Abstract: Until recently, researchers have developed various
tools and methodologies for effective clinical decision-making.
Among those decisions, chest pain diseases have been one of
important diagnostic issues especially in an emergency department. To
improve the ability of physicians in diagnosis, many researchers have
developed diagnosis intelligence by using machine learning and data
mining. However, most of the conventional methodologies have been
generally based on a single classifier for disease classification and
prediction, which shows moderate performance. This study utilizes an
ensemble strategy to combine multiple different classifiers to help
physicians diagnose chest pain diseases more accurately than ever.
Specifically the ensemble strategy is applied by using the integration
of decision trees, neural networks, and support vector machines. The
ensemble models are applied to real-world emergency data. This study
shows that the performance of the ensemble models is superior to each
of single classifiers.
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: Financial forecasting using machine learning techniques has received great efforts in the last decide . In this ongoing work, we show how machine learning of graphical models will be able to infer a visualized causal interactions between different banks in the Saudi equities market. One important discovery from such learned causal graphs is how companies influence each other and to what extend. In this work, a set of graphical models named Gaussian graphical models with developed ensemble penalized feature selection methods that combine ; filtering method, wrapper method and a regularizer will be shown. A comparison between these different developed ensemble combinations will also be shown. The best ensemble method will be used to infer the causal relationships between banks in Saudi equities market.
Abstract: A novel method of learning complex fuzzy decision regions in the n-dimensional feature space is proposed. Through the fuzzy decision regions, a given pattern's class membership value of every class is determined instead of the conventional crisp class the pattern belongs to. The n-dimensional fuzzy decision region is approximated by union of hyperellipsoids. By explicitly parameterizing these hyperellipsoids, the decision regions are determined by estimating the parameters of each hyperellipsoid.Genetic Algorithm is applied to estimate the parameters of each region component. With the global optimization ability of GA, the learned decision region can be arbitrarily complex.
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 the globalized e-learning environment, students coming from different cultures and countries have different characteristics and require different support designed for their approaches to study and learning styles. This paper explores the ways in which cultural background influences students- approaches to study and learning styles. Participants in the study consisted of 131 eastern students and 54 western students from an Australian university. The students were tested using the Study Process Questionnaire (SPQ) for assessing their approaches to study and the Index of Learning Styles Questionnaire (ILS) for assessing their learning styles. The results of the study led to a set of principles being proposed to guide personalization of e-learning system design on the basis of cultural differences.
Abstract: After the Terengganu state government decided to give a boost in teaching and learning through the allocation of free ebooks to all Primary five and six students; it was time to examine the presence of e-books in the classrooms. A survey was conducted on 101 students to determine how they felt about using the e-book and their experiences. It was discovered that a majority of these students liked using the e-book. However, although they had little problems using the e-book and the e-book helped to lighten the schoolbags, these new-age textbooks were not fully utilized. It is implied that perhaps the school administrators, teachers and students may not be able to overcome the unfamiliar characteristics of the e-book and its limitations.
Abstract: Feature selection has recently been the subject of intensive research in data mining, specially for datasets with a large number of attributes. Recent work has shown that feature selection can have a positive effect on the performance of machine learning algorithms. The success of many learning algorithms in their attempts to construct models of data, hinges on the reliable identification of a small set of highly predictive attributes. The inclusion of irrelevant, redundant and noisy attributes in the model building process phase can result in poor predictive performance and increased computation. In this paper, a novel feature search procedure that utilizes the Ant Colony Optimization (ACO) is presented. The ACO is a metaheuristic inspired by the behavior of real ants in their search for the shortest paths to food sources. It looks for optimal solutions by considering both local heuristics and previous knowledge. When applied to two different classification problems, the proposed algorithm achieved very promising results.
Abstract: An experiment was conducted to examine the effect of the level of performance stabilization on the human adaptability to perceptual-motor perturbation in a complex coincident timing task. Three levels of performance stabilization were established operationally: pre-stabilization, stabilization, and super-stabilization groups. Each group practiced the task until reached its level of stabilization in a constant sequence of movements and under a constant time constraint before exposure to perturbation. The results clearly showed that performance stabilization is a pre-condition for adaptation. Moreover, variability before reaching stabilization is harmful to adaptation and persistent variability after stabilization is beneficial. Moreover, the behavior of variability is specific to each measure.
Abstract: Result of the study on knowledge management systems in businesses was shown that the most of these businesses provide internet accessibility for their employees in order to study new knowledge via internet, corporate website, electronic mail, and electronic learning system. These business organizations use information technology application for knowledge management because of convenience, time saving, ease of use, accuracy of information and knowledge usefulness. The result indicated prominent improvements for corporate knowledge management systems as the following; 1) administrations must support corporate knowledge management system 2) the goal of corporate knowledge management must be clear 3) corporate culture should facilitate the exchange and sharing of knowledge within the organization 4) cooperation of personnel of all levels must be obtained 5) information technology infrastructure must be provided 6) they must develop the system regularly and constantly.
Abstract: Simulations play a major role in education not only because they provide realistic models with which students can interact to acquire real world experiences, but also because they constitute safe environments in which students can repeat processes without any risk in order to perceive easier concepts and theories. Virtual reality is widely recognized as a significant technological advance that can facilitate learning process through the development of highly realistic 3D simulations supporting immersive and interactive features. The objective of this paper is to analyze the influence of virtual reality-s use in chemistry instruction as well as to present an integrated web-based learning environment for the simulation of chemical experiments. The proposed application constitutes a cost-effective solution for both schools and universities without appropriate infrastructure and a valuable tool for distance learning and life-long education in chemistry. Its educational objectives are the familiarization of students with the equipment of a real chemical laboratory and the execution of virtual volumetric analysis experiments with the active participation of students.
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: Music Information Retrieval (MIR) and modern data mining techniques are applied to identify style markers in midi music for stylometric analysis and author attribution. Over 100 attributes are extracted from a library of 2830 songs then mined using supervised learning data mining techniques. Two attributes are identified that provide high informational gain. These attributes are then used as style markers to predict authorship. Using these style markers the authors are able to correctly distinguish songs written by the Beatles from those that were not with a precision and accuracy of over 98 per cent. The identification of these style markers as well as the architecture for this research provides a foundation for future research in musical stylometry.
Abstract: In the recent past, there has been an increasing interest
in applying evolutionary methods to Knowledge Discovery in
Databases (KDD) and a number of successful applications of Genetic
Algorithms (GA) and Genetic Programming (GP) to KDD have been
demonstrated. The most predominant representation of the
discovered knowledge is the standard Production Rules (PRs) in the
form If P Then D. The PRs, however, are unable to handle
exceptions and do not exhibit variable precision. The Censored
Production Rules (CPRs), an extension of PRs, were proposed by
Michalski & Winston that exhibit variable precision and supports an
efficient mechanism for handling exceptions. A CPR is an
augmented production rule of the form:
If P Then D Unless C, where C (Censor) is an exception to the rule.
Such rules are employed in situations, in which the conditional
statement 'If P Then D' holds frequently and the assertion C holds
rarely. By using a rule of this type we are free to ignore the exception
conditions, when the resources needed to establish its presence are
tight or there is simply no information available as to whether it
holds or not. Thus, the 'If P Then D' part of the CPR expresses
important information, while the Unless C part acts only as a switch
and changes the polarity of D to ~D.
This paper presents a classification algorithm based on evolutionary
approach that discovers comprehensible rules with exceptions in the
form of CPRs.
The proposed approach has flexible chromosome encoding, where
each chromosome corresponds to a CPR. Appropriate genetic
operators are suggested and a fitness function is proposed that
incorporates the basic constraints on CPRs. Experimental results are
presented to demonstrate the performance of the proposed algorithm.
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: The paper discusses the results obtained to predict
reinforcement in singly reinforced beam using Neural Net (NN),
Support Vector Machines (SVM-s) and Tree Based Models. Major
advantage of SVM-s over NN is of minimizing a bound on the
generalization error of model rather than minimizing a bound on
mean square error over the data set as done in NN. Tree Based
approach divides the problem into a small number of sub problems to
reach at a conclusion. Number of data was created for different
parameters of beam to calculate the reinforcement using limit state
method for creation of models and validation. The results from this
study suggest a remarkably good performance of tree based and
SVM-s models. Further, this study found that these two techniques
work well and even better than Neural Network methods. A
comparison of predicted values with actual values suggests a very
good correlation coefficient with all four techniques.
Abstract: The key to the continued success of ANN depends, considerably,
on the use of hybrid structures implemented on cooperative
frame-works. Hybrid architectures provide the ability to the ANN
to validate heterogeneous learning paradigms. This work describes
the implementation of a set of Distributed and Hybrid ANN models
for Character Recognition applied to Anglo-Assamese scripts. The
objective is to describe the effectiveness of Hybrid ANN setups as
innovative means of neural learning for an application like multilingual
handwritten character and numeral recognition.
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: A new method of adaptation in a partially integrated learning environment that includes electronic textbook (ET) and integrated tutoring system (ITS) is described. The algorithm of adaptation is described in detail. It includes: establishment of Interconnections of operations and concepts; estimate of the concept mastering level (for all concepts); estimate of student-s non-mastering level on the current learning step of information on each page of ET; creation of a rank-order list of links to the e-manual pages containing information that require repeated work.
Abstract: This paper proposes a Web service and serviceoriented
architecture (SOA) for a computer-adaptive testing (CAT)
process on e-learning systems. The proposed architecture is
developed to solve an interoperability problem of the CAT process by
using Web service. The proposed SOA and Web service define all
services needed for the interactions between systems in order to
deliver items and essential data from Web service to the CAT Webbased
application. These services are implemented in a XML-based
architecture, platform independence and interoperability between the
Web service and CAT Web-based applications.