Abstract: In this paper back-propagation artificial neural network
(BPANN )with Levenberg–Marquardt algorithm is employed to
predict the deformation of the upsetting process. To prepare a
training set for BPANN, some finite element simulations were
carried out. The input data for the artificial neural network are a set
of parameters generated randomly (aspect ratio d/h, material
properties, temperature and coefficient of friction). The output data
are the coefficient of polynomial that fitted on barreling curves.
Neural network was trained using barreling curves generated by
finite element simulations of the upsetting and the corresponding
material parameters. This technique was tested for three different
specimens and can be successfully employed to predict the
deformation of the upsetting process
Abstract: The majority of micro-entrepreneurs in Malaysia
operate very small-scaled business activities such as food stalls,
burger stalls, night market hawkers, grocery stores, constructions,
rubber and oil palm small holders, and other agro-based services and
activities. Why are they venturing into entrepreneurship - is it for
survival, out of interest or due to encouragement and assistance from
the local government? And why is it that some micro-entrepreneurs
are lagging behind in entrepreneurship, and what do they need to
rectify this situation so that they are able to progress further?
Furthermore, what are the skills that the micro entrepreneurs should
developed to transform them into successful micro-enterprises and
become small and medium-sized enterprises (SME)? This paper
proposes a 7-Step approach that can serve as a basis for identification
of critical entrepreneurial success factors that enable policy makers,
practitioners, consultants, training managers and other agencies in
developing tools to assist micro business owners. This paper also
highlights the experience of one of the successful companies in
Malaysia that has transformed from micro-enterprise to become a
large organization in less than 10 years.
Abstract: Based on statistics released by Islamic Republic of
Iran Police (IRIP), from among the total 9555 motorcycle accidents
that happened in 2007, 857 riders died and 11219 one got injured. If
we also consider the death toll and injuries of other vehicles'
accidents resulted from traffic violation by motorcycle riders, then
paying attention to the motorcycle accidents seems to be very
necessary. Therefore, in this study we tried to investigate the traits
and issues related to production, application, and training, along with
causes of motorcycle accidents from 4 perspectives of road, human,
environment and vehicle and also based on statistical and
geographical analysis of accident-sheets prepared by Iran Road
Patrol Department (IRPD). Unfamiliarity of riders with regulations
and techniques of motorcycling, disuse of safety equipments,
inefficiency of roads and design of junctions for safe trafficking of
motorcycles and finally the lack of sufficient control of responsible
organizations are among the major causes which lead to these
accidents.
Abstract: We address the problem of joint beamforming and multipath channel parameters estimation in Wideband Code Division Multiple Access (WCDMA) communication systems that employ Multiple-Access Interference (MAI) suppression techniques in the uplink (from mobile to base station). Most of the existing schemes rely on time multiplex a training sequence with the user data. In WCDMA, the channel parameters can also be estimated from a code multiplexed common pilot channel (CPICH) that could be corrupted by strong interference resulting in a bad estimate. In this paper, we present new methods to combine interference suppression together with channel estimation when using multiple receiving antennas by using adaptive signal processing techniques. Computer simulation is used to compare between the proposed methods and the existing conventional estimation techniques.
Abstract: This paper proposes an auto-classification algorithm
of Web pages using Data mining techniques. We consider the
problem of discovering association rules between terms in a set of
Web pages belonging to a category in a search engine database, and
present an auto-classification algorithm for solving this problem that
are fundamentally based on Apriori algorithm. The proposed
technique has two phases. The first phase is a training phase where
human experts determines the categories of different Web pages, and
the supervised Data mining algorithm will combine these categories
with appropriate weighted index terms according to the highest
supported rules among the most frequent words. The second phase is
the categorization phase where a web crawler will crawl through the
World Wide Web to build a database categorized according to the
result of the data mining approach. This database contains URLs and
their categories.
Abstract: Virtual engineering technology has undergone rapid progress in recent years and is being adopted increasingly by manufacturing companies of many engineering disciplines. There is an increasing demand from industry for qualified virtual engineers. The qualified virtual engineers should have the ability of applying engineering principles and mechanical design methods within the commercial software package environment. It is a challenge to the engineering education in universities which traditionally tends to lack the integration of knowledge and skills required for solving real world problems. In this paper, a case study shows some recent development of a MSc Mechanical Engineering course at Department of Engineering and Technology in MMU, and in particular, two units Simulation of Mechanical Systems(SMS) and Computer Aided Fatigue Analysis(CAFA) that emphasize virtual engineering education and promote integration of knowledge acquisition, skill training and industrial application.
Abstract: Thanks to VR technology advanced, there are many
researches had used VR technology to develop a training system.
Using VR characteristics can simulate many kinds of situations to
reach our training-s goal. However, a good training system not only
considers real simulation but also considers learner-s learning
motivation. So, there are many researches started to conduct game-s
features into VR training system. We typically called this is a serious
game. It is using game-s features to engage learner-s learning
motivation. However, VR or Serious game has another important
advantage. That is simulating feature. Using this feature can create
any kinds of pressured environments. Because in the real
environment may happen any emergent situations. So, increasing the
trainees- pressure is more important when they are training. Most
pervious researches are investigated serious game-s applications and
learning performance. Seldom researches investigated how to
increase the learner-s mental workload when they are training. So, in
our study, we will introduce a real case study and create two types
training environments. Comparing the learner-s mental workload
between VR training and serious game.
Abstract: In this paper, a Web-based e-Training platform that is dedicated to multimodal breast imaging is presented. The assets of this platform are summarised in (i) the efficient representation of the curriculum flow that will permit efficient training; (ii) efficient tagging of multimodal content appropriate for the completion of realistic cases and (iii) ubiquitous accessibility and platform independence via a web-based approach.
Abstract: Government of Indonesia held a certification program to enhance the professionalism of teachers by using portfolio assessment. This research discusses about the effectiveness of certification programs to enhance the professionalism of teacher in Indonesia. Portfolio assessment method has drawbacks. The certified teachers do not show significant performance improvement. Therefore, the government changes the portfolio assessment method to the education and training for teachers.
Abstract: The mitigation of crop loss due to damaging freezes
requires accurate air temperature prediction models. Previous work
established that the Ward-style artificial neural network (ANN) is a
suitable tool for developing such models. The current research
focused on developing ANN models with reduced average prediction
error by increasing the number of distinct observations used in
training, adding additional input terms that describe the date of an
observation, increasing the duration of prior weather data included in
each observation, and reexamining the number of hidden nodes used
in the network. Models were created to predict air temperature at
hourly intervals from one to 12 hours ahead. Each ANN model,
consisting of a network architecture and set of associated parameters,
was evaluated by instantiating and training 30 networks and
calculating the mean absolute error (MAE) of the resulting networks
for some set of input patterns. The inclusion of seasonal input terms,
up to 24 hours of prior weather information, and a larger number of
processing nodes were some of the improvements that reduced
average prediction error compared to previous research across all
horizons. For example, the four-hour MAE of 1.40°C was 0.20°C, or
12.5%, less than the previous model. Prediction MAEs eight and 12
hours ahead improved by 0.17°C and 0.16°C, respectively,
improvements of 7.4% and 5.9% over the existing model at these
horizons. Networks instantiating the same model but with different
initial random weights often led to different prediction errors. These
results strongly suggest that ANN model developers should consider
instantiating and training multiple networks with different initial
weights to establish preferred model parameters.
Abstract: This paper reports the study results on neural network
training algorithm of numerical optimization techniques multiface
detection in static images. The training algorithms involved are scale
gradient conjugate backpropagation, conjugate gradient
backpropagation with Polak-Riebre updates, conjugate gradient
backpropagation with Fletcher-Reeves updates, one secant
backpropagation and resilent backpropagation. The final result of
each training algorithms for multiface detection application will also
be discussed and compared.
Abstract: This paper presents and evaluates a new classification
method that aims to improve classifiers performances and speed up
their training process. The proposed approach, called labeled
classification, seeks to improve convergence of the BP (Back
propagation) algorithm through the addition of an extra feature
(labels) to all training examples. To classify every new example, tests
will be carried out each label. The simplicity of implementation is the
main advantage of this approach because no modifications are
required in the training algorithms. Therefore, it can be used with
others techniques of acceleration and stabilization. In this work, two
models of the labeled classification are proposed: the LMLP
(Labeled Multi Layered Perceptron) and the LNFC (Labeled Neuro
Fuzzy Classifier). These models are tested using Iris, wine, texture
and human thigh databases to evaluate their performances.
Abstract: The Emergency Department of a medical center in
Taiwan cooperated to conduct the research. A predictive model of
triage system is contracted from the contract procedure, selection of
parameters to sample screening. 2,000 pieces of data needed for the
patients is chosen randomly by the computer. After three
categorizations of data mining (Multi-group Discriminant Analysis,
Multinomial Logistic Regression, Back-propagation Neural
Networks), it is found that Back-propagation Neural Networks can
best distinguish the patients- extent of emergency, and the accuracy
rate can reach to as high as 95.1%. The Back-propagation Neural
Networks that has the highest accuracy rate is simulated into the triage
acuity expert system in this research. Data mining applied to the
predictive model of the triage acuity expert system can be updated
regularly for both the improvement of the system and for education
training, and will not be affected by subjective factors.
Abstract: The aim of this retrospective study was to evaluate the
parameters of dental implants such as patient gender, number of
implant, failed implant before prosthetic restorations and failed
implant after implantation and failed implant after prosthetic
restorations. 135 male and 99 female patients, total 234 implant
patients which have been treated with 450 implant between 2005-
2009 years in GATA Haydarpasa Training Hospital Dental Service.
Twelve implants were failed before prosthetic restorations. Four
implant were failed after fixed prosthetic restorations. Cumulative
survival rate after prostheses were 97.56 % during 6 years period.
Abstract: In this article we explore how computer assisted exercises may allow for bridging the traditional gap between theory and practice in professional education. To educate officers able to master the complexity of the battlefield the Norwegian Military Academy needs to develop a learning environment that allows for creating viable connections between the educational environment and the field of practice. In response to this challenge we explore the conditions necessary to make computer assisted training systems (CATS) a useful tool to create structural similarities between an educational context and the field of military practice. Although, CATS may facilitate work procedures close to real life situations, this case do demonstrate how professional competence also must build on viable learning theories and environments. This paper explores the conditions that allow for using simulators to facilitate professional competence from within an educational setting. We develop a generic didactic model that ascribes learning to participation in iterative cycles of action and reflection. The development of this model is motivated by the need to develop an interdisciplinary professional education rooted in the pattern of military practice.
Abstract: Fundamental sensor-motor couplings form the backbone
of most mobile robot control tasks, and often need to be implemented
fast, efficiently and nevertheless reliably. Machine learning
techniques are therefore often used to obtain the desired sensor-motor
competences.
In this paper we present an alternative to established machine
learning methods such as artificial neural networks, that is very fast,
easy to implement, and has the distinct advantage that it generates
transparent, analysable sensor-motor couplings: system identification
through nonlinear polynomial mapping.
This work, which is part of the RobotMODIC project at the
universities of Essex and Sheffield, aims to develop a theoretical understanding
of the interaction between the robot and its environment.
One of the purposes of this research is to enable the principled design
of robot control programs.
As a first step towards this aim we model the behaviour of the
robot, as this emerges from its interaction with the environment, with
the NARMAX modelling method (Nonlinear, Auto-Regressive, Moving
Average models with eXogenous inputs). This method produces
explicit polynomial functions that can be subsequently analysed using
established mathematical methods.
In this paper we demonstrate the fidelity of the obtained NARMAX
models in the challenging task of robot route learning; we present a
set of experiments in which a Magellan Pro mobile robot was taught
to follow four different routes, always using the same mechanism to
obtain the required control law.
Abstract: Previous studies have shown that there are arguments
regarding the reliability and validity of the Ashworth and Modified
Ashworth Scale towards evaluating patients diagnosed with upper
limb disorders. These evaluations depended on the raters’ experiences.
This initiated us to develop an upper limb disorder part-task trainer
that is able to simulate consistent upper limb disorders, such as
spasticity and rigidity signs, based on the Modified Ashworth Scale to
improve the variability occurring between raters and intra-raters
themselves. By providing consistent signs, novice therapists would be
able to increase training frequency and exposure towards various
levels of signs. A total of 22 physiotherapists and occupational
therapists participated in the study. The majority of the therapists
agreed that with current therapy education, they still face problems
with inter-raters and intra-raters variability (strongly agree 54%; n =
12/22, agree 27%; n = 6/22) in evaluating patients’ conditions. The
therapists strongly agreed (72%; n = 16/22) that therapy trainees
needed to increase their frequency of training; therefore believe that
our initiative to develop an upper limb disorder training tool will help
in improving the clinical education field (strongly agree and agree
63%; n = 14/22).
Abstract: Hemorrhage Disease of Grass Carp (HDGC) is a kind
of commonly occurring illnesses in summer, and the extremely high
death rate result in colossal losses to aquaculture. As the complex
connections among each factor which influences aquiculture diseases,
there-s no quit reasonable mathematical model to solve the problem at
present.A BP neural network which with excellent nonlinear mapping
coherence was adopted to establish mathematical model;
Environmental factor, which can easily detected, such as breeding
density, water temperature, pH and light intensity was set as the main
analyzing object. 25 groups of experimental data were used for
training and test, and the accuracy of using the model to predict the
trend of HDGC was above 80%. It is demonstrated that BP neural
network for predicating diseases in HDGC has a particularly
objectivity and practicality, thus it can be spread to other aquiculture
disease.
Abstract: Despite the fact that Arabic language is currently one
of the most common languages worldwide, there has been only a
little research on Arabic speech recognition relative to other
languages such as English and Japanese. Generally, digital speech
processing and voice recognition algorithms are of special
importance for designing efficient, accurate, as well as fast automatic
speech recognition systems. However, the speech recognition process
carried out in this paper is divided into three stages as follows: firstly,
the signal is preprocessed to reduce noise effects. After that, the
signal is digitized and hearingized. Consequently, the voice activity
regions are segmented using voice activity detection (VAD)
algorithm. Secondly, features are extracted from the speech signal
using Mel-frequency cepstral coefficients (MFCC) algorithm.
Moreover, delta and acceleration (delta-delta) coefficients have been
added for the reason of improving the recognition accuracy. Finally,
each test word-s features are compared to the training database using
dynamic time warping (DTW) algorithm. Utilizing the best set up
made for all affected parameters to the aforementioned techniques,
the proposed system achieved a recognition rate of about 98.5%
which outperformed other HMM and ANN-based approaches
available in the literature.
Abstract: The System Identification problem looks for a
suitably parameterized model, representing a given process. The
parameters of the model are adjusted to optimize a performance
function based on error between the given process output and
identified process output. The linear system identification field is
well established with many classical approaches whereas most of
those methods cannot be applied for nonlinear systems. The problem
becomes tougher if the system is completely unknown with only the
output time series is available. It has been reported that the
capability of Artificial Neural Network to approximate all linear and
nonlinear input-output maps makes it predominantly suitable for the
identification of nonlinear systems, where only the output time series
is available. [1][2][4][5]. The work reported here is an attempt to
implement few of the well known algorithms in the context of
modeling of nonlinear systems, and to make a performance
comparison to establish the relative merits and demerits.