Abstract: In this paper in consideration of each available
techniques deficiencies for speech recognition, an advanced method
is presented that-s able to classify speech signals with the high
accuracy (98%) at the minimum time. In the presented method, first,
the recorded signal is preprocessed that this section includes
denoising with Mels Frequency Cepstral Analysis and feature
extraction using discrete wavelet transform (DWT) coefficients; Then
these features are fed to Multilayer Perceptron (MLP) network for
classification. Finally, after training of neural network effective
features are selected with UTA algorithm.
Abstract: This paper proposes a technique to protect against
email bombing. The technique employs a statistical approach, Naïve
Bayes (NB), and Neural Networks to show that it is possible to
differentiate between good and bad traffic to protect against email
bombing attacks. Neural networks and Naïve Bayes can be trained
by utilizing many email messages that include both input and output
data for legitimate and non-legitimate emails. The input to the model
includes the contents of the body of the messages, the subject, and
the headers. This information will be used to determine if the email
is normal or an attack email. Preliminary tests suggest that Naïve
Bayes can be trained to produce an accurate response to confirm
which email represents an attack.
Abstract: This paper proposes view-point insensitive human
pose recognition system using neural network. Recognition system
consists of silhouette image capturing module, data driven database,
and neural network. The advantages of our system are first, it is
possible to capture multiple view-point silhouette images of 3D human
model automatically. This automatic capture module is helpful to
reduce time consuming task of database construction. Second, we
develop huge feature database to offer view-point insensitivity at pose
recognition. Third, we use neural network to recognize human pose
from multiple-view because every pose from each model have similar
feature patterns, even though each model has different appearance and
view-point. To construct database, we need to create 3D human model
using 3D manipulate tools. Contour shape is used to convert silhouette
image to feature vector of 12 degree. This extraction task is processed
semi-automatically, which benefits in that capturing images and
converting to silhouette images from the real capturing environment is
needless. We demonstrate the effectiveness of our approach with
experiments on virtual environment.
Abstract: Hepatocellular carcinoma, also called hepatoma, most
commonly appears in a patient with chronic viral hepatitis. In
patients with a higher suspicion of HCC, such as small or subtle
rising of serum enzymes levels, the best method of diagnosis
involves a CT scan of the abdomen, but only at high cost. The aim of
this study was to increase the ability of the physician to early detect
HCC, using a probabilistic neural network-based approach, in order
to save time and hospital resources.
Abstract: In this paper, Differential Evolution (DE) algorithm, a new promising evolutionary algorithm, is proposed to train Radial Basis Function (RBF) network related to automatic configuration of network architecture. Classification tasks on data sets: Iris, Wine, New-thyroid, and Glass are conducted to measure the performance of neural networks. Compared with a standard RBF training algorithm in Matlab neural network toolbox, DE achieves more rational architecture for RBF networks. The resulting networks hence obtain strong generalization abilities.
Abstract: Non-Destructive evaluation of in-service power
transformer condition is necessary for avoiding catastrophic failures.
Dissolved Gas Analysis (DGA) is one of the important methods.
Traditional, statistical and intelligent DGA approaches have been
adopted for accurate classification of incipient fault sources.
Unfortunately, there are not often enough faulty patterns required for
sufficient training of intelligent systems. By bootstrapping the
shortcoming is expected to be alleviated and algorithms with better
classification success rates to be obtained. In this paper the
performance of an artificial neural network, K-Nearest Neighbour
and support vector machine methods using bootstrapped data are
detailed and shown that while the success rate of the ANN algorithms
improves remarkably, the outcome of the others do not benefit so
much from the provided enlarged data space. For assessment, two
databases are employed: IEC TC10 and a dataset collected from
reported data in papers. High average test success rate well exhibits
the remarkable outcome.
Abstract: All the available algorithms for blind estimation namely constant modulus algorithm (CMA), Decision-Directed Algorithm (DDA/DFE) suffer from the problem of convergence to local minima. Also, if the channel drifts considerably, any DDA looses track of the channel. So, their usage is limited in varying channel conditions. The primary limitation in such cases is the requirement of certain overhead bits in the transmit framework which leads to wasteful use of the bandwidth. Also such arrangements fail to use channel state information (CSI) which is an important aid in improving the quality of reception. In this work, the main objective is to reduce the overhead imposed by the pilot symbols, which in effect reduces the system throughput. Also we formulate an arrangement based on certain dynamic Artificial Neural Network (ANN) topologies which not only contributes towards the lowering of the overhead but also facilitates the use of the CSI. A 2×2 Multiple Input Multiple Output (MIMO) system is simulated and the performance variation with different channel estimation schemes are evaluated. A new semi blind approach based on dynamic ANN is proposed for channel tracking in varying channel conditions and the performance is compared with perfectly known CSI and least square (LS) based estimation.
Abstract: In this paper, a novel associative memory model will be proposed and applied to memory retrievals based on the conventional continuous time model. The conventional model presents memory capacity is very low and retrieval process easily converges to an equilibrium state which is very different from the stored patterns. Genetic Algorithms is well-known with the capability of global optimal search escaping local optimum on progress to reach a global optimum. Based on the well-known idea of Genetic Algorithms, this work proposes a heuristic rule to make a mutation when the state of the network is trapped in a spurious memory. The proposal heuristic associative memory show the stored capacity does not depend on the number of stored patterns and the retrieval ability is up to ~ 1.
Abstract: Rapid progress in process automation and tightening
quality standards result in a growing demand being placed on fault
detection and diagnostics methods to provide both speed and
reliability of motor quality testing. Doubly fed induction generators
are used mainly for wind energy conversion in MW power plants.
This paper presents a detection of an inter turn stator and an open
phase faults, in a doubly fed induction machine whose stator and
rotor are supplied by two pulse width modulation (PWM) inverters.
The method used in this article to detect these faults, is based on
Park-s Vector Approach, using a neural network.
Abstract: Text Mining is around applying knowledge discovery techniques to unstructured text is termed knowledge discovery in text (KDT), or Text data mining or Text Mining. In Neural Network that address classification problems, training set, testing set, learning rate are considered as key tasks. That is collection of input/output patterns that are used to train the network and used to assess the network performance, set the rate of adjustments. This paper describes a proposed back propagation neural net classifier that performs cross validation for original Neural Network. In order to reduce the optimization of classification accuracy, training time. The feasibility the benefits of the proposed approach are demonstrated by means of five data sets like contact-lenses, cpu, weather symbolic, Weather, labor-nega-data. It is shown that , compared to exiting neural network, the training time is reduced by more than 10 times faster when the dataset is larger than CPU or the network has many hidden units while accuracy ('percent correct') was the same for all datasets but contact-lences, which is the only one with missing attributes. For contact-lences the accuracy with Proposed Neural Network was in average around 0.3 % less than with the original Neural Network. This algorithm is independent of specify data sets so that many ideas and solutions can be transferred to other classifier paradigms.
Abstract: By using the method of coincidence degree theory and constructing suitable Lyapunov functional, several sufficient conditions are established for the existence and global exponential stability of anti-periodic solutions for Cohen-Grossberg shunting inhibitory neural networks with delays. An example is given to illustrate our feasible results.
Abstract: Several valve stiction models have been proposed in the literature to help understand and study the behavior of sticky valves. In this paper, an alternative black-box modeling approach based on Neural Network (NN) is presented. It is shown that with proper network type and optimum model structures, the performance of the developed NN stiction model is comparable to other established method. The resulting NN model is also tested for its robustness against the uncertainty in the stiction parameter values. Predictive mode operation also shows excellent performance of the proposed model for multi-steps ahead prediction.
Abstract: In this paper, we propose to study the synthesis of the
vertical dipole antenna over imperfect ground. The synthesis
implementation-s method for this type of antenna permits to
approach the appropriated radiance-s diagram. The used approach is
based on neural network. Our main contribution in this paper is the
extension of a synthesis model of this vertical dipole antenna over
imperfect ground.
Abstract: This paper presents the use of a newly created network
structure known as a Self-Delaying Dynamic Network (SDN) to
create a high resolution image from a set of time stepped input
frames. These SDNs are non-recurrent temporal neural networks
which can process time sampled data. SDNs can store input data
for a lifecycle and feature dynamic logic based connections between
layers. Several low resolution images and one high resolution image
of a scene were presented to the SDN during training by a Genetic
Algorithm. The SDN was trained to process the input frames in order
to recreate the high resolution image. The trained SDN was then used
to enhance a number of unseen noisy image sets. The quality of high
resolution images produced by the SDN is compared to that of high
resolution images generated using Bi-Cubic interpolation. The SDN
produced images are superior in several ways to the images produced
using Bi-Cubic interpolation.
Abstract: Embedded systems need to respect stringent real
time constraints. Various hardware components included in such
systems such as cache memories exhibit variability and therefore
affect execution time. Indeed, a cache memory access from an
embedded microprocessor might result in a cache hit where the
data is available or a cache miss and the data need to be fetched
with an additional delay from an external memory. It is therefore
highly desirable to predict future memory accesses during
execution in order to appropriately prefetch data without incurring
delays. In this paper, we evaluate the potential of several artificial
neural networks for the prediction of instruction memory
addresses. Neural network have the potential to tackle the nonlinear
behavior observed in memory accesses during program
execution and their demonstrated numerous hardware
implementation emphasize this choice over traditional forecasting
techniques for their inclusion in embedded systems. However,
embedded applications execute millions of instructions and
therefore millions of addresses to be predicted. This very
challenging problem of neural network based prediction of large
time series is approached in this paper by evaluating various neural
network architectures based on the recurrent neural network
paradigm with pre-processing based on the Self Organizing Map
(SOM) classification technique.
Abstract: In modern human computer interaction systems
(HCI), emotion recognition is becoming an imperative characteristic.
The quest for effective and reliable emotion recognition in HCI has
resulted in a need for better face detection, feature extraction and
classification. In this paper we present results of feature space analysis
after briefly explaining our fully automatic vision based emotion
recognition method. We demonstrate the compactness of the feature
space and show how the 2d/3d based method achieves superior features
for the purpose of emotion classification. Also it is exposed that
through feature normalization a widely person independent feature
space is created. As a consequence, the classifier architecture has
only a minor influence on the classification result. This is particularly
elucidated with the help of confusion matrices. For this purpose
advanced classification algorithms, such as Support Vector Machines
and Artificial Neural Networks are employed, as well as the simple k-
Nearest Neighbor classifier.
Abstract: An Optimal Power Flow based on Improved Particle
Swarm Optimization (OPF-IPSO) with Generator Capability Curve
Constraint is used by NN-OPF as a reference to get pattern of
generator scheduling. There are three stages in Designing NN-OPF.
The first stage is design of OPF-IPSO with generator capability curve
constraint. The second stage is clustering load to specific range and
calculating its index. The third stage is training NN-OPF using
constructive back propagation method. In training process total load
and load index used as input, and pattern of generator scheduling
used as output. Data used in this paper is power system of Java-Bali.
Software used in this simulation is MATLAB.
Abstract: Developing a stable early warning system (EWS)
model that is capable to give an accurate prediction is a challenging
task. This paper introduces k-nearest neighbour (k-NN) method
which never been applied in predicting currency crisis before with the
aim of increasing the prediction accuracy. The proposed k-NN
performance depends on the choice of a distance that is used where in
our analysis; we take the Euclidean distance and the Manhattan as a
consideration. For the comparison, we employ three other methods
which are logistic regression analysis (logit), back-propagation neural
network (NN) and sequential minimal optimization (SMO). The
analysis using datasets from 8 countries and 13 macro-economic
indicators for each country shows that the proposed k-NN method
with k = 4 and Manhattan distance performs better than the other
methods.
Abstract: Partitioning is a critical area of VLSI CAD. In order to build complex digital logic circuits its often essential to sub-divide multi -million transistor design into manageable Pieces. This paper looks at the various partitioning techniques aspects of VLSI CAD, targeted at various applications. We proposed an evolutionary time-series model and a statistical glitch prediction system using a neural network with selection of global feature by making use of clustering method model, for partitioning a circuit. For evolutionary time-series model, we made use of genetic, memetic & neuro-memetic techniques. Our work focused in use of clustering methods - K-means & EM methodology. A comparative study is provided for all techniques to solve the problem of circuit partitioning pertaining to VLSI design. The performance of all approaches is compared using benchmark data provided by MCNC standard cell placement benchmark net lists. Analysis of the investigational results proved that the Neuro-memetic model achieves greater performance then other model in recognizing sub-circuits with minimum amount of interconnections between them.
Abstract: This paper reports work done to improve the modeling of complex processes when only small experimental data sets are available. Neural networks are used to capture the nonlinear underlying phenomena contained in the data set and to partly eliminate the burden of having to specify completely the structure of the model. Two different types of neural networks were used for the application of Pulping of Sugar Maple problem. A three layer feed forward neural networks, using the Preconditioned Conjugate Gradient (PCG) methods were used in this investigation. Preconditioning is a method to improve convergence by lowering the condition number and increasing the eigenvalues clustering. The idea is to solve the modified problem where M is a positive-definite preconditioner that is closely related to A. We mainly focused on Preconditioned Conjugate Gradient- based training methods which originated from optimization theory, namely Preconditioned Conjugate Gradient with Fletcher-Reeves Update (PCGF), Preconditioned Conjugate Gradient with Polak-Ribiere Update (PCGP) and Preconditioned Conjugate Gradient with Powell-Beale Restarts (PCGB). The behavior of the PCG methods in the simulations proved to be robust against phenomenon such as oscillations due to large step size.