Abstract: A new approach for protection of power transformer is
presented using a time-frequency transform known as Wavelet transform.
Different operating conditions such as inrush, Normal, load,
External fault and internal fault current are sampled and processed
to obtain wavelet coefficients. Different Operating conditions provide
variation in wavelet coefficients. Features like energy and Standard
deviation are calculated using Parsevals theorem. These features
are used as inputs to PNN (Probabilistic neural network) for fault
classification. The proposed algorithm provides more accurate results
even in the presence of noise inputs and accurately identifies inrush
and fault currents. Overall classification accuracy of the proposed
method is found to be 96.45%. Simulation of the fault (with and
without noise) was done using MATLAB AND SIMULINK software
taking 2 cycles of data window (40 m sec) containing 800 samples.
The algorithm was evaluated by using 10 % Gaussian white noise.
Abstract: This paper aims to develop a NOx emission model of
an acid gas incinerator using Nelder-Mead least squares support
vector regression (LS-SVR). Malaysia DOE is actively imposing the
Clean Air Regulation to mandate the installation of analytical
instrumentation known as Continuous Emission Monitoring System
(CEMS) to report emission level online to DOE . As a hardware
based analyzer, CEMS is expensive, maintenance intensive and often
unreliable. Therefore, software predictive technique is often
preferred and considered as a feasible alternative to replace the
CEMS for regulatory compliance. The LS-SVR model is built based
on the emissions from an acid gas incinerator that operates in a LNG
Complex. Simulated Annealing (SA) is first used to determine the
initial hyperparameters which are then further optimized based on the
performance of the model using Nelder-Mead simplex algorithm.
The LS-SVR model is shown to outperform a benchmark model
based on backpropagation neural networks (BPNN) in both training
and testing data.
Abstract: Power flow (PF) study, which is performed to
determine the power system static states (voltage magnitudes and
voltage angles) at each bus to find the steady state operating
condition of a system, is very important and is the most frequently
carried out study by power utilities for power system planning,
operation and control. In this paper, a counterpropagation neural
network (CPNN) is proposed to solve power flow problem under
different loading/contingency conditions for computing bus voltage
magnitudes and angles of the power system. The counterpropagation
network uses a different mapping strategy namely
counterpropagation and provides a practical approach for
implementing a pattern mapping task, since learning is fast in this
network. The composition of the input variables for the proposed
neural network has been selected to emulate the solution process of a
conventional power flow program. The effectiveness of the proposed
CPNN based approach for solving power flow is demonstrated by
computation of bus voltage magnitudes and voltage angles for
different loading conditions and single line-outage contingencies in
IEEE 14-bus system.
Abstract: The ElectroEncephaloGram (EEG) is useful for
clinical diagnosis and biomedical research. EEG signals often
contain strong ElectroOculoGram (EOG) artifacts produced
by eye movements and eye blinks especially in EEG recorded
from frontal channels. These artifacts obscure the underlying
brain activity, making its visual or automated inspection
difficult. The goal of ocular artifact removal is to remove
ocular artifacts from the recorded EEG, leaving the underlying
background signals due to brain activity. In recent times,
Independent Component Analysis (ICA) algorithms have
demonstrated superior potential in obtaining the least
dependent source components. In this paper, the independent
components are obtained by using the JADE algorithm (best
separating algorithm) and are classified into either artifact
component or neural component. Neural Network is used for
the classification of the obtained independent components.
Neural Network requires input features that exactly represent
the true character of the input signals so that the neural
network could classify the signals based on those key
characters that differentiate between various signals. In this
work, Auto Regressive (AR) coefficients are used as the input
features for classification. Two neural network approaches
are used to learn classification rules from EEG data. First, a
Polynomial Neural Network (PNN) trained by GMDH (Group
Method of Data Handling) algorithm is used and secondly,
feed-forward neural network classifier trained by a standard
back-propagation algorithm is used for classification and the
results show that JADE-FNN performs better than JADEPNN.
Abstract: Cosmic showers, during the transit through space, produce
sub - products as a result of interactions with the intergalactic
or interstellar medium which after entering earth generate secondary
particles called Extensive Air Shower (EAS). Detection and analysis
of High Energy Particle Showers involve a plethora of theoretical and
experimental works with a host of constraints resulting in inaccuracies
in measurements. Therefore, there exist a necessity to develop a
readily available system based on soft-computational approaches
which can be used for EAS analysis. This is due to the fact that soft
computational tools such as Artificial Neural Network (ANN)s can be
trained as classifiers to adapt and learn the surrounding variations. But
single classifiers fail to reach optimality of decision making in many
situations for which Multiple Classifier System (MCS) are preferred
to enhance the ability of the system to make decisions adjusting
to finer variations. This work describes the formation of an MCS
using Multi Layer Perceptron (MLP), Recurrent Neural Network
(RNN) and Probabilistic Neural Network (PNN) with data inputs
from correlation mapping Self Organizing Map (SOM) blocks and
the output optimized by another SOM. The results show that the setup
can be adopted for real time practical applications for prediction
of primary energy and location of EAS from density values captured
using detectors in a circular grid.
Abstract: A new approach based on the consideration that electroencephalogram (EEG) signals are chaotic signals was presented for automated diagnosis of electroencephalographic changes. This consideration was tested successfully using the nonlinear dynamics tools, like the computation of Lyapunov exponents. This paper presented the usage of statistics over the set of the Lyapunov exponents in order to reduce the dimensionality of the extracted feature vectors. Since classification is more accurate when the pattern is simplified through representation by important features, feature extraction and selection play an important role in classifying systems such as neural networks. Multilayer perceptron neural network (MLPNN) architectures were formulated and used as basis for detection of electroencephalographic changes. Three types of EEG signals (EEG signals recorded from healthy volunteers with eyes open, epilepsy patients in the epileptogenic zone during a seizure-free interval, and epilepsy patients during epileptic seizures) were classified. The selected Lyapunov exponents of the EEG signals were used as inputs of the MLPNN trained with Levenberg- Marquardt algorithm. The classification results confirmed that the proposed MLPNN has potential in detecting the electroencephalographic changes.
Abstract: A subjectively influenced router for vehicles in a fourjunction
traffic system is presented. The router is based on a 3-layer
Backpropagation Neural Network (BPNN) and a greedy routing
procedure. The BPNN detects priorities of vehicles based on the
subjective criteria. The subjective criteria and the routing procedure
depend on the routing plan towards vehicles depending on the user.
The routing procedure selects vehicles from their junctions based on
their priorities and route them concurrently to the traffic system. That
is, when the router is provided with a desired vehicles selection
criteria and routing procedure, it routes vehicles with a reasonable
junction clearing time. The cost evaluation of the router determines
its efficiency. In the case of a routing conflict, the router will route
the vehicles in a consecutive order and quarantine faulty vehicles.
The simulations presented indicate that the presented approach is an
effective strategy of structuring a subjective vehicle router.
Abstract: The objective of this study is to design an adaptive
neuro-fuzzy inference system (ANFIS) for estimation of surface
roughness in grinding process. The Used data have been generated
from experimental observations when the wheel has been dressed
using a rotary diamond disc dresser. The input parameters of model
are dressing speed ratio, dressing depth and dresser cross-feed rate
and output parameter is surface roughness. In the experimental
procedure the grinding conditions are constant and only the dressing
conditions are varied. The comparison of the predicted values and the
experimental data indicates that the ANFIS model has a better
performance with respect to back-propagation neural network
(BPNN) model which has been presented by the authors in previous
work for estimation of the surface roughness.
Abstract: Advances in clinical medical imaging have brought about the routine production of vast numbers of medical images that need to be analyzed. As a result an enormous amount of computer vision research effort has been targeted at achieving automated medical image analysis. Computed Tomography (CT) is highly accurate for diagnosing liver tumors. This study aimed to evaluate the potential role of the wavelet and the neural network in the differential diagnosis of liver tumors in CT images. The tumors considered in this study are hepatocellular carcinoma, cholangio carcinoma, hemangeoma and hepatoadenoma. Each suspicious tumor region was automatically extracted from the CT abdominal images and the textural information obtained was used to train the Probabilistic Neural Network (PNN) to classify the tumors. Results obtained were evaluated with the help of radiologists. The system differentiates the tumor with relatively high accuracy and is therefore clinically useful.
Abstract: In this paper, a new algorithm for generating codebook is proposed for vector quantization (VQ) in image coding. The significant features of the training image vectors are extracted by using the proposed Orthogonal Polynomials based transformation. We propose to generate the codebook by partitioning these feature vectors into a binary tree. Each feature vector at a non-terminal node of the binary tree is directed to one of the two descendants by comparing a single feature associated with that node to a threshold. The binary tree codebook is used for encoding and decoding the feature vectors. In the decoding process the feature vectors are subjected to inverse transformation with the help of basis functions of the proposed Orthogonal Polynomials based transformation to get back the approximated input image training vectors. The results of the proposed coding are compared with the VQ using Discrete Cosine Transform (DCT) and Pairwise Nearest Neighbor (PNN) algorithm. The new algorithm results in a considerable reduction in computation time and provides better reconstructed picture quality.
Abstract: Recently, a lot of attention has been devoted to
advanced techniques of system modeling. PNN(polynomial neural
network) is a GMDH-type algorithm (Group Method of Data
Handling) which is one of the useful method for modeling nonlinear
systems but PNN performance depends strongly on the number of
input variables and the order of polynomial which are determined by
trial and error. In this paper, we introduce GPNN (genetic
polynomial neural network) to improve the performance of PNN.
GPNN determines the number of input variables and the order of all
neurons with GA (genetic algorithm). We use GA to search between
all possible values for the number of input variables and the order of
polynomial. GPNN performance is obtained by two nonlinear
systems. the quadratic equation and the time series Dow Jones stock
index are two case studies for obtaining the GPNN performance.
Abstract: Diabetes mellitus (DM) is frequently characterized by
autonomic nervous dysfunction. Analysis of heart rate variability
(HRV) has become a popular noninvasive tool for assessing the
activities of autonomic nervous system (ANS). In this paper, changes
in ANS activity are quantified by means of frequency and time
domain analysis of R-R interval variability. Electrocardiograms
(ECG) of 16 patients suffering from DM and of 16 healthy volunteers
were recorded. Frequency domain analysis of extracted normal to
normal interval (NN interval) data indicates significant difference in
very low frequency (VLF) power, low frequency (LF) power and
high frequency (HF) power, between the DM patients and control
group. Time domain measures, standard deviation of NN interval
(SDNN), root mean square of successive NN interval differences
(RMSSD), successive NN intervals differing more than 50 ms (NN50
Count), percentage value of NN50 count (pNN50), HRV triangular
index and triangular interpolation of NN intervals (TINN) also show
significant difference between the DM patients and control group.
Abstract: In this paper, the processing of sonar signals has been
carried out using Minimal Resource Allocation Network (MRAN)
and a Probabilistic Neural Network (PNN) in differentiation of
commonly encountered features in indoor environments. The
stability-plasticity behaviors of both networks have been
investigated. The experimental result shows that MRAN possesses
lower network complexity but experiences higher plasticity than
PNN. An enhanced version called parallel MRAN (pMRAN) is
proposed to solve this problem and is proven to be stable in
prediction and also outperformed the original MRAN.
Abstract: In this paper, novel techniques in increasing the accuracy
and speed of convergence of a Feed forward Back propagation
Artificial Neural Network (FFBPNN) with polynomial activation
function reported in literature is presented. These technique was
subsequently used to determine the coefficients of Autoregressive
Moving Average (ARMA) and Autoregressive (AR) system. The
results obtained by introducing sequential and batch method of weight
initialization, batch method of weight and coefficient update, adaptive
momentum and learning rate technique gives more accurate result
and significant reduction in convergence time when compared t the
traditional method of back propagation algorithm, thereby making
FFBPNN an appropriate technique for online ARMA coefficient
determination.
Abstract: The behavior of Radial Basis Function (RBF) Networks greatly depends on how the center points of the basis functions are selected. In this work we investigate the use of instance reduction techniques, originally developed to reduce the storage requirements of instance based learners, for this purpose. Five Instance-Based Reduction Techniques were used to determine the set of center points, and RBF networks were trained using these sets of centers. The performance of the RBF networks is studied in terms of classification accuracy and training time. The results obtained were compared with two Radial Basis Function Networks: RBF networks that use all instances of the training set as center points (RBF-ALL) and Probabilistic Neural Networks (PNN). The former achieves high classification accuracies and the latter requires smaller training time. Results showed that RBF networks trained using sets of centers located by noise-filtering techniques (ALLKNN and ENN) rather than pure reduction techniques produce the best results in terms of classification accuracy. The results show that these networks require smaller training time than that of RBF-ALL and higher classification accuracy than that of PNN. Thus, using ALLKNN and ENN to select center points gives better combination of classification accuracy and training time. Our experiments also show that using the reduced sets to train the networks is beneficial especially in the presence of noise in the original training sets.
Abstract: In this paper, different approaches to solve the
forward kinematics of a three DOF actuator redundant hydraulic
parallel manipulator are presented. On the contrary to series
manipulators, the forward kinematic map of parallel manipulators
involves highly coupled nonlinear equations, which are almost
impossible to solve analytically. The proposed methods are using
neural networks identification with different structures to solve the
problem. The accuracy of the results of each method is analyzed in
detail and the advantages and the disadvantages of them in
computing the forward kinematic map of the given mechanism is
discussed in detail. It is concluded that ANFIS presents the best
performance compared to MLP, RBF and PNN networks in this
particular application.
Abstract: Cancer classification to their corresponding cohorts has been key area of research in bioinformatics aiming better prognosis of the disease. High dimensionality of gene data has been makes it a complex task and requires significance data identification technique in order to reducing the dimensionality and identification of significant information. In this paper, we have proposed a novel approach for classification of oral cancer into metastasis positive and negative patients. We have used significance analysis of microarrays (SAM) for identifying significant genes which constitutes gene signature. 3 different gene signatures were identified using SAM from 3 different combination of training datasets and their classification accuracy was calculated on corresponding testing datasets using k-Nearest Neighbour (kNN), Fuzzy C-Means Clustering (FCM), Support Vector Machine (SVM) and Backpropagation Neural Network (BPNN). A final gene signature of only 9 genes was obtained from above 3 individual gene signatures. 9 gene signature-s classification capability was compared using same classifiers on same testing datasets. Results obtained from experimentation shows that 9 gene signature classified all samples in testing dataset accurately while individual genes could not classify all accurately.
Abstract: This paper presents a new method of analog fault diagnosis based on back-propagation neural networks (BPNNs) using wavelet decomposition and fractal dimension as preprocessors. The proposed method has the capability to detect and identify faulty components in an analog electronic circuit with tolerance by analyzing its impulse response. Using wavelet decomposition to preprocess the impulse response drastically de-noises the inputs to the neural network. The second preprocessing by fractal dimension can extract unique features, which are the fed to a neural network as inputs for further classification. A comparison of our work with [1] and [6], which also employs back-propagation (BP) neural networks, reveals that our system requires a much smaller network and performs significantly better in fault diagnosis of analog circuits due to our proposed preprocessing techniques.