Abstract: This paper investigates how the use of machine learning techniques can significantly predict the three major dimensions of learner-s emotions (pleasure, arousal and dominance) from brainwaves. This study has adopted an experimentation in which participants were exposed to a set of pictures from the International Affective Picture System (IAPS) while their electrical brain activity was recorded with an electroencephalogram (EEG). The pictures were already rated in a previous study via the affective rating system Self-Assessment Manikin (SAM) to assess the three dimensions of pleasure, arousal, and dominance. For each picture, we took the mean of these values for all subjects used in this previous study and associated them to the recorded brainwaves of the participants in our study. Correlation and regression analyses confirmed the hypothesis that brainwave measures could significantly predict emotional dimensions. This can be very useful in the case of impassive, taciturn or disabled learners. Standard classification techniques were used to assess the reliability of the automatic detection of learners- three major dimensions from the brainwaves. We discuss the results and the pertinence of such a method to assess learner-s emotions and integrate it into a brainwavesensing Intelligent Tutoring System.
Abstract: In this study, a high accuracy protein-protein interaction
prediction method is developed. The importance of the proposed
method is that it only uses sequence information of proteins while
predicting interaction. The method extracts phylogenetic profiles of
proteins by using their sequence information. Combining the phylogenetic
profiles of two proteins by checking existence of homologs
in different species and fitting this combined profile into a statistical
model, it is possible to make predictions about the interaction status
of two proteins.
For this purpose, we apply a collection of pattern recognition
techniques on the dataset of combined phylogenetic profiles of protein
pairs. Support Vector Machines, Feature Extraction using ReliefF,
Naive Bayes Classification, K-Nearest Neighborhood Classification,
Decision Trees, and Random Forest Classification are the methods
we applied for finding the classification method that best predicts
the interaction status of protein pairs. Random Forest Classification
outperformed all other methods with a prediction accuracy of 76.93%
Abstract: Three-phase induction machines are today a standard
for industrial electrical drives. Cost, reliability, robustness and maintenance free operation are among the reasons these machines are
replacing dc drive systems. The development of power electronics
and signal processing systems has eliminated one of the greatest
disadvantages of such ac systems, which is the issue of control. With
modern techniques of field oriented vector control, the task of
variable speed control of induction machines is no longer a
disadvantage. The need to increase system performance, particularly
when facing limits on the power ratings of power supplies and
semiconductors, motivates the use of phase number other than three,
In this paper a novel scheme of connecting two, three phase
induction motors in parallel fed by two inverters; viz. VSI and CSI
and their vector control is presented.
Abstract: The most common cause of power transformer failures
is mechanical defect brought about by excessive vibration, which is
formed by the combination of multiples of a frequency of 120 Hz. In
this paper, the types of mechanical exciting forces applied to the
power transformer were classified, and the mechanical damage
mechanism of the power transformer was identified using the
vibration transfer route to the machine or structure. The general
effects of 120 Hz-vibration on the enclosure, bushing, Buchholz
relay, pressure release valve and tap changer of the transformer were
also examined.
Abstract: A virtualized and virtual approach is presented on
academically preparing students to successfully engage at a strategic
perspective to understand those concerns and measures that are both
structured and not structured in the area of cyber security and
information assurance. The Master of Science in Cyber Security and
Information Assurance (MSCSIA) is a professional degree for those
who endeavor through technical and managerial measures to ensure
the security, confidentiality, integrity, authenticity, control,
availability and utility of the world-s computing and information
systems infrastructure. The National University Cyber Security and
Information Assurance program is offered as a Master-s degree. The
emphasis of the MSCSIA program uniquely includes hands-on
academic instruction using virtual computers. This past year, 2011,
the NU facility has become fully operational using system
architecture to provide a Virtual Education Laboratory (VEL)
accessible to both onsite and online students. The first student cohort
completed their MSCSIA training this past March 2, 2012 after
fulfilling 12 courses, for a total of 54 units of college credits. The
rapid pace scheduling of one course per month is immensely
challenging, perpetually changing, and virtually multifaceted. This
paper analyses these descriptive terms in consideration of those
globalization penetration breaches as present in today-s world of
cyber security. In addition, we present current NU practices to
mitigate risks.
Abstract: Many studies have emphasized the importance of
resistive exercise to maintain a healthy human body, particular in
prevention of weakening of physical strength. Recently, some studies
advocated that an application of vibration as a supplementary means in
a regular training was effective in encouraging physical strength. Aim
of the current study was, therefore, to identify if an application of
vibration in a resistive exercise was effective in encouraging physical
strength as that in a regular training. A 3-dimensional virtual lower
extremity model for a healthy male and virtual leg-press model were
generated and synchronized. Dynamic leg-press exercises on a slide
machine with/without extra load and on a footboard with vibration as
well as on a slide machine with extra load were analyzed. The results
of the current indicated that the application of the vibration on the
dynamic leg-press exercise might be not greatly effective in
encouraging physical strength, compared with the dynamic leg press
exercise with extra load. It was, however, thought that the application
of the vibration might be helpful to elderly individuals because the
reduced maximum muscle strength appeared by the effect of the
vibration may avoid a muscular spasm, which can be driven from a
high muscle strength sometimes produced during the leg-press
exercise with extra load.
Abstract: The present work deals with the structural analysis of
turbine blades and modeling of turbine blades. A common failure
mode for turbine machines is high cycle of fatigue of compressor and
turbine blades due to high dynamic stresses caused by blade vibration
and resonance within the operation range of the machinery. In this
work, proper damping system will be analyzed to reduce the
vibrating blade. The main focus of the work is the modeling of under
platform damper to evaluate the dynamic analysis of turbine-blade
vibrations. The system is analyzed using Bond graph technique. Bond
graph is one of the most convenient ways to represent a system from
the physical aspect in foreground. It has advantage of putting together
multi-energy domains of a system in a single representation in a
unified manner. The bond graph model of dry friction damper is
simulated on SYMBOLS-shakti® software. In this work, the blades
are modeled as Timoshenko beam. Blade Vibrations under different
working conditions are being analyzed numerically.
Abstract: Laser engraving is a manufacturing method for those applications where previously Electrical Discharge Machining (EDM) was the only choice. Laser engraving technology removes material layer-by-layer and the thickness of layers is usually in the range of few microns. The aim of the present work is to investigate the influence of the process parameters on the surface quality when machined by laser engraving. The examined parameters were: the pulse frequency, the beam speed and the layer thickness. The surface quality was determined by the surface roughness for every set of parameters. Experimental results on Al7075 material showed that the surface roughness strictly depends on the process parameters used.
Abstract: As the network based technologies become
omnipresent, demands to secure networks/systems against threat
increase. One of the effective ways to achieve higher security is
through the use of intrusion detection systems (IDS), which are a
software tool to detect anomalous in the computer or network. In this
paper, an IDS has been developed using an improved machine
learning based algorithm, Locally Linear Neuro Fuzzy Model
(LLNF) for classification whereas this model is originally used for
system identification. A key technical challenge in IDS and LLNF
learning is the curse of high dimensionality. Therefore a feature
selection phase is proposed which is applicable to any IDS. While
investigating the use of three feature selection algorithms, in this
model, it is shown that adding feature selection phase reduces
computational complexity of our model. Feature selection algorithms
require the use of a feature goodness measure. The use of both a
linear and a non-linear measure - linear correlation coefficient and
mutual information- is investigated respectively
Abstract: This paper addresses the problem of recognizing and
interpreting the behavior of human workers in industrial
environments for the purpose of integrating humans in software
controlled manufacturing environments. In this work we propose a
generic concept in order to derive solutions for task-related manual
production applications. Thus, we are able to use a versatile concept
providing flexible components and being less restricted to a specific
problem or application. We instantiate our concept in a spot welding
scenario in which the behavior of a human worker is interpreted
when performing a welding task with a hand welding gun. We
acquire signals from inertial sensors, video cameras and triggers and
recognize atomic actions by using pose data from a marker based
video tracking system and movement data from inertial sensors.
Recognized atomic actions are analyzed on a higher evaluation level
by a finite state machine.
Abstract: In this paper test generation methods and appropriate fault models for testing and analysis of embedded systems described as (extended) finite state machines ((E)FSMs) are presented. Compared to simple FSMs, EFSMs specify not only the control flow but also the data flow. Thus, we define a two-level fault model to cover both aspects. The goal of this paper is to reuse well-known FSM-based test generation methods for automation of embedded system testing. These methods have been widely used in testing and validation of protocols and communicating systems. In particular, (E)FSMs-based specification and testing is more advantageous because (E)FSMs support the formal semantic of already standardised formal description techniques (FDTs) despite of their popularity in the design of hardware and software systems.
Abstract: Linear induction motors are used in various industries
but they have some specific phenomena which are the causes for
some problems. The most important phenomenon is called end effect.
End effect decreases efficiency, power factor and output force and
unbalances the phase currents. This phenomenon is more important
in medium and high speeds machines. In this paper a factor, EEF , is
obtained by an accurate equivalent circuit model, to determine the
end effect intensity. In this way, all of effective design parameters on
end effect is described. Accuracy of this equivalent circuit model is
evaluated by two dimensional finite-element analysis using ANSYS.
The results show the accuracy of the equivalent circuit model.
Abstract: Logic based methods for learning from structured data
is limited w.r.t. handling large search spaces, preventing large-sized
substructures from being considered by the resulting classifiers. A
novel approach to learning from structured data is introduced that
employs a structure transformation method, called finger printing, for
addressing these limitations. The method, which generates features
corresponding to arbitrarily complex substructures, is implemented in
a system, called DIFFER. The method is demonstrated to perform
comparably to an existing state-of-art method on some benchmark
data sets without requiring restrictions on the search space.
Furthermore, learning from the union of features generated by finger
printing and the previous method outperforms learning from each
individual set of features on all benchmark data sets, demonstrating
the benefit of developing complementary, rather than competing,
methods for structure classification.
Abstract: Determining how many virtual machines a Linux host
could run can be a challenge. One of tough missions is to find the
balance among performance, density and usability. Now KVM
hypervisor has become the most popular open source full
virtualization solution. It supports several ways of running guests with
more memory than host really has. Due to large differences between
minimum and maximum guest memory requirements, this paper
presents initial results on same-page merging, ballooning and live
migration techniques that aims at optimum memory usage on
KVM-based cloud platform. Given the design of initial experiments,
the results data is worth reference for system administrators. The
results from these experiments concluded that each method offers
different reliability tradeoff.
Abstract: In this paper, we propose a new method to distinguish
between arousal and relaxation states by using multiple features
acquired from a photoplethysmogram (PPG) and support vector
machine (SVM). To induce arousal and relaxation states in subjects, 2
kinds of sound stimuli are used, and their corresponding biosignals are
obtained using the PPG sensor. Two features–pulse to pulse interval
(PPI) and pulse amplitude (PA)–are extracted from acquired PPG
data, and a nonlinear classification between arousal and relaxation is
performed using SVM.
This methodology has several advantages when compared with
previous similar studies. Firstly, we extracted 2 separate features from
PPG, i.e., PPI and PA. Secondly, in order to improve the classification
accuracy, SVM-based nonlinear classification was performed.
Thirdly, to solve classification problems caused by generalized
features of whole subjects, we defined each threshold according to
individual features.
Experimental results showed that the average classification
accuracy was 74.67%. Also, the proposed method showed the better
identification performance than the single feature based methods.
From this result, we confirmed that arousal and relaxation can be
classified using SVM and PPG features.
Abstract: This paper presents a subjective job scheduler based
on a 3-layer Backpropagation Neural Network (BPNN) and a greedy
alignment procedure in order formulates a real-life situation. The
BPNN estimates critical values of jobs based on the given subjective
criteria. The scheduler is formulated in such a way that, at each time
period, the most critical job is selected from the job queue and is
transferred into a single machine before the next periodic job arrives.
If the selected job is one of the oldest jobs in the queue and its
deadline is less than that of the arrival time of the current job, then
there is an update of the deadline of the job is assigned in order to
prevent the critical job from its elimination. The proposed
satisfiability criteria indicates that the satisfaction of the scheduler
with respect to performance of the BPNN, validity of the jobs and the
feasibility of the scheduler.
Abstract: Power System Security is a major concern in real time
operation. Conventional method of security evaluation consists of
performing continuous load flow and transient stability studies by
simulation program. This is highly time consuming and infeasible
for on-line application. Pattern Recognition (PR) is a promising
tool for on-line security evaluation. This paper proposes a Support
Vector Machine (SVM) based binary classification for static and
transient security evaluation. The proposed SVM based PR approach
is implemented on New England 39 Bus and IEEE 57 Bus systems.
The simulation results of SVM classifier is compared with the other
classifier algorithms like Method of Least Squares (MLS), Multi-
Layer Perceptron (MLP) and Linear Discriminant Analysis (LDA)
classifiers.
Abstract: To create a solution for a specific problem in machine
learning, the solution is constructed from the data or by use a search
method. Genetic algorithms are a model of machine learning that can
be used to find nearest optimal solution. While the great advantage of
genetic algorithms is the fact that they find a solution through
evolution, this is also the biggest disadvantage. Evolution is inductive,
in nature life does not evolve towards a good solution but it evolves
away from bad circumstances. This can cause a species to evolve into
an evolutionary dead end. In order to reduce the effect of this
disadvantage we propose a new a learning tool (criteria) which can be
included into the genetic algorithms generations to compare the
previous population and the current population and then decide
whether is effective to continue with the previous population or the
current population, the proposed learning tool is called as Keeping
Efficient Population (KEP). We applied a GA based on KEP to the
production line layout problem, as a result KEP keep the evaluation
direction increases and stops any deviation in the evaluation.
Abstract: We present an Electronic Nose (ENose), which is
aimed at identifying the presence of one out of two gases, possibly
detecting the presence of a mixture of the two. Estimation of the
concentrations of the components is also performed for a volatile
organic compound (VOC) constituted by methanol and acetone, for
the ranges 40-400 and 22-220 ppm (parts-per-million), respectively.
Our system contains 8 sensors, 5 of them being gas sensors (of the
class TGS from FIGARO USA, INC., whose sensing element is a tin
dioxide (SnO2) semiconductor), the remaining being a temperature
sensor (LM35 from National Semiconductor Corporation), a
humidity sensor (HIH–3610 from Honeywell), and a pressure sensor
(XFAM from Fujikura Ltd.).
Our integrated hardware–software system uses some machine
learning principles and least square regression principle to identify at
first a new gas sample, or a mixture, and then to estimate the
concentrations. In particular we adopt a training model using the
Support Vector Machine (SVM) approach with linear kernel to teach
the system how discriminate among different gases. Then we apply
another training model using the least square regression, to predict
the concentrations.
The experimental results demonstrate that the proposed
multiclassification and regression scheme is effective in the
identification of the tested VOCs of methanol and acetone with
96.61% correctness. The concentration prediction is obtained with
0.979 and 0.964 correlation coefficient for the predicted versus real
concentrations of methanol and acetone, respectively.
Abstract: Selecting the word translation from a set of target
language words, one that conveys the correct sense of source word
and makes more fluent target language output, is one of core
problems in machine translation. In this paper we compare the 3
methods of estimating word translation probabilities for selecting the
translation word in Thai – English Machine Translation. The 3
methods are (1) Method based on frequency of word translation, (2)
Method based on collocation of word translation, and (3) Method
based on Expectation Maximization (EM) algorithm. For evaluation
we used Thai – English parallel sentences generated by NECTEC.
The method based on EM algorithm is the best method in comparison
to the other methods and gives the satisfying results.