Abstract: This paper illustrates the use of a combined neural
network model for classification of electrocardiogram (ECG) beats.
We present a trainable neural network ensemble approach to develop
customized electrocardiogram beat classifier in an effort to further
improve the performance of ECG processing and to offer
individualized health care.
We process a three stage technique for detection of premature
ventricular contraction (PVC) from normal beats and other heart
diseases. This method includes a denoising, a feature extraction and a
classification. At first we investigate the application of stationary
wavelet transform (SWT) for noise reduction of the
electrocardiogram (ECG) signals. Then feature extraction module
extracts 10 ECG morphological features and one timing interval
feature. Then a number of multilayer perceptrons (MLPs) neural
networks with different topologies are designed.
The performance of the different combination methods as well as
the efficiency of the whole system is presented. Among them,
Stacked Generalization as a proposed trainable combined neural
network model possesses the highest recognition rate of around 95%.
Therefore, this network proves to be a suitable candidate in ECG
signal diagnosis systems. ECG samples attributing to the different
ECG beat types were extracted from the MIT-BIH arrhythmia
database for the study.
Abstract: In this paper, an artificial intelligent technique for
robust digital image watermarking in multiwavelet domain is
proposed. The embedding technique is based on the quantization
index modulation technique and the watermark extraction process
does not require the original image. We have developed an
optimization technique using the genetic algorithms to search for
optimal quantization steps to improve the quality of watermarked
image and robustness of the watermark. In addition, we construct a
prediction model based on image moments and back propagation
neural network to correct an attacked image geometrically before the
watermark extraction process begins. The experimental results show
that the proposed watermarking algorithm yields watermarked image
with good imperceptibility and very robust watermark against various
image processing attacks.
Abstract: With the proliferation of multi-channel retailing, developing a better understanding of the factors that affect customers- purchase behaviors within a multi-channel retail context has become an important topic for practitioners and academics. While many studies have investigated the various customer behaviors associated with brick-and-mortar retailing, online retailing, and brick-and-click retailing, little research has explored how customer shopping value perceptions influence online purchase behaviors within the TV-and-online retail environment. The main purpose of this study is to investigate the influence of TV and online shopping values on online patronage intention. Data collected from 116 respondents in Taiwan are tested against the research model using the partial least squares (PLS) approach. The results indicate that utilitarian and hedonic TV shopping values have indirect, positive influences on online patronage intention through their online counterparts in the TV-and-online retail context. The findings of this study provide several important theoretical and practical implications for multi-channel retailing.
Abstract: It is well known that the phraseology of a language - the phenomenon of identity. This uniqueness is due to the fact that "there are idioms image-based views of reality that shows mainly of everyday empirical, historical and spiritual experience of a language community, associated with its cultural traditions. The article says that the phraseological units very clearly show the image of the people and give us a great view of the national identity. With the phraseology of the Kazakh and Korean language can understand the mentality of the nation, identity, perception of people. It is in the phraseological units can surprise the culture and customs of the people. Phraseological units store and transmit information about the level of material and spiritual culture of the people, his life, past and present, the development of society in general. And in Korean and Kazakh languages idioms occupy a particularly important role.
Abstract: In this paper, we propose a Perceptually Optimized Embedded ZeroTree Image Coder (POEZIC) that introduces a perceptual weighting to wavelet transform coefficients prior to control SPIHT encoding algorithm in order to reach a targeted bit rate with a perceptual quality improvement with respect to the coding quality obtained using the SPIHT algorithm only. The paper also, introduces a new objective quality metric based on a Psychovisual model that integrates the properties of the HVS that plays an important role in our POEZIC quality assessment. Our POEZIC coder is based on a vision model that incorporates various masking effects of human visual system HVS perception. Thus, our coder weights the wavelet coefficients based on that model and attempts to increase the perceptual quality for a given bit rate and observation distance. The perceptual weights for all wavelet subbands are computed based on 1) luminance masking and Contrast masking, 2) the contrast sensitivity function CSF to achieve the perceptual decomposition weighting, 3) the Wavelet Error Sensitivity WES used to reduce the perceptual quantization errors. The new perceptually optimized codec has the same complexity as the original SPIHT techniques. However, the experiments results show that our coder demonstrates very good performance in terms of quality measurement.
Abstract: Retrieval image by shape similarity, given a template
shape is particularly challenging, owning to the difficulty to derive a
similarity measurement that closely conforms to the common
perception of similarity by humans. In this paper, a new method for the
representation and comparison of shapes is present which is based on
the shape matrix and snake model. It is scaling, rotation, translation
invariant. And it can retrieve the shape images with some missing or
occluded parts. In the method, the deformation spent by the template
to match the shape images and the matching degree is used to evaluate
the similarity between them.
Abstract: In this paper, the application of neural networks to study the design of short-term load forecasting (STLF) Systems for Illam state located in west of Iran was explored. One important architecture of neural networks named Multi-Layer Perceptron (MLP) to model STLF systems was used. Our study based on MLP was trained and tested using three years (2004-2006) data. The results show that MLP network has the minimum forecasting error and can be considered as a good method to model the STLF systems.
Abstract: Inverse kinematics analysis plays an important role in developing a robot manipulator. But it is not too easy to derive the inverse kinematic equation of a robot manipulator especially robot manipulator which has numerous degree of freedom. This paper describes an application of Artificial Neural Network for modeling the inverse kinematics equation of a robot manipulator. In this case, the robot has three degree of freedoms and the robot was implemented for drilling a printed circuit board. The artificial neural network architecture used for modeling is a multilayer perceptron networks with steepest descent backpropagation training algorithm. The designed artificial neural network has 2 inputs, 2 outputs and varies in number of hidden layer. Experiments were done in variation of number of hidden layer and learning rate. Experimental results show that the best architecture of artificial neural network used for modeling inverse kinematics of is multilayer perceptron with 1 hidden layer and 38 neurons per hidden layer. This network resulted a RMSE value of 0.01474.
Abstract: As nanotechnology advances, the use of nanotechnology for medical purposes in the field of nanomedicine seems more promising; the rise of nanorobots for medical diagnostics and treatments could be arriving in the near future. This study proposes a swarm intelligence based control mechanism for swarm nanorobots that operate as artificial platelets to search for wounds. The canonical particle swarm optimization algorithm is employed in this study. A simulation in the circulatory system is constructed and used for demonstrating the movement of nanorobots with essential characteristics to examine the performance of proposed control mechanism. The effects of three nanorobot capabilities including their perception range, maximum velocity and respond time are investigated. The results show that canonical particle swarm optimization can be used to control the early version nanorobots with simple behaviors and actions.
Abstract: The conjugate gradient optimization algorithm
usually used for nonlinear least squares is presented and is
combined with the modified back propagation algorithm yielding
a new fast training multilayer perceptron (MLP) algorithm
(CGFR/AG). The approaches presented in the paper consist of
three steps: (1) Modification on standard back propagation
algorithm by introducing gain variation term of the activation
function, (2) Calculating the gradient descent on error with
respect to the weights and gains values and (3) the determination
of the new search direction by exploiting the information
calculated by gradient descent in step (2) as well as the previous
search direction. The proposed method improved the training
efficiency of back propagation algorithm by adaptively modifying
the initial search direction. Performance of the proposed method
is demonstrated by comparing to the conjugate gradient algorithm
from neural network toolbox for the chosen benchmark. The
results show that the number of iterations required by the
proposed method to converge is less than 20% of what is required
by the standard conjugate gradient and neural network toolbox
algorithm.
Abstract: Studies in neuroscience suggest that both global and
local feature information are crucial for perception and recognition of
faces. It is widely believed that local feature is less sensitive to
variations caused by illumination, expression and illumination. In
this paper, we target at designing and learning local features for face
recognition. We designed three types of local features. They are
semi-global feature, local patch feature and tangent shape feature.
The designing of semi-global feature aims at taking advantage of
global-like feature and meanwhile avoiding suppressing AdaBoost
algorithm in boosting weak classifies established from small local
patches. The designing of local patch feature targets at automatically
selecting discriminative features, and is thus different with traditional
ways, in which local patches are usually selected manually to cover
the salient facial components. Also, shape feature is considered in
this paper for frontal view face recognition. These features are
selected and combined under the framework of boosting algorithm
and cascade structure. The experimental results demonstrate that the
proposed approach outperforms the standard eigenface method and
Bayesian method. Moreover, the selected local features and
observations in the experiments are enlightening to researches in
local feature design in face recognition.
Abstract: In this article, a method has been offered to classify
normal and defective tiles using wavelet transform and artificial
neural networks. The proposed algorithm calculates max and min
medians as well as the standard deviation and average of detail
images obtained from wavelet filters, then comes by feature vectors
and attempts to classify the given tile using a Perceptron neural
network with a single hidden layer. In this study along with the
proposal of using median of optimum points as the basic feature and
its comparison with the rest of the statistical features in the wavelet
field, the relational advantages of Haar wavelet is investigated. This
method has been experimented on a number of various tile designs
and in average, it has been valid for over 90% of the cases. Amongst
the other advantages, high speed and low calculating load are
prominent.
Abstract: Interest in Human Consciousness has been revived in the late 20th century from different scientific disciplines. Consciousness studies involve both its understanding and its application. In this paper, a computational model of the minimum consciousness functions necessary in my point of view for Artificial Intelligence applications is presented with the aim of improving the way computations will be made in the future. In section I, human consciousness is briefly described according to the scope of this paper. In section II, a minimum set of consciousness functions is defined - based on the literature reviewed - to be modelled, and then a computational model of these functions is presented in section III. In section IV, an analysis of the model is carried out to describe its functioning in detail.
Abstract: Online auctions are not very popular in Croatia. The
main reason for this is a very limited number of services which can
be used by Croatian users. Until recent times, even selling through
the most popular online auction site eBay wasn't possible because
PayPal services could not make payment to bank or debit card
accounts in Croatia. Furthermore, many foreign sellers do not offer
delivery of their products to Croatia which means that large
quantities of goods initially offered on such sites are not available.
With that in mind, it is necessary to analyze the buying and selling
habits of Croatian users and existing online auction sites, both
Croatian and foreign, and create a model for new domestic site. This
site will have to exploit every positive aspect of existing models and
neutralize every negative perception indicated by users in the survey
so that, hopefully, it would attract new users.
Abstract: Weblog is an Internet tool that is believed to possess
great potential to facilitate learning in education. This study wants to
know if weblog can be used to promote students- critical thinking. It
used a group of secondary two students from a Singapore school to
write weblogs as a means of substitution for their traditional
handwritten assignments. The topics for the weblogging are taken
from History syllabus but modified to suit the purpose of this study.
Weblogs from the students were collected and analysed using a
known coding system for measuring critical thinking. Results show
that the topic for blogging is crucial in determining the types of
critical thinking employed by the students. Students are seen to
display critical thinking traits in the areas of information sourcing,
linking information to arguments and viewpoints justification.
Students- criticalness is more profound when the information for
writing a topic is readily available. Otherwise, they tend to be less
critical and subjective. The study also found that students lack the
ability to source for external information suggesting that students
may need to be taught information literacy in order to widen their use
of critical thinking skills.
Abstract: The recent development of humanoid robots has led robot designers to imagine a great variety of anthropomorphic forms for human-like machine. Which form is the best ? We try to answer this question from a double meaning of the anthropomorphism : a positive anthropomorphism corresponing to the realization of an effective anthropomorphic form object and a negative one corresponding to our natural tendency in certain circumstances to give human attributes to non-human beings. We postulate that any humanoid robot is concerned by both these two anthropomorphism kinds. We propose to use gestalt theory and Heider-s balance theory in order to analyze how negative anthropomorphism can influence our perception of human-like robots. From our theoretical approach we conclude that an “even shape" as defined by gestalt theory is not a sufficient condition for a good integration of future humanoid robots into a human community. Aesthetic perception of the robot cannot be splitted from a social perception : a humanoid robot, any how the efforts made for improving its appearance, could be rejected if it is devoted to a task with too high affective implications.
Abstract: In this paper we present an efficient system for
independent speaker speech recognition based on neural network
approach. The proposed architecture comprises two phases: a
preprocessing phase which consists in segmental normalization and
features extraction and a classification phase which uses neural
networks based on nonparametric density estimation namely the
general regression neural network (GRNN). The relative
performances of the proposed model are compared to the similar
recognition systems based on the Multilayer Perceptron (MLP), the
Recurrent Neural Network (RNN) and the well known Discrete
Hidden Markov Model (HMM-VQ) that we have achieved also.
Experimental results obtained with Arabic digits have shown that the
use of nonparametric density estimation with an appropriate
smoothing factor (spread) improves the generalization power of the
neural network. The word error rate (WER) is reduced significantly
over the baseline HMM method. GRNN computation is a successful
alternative to the other neural network and DHMM.