Abstract: This work presents a new phonetic transcription system based on a tree of hierarchical pronunciation rules expressed as context-specific grapheme-phoneme correspondences. The tree is automatically inferred from a phonetic dictionary by incrementally analyzing deeper context levels, eventually representing a minimum set of exhaustive rules that pronounce without errors all the words in the training dictionary and that can be applied to out-of-vocabulary words. The proposed approach improves upon existing rule-tree-based techniques in that it makes use of graphemes, rather than letters, as elementary orthographic units. A new linear algorithm for the segmentation of a word in graphemes is introduced to enable outof- vocabulary grapheme-based phonetic transcription. Exhaustive rule trees provide a canonical representation of the pronunciation rules of a language that can be used not only to pronounce out-of-vocabulary words, but also to analyze and compare the pronunciation rules inferred from different dictionaries. The proposed approach has been implemented in C and tested on Oxford British English and Basic English. Experimental results show that grapheme-based rule trees represent phonetically sound rules and provide better performance than letter-based rule trees.
Abstract: In the present work, we propose a new technique to
enhance the learning capabilities and reduce the computation
intensity of a competitive learning multi-layered neural network
using the K-means clustering algorithm. The proposed model use
multi-layered network architecture with a back propagation learning
mechanism. The K-means algorithm is first applied to the training
dataset to reduce the amount of samples to be presented to the neural
network, by automatically selecting an optimal set of samples. The
obtained results demonstrate that the proposed technique performs
exceptionally in terms of both accuracy and computation time when
applied to the KDD99 dataset compared to a standard learning
schema that use the full dataset.
Abstract: Positioning the organization in the strategic
environment of its industry is one of the first and most important
phases of the organizational strategic planning and in today
knowledge-based economy has its importance been duplicated for
higher education institutes as the centers of education, knowledge
creation and knowledge worker training. Up to now, various models
with diverse approaches have been applied to investigate
organizations- strategic position in different industries. Regarding the
essential importance and strategic role of quality in higher education
institutes, in this study, a quality-oriented approach has been
suggested to positioning them in their strategic environment. Then
the European Foundation of Quality Management (EFQM) model has
been adopted to position the top Iranian business schools in their
strategic environment. The result of this study can be used in strategic
planning of these institutes as well as the other Iranian business
schools.
Abstract: In this paper, the modelling and design of artificial neural network architecture for load forecasting purposes is investigated. The primary pre-requisite for power system planning is to arrive at realistic estimates of future demand of power, which is known as Load Forecasting. Short Term Load Forecasting (STLF) helps in determining the economic, reliable and secure operating strategies for power system. The dependence of load on several factors makes the load forecasting a very challenging job. An over estimation of the load may cause premature investment and unnecessary blocking of the capital where as under estimation of load may result in shortage of equipment and circuits. It is always better to plan the system for the load slightly higher than expected one so that no exigency may arise. In this paper, a load-forecasting model is proposed using a multilayer neural network with an appropriately modified back propagation learning algorithm. Once the neural network model is designed and trained, it can forecast the load of the power system 24 hours ahead on daily basis and can also forecast the cumulative load on daily basis. The real load data that is used for the Artificial Neural Network training was taken from LDC, Gujarat Electricity Board, Jambuva, Gujarat, India. The results show that the load forecasting of the ANN model follows the actual load pattern more accurately throughout the forecasted period.
Abstract: A geothermal power plant multiple simulator for
operators training is presented. The simulator is designed to be
installed in a wireless local area network and has a capacity to train
one to six operators simultaneously, each one with an independent
simulation session. The sessions must be supervised only by one
instructor. The main parts of this multiple simulator are: instructor
and operator-s stations. On the instructor station, the instructor
controls the simulation sessions, establishes training exercises and
supervises each power plant operator in individual way. This station
is hosted in a Main Personal Computer (NS) and its main functions
are: to set initial conditions, snapshots, malfunctions or faults,
monitoring trends, and process and soft-panel diagrams. On the other
hand the operators carry out their actions over the power plant
simulated on the operator-s stations; each one is also hosted in a PC.
The main software of instructor and operator-s stations are executed
on the same NS and displayed in PCs through graphical Interactive
Process Diagrams (IDP). The geothermal multiple simulator has been
installed in the Geothermal Simulation Training Center (GSTC) of
the Comisi├│n Federal de Electricidad, (Federal Commission of
Electricity, CFE), Mexico, and is being utilized as a part of the
training courses for geothermal power plant operators.
Abstract: In this paper in consideration of each available
techniques deficiencies for speech recognition, an advanced method
is presented that-s able to classify speech signals with the high
accuracy (98%) at the minimum time. In the presented method, first,
the recorded signal is preprocessed that this section includes
denoising with Mels Frequency Cepstral Analysis and feature
extraction using discrete wavelet transform (DWT) coefficients; Then
these features are fed to Multilayer Perceptron (MLP) network for
classification. Finally, after training of neural network effective
features are selected with UTA algorithm.
Abstract: In this paper the application of neuro-fuzzy system for equalization of channel distortion is considered. The structure and operation algorithm of neuro-fuzzy equalizer are described. The use of neuro-fuzzy equalizer in digital signal transmission allows to decrease training time of parameters and decrease the complexity of the network. The simulation of neuro-fuzzy equalizer is performed. The obtained result satisfies the efficiency of application of neurofuzzy technology in channel equalization.
Abstract: In this paper, Differential Evolution (DE) algorithm, a new promising evolutionary algorithm, is proposed to train Radial Basis Function (RBF) network related to automatic configuration of network architecture. Classification tasks on data sets: Iris, Wine, New-thyroid, and Glass are conducted to measure the performance of neural networks. Compared with a standard RBF training algorithm in Matlab neural network toolbox, DE achieves more rational architecture for RBF networks. The resulting networks hence obtain strong generalization abilities.
Abstract: Non-Destructive evaluation of in-service power
transformer condition is necessary for avoiding catastrophic failures.
Dissolved Gas Analysis (DGA) is one of the important methods.
Traditional, statistical and intelligent DGA approaches have been
adopted for accurate classification of incipient fault sources.
Unfortunately, there are not often enough faulty patterns required for
sufficient training of intelligent systems. By bootstrapping the
shortcoming is expected to be alleviated and algorithms with better
classification success rates to be obtained. In this paper the
performance of an artificial neural network, K-Nearest Neighbour
and support vector machine methods using bootstrapped data are
detailed and shown that while the success rate of the ANN algorithms
improves remarkably, the outcome of the others do not benefit so
much from the provided enlarged data space. For assessment, two
databases are employed: IEC TC10 and a dataset collected from
reported data in papers. High average test success rate well exhibits
the remarkable outcome.
Abstract: This study analyzed the creativity of student teams
participating in an exploratory information system development
project (ISDP) and examined antecedents of their creativity. By using
partial least squares (PLS) to analyze a sample of thirty-six teams
enrolled in an information system department project training course
that required three semesters of project-based lessons, the results
found social capitals (structural, relational and cognitive social capital)
positively influence knowledge integration. However, relational social
capital does not significantly influence knowledge integration.
Knowledge integration positively affects team creativity. This study
also demonstrated that social capitals significantly influence team
creativity through knowledge integration. The implications of our
findings for future research are discussed.
Abstract: Designing a simulated system and training it to optimize its tasks in simulated environment helps the designers to avoid problems that may appear when designing the system directly in real world. These problems are: time consuming, high cost, high errors percentage and low efficiency and accuracy of the system. The proposed system will investigate and improve the efficiency and accuracy of a simulated robot to choose correct behavior to perform its task. In this paper, machine learning, which uses genetic algorithm, is adopted. This type of machine learning is called genetic-based machine learning in which a distributed classifier system is used to improve the efficiency and accuracy of the robot. Consequently, it helps the robot to achieve optimal action.
Abstract: The purpose of this research was to study the inspector performance by using computer based training (CBT). Visual inspection task was printed circuit board (PCB) simulated on several types of defects. Subjects were 16 undergraduate randomly selected from King Mongkut-s University of Technology Thonburi and test for 20/20. Then, they were equally divided on performance into two groups (control and treatment groups) and were provided information before running the experiment. Only treatment group was provided feedback information after first experiment. Results revealed that treatment group was showed significantly difference at the level of 0.01. The treatment group showed high percentage on defects detected. Moreover, the attitude of inspectors on using the CBT to inspection was showed on good. These results have been showed that CBT could be used for training to improve inspector performance.
Abstract: Heavy rainfall greatly affects the aerodynamic performance of the aircraft. There are many accidents of aircraft caused by aerodynamic efficiency degradation by heavy rain.
In this Paper we have studied the heavy rain effects on the aerodynamic efficiency of cambered NACA 64-210 and symmetric
NACA 0012 airfoils. Our results show significant increase in drag and decrease in lift. We used preprocessing software gridgen for creation of geometry and mesh, used fluent as solver and techplot as postprocessor. Discrete phase modeling called DPM is used to model the rain particles using two phase flow approach. The rain particles are assumed to be inert.
Both airfoils showed significant decrease in lift and increase in drag in simulated rain environment. The most significant difference between these two airfoils was the NACA 64-210 more sensitivity than NACA 0012 to liquid water content (LWC). We believe that the results showed in this paper will be useful for the designer of the commercial aircrafts and UAVs, and will be helpful for training of the pilots to control the airplanes in heavy rain.
Abstract: Text Mining is around applying knowledge discovery techniques to unstructured text is termed knowledge discovery in text (KDT), or Text data mining or Text Mining. In Neural Network that address classification problems, training set, testing set, learning rate are considered as key tasks. That is collection of input/output patterns that are used to train the network and used to assess the network performance, set the rate of adjustments. This paper describes a proposed back propagation neural net classifier that performs cross validation for original Neural Network. In order to reduce the optimization of classification accuracy, training time. The feasibility the benefits of the proposed approach are demonstrated by means of five data sets like contact-lenses, cpu, weather symbolic, Weather, labor-nega-data. It is shown that , compared to exiting neural network, the training time is reduced by more than 10 times faster when the dataset is larger than CPU or the network has many hidden units while accuracy ('percent correct') was the same for all datasets but contact-lences, which is the only one with missing attributes. For contact-lences the accuracy with Proposed Neural Network was in average around 0.3 % less than with the original Neural Network. This algorithm is independent of specify data sets so that many ideas and solutions can be transferred to other classifier paradigms.
Abstract: From past many decades human beings are suffering
from plethora of natural disasters. Occurrence of disasters is a
frequent process; it changes conceptual myths as more and more
advancement are made. Although we are living in technological era
but in developing countries like Pakistan disasters are shaped by
socially constructed roles. The need is to understand the most
vulnerable group of society i.e. females; their issues are complex in
nature because of undermined gender status in the society. There is a
need to identify maximum issues regarding females and to enhance
the achievement of millennium development goals (MDGs). Gender
issues are of great concern all around the globe including Pakistan.
Here female visibility in society is low, and also during disasters, the
failure to understand the reality that concentrates on double burden
including productive and reproductive care. Women have to
contribute a lot in society so we need to make them more disaster
resilient. For this non-structural measures like awareness, trainings
and education must be carried out. In rural and in urban settings in
any disaster like earthquake or flood, elements like gender
perspective, their age, physical health, demographic issues contribute
towards vulnerability. In Pakistan the gender issues in disasters were
of less concern before 2005 earthquake and 2010 floods. Significant
achievements are made after 2010 floods when gender and child cell
was created to provide all facilities to women and girls. The aim of
the study is to highlight all necessary facilities in a disaster to build
coping mechanism in females from basic rights till advance level
including education.
Abstract: Assessment of IEP (Individual Education Plan) is an
important stage in the area of special education. This paper deals
with this problem by introducing computer software which process
the data gathered from application of IEP. The software is intended
to be used by special education institution in Turkey and allows
assessment of school and family trainings. The software has a user
friendly interface and its design includes graphical developer tools.
Abstract: This paper presents the outcomes of a qualitative
study which aims to investigate the pedagogical potentials of serious
games in the preparation of future teachers. The authors discuss the
existing problems and barriers associated with the organization of
teaching practices in Bulgaria as part of the pre-service teacher
training, as well as the attitudes and perceptions of the interviewed
academics, teachers and trainees concerning the integration of serious
games in the teaching practicum. The study outcomes strongly
confirm the positive attitudes of the respondents to the introduction
of virtual learning environments for the development of professional
skills of future teachers as a supplement to the traditional forms of
education. Through the inclusion of serious games it is expected to
improve the quality of practical training of pre-service teachers as
they overcome many of the problems identified in the existing
teaching practices. The outcomes of the study will inform the design
of the educational simulation software which is part of the project
SimAula Tomorrow's Teachers Training.
Abstract: This paper presents a new approach for automatic
document categorization. Exploiting the logical structure of the
document, our approach assigns a HTML document to one or more
categories (thesis, paper, call for papers, email, ...). Using a set of
training documents, our approach generates a set of rules used to
categorize new documents. The approach flexibility is carried out
with rule weight association representing your importance in the
discrimination between possible categories. This weight is
dynamically modified at each new document categorization. The
experimentation of the proposed approach provides satisfactory
results.
Abstract: Oral health is particular important to the hospitalized
patients with chronic schizophrenia for an extreme high potential of the respiratory infections. Due to the degeneration of physical capability, patients of this kind typically fall dependent in the activity of daily living (ADL). A very high percentage of patients had dental
problems of which mostly could be easily avoid by easy regular tooth brushing. Purpose of the project is to develop a mechanism in helping the schizophrenia patients in rebuilding a tooth-cleaning habit. The
project observed and evaluated the tooth-cleaning behavior of 100
male patients in a psychiatric hospital, and found the majority of them
ignored such an activity in a three-month period of time. In the meantime, the primary care-givers were not aware or not convinced
the importance of such a need of dental hygiene, and thus few if any
tooth cleaning training or knowledge on dental hygiene were given to
the patients. The project then developed a program based on the numerous observations and discussions. The improvement program
included patients- group education, care-givers- training, and a
tool-kit for tooth-brush holding was erected. The project launched
with some incentive package. The outcomes were encouraging with
87% of the patients had rebuilt their tooth-brushing habits against
previous 22%, and the tooth cleaning kits were 100% kept against 22%
in the past. This project had significantly improved the oral health of
the patients. The project, included the procedure and the tool-kit
holder specific for this purpose, was a good examples for psychiatric
hospitals.
Abstract: The role of knowledge is a determinative factor in the
life of economy and society. To determine knowledge is not an easy
task yet the real task is to determine the right knowledge. From this
view knowledge is a sum of experience, ideas and cognitions which
can help companies to remain in markets and to realize a maximum
profit. At the same time changes of circumstances project in advance
that contents and demands of the right knowledge are changing. In
this paper we will analyse a special segment on the basis of an
empirical survey. We investigated the behaviour and strategies of
small and medium sized enterprises (SMEs) in the area of
knowledge-handling. This survey was realized by questionnaires and
wide range statistical methods were used during processing. As a
result we will show how these companies are prepared to operate in a
knowledge-based economy and in which areas they have prominent
deficiencies.