Abstract: In this paper we use exponential particle swarm
optimization (EPSO) to cluster data. Then we compare between
(EPSO) clustering algorithm which depends on exponential variation
for the inertia weight and particle swarm optimization (PSO)
clustering algorithm which depends on linear inertia weight. This
comparison is evaluated on five data sets. The experimental results
show that EPSO clustering algorithm increases the possibility to find
the optimal positions as it decrease the number of failure. Also show
that (EPSO) clustering algorithm has a smaller quantization error
than (PSO) clustering algorithm, i.e. (EPSO) clustering algorithm
more accurate than (PSO) clustering algorithm.
Abstract: The aerodynamic noise radiation from a side view mirror (SVM) in the high-speed airflow is calculated by the combination of unsteady incompressible fluid flow analysis and acoustic analysis. The transient flow past the generic SVM is simulated with variable turbulence model, namely DES Detached Eddy Simulation and LES (Large Eddy Simulation). Detailed velocity vectors and contour plots of the time-varying velocity and pressure fields are presented along cut planes in the flow-field. Mean and transient pressure are also monitored at several points in the flow field and compared to corresponding experimentally data published in literature. The acoustic predictions made using the Ffowcs-Williams-Hawkins acoustic analogy (FW-H) and the boundary element (BEM).
Abstract: This study examined the effects of eight weeks of
whole-body vibration training (WBVT) on vertical and decuple jump
performance in handball athletes. Sixteen collegiate Level I handball
athletes volunteered for this study. They were divided equally as
control group and experimental group (EG). During the period of the
study, all athletes underwent the same handball specific training, but
the EG received additional WBVT (amplitude: 2 mm, frequency: 20 -
40 Hz) three time per week for eight consecutive weeks. The vertical
jump performance was evaluated according to the maximum height of
squat jump (SJ) and countermovement jump (CMJ). Single factor
ANCOVA was used to examine the differences in each parameter
between the groups after training with the pretest values as a covariate.
The statistic significance was set at p < .05. After 8 weeks WBVT, the
EG had significantly improved the maximal height of SJ (40.92 ± 2.96
cm vs. 48.40 ± 4.70 cm, F = 5.14, p < .05) and the maximal height
CMJ (47.25 ± 7.48 cm vs. 52.20 ± 6.25 cm, F = 5.31, p < .05). 8 weeks
of additional WBVT could improve the vertical and decuple jump
performance in handball athletes. Enhanced motor unit
synchronization and firing rates, facilitated muscular contraction
stretch-shortening cycle, and improved lower extremity
neuromuscular coordination could account for these enhancements.
Abstract: Although backpropagation ANNs generally predict
better than decision trees do for pattern classification problems, they
are often regarded as black boxes, i.e., their predictions cannot be
explained as those of decision trees. In many applications, it is
desirable to extract knowledge from trained ANNs for the users to
gain a better understanding of how the networks solve the problems.
A new rule extraction algorithm, called rule extraction from artificial
neural networks (REANN) is proposed and implemented to extract
symbolic rules from ANNs. A standard three-layer feedforward ANN
is the basis of the algorithm. A four-phase training algorithm is
proposed for backpropagation learning. Explicitness of the extracted
rules is supported by comparing them to the symbolic rules generated
by other methods. Extracted rules are comparable with other methods
in terms of number of rules, average number of conditions for a rule,
and predictive accuracy. Extensive experimental studies on several
benchmarks classification problems, such as breast cancer, iris,
diabetes, and season classification problems, demonstrate the
effectiveness of the proposed approach with good generalization
ability.
Abstract: The feature extraction method(s) used to recognize
hand-printed characters play an important role in ICR applications.
In order to achieve high recognition rate for a recognition system, the
choice of a feature that suits for the given script is certainly an
important task. Even if a new feature required to be designed for a
given script, it is essential to know the recognition ability of the
existing features for that script. Devanagari script is being used in
various Indian languages besides Hindi the mother tongue of majority
of Indians. This research examines a variety of feature extraction
approaches, which have been used in various ICR/OCR applications,
in context to Devanagari hand-printed script. The study is conducted
theoretically and experimentally on more that 10 feature extraction
methods. The various feature extraction methods have been evaluated
on Devanagari hand-printed database comprising more than 25000
characters belonging to 43 alphabets. The recognition ability of the
features have been evaluated using three classifiers i.e. k-NN, MLP
and SVM.
Abstract: This paper reports the results of an experimental work
conducted to investigate the effect of curing conditions on the
compressive strength of self-compacting geopolymer concrete
prepared by using fly ash as base material and combination of sodium
hydroxide and sodium silicate as alkaline activator. The experiments
were conducted by varying the curing time and curing temperature in
the range of 24-96 hours and 60-90°C respectively. The essential
workability properties of freshly prepared Self-compacting
Geopolymer concrete such as filling ability, passing ability and
segregation resistance were evaluated by using Slump flow,
V-funnel, L-box and J-ring test methods. The fundamental
requirements of high flowability and resistance to segregation as
specified by guidelines on Self-compacting Concrete by EFNARC
were satisfied. Test results indicate that longer curing time and curing
the concrete specimens at higher temperatures result in higher
compressive strength. There was increase in compressive strength
with the increase in curing time; however increase in compressive
strength after 48 hours was not significant. Concrete specimens cured
at 70°C produced the highest compressive strength as compared to
specimens cured at 60°C, 80°C and 90°C.
Abstract: Ensemble learning algorithms such as AdaBoost and
Bagging have been in active research and shown improvements in
classification results for several benchmarking data sets with mainly
decision trees as their base classifiers. In this paper we experiment to
apply these Meta learning techniques with classifiers such as random
forests, neural networks and support vector machines. The data sets
are from MAGIC, a Cherenkov telescope experiment. The task is to
classify gamma signals from overwhelmingly hadron and muon
signals representing a rare class classification problem. We compare
the individual classifiers with their ensemble counterparts and
discuss the results. WEKA a wonderful tool for machine learning has
been used for making the experiments.
Abstract: Injection forging is a Nett-shape manufacturing
process in which one or two punches move axially causing a radial
flow into a die cavity in a form which is prescribed by the exitgeometry,
such as pulley, flanges, gears and splines on a shaft. This
paper presents an experimental and numerical study of the injection
forging of splines in terms of load requirement and material flow.
Three dimensional finite element analyses are used to investigate the
effect of some important parameters in this process. The experiment
has been carried out using solid commercial lead billets with two
different billet diameters and four different dies.
Abstract: Fair share is one of the scheduling objectives supported on many production systems. However, fair share has been shown to cause performance problems for some users, especially the users with difficult jobs. This work is focusing on extending goaloriented parallel computer job scheduling policies to cover the fair share objective. Goal-oriented parallel computer job scheduling policies have been shown to achieve good scheduling performances when conflicting objectives are required. Goal-oriented policies achieve such good performance by using anytime combinatorial search techniques to find a good compromised schedule within a time limit. The experimental results show that the proposed goal-oriented parallel computer job scheduling policy (namely Tradeofffs( Tw:avgX)) achieves good scheduling performances and also provides good fair share performance.
Abstract: The dental composites are preferably used as filling
materials due to their esthetic appearances. Nevertheless one of the
major problems, during the application of the dental composites, is
shape change named as “polymerisation shrinkage" affecting clinical
success of the dental restoration while photo-polymerisation.
Polymerisation shrinkage of composites arises basically from the
formation of a polymer due to the monomer transformation which
composes of an organic matrix phase. It was sought, throughout this
study, to detect and evaluate the structural polymerisation shrinkage
of prepared dental composites in order to optimize the effects of
various fillers included in hydroxyapatite (HA)-reinforced dental
composites and hence to find a means to modify the properties of
these dental composites prepared with defined parameters. As a
result, the shrinkage values of the experimental dental composites
were decreased by increasing the filler content of composites and the
composition of different fillers used had effect on the shrinkage of
the prepared composite systems.
Abstract: This paper presents the applicability of artificial
neural networks for 24 hour ahead solar power generation forecasting
of a 20 kW photovoltaic system, the developed forecasting is suitable
for a reliable Microgrid energy management. In total four neural
networks were proposed, namely: multi-layred perceptron, radial
basis function, recurrent and a neural network ensemble consisting in
ensemble of bagged networks. Forecasting reliability of the proposed
neural networks was carried out in terms forecasting error
performance basing on statistical and graphical methods. The
experimental results showed that all the proposed networks achieved
an acceptable forecasting accuracy. In term of comparison the neural
network ensemble gives the highest precision forecasting comparing
to the conventional networks. In fact, each network of the ensemble
over-fits to some extent and leads to a diversity which enhances the
noise tolerance and the forecasting generalization performance
comparing to the conventional networks.
Abstract: Simultaneous effects of temperature, immersion time, salt concentration, sucrose concentration, pressure and convective dryer temperature on the combined osmotic dehydration - convective drying of edible button mushrooms were investigated. Experiments were designed according to Central Composite Design with six factors each at five different levels. Response Surface Methodology (RSM) was used to determine the optimum processing conditions that yield maximum water loss and rehydration ratio and minimum solid gain and shrinkage in osmotic-convective drying of edible button mushrooms. Applying surfaces profiler and contour plots optimum operation conditions were found to be temperature of 39 °C, immersion time of 164 min, salt concentration of 14%, sucrose concentration of 53%, pressure of 600 mbar and drying temperature of 40 °C. At these optimum conditions, water loss, solid gain, rehydration ratio and shrinkage were found to be 63.38 (g/100 g initial sample), 3.17 (g/100 g initial sample), 2.26 and 7.15%, respectively.
Abstract: This paper presents preliminary results regarding system-level power awareness for FPGA implementations in wireless sensor networks. Re-configurability of field programmable gate arrays (FPGA) allows for significant flexibility in its applications to embedded systems. However, high power consumption in FPGA becomes a significant factor in design considerations. We present several ideas and their experimental verifications on how to optimize power consumption at high level of designing process while maintaining the same energy per operation (low-level methods can be used additionally). This paper demonstrates that it is possible to estimate feasible power consumption savings even at the high level of designing process. It is envisaged that our results can be also applied to other embedded systems applications, not limited to FPGA-based.
Abstract: Water leakage is a serious problem in the maintenance of a waterworks facility. Monitoring the water flow rate is one way to locate leakage. However, conventional flowmeters such as the wet-type flowmeter and the clamp-on type ultrasonic flowmeter require additional construction for their installation and are therefore quite expensive. This paper proposes a novel estimation system for the flow rate in a water pipeline, which employs a vibration sensor. This assembly can be attached to any water pipeline without the need for additional high-cost construction. The vibration sensor is designed based on a condenser microphone. This sensor detects vibration caused by water flowing through a pipeline. It is possible to estimate the water flow rate by measuring the amplitude of the output signal from the vibration sensor. We confirmed the validity of the proposed sensing system experimentally.
Abstract: The modeling of inelastic behavior of plastic materials requires measurements providing information on material response to different multiaxial loading conditions. Different triaxiality conditions and values of Lode parameters have to be
covered for complex description of the material plastic behavior.
Samples geometries providing material plastic behavoiur over the range of interest are proposed with the use of FEM analysis. Round samples with 3 different notches and smooth surface are used
together with butterfly type of samples tested at angle ranging for 0 to
90°. Identification of ductile damage parameters is carried out on
the basis of obtained experimental data for austenitic stainless steel.
The obtained material plastic damage parameters are subsequently applied to FEM simulation of notched CT normally samples used for
fracture mechanics testing and results from the simulation are
compared with real tests.
Abstract: Detection of squirrel cage induction motor (SCIM) broken bars has long been an important but difficult job in the detection area of motor faults. Early detection of this abnormality in the motor would help to avoid costly breakdowns. A new detection method based on particle swarm optimization (PSO) is presented in this paper. Stator current in an induction motor will be measured and characteristic frequency components of faylted rotor will be detected by minimizing a fitness function using pso. Supply frequency and side band frequencies and their amplitudes can be estimated by the proposed method. The proposed method is applied to a faulty motor with one and two broken bars in different loading condition. Experimental results prove that the proposed method is effective and applicable.
Abstract: Nowadays, hand vein recognition has attracted more attentions in identification biometrics systems. Generally, hand vein image is acquired with low contrast and irregular illumination. Accordingly, if you have a good preprocessing of hand vein image, we can easy extracted the feature extraction even with simple binarization. In this paper, a proposed approach is processed to improve the quality of hand vein image. First, a brief survey on existing methods of enhancement is investigated. Then a Radon Like features method is applied to preprocessing hand vein image. Finally, experiments results show that the proposed method give the better effective and reliable in improving hand vein images.
Abstract: Excilamps are new UV sources with great potential
for application in wastewater treatment. In the present work, a XeBr
excilamp emitting radiation at 283 nm has been used for the
photodegradation of 4-chlorophenol within a range of concentrations
from 50 to 500 mg L-1. Total removal of 4-chlorophenol was
achieved for all concentrations assayed. The two main photoproduct
intermediates formed along the photodegradation process,
benzoquinone and hydroquinone, although not being completely
removed, remain at very low residual concentrations. Such
concentrations are insignificant compared to the 4-chlorophenol
initial ones and non-toxic. In order to simulate the process and scaleup,
a kinetic model has been developed and validated from the
experimental data.
Abstract: In this paper we introduce a novel kernel classifier
based on a iterative shrinkage algorithm developed for compressive
sensing. We have adopted Bregman iteration with soft and hard
shrinkage functions and generalized hinge loss for solving l1 norm
minimization problem for classification. Our experimental results
with face recognition and digit classification using SVM as the
benchmark have shown that our method has a close error rate
compared to SVM but do not perform better than SVM. We have
found that the soft shrinkage method give more accuracy and in some
situations more sparseness than hard shrinkage methods.
Abstract: In this paper, we present a novel objective nonreference performance assessment algorithm for image fusion. It takes into account local measurements to estimate how well the important information in the source images is represented by the fused image. The metric is based on the Universal Image Quality Index and uses the similarity between blocks of pixels in the input images and the fused image as the weighting factors for the metrics. Experimental results confirm that the values of the proposed metrics correlate well with the subjective quality of the fused images, giving a significant improvement over standard measures based on mean squared error and mutual information.