Mohamed Dahab

King AbdulAziz University (KAU) Jeddah, Saudi Arabia, COMPUTER SCIENCE, Faculty Member

Followers

Following

Co-authors

Public Views

InterestsView All (17)

Uploads

Papers by Mohamed Dahab

Automatic Identifying Rhythm of Arabic Poem

The poem in the Arabic language is a composition of verse to describe the sense of people to effe... more The poem in the Arabic language is a composition of verse to describe the sense of people to effect and share the feeling with listeners, the poem written in separate lines, that usually has figurative language and has a repeated rhythm and rhyme. Al-Khaleel Bin Ahmad Al-Frahide is the inventor of 'AlOrood' (‫)اىعسٗض‬ poem template science (PTS). He invented weighting of Arabic poem which identifies poem. The Arabic poem contains one or more poem segments (PS) (‫.)اىثيت‬ The PS is a correct construction lyrics group, weighted according to the knowledge of the rules and RS, be in the same unit matching by a specific 'TafEelAh' (‫)تفعييح‬ musical pattern (MP). The Arabic PS classified according to how it matches with (‫)تحس‬ poem template (PT). This paper provides set of algorithms to identify Arabic poem template of Arabic poem segments that rely on poem template science.

A Novel Information Retrieval Approach using Query Expansion and Spectral-based

Abstract—Most of the information retrieval (IR) models rank the documents by computing a score us... more Abstract—Most of the information retrieval (IR) models rank the documents by computing a score using only the lexicographical query terms or frequency information of the query terms in the document. These models have a limitation as they does not consider the terms proximity in the document or the term-mismatch or both of the two. The terms proximity information is an important factor that determines the relatedness of the document to the query. The ranking functions of the Spectral-Based Information Retrieval Model (SBIRM)
consider the query terms frequency and proximity in the document by comparing the signals of the query terms in the spectral domain instead of the spatial domain using Discrete Wavelet Transform (DWT). The query expansion (QE) approaches are used to overcome the word-mismatch problem by adding terms to query, which have related meaning with the query. The QE approaches are divided to statistical approach Kullback-Leibler divergence (KLD) and semantic approach PWNET that uses WordNet. These approaches enhance the
performance. Based on the foregoing considerations, the objective of this research is to build an efficient QESBIRM that combines QE and proximity SBIRM by implementing the SBIRM using the DWT and KLD or P-WNET. The experiments conducted to test and evaluate the QESBIRM using Text Retrieval Conference (TREC) dataset. The result shows that the SBIRM with the KLD or P-WNET model outperform the SBIRM model in precision (P@), R-precision, Geometric Mean Average Precision (GMAP) and Mean Average Precision (MAP).

Developing strategic expert system using multiple design approach

Automatic Generation of Question Bank Based on Pre-defined Templates

The preparation of question bank is a difficult and time consuming. This paper explains an algori... more The preparation of question bank is a difficult and time consuming. This paper explains an algorithm that provides solution to automatic generation of question bank based on a set of pre-defined templates. All possible questions are generated by parameterized concepts from a set of pre-defined templates. The generated questions cover all selected topics in all level of difficulties the form of a multiple-choice question (MCQ). The outputs can be used for both examinations and asynchronous training. If the output used in asynchronous training, it augmented with a set of brief explanation. A successful automatic generation of question bank has been developed for a biology course (Bio110) in KING ABDULAZIZ UNIVERSITY (KAU).

Download

Automatic Transliteration of an Arabic Dictionary

Arabic Language has two kinds of vowels: Long vowels which are written as normal letters; and sho... more Arabic Language has two kinds of vowels: Long vowels which are written as normal letters; and short vowels which are written as punctuation marks. Those short vowels are normally omitted in Modern Standard Arabic (MSA) words. MSA texts need to be augmented with diacritics as a step forward to be analyzed and lexical disambiguation. In this paper, we present a tool to transliterate an Arabic dictionary augmented with diacritics. Also, the tool will enrich the Arabic dictionary with part of speech (POS) and term pattern using the extracted transliteration. Generally; Arabic texts need to be supplied with short vowels in order to be analyzed. Search engines, text to speech engines, morphological analyzers and text mining tools are just some examples of applications that need Arabic texts to be vocalized before being processed.

Regular Expressions in Java

Regular expression (also known by pattern matching) is one of the most powerful tools available t... more Regular expression (also known by pattern matching) is one of the most powerful tools available to programmers for most of modern programming languages. This report targets students who have some experiences in Java programming language. In addition, it can be used in Java programming advanced course. In this report, we shall answer the following questions: • What is the regular expressions? • Why using regular expressions? • How to use regular expressions in Java?

Arabic Sentiment Lexicon (Data set V1)

CUGrid: Towards the Visualization of Aggregated Computing Resources in Campus Grid Systems

by Mohamed Dahab and Hesham Hassan

Forecasting Exchange Rates

International Journal of Rough Sets and Data Analysis, 2015

Rapid Generation Of Plant Protection Expert Systems

by Mohamed Dahab and Ahmed Said

Computers in Agriculture and Natural Resources, 23-25 July 2006, Orlando Florida, 2006

1 International Center for Agricultural Research in the Dry Areas (ICARDA), PO Box 5466, Aleppo, ... more

Pattern Based Concept Extraction for Arabic Documents

by Mohamed Dahab, Amira Idrees, and Hesham Hassan

Information Extraction from texts (IE) is one of the most promising areas of Knowledge Management... more Information Extraction from texts (IE) is one of the most promising areas of Knowledge Management (KM) applications including Knowledge Identification and Extraction. It can – for example - provide support in protocol analysis either in an automatic way (unsupervised extraction of information) or semi-automatic way (e.g. helping knowledge engineers locating the important facts in protocols, via information highlighting). In this paper we propose a semantic pattern concept extraction method which depends on applying a set of rules determined by an external agent for extracting concepts from a raw Arabic text. Considering that Arabic is lacking the existence of tools as well as necessary resources that could be used in IE, the proposed method succeeds to extract concepts from a raw Arabic text with no use of predefined resources such as Lexicon.

Developing a Generic Decision Support System for Poultry Feeding

Poultry breeding of birds such as chickens, ducks, and turkeys, provide humans mainly with meat a... more Poultry breeding of birds such as chickens, ducks, and turkeys, provide humans mainly with meat and eggs. It represents a great share of investment in many countries. Feeding is one of the factors that play an essential role in poultry industry. Moreover, feeding represents a major direct cost in poultry industry. Therefore, it is generally vital to deliver the best animal diet at the minimum cost, to gain more profit. However, mixing feed ingredients turns out to be more troublesome, since several issues got the opportunity to be involved all at the same time. In this paper, the linear programming algorithm is applied and used in a web application to help farmers and producers to find the minimum cost of feeding, considering many factors including: the purpose of breeding, poultry type, growth stage, nutritional requirements and available feedstuffs.

A Comparative Study on Arabic Stemmers

by Asma'a AL Ibrahem and Mohamed Dahab

Stemming is considered as a pre-processing step in many applications: text mining, information re... more Stemming is considered as a pre-processing step in many applications: text mining, information retrieval, machine translation etc. The Arabic language has many special cases or properties that affect stemming or any automatic method, it depends on both inflectional and derivational morphology to produce the various forms of the language words. Many researchers have proposed algorithms to solve the problems of stemming. This paper aims to make a comparison study among the existing Arabic stemmers, the comparison study is based on the methodologies, the usage, main idea, algorithm, the affixes, limitations, output, and the stemmers' sensitivity for both diacritics and context.

Query Answering Approach Based on Document Summarization

by IJMER Journal, Mohamed Dahab, and Hesham Hassan

The growing of online information obliged the availability of a thorough research in the domain o... more The growing of online information obliged the availability of a thorough research in the
domain of automatic text summarization within the Natural Language Processing (NLP)
community.The aim of this paper is to propose a novel approach for a language independent automatic
summarization approach that combines three main approaches. The Rhetorical Structure Theory
(RST), the query processing approach, and the Network Representationapproach (NRA). RST, as a
theory of major aspect for the structure of natural text, is used to extract the semantic relation behind
the text.Query processing approachclassifies the question type and finds the answer in a way that suits
the user’s needs. The NRA is used to create a graph representing the extracted semantic relation. The
output is an answer, which not only responses to the question, but also gives the user an opportunity to
find additional information that is related to the question.We implemented the proposed approach. As a
case study, the implemented approachis applied on Arabic text in the agriculture field. The
implemented approach succeeded in summarizing extension documents according to user's query. The
approach results have been evaluated using Recall, Precision and F-score measures

Download

Arabic Documents Classification Method a Step towards Efficient Documents Summarization

by Amira Idrees, Mohamed Dahab, Amira M. Idrees, and Mohamed YehiaDahab

The massive growth of online information obliged the availability of a thorough research in the d... more The massive growth of online information obliged the availability of a thorough research in the domain of automatic text summarization within the Natural Language Processing (NLP) community. To reach this goal, different approaches should be integrated and collaborated. One of these approaches is the classification od documents. Therefore, the aim of this paper is to propose a successful framework for agricultural documents classification as a step forward for a language independent automatic summarization approach. The main target of our serial research is to propose a complete novel framework which not only responses to the question, but also gives the user an opportunity to find additional information that is related to the question. We implemented the proposed method. As a case study, the implemented method is applied on Arabic text in the agriculture field. The implemented approach succeeded in classifying the documents submitted by the user. The approach results have been evaluated using Recall, Precision and F-score measures.

Download

Building A Sentiment Analysis Corpus With Multifaceted Hierarchical Annotation

A corpus is a collection of documents. An annotated corpus consists of documents or entities anno... more A corpus is a collection of documents. An annotated corpus consists of documents or entities annotated with some task related labels such as part of speech tags, sentiment etc. While it is customary to annotate a document for a specific task, it is also possible to annotate it for multiple tasks, resulting in a multifaceted annotation scheme. These annotations can be organized in a hierarchical fashion, if such a scheme naturally occurred in the data, resulting in a hierarchical text categorization problem. We developed a multifaceted, multilingual corpus for hierarchical sentiment analysis. The different facets include hierarchical nominal sentiment labels, a numerical sentiment score, language, and the dialect. Our corpus consists of 191K reviews of hotels in Saudi Arabia. The reviews are divided into eleven different categories. Within each category, the reviews are further divided into two positive and negative categories. The corpus contains 1.8 million tokens. Reviews are mostly written in Arabic and English but there are instances of other languages too.

Query Answering Approach Based on Document Summarization

by Amira Idrees, Amira M. Idrees, and Mohamed Dahab

The growing of online information obliged the availability of a thorough research in the domain o... more The growing of online information obliged the availability of a thorough research in the domain of automatic text summarization within the Natural Language Processing (NLP) community.The aim of this paper is to propose a novel approach for a language independent automatic summarization approach that combines three main approaches. The Rhetorical Structure Theory (RST), the query processing approach, and the Network Representationapproach (NRA). RST, as a theory of major aspect for the structure of natural text, is used to extract the semantic relation behind the text.Query processing approachclassifies the question type and finds the answer in a way that suits the user’s needs. The NRA is used to create a graph representing the extracted semantic relation. The output is an answer, which not only responses to the question, but also gives the user an opportunity to find additional information that is related to the question.We implemented the proposed approach. As a case study, the implemented approachis applied on Arabic text in the agriculture field. The implemented approach succeeded in summarizing extension documents according to user's query. The approach results have been evaluated using Recall, Precision and F-score measures.

Download

Arabic Text-Based Chat Topic Classification Using Discrete Wavelet Transform

Research studies on topic classification of chat conversations use the Vector Space Model (VSM) e... more Research studies on topic classification of chat conversations use the Vector Space Model (VSM) extensively. The VSM represents documents and queries as vectors of features. These features are the terms that occur within the collection. The VSM's limitation is that it does not consider the proximity of the terms in the document. The proximity information of the terms is an important factor that determines their position in the document. Another model used in information retrieval systems is the Spectral-Based Information Retrieval Method (SBIRM), which employs the Discrete Wavelet Transform (DWT) to rank documents according to document scores. This method's advantage is that it not only counts the frequency of the terms used in the document, but also considers their proximity by comparing the query terms in their spectral domain rather than their spatial domain. Based on the foregoing considerations, the objective of this research is to build a framework for Arabic Chat Classification (ACC) that can help detect illegal topics in Arabic text-based chat conversations. This framework is a combination of Information Retrieval (IR) and Machine Learning (ML) methods. The ACC implements two methods: first, the SBIRM using the DWT and second, the Naïve Bayes method. Two experiments were conducted to test the ACC framework, one for root-based and the other for stem-based chat conversations. The results showed that the former outperformed the latter in terms of accuracy, precision, and F-measure. The recall results were the same for both experiments.

AN APPROACH FOR BUILDING GENERIC DIAGNOSIS MODEL IN AGRICULTURAL DOMAIN

Expert systems development,is a complex,and expensive process that needs to be applied in an orga... more Expert systems development,is a complex,and expensive process that needs to be applied in an organized manner. Building expert systems has been seen as a modeling activity. The aim of this research is to pres ent an approach for building generic diagnosis model in the agricultural domain. This generic model has the ability to derive diagnoses for differently structured individual systems from the agriculture domain. The generic model,would ,serve both the developers and the implementers ,of a ,diagnosis expert system. The primary goal for developing this model, and consequently a tool based on it, isto facilitate the rapid development ,of a diagnosis component ,by offering ,the system builder a template that can be easily filled.

NEPER: a multiple strategy wheat expert system

by Mohamed Dahab and Ahmed Rafea

This paper presents a methodology for developing a strategic Expert System for wheat crop product... more This paper presents a methodology for developing a strategic Expert System for wheat crop production, which has been developed using a Multiple Design approach. This Expert System consists of six subsystems; namely, variety selection, land preparation, sowing, irrigation, fertilization, and harvest. These subsystems exchange data between them through a common database. Each subsystem advises wheat growers on the corresponding plan(s), comprising a set of agricultural/chemical operations before or during the growing season. Applying an appropriate plan reduces risk to farmers from having a problem during the growing season. The system was verified, validated, and, tested in the field. Beneficial economic and environmental impacts have been demonstrated.

Mohamed Dahab

Uploads

Papers by Mohamed Dahab

Log In