Mohammed Zeki Khedher | University of Jordan (original) (raw)
Papers by Mohammed Zeki Khedher
Text of Quran has been served in many forms. Recent attempts have presented such serves in corpus... more Text of Quran has been served in many forms. Recent attempts have presented such serves in corpus form. However no previous attempt made to deal with multiword in Quran in corpus form. This paper is based on presenting multiword corpus of Quran based on roots of the word rather than the word itself. This combines the relations between same words in addition to other words with common roots. This enriches the corpus since Arabic language word structure is based on root of the word. This corpus should enable future research in going deep in analyzing Quran ontology, Arabic language studies and inter relations between Quran and other Islamic resources, e.g. Hadith, Fiqh, Usool etc.
2015 IEEE Jordan Conference on Applied Electrical Engineering and Computing Technologies (AEECT), 2015
—This paper focuses on the effects of topic on the Arabic language used in Facebook, Twitter, new... more —This paper focuses on the effects of topic on the Arabic language used in Facebook, Twitter, news sites, blogging sites, and mobile phone messaging. The results presented in this paper are based on a comprehensive study that was carried out using 8,538 text samples from these five forums. The sample topics are categorized into nine categories: political, social, economic, academic, religious, scientific, sports, arts, and others. The effect of topic is analyzed on several Arabic language aspects including the language whether Arabic, English, or mixed; the alphabet whether Arabic, English, or Arabizi; the dialect whether standard, colloquial, or mixed; the use of symbols; the style whether normal, metaphor, cynical, vulgar, or other; and the text cohesion level. This paper shows that there are large differences found in these six language aspects among the nine topic categories. Most notably, standard and refined language is common in serious topics such as religion and politics. Colloquial Arabic dialect and weak cohesion with Arabizi alphabet is common in casual topics such as social and academic topics.
... Recognition of Typewritten Arabic characters gave good results using external features such a... more ... Recognition of Typewritten Arabic characters gave good results using external features such as character area ratio, n-th quadrant ratio, vertical line ratio, horizontal line ratio, number of upper edges, and other similar features (Al-Ohali, 1995). Online character recognition uses ...
The aim of the program described here is to provide the students taking the course of electric ma... more The aim of the program described here is to provide the students taking the course of electric machines with an on line information and tutorial which help them during the course of their study. The program contains textbook materials in a lively manner. This encourages the student to follow up the explanations in an interesting , easy to follow, self explanatory and step by step manner. The program consists of four modules: Transformer module , winding module, dc machines module and ac machines module. The first one was written in C-Language , while the other three modules were programmed using Visual Basic. It was found that the Visual Basic is quite suitable for such a problem. The four modules were integrated under one package using Visual Basic. The program was developed over a period of more than 3 years by students in their final year study under the two semesters final year project course. The program is still under test before full implementation along with course work.
E-laboratories are having increasing applications all over the world. Engineering management of s... more E-laboratories are having increasing applications all over the world. Engineering management of such laboratories has to start from clear definition of the purpose. This is followed by the pre-design arrangements; then to the various aspects of the design. After running such e-lab courses, the experience gained has to be evaluated. Different aspects of management of various steps are discussed in
… Processing, Pattern Recognition …, 2008
Users are still waiting for accurate optical character recognition solutions for Arabic handwritt... more Users are still waiting for accurate optical character recognition solutions for Arabic handwritten scripts. This research explores best sets of feature extraction techniques and studies the accuracy of well-known classifiers for Arabic letters. Depending on their position in the word, Arabic letters are drawn in four forms: Isolated, Initial, Medial, and Final. The principal component analysis technique is used to select best subset of features out of a large number of extracted features. We used parametric and non-parametric classifiers and found out that a subset of 25 features is needed to get 84% recognition accuracy using a linear discriminant classifier, and using more features does not substantially improve this accuracy. However, for features fewer than 25 features, a quadratic discriminant classifier is more accurate than the linear classifier. Classifiers that are parameterized for the individual four forms score better accuracy than classifiers that do not make use of this input information.
… Conference on Signal …, 2005
Recognition of characters greatly depends upon the features used. Several features of the handwri... more Recognition of characters greatly depends upon the features used. Several features of the handwritten Arabic characters are selected and discussed. An off-line recognition system based on the selected features was built. The system was trained and tested with realistic samples of handwritten Arabic characters. Evaluation of the importance and accuracy of the selected features is made. The recognition based on the selected features give average accuracies of 88% and 70% for the numbers and letters, respectively. Further improvements are achieved by using feature weights based on insights gained from the accuracies of individual features.
International journal of …, 2011
Aim. To investigate the relationship between high blood pressure (HBP) and obesity in Egyptian ad... more Aim. To investigate the relationship between high blood pressure (HBP) and obesity in Egyptian adolescents. Methods. A cross-sectional study of 1500 adolescents (11-19 years) in Alexandria, Egypt, was conducted. Resting BP was measured and measurements were categorized using the 2004 fourth report on blood pressure screening recommendations. Additional measures included height, weight, and waist and hip circumferences. Obesity was determined based on BMI, waist circumference (WC) and waist-to-hip ratio (WHR), and waist-to-height ratio (WHtR) indicators. Crude and adjusted odds ratios were used as measures of association between BP and obesity. Results. Prevalence rates of prehypertension and hypertension were 5.7% and 4.0%, respectively. Obesity was seen in 34.6%, 16.1%, 4.5%, and 16.7% according to BMI, WHR, WC, and WHtR, respectively. Adjusting for confounders, HBP was significantly associated with overall obesity based on BMI (OR = 2.18, 95%, CI = 1.38-3.44) and central obesity based on WC (OR = 3.14, 95%, CI = 1.67-5.94). Conclusion. Both overall obesity and central obesity were significant predictors of HBP in Egyptian adolescents.
The 7th International Conference on Information Technology, 2015
The internet and smartphone penetrations continue to rise reaching large percentages of the world... more The internet and smartphone penetrations continue to rise reaching large percentages of the world populations. Likewise, many Jordanians are actively communicating through the popular social networks and mobile phone messages. There are large questions and concerns related to the characteristics and quality of the language used in these forums and how to improve it. This study addresses these issues by collecting and analyzing a large sample of text from five sources: Facebook, Twitter, news sites, blogging sites, and mobile phone short messages. We analyzed the sample comprehensively including the sender, context, message, channel, and code. We present in this paper the results related to the used language, alphabet, dialect, text components, and style. The study concludes that the bilingualism problem is manifested in Twitter and Facebook with 24% and 14% of contributions in English, respectively. Moreover, 6.4% of the analyzed Arabic samples have English words and 13.2% are written in Arabizi (Arabic in English letters and numerals). The diglossia problem is manifested as 55.4% of the sample is in colloquial Arabic, 36.4% in the standard Arabic, and 8.2% in standard with some colloquial words.
International Journal of Computer Processing of Languages, 2009
The Arabic letters are used in many written languages. However, little work has been done to anal... more The Arabic letters are used in many written languages. However, little work has been done to analyze and characterize handwritten Arabic letters comprehensively. Such characterization is important for the active research in the computer processing of Arabic written scripts. We extract carefully selected features from a large database of handwritten Arabic letters, from the letter's secondary components, main body, skeleton, and boundary. These features are studied and statistically analyzed to reach the targeted characterization. Observations about the important writing style variations are presented and statistically specified. The Arabic letters have multiple forms depending on the letter's position in the word. Comparisons among the four main letter forms (isolated, initial, medial, and final) are also presented.
A fuzzy expert system for selected Arabic sub-words recognition is presented in this paper. For e... more A fuzzy expert system for selected Arabic sub-words recognition is presented in this paper. For each sub-word pattern, membership values are determined for a number of fuzzy sets defined on the features extracted from the pattern. These sub-words consist of two characters and are written cursively, so, the first step is to segment the sub-words into two objects, main and secondary objects, keeping the two characters connected and making use of the general and special features in the recognition process. Presence or absence of dots in a sub-word and the number of such dots are fuzzy features, since the dot(s) may not appear exactly above or below the related character and they may appear mixed together. Closed loop is a fuzzy feature also. The proposed expert system consists of two main parts. First, the preprocessing part includes the feature extraction step that provides sufficient information to the inference engine. Second, the inference engine which applies the suitable set of fuzzy rules and aggregates them towards the final decision
... Recognition of Typewritten Arabic characters gave good results using external features such a... more ... Recognition of Typewritten Arabic characters gave good results using external features such as character area ratio, n-th quadrant ratio, vertical line ratio, horizontal line ratio, number of upper edges, and other similar features (Al-Ohali, 1995). Online character recognition uses ...
E-laboratories are having increasing applications all over the world. Engineering management of s... more E-laboratories are having increasing applications all over the world. Engineering management of such laboratories has to start from clear definition of the purpose. This is followed by the pre-design arrangements; then to the various aspects of the design. After running such e-lab courses, the experience gained has to be evaluated. Different aspects of management of various steps are discussed in this paper. An example for e-lab experiments in electrical engineering is given. Evaluation of understanding of students using e-lab compared to normal labs is discussed. Online laboratories, however, are not as mature as online courses yet.
Text of Quran has been served in many forms. Recent attempts have presented such serves in corpus... more Text of Quran has been served in many forms. Recent attempts have presented such serves in corpus form. However no previous attempt made to deal with multiword in Quran in corpus form. This paper is based on presenting multiword corpus of Quran based on roots of the word rather than the word itself. This combines the relations between same words in addition to other words with common roots. This enriches the corpus since Arabic language word structure is based on root of the word. This corpus should enable future research in going deep in analyzing Quran ontology, Arabic language studies and inter relations between Quran and other Islamic resources, e.g. Hadith, Fiqh, Usool etc.
2015 IEEE Jordan Conference on Applied Electrical Engineering and Computing Technologies (AEECT), 2015
—This paper focuses on the effects of topic on the Arabic language used in Facebook, Twitter, new... more —This paper focuses on the effects of topic on the Arabic language used in Facebook, Twitter, news sites, blogging sites, and mobile phone messaging. The results presented in this paper are based on a comprehensive study that was carried out using 8,538 text samples from these five forums. The sample topics are categorized into nine categories: political, social, economic, academic, religious, scientific, sports, arts, and others. The effect of topic is analyzed on several Arabic language aspects including the language whether Arabic, English, or mixed; the alphabet whether Arabic, English, or Arabizi; the dialect whether standard, colloquial, or mixed; the use of symbols; the style whether normal, metaphor, cynical, vulgar, or other; and the text cohesion level. This paper shows that there are large differences found in these six language aspects among the nine topic categories. Most notably, standard and refined language is common in serious topics such as religion and politics. Colloquial Arabic dialect and weak cohesion with Arabizi alphabet is common in casual topics such as social and academic topics.
... Recognition of Typewritten Arabic characters gave good results using external features such a... more ... Recognition of Typewritten Arabic characters gave good results using external features such as character area ratio, n-th quadrant ratio, vertical line ratio, horizontal line ratio, number of upper edges, and other similar features (Al-Ohali, 1995). Online character recognition uses ...
The aim of the program described here is to provide the students taking the course of electric ma... more The aim of the program described here is to provide the students taking the course of electric machines with an on line information and tutorial which help them during the course of their study. The program contains textbook materials in a lively manner. This encourages the student to follow up the explanations in an interesting , easy to follow, self explanatory and step by step manner. The program consists of four modules: Transformer module , winding module, dc machines module and ac machines module. The first one was written in C-Language , while the other three modules were programmed using Visual Basic. It was found that the Visual Basic is quite suitable for such a problem. The four modules were integrated under one package using Visual Basic. The program was developed over a period of more than 3 years by students in their final year study under the two semesters final year project course. The program is still under test before full implementation along with course work.
E-laboratories are having increasing applications all over the world. Engineering management of s... more E-laboratories are having increasing applications all over the world. Engineering management of such laboratories has to start from clear definition of the purpose. This is followed by the pre-design arrangements; then to the various aspects of the design. After running such e-lab courses, the experience gained has to be evaluated. Different aspects of management of various steps are discussed in
… Processing, Pattern Recognition …, 2008
Users are still waiting for accurate optical character recognition solutions for Arabic handwritt... more Users are still waiting for accurate optical character recognition solutions for Arabic handwritten scripts. This research explores best sets of feature extraction techniques and studies the accuracy of well-known classifiers for Arabic letters. Depending on their position in the word, Arabic letters are drawn in four forms: Isolated, Initial, Medial, and Final. The principal component analysis technique is used to select best subset of features out of a large number of extracted features. We used parametric and non-parametric classifiers and found out that a subset of 25 features is needed to get 84% recognition accuracy using a linear discriminant classifier, and using more features does not substantially improve this accuracy. However, for features fewer than 25 features, a quadratic discriminant classifier is more accurate than the linear classifier. Classifiers that are parameterized for the individual four forms score better accuracy than classifiers that do not make use of this input information.
… Conference on Signal …, 2005
Recognition of characters greatly depends upon the features used. Several features of the handwri... more Recognition of characters greatly depends upon the features used. Several features of the handwritten Arabic characters are selected and discussed. An off-line recognition system based on the selected features was built. The system was trained and tested with realistic samples of handwritten Arabic characters. Evaluation of the importance and accuracy of the selected features is made. The recognition based on the selected features give average accuracies of 88% and 70% for the numbers and letters, respectively. Further improvements are achieved by using feature weights based on insights gained from the accuracies of individual features.
International journal of …, 2011
Aim. To investigate the relationship between high blood pressure (HBP) and obesity in Egyptian ad... more Aim. To investigate the relationship between high blood pressure (HBP) and obesity in Egyptian adolescents. Methods. A cross-sectional study of 1500 adolescents (11-19 years) in Alexandria, Egypt, was conducted. Resting BP was measured and measurements were categorized using the 2004 fourth report on blood pressure screening recommendations. Additional measures included height, weight, and waist and hip circumferences. Obesity was determined based on BMI, waist circumference (WC) and waist-to-hip ratio (WHR), and waist-to-height ratio (WHtR) indicators. Crude and adjusted odds ratios were used as measures of association between BP and obesity. Results. Prevalence rates of prehypertension and hypertension were 5.7% and 4.0%, respectively. Obesity was seen in 34.6%, 16.1%, 4.5%, and 16.7% according to BMI, WHR, WC, and WHtR, respectively. Adjusting for confounders, HBP was significantly associated with overall obesity based on BMI (OR = 2.18, 95%, CI = 1.38-3.44) and central obesity based on WC (OR = 3.14, 95%, CI = 1.67-5.94). Conclusion. Both overall obesity and central obesity were significant predictors of HBP in Egyptian adolescents.
The 7th International Conference on Information Technology, 2015
The internet and smartphone penetrations continue to rise reaching large percentages of the world... more The internet and smartphone penetrations continue to rise reaching large percentages of the world populations. Likewise, many Jordanians are actively communicating through the popular social networks and mobile phone messages. There are large questions and concerns related to the characteristics and quality of the language used in these forums and how to improve it. This study addresses these issues by collecting and analyzing a large sample of text from five sources: Facebook, Twitter, news sites, blogging sites, and mobile phone short messages. We analyzed the sample comprehensively including the sender, context, message, channel, and code. We present in this paper the results related to the used language, alphabet, dialect, text components, and style. The study concludes that the bilingualism problem is manifested in Twitter and Facebook with 24% and 14% of contributions in English, respectively. Moreover, 6.4% of the analyzed Arabic samples have English words and 13.2% are written in Arabizi (Arabic in English letters and numerals). The diglossia problem is manifested as 55.4% of the sample is in colloquial Arabic, 36.4% in the standard Arabic, and 8.2% in standard with some colloquial words.
International Journal of Computer Processing of Languages, 2009
The Arabic letters are used in many written languages. However, little work has been done to anal... more The Arabic letters are used in many written languages. However, little work has been done to analyze and characterize handwritten Arabic letters comprehensively. Such characterization is important for the active research in the computer processing of Arabic written scripts. We extract carefully selected features from a large database of handwritten Arabic letters, from the letter's secondary components, main body, skeleton, and boundary. These features are studied and statistically analyzed to reach the targeted characterization. Observations about the important writing style variations are presented and statistically specified. The Arabic letters have multiple forms depending on the letter's position in the word. Comparisons among the four main letter forms (isolated, initial, medial, and final) are also presented.
A fuzzy expert system for selected Arabic sub-words recognition is presented in this paper. For e... more A fuzzy expert system for selected Arabic sub-words recognition is presented in this paper. For each sub-word pattern, membership values are determined for a number of fuzzy sets defined on the features extracted from the pattern. These sub-words consist of two characters and are written cursively, so, the first step is to segment the sub-words into two objects, main and secondary objects, keeping the two characters connected and making use of the general and special features in the recognition process. Presence or absence of dots in a sub-word and the number of such dots are fuzzy features, since the dot(s) may not appear exactly above or below the related character and they may appear mixed together. Closed loop is a fuzzy feature also. The proposed expert system consists of two main parts. First, the preprocessing part includes the feature extraction step that provides sufficient information to the inference engine. Second, the inference engine which applies the suitable set of fuzzy rules and aggregates them towards the final decision
... Recognition of Typewritten Arabic characters gave good results using external features such a... more ... Recognition of Typewritten Arabic characters gave good results using external features such as character area ratio, n-th quadrant ratio, vertical line ratio, horizontal line ratio, number of upper edges, and other similar features (Al-Ohali, 1995). Online character recognition uses ...
E-laboratories are having increasing applications all over the world. Engineering management of s... more E-laboratories are having increasing applications all over the world. Engineering management of such laboratories has to start from clear definition of the purpose. This is followed by the pre-design arrangements; then to the various aspects of the design. After running such e-lab courses, the experience gained has to be evaluated. Different aspects of management of various steps are discussed in this paper. An example for e-lab experiments in electrical engineering is given. Evaluation of understanding of students using e-lab compared to normal labs is discussed. Online laboratories, however, are not as mature as online courses yet.