Abstract: Discrimination between different classes of environmental
sounds is the goal of our work. The use of a sound recognition
system can offer concrete potentialities for surveillance and
security applications. The first paper contribution to this research
field is represented by a thorough investigation of the applicability
of state-of-the-art audio features in the domain of environmental
sound recognition. Additionally, a set of novel features obtained by
combining the basic parameters is introduced. The quality of the
features investigated is evaluated by a HMM-based classifier to which
a great interest was done. In fact, we propose to use a Multi-Style
training system based on HMMs: one recognizer is trained on a
database including different levels of background noises and is used
as a universal recognizer for every environment. In order to enhance
the system robustness by reducing the environmental variability, we
explore different adaptation algorithms including Maximum Likelihood
Linear Regression (MLLR), Maximum A Posteriori (MAP)
and the MAP/MLLR algorithm that combines MAP and MLLR.
Experimental evaluation shows that a rather good recognition rate
can be reached, even under important noise degradation conditions
when the system is fed by the convenient set of features.
Abstract: Today, money laundering (ML) poses a serious threat
not only to financial institutions but also to the nation. This criminal
activity is becoming more and more sophisticated and seems to have
moved from the cliché of drug trafficking to financing terrorism and
surely not forgetting personal gain. Most international financial
institutions have been implementing anti-money laundering solutions
(AML) to fight investment fraud. However, traditional investigative
techniques consume numerous man-hours. Recently, data mining
approaches have been developed and are considered as well-suited
techniques for detecting ML activities. Within the scope of a
collaboration project for the purpose of developing a new solution for
the AML Units in an international investment bank, we proposed a
data mining-based solution for AML. In this paper, we present a
heuristics approach to improve the performance for this solution. We
also show some preliminary results associated with this method on
analysing transaction datasets.
Abstract: This is a comprehensive large-sample study of Australian earnings management. Using a sample of 4,844 firm-year observations across nine Australia industries from 2000 to 2006, we find substantial corporate earnings management activity across several Australian industries. We document strong evidence of size and return on assets being primary determinants of earnings management in Australia. The effects of size and return on assets are also found to be dominant in both income-increasing and incomedecreasing earnings manipulation. We also document that that periphery sector firms are more likely to involve larger magnitude of earnings management than firms in the core sector.
Abstract: This paper presents a new method for estimating the mean curve of impulse voltage waveforms that are recorded during impulse tests. In practice, these waveforms are distorted by noise, oscillations and overshoot. The problem is formulated as an estimation problem. Estimation of the current signal parameters is achieved using a fast and accurate technique. The method is based on discrete dynamic filtering algorithm (DDF). The main advantage of the proposed technique is its ability in producing the estimates in a very short time and at a very high degree of accuracy. The algorithm uses sets of digital samples of the recorded impulse waveform. The proposed technique has been tested using simulated data of practical waveforms. Effects of number of samples and data window size are studied. Results are reported and discussed.
Abstract: This paper aims to study decomposition behavior in
pyrolytic environment of four lignocellulosic biomass (oil palm shell,
oil palm frond, rice husk and paddy straw), and two commercial
components of biomass (pure cellulose and lignin), performed in a
thermogravimetry analyzer (TGA). The unit which consists of a
microbalance and a furnace flowed with 100 cc (STP) min-1 Nitrogen,
N2 as inert. Heating rate was set at 20⁰C min-1 and temperature
started from 50 to 900⁰C. Hydrogen gas production during the
pyrolysis was observed using Agilent Gas Chromatography Analyzer
7890A. Oil palm shell, oil palm frond, paddy straw and rice husk
were found to be reactive enough in a pyrolytic environment of up to
900°C since pyrolysis of these biomass starts at temperature as low as
200°C and maximum value of weight loss is achieved at about
500°C. Since there was not much different in the cellulose,
hemicelluloses and lignin fractions between oil palm shell, oil palm
frond, paddy straw and rice husk, the T-50 and R-50 values obtained
are almost similar. H2 productions started rapidly at this temperature
as well due to the decompositions of biomass inside the TGA.
Biomass with more lignin content such as oil palm shell was found to
have longer duration of H2 production compared to materials of high
cellulose and hemicelluloses contents.
Abstract: Leave of absence is important in maintaining a good
status of human resource quality. Allowing the employees temporarily
free from the routine assignments can vitalize the workers- morality
and productivity. This is particularly critical to secure a satisfactory
service quality for healthcare professionals of which were typically
featured with labor intensive and complicated works to perform. As
one of the veteran hospitals that were found and operated by the
Veteran Department of Taiwan, the nursing staff of the case hospital
was squeezed to an extreme minimum level under the pressure of a
tight budgeting. Leave of absence on schedule became extremely
difficult, especially for the intensive care units (ICU), in which
required close monitoring over the cared patients, and that had more
easily driven the ICU nurses nervous. Even worse, the deferred leaves
were more than 10 days at any time in the ICU because of a fluctuating
occupancy. As a result, these had brought a bad setback to this
particular nursing team, and consequently defeated the job
performance and service quality. To solve this problem and
accordingly to strengthen their morality, a project team was organized
across different departments specific for this. Sufficient information
regarding jobs and positions requirements, labor resources, and actual
working hours in detail were collected and analyzed in the team
meetings. Several alternatives were finalized. These included job
rotating, job combination, leave on impromptu and cross-departmental
redeployment. Consequently, the deferred leave days sharply reduced
70% to a level of 3 or less days. This improvement had not only
provided good shelter for the ICU nurses that improved their job
performance and patient safety but also encouraged the nurses active
participating of a project and learned the skills of solving problems
with colleagues.
Abstract: This paper presents the prediction of kidney
dysfunction using different neural network (NN) approaches. Self
organization Maps (SOM), Probabilistic Neural Network (PNN) and
Multi Layer Perceptron Neural Network (MLPNN) trained with Back
Propagation Algorithm (BPA) are used in this study. Six hundred and
sixty three sets of analytical laboratory tests have been collected from
one of the private clinical laboratories in Baghdad. For each subject,
Serum urea and Serum creatinin levels have been analyzed and tested
by using clinical laboratory measurements. The collected urea and
cretinine levels are then used as inputs to the three NN models in
which the training process is done by different neural approaches.
SOM which is a class of unsupervised network whereas PNN and
BPNN are considered as class of supervised networks. These
networks are used as a classifier to predict whether kidney is normal
or it will have a dysfunction. The accuracy of prediction, sensitivity
and specificity were found for each type of the proposed networks
.We conclude that PNN gives faster and more accurate prediction of
kidney dysfunction and it works as promising tool for predicting of
routine kidney dysfunction from the clinical laboratory data.
Abstract: In this paper, a new recursive strategy is proposed for determining $\frac{(n-1)!}{2}$ of $n$th order diagrams. The generalization of $n$th diagram for cross multiplication method were proposed by Pavlovic and Bankier but the specific rule of determining $\frac{(n-1)!}{2}$ of the $n$th order diagrams for square matrix is yet to be discovered. Thus using combinatorial approach, $\frac{(n-1)!}{2}$ of the $n$th order diagrams will be presented as $\frac{(n-1)!}{2}$ starter sets. These starter sets will be generated based on exchanging one element. The advantages of this new strategy are the discarding process was eliminated and the sign of starter set is alternated to each others.
Abstract: The Maximum Weighted Independent Set (MWIS)
problem is a classic graph optimization NP-hard problem. Given an
undirected graph G = (V, E) and weighting function defined on the
vertex set, the MWIS problem is to find a vertex set S V whose total
weight is maximum subject to no two vertices in S are adjacent. This
paper presents a novel approach to approximate the MWIS of a graph
using minimum weighted vertex cover of the graph. Computational
experiments are designed and conducted to study the performance
of our proposed algorithm. Extensive simulation results show that
the proposed algorithm can yield better solutions than other existing
algorithms found in the literature for solving the MWIS.
Abstract: The physical methods for RNA secondary structure prediction are time consuming and expensive, thus methods for computational prediction will be a proper alternative. Various algorithms have been used for RNA structure prediction including dynamic programming and metaheuristic algorithms. Musician's behaviorinspired harmony search is a recently developed metaheuristic algorithm which has been successful in a wide variety of complex optimization problems. This paper proposes a harmony search algorithm (HSRNAFold) to find RNA secondary structure with minimum free energy and similar to the native structure. HSRNAFold is compared with dynamic programming benchmark mfold and metaheuristic algorithms (RnaPredict, SetPSO and HelixPSO). The results showed that HSRNAFold is comparable to mfold and better than metaheuristics in finding the minimum free energies and the number of correct base pairs.
Abstract: In this paper, we consider nested sliding mode control of SISO nonlinear systems, perturbed by bounded matched and unmatched uncertainties. The systems are assumed to be in strict-feedback form. A step wise procedure is introduced to obtain the controller. In each step, a continuous sliding mode controller is designed as virtual control law. Then the next step sliding surface is defined by using this virtual controller. These sliding surfaces are selected as nonlinear static functions of the system states. Finally in the last step, smooth static state feedback control law is determined such that the output reaches the desired set-point while the system is forced arbitrary close to the intersection of sliding surfaces and the states remain bounded.
Abstract: In this paper we discuss a set of guidelines which
could be adapted when designing an audio user interface for the
visually impaired. It is based on an audio environment that is
focused on audio positioning. Unlike current applications which only
interpret Graphical User Interface (GUI) for the visually impaired,
this particular audio environment bypasses GUI to provide a direct
auditory output. It presents the capability of two dimensional (2D)
navigation on audio interfaces. This paper highlights the significance
of a 2D audio environment with spatial information in the context
of the visually impaired. A thorough usability study has been conducted
to prove the applicability of proposed design guidelines for
these auditory interfaces. While proving these guidelines, previously
unearthed design aspects have been revealed in this study.
Abstract: This paper presents a new approach for the prob-ability density function estimation using the Support Vector Ma-chines (SVM) and the Expectation Maximization (EM) algorithms.In the proposed approach, an advanced algorithm for the SVM den-sity estimation which incorporates the Mean Field theory in the learning process is used. Instead of using ad-hoc values for the para-meters of the kernel function which is used by the SVM algorithm,the proposed approach uses the EM algorithm for an automatic optimization of the kernel. Experimental evaluation using simulated data set shows encouraging results.
Abstract: Offset Double-Disk Opener (DDO) is a popular
furrow opener in conservation tillage. It has some limitations such as
negative suction to penetrate in the soil, hair pinning and mixing seed
and fertilizer in the slot. Because of importance of separation of seed
and fertilizer in the slot, by adding two horizontal mini disks to DDO
a modified opener was made (MDO) which placed the fertilizer
between and under two rows of seed. To consider performance of
novel opener an indoor comparison test between DDO and MDO was
performed at soil bin. The experiment was conducted with three
working speeds (3, 6 and 8 km h-1), two bulk densities of soil (1.1
and 1.4 Mg m-3) and two levels of residues (1 and 2 ton ha-1). The
experimental design consisted in a (3×2×2) complete randomized
factorial with three replicates for each test. Moisture of seed furrow,
separation of seed and fertilizer, hair pinning and resultant forces
acting on the openers were used as assessing indexes. There was no
significant difference between soil moisture content in slots created
by DDO and MDO at 0-4 cm depth, but at 4-8 cm the in the slot
created by MDO moisture content was higher about 9%. Horizontal
force for both openers increased with increasing speed and soil bulk
density. Vertical force for DDO was negative so it needed additional
weight for penetrating in the soil, but vertical force for MDO was
positive and, which can solve the challenge of penetration in the soil
in DDO. In soft soil with heavy residues some trash was pushed by
DDO into seed furrow (hair pinning) but at MDO seed were placed at
clean groove. Lateral and vertical separation of seed and fertilizer
was performed effectively by MDO (4.5 and 5 cm, respectively)
while DDO put seed and fertilizer close to each other. Overall, the
Modified Offset Double-disks (MDO) had better performance. So by
adapting this opener with no-tillage drillers it would possible to have
higher yield in conservation tillage where the most appropriate
opener is disk type.
Abstract: The Neuro-Fuzzy hybridization scheme has become
of research interest in pattern classification over the past decade. The
present paper proposes a novel Modified Adaptive Fuzzy Inference
Engine (MAFIE) for pattern classification. A modified Apriori
algorithm technique is utilized to reduce a minimal set of decision
rules based on input output data sets. A TSK type fuzzy inference
system is constructed by the automatic generation of membership
functions and rules by the fuzzy c-means clustering and Apriori
algorithm technique, respectively. The generated adaptive fuzzy
inference engine is adjusted by the least-squares fit and a conjugate
gradient descent algorithm towards better performance with a
minimal set of rules. The proposed MAFIE is able to reduce the
number of rules which increases exponentially when more input
variables are involved. The performance of the proposed MAFIE is
compared with other existing applications of pattern classification
schemes using Fisher-s Iris and Wisconsin breast cancer data sets and
shown to be very competitive.
Abstract: This paper explores the scalability issues associated
with solving the Named Entity Recognition (NER) problem using
Support Vector Machines (SVM) and high-dimensional features. The
performance results of a set of experiments conducted using binary
and multi-class SVM with increasing training data sizes are
examined. The NER domain chosen for these experiments is the
biomedical publications domain, especially selected due to its
importance and inherent challenges. A simple machine learning
approach is used that eliminates prior language knowledge such as
part-of-speech or noun phrase tagging thereby allowing for its
applicability across languages. No domain-specific knowledge is
included. The accuracy measures achieved are comparable to those
obtained using more complex approaches, which constitutes a
motivation to investigate ways to improve the scalability of multiclass
SVM in order to make the solution more practical and useable.
Improving training time of multi-class SVM would make support
vector machines a more viable and practical machine learning
solution for real-world problems with large datasets. An initial
prototype results in great improvement of the training time at the
expense of memory requirements.
Abstract: Regression testing is a maintenance activity applied to
modified software to provide confidence that the changed parts are
correct and that the unchanged parts have not been adversely affected
by the modifications. Regression test selection techniques reduce the
cost of regression testing, by selecting a subset of an existing test
suite to use in retesting modified programs. This paper presents the
first general regression-test-selection technique, which based on code
and allows selecting test cases for any programs written in any
programming language. Then it handles incomplete program. We
also describe RTSDiff, a regression-test-selection system that
implements the proposed technique. The results of the empirical
studied that performed in four programming languages java, C#, Cµ
and Visual basic show that the efficiency and effective in reducing
the size of test suit.
Abstract: The effect of a time delay on the transmission on
dengue fever is studied. The time delay is due to the presence of an
incubation period for the dengue virus to develop in the mosquito
before the mosquito becomes infectious. The conditions for the
existence of a Hopf bifurcation to limit cycle behavior are
established. The conditions are different from the usual one and they
are based on whether a particular third degree polynomial has
positive real roots. A theorem for determining whether for a given
set of parameter values, a critical delay time exist is given. It is
found that for a set of realistic values of the parameters in the model,
a Hopf bifurcation can not occur. For a set of unrealistic values of
some of the parameters, it is shown that a Hopf bifurcation can occur.
Numerical solutions using this last set show the trajectory of two of
the variables making a transition from a spiraling orbit to a limit
cycle orbit.
Abstract: A Decision Support System/Expert System for stock
portfolio selection presented where at first step, both technical and
fundamental data used to estimate technical and fundamental return
and risk (1st phase); Then, the estimated values are aggregated with
the investor preferences (2nd phase) to produce convenient stock
portfolio.
In the 1st phase, there are two expert systems, each of which is
responsible for technical or fundamental estimation. In the technical
expert system, for each stock, twenty seven candidates are identified
and with using rough sets-based clustering method (RC) the effective
variables have been selected. Next, for each stock two fuzzy rulebases
are developed with fuzzy C-Mean method and Takai-Sugeno-
Kang (TSK) approach; one for return estimation and the other for
risk. Thereafter, the parameters of the rule-bases are tuned with backpropagation
method. In parallel, for fundamental expert systems,
fuzzy rule-bases have been identified in the form of “IF-THEN" rules
through brainstorming with the stock market experts and the input
data have been derived from financial statements; as a result two
fuzzy rule-bases have been generated for all the stocks, one for return
and the other for risk.
In the 2nd phase, user preferences represented by four criteria and
are obtained by questionnaire. Using an expert system, four estimated
values of return and risk have been aggregated with the respective
values of user preference. At last, a fuzzy rule base having four rules,
treats these values and produce a ranking score for each stock which
will lead to a satisfactory portfolio for the user.
The stocks of six manufacturing companies and the period of
2003-2006 selected for data gathering.
Abstract: Liquid-liquid extraction is a process using two immiscible
liquids to extract compounds from one phase without high
temperature requirement. Mostly, the technical implementation of
this process is carried out in mixer-settlers or extraction columns. In
real chemical processes, chemicals may have high viscosity and
contain impurities. These impurities may change the settling behavior
of the process without measurably changing the physical properties
of the phases. In the current study, the settling behavior and the affected
parameters in a high-viscosity system were observed. Batchsettling
experiments were performed to experimentally quantify the
settling behavior and the mixer-settler model of Henschke [1] was
used to evaluate the behavior of the toluene + water system. The
viscosity of the system was increased by adding polyethylene glycol
4000 to the aqueous phase. NaCl and Na2SO4 were used to study the
influence of electrolytes. The results from this study show that increasing
the viscosity of water has a higher influence on the settling
behavior in comparison to the effects of the electrolytes. It can be
seen from the experiments that at high salt concentrations, there was
no effect on the settling behavior.