Abstract: In this paper, the requirement for Coke quality
prediction, its role in Blast furnaces, and the model output is
explained. By applying method of Artificial Neural Networking
(ANN) using back propagation (BP) algorithm, prediction model has
been developed to predict CSR. Important blast furnace functions
such as permeability, heat exchanging, melting, and reducing
capacity are mostly connected to coke quality. Coke quality is further
dependent upon coal characterization and coke making process
parameters. The ANN model developed is a useful tool for process
experts to adjust the control parameters in case of coke quality
deviations. The model also makes it possible to predict CSR for new
coal blends which are yet to be used in Coke Plant. Input data to the
model was structured into 3 modules, for tenure of past 2 years and
the incremental models thus developed assists in identifying the
group causing the deviation of CSR.
Abstract: This paper examines many mathematical methods for
molding the hourly price forward curve (HPFC); the model will be
constructed by numerous regression methods, like polynomial
regression, radial basic function neural networks & a furrier series.
Examination the models goodness of fit will be done by means of
statistical & graphical tools. The criteria for choosing the model will
depend on minimize the Root Mean Squared Error (RMSE), using the
correlation analysis approach for the regression analysis the optimal
model will be distinct, which are robust against model
misspecification. Learning & supervision technique employed to
determine the form of the optimal parameters corresponding to each
measure of overall loss. By using all the numerical methods that
mentioned previously; the explicit expressions for the optimal model
derived and the optimal designs will be implemented.
Abstract: In this paper, a clustering algorithm named KHarmonic
means (KHM) was employed in the training of Radial
Basis Function Networks (RBFNs). KHM organized the data in
clusters and determined the centres of the basis function. The popular
clustering algorithms, namely K-means (KM) and Fuzzy c-means
(FCM), are highly dependent on the initial identification of elements
that represent the cluster well. In KHM, the problem can be avoided.
This leads to improvement in the classification performance when
compared to other clustering algorithms. A comparison of the
classification accuracy was performed between KM, FCM and KHM.
The classification performance is based on the benchmark data sets:
Iris Plant, Diabetes and Breast Cancer. RBFN training with the KHM
algorithm shows better accuracy in classification problem.
Abstract: In the present study, position estimation of switched reluctance motor (SRM) has been achieved on the basis of the artificial neural networks (ANNs). The ANNs can estimate the rotor position without using an extra rotor position sensor by measuring the phase flux linkages and phase currents. Flux linkage-phase current-rotor position data set and supervised backpropagation learning algorithm are used in training of the ANN based position estimator. A 4-phase SRM have been used to verify the accuracy and feasibility of the proposed position estimator. Simulation results show that the proposed position estimator gives precise and accurate position estimations for both under the low and high level reference speeds of the SRM
Abstract: It is known that an analog Hopfield neural network
with time delay can generate the outputs which are similar to the
human electroencephalogram. To gain deeper insights into the
mechanisms of rhythm generation by the Hopfield neural networks
and to study the effects of noise on their activities, we investigated
the behaviors of the networks with symmetric and asymmetric
interneuron connections. The neural network under the study consists
of 10 identical neurons. For symmetric (fully connected) networks all
interneuron connections aij = +1; the interneuron connections for
asymmetric networks form an upper triangular matrix with non-zero
entries aij = +1. The behavior of the network is described by 10
differential equations, which are solved numerically. The results of
simulations demonstrate some remarkable properties of a Hopfield
neural network, such as linear growth of outputs, dependence of
synchronization properties on the connection type, huge
amplification of oscillation by the external uniform noise, and the
capability of the neural network to transform one type of noise to
another.
Abstract: The paper presents a complete discrete statistical framework, based on a novel vector quantization (VQ) front-end process. This new VQ approach performs an optimal distribution of VQ codebook components on HMM states. This technique that we named the distributed vector quantization (DVQ) of hidden Markov models, succeeds in unifying acoustic micro-structure and phonetic macro-structure, when the estimation of HMM parameters is performed. The DVQ technique is implemented through two variants. The first variant uses the K-means algorithm (K-means- DVQ) to optimize the VQ, while the second variant exploits the benefits of the classification behavior of neural networks (NN-DVQ) for the same purpose. The proposed variants are compared with the HMM-based baseline system by experiments of specific Arabic consonants recognition. The results show that the distributed vector quantization technique increase the performance of the discrete HMM system.
Abstract: In this paper, based on linear matrix inequality (LMI), by using Lyapunov functional theory, the exponential stability criterion is obtained for a class of uncertain Takagi-Sugeno fuzzy Hopfield neural networks (TSFHNNs) with time delays. Here we choose a generalized Lyapunov functional and introduce a parameterized model transformation with free weighting matrices to it, these techniques lead to generalized and less conservative stability condition that guarantee the wide stability region. Finally, an example is given to illustrate our results by using MATLAB LMI toolbox.
Abstract: Chaos and fractals are novel fields of physics and mathematics showing up a new way of universe viewpoint and creating many ideas to solve several present problems. In this paper, a novel algorithm based on the chaotic sequence generator with the highest ability to adapt and reach the global optima is proposed. The adaptive ability of proposal algorithm is flexible in 2 steps. The first one is a breadth-first search and the second one is a depth-first search. The proposal algorithm is examined by 2 functions, the Camel function and the Schaffer function. Furthermore, the proposal algorithm is applied to optimize training Multilayer Neural Networks.
Abstract: Human identification at a distance has recently gained
growing interest from computer vision researchers. Gait recognition
aims essentially to address this problem by identifying people based
on the way they walk [1]. Gait recognition has 3 steps. The first step
is preprocessing, the second step is feature extraction and the third
one is classification. This paper focuses on the classification step that
is essential to increase the CCR (Correct Classification Rate).
Multilayer Perceptron (MLP) is used in this work. Neural Networks
imitate the human brain to perform intelligent tasks [3].They can
represent complicated relationships between input and output and
acquire knowledge about these relationships directly from the data
[2]. In this paper we apply MLP NN for 11 views in our database and
compare the CCR values for these views. Experiments are performed
with the NLPR databases, and the effectiveness of the proposed
method for gait recognition is demonstrated.
Abstract: Recently, neural networks have shown good
results for detection of a certain pattern in a given image. In
our previous papers [1-5], a fast algorithm for pattern
detection using neural networks was presented. Such
algorithm was designed based on cross correlation in the
frequency domain between the input image and the weights
of neural networks. Image conversion into symmetric shape
was established so that fast neural networks can give the
same results as conventional neural networks. Another
configuration of symmetry was suggested in [3,4] to improve
the speed up ratio. In this paper, our previous algorithm for
fast neural networks is developed. The frequency domain
cross correlation is modified in order to compensate for the
symmetric condition which is required by the input image.
Two new ideas are introduced to modify the cross correlation
algorithm. Both methods accelerate the speed of the fast
neural networks as there is no need for converting the input
image into symmetric one as previous. Theoretical and
practical results show that both approaches provide faster
speed up ratio than the previous algorithm.
Abstract: In this paper, the issue of pth moment exponential stability of stochastic recurrent neural network with distributed time delays is investigated. By using the method of variation parameters, inequality techniques, and stochastic analysis, some sufficient conditions ensuring pth moment exponential stability are obtained. The method used in this paper does not resort to any Lyapunov function, and the results derived in this paper generalize some earlier criteria reported in the literature. One numerical example is given to illustrate the main results.
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 a class of analog algorithms based on the
concept of Cellular Neural Network (CNN) is applied in some
processing operations of some important medical images, namely
retina images, for detecting various symptoms connected with
diabetic retinopathy. Some specific processing tasks like
morphological operations, linear filtering and thresholding are
proposed, the corresponding template values are given and
simulations on real retina images are provided.
Abstract: This study presents a hybrid neural network and Gravitational Search Algorithm (HNGSA) method to solve well known Wessinger's equation. To aim this purpose, gravitational search algorithm (GSA) technique is applied to train a multi-layer perceptron neural network, which is used as approximation solution of the Wessinger's equation. A trial solution of the differential equation is written as sum of two parts. The first part satisfies the initial/ boundary conditions and does not contain any adjustable parameters and the second part which is constructed so as not to affect the initial/boundary conditions. The second part involves adjustable parameters (the weights and biases) for a multi-layer perceptron neural network. In order to demonstrate the presented method, the obtained results of the proposed method are compared with some known numerical methods. The given results show that presented method can introduce a closer form to the analytic solution than other numerical methods. Present method can be easily extended to solve a wide range of problems.
Abstract: Instead of representing individual cognition only, population cognition is represented using artificial neural networks whilst maintaining individuality. This population network trains continuously, simulating adaptation. An implementation of two coexisting populations is compared to the Lotka-Volterra model of predator-prey interaction. Applications include multi-agent systems such as artificial life or computer games.
Abstract: Soil organic carbon (SOC) plays a key role in soil
fertility, hydrology, contaminants control and acts as a sink or source
of terrestrial carbon content that can affect the concentration of
atmospheric CO2. SOC supports the sustainability and quality of
ecosystems, especially in semi-arid region. This study was
conducted to determine relative importance of 13 different
exploratory climatic, soil and geometric factors on the SOC contents
in one of the semiarid watershed zones in Iran. Two methods
canonical discriminate analysis (CDA) and feed-forward back
propagation neural networks were used to predict SOC. Stepwise
regression and sensitivity analysis were performed to identify
relative importance of exploratory variables. Results from sensitivity
analysis showed that 7-2-1 neural networks and 5 inputs in CDA
models output have highest predictive ability that explains %70 and
%65 of SOC variability. Since neural network models outperformed
CDA model, it should be preferred for estimating SOC.
Abstract: In many data mining applications, it is a priori known
that the target function should satisfy certain constraints imposed
by, for example, economic theory or a human-decision maker. In this
paper we consider partially monotone prediction problems, where the
target variable depends monotonically on some of the input variables
but not on all. We propose a novel method to construct prediction
models, where monotone dependences with respect to some of
the input variables are preserved by virtue of construction. Our
method belongs to the class of mixture models. The basic idea is to
convolute monotone neural networks with weight (kernel) functions
to make predictions. By using simulation and real case studies,
we demonstrate the application of our method. To obtain sound
assessment for the performance of our approach, we use standard
neural networks with weight decay and partially monotone linear
models as benchmark methods for comparison. The results show that
our approach outperforms partially monotone linear models in terms
of accuracy. Furthermore, the incorporation of partial monotonicity
constraints not only leads to models that are in accordance with the
decision maker's expertise, but also reduces considerably the model
variance in comparison to standard neural networks with weight
decay.
Abstract: Imperfect knowledge cannot be avoided all the time. Imperfections may have several forms; uncertainties, imprecision and incompleteness. When we look to classification of methods for the management of imperfect knowledge we see fuzzy set-based techniques. The choice of a method to process data is linked to the choice of knowledge representation, which can be numerical, symbolic, logical or semantic and it depends on the nature of the problem to be solved for example decision support, which will be mentioned in our study. Fuzzy Logic is used for its ability to manage imprecise knowledge, but it can take advantage of the ability of neural networks to learn coefficients or functions. Such an association of methods is typical of so-called soft computing. In this study a new method was used for the management of imprecision for collected knowledge which related to economic analysis of construction industry in Turkey. Because of sudden changes occurring in economic factors decrease competition strength of construction companies. The better evaluation of these changes in economical factors in view of construction industry will made positive influence on company-s decisions which are dealing construction.
Abstract: Emerging Bio-engineering fields such as Brain
Computer Interfaces, neuroprothesis devices and modeling and
simulation of neural networks have led to increased research activity
in algorithms for the detection, isolation and classification of Action
Potentials (AP) from noisy data trains. Current techniques in the field
of 'unsupervised no-prior knowledge' biosignal processing include
energy operators, wavelet detection and adaptive thresholding. These
tend to bias towards larger AP waveforms, AP may be missed due to
deviations in spike shape and frequency and correlated noise
spectrums can cause false detection. Also, such algorithms tend to
suffer from large computational expense.
A new signal detection technique based upon the ideas of phasespace
diagrams and trajectories is proposed based upon the use of a
delayed copy of the AP to highlight discontinuities relative to
background noise. This idea has been used to create algorithms that
are computationally inexpensive and address the above problems.
Distinct AP have been picked out and manually classified from
real physiological data recorded from a cockroach. To facilitate
testing of the new technique, an Auto Regressive Moving Average
(ARMA) noise model has been constructed bases upon background
noise of the recordings. Along with the AP classification means this
model enables generation of realistic neuronal data sets at arbitrary
signal to noise ratio (SNR).
Abstract: In this paper, delay-dependent stability analysis for
neutral type neural networks with uncertain paramters and
time-varying delay is studied. By constructing new
Lyapunov-Krasovskii functional and dividing the delay interval into
multiple segments, a novel sufficient condition is established to
guarantee the globally asymptotically stability of the considered
system. Finally, a numerical example is provided to illustrate the
usefulness of the proposed main results.