal either from both genders or male and female separately. The accuracy for age
classification is about 88%.
Sujan Rajbhandari, Zabih Ghassemlooy, Maia Angelova,
Volume 5, Issue 2 (6-2009)
Abstract
Artificial neural network (ANN) has application in communication engineering in diverse areas such as channel equalization, channel modeling, error control code because of its capability of nonlinear processing, adaptability, and parallel processing. On the other hand, wavelet transform (WT) with both the time and the frequency resolution provides the exact representation of signal in both domains. Applying these signal processing tools for channel compensation and noise reduction can provide an enhanced performance compared to the traditional tools. In this paper, the slot error rate (SER) performance of digital pulse interval modulation (DPIM) in diffuse indoor optical wireless (OW) links subjected to the artificial light interference (ALI) is reported with new receiver structure based on the discrete WT (DWT) and ANN. Simulation results show that the DWT-ANN based receiver is very effective in reducing the effect of multipath induced inter-symbol interference (ISI) and ALI.
M. R. Mosavi,
Volume 5, Issue 4 (12-2009)
Abstract
This paper presents design and implementation of three new Infrared Counter-Countermeasure (IRCCM) efficient methods using Neural Network (NN), Fuzzy System (FS), and Kalman Filter (KF). The proposed algorithms estimate tracking error or correction signal when jamming occurs. An experimental test setup is designed and implemented for performance evaluation of the proposed methods. The methods validity is verified with experiments on IR seeker reticle based on a Digital Signal Processing (DSP) processor. The practical results emphasize that the proposed algorithms are highly effective and can reduce the jamming effects. The experimental results obtained strongly support the potential of the method using FS to eliminate the IRCM effect 83%.
R. Yousefi, M. K. Moravvej-Farshi, K. Saghafi,
Volume 6, Issue 2 (6-2010)
Abstract
In this paper, using the neural space mapping (NSM) concept, we present a
SPICE-compatible modeling technique to modify the conventional MOSFET equations, to
be suitable for ballistic carbon nanotube transistors (CNTTs). We used the NSM concept in
order to correct conventional MOSFET equations so that they could be used for carbon
nanotube transistors. To demonstrate the accuracy of our model, we have compared our
results with those obtained by using open-source software known as FETToy. This
comparison shows that the RMS errors in our calculated IDS, under various conditions, are
smaller than the RMS errors in IDS values calculated by the existing analytical models
published by others.
L. Ghods, M. Kalantar,
Volume 6, Issue 3 (9-2010)
Abstract
Prediction of peak loads in Iran up to year 2011 is discussed using the Radial
Basis Function Networks (RBFNs). In this study, total system load forecast reflecting the
current and future trends is carried out for global grid of Iran. Predictions were done for
target years 2007 to 2011 respectively. Unlike short-term load forecasting, long-term load
forecasting is mainly affected by economy factors rather than weather conditions. This
study focuses on economical data that seem to have influence on long-term electric load
demand. The data used are: actual yearly, incremental growth rate from previous year, and
blend (actual and incremental growth rate from previous years). As the results, the
maximum demands for 2007 through 2011 are predicted and is shown to be elevated from
37138 MW to 45749 MW for Iran Global Grid. The annual average rate of load growth
seen per five years until 2011 is about 5.35%
M. Aghamohammadi, S. S. Hashemi, M. S. Ghazizadeh,
Volume 7, Issue 1 (3-2011)
Abstract
This paper presents a new approach for estimating and improving voltage stability margin from phase and magnitude profile of bus voltages using sensitivity analysis of Voltage Stability Assessment Neural Network (VSANN). Bus voltage profile contains useful information about system stability margin including the effect of load-generation, line outage and reactive power compensation so, it is adopted as input pattern for VSANN. In fact, VSANN establishes a functionality for VSM with respect to voltage profile. Sensitivity analysis of VSM with respect to voltage profile and reactive power compensation extracted from information stored in the weighting factor of VSANN, is the most dominant feature of the proposed approach. Sensitivity of VSM helps one to select most effective buses for reactive power compensation aimed enhancing VSM. The proposed approach has been applied on IEEE 39-bus test system which demonstrated applicability of the proposed approach.
D. Arab Khaburi, H. Rostami,
Volume 7, Issue 1 (3-2011)
Abstract
This paper presents a method to control both the dc boost and the ac output voltage of Z-source inverter using neural network controllers. The capacitor voltage of Z-source network has been controlled linearly in order to improve the transient response of the dc boost control of the Z-source inverter. The peak value of the line to line ac output voltage is used to control and keep the ac output at its desired value. A modified space vector pulse-width-modulation method is also applied to control the shoot-through duty ratio for boosting dc voltage. This modified method lets the dc voltage stress across the inverter switches be minimized. The neural network control technique is verified by simulation results. The results are compared with that of the traditional PI controller.
L. Ghods, M. Kalantar,
Volume 7, Issue 4 (12-2011)
Abstract
Long-term demand forecasting presents the first step in planning and developing future generation, transmission and distribution facilities. One of the primary tasks of an electric utility accurately predicts load demand requirements at all times, especially for long-term. Based on the outcome of such forecasts, utilities coordinate their resources to meet the forecasted demand using a least-cost plan. In general, resource planning is performed subject to numerous uncertainties. Expert opinion indicates that a major source of uncertainty in planning for future capacity resource needs and operation of existing generation resources is the forecasted load demand. This paper presents an overview of the past and current practice in long- term demand forecasting. It introduces methods, which consists of some traditional methods, neural networks, genetic algorithms, fuzzy rules, support vector machines, wavelet networks and expert systems.
R. Ebrahimpour, S. Sarhangi, F. Sharifizadeh,
Volume 7, Issue 4 (12-2011)
Abstract
This paper presents the results of Persian handwritten word recognition based on Mixture of Experts technique. In the basic form of ME the problem space is automatically divided into several subspaces for the experts, and the outputs of experts are combined by a gating network. In our proposed model, we used Mixture of Experts Multi Layered Perceptrons with Momentum term, in the classification Phase. We produce three different Mixture of Experts structure. Experimental result for proposed method show an error rate reduction of 6.42 % compare to the mixture of MLPs experts. Comparison with some of the most related methods indicates that the proposed model yields excellent recognition rate in handwritten word recognition.
D. S. Javan, H. Rajabi Mashhadi,
Volume 7, Issue 4 (12-2011)
Abstract
Deregulation of power system in recent years has changed static security assessment to the major concerns for which fast and accurate evaluation methodology is needed. Contingencies related to voltage violations and power line overloading have been responsible for power system collapse. This paper presents an enhanced radial basis function neural network (RBFNN) approach for on-line ranking of the contingencies expected to cause steady state bus voltage and power flow violations. Hidden layer units (neurons) have been selected with the growing and pruning algorithm which has the superiority of being able to choose optimal unit’s center and width (radius). A feature preference technique-based class separability index and correlation coefficient has been employed to identify the relevant inputs for the neural network. The advantages of this method are simplicity of algorithm and high accuracy in classification. The effectiveness of the proposed approach has been demonstrated on IEEE 14-bus power system.
M. Mollanezhad Heydar-Abadi , A. Akbari Foroud,
Volume 9, Issue 3 (9-2013)
Abstract
Fault classification in distance protection of transmission lines, with considering the wide variation in the fault operating conditions, has been very challenging task. This paper presents a probabilistic neural network (PNN) and new feature selection technique for fault classification in transmission lines. Initially, wavelet transform is used for feature extraction from half cycle of post-fault three phase currents at one end of line. In the proposed method three classifiers corresponding with three phases are used which fed by normalized particular features as wavelet energy ratio (WER) and ground index (GI). The PNNs are trained to provide faulted phase selection in different ten fault types. Finally, logic outputs of classifiers and GI identify the fault type. The feasibility of the proposed algorithm is tested on transmission line using PSCAD/EMTDC software. Variation of operating conditions in train cases is limited, but it is wide for test cases. Also, quantity of the test data sets is larger than the train data sets. The results indicate that the proposed technique is high speed, accurate and robust for a wide variation in operating conditions and noisy environments.
N. Eskandari, S. Jalilzadeh,
Volume 12, Issue 4 (12-2016)
Abstract
Load side management is the basic and significant principle to keeping the balance between generation side and consumption side of electrical power energy. Load side management on typical medium voltage feeder is the power energy consumption control of connected loads with variation of essential parameters that loads do reaction to their variation. Knowing amount of load's reaction to each parameters variation in typical medium voltage feeder during the day, leads to gain Load Manageability Factor (LMF) for that specific feeder that helps power utilities to manage their connected loads. Calculating this LMF needs to find out each types of load with unique inherent features behavior to each parameters variation. This paper results and future work results will help us to catch mentioned LMF. In this paper analysis of residential load behavior due to temperature variation with training artificial neural network will be done. Load behavior due to other essential parameters variations like energy pricing variation, major event happening, and power utility announcing to the customers, and etc will study in future works. Collecting all related works results in a unit mathematical equation or an artificial neural network will gain LMF.
M. R. Mosavi, A. Rashidinia,
Volume 13, Issue 3 (9-2017)
Abstract
Differential Global Positioning System (DGPS) provides differential corrections for a GPS receiver in order to improve the navigation solution accuracy. DGPS position signals are accurate, but very slow updates. Improving DGPS corrections prediction accuracy has received considerable attention in past decades. In this research work, the Neural Network (NN) based on the Gaussian Radial Basis Function (RBF) has been developed. In many previous works all parameter of RBF NN are optimizing by evolutionary algorithm such as Particle Swarm Optimization (PSO), but in our approach shape parameter and centers of RBF NN are calculated in better way, in addition, search space for PSO algorithm will be reduced which cause more accurate and faster approach. The obtained results show that RMS has been reduced about 0.13 meter. Moreover, results are tabulated in the tables which verify the accuracy and faster convergence nature of our approach in both on-line and off-line training methods.
M. K. Saini, R. K. Beniwal,
Volume 14, Issue 2 (6-2018)
Abstract
This paper presents a new framework based on modified EMD method for detection of single and multiple PQ issues. In modified EMD, DWT precedes traditional EMD process. This scheme makes EMD better by eliminating the mode mixing problem. This is a two step algorithm; in the first step, input PQ signal is decomposed in low and high frequency components using DWT. In the second stage, the low frequency component is further processed with EMD technique to get IMFs. Eight features are extracted from IMFs of low frequency component. Unlike low frequency component, features are directly extracted from the high frequency component. All these features form feature vector which is fed to PNN classifier for classification of PQ issues. For comparative analysis of performance of PNN, results are compared with SVM classifier. Moreover, performance of proposed methodology is also validated with noisy PQ signals. PNN has outperformed SVM for both noiseless and noisy PQ signals.
S. Mirzakuchaki, Z. Paydar,
Volume 14, Issue 4 (12-2018)
Abstract
In this study a method has been introduced to map the features extracted from the recorded electromyogram signals from the forearm and the force generated by the fingers. In order to simultaneously record of sEMG signals and the force produced by fingers, 9 requested movements of fingers conducted by 10 healthy people. Estimation was done for 6 degrees of freedom (DoF) and generalized regression neural network (GRNN) was selected for system training. The optimal parameters, including the length of the time windows, the parameters of the neural network, and the characteristics of the sEMG signal were calculated to improve the performance of the estimate. The performance was obtained based on R2 criterion. The Total value of R2 for 6 DoF was 92.8±5.2% that obtained by greedy looking system parameters in all the subjects. The result shows that proposed method can be significant in simultaneous myoelectric control.
H. Benbouhenni, Z. Boudjema, A. Belaidi,
Volume 14, Issue 4 (12-2018)
Abstract
This paper applied second order sliding mode control (SOSMC) strategy using artificial neural network (ANN) on the rotor side converter of a 1.5 MW doubly fed induction generator (DFIG) integrated in a wind turbine system. In this work, the converter is controlled by a neural space vector modulation (NSVM) technique in order to reduce powers ripples and total harmonic distortion (THD) of stator current. The validity of the proposed control technique applied on the DFIG is verified by Matlab/Simulink. The active power, reactive power, torque and stator current are determined and compared with conventional control method. Simulation results presented in this paper shown that the proposed control scheme reduces the THD value and powers ripples compared to traditional control under various operating conditions.
M. H. Lazreg, A. Bentaallah,
Volume 15, Issue 1 (3-2019)
Abstract
This article presents a sensorless five level DTC control based on neural networks using Extended Kalman Filter (EKF) applied to Double Star Induction Machine (DSIM). The application of the DTC control brings a very interesting solution to the problems of robustness and dynamics. However, this control has some drawbacks such as the uncontrolled of the switching frequency and the strong ripple torque. To improve the performance of the system to be controlled, robust techniques have been applied, namely artificial neural networks. In order to reduce the number of sensors used, and thus the cost of installation, Extended Kalman filter is used to estimate the rotor speed. By viewing the simulation results using the MATLAB language for the control. The results of simulations obtained showed a very satisfactory behaviour of the machine.
