Abstract: Information and Communications Technologies (ICT) has been integrated in education in many developing and developed countries alike, but the use of ICT in Tanzanian schools is dismal. Many Tanzanian secondary schools have no computers. The few schools with computers use them primarily for secretarial services and computer literacy training. The Tanzanian education system at other levels like secondary school level has to undergo substantial transformation, underscored by the growing application of new information and communication technology. This paper presents the e-readiness survey result from secondary schools in Tanzania. The paper also suggests how Tanzania can make use of the few present ICT resources to support and improve teaching and learning functions to improve performance and acquisition of knowledge by using e-Learning Management System (e-LMS).
Abstract: A novel feature selection strategy to improve the recognition accuracy on the faces that are affected due to nonuniform illumination, partial occlusions and varying expressions is proposed in this paper. This technique is applicable especially in scenarios where the possibility of obtaining a reliable intra-class probability distribution is minimal due to fewer numbers of training samples. Phase congruency features in an image are defined as the points where the Fourier components of that image are maximally inphase. These features are invariant to brightness and contrast of the image under consideration. This property allows to achieve the goal of lighting invariant face recognition. Phase congruency maps of the training samples are generated and a novel modular feature selection strategy is implemented. Smaller sub regions from a predefined neighborhood within the phase congruency images of the training samples are merged to obtain a large set of features. These features are arranged in the order of increasing distance between the sub regions involved in merging. The assumption behind the proposed implementation of the region merging and arrangement strategy is that, local dependencies among the pixels are more important than global dependencies. The obtained feature sets are then arranged in the decreasing order of discriminating capability using a criterion function, which is the ratio of the between class variance to the within class variance of the sample set, in the PCA domain. The results indicate high improvement in the classification performance compared to baseline algorithms.
Abstract: Currently, a large number of license activities (Early
Site Permits, Combined Operating License, reactor certifications,
etc.), are pending for review before the United States Nuclear
Regulatory Commission (US NRC). Much of the senior staff at the
NRC is now committed to these review and licensing actions. To
address this additional workload, the NRC has recruited a large
number of new Regulatory Staff for dealing with these and other
regulatory actions such as the US Fleet of Research and Test Reactors
(RTRs). These reactors pose unusual demands on Regulatory Staff
since the US Fleet of RTRs, although few (32 Licensed RTRs as of
2010), they represent a broad range of reactor types, operations, and
research and training aspects that nuclear reactor power plants (such
as the 104 LWRs) do not pose. The NRC must inspect and regulate
all these facilities. This paper addresses selected training topics and
regulatory activities providedNRC Inspectors for RTRs.
Abstract: Motion detection is a basic operation in the selection of significant segments of the video signals. For an effective Human Computer Intelligent Interaction, the computer needs to recognize the motion and track the moving object. Here an efficient neural network system is proposed for motion detection from the static background. This method mainly consists of four parts like Frame Separation, Rough Motion Detection, Network Formation and Training, Object Tracking. This paper can be used to verify real time detections in such a way that it can be used in defense applications, bio-medical applications and robotics. This can also be used for obtaining detection information related to the size, location and direction of motion of moving objects for assessment purposes. The time taken for video tracking by this Neural Network is only few seconds.
Abstract: In this paper we are interested in classification problems
with a performance constraint on error probability. In such
problems if the constraint cannot be satisfied, then a rejection option
is introduced. For binary labelled classification, a number of SVM
based methods with rejection option have been proposed over the
past few years. All of these methods use two thresholds on the SVM
output. However, in previous works, we have shown on synthetic data
that using thresholds on the output of the optimal SVM may lead to
poor results for classification tasks with performance constraint. In
this paper a new method for supervised classification with rejection
option is proposed. It consists in two different classifiers jointly
optimized to minimize the rejection probability subject to a given
constraint on error rate. This method uses a new kernel based linear
learning machine that we have recently presented. This learning
machine is characterized by its simplicity and high training speed
which makes the simultaneous optimization of the two classifiers
computationally reasonable. The proposed classification method with
rejection option is compared to a SVM based rejection method
proposed in recent literature. Experiments show the superiority of
the proposed method.
Abstract: This paper presented a collaborative education model,
which consists four parts: collaborative teaching, collaborative
working, collaborative training and interaction. Supported by an
e-learning platform, collaborative education was practiced in a data
structure e-learning course. Data collected shows that most of students
accept collaborative education. This paper goes one step attempting to
determine which aspects appear to be most important or helpful in
collaborative education.
Abstract: Within the last years, several technologies have been developed to help building e-learning portals. Most of them follow approaches that deliver a vast amount of functionalities, suitable for class-like learning. The SuGI project, as part of the D-Grid (funded by the BMBF), targets on delivering a highly scalable and sustainable learning solution to provide materials (e.g. learning modules, training systems, webcasts, tutorials, etc.) containing knowledge about Grid computing to the D-Grid community. In this article, the process of the development of an e-learning portal focused on the requirements of this special user group is described. Furthermore, it deals with the conceptual and technical design of an e-learning portal, addressing the special needs of heterogeneous target groups. The main focus lies on the quality management of the software development process, Web templates for uploading new contents, the rich search and filter functionalities which will be described from a conceptual as well as a technical point of view. Specifically, it points out best practices as well as concepts to provide a sustainable solution to a relatively unknown and highly heterogeneous community.
Abstract: In this paper, frequency offset (FO) estimation schemes
robust to the non-Gaussian noise environments are proposed for
orthogonal frequency division multiplexing (OFDM) systems. First,
a maximum-likelihood (ML) estimation scheme in non-Gaussian
noise environments is proposed, and then, the complexity of the
ML estimation scheme is reduced by employing a reduced set of
candidate values. In numerical results, it is demonstrated that the
proposed schemes provide a significant performance improvement
over the conventional estimation scheme in non-Gaussian noise
environments while maintaining the performance similar to the
estimation performance in Gaussian noise environments.
Abstract: In recent years in Kazakhstan, as well as in all countries, we have been talking not only about the professional stress, but also professional Burnout Syndrome of employees. Burnout is essentially a response to chronic emotional stress – manifests itself in the form of chronic fatigue, despondency, unmotivated aggression, anger, and others. This condition is due to mental fatigue among teachers as a sort of payment for overstrain when professional commitments include the impact of “heat your soul", emotional investment. The emergence of professional Burnout among teachers is due to the system of interrelated and mutually reinforcing factors relating to the various levels of the personality: individually-psychological level is psychodynamic special subject characteristics of valuemotivational sphere and formation of skills and habits of selfregulation; the socio-psychological level includes especially the Organization and interpersonal interaction of a teacher. Signs of the Burnout were observed in 15 testees, and virtually a symptom could be observed in every teacher. As a result of the diagnosis 48% of teachers had the signs of stress (phase syndrome), resulting in a sense of anxiety, mood, heightened emotional susceptibility. The following results have also been got:-the fall of General energy potential – 14 pers. -Psychosomatic and psycho vegetative syndrome – 26 pers. -emotional deficit-34 pers. -emotional Burnout Syndrome-6 pers. The problem of professional Burnout of teachers in the current conditions should become not only meaningful, but particularly relevant. The quality of education of the younger generation depends on professional development; teachers- training level, and how “healthy" teachers are. That is why the systematic maintenance of pedagogic-professional development for teachers (including disclosure of professional Burnout Syndrome factors) takes on a special meaning.
Abstract: A new approach to promote the generalization ability
of neural networks is presented. It is based on the point of view of
fuzzy theory. This approach is implemented through shrinking or
magnifying the input vector, thereby reducing the difference between
training set and testing set. It is called “shrinking-magnifying
approach" (SMA). At the same time, a new algorithm; α-algorithm is
presented to find out the appropriate shrinking-magnifying-factor
(SMF) α and obtain better generalization ability of neural networks.
Quite a few simulation experiments serve to study the effect of SMA
and α-algorithm. The experiment results are discussed in detail, and
the function principle of SMA is analyzed in theory. The results of
experiments and analyses show that the new approach is not only
simpler and easier, but also is very effective to many neural networks
and many classification problems. In our experiments, the proportions
promoting the generalization ability of neural networks have even
reached 90%.
Abstract: In this paper, we propose a new hybrid learning model for stock market indices prediction by adding a passive congregation term to the standard hybrid model comprising Particle Swarm Optimization (PSO) with Genetic Algorithm (GA) operators in training Neural Networks (NN). This new passive congregation term is based on the cooperation between different particles in determining new positions rather than depending on the particles selfish thinking without considering other particles positions, thus it enables PSO to perform both the local and global search instead of only doing the local search. Experiment study carried out on the most famous European stock market indices in both long term and short term prediction shows significantly the influence of the passive congregation term in improving the prediction accuracy compared to standard hybrid model.
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 decision tree
approach is most useful in classification problem. With this
technique, tree is constructed to model the classification process.
There are two basic steps in the technique: building the tree and
applying the tree to the database. This paper describes a proposed
C5.0 classifier that performs rulesets, cross validation and boosting
for original C5.0 in order to reduce the optimization of error ratio.
The feasibility and the benefits of the proposed approach are
demonstrated by means of medial data set like hypothyroid. It is
shown that, the performance of a classifier on the training cases from
which it was constructed gives a poor estimate by sampling or using a
separate test file, either way, the classifier is evaluated on cases that
were not used to build and evaluate the classifier are both are large. If
the cases in hypothyroid.data and hypothyroid.test were to be
shuffled and divided into a new 2772 case training set and a 1000
case test set, C5.0 might construct a different classifier with a lower
or higher error rate on the test cases. An important feature of see5 is
its ability to classifiers called rulesets. The ruleset has an error rate
0.5 % on the test cases. The standard errors of the means provide an
estimate of the variability of results. One way to get a more reliable
estimate of predictive is by f-fold –cross- validation. The error rate of
a classifier produced from all the cases is estimated as the ratio of the
total number of errors on the hold-out cases to the total number of
cases. The Boost option with x trials instructs See5 to construct up to
x classifiers in this manner. Trials over numerous datasets, large and
small, show that on average 10-classifier boosting reduces the error
rate for test cases by about 25%.
Abstract: This study endeavors to evaluate the effects of farmers’ training program on the adoption of improved farming practices, the output of rice farming, and the income as well as the profit from rice farming by employing an ex-post non-experimental data in Sierra Leone. It was established that participating in farmers’ training program increased the possibility of adoption of the improved farming activities that were implemented in the study area. Through the training program also, the proceeds from rice production was also established to have increased considerably. These results were in line with the assumption that one of the main constraints on the growth in agricultural output particularly rice cultivation in most African states is the lack of efficient extension programs.
Abstract: This paper presents a Neural Network (NN) identification of icing parameters in an A340 aircraft and a reconfiguration technique to keep the A/C performance close to the performance prior to icing. Five aircraft parameters are assumed to be considerably affected by icing. The off-line training for identifying the clear and iced dynamics is based on the Levenberg-Marquard Backpropagation algorithm. The icing parameters are located in the system matrix. The physical locations of the icing are assumed at the right and left wings. The reconfiguration is based on the technique known as the control mixer approach or pseudo inverse technique. This technique generates the new control input vector such that the A/C dynamics is not much affected by icing. In the simulations, the longitudinal and lateral dynamics of an Airbus A340 aircraft model are considered, and the stability derivatives affected by icing are identified. The simulation results show the successful NN identification of the icing parameters and the reconfigured flight dynamics having the similar performance before the icing. In other words, the destabilizing icing affect is compensated.
Abstract: Heart disease (HD) is a major cause of morbidity and mortality in the modern society. Medical diagnosis is an important but complicated task that should be performed accurately and efficiently and its automation would be very useful. All doctors are unfortunately not equally skilled in every sub specialty and they are in many places a scarce resource. A system for automated medical diagnosis would enhance medical care and reduce costs. In this paper, a new approach based on coactive neuro-fuzzy inference system (CANFIS) was presented for prediction of heart disease. The proposed CANFIS model combined the neural network adaptive capabilities and the fuzzy logic qualitative approach which is then integrated with genetic algorithm to diagnose the presence of the disease. The performances of the CANFIS model were evaluated in terms of training performances and classification accuracies and the results showed that the proposed CANFIS model has great potential in predicting the heart disease.
Abstract: Many factors affect the success of Machine Learning
(ML) on a given task. The representation and quality of the instance
data is first and foremost. If there is much irrelevant and redundant
information present or noisy and unreliable data, then knowledge
discovery during the training phase is more difficult. It is well known
that data preparation and filtering steps take considerable amount of
processing time in ML problems. Data pre-processing includes data
cleaning, normalization, transformation, feature extraction and
selection, etc. The product of data pre-processing is the final training
set. It would be nice if a single sequence of data pre-processing
algorithms had the best performance for each data set but this is not
happened. Thus, we present the most well know algorithms for each
step of data pre-processing so that one achieves the best performance
for their data set.
Abstract: This paper proposes an efficient learning method for the layered neural networks based on the selection of training data and input characteristics of an output layer unit. Comparing to recent neural networks; pulse neural networks, quantum neuro computation, etc, the multilayer network is widely used due to its simple structure. When learning objects are complicated, the problems, such as unsuccessful learning or a significant time required in learning, remain unsolved. Focusing on the input data during the learning stage, we undertook an experiment to identify the data that makes large errors and interferes with the learning process. Our method devides the learning process into several stages. In general, input characteristics to an output layer unit show oscillation during learning process for complicated problems. The multi-stage learning method proposes by the authors for the function approximation problems of classifying learning data in a phased manner, focusing on their learnabilities prior to learning in the multi layered neural network, and demonstrates validity of the multi-stage learning method. Specifically, this paper verifies by computer experiments that both of learning accuracy and learning time are improved of the BP method as a learning rule of the multi-stage learning method. In learning, oscillatory phenomena of a learning curve serve an important role in learning performance. The authors also discuss the occurrence mechanisms of oscillatory phenomena in learning. Furthermore, the authors discuss the reasons that errors of some data remain large value even after learning, observing behaviors during learning.
Abstract: This work deals with aspects of support vector learning for large-scale data mining tasks. Based on a decomposition algorithm that can be run in serial and parallel mode we introduce a data transformation that allows for the usage of an expensive generalized kernel without additional costs. In order to speed up the decomposition algorithm we analyze the problem of working set selection for large data sets and analyze the influence of the working set sizes onto the scalability of the parallel decomposition scheme. Our modifications and settings lead to improvement of support vector learning performance and thus allow using extensive parameter search methods to optimize classification accuracy.
Abstract: This paper proposes a neural network weights and
topology optimization using genetic evolution and the
backpropagation training algorithm. The proposed crossover and
mutation operators aims to adapt the networks architectures and
weights during the evolution process. Through a specific inheritance
procedure, the weights are transmitted from the parents to their
offsprings, which allows re-exploitation of the already trained
networks and hence the acceleration of the global convergence of the
algorithm. In the preprocessing phase, a new feature extraction
method is proposed based on Legendre moments with the Maximum
entropy principle MEP as a selection criterion. This allows a global
search space reduction in the design of the networks. The proposed
method has been applied and tested on the well known MNIST
database of handwritten digits.
Abstract: A collaboration among the Hospital S. Giovanni Battista
of Turin, the Politecnico of Turin, and the MUST company is
described. The content of the collaboration has been and is the use of
ICT-s, e-learning, and blended learning for the internal professional
education, training, and keeping up to date of the personnel of the
hospital. A platform for the delivery of the teaching materials has
been built, including an evaluation and self-evaluation tool. The first
on line courses have been developed and delivered and many more
are in preparation. The first results of the monitoring of the efficacy
of the online education have been positive.