International Journal of Advanced Computer Science and Information Technology

9

Authors: Do Nguyet Quang , Ong Hang See , Ong Xing Jui

Heterogeneous and hybrid smart grid communication network is a network that comprises of different communication mediums and technologies. Performance evaluation is one of the main concerns in smart grid communication system. In any smart grid communication implementation, to determine the performance factor of the network, a testing of an end-to-end process flow is required. Therefore, an effective testing tool plays a crucial role in evaluating the performance of smart grid communications. Ping is currently one of the most common network testing tools. In this paper, a customized ping utility, called Smart Grid Ping, is introduced. This utility provides random ping intervals with user selectable distribution, allowing network administrators to test the reachability and availability of various applications in smart grid communication system.

21

Authors: Mohammed A. Shreef , Haider K. Hoomod

Today, information security is becoming one of the most important issues in social network era. The fast development of network technology leads to facilitate many aspects of life, but it also gives attackers or unauthorized users an opportunity to violate the privacy of people. Encryption is a common technique that exists to protect information security, thereby deters attackers. Actually, digital images are widely used in storage and communication applications. Therefore, the protection of image data from unauthorized access has attracted much attention recently. This paper adopts a new image cryptosystem, XLLS, which consists of two main parts: encryption/decryption algorithm and ciphered key. The encryption algorithm is composed of two main stages: the diffusion stage and the substitution stage. In the diffusion stage, the pixels values are modified so that a slight change in one pixel is spread out to all pixels in the image. This stage completely depends in its construction on ‘XOR’ operation. For the substitution stage, it mainly composes of two encryption processes: Lagrange Process (LP) and Least Squares Process (LSP). This stage aims at changing the value of each pixel in the diffused image by using the principles of Lagrange interpolation and least squares method. For the decryption algorithm, it is simply the reverse of the encryption algorithm. On the other hand, the proposed cryptosystem introduces two different approaches of initial key. The users have option to choose any one of them to encrypt the plain-image. In the first approach, the proposed cryptosystem uses a key whose length is of 192 bits (24 bytes) in hexadecimal system as its input, and then expands it by using AES-192 key expansion algorithm. Conversely, in the second approach, the proposed cryptosystem uses an image as a key to cipher the plain-image, and then processes and expands the key-image by using the CBI key expansion algorithm.

8

Authors: Hossein Moradi Koupaie , Suhaimi Ibrahim , Javad Hosseinkhani

In recent years, intrusion detection has emerged as an important technique for network security. Machine learning techniques have been applied to the field of intrusion detection. They can learn normal and anomalous patterns from training data and via Feature selection improving classification by searching for the subset of features which best classifies the training data to detect attacks on computer system. The quality of features directly affects the performance of classification. Many feature selection methods introduced to remove redundant and irrelevant features, because raw features may reduce accuracy or robustness of classification. Outlier detection in stream data is an important and active research issue in anomaly detection. Most of the existing outlier detection algorithms has less accurate because use some clustering method. Some data are so essential and secretary. Therefore, it needs to mine carefully even if spend cost. This paper presents a framework to detect outlier in stream data by machine learning method. Moreover, it is considered if data was high dimensional. This method is more accurate from other preferred models, because machine learning method is more accurate of other methods.

16

Authors: Ahmed Tariq Sadiq , Mehdi Gzar Duaimi , Samir Adil Shaker

This paper presents a hybrid approach for solving null values problem; it hybridizes rough set theory with intelligent swarm algorithm. The proposed approach is a supervised learning model. A large set of complete data called learning data is used to find the decision rule sets that then have been used in solving the incomplete data problem. The intelligent swarm algorithm is used for feature selection which represents bees algorithm as heuristic search algorithm combined with rough set theory as evaluation function. Also another feature selection algorithm called ID3 is presented, it works as statistical algorithm instead of intelligent algorithm. A comparison between those two approaches is made in their performance for null values estimation through working with rough set theory. The results obtained from most code sets show that bees algorithm better than ID3 in decreasing the number of extracted rules without affecting the accuracy and increasing the accuracy ratio of null values estimation, especially when the number of null values is increasing.

10

Authors: Javad Hosseinkhani , Suriayati Chuprat , Hamed Taherdoost , Morteza Harati Cool , Sadegh Emami Korani

Criminal web data always offer novel and useful knowledge and information for Law administration. The used digital data in legal assessments are involved parts of information about the accused’ social networks. Thus, evaluation of these parts of information is challenging. Therefore, an investigator has to pull out the appropriate information from the text manually, these information are on the website. An investigator also makes the relationship between various parts of information and classify them in to a structured database so the category is ready to use in different criminal network evaluation tools for analysis. On the other hand, these manual processes are not adequate in the case that it has many errors. Moreover, as the quality of resulted evaluation depends on the investigator’s proficiency, the reliability is not stable. On another word, the more proficient operator, the better result achieved. The purpose of this paper is suggesting a framework by using concurrent crawler to show the process of exploring the criminal accused of legal data evaluation which insures the reliability gap.

18

Authors: Dr. Ahmed T. Sadiq , Sura Mahmood Abdullah

Text categorization is the task in which text documents are classified into one or more of predefined categories based on their contents. This paper shows that the proposed system consists of three main steps: text document representation, classifier construction and performance evaluation. In the first step, a set of pre-classified text documents is provided. Each text document is initially preprocessed in order to be split into features, these features are weighted based on the frequency of each feature in that text document and eliminate the non-informative features. The remaining features are next standardized by reducing a feature to its root using the stemming process. Due to the large number of features even after the non-informative features removal and the stemming process, the proposed system applies specific thresholds to extract distinct features which represent that text document. In the second step, the text categorization model (classifier) is built by learning the distinct features which represent all the preclassified text documents for each sub-category of main categories; this process can be achieved by using one of the supervised categorization techniques that is called the rough set theory. Thereafter, the model uses a pair of precise concepts from the above theory that are called the lower and upper approximations to classify any test text document into one or more of main categories and sub-categories. In the final step, the performance of the proposed system is evaluated. It has achieved good results up to 96%, when applied to a number of test text documents for each sub-category of main categories.

11

Authors: Farnaz Farshchian , Ebrahim Parcham , Ebrahim Parcham

This paper aims at identification of individuals using the retinal image that the extraction of blood vessels based on density classification and identification is carried out according to the Fuzzy logic and then according to the performed operations of individual’s electronic health record. For this purpose, a new algorithm was presented for extraction of specific characteristics of retina based on image analysis and statistic calculations. Extraction of eye blood vessels is carried out based on adaptive filters. Our proposed method in comparison to previous methods which merely have carried out the identification through individually comparison of retina has a higher accuracy and speed. This distinction in the identification accuracy and speed was used in the type of classification and Fuzzy rules. In this paper, we will cluster the image noise at the first stage and at the end of clustering, two classes of noise and the original image will remain. This clustering will be done using the density method of Density-Based Clustering. Then we will extract the eye vessels using adaptive filters. After identifying classes and eye vessels extraction, we will identify the image of the retina under experiment based on the five-stage Fuzzy logic and rules and extract the individual’s file.

13

Authors: Mohd Izzuddin Mohd Tamrin , Tengku Mohd Tengku Sembok , Mira Kartiwi

Heavy reliance on the other nodes in a complex supply chain network and failure to deliver the specialized assignment by merely one node can caused disruption to the entire processes. The authors introduce the Integrative Information Management Architecture (IIMA) to generate semi-automated assistance against common supply chain deviations. Support models are used and they are made from tree-like structure in XML documents. The recommendations are stored in the leaf nodes whereas the intermediary nodes are filled with characteristics of the deviation. The IIMA employed the XPath together with a series of questions to navigate through the relevant path. We had developed the prototype of the IIMA but run it in simulated environments. The results showed that the group with IIMA support improved the number of completed processes compared to without the IIMA support.