Rached Zantout | Rafik Hariri University (original) (raw)
Papers by Rached Zantout
2015 Fifth International Conference on Digital Information and Communication Technology and its Applications (DICTAP), 2015
2015 International Conference on Applied Research in Computer Science and Engineering (ICAR), 2015
2015 5th International Conference on Information & Communication Technology and Accessibility (ICTA), 2015
Web page evaluation systems are needed to evaluate the accessibility of websites. Such evaluation... more Web page evaluation systems are needed to evaluate the accessibility of websites. Such evaluation is important so that website administrators can change their websites so people with disabilities would be able to use them. Currently, such systems produce varying results that are not always useful for website administrators. Moreover it is difficult to ascertain for sure to what degree the web pages conform to accessibility guidelines. In this paper, the current state of open-source web accessibility evaluation tools is reviewed. As a result, AChecker, a system that evaluates web page compliance with WCAG 2.0, is identified as the best available. Three types of deficiencies in AChecker are identified, unclear comments, redundancy of errors reporting and lack of automatic or semiautomatic repair. An interactive evaluation tool (IWAET) is developed based on AChecker. The usability of the new system is studied. The study involved a group of web developers with different levels of programming experience and no accessibility knowledge. Both quantitative and qualitative approaches were adopted in usability evaluation. The developed system is compared to AChecker. The results of the evaluation are presented which show clearly the superiority of the new system compared to the currently available systems.
2015 5th International Conference on Information & Communication Technology and Accessibility (ICTA), 2015
Visually impaired people usually try to build their careers in areas where the use of mathematics... more Visually impaired people usually try to build their careers in areas where the use of mathematics is minimal. This is because learning or practicing mathematics demands highly visual abilities. In this paper, a framework is introduced which will enable visually impaired students to learn and practice mathematics like sighted students. The framework was instantiated successfully to enable visually impaired students to learn and practice linear algebra. An electronic system was developed which was used by visually impaired university students. In addition, an instantiation was implemented to help visually impaired upper elementary and middle school students learn and practice Algebra using either Arabic or English. This instantiation has been implemented as an electronic system and tested for upper elementary students. Encouraging results were reported. Currently work is ongoing to augment it to serve middle school students.
In this paper an interactive workspace designed to help visually impaired students practice the f... more In this paper an interactive workspace designed to help visually impaired students practice the fundamentals of linear algebra is introduced. Unlike most of the approaches, this interactive workspace aims at enhancing math manipulation abilities for students who are visually impaired, mainly dealing with linear algebra expression that requires more complicated techniques in accessing. Read-expression, Hide-Row/Column, and Text-Tools are examples of techniques that the workspace implements. Such techniques are invoked by hot access keys which in turn with audio feedback allow the user to navigate and edit the linear algebra expression, access its elements especially matrices, find the solution and save it for further review and edit. The methodology followed is to list all the operations required in Linear Algebra. Then the tasks which require visual abilities were isolated and implemented in the framework.
2015 Fifth International Conference on Digital Information and Communication Technology and its Applications (DICTAP), 2015
2015 International Conference on Applied Research in Computer Science and Engineering (ICAR), 2015
Arabic is a morphologically and syntactically complex language and English-Arabic parallel corpor... more Arabic is a morphologically and syntactically complex language and English-Arabic parallel corpora are not abundant. The challenges that lie ahead of the availability of such parallel corpora are the selection and building of corpora, their cleanup, preprocessing, tagging, and alignment. Further challenges lie ahead such as building a system that would act like the Transfer Module (TM). In this chapter, the types of problems faced when building an Arabic MT (AMT) system are discussed. First, the experience in preparing bilingual corpora for statistical alignment is summarized. Second, the methodology for building an ANN-based MT transfer module is presented. A hybrid approach to MT, i.e. that uses a combination of the transfer approach and a corpus-based approach, is used. While presenting both experiences, the challenges faced are outlined and solutions are discussed.
A massive amount of documents are being posted online every minute. The task of document classifi... more A massive amount of documents are being posted online every minute. The task of document classification requires extensive background work on the content of documents, where keyword-based matching alone may not be sufficient. Much research has been carried out in several languages that has revealed significant results. However, Arabic documents still pose a great challenge due to the nature of Arabic language. Extracting roots or stems from the breakdown of multiple Arabic words and phrases are an important task that must be completed before applying text classification. The research at hand proposes an algorithm for classifying Arabic-Text documents using semantic relations between words based on an Arabic thesaurus, mainly synonyms, hyperonyms and hyponyms. The experiments conducted in this study evaluated the results using F1-Measure and compared them to results obtained via other existing methods, such as utilizing stemmers and part-of-speech taggers, where it indicated an incre...
Text, Speech and Language Technology, 2007
... Ahmed Guessoum and Rached Zantout Department of Computer Science, The University of Sharjah, ... more ... Ahmed Guessoum and Rached Zantout Department of Computer Science, The University of Sharjah, PO Box 27272, Sharjah, UAE guessoum@sharjah.ac ... word depending on these features must obviously be done very care-fully and is in fact a common mistake among native ...
2009 International Conference on Innovations in Information Technology (IIT), 2009
Automatic recognition of printed and handwritten documents remains an active area of research. Ar... more Automatic recognition of printed and handwritten documents remains an active area of research. Arabic is one of the languages that present special problems. Arabic is cursive and therefore necessitates a segmentation process to determine the boundaries of a ...
Proceedings of CIBITIC, 2006
Natural Language Processing (NLP) has gained a lot of importance nowadays with many applications ... more Natural Language Processing (NLP) has gained a lot of importance nowadays with many applications requiring real-time performance. In order to achieve the real-time requirements, the components of a NLP system should be made more efficient. An ...
When it comes to Arabic text documents, Text Categorization (TC) becomes a challenge. TC is neede... more When it comes to Arabic text documents, Text Categorization (TC) becomes a challenge. TC is needed for clustering purposes in order to complete Text Mining (TC). Based on the nature of Arabic language, extracting roots or stems from the breakdown of multiple Arabic words and phrases is important task before applying TC. The results obtained by applying the proposed algorithm are compared with the results of three popular algorithms. These algorithms are Khoja stemmer, Light stemmer, and Root extractor. The performance of these three techniques are evaluated and compared based on the accuracy of Naive Bayesian classifier. The obtained result demonstrates that these techniquesare not as promising as expected.Therefore, we decided to consider the position tagger and conceptual representation to answer the question, which approach enhances the Arabic TC performance? Arabic WordNet (AWN))is used as a lexical and semantic resource. The performance of new relation "Has-hyponym",suggested in this work, iscompared with otheralready used relations like Synset, term+ Synset, all Synsets, and Bag of words representation to demonstrate its effectiveness. From the experimental results, it was found that the new suggested relationimproved the Arabic text classification, at which the macro average F1 is raised to 0.75437compared with the performance of the other approaches.
IEEE GCC Conference & Exhibition, 2011
In this paper character recognition in Saudi Automobile License Plates is described. Due to speci... more In this paper character recognition in Saudi Automobile License Plates is described. Due to special properties of Saudi license plates, simpler procedures as compared to the ones used for Lebanese plates have been developed. A limited character set for recognition enables the development of smaller recognition trees. The developed procedure was applied to different characters taken from real license plates
MELECON 2014 - 2014 17th IEEE Mediterranean Electrotechnical Conference, 2014
ABSTRACT
2011 International Conference on Innovations in Information Technology, 2011
In this paper character recognition in Saudi Automobile License Plates is described. Due to speci... more In this paper character recognition in Saudi Automobile License Plates is described. Due to special properties of Saudi license plates, simpler procedures as compared to the ones used for Lebanese plates have been developed. A limited character set for recognition enables the development of smaller recognition trees. The developed procedure was applied to different characters taken from real license plates
In this paper character recognition in Saudi Automobile License Plates is described. Due to speci... more In this paper character recognition in Saudi Automobile License Plates is described. Due to special properties of Saudi license plates, simpler procedures as compared to the ones used for Lebanese plates have been developed. A limited character set for recognition enables the development of smaller recognition trees. The developed procedure was applied to different characters taken from real license plates
2012 2nd International Conference on Advances in Computational Tools for Engineering Applications (ACTEA), 2012
ABSTRACT Social networks contain large amounts of posts of different data types (text, images, so... more ABSTRACT Social networks contain large amounts of posts of different data types (text, images, sounds and videos). Textual posts express authors' opinions (with or against) or feeling (love, hate, optimism, pessimism, or anger). Such opinions are important for commercial and governmental organization since they help checking public opinion about a product, policy or an object in general. In this paper we present the application of two different approaches to classify Arabic Facebook posts. The first one depends on syntactic features, using common patterns used in different Arabic dialects to express opinions. These patterns achieved high accuracy in determining the polarity of a sentiment even when tested against new corpus. This approach acts on informal Arabic text, which has not been addressed before. Different setups were tried and the highest coverage and accuracy achieved were 49.5% and 83.4 % respectively. The second approach is an ordinary probabilistic model, Naïve-Bayes classifier, that assumes the independence of features in determining the class the highest coverage achieved in this approach was 60.5% in the first setup and 91.2% when Naïve search was used as a binary classifier to classify the posts as objective or subjective.
2012 2nd International Conference on Advances in Computational Tools for Engineering Applications (ACTEA), 2012
ABSTRACT Automatic detection and recognition of traffic signs is an important tool in intelligent... more ABSTRACT Automatic detection and recognition of traffic signs is an important tool in intelligent vehicles. It allows more autonomous vehicles and it can alert the driver to possible hazards and changes in the road. In this paper we focus on the recognition of a wide set of triangular traffic signs using a novel algorithm, the Number of Peaks. Once a traffic sign is detected, three horizontal lines (T, H, B) and three vertical lines (R, V, L) across the image are used to recognize the sign. The number of crossings from a black pixel to a white pixel (peak) on each line is calculated. A simple and fast decision-tree-like search algorithm uses the number of peaks to differentiate between the triangular road signs. A 100% correct detection rate is achievable even in a fairly noisy environment.
2015 Fifth International Conference on Digital Information and Communication Technology and its Applications (DICTAP), 2015
2015 International Conference on Applied Research in Computer Science and Engineering (ICAR), 2015
2015 5th International Conference on Information & Communication Technology and Accessibility (ICTA), 2015
Web page evaluation systems are needed to evaluate the accessibility of websites. Such evaluation... more Web page evaluation systems are needed to evaluate the accessibility of websites. Such evaluation is important so that website administrators can change their websites so people with disabilities would be able to use them. Currently, such systems produce varying results that are not always useful for website administrators. Moreover it is difficult to ascertain for sure to what degree the web pages conform to accessibility guidelines. In this paper, the current state of open-source web accessibility evaluation tools is reviewed. As a result, AChecker, a system that evaluates web page compliance with WCAG 2.0, is identified as the best available. Three types of deficiencies in AChecker are identified, unclear comments, redundancy of errors reporting and lack of automatic or semiautomatic repair. An interactive evaluation tool (IWAET) is developed based on AChecker. The usability of the new system is studied. The study involved a group of web developers with different levels of programming experience and no accessibility knowledge. Both quantitative and qualitative approaches were adopted in usability evaluation. The developed system is compared to AChecker. The results of the evaluation are presented which show clearly the superiority of the new system compared to the currently available systems.
2015 5th International Conference on Information & Communication Technology and Accessibility (ICTA), 2015
Visually impaired people usually try to build their careers in areas where the use of mathematics... more Visually impaired people usually try to build their careers in areas where the use of mathematics is minimal. This is because learning or practicing mathematics demands highly visual abilities. In this paper, a framework is introduced which will enable visually impaired students to learn and practice mathematics like sighted students. The framework was instantiated successfully to enable visually impaired students to learn and practice linear algebra. An electronic system was developed which was used by visually impaired university students. In addition, an instantiation was implemented to help visually impaired upper elementary and middle school students learn and practice Algebra using either Arabic or English. This instantiation has been implemented as an electronic system and tested for upper elementary students. Encouraging results were reported. Currently work is ongoing to augment it to serve middle school students.
In this paper an interactive workspace designed to help visually impaired students practice the f... more In this paper an interactive workspace designed to help visually impaired students practice the fundamentals of linear algebra is introduced. Unlike most of the approaches, this interactive workspace aims at enhancing math manipulation abilities for students who are visually impaired, mainly dealing with linear algebra expression that requires more complicated techniques in accessing. Read-expression, Hide-Row/Column, and Text-Tools are examples of techniques that the workspace implements. Such techniques are invoked by hot access keys which in turn with audio feedback allow the user to navigate and edit the linear algebra expression, access its elements especially matrices, find the solution and save it for further review and edit. The methodology followed is to list all the operations required in Linear Algebra. Then the tasks which require visual abilities were isolated and implemented in the framework.
2015 Fifth International Conference on Digital Information and Communication Technology and its Applications (DICTAP), 2015
2015 International Conference on Applied Research in Computer Science and Engineering (ICAR), 2015
Arabic is a morphologically and syntactically complex language and English-Arabic parallel corpor... more Arabic is a morphologically and syntactically complex language and English-Arabic parallel corpora are not abundant. The challenges that lie ahead of the availability of such parallel corpora are the selection and building of corpora, their cleanup, preprocessing, tagging, and alignment. Further challenges lie ahead such as building a system that would act like the Transfer Module (TM). In this chapter, the types of problems faced when building an Arabic MT (AMT) system are discussed. First, the experience in preparing bilingual corpora for statistical alignment is summarized. Second, the methodology for building an ANN-based MT transfer module is presented. A hybrid approach to MT, i.e. that uses a combination of the transfer approach and a corpus-based approach, is used. While presenting both experiences, the challenges faced are outlined and solutions are discussed.
A massive amount of documents are being posted online every minute. The task of document classifi... more A massive amount of documents are being posted online every minute. The task of document classification requires extensive background work on the content of documents, where keyword-based matching alone may not be sufficient. Much research has been carried out in several languages that has revealed significant results. However, Arabic documents still pose a great challenge due to the nature of Arabic language. Extracting roots or stems from the breakdown of multiple Arabic words and phrases are an important task that must be completed before applying text classification. The research at hand proposes an algorithm for classifying Arabic-Text documents using semantic relations between words based on an Arabic thesaurus, mainly synonyms, hyperonyms and hyponyms. The experiments conducted in this study evaluated the results using F1-Measure and compared them to results obtained via other existing methods, such as utilizing stemmers and part-of-speech taggers, where it indicated an incre...
Text, Speech and Language Technology, 2007
... Ahmed Guessoum and Rached Zantout Department of Computer Science, The University of Sharjah, ... more ... Ahmed Guessoum and Rached Zantout Department of Computer Science, The University of Sharjah, PO Box 27272, Sharjah, UAE guessoum@sharjah.ac ... word depending on these features must obviously be done very care-fully and is in fact a common mistake among native ...
2009 International Conference on Innovations in Information Technology (IIT), 2009
Automatic recognition of printed and handwritten documents remains an active area of research. Ar... more Automatic recognition of printed and handwritten documents remains an active area of research. Arabic is one of the languages that present special problems. Arabic is cursive and therefore necessitates a segmentation process to determine the boundaries of a ...
Proceedings of CIBITIC, 2006
Natural Language Processing (NLP) has gained a lot of importance nowadays with many applications ... more Natural Language Processing (NLP) has gained a lot of importance nowadays with many applications requiring real-time performance. In order to achieve the real-time requirements, the components of a NLP system should be made more efficient. An ...
When it comes to Arabic text documents, Text Categorization (TC) becomes a challenge. TC is neede... more When it comes to Arabic text documents, Text Categorization (TC) becomes a challenge. TC is needed for clustering purposes in order to complete Text Mining (TC). Based on the nature of Arabic language, extracting roots or stems from the breakdown of multiple Arabic words and phrases is important task before applying TC. The results obtained by applying the proposed algorithm are compared with the results of three popular algorithms. These algorithms are Khoja stemmer, Light stemmer, and Root extractor. The performance of these three techniques are evaluated and compared based on the accuracy of Naive Bayesian classifier. The obtained result demonstrates that these techniquesare not as promising as expected.Therefore, we decided to consider the position tagger and conceptual representation to answer the question, which approach enhances the Arabic TC performance? Arabic WordNet (AWN))is used as a lexical and semantic resource. The performance of new relation "Has-hyponym",suggested in this work, iscompared with otheralready used relations like Synset, term+ Synset, all Synsets, and Bag of words representation to demonstrate its effectiveness. From the experimental results, it was found that the new suggested relationimproved the Arabic text classification, at which the macro average F1 is raised to 0.75437compared with the performance of the other approaches.
IEEE GCC Conference & Exhibition, 2011
In this paper character recognition in Saudi Automobile License Plates is described. Due to speci... more In this paper character recognition in Saudi Automobile License Plates is described. Due to special properties of Saudi license plates, simpler procedures as compared to the ones used for Lebanese plates have been developed. A limited character set for recognition enables the development of smaller recognition trees. The developed procedure was applied to different characters taken from real license plates
MELECON 2014 - 2014 17th IEEE Mediterranean Electrotechnical Conference, 2014
ABSTRACT
2011 International Conference on Innovations in Information Technology, 2011
In this paper character recognition in Saudi Automobile License Plates is described. Due to speci... more In this paper character recognition in Saudi Automobile License Plates is described. Due to special properties of Saudi license plates, simpler procedures as compared to the ones used for Lebanese plates have been developed. A limited character set for recognition enables the development of smaller recognition trees. The developed procedure was applied to different characters taken from real license plates
In this paper character recognition in Saudi Automobile License Plates is described. Due to speci... more In this paper character recognition in Saudi Automobile License Plates is described. Due to special properties of Saudi license plates, simpler procedures as compared to the ones used for Lebanese plates have been developed. A limited character set for recognition enables the development of smaller recognition trees. The developed procedure was applied to different characters taken from real license plates
2012 2nd International Conference on Advances in Computational Tools for Engineering Applications (ACTEA), 2012
ABSTRACT Social networks contain large amounts of posts of different data types (text, images, so... more ABSTRACT Social networks contain large amounts of posts of different data types (text, images, sounds and videos). Textual posts express authors' opinions (with or against) or feeling (love, hate, optimism, pessimism, or anger). Such opinions are important for commercial and governmental organization since they help checking public opinion about a product, policy or an object in general. In this paper we present the application of two different approaches to classify Arabic Facebook posts. The first one depends on syntactic features, using common patterns used in different Arabic dialects to express opinions. These patterns achieved high accuracy in determining the polarity of a sentiment even when tested against new corpus. This approach acts on informal Arabic text, which has not been addressed before. Different setups were tried and the highest coverage and accuracy achieved were 49.5% and 83.4 % respectively. The second approach is an ordinary probabilistic model, Naïve-Bayes classifier, that assumes the independence of features in determining the class the highest coverage achieved in this approach was 60.5% in the first setup and 91.2% when Naïve search was used as a binary classifier to classify the posts as objective or subjective.
2012 2nd International Conference on Advances in Computational Tools for Engineering Applications (ACTEA), 2012
ABSTRACT Automatic detection and recognition of traffic signs is an important tool in intelligent... more ABSTRACT Automatic detection and recognition of traffic signs is an important tool in intelligent vehicles. It allows more autonomous vehicles and it can alert the driver to possible hazards and changes in the road. In this paper we focus on the recognition of a wide set of triangular traffic signs using a novel algorithm, the Number of Peaks. Once a traffic sign is detected, three horizontal lines (T, H, B) and three vertical lines (R, V, L) across the image are used to recognize the sign. The number of crossings from a black pixel to a white pixel (peak) on each line is calculated. A simple and fast decision-tree-like search algorithm uses the number of peaks to differentiate between the triangular road signs. A 100% correct detection rate is achievable even in a fairly noisy environment.