Thabit Sabbah

Hybridized term-weighting method for Dark Web classification

The role of intelligence and security informatics based on statistical computations is becoming more significant in detecting terrorism activities proactively as the extremist groups are misusing many of the obtainable facilities on the Internet to incite violence and hatred. However, the performance of statistical methods is limited due to the inadequate accuracy produced by the inability of these methods to comprehend the texts created by humans. In this paper, we propose a hybridized feature selection method based on the basic term-weighting techniques for accurate terrorism activities detection in textual contexts. The proposed method combines the feature sets selected based on different individual feature selection methods into one feature space for effective web pages classification. UNION and Symmetric Difference combination functions are proposed for dimensionality reduction of the combined feature space. The method is tested on a selected dataset from the Dark Web Forum Portal and benchmarked using various famous text classifiers. Experimental results show that the hybridized method efficiently identifies the terrorist activities content and outperforms the individual methods. Furthermore, the results revealed that the classification performance achieved by hybridizing few feature sets is relatively competitive in the number of features used for classification with higher hybridization levels. Moreover, the experiments of hybridizing functions show that the dimensionality of the feature sets is significantly reduced by applying the Symmetric Difference function for feature sets combination. A hybrid text classifications method with term-weighting techniques is proposed.The proposed method combines various feature sets for effective classification.We proposed a method to reduce the dimension of feature sets for classification.The method is tested on a selected dataset from the Dark Web Portal Forum.Experimental results show that the proposed method outperforms other methods.

Coverage Enhancement Algorithms for Distributed Mobile Sensors Deployment in Wireless Sensor Networks

Sensor nodes in wireless sensor networks are deployed to observe the surroundings for some phenomenon of interest. The fundamental issue in observing such environments is the area coverage which reflects how well the region is monitored. The nonuniform sensor nodes distribution in a certain region caused by random deployment might lead to coverage holes/gaps in the network. One of the solutions to improve area coverage after initial deployment is by sensor nodes mobility. However, the main challenge in this approach is how to increase area coverage with the least energy consumption. This research work aims to improve area coverage with minimal energy consumption and faster convergence rate. The Edge Based Centroid (EBC) algorithm is presented to improve the area coverage with faster convergence rate in a distributed network. The simulation based performance evaluations of the proposed algorithms are carried out in terms of area coverage, convergence rate, and energy efficiency. Compared to the existing works, EBC improved area coverage with faster convergence. It is concluded that the proposed algorithm has improved area coverage with faster convergence and minimal energy consumption.

A Framework for Quranic Verses Authenticity Detection in Online Forum

Quran is the holy book for all Muslims around the world. Since more than 1400 years, it was preserved in all possible ways from distortion. The huge increment and spread of digital media and internet usage, leaded to many organizational and individual websites, services, and applications are being introduced to spread the knowledge related to Quran as well as Quranic Verses, Translations, Explanations with the Tafseer and other Quranic sciences in its digital formats, some of these services are less authentic. In this paper we introduce a framework to detect and authenticate Quranic verses in a text extracted from online source especially forums posts. The proposed methodology of detection is based on the assumption that Quranic Verses are the parts of the text that contain more diacritics (Harakat). Other assumptions were also established to increase the accuracy of detection in case of less diacritic text. Authentication methodology is based on computing numerical Identifiers of words in the detected text then comparing these identifiers with Identifiers of original Quranic manuscript. Experiments show acceptable results on the detections rate of the highly and less diacritic text. The accuracy was 62% in average while the precision and recall were 75% and 78%, respectively. Future works will focus on authentication side as well as incorporating computational intelligence methods, that involved the sound of the words pronounce during the reading of Quranic verses, image processing and others, to improve the detection.

Effect of thesaurus size on schema matching quality

Thesaurus is used in many Information Retrieval (IR) applications such as data integration, data warehousing, semantic query processing and schema matching. Schema matching or mapping is one of the most important basic steps in data integration. It is the process of identifying the semantic correspondence or equivalent between two or more schemas. Considering the fact of the existence of many thesauri for identical knowledge domain, the quality and the change in the results of schema matching when using different thesauri in specific knowledge field are not predictable. In this research, we studied the effect of thesaurus size on schema matching quality by conducting many experiments using different thesauri. In addition, a new method in calculating the similarity between vectors extracted from thesaurus database is proposed. The method is based on the ratio of individual shared elements to the elements in the compound set of the vectors. Moreover, we explained in details the efficient algorithm used in searching thesaurus database. After describing the experiments, results that show enhancement in the average of the similarity is presented. The completeness, effectiveness, and their harmonic mean measures were calculated to quantify the quality of matching. Experiments on two different thesauri show positive results with average Precision of 35% and a less value in the average of Recall. The effect of thesaurus size on the quality of matching was statically insignificant; however, other factors affecting the output and the exact value of change are still in the focus of our future study.

Modified Frequency-Based Term Weighting Scheme for Accurate Dark Web Content Classification

Security informatics and intelligence computation plays a vital role in detecting and classifying terrorism contents in the web. Accurate web content classification using the computational intelligence and security informatics will increase the opportunities of the early detection of the potential terrorist activities. In this paper, we propose a modified frequency-based term weighting scheme for accurate Dark Web content classification. The proposed term weighting scheme is compared to the common techniques used in text classification such as Term Frequency (TF), Term Frequency-Inverse Document Frequency (TF-IFD), and Term Frequency- Relative Frequency (tf.rf), on a dataset selected from Dark Web Portal Forum. The experimental results show that the classification accuracy and other evaluation measures based on the proposed scheme outperforms other term weighting techniques based classification.

Hybridized Feature Set for Accurate Arabic Dark Web Pages Classification

Security informatics and computational intelligence are gaining more importance in detecting terrorist activities as the extremist groups are misusing many of the available Internet services to incite violence and hatred. However, inadequate performance of statistical based computational intelligence methods reduces intelligent techniques efficiency in supporting counterterrorism efforts, and limits the early detection opportunities of potential terrorist activities. In this paper, we propose a feature set hybridization method, based on feature selection and extraction methods, for accurate content classification in Arabic dark web pages. The proposed method hybridizes the feature sets so that the generated feature set contains less number of features that capable of achieving higher classification performance. A selected dataset from Dark Web Forum Portal (DWFP) is used to test the performance of the proposed method that based on Term Frequency - Inverse Document Frequency (TFIDF) as feature selection method on one hand, while Random Projection (RP) and Principal Component Analysis (PCA) feature selection methods on the other hand. Classification results using the Support Vector Machine (SVM) classifier show that a high classification performance has been achieved base on the hybridization of TFIDF and PCA, where 99 % of F1 and accuracy performance has been achieved.

Fuzzy granular classifier approach for spam detection

Spam email problem is a major shortcoming of email technology for computer security. In this research, a granular classifier model is proposed to discover hyperboxes in the geometry of information granules for spam detection in three steps. In the first step, the k-means clustering algorithm is applied to find the seed_points to build the granular structure of the spam and non-spam patterns. Moreover, applying the interval analysis through the high homogeneity of the patterns captures the key part of the spam and non-spam classifiers’ structure. In the second step, PSO algorithm is hybridized with the k-means to optimize the formalized information granules’ performance. The proposed model is evaluated based on the accuracy, misclassification and coverage criteria. Experimental results reveal that the performance of our proposed model is increased through applying Particle Swarm Optimization and fuzzy set.

Thesaurus Performance with Information Retrieval: Schema Matching as a Case Study

Thesaurus is used with many Information Retrieval (IR) models such as data integration, data warehousing, semantic query processing and classifiers. Considering the existence of various thesauri for a particular domain of knowledge, output quality of an IR model when using different thesauri in the same domain is not predictable. In this paper, we propose a methodology to study the performance of thesaurus in solving schema matching as a case study of IR models. The paper also presents initial results of experiment conducted using different thesauri. Precision, recall, and F-measure were calculated to show that the quality of matching was changed according to the used thesaurus.