Abstract: We present a hybrid architecture of recurrent neural
networks (RNNs) inspired by hidden Markov models (HMMs). We
train the hybrid architecture using genetic algorithms to learn and
represent dynamical systems. We train the hybrid architecture on a
set of deterministic finite-state automata strings and observe the
generalization performance of the hybrid architecture when presented
with a new set of strings which were not present in the training data
set. In this way, we show that the hybrid system of HMM and RNN
can learn and represent deterministic finite-state automata. We ran
experiments with different sets of population sizes in the genetic
algorithm; we also ran experiments to find out which weight
initializations were best for training the hybrid architecture. The
results show that the hybrid architecture of recurrent neural networks
inspired by hidden Markov models can train and represent dynamical
systems. The best training and generalization performance is
achieved when the hybrid architecture is initialized with random real
weight values of range -15 to 15.
Abstract: During the last few years, several sheet hydroforming
processes have been introduced. Despite the advantages of these
methods, they have some limitations. Of the processes, the two main
ones are the standard hydroforming and hydromechanical deep
drawing. A new sheet hydroforming die set was proposed that has the
advantages of both processes and eliminates their limitations. In this
method, a polyurethane plate was used as a part of the die-set to
control the blank holder force. This paper outlines the Taguchi
optimization methodology, which is applied to optimize the effective
parameters in forming cylindrical cups by the new die set of sheet
hydroforming process. The process parameters evaluated in this
research are polyurethane hardness, polyurethane thickness, forming
pressure path and polyurethane hole diameter. The design of
experiments based upon L9 orthogonal arrays by Taguchi was used
and analysis of variance (ANOVA) was employed to analyze the
effect of these parameters on the forming pressure. The analysis of
the results showed that the optimal combination for low forming
pressure is harder polyurethane, bigger diameter of polyurethane hole
and thinner polyurethane. Finally, the confirmation test was derived
based on the optimal combination of parameters and it was shown
that the Taguchi method is suitable to examine the optimization
process.
Abstract: Experiments were carried out on the survival and growth of Rasbora daniconius, Puntius ticto and Puntius conchonius. The motivation of the study was to obtain information for growing the fish on a commercial scale for their use as biological control agents against mosquito larvae. The effects of temperature, total hardness, DO, pH and feed on the growth of fish were also investigated. Excessive value of total hardness was found because very rich calcium ion is present in Chitrakoot area. There was significant increases in growth rates of fish as temperature was increased from 280C to 300C. Further increases in temperature up to 320C, did not further affect growth. The positive and highly significant correlations 0.991488, 0.9581 and 0.9935 were found between length and weight of P. ticto, P. conchonius and R. daniconius respectively. The regression was significant at 5% level of probability.
Abstract: Bubble generation was observed using a high-speed
camera in subcooled flow boiling at low void fraction. Constant heat
flux was applied on one side of an upward rectangular channel to
make heated test channel. Water as a working fluid from high
subcooling to near saturation temperature was injected step by step to
investigate bubble behavior during void development. Experiments
were performed in two different pressures condition close to 2bar and
4bar. It was observed that in high subcooling when boiling was
commenced, bubble after nucleation departed its origin and slid
beside heated surface. In an observation window mean release
frequency of bubble fb,mean, nucleation site Ns and mean bubble
volume Vb,mean in each step of experiments were measured to
investigate wall vaporization rate. It was found that in proximity of
PNVG vaporization rate was increased significantly in compare with
condensation rate which remained in low value.
Abstract: Combining classifiers is a useful method for solving
complex problems in machine learning. The ECOC (Error Correcting
Output Codes) method has been widely used for designing combining
classifiers with an emphasis on the diversity of classifiers. In this
paper, in contrast to the standard ECOC approach in which individual
classifiers are chosen homogeneously, classifiers are selected
according to the complexity of the corresponding binary problem. We
use SATIMAGE database (containing 6 classes) for our experiments.
The recognition error rate in our proposed method is %10.37 which
indicates a considerable improvement in comparison with the
conventional ECOC and stack generalization methods.
Abstract: Naive Bayes Nearest Neighbor (NBNN) and its variants, i,e., local NBNN and the NBNN kernels, are local feature-based classifiers that have achieved impressive performance in image classification. By exploiting instance-to-class (I2C) distances (instance means image/video in image/video classification), they avoid quantization errors of local image descriptors in the bag of words (BoW) model. However, the performances of NBNN, local NBNN and the NBNN kernels have not been validated on video analysis. In this paper, we introduce these three classifiers into human action recognition and conduct comprehensive experiments on the benchmark KTH and the realistic HMDB datasets. The results shows that those I2C based classifiers consistently outperform the SVM classifier with the BoW model.
Abstract: Heavy metals have bad effects on environment and
soils and it can uptake by natural HAP .natural Hap is an inexpensive
material that uptake large amounts of various heavy metals like Zn
(II) .Natural HAP (N-HAP), extracted from bovine cortical bone ash,
is a good choice for substitution of commercial HAP. Several
experiments were done to investigate the sorption capacity of Zn (II)
to N-HAP in various particles sizes, temperatures, initial
concentrations, pH and reaction times. In this study, the sorption of
Zinc ions from a Zn solution onto HAP particles with sizes of 1537.6
nm and 47.6 nm at three initial pH values of 4.50, 6.00 and 7.50 was
studied. The results showed that better performance was obtained
through a 47.6 nm particle size and higher pH values. The
experimental data were analyzed using Langmuir, Freundlich, and
Arrhenius equations for equilibrium, kinetic and thermodynamic
studies. The analysis showed a maximum adsorption capacity of NHAP
as being 1.562 mmol/g at a pH of 7.5 and small particle size.
Kinetically, the prepared N-HAP is a feasible sorbent that retains Zn
(II) ions through a favorable and spontaneous sorption process.
Abstract: Laboratory classes in Electrical Engineering are often hampered by safety issues, as students have to work on high voltage lines. One solution is to make use of virtual laboratory simulations, to help students understand the concepts taught in their coursework. In this context, we have conceived and implemented virtual lab experiments in connection with the study of earthing arrangements. In this work, software was developed, which aid student in understanding the working of a residual current device (RCD) in a TT earthing system. Various parameters, such as the earthing resistances, leakage currents and harmonics were included for a TT system with RCD connection.
Abstract: This paper presents a rule-based text- to- speech
(TTS) Synthesis System for Standard Malay, namely SMaTTS. The
proposed system using sinusoidal method and some pre- recorded
wave files in generating speech for the system. The use of phone
database significantly decreases the amount of computer memory
space used, thus making the system very light and embeddable. The
overall system was comprised of two phases the Natural Language
Processing (NLP) that consisted of the high-level processing of text
analysis, phonetic analysis, text normalization and morphophonemic
module. The module was designed specially for SM to overcome
few problems in defining the rules for SM orthography system before
it can be passed to the DSP module. The second phase is the Digital
Signal Processing (DSP) which operated on the low-level process of
the speech waveform generation. A developed an intelligible and
adequately natural sounding formant-based speech synthesis system
with a light and user-friendly Graphical User Interface (GUI) is
introduced. A Standard Malay Language (SM) phoneme set and an
inclusive set of phone database have been constructed carefully for
this phone-based speech synthesizer. By applying the generative
phonology, a comprehensive letter-to-sound (LTS) rules and a
pronunciation lexicon have been invented for SMaTTS. As for the
evaluation tests, a set of Diagnostic Rhyme Test (DRT) word list was
compiled and several experiments have been performed to evaluate
the quality of the synthesized speech by analyzing the Mean Opinion
Score (MOS) obtained. The overall performance of the system as
well as the room for improvements was thoroughly discussed.
Abstract: Word sense disambiguation is one of the most important open problems in natural language processing applications such as information retrieval and machine translation. Many approach strategies can be employed to resolve word ambiguity with a reasonable degree of accuracy. These strategies are: knowledgebased, corpus-based, and hybrid-based. This paper pays attention to the corpus-based strategy that employs an unsupervised learning method for disambiguation. We report our investigation of Latent Semantic Indexing (LSI), an information retrieval technique and unsupervised learning, to the task of Thai noun and verbal word sense disambiguation. The Latent Semantic Indexing has been shown to be efficient and effective for Information Retrieval. For the purposes of this research, we report experiments on two Thai polysemous words, namely /hua4/ and /kep1/ that are used as a representative of Thai nouns and verbs respectively. The results of these experiments demonstrate the effectiveness and indicate the potential of applying vector-based distributional information measures to semantic disambiguation.
Abstract: recurrent neural network (RNN) is an efficient tool for
modeling production control process as well as modeling services. In
this paper one RNN was combined with regression model and were
employed in order to be checked whether the obtained data by the
model in comparison with actual data, are valid for variable process
control chart. Therefore, one maintenance process in workshop of
Esfahan Oil Refining Co. (EORC) was taken for illustration of
models. First, the regression was made for predicting the response
time of process based upon determined factors, and then the error
between actual and predicted response time as output and also the
same factors as input were used in RNN. Finally, according to
predicted data from combined model, it is scrutinized for test values
in statistical process control whether forecasting efficiency is
acceptable. Meanwhile, in training process of RNN, design of
experiments was set so as to optimize the RNN.
Abstract: This paper analyses the performance of a genetic algorithm using a new concept, namely a fractional-order dynamic fitness function, for the synthesis of combinational logic circuits. The experiments reveal superior results in terms of speed and convergence to achieve a solution.
Abstract: This text studies glass bottle intelligent inspector
based machine vision instead of manual inspection. The system
structure is illustrated in detail in this paper. The text presents the
method based on watershed transform methods to segment the
possible defective regions and extract features of bottle wall by rules.
Then wavelet transform are used to exact features of bottle finish
from images. After extracting features, the fuzzy support vector
machine ensemble is putted forward as classifier. For ensuring that
the fuzzy support vector machines have good classification ability,
the GA based ensemble method is used to combining the several
fuzzy support vector machines. The experiments demonstrate that
using this inspector to inspect glass bottles, the accuracy rate may
reach above 97.5%.
Abstract: The use of contour strips of perennial vegetation with
bio-fuel potential can improve surface water quality by reducing
NO3-N and sediment outflow from cropland to surface water-bodies.
It also has economic benefits of producing ethanol. In this study,
The Soil and Water Assessment Tool (SWAT) model was applied to
a watershed in Iowa, USA to examine the effectiveness of contour
strips of switch grass in reducing the NO3-N outflows from crop
fields to rivers or lakes. Numerical experiments were conducted to
identify potential subbasins in the watershed that have high water
quality impact, and to examine the effects of strip size on NO3-N
reduction under various meteorological conditions, i.e. dry, average
and wet years. Useful information was obtained for the evaluation of
economic feasibility of growing switch grass for bio-fuel in contour
strips. The results can assist in cost-benefit analysis and decisionmaking
in best management practices for environmental protection.
Abstract: In this paper, the difference between the Alternating
Direction Method (ADM) and the Non-Splitting Method (NSM) is
investigated, while both methods applied to the simulations for 2-D
multimaterial radiation diffusion issues. Although the ADM have the
same accuracy orders with the NSM on the uniform meshes, the
accuracy of ADM will decrease on the distorted meshes or the
boundary of domain. Numerical experiments are carried out to
confirm the theoretical predication.
Abstract: Recently many research has been conducted to
retrieve pertinent parameters and adequate models for automatic
music genre classification. In this paper, two measures based upon
information theory concepts are investigated for mapping the features
space to decision space. A Gaussian Mixture Model (GMM) is used
as a baseline and reference system. Various strategies are proposed
for training and testing sessions with matched or mismatched
conditions, long training and long testing, long training and short
testing. For all experiments, the file sections used for testing are
never been used during training. With matched conditions all
examined measures yield the best and similar scores (almost 100%).
With mismatched conditions, the proposed measures yield better
scores than the GMM baseline system, especially for the short testing
case. It is also observed that the average discrimination information
measure is most appropriate for music category classifications and on
the other hand the divergence measure is more suitable for music
subcategory classifications.
Abstract: Microbial contamination, most of which are fecal born in drinking water and food industry is a serious threat to humans. Escherichia coli is one of the most common and prevalent among them. We have developed a sensor for rapid and an early detection of contaminants, taking E.coli as a threat indicator organism. The sensor is based on co-polymerizations of aniline and formaldehyde in form of thin film over glass surface using the vacuum deposition technique. The particular doping combination of thin film with Fe-Al and Fe-Cu in different concentrations changes its non conducting properties to p- type semi conductor. This property is exploited to detect the different contaminants, believed to have the different surface charge. It was found through experiments that different microbes at same OD (0.600 at 600 nm) have different conductivity in solution. Also the doping concentration is found to be specific for attracting microbes on the basis of surface charge. This is a simple, cost effective and quick detection method which not only decreases the measurement time but also gives early warnings for highly contaminated samples.
Abstract: 15 strains of oil-destructing microorganisms were
isolated from oil polluted soil of Western Kazakhstan. Strains 2-A
and 41-3 with the highest oil-destructing activities were chosen from
them. It was shown that these strains oxidized n-alkanes very well,
but isoalkanes, isoparaffin, cycloparaffin and heavy aromatic
compounds were destructed very slowly. These both strains were
tested as preparations for bioremediation of oil-polluted soil in model
and field experiments. The degree of utilizing of soil oil by this
preparation was 79-84 % in field experiments.
Abstract: This research is to study the performance of heat
pump dryer for drying of kaffir lime leaves under different media and
to compare the color values and essential oil content of final products
after drying. In the experiments, kaffir lime leaves were dried in the
closed-loop system at drying temperatures of 40, 50 and 60 oC. The
drying media used in this study were hot air, CO2 and N2 gases. The
velocity of drying media in the drying chamber was 0.4 m/s with
bypass ratio of 30%. The initial moisture content of kaffir lime leaves
was approximately 180-190 % d.b. It was dried until down to a final
moisture content of 10% d.b. From the experiments, the results
showed that drying rate, the coefficient of performance (COP) and
specific energy consumption (SEC) depended on drying temperature.
While drying media did not affect on drying rate. The time for kaffir
lime leaves drying at 40, 50 and 60 oC was 10, 5 and 3 hours,
respectively. The performance of the heat pump system decreased
with drying temperature in the range of 2.20-3.51. In the aspect of
final product color, the greenness and overall color had a great
change under drying temperature at 60 oC rather than drying at 40
and 50 oC. When compared among drying media, the greenness and
overall color of product dried with hot air at 60 oC had a great change
rather than dried with CO2 and N2.
Abstract: Summarizing skills have been introduced to English
syllabus in secondary school in Malaysia to evaluate student-s comprehension for a given text where it requires students to employ several strategies to produce the summary. This paper reports on our effort to develop a computer-based summarization assessment system
that detects the strategies used by the students in producing their
summaries. Sentence decomposition of expert-written summaries is
used to analyze how experts produce their summary sentences. From
the analysis, we identified seven summarizing strategies and their
rules which are then transformed into a set of heuristic rules on how
to determine the summarizing strategies. We developed an algorithm
based on the heuristic rules and performed some experiments to
evaluate and support the technique proposed.