Abstract: The work reported in this paper is motivated by the fact that there is a need to apply autonomic computing concepts to parallel computing systems. Advancing on prior work based on intelligent cores [36], a swarm-array computing approach, this paper focuses on 'Intelligent agents' another swarm-array computing approach in which the task to be executed on a parallel computing core is considered as a swarm of autonomous agents. A task is carried to a computing core by carrier agents and is seamlessly transferred between cores in the event of a predicted failure, thereby achieving self-ware objectives of autonomic computing. The feasibility of the proposed swarm-array computing approach is validated on a multi-agent simulator.
Abstract: In the present study, a steady-state simulation model
has been developed to evaluate the system performance of a
transcritical carbon dioxide heat pump system for simultaneous water
cooling and heating. Both the evaporator (including both two-phase
and superheated zone) and gas cooler models consider the highly
variable heat transfer characteristics of CO2 and pressure drop. The
numerical simulation model of transcritical CO2 heat pump has been
validated by test data obtained from experiments on the heat pump
prototype. Comparison between the test results and the model
prediction for system COP variation with compressor discharge
pressure shows a modest agreement with a maximum deviation of
15% and the trends are fairly similar. Comparison for other operating
parameters also shows fairly similar deviation between the test
results and the model prediction. Finally, the simulation results are
presented to study the effects of operating parameters such as,
temperature of heat exchanger fluid at the inlet, discharge pressure,
compressor speed on system performance of CO2 heat pump, suitable
in a dairy plant where simultaneous cooling at 4oC and heating at
73oC are required. Results show that good heat transfer properties of
CO2 for both two-phase and supercritical region and efficient
compression process contribute a lot for high system COPs.
Abstract: In this paper, the Lennard -Jones potential is applied
to molecules of liquid argon as well as its vapor and platinum as solid
surface in order to perform a non-equilibrium molecular dynamics
simulation to study the microscopic aspects of liquid-vapor-solid
interactions. The channel is periodic in x and y directions and along z
direction it is bounded by atomic walls. It was found that density of
the liquids near the solid walls fluctuated greatly and that the
structure was more like a solid than a liquid. This indicates that the
interactions of solid and liquid molecules are very strong. The
resultant surface tension, liquid density and vapor density are found
to be well predicted when compared with the experimental data for
argon. Liquid and vapor densities were found to depend on the cutoff
radius which induces the use of P3M (particle-particle particle-mesh)
method which was implemented for evaluation of force and surface
tension.
Abstract: A New features are extracted and compared to
improve the prediction of protein-protein interactions. The basic idea
is to select and use the best set of features from the Tensor matrices
that are produced by the frequency vectors of the protein sequences.
Three set of features are compared, the first set is based on the
indices that are the most common in the interacting proteins, the
second set is based on the indices that tend to be common in the
interacting and non-interacting proteins, and the third set is
constructed by using random indices. Moreover, three encoding
strategies are compared; that are based on the amino asides polarity,
structure, and chemical properties. The experimental results indicate
that the highest accuracy can be obtained by using random indices
with chemical properties encoding strategy and support vector
machine.
Abstract: The purpose of this study was to investigate the
relationships among students- process of study, creative self-efficacy
and creativity while attending college. A total of 60 students enrolled
in Hsiuping Institute of Technology in central Taiwan were selected as
samples for the study. The instruments for this study included three
questionnaires to explore the aforesaid aspects.
This researchers tested creative self-efficacy and process of study,
and creativity with Pearson correlation and hierarchical regression
analyses. The major findings of this research are (1) the process of
study had direct positive predictability on creativity, and (2) the
relationship between process of study and creativity is partially
mediated by creative self-efficacy.
Abstract: This paper investigates the performance of a speech
recognizer in an interactive voice response system for various coded
speech signals, coded by using a vector quantization technique namely
Multi Switched Split Vector Quantization Technique. The process of
recognizing the coded output can be used in Voice banking application.
The recognition technique used for the recognition of the coded speech
signals is the Hidden Markov Model technique. The spectral distortion
performance, computational complexity, and memory requirements of
Multi Switched Split Vector Quantization Technique and the
performance of the speech recognizer at various bit rates have been
computed. From results it is found that the speech recognizer is
showing better performance at 24 bits/frame and it is found that the
percentage of recognition is being varied from 100% to 93.33% for
various bit rates.
Abstract: In this research work, investigations are carried out on
Continuous Wave (CW) Nd:YAG laser welding system after
preliminary experimentation to understand the influencing parameters
associated with laser welding of AISI 304. The experimental
procedure involves a series of laser welding trials on AISI 304
stainless steel sheets with various combinations of process parameters
like beam power, beam incident angle and beam incident angle. An
industrial 2 kW CW Nd:YAG laser system, available at Welding
Research Institute (WRI), BHEL Tiruchirappalli, is used for
conducting the welding trials for this research. After proper tuning of
laser beam, laser welding experiments are conducted on AISI 304
grade sheets to evaluate the influence of various input parameters on
weld bead geometry i.e. bead width (BW) and depth of penetration
(DOP). From the laser welding results, it is noticed that the beam
power and welding speed are the two influencing parameters on
depth and width of the bead. Three dimensional finite element
simulation of high density heat source have been performed for laser
welding technique using finite element code ANSYS for predicting
the temperature profile of laser beam heat source on AISI 304
stainless steel sheets. The temperature dependent material properties
for AISI 304 stainless steel are taken into account in the simulation,
which has a great influence in computing the temperature profiles.
The latent heat of fusion is considered by the thermal enthalpy of
material for calculation of phase transition problem. A Gaussian
distribution of heat flux using a moving heat source with a conical
shape is used for analyzing the temperature profiles. Experimental
and simulated values for weld bead profiles are analyzed for stainless
steel material for different beam power, welding speed and beam
incident angle. The results obtained from the simulation are
compared with those from the experimental data and it is observed
that the results of numerical analysis (FEM) are in good agreement
with experimental results, with an overall percentage of error
estimated to be within ±6%.
Abstract: Data mining (DM) is the process of finding and extracting frequent patterns that can describe the data, or predict unknown or future values. These goals are achieved by using various learning algorithms. Each algorithm may produce a mining result completely different from the others. Some algorithms may find millions of patterns. It is thus the difficult job for data analysts to select appropriate models and interpret the discovered knowledge. In this paper, we describe a framework of an intelligent and complete data mining system called SUT-Miner. Our system is comprised of a full complement of major DM algorithms, pre-DM and post-DM functionalities. It is the post-DM packages that ease the DM deployment for business intelligence applications.
Abstract: Nowadays, several techniques such as; Fuzzy
Inference System (FIS) and Neural Network (NN) are employed for
developing of the predictive models to estimate parameters of water
quality. The main objective of this study is to compare between the
predictive ability of the Adaptive Neuro-Fuzzy Inference System
(ANFIS) model and Artificial Neural Network (ANN) model to
estimate the Biochemical Oxygen Demand (BOD) on data from 11
sampling sites of Saen Saep canal in Bangkok, Thailand. The data is
obtained from the Department of Drainage and Sewerage, Bangkok
Metropolitan Administration, during 2004-2011. The five parameters
of water quality namely Dissolved Oxygen (DO), Chemical Oxygen
Demand (COD), Ammonia Nitrogen (NH3N), Nitrate Nitrogen
(NO3N), and Total Coliform bacteria (T-coliform) are used as the
input of the models. These water quality indices affect the
biochemical oxygen demand. The experimental results indicate that
the ANN model provides a higher correlation coefficient (R=0.73)
and a lower root mean square error (RMSE=4.53) than the
corresponding ANFIS model.
Abstract: Dense slurry flow through centrifugal pump casing
has been modeled using the Eulerian-Eulerian approach with
Eulerian multiphase model in FLUENT 6.1®. First order upwinding
is considered for the discretization of momentum, k and ε terms.
SIMPLE algorithm has been applied for dealing with pressurevelocity
coupling. A mixture property based k-ε turbulence model
has been used for modeling turbulence. Results are validated first
against mesh independence and experiments for a particular set of
operational and geometric conditions. Parametric analysis is then
performed to determine the effect on important physical quantities
viz. solid velocities, solid concentration and solid stresses near the
wall with various operational geometric conditions of the pump.
Abstract: Understanding proteins functions is a major goal in
the post-genomic era. Proteins usually work in context of other
proteins and rarely function alone. Therefore, it is highly relevant to
study the interaction partners of a protein in order to understand its
function. Machine learning techniques have been widely applied to
predict protein-protein interactions. Kernel functions play an
important role for a successful machine learning technique. Choosing
the appropriate kernel function can lead to a better accuracy in a
binary classifier such as the support vector machines. In this paper,
we describe a Bayesian kernel for the support vector machine to
predict protein-protein interactions. The use of Bayesian kernel can
improve the classifier performance by incorporating the probability
characteristic of the available experimental protein-protein
interactions data that were compiled from different sources. In
addition, the probabilistic output from the Bayesian kernel can assist
biologists to conduct more research on the highly predicted
interactions. The results show that the accuracy of the classifier has
been improved using the Bayesian kernel compared to the standard
SVM kernels. These results imply that protein-protein interaction can
be predicted using Bayesian kernel with better accuracy compared to
the standard SVM kernels.
Abstract: System identification is the process of creating
models of dynamic process from input- output signals. The aim of
system identification can be identified as “ to find a model with
adjustable parameters and then to adjust them so that the predicted
output matches the measured output". This paper presents a method
of modeling and simulating with system identification to achieve the
maximum fitness for transformation function. First by using
optimized KLM equivalent circuit for PVDF piezoelectric transducer
and assuming different inputs including: sinuside, step and sum of
sinusides, get the outputs, then by using system identification
toolbox in MATLAB, we estimate the transformation function from
inputs and outputs resulted in last program. Then compare the fitness
of transformation function resulted from using ARX,OE(Output-
Error) and BJ(Box-Jenkins) models in system identification toolbox
and primary transformation function form KLM equivalent circuit.
Abstract: An experimental and numerical study has been conducted to clarify heat transfer characteristics and effectiveness of a cross-flow heat exchanger employing staggered wing-shaped tubes at different angels of attack. The water-side Rew and the air-side Rea were at 5 x 102 and at from 1.8 x 103 to 9.7 x 103, respectively. The tubes arrangements were employed with various angles of attack θ1,2,3 from 0° to 330° at the considered Rea range. Correlation of Nu, St, as well as the heat transfer per unit pumping power (ε) in terms of Rea, design parameters for the studied bundle were presented. The temperature fields around the staggered wing-shaped tubes bundle were predicted by using commercial CFD FLUENT 6.3.26 software package. Results indicated that the heat transfer was increased by increasing the angle of attack from 0° to 45°, while the opposite was true for angles of attack from 135° to 180°. The best thermal performance and hence η of studied bundle was occurred at the lowest Rea and/or zero angle of attack. Comparisons between the experimental and numerical results of the present study and those, previously, obtained for similar available studies showed good agreements.
Abstract: Development of artificial neural network (ANN) for
prediction of aluminum workpieces' surface roughness in ultrasonicvibration
assisted turning (UAT) has been the subject of the present
study. Tool wear as the main cause of surface roughness was also
investigated. ANN was trained through experimental data obtained
on the basis of full factorial design of experiments. Various
influential machining parameters were taken into consideration. It
was illustrated that a multilayer perceptron neural network could
efficiently model the surface roughness as the response of the
network, with an error less than ten percent. The performance of the
trained network was verified by further experiments. The results of
UAT were compared with the results of conventional turning
experiments carried out with similar machining parameters except for
the vibration amplitude whence considerable reduction was observed
in the built-up edge and the surface roughness.
Abstract: In this study a neural network (NN) was proposed to
predict the sorption of binary mixture of copper-cobalt ions into
clinoptilolite as ion-exchanger. The configuration of the
backpropagation neural network giving the smallest mean square
error was three-layer NN with tangent sigmoid transfer function at
hidden layer with 10 neurons, linear transfer function at output layer
and Levenberg-Marquardt backpropagation training algorithm.
Experiments have been carried out in the batch reactor to obtain
equilibrium data of the individual sorption and the mixture of coppercobalt
ions. The obtained modeling results have shown that the used
of neural network has better adjusted the equilibrium data of the
binary system when compared with the conventional sorption
isotherm models.
Abstract: To identify an endothelial cell-specific promoter suitable for vascular-specific targeting, we tested five promoters in vitro--Tie2SE, Tie2LE, ICAM2, Flt-1 and vWF--for promoter activity and specificity in endothelial cells, smooth muscle cells and non-vascular resident cells as well as tissues. These promoters, except for vWF, exhibited good endothelial activity and specificity in vitro. In a syngenic heart transplantation model, the ICAM2 promoter was variably functional in coronary endothelial cells of donor hearts. Thus, the ICAM2, Flt-1, Tie2SE and Tie2LE promoters hold promise for endothelial-specific targeting, but in vitro expression may not predict in vivo expression.
Abstract: The main goal of the present work is to decrease the
computational burden for optimum design of steel frames with
frequency constraints using a new type of neural networks called
Wavelet Neural Network. It is contested to train a suitable neural
network for frequency approximation work as the analysis program.
The combination of wavelet theory and Neural Networks (NN)
has lead to the development of wavelet neural networks.
Wavelet neural networks are feed-forward networks using
wavelet as activation function. Wavelets are mathematical
functions within suitable inner parameters, which help them to
approximate arbitrary functions. WNN was used to predict the
frequency of the structures. In WNN a RAtional function with
Second order Poles (RASP) wavelet was used as a transfer
function. It is shown that the convergence speed was faster
than other neural networks. Also comparisons of WNN with
the embedded Artificial Neural Network (ANN) and with
approximate techniques and also with analytical solutions are
available in the literature.
Abstract: In this paper bi-annual time series data on unemployment rates (from the Labour Force Survey) are expanded to quarterly rates and linked to quarterly unemployment rates (from the Quarterly Labour Force Survey). The resultant linked series and the consumer price index (CPI) series are examined using Johansen’s cointegration approach and vector error correction modeling. The study finds that both the series are integrated of order one and are cointegrated. A statistically significant co-integrating relationship is found to exist between the time series of unemployment rates and the CPI. Given this significant relationship, the study models this relationship using Vector Error Correction Models (VECM), one with a restriction on the deterministic term and the other with no restriction.
A formal statistical confirmation of the existence of a unique linear and lagged relationship between inflation and unemployment for the period between September 2000 and June 2011 is presented. For the given period, the CPI was found to be an unbiased predictor of the unemployment rate. This relationship can be explored further for the development of appropriate forecasting models incorporating other study variables.
Abstract: Prediction of bacterial virulent protein sequences can
give assistance to identification and characterization of novel
virulence-associated factors and discover drug/vaccine targets against
proteins indispensable to pathogenicity. Gene Ontology (GO)
annotation which describes functions of genes and gene products as a
controlled vocabulary of terms has been shown effectively for a
variety of tasks such as gene expression study, GO annotation
prediction, protein subcellular localization, etc. In this study, we
propose a sequence-based method Virulent-GO by mining informative
GO terms as features for predicting bacterial virulent proteins.
Each protein in the datasets used by the existing method
VirulentPred is annotated by using BLAST to obtain its homologies
with known accession numbers for retrieving GO terms. After
investigating various popular classifiers using the same five-fold
cross-validation scheme, Virulent-GO using the single kind of GO
term features with an accuracy of 82.5% is slightly better than
VirulentPred with 81.8% using five kinds of sequence-based features.
For the evaluation of independent test, Virulent-GO also yields better
results (82.0%) than VirulentPred (80.7%). When evaluating single
kind of feature with SVM, the GO term feature performs much well,
compared with each of the five kinds of features.
Abstract: Corporate credit rating prediction using statistical and
artificial intelligence (AI) techniques has been one of the attractive
research topics in the literature. In recent years, multiclass
classification models such as artificial neural network (ANN) or
multiclass support vector machine (MSVM) have become a very
appealing machine learning approaches due to their good
performance. However, most of them have only focused on classifying
samples into nominal categories, thus the unique characteristic of the
credit rating - ordinality - has been seldom considered in their
approaches. This study proposes new types of ANN and MSVM
classifiers, which are named OMANN and OMSVM respectively.
OMANN and OMSVM are designed to extend binary ANN or SVM
classifiers by applying ordinal pairwise partitioning (OPP) strategy.
These models can handle ordinal multiple classes efficiently and
effectively. To validate the usefulness of these two models, we applied
them to the real-world bond rating case. We compared the results of
our models to those of conventional approaches. The experimental
results showed that our proposed models improve classification
accuracy in comparison to typical multiclass classification techniques
with the reduced computation resource.