Jalal Atoum - Academia.edu (original) (raw)

Papers by Jalal Atoum

2021 International Conference on Computational Science and Computational Intelligence (CSCI)

Image segmentation is an important and interesting digital image pre-processing phase to enhance ... more Image segmentation is an important and interesting digital image pre-processing phase to enhance the performance of various pattern recognition and computer vision applications. Segmentation process enhance images analysis through the extractions of features from the relevance part of image only. In this paper, a comparative study between five different color segmentation techniques is performed. The experimental results of PSNR and MSE metrics show that K-means clustering algorithm has better results when compared to the other algorithms, but still need to be modified to deal with different types of sharp and smooth edges.

This this paper presents an important enhanced method to detect suspicious PDF files by applying ... more This this paper presents an important enhanced method to detect suspicious PDF files by applying two scanning methods (structure scan and YARA scan), which depend on extracting and pointing out malicious objects that are often used for attacks. This enhanced method will be a great assistant to forensic analysts in analyzing PDF files and detecting malicious content in them. Testing both scanning methods was carried out through conducting several experiments on a real dataset. The results show an improvement for detecting malicious PDF files when applying both methods. The structure scan achieved an accuracy of 99.91% and the YARA scan achieved an accuracy of 98.05%.

International Journal of Communications, Network and System Sciences, 2015

Anti-censorship applications are becoming increasingly popular mean to circumvent Internet censor... more Anti-censorship applications are becoming increasingly popular mean to circumvent Internet censorship, whether imposed by governments seeking to control the flow of information available to their citizens, or by parental figures wishing to shield their "parishioners" from the dangers of the Internet, or in organizations trying to restrict the Internet usage within their networking territory. Numerous applications are readily accessible for the average user to aid-in bypassing Internet censorship. Several technologies and techniques are associated with the formation of these applications, whereas, each of these applications deploys its unique mechanism to circumvent Internet censorship. Using anti-censorship applications in the work environment can have a negative impact on the network, leading to excessive degradation in the bandwidth, immense consumption of the Internet data usage capacity and possibly open the door for security breaches. Triumphing the war on anti-censorship applications has become more difficult to achieve at the network level due to the rapid updates and the adopted new technologies to circumvent censorship. In this study, a comprehensive overview on Internet censorship and anti-censorship applications is provided by analyzing Ultrasurf behavior, classifying its traffic patterns and proposing a behavioral-based solution that is capable of detecting and preventing the Ultrasurf traffic at the network level.

International Journal of Computer Processing of Languages, 2009

Searching for a pattern in an Arabic text raises various problems due to the association of vocal... more Searching for a pattern in an Arabic text raises various problems due to the association of vocalization characters with alphabetical letters of Arabic words. This feature causes a problem for existing searching algorithms. They either fail to find all partial matches of a pattern or they may suffer from performance degradation when they are simply modified to ignore these vocalization characters. This paper presents a new coding schema for Arabic vocalization characters that will facilitate and improve the performance of searching for vocalized and unvocalized patterns in any Arabic text (vocalized or unvocalized). This schema is based on repositioning the vocalization characters at the end of each word. We present in this paper the coding and decoding algorithms needed to support our new coding schema. In addition, we explain the modifications to the Boyer-Moore algorithm that take advantage of our improved coding schema together with the complexity analysis.

2010 Second International Conference on Computer Engineering and Applications, 2010

A Distributed Denial of Service attack (DDoS) is one the most dangerous attacks that can be initi... more A Distributed Denial of Service attack (DDoS) is one the most dangerous attacks that can be initiated on computer systems that targets their availability. No defense technique was suggested until now to be called an absolute defense that stands against all types of DDoS attacks. ...

2006 2nd International Conference on Information & Communication Technologies

This paper presents an alternative approach to modeling of an e-negotiation process based on inte... more This paper presents an alternative approach to modeling of an e-negotiation process based on integration of case-based reasoning with multiagent technology whose complementary properties can be advantageously combined to build an efficient e-negotiation model where using any single technique fails to provide a satisfactory solution. Integration of centralized and decentralized decision making techniques allows to minimize the volume of required

American Journal of Applied Sciences, 2009

Problem statement: Genetic Algorithms (GAs) have been used as search algorithms to find near-opti... more Problem statement: Genetic Algorithms (GAs) have been used as search algorithms to find near-optimal solutions for many NP problems. GAs require effective chromosome representations as well as carefully designed crossover and mutation operators to achieve an efficient search. The Traveling Salesman Problem (TSP), as an NP search problem, involves finding the shortest Hamiltonian Path or Cycle in a graph of N cities. The main objective of this study was to propose a new representation method of chromosomes using upper triangle binary matrices and a new crossover operator to be used as a heuristic method to find near-optimum solutions for the TSP. Approach: A proposed genetic algorithm, that employed these new methods of representation and crossover operator, had been implemented using DELPHI programming language on a personal computer. Also, for the purpose of comparisons, the genetic algorithm of Sneiw had been implemented using the same programming language on the same computer. Results: The outcomes obtained from running the proposed genetic algorithm on several TSP instances taken from the TSPLIB had showed that proposed methods found optimum solution of many TSP benchmark problems and near optimum of the others. Conclusion: Proposed chromosome representation minimized the memory space requirements and proposed genetic crossover operator improved the quality of the solutions in significantly less time in comparison with Sneiw's genetic algorithm.

The International Arab Journal of Information Technology, 2010

Warehouses scheduling is the problem of sequencing requests of products to fulfill several custom... more Warehouses scheduling is the problem of sequencing requests of products to fulfill several customers' orders so as to minimize the average time and shipping costs. In this paper, a solution to the problem of multiple warehouses scheduling using the steady state genetic algorithm is presented. A mathematical model that organizes the relationships between customers and warehouses is also presented in

Journal of Computer Science, 2008

Data Mining (DM) represents the process of extracting interesting and previously unknown knowledg... more Data Mining (DM) represents the process of extracting interesting and previously unknown knowledge from data. This study proposes a new algorithm called FD_Discover for discovering Functional Dependencies (FDs) from databases. This algorithm employs some concepts from relational databases design theory specifically the concepts of equivalences and the minimal cover. It has resulted in large improvement in performance in comparison with a recent and similar algorithm called FD_MINE.

As the digital technology advances, especially the data storage and image capturing technologies,... more As the digital technology advances, especially the data storage and image capturing technologies, more digital images are being created and stored digitally. This led to the creation of large numbers of digital image libraries. Hence, the need for intuitive and effective image storage, indexing, classification and retrieval mechanisms rises. In this paper, an enhancement on the use of color and texture visual features in Content-Based Image Retrieval (CBIR) is proposed by adding a new color feature called Average Color Dominance which tries to enhance color description using the dominant colors of an image. The proposed methodology was compared with the work of Kavitha et al [1] and has shown an increase in the average precision from 40.4% to 45.06%.

In recent years with the widespread of social media platforms across the globe especially among y... more In recent years with the widespread of social media platforms across the globe especially among young people, cyberbullying and aggression have become a serious and annoying problem that communities must deal with. Such platforms provide various ways for bullies to attack and threaten others in their communities. Various techniques and methodologies have been used or proposed to combat cyberbullying through early detection and alerts to discover and/or protect victims from such attacks. Machine learning (ML) techniques have been widely used to detect some language patterns that are exploited by bullies to attack their victims. Also. Sentiment Analysis (SA) of social media content has become one of the growing areas of research in machine learning. SA provides the ability to detect cyberbullying in real-time. SA provides the ability to detect cyberbullying in real-time. This paper proposes a SA model for identifying cyberbullying texts in Twitter social media. Support Vector Machines...

Complexity study of two developed algorithms for sorting vocalized arabic words using a new codin... more Complexity study of two developed algorithms for sorting vocalized arabic words using a new coding schema

2017 International Conference on New Trends in Computing Sciences (ICTCS)

The fast growth of technology in both software and hardware levels resulted in moving several ind... more The fast growth of technology in both software and hardware levels resulted in moving several industries such as media, news, publishing, printing, and entertainment from classic approach to more digital approach. Thus, creates the need to understand the audience and their behaviors toward their products, advertising campaigns, or services to increase their growth and improve satisfaction of both readers and publishers. This paper proposes a framework for recommending content for news websites to users in real time to increase both user and business satisfactions using academic and news industry standards, it starts with gathering data and ending with delivering personalized recommendations per user. Results showed an improvement of users' engagement when such recommendation system was active.

International Journal of Advanced Computer Science and Applications

Sentiment Analysis (SA) of social media contents has become one of the growing areas of research ... more Sentiment Analysis (SA) of social media contents has become one of the growing areas of research in data mining. SA provides the ability of text mining the public opinions of a subjective manner in real time. This paper proposes a SA model of Arabic Jordanian dialect tweets. Tweets are annotated on three different classes; positive, negative, and neutral. Support Vector Machines (SVM) and Naïve Bayes (NB) are used as supervised machine learning classification tools. Preprocessing of such tweets for SA is done via; cleaning noisy tweets, normalization, tokenization, namely, Entity Recognition, removing stop words, and stemming. The results of the experiments conducted on this model showed encouraging outcomes when Arabic light stemmer/segment is applied on Arabic Jordanian dialect tweets. Also, the results showed that SVM has better performance than NB on such tweets' classifications.

International Journal of Software Engineering and Its Applications

International Journal of Computer Trends and Technology, 2016

The fascinating world of Cloud computing has definitely changed the way of using computers and th... more The fascinating world of Cloud computing has definitely changed the way of using computers and the Internet. The impact it has left so far on how IT and business services are delivered and managed is undeniable. However, the evolutionary change that Cloud computing has left on the IT landscape has given rise to a range of concerns by Cloud providers and customers. The current study introduces and examines two major problems in Cloud computing system. The first one is the Cloud internal and external data security and client’s privacy, and the tasks mobility and resources utilization. The study also provides practical solutions to the two aforementioned problems and a prototype, called SPI, which has been successfully tested. The present study suggests using SSL with proxy server and secured access to members control panel for Cloud external data security. As for internal security and client’s privacy, multiple approaches have been applied.

British Journal of Mathematics & Computer Science, 2016

Mining Approximate Functional Dependencies (AFDs) from a database may produce valuable interestin... more Mining Approximate Functional Dependencies (AFDs) from a database may produce valuable interesting relationships among its variables that would be beneficial in several domain applications such as marketing, financial data analysis, biological data analysi s, and intrusion detection. Mining of association rules is concerned with extracting new knowledge from dat abases in the form of patterns and associations among data items. The mining of AFDs still posing special se t of challenges such as the space and time requirements in addition to the quality of the discovered AFD s. In this paper, an approach for AFDs mining is being developed through employing the specificity interestingness measure and its monotonic property used in some association rules mining algorithms. Thi s approach has been tested on a set of test bed of datasets. The results showed an improvement in time requirements and in the number of mined AFDs.