OTHERS_CITABLE
Fuzzy Clustering for Semantic Web Services Discovery based on Ontology
Web services as the most important event in distributed computing, have achieved great popularity among software developers today. A critical step in the process of developing service-oriented applications is web service discovery, i.e., the identification of existing relevant web services that can potentially be used in the context of a new web application.
In this paper, we have proposed a novel method based on data mining techniques to assist and improve the web service discovery process as well as the development of service-oriented applications. Our assistant discovery approach is based on automatic finding of semantic similarity between web services through the application of clustering methods. We have introduced a new fuzzy semantic clustering algorithm which assists web service consumers in discovering a group of similar web services through an individual query. This objective is attained by way of a search space reduction mechanism which adds to the efficiency of the approach. Our proposed approach provides dynamic and flexible clusters which can be changed at discovery process.
We have conducted an experimental study on a data set of tagged web services with ontology. The ontology supports the semantic analysis. Preliminary results from clustering indicate the possibility of retrieving web services at the discovery process with reasonable precision by applying the proposed similarity model. From these promising results, we conclude that web service discovery process could be performing in a reasonable time because of reduced search space.
http://ijict.itrc.ac.ir/article-1-252-en.pdf
2019-01-13
1
8
Fuzzy Clustering
Ontology
Data Mining
Semantic
Web Service Discovery
Nayereh
Gholamzadeh
1
School of Electrical and Computer Engineering, College of Engineering, University of Tehran, Tehran, Iran
AUTHOR
Fattaneh
Taghiyareh
2
School of Electrical and Computer Engineering, College of Engineering, University of Tehran, Tehran, Iran
AUTHOR
Azadeh
Shakery
3
School of Electrical and Computer Engineering, College of Engineering, University of Tehran, Tehran, Iran
AUTHOR
OTHERS_CITABLE
Publishing Persian Linked Data; Challenges and Lessons Learned
Linked Data as an important and novel subject has attracted great attention in the realm of the Semantic Web. Many works deal with publishing existing datasets as Linked Data. This paper discusses the challenges of publishing Persian linked data, and their potential solutions, based on the experiences and lessons learned from a project focused on publishing some academic data of the Ferdowsi University of Mashhad as Linked Data.
http://ijict.itrc.ac.ir/article-1-253-en.pdf
2019-01-13
9
19
Linked Data
Persian Dataset
LOD cloud
RDF
challenges and Solutions
Samad
Paydar
1
Web Technology Lab., Dept. of Computer Engineering Ferdowsi University of Mashhad Mashhad, Iran
AUTHOR
Mohsen
Kahani
2
Web Technology Lab., Dept. of Computer Engineering Ferdowsi University of Mashhad Mashhad, Iran
AUTHOR
Behshid
Behkamal
3
Web Technology Lab., Dept. of Computer Engineering Ferdowsi University of Mashhad Mashhad, Iran
AUTHOR
Mahboobeh
Dadkhah
4
Web Technology Lab., Dept. of Computer Engineering Ferdowsi University of Mashhad Mashhad, Iran
AUTHOR
OTHERS_CITABLE
A Timelier Credit Card Fraud Detection by Mining Transaction Time Series
As e-commerce sales continue to grow, the associated online fraud remains an attractive source of revenue for fraudsters. These fraudulent activities impose a considerable financial loss to merchants, making online fraud detection a necessity. The problem of fraud detection is concerned with not only capturing the fraudulent activities, but also capturing them as quickly as possible. This timeliness is crucial to decrease financial losses. In this research, a profiling method has been proposed for credit card fraud detection. The focus is on fraud cases which cannot be detected at the transaction level. Based on the fact that there are strong periodic patterns in cardholders' behavior, the time series of aggregated daily amounts spent on an individual credit card has been considered in the proposed method. In this method, the inherent periodic and seasonal patterns are extracted from the time series to construct a cardholder's profile. These patterns have been used to shorten the time between when a fraud occurs and when it is finally detected. Simulation results indicate that the new approach has resulted in a timelier fraud detection, improved detection rate and consequently less financial loss in the cases where a cardholder follows a regular or semi regular periodic behavior. The proposed method is equally applicable to other e-payment methods with minor application-specific modifications.
http://ijict.itrc.ac.ir/article-1-254-en.pdf
2019-01-13
21
28
Fraud detection
aggregatioal profile
time series
Leila
Seyedhossein
1
School of Electrical and Computer Engineering, College of Engineering, University of Tehran, Tehran, Iran
AUTHOR
Mahmoud Reza
Hashemi
2
School of Electrical and Computer Engineering, College of Engineering, University of Tehran, Tehran, Iran
AUTHOR
OTHERS_CITABLE
A Multi-Aspect Architecture with Co-alignment between Layers for Intra-Organizational Knowledge Networking Purposes
In this paper, architecture is proposed for the new emerging concept of knowledge networks. This architecture is based on a multi-aspect view to the problem of starting such a network in an organization. By integrating infrastructure, knowledge and business layers mounted on two aspects of human-based and organizational supportive conditions in a layered architecture, we proposed a novel architecture that contains intra-layer built-in assessment mechanisms as well. These assessment mechanisms ensure the gradual refinement of the network as the structure of each layer becomes fixed. In this paper, it has been discussed that how a multi-layer architecture with minimum amount of dependency among layers (that has the ability of interaction in business and knowledge layers) may facilitate knowledge management processes. The architecture can also give some guidelines on how to start such networks in inter-organizational level .One of the main applications of this architecture is to propose appropriate guidelines for the development of required sub-systems of intraorganizational knowledge networks. Therefore, at the end of this paper, the method of extracting these guidelines on the establishment of one of the key sub-systems for managing explicit organizational knowledge (e.g. Document Management system) is explained in details. These recommendations are based on a well-known standard of this domain. As the proposed extraction method is originated from the layers independency and self-assessment mechanism between layers, it can purposefully be re-used for collaboration/experience/process management systems as well.
http://ijict.itrc.ac.ir/article-1-255-en.pdf
2019-01-13
29
37
Architecture
Knowledge Network
Knowledge Management
Business Strategies
Maryam
S. Mirian
1
Knowledge Engineering and Intelligent Systems Research Group, IT Faculty Iran Telecom. Research Center
AUTHOR
Leila
Beig
2
Knowledge Engineering and Intelligent Systems Research Group, IT Faculty Iran Telecom. Research Center
AUTHOR
Mahmood
Kharrat
3
Knowledge Engineering and Intelligent Systems Research Group, IT Faculty Iran Telecom. Research Center
AUTHOR
OTHERS_CITABLE
A New Mathematical Method to Estimate Resources for E-commerce Application
Considering convergence of vast and different technologies in new generation networ . the required quality of service is the key success factor. The site implementation according to special benchmarkinJ(TPC-W), to achieve the acceptable service performance may be offered in a cost effective manner, is very complicated. In this paper a mathematical method will be introduced to help providers to make informed eel ions with respect of right level of resources (number and server capacity, number and power of CPUs, and amo nl of permanent and temporary memory). The numerical results show that the new formulation confirms the re uJt e-commerce site emulation in an acceptable level.
http://ijict.itrc.ac.ir/article-1-256-en.pdf
2019-01-13
39
47
e-commerce
QoS
resource
TPC-W
emulation
mathematical method
Leili
Pourjavaheri
1
Department of electrical engineering Science and Research branch Islamic Azad University Tehran, Iran
AUTHOR
Abbas
Asoshesh
2
IT Group- Engineering Department of Tarbiat Modares University,Tehran, Iran
AUTHOR
OTHERS_CITABLE
Adaptive Autonomy Expert System in Smart Grid based on Deterministic Timed Petri Nets
Interaction of humans and computer agents should be harmonized by adapting the utomation level of IT systems, to maintain a high performance for the system, in the changing environmental condition . This research presents an expert system for realization of adaptive autonomy (AA), using deterministic time Petri nets (DTPNs), referred to as AAPNES. The design is based on the practical list of environmental conditions nd superior expert`s judgments. As revealed by the results, the presented AAPNES can effectively determine the proper level of automation for the changing performance shaping factors of human-automation interaction systems in the smart grid.
http://ijict.itrc.ac.ir/article-1-257-en.pdf
2019-01-13
49
57
adaptive autonomy
expert system
human-computer interaction (HCI)
human-automation interaction (HAI)
level of automation (LOA)
smart grid
power distribution automation
Mohammad Ali
Zamani
1
CIPCE, School ofECE, University College ofEngg., University of Tehran Tehran, Iran
AUTHOR
Mohammad Amin
Sharifi Kolarijani
2
CIPCE, School ofECE, University College ofEngg., University of Tehran Tehran, Iran
AUTHOR
Alireza
Fereidunian
3
ECE Dep., Power and Water University of Technology and CIPCE, School ofECE, University of Tehran Tehran, Iran
AUTHOR
Hamid
Lesani
4
CIPCE, School of ECE, Universi y College of Engg, University of Tehan Tehran, Iran
AUTHOR
Caro
Lucas
5
CIPCE, School ofECE, University College of Eng., University of Tehran Tehran, Iran
AUTHOR
OTHERS_CITABLE
Content-Based Approach for Trfcking Concept Drift in Email Spam Filtering
The continued growth of Email usage, which is naturally followed by an increase i unsolicited emails so called spams, motivates research in spam filtering area. In the context of spam filtering systems, addressing th evolving nature of spams, which leads to obsolete the related models, has been always a challenge. In this paper an adaptive spam filtering system based on language model is proposed which can detect concept drift based on computing the deviation in email contents distribution. The proposed method can be used a ong with any existing classifier; particularly in this paper we use Naive Bayes method as classifier. The proposed method has been evaluated with Enron data set. The results indicate the efficiency of the method in detectin concept drift and its superiority over Naive Bayes classifier in terms of accuracy.
http://ijict.itrc.ac.ir/article-1-258-en.pdf
2019-01-13
59
65
component
spam.filtering
concept drift
KL divergence
language model
Morteza
Zi Hayat
1
School of Electrical and Computer Engineering, College of Engineering, University of Tehran, Tehran, Iran
AUTHOR
Javad
Basiri
2
School of Electrical and Computer Engineering University of Tehran, Tehran, Iran
AUTHOR
Leila
Seyedhossein
3
School of Electrical and Computer Engineering University of Tehran, Tehran, Iran
AUTHOR
Azadeh
Shakery
4
School of Electrical and Computer Engineering University of Tehran, Tehran, Iran
AUTHOR