|
|
|
Issue
1, Volume 5, January 2008
Title of the Paper: Application
of Image Processing to Measure
Road Distresses
DOWNLOAD
FULL PDF
Authors: Maher I.
Rajab, Mohammad H. Alawi, Mohammed A. Saif
Abstract: Pavements usually experience different types of distresses due to
repeated traffic loads, aggressive environmental conditions, construction
materials, soil condition of the underline subgrade, and the method of
construction. Longitudinal and transverse cracking, potholes, rutting, and
bleeding are common examples of such distresses associated with flexible
pavements. As time progresses, the severity of these distresses increases and
consequently, ride quality is adversely affected. Early detection and
measurement of the extent of distresses coupled with prompt reactive measures
are necessary to keep the pavement function at an acceptable level.
Traditional methods for distress detection and measurement are laborious,
time consuming, and subject the involved personnel to accidents. In contrast,
image measurement methods are effortless, safe, and can be performed in a
short time. This research paper performs image processing measurements to
estimate areas of a pothole and alligator cracking, and sets a program for
plane measurements of an area that experience rutting. The image measurements
are compared with the traditional measurements. The results show that image
measurements are close to those obtained by using the traditional methods.
Keywords:
Pavement surface cracking, road distresses, alligator cracking, rutting,
image measurements.
Title of the Paper: A
Design and Implementation of a Web Server Log File Analyzer
DOWNLOAD
FULL PDF
Authors: Yu-Hsin Cheng,
Chien-Hung Huang
Abstract: More and more enterprises use network to communicate with the
suppliers or the customers, and also in receiving order forms, data
transmission, produces goods, stock warehousing in all enterprise management
procedure, carry on to the e-movement and enterprise competitive ability,
this act not only may save the production cost, moreover may fast reflect the
correlation information. But the enterprise owners or the website
administrators often cannot judge precisely whether their commercial websites
play the leading role in marketing function. In the settlement of this
problem, an intelligent website analysis software can often provide good and
effective assistance to business owners or website administrators, and then
improve the marketing results of the websites. The website analysis software
usually uses the log files in the system to produce statistical-related data,
and then obtains the useful information through the analysis. In this paper,
we discuss the implementation of an enterprise website analysis software we
have developed, and by the modification and the expansion the Analog from
free software to analyze the log files in the Apache web server, provides
more important information about visitors. We provide a user friendly
interface in the system for the enterprise administrators to accumulate the
important information of log files, in establishing the system, we add on
functions which detect illegal information, make the protective action, and provide
the dynamic E-Mail report function to the user.
Keywords: log file, web
server, website analysis, Configuration Interface Subsystem, Illegal
Information Detection Subsystem, Report Delivery Subsystem
Title of the Paper: Batu
Aceh Typology Identification Using Back Propagation Algorithm
DOWNLOAD
FULL PDF
Authors: Azlinah
Mohamed, Faizatul Huda Bt Mat, Sofianita Mutalib,Shuzlina Abdul Rahman, Noor
Habibah Arshad
Abstract: Historical and cultural artifacts have defined the existence of
humankind all over the world. It is therefore important to preserve this
heritage for future endeavors. In the Malay-Indonesia Archipelago, the
forgotten and extinct artifact is the Islamic gravestone that originated in
Aceh known as Batu Aceh. This research is an attempt to preserve our heritage
by developing a prototype to guide the future generation to appreciate these
precious cultural heritage artifacts. Back propagation algorithm is applied
on a supervised classification of Batu Aceh object images. Several images of
each type of Batu Aceh are used as training samples. Data samples were
converted into binary forms and used to train the network. To ensure the
performance of the system, network parameters such as momentum value,
learning rate and number of hidden neuron would be adjusted to get the
appropriate setting. It is found that the prototype devised can identify the
type of Batu Aceh presented and its century. This research would provide
experts in this field an alternative to identify damaged or unclear images of
Batu Aceh.
Keywords:
Artificial Neural Network, Back Propagation, Batu Aceh, Image Processing,
Image Classification and Pattern Recognition.
Title of the Paper: A
Neuro-Fuzzy Model for Function Point Calibration
DOWNLOAD
FULL PDF
Authors: Wei Xia, Luiz
Fernando Capretz, Danny Ho
Abstract: The need to update the calibration of Function Point (FP)
complexity weights is discussed, whose aims are to fit specific software
application, to reflect software industry trend, and to improve cost
estimation. Neuro-Fuzzy is a technique that incorporates the learning ability
from neural network and the ability to capture human knowledge from fuzzy
logic. The empirical validation using ISBSG data repository Release 8 shows a
22% improvement in software effort estimation after calibration using
Neuro-Fuzzy technique.
Keywords:
neuro-fuzzy, neural networks, fuzzy logic, software cost estimation.
Title of the Paper:
Applications of Fuzzy Theory on Health Care: An Example of Depression
Disorder Classification Based on FCM
DOWNLOAD
FULL PDF
Authors: Sen-Chi Yu,
Yuan-Horng Lin
Abstract: The purpose of this study is to apply fuzzy theory on health care. To
achieve this goal, Beck Depression Inventory (BDI)-II was adopted as the
instrument and outpatients of a psychiatric clinic were recruited as samples
and undergraduates as non-clinical sample as well. To elicit the membership
degree, we asked the subjects are free to choose more than one alternative
for each item listed in BDI and, in turn, assign percentages on the chosen
alternatives. Moreover, the sum of percentages of the chosen categories is
restricted to 100%.We performed the possibility- based (fuzzy c-means, FCM)
and probability-based classification (Wald’s method and k-means) to
classification of severity of depression. The scoring of BDI of subjects were
analyzed by clustering analysis while the diagnose of depression-severity by
a psychiatrist was used as the criterion to evaluate classification accuracy.
The percentage of correct classification among FCM, Wald’s method and k-means
were compared. The analytical results show the Kendall's
τ coefficient of FCM, Wald’s method and k-means were .549, .316, and
.395, respectively. That is, FCM exhibited a higher association between the
original and classified membership than did Wald’s and k-means methods. We
concluded that FCM identified the data structure more accurately than the two
crisp clustering methods. It is also suggested that considerable cost
concerning prevention and cure of depression might be reduced via FCM.
Keywords: fuzzy c-means,
depression, fuzzy logic, psychological assessment.
Issue
2, Volume 5, February 2008
Title of the Paper: A
Detecting Peak’s Number Technique for Multimodal
Function Optimization
DOWNLOAD
FULL PDF
Authors: Qiang Hua, Bin
Wu, Hao Tian
Abstract: A Detecting Peak's Number (DPN) technique is proposed for
multimodal optimization. In DPN technique, we want to know the peak’s number
of locally multimodal domain of every individual, firstly we use the idea of
orthogonal intersection for getting the exploration direction in every
locally multimodal domain, and then we attempt to detect peak’s number in
every one-dimension direction as the result of detecting of locally
multimodal domain. At last we design an evolution algorithm (DPNA) based on
the characters of DNP technique, which contain four characters: niching,
variable population, variable radius and life time, and then give a series of
experiment results which show the effectiveness of algorithm, as the DPNA is
not only adapting to obtaining multiple optima or suboptima, but also
effective for problem of ill-scaled and locally multimodal domain described
in [11].
Keywords:
Evolution Algorithm; Multimodal Function Optimization; Niching; Detecting
Peak's Number
Title of the Paper:
Context-Dependent Extensible Syntax-Oriented Verifier
with Recursive Verification
DOWNLOAD
FULL PDF
Authors: Nhor Sok Lang,
Takao Shimomura, Quan Liang Chen, Kenji Ikeda
Abstract: In order to develop Web applications of high quality, it is
important to apply efficient frameworks to standardize the process of
development in projects, or apply useful design patterns to produce the program
code that can easily be enhanced. However, it is not enough. In addition to
these efforts, we have to check the programs to see whether they keep various
kinds of rules such as verification items for security which are common for
all kinds of Web applications, and verification items for coding styles or
code conventions which are pertain to each project. This paper proposes a
verification method for the syntax-oriented verifier, and describes the
implementation of its prototype system, SyntaxVerifier. SyntaxVerifier makes
it possible to detect syntactical objects based on their syntactic contexts.
It realizes a recursive verification which makes it easy to dynamically trace
a syntax tree in a verification process itself.
Keywords:
Customaizable, Extensible, Recursive, Syntax analysis, Verification
Title of the Paper:
Context-Dependent Extensible Syntax-Oriented Verifier
with Recursive Verification
DOWNLOAD
FULL PDF
Authors: Nhor Sok Lang,
Takao Shimomura, Quan Liang Chen, Kenji Ikeda
Abstract: In order to develop Web applications of high quality, it is
important to apply efficient frameworks to standardize the process of
development in projects, or apply useful design patterns to produce the
program code that can easily be enhanced. However, it is not enough. In
addition to these efforts, we have to check the programs to see whether they
keep various kinds of rules such as verification items for security which are
common for all kinds of Web applications, and verification items for coding
styles or code conventions which are pertain to each project. This paper
proposes a verification method for the syntax-oriented verifier, and
describes the implementation of its prototype system, SyntaxVerifier.
SyntaxVerifier makes it possible to detect syntactical objects based on their
syntactic contexts. It realizes a recursive verification which makes it easy
to dynamically trace a syntax tree in a verification process itself.
Keywords:
Customaizable, Extensible, Recursive, Syntax analysis, Verification
Title of the Paper:
Stroke Order Computer-based Assessment with Fuzzy Measure Scoring
DOWNLOAD
FULL PDF
Authors: Guey-Shya Chen,
Yu-Du Jheng, Hsu-Chan Yao,
Hsiang-Chuan Liu
Abstract: The purpose of this research is to develop a computer-based
assessment for stroke order and a novel algorithm based on Choquet integral
with fuzzy measure for scoring stroke order of Chinese Character writing. The
learning of stroke order is very important for a fixed stroke writing
character system therefore this research based on the theory of “five
indexing system of Chinese characters” and combine the features of strokes
develops a stroke order assessment system to real-time evaluate learners’
stroke order and score their character writings. Except using traditional
additive scoring method, a non-additive scoring algorithm based on Choquet
integral with λ-measure and L-measure was proposed. A real data set with
121 samples was examined and experiment results show that the performances of
this novel scoring model based on Choquet integral with both λL-measure
and -measure outperform the performance of traditional scoring approach.
Keywords:
stroke order, computer-based assessment, five indexing systems of Chinese
characters, λL-measure, -measure, Choquet integral
Title of the Paper:
Analysis of Neural Network Edge Pattern Detectors in Terms of Domain
Functions
DOWNLOAD
FULL PDF
Authors: Maher I.
Rajab and khalid A. Al-Hindi
Abstract: This paper investigates the analysis of feed-forward BP neural
network that has been trained to detect noisy edge patterns, so as to achieve
close insight into their internal functionality. The analysis of neural network
edge detector’s hidden units, as templates, were analysed into three gradient
components: low pass or averaging, gradient, and second-order gradients. The
weights between NNets hidden units and their output units represent the
importance of the hidden unit’s edge detection outcome. To this purpose, the
elements of the NNets, that have been trained to detect prototype noisy edge
patterns with various angle of operation, were analysed in terms of domain
functions. The results show that the NNets analysis using the domain
functions method could confirms the results of NNets recognition accuracies.
Although the work presented only gives some analysis results for the units in
the NNets hidden units, it should be clear that a characterization of the
neural network as a whole could also be derived from these results.
Keywords:
Neural networks analysis, domain functions, BP, recognition accuracy,
domain-specific base functions, Taylor
series coefficients.
Title of the Paper:
Using System Dynamics for Managing Risks in Information Systems
DOWNLOAD
FULL PDF
Authors: Denis
Trček
Abstract: Each and every security oriented activity in information systems
has to start with the basics, which is risk management. Although risk
management is a well established and known discipline in many other areas,
its direct translation to information systems is not an easy and
straightforward because of specifics of contemporary information systems.
Among these specifics there are the global connectivity of information
systems, the large number of elements (e.g. thousands of software
components), strong involvement of human factor, almost endless possible ways
of interactions, etc. Thus a new methodological approach is presented in this
paper that is based on business dynamics. It enables effective addressing of
the above-mentioned elements, and through this it supports and improves
decision making in information systems security.
Keywords:
information systems, security, risk management methodologies, system
dynamics, simulations, reference models.
Title of the Paper:
Contrast Enhancement and Clustering Segmentation of Gray Level Images with
Quantitative Information Evaluation
DOWNLOAD
FULL PDF
Authors: Zhengmao Ye, Habib
Mohamadian, Su-Seng Pang, Sitharama Iyengar
Abstract: Improper illumination and medium dispersing could occur in quite
some gray level image collecting processes. Contrast enhancement and
clustering segmentation are two effective approaches for the related pattern
recognition problems. Image enhancement and image segmentation can be applied
to different areas of science and engineering, such as biometric
identification, national defense and resource exploration. Thus, adaptive
image enhancement can be implemented to improve the image quality and to
reduce random noise simultaneously, which is used to adapt to the intensity
distribution within an image. Nonlinear K-means clustering can be applied for
image segmentation, which is to classify an image into parts which have
strong correlations with objects in order to reflect the actual information
being collected. For example, it can be used against the effects from
unevenly distributed pressure or temperature condition under atmosphere
medium and water medium. To evaluate the actual roles of image enhancement
and image segmentation, some quantity measures should be taken into account.
In this study, a set of quantitative measures is proposed to evaluate the
information flow of gray level image processing. Concepts of the gray level
energy, discrete entropy, relative entropy and mutual information are
proposed to measure outcomes of the adaptive image enhancement and K-means
image clustering.
Keywords:
Contrast Enhancement, K-Means Segmentation, Gray Level Image, Energy,
Entropy, Relative Entropy, Mutual Information
Title of the Paper: A
Case Study of Usability Testing – the SUMI Evaluation Approach of the
EducaNext Portal
DOWNLOAD
FULL PDF
Authors: Tanja Arh,
Borka Jerman Blažič
Abstract: The new challenge for designers and Human–computer interaction
(HCI) researchers is to develop software tools and applications for effective
e-learning. Software usability is one aspect of Human–computer interaction
that can benefit from knowledge of the user and their tasks. However, in
practice not much attention is given to this issue during testing. Evaluators
often do not have the knowledge, instruments and/or time available to handle
usability. One set of methods for determining whether an application enables
users to achieve their predetermined goals effectively and efficiently is
usability evaluation with end users. The paper presents the results of
empirical study of usability evaluation which was based on SUMI (Software
Usability Measurement Inventory) questionnaires. The software application
tested was a multilingual educational portal EducaNext.
Keywords:
human computer interaction (HCI), EducaNext educational portal, distance
learning, software usability measurement inventory (SUMI), usability, end
users
Title of the Paper:
Dynamic Backward Scheduling Method for Max-Plus Linear Systems with a
Repetitive, MIMO, FIFO Structure
DOWNLOAD
FULL PDF
Authors: Hiroyuki Goto
and Shiro Masuda
Abstract: This paper proposes a dynamic scheduling method that considers
no-concurrency of resource with a subsequent event. We focus on repetitive
discrete event systems with a MIMO (Multiple Inputs and Multiple
Outputs)-FIFO structure. The behavior of this kind of system can be described
with linear equations in the max-plus algebra, also referred to as MPL
(Max-Plus Linear). Conventional MPL representation formulates no-concurrency
of resource with a previous event and can provide the earliest starting times
in internal facilities. We recently proposed a calculation method for a
single job; however, resource no-concurrency with a subsequent job is not
considered. Thus, it may not give an optimal solution if a large number of
jobs have to be considered simultaneously. Therefore, we derive a general
form of the MPL representation that provides the latest start times
considering no-concurrency with a subsequent event. We also consider an
effective rescheduling method that is applicable in cases in which the system
parameters are changed after the job has commenced.
Keywords:
Repetitive system, state-space representation, max-plus linear system,
earliest/latest time, forward/backward type, rescheduling
Title of the Paper:
Intelligent Support to Specific Design Aspects
DOWNLOAD
FULL PDF
Authors: Urška Sancin,
Jasmin Kaljun, Bojan Dolšak
Abstract: Due to increased rivalry on the market, some specific design
aspects like the use of modern plastics materials, ergonomics and aesthetics
are becoming more important and are not kept in the background any more in
correlation with functionality and economic aspect of the product. Design
engineer faces many dilemmas while designing new products as a single person
is not able to possess a wide spectrum of knowledge needed for optimal design
solutions. At this point designer have to rely on his or her experience and
on the knowledge of the expert team involved in the project. The fundamental
purpose of the research presented in this paper is to make the product
development process less experience dependent. The main goal of thematically
oriented research is to develop intelligent advisory system with integrated
modules for some specific design aspects.
Keywords:
product development, ergonomics, aesthetics, plastics, knowledge based
engineering, intelligent systems
Title of the Paper:
Mining Long High Utility Itemsets in Transaction Databases
DOWNLOAD
FULL PDF
Authors: Guangzhu Yu,
Shihuang Shao and Xianhui Zeng
Abstract: Existing algorithms for utility mining are column enumeration based,
adopt an Apriori-like candidate set generation-and-test approach, and thus
are inadequate on datasets with high dimensions or long patterns. To solve
the problem, this paper proposes a hybrid model and a row enumeration based
algorithm, i.e., inter-transaction, to discover high utility itemsets from
two directions: existing algorithms such as UMining [1] can be used to seek
short high utility itemsets from the bottom, while inter-transaction seeks
long high utility itemsets from the top. By intersecting relevant
transactions, the new algorithm can identify long high utility itemsets
directly, without extending short itemsets step by step. In addition, new
pruning strategies are used to cut down search space; optimization technique
is adopted to improve the performance of the intersection of transactions.
Experiments on synthetic data show that our method achieves high performance,
especially in large high dimensional datasets.
Keywords:
long high utility itemset; hybrid mode; utility; intersection transaction;
row enumeration
Issue 3, Volume 5, March 2008
Title of the Paper: An
Interactive Web-Based Wedding Planner with Comparative Analysis Decision
Support System
DOWNLOAD
FULL PDF
Authors: L. Y. Por, R.
F. Boey, T. F. Ang and C. S. Liew
Abstract: Preparing for weddings is always tedious, especially when it does
not involve hired help. Long checklists await soon-to-be brides and grooms
before their auspicious wedding ceremony. Without experienced assistance,
these brides and grooms face frustrating situations in hunting for suitable
bridal products and services. This work presents an ideal one stop solution,
called the Wedding Arch, for the brides and grooms to retrieve information on
available bridal products and services in the shortest possible time. This
web based wedding planner provides a platform for brides and grooms to
acquire information on bridal products and services, as well as information
of vendors registered with Wedding Arch and make wedding planning
reservations online with the simple click of a mouse. Thus, the long and
tedious task of information gathering has been shortened and made more
convenient. Most importantly, Wedding Arch also functions as a web based
comparative analysis decision support system that allows the brides and
grooms to subscribe to a service that will assist them in the process of
wedding planning and preparations. The system assists brides and grooms in
making decisions based on their preferences and budget while taking in
updated and current market pricings for their desired bridal products and
services.
Keywords:
Wedding Arch, Wedding planner, Decision support system (DSS), Budget planning
and Web-based.
Title of the Paper:
FAQ-master: An Ontological Multi-Agent System for Web FAQ Services
DOWNLOAD
FULL PDF
Authors: Sheng-Yuan Yang
Chun-Liang Hsu Dong-Liang Lee Lawrence Y. Deng
Abstract: This paper expresses the results of our research in developing a
multi-agent system: FAQ-master as an intelligent Web information integration
system based upon intelligent retrieval, filtering, integration, and ranking
capabilities in order to provide highquality FAQ answers from the Web to meet
the user information request. We are describing FAQ-master, discussing how it
improves FAQ query quality from the following three aspects of Web search
activities at the same time: user intention, document content processing, and
website search. The system is implemented as four agents working together
through an ontology-supported content base. Techniques involved in the design
include domain ontology, ontology-supported user query processing,
ontology-supported solution caching, ontology-directed FAQ wrapping, storage,
retrieval and ranking, and ontology-supported website classification and
expansion.
Keywords:
Ontology, User Modeling, Proxy Mechanism, Website Modeling, Multi-Agent
Systems.
Title of the Paper:
Online and Post-processing of AVL Data in Public Bus Transportation System
DOWNLOAD
FULL PDF
Authors: Dejan
Rančić, Bratislav Predić, Vladan Mihajlović
Abstract: For a number of years vehicle fleet tracking systems are in use in
companies operating large number of vehicles in the field. Proliferation of
cheap and compact GPS receivers had the effect that Automatic Vehicle
Location (AVL) systems today almost exclusively use satellite based locating
systems. This paper presents characteristics of realized system tracking and
analyzing city bus transit traffic in the city of Niš. Since the described system also uses
GPS for vehicle location, initially, data about vehicles’ locations acquired
from AVL subsystem need to be transformed into form that is adequate for
further usage in the system, analysis and prediction. Also, city bus transit
tracking systems are specific concerning functionalities differing them from
other vehicle fleet tracking systems. These specifics include cyclic vehicle
routes, the need for specific performance reports etc. This paper
specifically deals with vehicle motion prediction with on station arrival
time estimation coupled with automatic report generation.
Keywords:
Automatic Vehicle Location (AVL), Prediction of arrival times, Continuous
query processing, Information services, Intelligent transportation systems
(ITS), line matching
Title of the Paper:
Questionnaire-based Evaluation of Characteristics of a Community in SNS
DOWNLOAD
FULL PDF
Authors: Susumu
Takeuchi, Masanori Akiyoshi, Norihisa Komoda
Abstract: Currently, SNSes (Social Networking Services) are widely available
on the Internet. In a SNS, users can communicate with the users who have a
similar interest in a community. To activate communications drastically in
SNS, users are encouraged to join other dissimilar communities. In this
paper, utilizing activities of communities and relationships with communities
is proposed to realize a dissimilar community recommendation. However, such
communities tend to be useless for the users, so that investigating
characteristics of communities that are selected by the methods is necessary
to recommend. By utilizing real data in the largest SNS in Japan, the correlations between
the users’ subjective judgments and the characteristics of communities are
evaluated. As a result, it is clarified that effective recommendation of
dissimilar communities will be possible by integrating activities of
communities and relationships with communities.
Keywords:
SNS, Social network, Interpersonal communication, Activation, Community,
Recommendation
Title of the Paper: An
Extraction of Emotion in Human Speech Using Speech Synthesize and Classifiers
for Each Emotion
DOWNLOAD
FULL PDF
Authors: Masaki
Kurematsu, Jun Hakura, Hamido Fujita
Abstract: The typical method of estimation of emotion in speech has the 3
steps. First, researchers collect a lot of human speech. Next, researchers
get speech features from human speech using frequency analysis and calculate
the statistical value of them. Finally they make a classifier from the
statistical value using a learning algorithm. Most researchers consider the
collection of human speech, feature selection and learning algorithm to
increase the validity of estimation. But the validity of estimation is not
high. In this paper, we propose the 3 new methods to enhance the typical
method of estimation of emotion in speech. First method is that we use
synthetic speech to make a classifier. Second method is that we use not only
mean and maximum but also Standard Deviation (SD), skewness and kurtosis to
make a classifier. Third method is that we use the classifier for each
emotion. In order to evaluate our approach, we did experiments. Experimental
results show the possibility in which our approach is effective for improving
the former method.
Keywords:
Emotion, Speech Synthesize, Regression Tree, Linear Discriminant Analysis,
Extraction of Emotion in Speech
Title of the Paper:
Prototype of Knowledge Management System in Chinese Offshore Software
Development Company
DOWNLOAD
FULL PDF
Authors: Li Cai, Zuoqi
Wang, Yufeng Jiao, Masanori Akiyoshi, Norihisa Komoda
Abstract: This paper illustrates preliminary design and evaluation of a
knowledge managing system in Chinese offshore software development company.
The major features of the knowledge management system are a BBS style Q&A
function, a management of Q&A results based on domain knowledge, an
association retrieval function for coping with grammatical ambiguity
including in the queries, and a display of Q&A texts on the plain for grasping
the general distribution of knowledge and problems. The prototype system has
developed using JAVA and .Net Frameworks, and has used in-house. Through the
trial use in-house, not only the advantage but also several improvement
problems are clarified.
Keywords:
knowledge management, question and answer system, association retrieval
Title of the Paper:
Decision Making With Textual and Spatial Information
DOWNLOAD
FULL PDF
Authors: Hana Kopackova,
Jitka Komarkova, Pavel Sedlak
Abstract: The aim of the paper is to show the way how textual and spatial
information can be used in decision making process. Structured information
represents only 10 % of available information. Despite of this fact managers
mostly rely on this type of information. Due to their marginalization in
decision making practice, we focused on textual and spatial information in
this article. Four case studies clearly illustrate usage of these types of
information on practical examples.
Keywords:
Decision Making, Information, Text Categorization, Clustering, GIS.
Title of the Paper:
Application of Social Relation Graphs for Early Detection of Transient
Spammers
DOWNLOAD
FULL PDF
Authors: Radoslaw
Brendel and Henryk Krawczyk
Abstract: Early detection of social threats and anomalies is a real challenge
in today’s dynamic societies. The people form many complex social relations
that can be shown by various types of graphs in which the nodes would
represent the subjects (individuals or groups of people) and the links would
indicate specific relations between them. The analysis of these constantly
changing relations can point out specific social threats that are imminent.
Observing the tendency of changes in the social relation graphs, such threats
can be early detected and adequate preventative steps can be taken. In the
paper we present how this approach can be efficiently used to early detect
imminent threats of spam to a local e-mail society and isolate groups of
spammers before their messages reach the users inboxes.
Keywords:
social graphs, imminent threats, graph patterns, spam detection, security
Title of the Paper: A
New Method for Enhanced Information Content in Product Model
DOWNLOAD
FULL PDF
Authors: László Horváth
Abstract: This paper introduces a new method in order to establish a better
communication between engineers and modeling procedures during lifecycle
management of product information in computer based engineering systems. The
proposed method is intended as one of the initial attempts for resolution of
an inherent conflict in product modeling. This conflict is between
information content based thinking of engineer and data based processing in
classical product modeling systems. The author applies a new sector of
product model that describes information content for engineering activities.
This sector controls engineering object data in the second sector for
classical product model entities. In this manner, the new modeling can be
interconnected with existing modeling in industrially applied engineering
systems. Information content is stored in interconnected levels of the
product model for human intent, meaning of concepts, engineering objectives,
contexts, and decisions. This paper explains basic concepts, refers to
research in the related topics, introduces role of humans and human-computer
interactions in the proposed modeling, and details information content based
product modeling. Following this, it emphasizes difficulties of decisions in
case of high number of dependencies amongst engineering objects in large
product models and proposes a new method for change management in those
models. Implementation of the proposed product modeling methods can be
realized in industrial professional modeling systems by using of their
functionality for open architecture.
Keywords:
Product modeling, Lifecycle management of product information, Information
content based product model, Design intent, Product changes, Affect zone of
modified engineering object
Title of the Paper:
Warehouse Redesign to Satisfy Tight Supply Chain Management Constraints
DOWNLOAD
FULL PDF
Authors: Roman Buil,
Miquel Angel Piera
Abstract: The picking process is a critical supply chain component for many
companies. A proper warehouse configuration, storage policy, trays replenishment
policy, and other factors are also important to reduce not only the delivery
time, but also increase productivity while maintaining quality factors at
competitive costs. This paper presents an integrated approach to tackle the
complexity of warehouse redesign under several space and quality factor
constraints. The proposed design methodology integrates warehouse layout
configuration, storage policy, replenishment policy, picking policy, routing
policy and also trays and shelves sizes design. As a result of the proposed
strategy, considerable savings on resource costs (equipment and workers) can
be achieved.
Keywords:
Picking, warehouse, simulation, colored petri nets, logistics, supply chain.
Title of the Paper:
Outcome Based Education Performance Measurement: A Rasch-based Longitudinal
Assessment Model to measure Information Management Courses LO’s
DOWNLOAD
FULL PDF
Authors: Azlinah
Mohamed, Azrilah Abd.Aziz, Abd.Rahman Ahlan Sohaimi Zakaria and Mohdsaidfudin
Masodi
Abstract: Malaysia Qualification Framework, 2005 (MQF) promotes outcome based
education (OBE) learning process. OBE calls for the evaluation of the
course’s Learning Outcomes (CLO) as specified in the Program Specification.
This good practice is implemented in the Faculty of Information Technology
and Quantitative Science, Universiti Teknologi MARA (FTMSK) teaching and
learning processes which was duly certified to ISO 9001:2000. Assessment
methods include giving students’ tasks such as tests, quizzes or assignments
at intervals during the 14 weeks study period per semester. CLO’s were
evaluated based on the students’ performance which gives an indication of
their learning achievements. Despite the marks obtained is orderly in manner,
it is on a continuum scale. Hence, further evaluation using the raw score is
rather complex to be carried out. This paper describes a Rasch-based
measurement model as performance assessment tool to measure the CLO. Rasch
Model uses ‘logit’ as the measurement unit thus transforms the assessment
results into a linear correlation. An overview of the measurement model and
its key concepts were presented and illustrated. An assessment form using
Bloom’s Taxonomy as parameter was designed showing each dimension of the
ability to be measured. The results there from were evaluated on how well it
relates to the attributes being assessed and scrutinized. It is further
checked against the CLO Maps for consistency and used as a guide for future
improvement of the teaching method and style. This provides the lecturers a
more accurate insight of the student level of competency achieved. The study
shows that this model of measurement can classify students’ grades into
linear competency scale accurately using only very few primary data sets to
enable corrective action to be taken effectively at the early stage of
learning.
Keywords:
Learning Outcomes, performance assessment, evaluation, competency, Bloom’s
Taxonomy, quality.
Title of the Paper:
Testing Cognitive Characteristics of Users in Interaction with Computer
DOWNLOAD
FULL PDF
Authors: Nebojša
Đorđević, Dejan Rančić
Abstract: This paper presents some new research results on Human Computer
Interaction (HCI) methodologies. We present an extension of cognitive model
for HCI - (XUAN/t), based on decomposition of user dialogue into elementary
actions (GOMS). Using this model, descriptions of elementary (sensor,
cognitive and motor) actions performed by user and system are introduced
sequentially, as they will happen. Based on the described model and
psychometric concepts, we developed software CASE tool for testing cognitive
as well as psychomotor abilities of a user in HCI. Software tool arranges
tests into test groups for psychosensomotor and memory capabilities. User
test results are persistently stored in a database and available for further
statistical analysis. The main research goal was suitability verification of
different HCI techniques for special user groups. Case study was performed
and numerical results verifying the proposed model are presented in the
paper.
Keywords:
HCI, User interface, Cognitive models, HCI testing tool, User profile.
Title of the Paper:
PIRR: a Methodology for Distributed Network Management in Mobile
Networks
DOWNLOAD
FULL PDF
Authors: Filippo Neri
Abstract: The current centralized Network Management approach in mobile
networks may lead to problems with being able to scale up when new customer
services and network nodes will be deployed in the network. The next
generation mobile networks proposed by 3rd Generation Partnership Project
(3GPP) envision a flat network architecture comprising some thousands of
network nodes, each of which will need to be managed, in a timely and efficient
fashion. This consideration has prompted a research activity to find
alternative application architectures that could overcome the limits of the
current centralized approaches. section approach to deal with the increasing
network size and complexity is to move from a centralized Network Management
system to a more distributed or decentralized approach where each Network
Management application consists of a controller part and a set of distributed
parts running on the individual network elements. This approach however
raises questions of how to measure and estimate the resource requirements
when planning to distribute the Network Management applications in the mobile
networks before starting to produce commercial systems. In this paper, we
describe the PIRR methodology we have developed to measure resource
requirements for distributed applications in mobile networks and the
experimental findings of its application to new Network Management
applications.
Keywords:
Software Agents, JADE, Telecom network management system, distributed
simulation systems, 3G cellular system.
Title of the Paper: A
Hierarchical Relevance Feedback Algorithm for Improving the Precision of
Virtual Tutoring Assistant Systems
DOWNLOAD
FULL PDF
Authors: Ji-Wei Wu and
Judy C.R. Tseng
Abstract: In recent years, several virtual tutoring assistant systems had
been proposed based on question-answering systems. These virtual tutoring
assistant systems are very helpful for the students to get instant helps when
the teachers are not available. Pedagogic scholars think that when a student
is stuck on a certain problem while learning, an instant tutoring assistant
is very helpful to promote his/her study. Therefore, the qualities
(precision) of the answers of virtual tutoring assistant systems are very
important. It determines the effectiveness of these systems. In practices,
some students are suffered from not being able to properly express their
need; some may not even know exactly what information they need. As a result,
some problems do not match any existing solutions, even if they do contain
some clues for finding solutions. That makes the effectiveness of the virtual
tutoring assistant systems not being acceptable. In the literatures,
researchers found that relevance feedback information are quite useful for
information retrieval systems to improve their effectiveness. Among them, the
Rocchio’s Relevance Feedback (RRF) algorithm is the most well-known and have
been employed in several information retrieval systems. In this paper, we
proposed a novel pseudo relevance feedback algorithm, called Hierarchical
Relevance Feedback (HRF) algorithm. The HRF algorithm is used for improving
the precision of virtual tutoring assistant systems. After a query is
submitted by some student, the new virtual tutoring assistant system will
automatically modify the student’s query according to the HRF algorithm and
re-submit it to the system. Experimental results showed that the
effectiveness of the system is improved by automatically modifying user’s
query using the HRF algorithm. Moreover, the HRF algorithm is also
outperformed the famous RRF algorithm.
Keywords:
E-learning, Tutoring assistant, Information Retrieval, Question-answering,
Relevance feedback
Issue 4, Volume 5, April 2008
Title of the Paper:
Analysis of the Potential for Nearly Circular Slope Failure Using On-site
Survey Information with Adverse Calculation
DOWNLOAD
FULL PDF
Authors: Tienfuan Kerh,
Y.M. Wang And H.C. Tsai
Abstract: Slope stability analysis is crucial for decreasing unwanted
economical loss at mountain highways which are prone to damage from heavy
rains. The objective of this study is to perform on-site investigation and
adverse calculation of slope damage at a specified road section along Tai-27
highway in Taiwan.
By analysing a total of 38 on-site survey results, it is found that the types
of slope damage may include debris flow (26%), shallow soil layer sliding
(26%), nearly circular sliding (8%), slope oriented sliding (3%), falling
rock (11%), river erosion (13%), and others (13%). Based on available
geological information at three locations with nearly circular slope failure,
the adverse calculations using computer software show that these slopes all failed
at a shallow soil layer. Some of the important soil strength parameters such
as cohesion force and friction angle are estimated, and a critical sliding
surface is predicted for a minimum safety factor. The results provide useful
information for choosing a suitable engineering protection work at these
hazardous locations by the relevant agency.
Keywords:
mountain highway, circular slope failure, adverse calculation, on-site
survey, factor of safety, cohesion force, friction angle, critical sliding
surface
Title of the Paper:
Analysis on the Adaptive Scaffolding Learning Path and the Learning
Performance of e-Learning
DOWNLOAD
FULL PDF
Authors: Chun-Hsiung
Lee, Gwo-Guang Lee ,Yungho Leu
Abstract: Existing instruction websites record learners’ portfolios, they
only collect the browsing time and homepage information, without directly
provide teachers with more data for further analyzing learner behaviors.
Consequently, this investigation uses the learners’ portfolio left in the
e-learning environment, and adopts “data mining” techniques to establish for
each cluster of learners the most adaptive learning path pattern, which can
provide a “scaffolding” to guide each cluster of learners. Using statistical
methods, this investigation analyzes whether the navigational learning map of
“scaffolding learning path (SLP)” can improve learning performance. This
investigation discovers that among the three clusters of learners, the
learners in the experimental group under the two clusters other than
high-score cluster, after taking the “scaffolding learning path” as their
navigational learning map, achieve more significant progress than the
learners of comparative group. This implies that through the “scaffolding
learning path,” the learning performance of most learners can be improved.
Keywords:
E-learning, Learning path, Scaffolding theory, Learning portfolio, Data
mining
Title of the Paper:
Using Integer Programming to Solve the Crew Scheduling Problem in the Taipei
Rapid Transit Corporation
DOWNLOAD
FULL PDF
Authors: Chui-Yen, Chen
Abstract: The transport operation volume has reached millions of people since
the Taipei Rapid Transit Corporation (TRTC) started operating 28 March 1996.
TRTC has become the key public transportation in Taipei city. Crew scheduling of station
employees has become one of the basic costs of operating the Public Rapid
Transit System. During the planning stage of the project, a mathematical
model of planning phases was established and used to find answers to crew
scheduling and reduce costs. In general, the crew scheduling problems relate
to the “set covering” problem or “set partitioning” problem; therefore, it is
often described by the methods of 0-1 Integer Programming. Hence, this study
will adopt the methods of integer programming for mathematical programming to
establish a crew scheduling program. The Target-based formula of using
integer programming to solve the crew shift scheduling problem is meant to
meet the interests of station employees. Furthermore, this study will use
comparison analysis to research (1) common shift scheduling; (2) employee’s
preferred working hours; and (3) specified work day for employees to help
solve day off or other problems. We hope to provide this method to the TRTC
in a rapid and convenient timetable to improve the efficiency of operations
and business competition.
Keywords:
Crew scheduling problem (CSP), 0-1 Integer programming, Taipei Rapid Transit
Corporation (TRTC)
Title of the Paper: Malaysian Smart School
Courseware Usability study: The Effectiveness of Analytical Evaluation
Technique Compared to Empirical Study
DOWNLOAD
FULL PDF
Authors: Azizah Jaafar
Abstract: Usability evaluation methods are used to evaluate the interaction
of the human with the computer for the purpose of identifying aspects of
interaction that could be improved t increase usability. This research was
carried out to determine the effectiveness of analytical evaluation technique
that was designed, developed and named as Jalan Rentasan Kognitif (JRK)
evaluation technique. This evaluation technique was conducted on thirty-seven
surrogate users that consist of courseware developers, teachers and
university students using the Malaysian Smart School Mathematics courseware.
The usability result was then compared statistically with the empirical usability
evaluation called Task Analysis Exploratory through Observation using video
camera (TAEO). The respondents of the empirical method were secondary school
students who used the same courseware as one of the learning aids in school.
Usability indicators used in the study were usability problems and users’
satisfaction. The study showed that the effectiveness of the two techniques
was quite similar if they were used independently during the evaluation
process. The usability indicators obtained in the study could be used as
references in the usability comparisons of other educational courseware.
Keywords:
Usability Evaluation Technique, Task Analysis, Surrogate user, Usability
problems.
Title of the Paper:
Analysis on Types of Mobile Games Played among the IHL Students in Malaysia
DOWNLOAD
FULL PDF
Authors: Hafizullah Amin
Hashim, Siti Hafizah Ab Hamid, Mas Idayu
Md Sabri
Abstract: Mobile phones are no longer a luxury but are now considered a
necessity by its users. Many applications are developed to replace electronic
devices and extra ‘baggage’ that people used to carry around with them. A
mobile phone now also serves as a planner, camera, music player, video
player, gaming console, calculator and other useful gadgets. Mobile gaming is
getting more attention from gamers as one of the most preferable type of
digital games. One good reason that contributes to the success of mobile game
is because of its mobility, which means gamers can play games anytime and
anywhere. In this paper, we examine the usage of mobile games as compared to
other types of digital games such as console or arcade games in Malaysia.
We also perform a series of analysis regarding to students preferences in
every gaming phase from console or arcade games to mobile games. A survey on
user preferences among students of Institute of Higher Learning (IHL) has
been done to gather useful information and relevant data to support this
paper. The survey showed that an overwhelming majority (60%) of the
respondents prefer to play games on mobile phone. The data that have been
gathered from the survey were analyzed using Statistical Package for Social
Science (SPSS), Release 13.0.0, to investigate the number and percentage of
students that use mobile games. The future direction of this study is
discussed at the end of the paper.
Keywords: Mobile game, mobile learning, mobile phone,
programming.
Title of the Paper:
Automated Decision Support System Based on Ordered Sources
DOWNLOAD
FULL PDF
Authors: Sylvia Encheva,
Sharil Tumin
Abstract: Making a decision based on comparing responses coming from different
sources has allways been difficult. In this paper we propose application of a
decision support system for selecting a shipyard based on the quality of
services provided by a number of shipyards.
Keywords:
Quality of services, selection, Web-based systems.
Title of the Paper: The
Introduction of Supply Chain Management Concepts to e-Government Research and
Practice
DOWNLOAD
FULL PDF
Authors: Ales Groznik,
Peter Trkman
Abstract: The paper deals with various aspects of e-government and highlights
the importance of the holistic treatment of business process renovation in
order to facilitate the transition towards e-government. It analyses both
upstream and downstream supply chain renovation and describes a four-step
procedure for downstream renovation. A new definition of e-government that
includes the whole supply chain of the public administration is proposed. The
chief problems of the proposed approach are analysed, along with some
interesting topics for further research. The findings are partly illustrated
with a case study of the development of the Slovenian eprocurement portal.
Keywords:
e-government, e-procurement, supply chain management, business renovation,
case study.
Title of the Paper:
E-logistics: Slovenian Transport Logistics Cluster creation
DOWNLOAD
FULL PDF
Authors: Ales Groznik
Abstract: In the pursuit of enhanced competitiveness organisations are today
searching for innovative business models in order to foster economic
benefits. In Slovenia,
several clusters are being formed, including the Slovenian Transport
Logistics Cluster (STLC) as one of the most important. The STLC is currently
in the stage of dynamic growth, demanding business model formation and
adequate informatisation. The main goal of the paper is to present the
informatisation of the STLC, bridging the gap between Supply Chain Management
(SCM) and e-Logistics. The STLC’s informatisation of is presented in several
phases. The first phase involves business modelling of the existing business
processes of organisations (AS-IS model). The results of the first phase
allow an in-depth view of the STLC that is used in the future in the business
model setup. Next, TO-BE processes are created which are to be implemented
and supported via informatisation. The result of the informatisation project
is revealed to be homogenous and transparent business activity between
cluster members. The purposes of the STLC’s informatisation are to create a
business model, standardise business processes, allow cost cutting and
improved business performance, reduce operating times, support asset
management, and trace shipments which are the basics of economic
competitiveness.
Keywords:
SCM, e-logistics, cluster, informatisation, business renovation.
Title of the Paper:
Experiences of Implementing a Value-Based Approach
DOWNLOAD
FULL PDF
Authors: Pasi Ojala
Abstract: This study tries to advance and define the concepts, principles and
practical methods of a value-based approach, involving definition of the
essential concepts of value, cost and worth in software development. These
definitions originate from the Value Engineering (VE) method, originally
applied and developed for the needs of the production industry. Therefore,
for the purposes of this study these concepts are firstly justified and
secondly defined. In order to study and evaluate the value-based approach, a
method called value assessment is developed and used when assessing processes
and products. The results of industrial case show that even though there is
still much to do in making the economic-driven view complete in software
engineering, the value-based approach outlines a way towards a more
comprehensive understanding of it. For industrial users value assessment
seems to give a practical help for handling cost and profitability related
challenges.
Keywords:
Software process and product improvement, assessment, value, worth, cost and
Value Engineering.
Title of the Paper: A
New Version of Flusser Moment Set for Pattern Feature Extraction
DOWNLOAD
FULL PDF
Authors: Constantin-Iulian
Vizitiu, Doru Munteanu, Cristian Molder
Abstract: The choice of a suitable feature extraction method is essential for
the success of the classification or recognition process. This paper proposes
a design method for a new pattern descriptor set based on the Flusser moment
class, which is invariant to elementary geometric transforms and has an
increased robustness to the action of some perturbations. Experimental
results based on the use of a real video image database confirm the basic
properties of this new descriptor set.
Keywords:
Pattern feature extraction, Flusser moment class, pattern recognition, neural
network.
Title of the Paper: The
Characteristics of Learning in Limited Data and the Comparative Assessment of
Learning Methods
DOWNLOAD
FULL PDF
Authors: Fengming M.
Chang
Abstract: Many studies about learning in limited data were made in recent
years. Without double, small data set learning is a challenging problem.
Information in data of small size is scarce and has some learning limit.
While discussing the learning accuracy in limited data, different
classification method causes different results for different data because
each classification method has its property. A method is the best solution
for one data but is not the best for another. Therefore, this study analyzes
the characteristics of small data set learning by the comparison of
classification methods. The Mega-fuzzification method for small data set
learning is applied mainly. The comparison of different classification
methods for small data set learning with several kinds of data is also
presented.
Keywords:
Small data set, Mega-fuzzification, Machine learning, Classification method,
Paucity of data.
Title of the Paper: The
Effects of DTAI on Nursing Skills and Self-Efficacy
DOWNLOAD
FULL PDF
Authors: Mei-Huang Huang
, Aih-Fung Chiu, Ju-Ling Liu
Abstract: This research is to evaluate the effects of Digital Technology
Assisted Instruction (DTAI) applied in the Physical-Examining (PE) skill
courses for nursing students. Both a "Learning Satisfaction with
DTAI" survey and a "Self-efficacy" survey for these courses
had been designed as tools in this study. Students of the third grade (five
years program) in the nursing department of a technological college in |
