كتابة النص: الأستاذ الدكتور يوسف أبو العدوس - جامعة جرش قراءة النص: الدكتور أحمد أبو دلو - جامعة اليرموك مونتاج وإخراج : الدكتور محمد أبوشقير، حمزة الناطور، علي ميّاس تصوير : الأستاذ أحمد الصمادي الإشراف العام: الأستاذ الدكتور يوسف أبو العدوس
فيديو بمناسبة الإسراء والمعراج - إحتفال كلية الشريعة بجامعة جرش 2019 - 1440
فيديو بمناسبة ذكرى المولد النبوي الشريف- مونتاج وإخراج الدكتور محمد أبوشقير- كلية تكنولوجيا المعلومات
التميز في مجالات التعليم والبحث العلمي، وخدمة المجتمع، والارتقاء لمصاف الجامعات المرموقة محليا واقليميا وعالميا.
المساهمة في بناء مجتمع المعرفة وتطوره من خلال إيجاد بيئة جامعية، وشراكة مجتمعية محفزة للابداع، وحرية الفكر والتعبير، ومواكبة التطورات التقنية في مجال التعليم، ومن ثم رفد المجتمع بما يحتاجه من موارد بشرية مؤهلة وملائمة لاحتياجات سوق العمل.
تلتزم الجامعة بترسيخ القيم الجوهرية التالية: الإلتزام الإجتماعي والأخلاقي، الإنتماء،العدالة والمساواة، الإبداع، الجودة والتميّز، الشفافية والمحاسبة، الحرية المنظبطة والمستقبلية.
PhD in Artificial intelligence, University of Banking and Financial Science, Amman-Jordan.(2009)
M.Sc. in Computer Information Systems, University of Banking and Financial Science, Amman-Jordan.(2005)
B.Sc. in Computer Science, yarmouk university, Irbid-Jordan. (2002)
To
From
#
Part-Time Lecturer, information technology faculty, Al-Albait University, Mafrak-Jordan.
2008
2005
1
Assistant Professor, Computer Information System Department, Amman Arab University, Amman-Jordan.
April 2015
October 2009
2
Associate Professor, Computer Information System Department, Amman Arab University, Amman-Jordan.
October 2015
3
Associate Professor, Cyber Security Department, Zarqa University, Zarqa-Jordan.
2023
4
Associate Professor, Computer Science Department, Jarash University, Jarash-Jordan.
now
march 2024
5
Cervical cancer is one of the most known health problems faced by women around the world. Early detection ofcervical cancer may reduce the mortality rate. Pap smear images are new techniques used for screening cervical cancer.This paper excludes the nucleus of pap smear images, and the resultant images are classified into seven classes based onthe surrounding region nucleus. Automated features are extracted using three pre-trained convolutional neural networks(CNN). The resultant features are twenty-one. The principal component analysis reduces the dimensionality and selects themost significant features into ten features. These features are fed to two types of machine learning algorithms: supportvector machine (SVM) classifier and random forest classifier. The support vector machine classifier achieved the highestaccuracy for seven classes, reaching 93.1%. This method will help the physicians in the diagnosis of cervical cancerdepending on the tissues, not the nucleus. Furthermore, the result can be enhanced using a huge amount of data.
Named entities recognition systems (Proper Names) are used in the development of many natural language processing applications. There is a paucity of published research in the field of identifying the named entities from texts written in Arabic. This is due to the fact that the Arabic language has a specificity regarding the complexity of spelling and morphology, which is an obstacle to the development of a technique to identify the names of the Arabic entities or the so-called Arabic Named Entity Recognition system (ANER). This paper presented the experiments conducted to identify the appropriate technique to design a robust and reliable system for identifying Arabic entities. For this purpose, this study focuses on the most common state-of-art in the field of identification of Arabic named entities, then a comparison was made between five of the most famous tools that interested in identifying the Arab entities, after that, integrated each of two tools together to get 10 different parallel techniques. The results of the comparison between the tools showed that Rosette achieved the best results followed by Madamira, while it was the worst performance results in the gate tool and for hybrid systems, the R-F (combining Rosette and Farasa) achieved the best performance with better accuracy than individual tools.
In this paper a new block grouping technique called “horizontal block grouping technique” is proposed and tested against three main factors; first: its ability to minimize the detectability of the resulting stego image. Second: host image distortion. Third: the time needed to choose the best cover from a collection of cover images. To test and evaluate the new horizontal block grouping technique we used four existing dividing ideas to divide the cover and the secret images into blocks of different sizes; for each block and its surrounding areas we calculated the mean, variance, and skewness as statistical measures. the collected statistics about each block will be used to find its similarity compared to the other blocks. Our proposed horizontal block grouping technique idea is to group the secret and the cover images blocks in a way that allow us to measure the similarity of 256 blocks for the secret image as a one group; with 16 groups created for the cover image which contains 4096 blocks. At last; the most suitable cover image for each dividing method that uses our new horizontal block grouping technique is chosen to hide the secret image within the chosen cover image using the least significant bit (LSB) technique. Wavelet based domain (WBS) and Fisher Linear Discriminator (FLD) were used to assess the robustness against detectability for the stego image, also we used the Peak signal-to-noise ratio(PSNR) to compare between the four versions (each version is implemented using our new horizontal grouping technique) in maintaining minimum distortion in the host image. The results show that (4×2) blocking gives the best security and the best minimum distortion, and (1×4) was the fastest version.
Very little research has been carried out on Arabic text. Arabic text nature and properties are different than the English and other languages texts, Arabic language text preprocessing is more challenging. This study proposed then explored the use of Genetic Algorithms (GA) in the vector space model (VSM) for the Cosine, and Jaccard as a similarity measures and fitness functions. Objective: This paper proposed, created, then compared 15 different combinations for the GA to improve the user query in the VSM when the Cosine, and Jaccard are used as a similarity measures. The GA combinations was created based on mixing a number of crossover strategies, mutations ideas, and fitness functions. Our goal is to find the best GA combination that can achieve the highest improvement for the user query in the VSM when the data collection is an Arabic language data collection. Results: Our results shows that; when using the Cosine, and Jaccard as a similarity measures then the GA approach which uses the Jaccard similarity as a fitness function, one point crossover operator, and chromosomal mutation is the best IR system in VSM with 12.48% improvement compared to the traditional approach. Conclusion: when comparing our results with other studies that used the DICE, and Inner Product as a similarity measures; we recommend the GA approach which uses one-point crossover operator, point mutation, and Inner Product similarity as a fitness function to be used with the Arabic data collections since it is the best combination that can improve the performance.
Mobile banking allows bank customers to conduct bank transactions at anytime from any place. The usage of mobile banking services is still in early stage compared to other services conducted by the banks sector. This study is important for the banking industry since it will provide practical recommendations to the banking industry in Jordan as a developing country. This study achieves three main goals: first; we developed a modified model by adding and removing new factors to the Unified Theory of Acceptance and Use of Technology (UTAUT) model; which is considered as one of the most powerful models in investigating the factors that affect the technology adoption decision of mobile banking services. The modifications on the UTAUT model were in two directions, the first direction was by adding new moderator factor called the influence of education. The second direction was by adding the Reliability, Design Issues, and Security as a three technology related factors to the UTAUT model. Second; we studied and investigated the factors that affect the technology adoption decision of mobile banking services in Jordan. We also explored if those factors are moderated by the proposed moderator factors or not. For this purpose we proposed 21 hypothesis, then we designed a questionnaire that is distributed to figure out the customer believes and intention to adopt mobile banking services. The questionnaire was distributed to 174 persons; from this number we approved 162 questionnaires for the purposes of research and analysis. We tested our proposed hypothesis using PLS Path Modeling. Third; we validated the modified model using the Varimax procedure; in which the loading factor values were more than 0.6, Kaiser-Mayer-Olkin (KMO) values were more than 0.5, and the Eigen values were more than one. The results shows our proposed model is valid, and that the Security factor plays the most significant factor on the intention to adopt m-bank services, and the Facilitating Conditions (FC) has a powerful effects in the actual use of m-bank services.
Websites like all web applications evolved very quickly, E-Companies are in highly competitive environment, they have to follow the customer needs and their competitors’ performance. To survive in this highly competitive environment; companies can adopt many alternatives; amongst them is the continues corrections and enhancements for the company’s website to meet the customer requirements. These corrections and enhancements occur much more frequent than those in traditional software, this mean that the need for reengineering will occur in shorter period of time compared to traditional software. Reengineering takes time, resources, and money ,so we want to make sure that we will do it in a way that will help us to reduce the need for website reengineering in the future, this can be accomplished if we use suitable software reengineering process model, that will address the needs of the website as a part of the software reengineering process, such model is not there yet ,so in this paper we will propose new cyclic process model that is suitable for reengineering websites, there are two main benefits for the proposed cyclic model; first: for each of the activities presented within the model it can be revisited, and for any particular cycle during the reengineering process, the process can be terminated after any one of these activities. Second: based on its cyclic nature; the model is suitable to be used with any approach to software re-engineering such as the Big Bang approach, incremental approach, and evolutionary approach.
The Use of genetic algorithms in the Information retrieval (IR) area, especially in optimizing a user query in Arabic data collections is presented in this paper. Very little research has been carried out on Arabic text collections. Boolean model have been used in this research. To optimize the query using GA we used different fitness functions, different mutation strategies to find which is the best strategy and fitness function that can be used with Boolean model when the data collection is the Arabic language. Our results show that the best GA strategy for the Boolean model is the GA (M2, Precision) method.
All Rights Reseved © 2025 - Developed by: Prof. Mohammed M. Abu Shquier Editor: Ali Zreqat
