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.
دكتوراة
علم الحاسوب
جامعة UNIZA
2024
Doctor of Philosophy in Computer Science.
Faculty of Informatic and Computing.
Sultan Zainal Abidin University, Malaysia
Master’s Degree in COMPUTER INFORMATION SYSTEMS CIS
The Arab Academy for Banking and Financial Sciences (AABFS) Jordan.
Master’s Degree In EDUCATIONAL MANAGEMENT
Jerash Private University, Jordon
Bachelor’s Degree in COMPUTER SCIENCE.
I am working now Assistant Professor at Jerash University
Worked as a lecturer at Jerash University from 2022 until 2024. (part-time)
Worked as a lecturer at Northern Border University from 2014 until 2019.
Worked as a lecturer at Tabuk University-College of Preparatory Year- Department of computer science from 2012 until 2014
Worked as a lecturer at Najran University- Sharourah from 2010 until 2012.
Worked as a lecturer at Jerash University from 2009 until 2010. (part-time)
Worked as a teacher in the Ministry of Education. The appointed year 2005 until 2010.
This study investigates the application of adaptive decision tree models for predicting student performance, focusing on their role in educational data mining and adaptive learning. A major challenge in student assessment is identifying at-risk learners and dynamically adjusting predictive models to accommodate evolving learning patterns. Traditional static models often fail to capture these variations, highlighting the need for adaptive approaches. This research develops an adaptive decision tree framework that integrates incremental learning and adaptive parameter tuning to improve predictive accuracy and stability. Using the Student Performance dataset from the UCI Machine Learning Repository, the study applies multiple decision tree variants, including C4.5, CART, Random Forest, and Gradient Boosted Trees. The dataset, consisting of demographic, social, and academic attributes of students, is preprocessed and split into 70% training and 30% testing sets. Models are evaluated using accuracy, precision, recall, and F1-score to assess their effectiveness. The results demonstrate that adaptive decision tree models significantly outperform static models, with the best adaptive model (Gradient Boosted Decision Trees) achieving an accuracy of 84% and an F1-score of 82%, compared to 77% and 74%, respectively, for static counterparts. These findings highlight the potential of adaptive learning models to enhance personalized learning interventions and support datadriven curriculum design. This paper concludes by discussing the implications of adaptive decision tree applications in real-world educational settings and proposes future directions for improving predictive modeling in adaptive learning environments. Index Terms—Adaptive Learning, Student Performance Prediction, Decision Trees, Machine Learning, Educational Data Mining.
—Integrating the Internet of Things (IoT), Artificial Intelligence and big data analytics in Industry 4.0 has revolutionized industrial processes, enabling enhanced operational efficiency, predictive maintenance, and innovation. However, the increasing volume of sensitive and decentralized data generated by Industrial IoT (IIoT) devices introduces significant challenges, including data fragmentation, privacy concerns, and interoperability issues. Traditional centralized data analysis methods often fail to address these challenges effectively. This paper proposes a novel privacy-preserving federated learning framework tailored for IIoT environments to bridge these gaps. The framework enables secure and decentralized distributed big data analysis while ensuring data sovereignty and minimizing communication overhead. The proposed approach enhances predictive maintenance and anomaly detection by integrating advanced deep learning models with edge-fog-cloud architectures, fostering crosscompany collaboration and scalability. Experimental evaluations using real-world predictive maintenance datasets demonstrate the framework’s effectiveness in achieving high accuracy, optimized resource utilization, and reduced runtime. Additionally, incorporating clustering techniques improves model personalization, enhancing performance without compromising data privacy. This research establishes FL as a transformative solution for secure, collaborative intelligence in Industry 4.0 ecosystems, paving the way for sustainable and intelligent manufacturing environments. Index Terms—Big data, federated learning, Industry 4.0, IoT, predictive maintenance, privacy preservation
Governments around the world, especially in non-industrial nations look to upgrade the reception of their e-administrations by vanquishing the difficulties blocking the reception cycle. Notwithstanding, in spite of the development of e-government and its advantages, the residents' e-administrations reception is still low and flawed especially in agricultural nations because of many variables. An enormous number of studies have examined those elements in emerging nations; be that as it may, not many examinations tended to them in the Middle Easterner world. This paper presents a survey of the investigations that tended to the variables impacting e-government resident reception in Arabic nations, particularly Jordan. Like other non-industrial nations, Jordan is seeing low resident reception of e-administrations in spite of the fact that it accomplished an impressive development in e-government improvement. Perceiving the huge variables influencing e-government resident's reception is significant to upgrading the dynamic interaction for carrying out viable e-government, better comprehension of residents' requirements, guaranteeing a fruitful conveyance of top-notch internet-based benefits, and expanding resident's reception and utilization of e-services.
Countries all over the world pursue to improve their government system in order to provide efficient e-services to stakeholders in real time with minimum efforts. Regardless the inclusive adoption and benefits of using ICT, many developing countries face several implementation and adoption challenges. To understand the user adoption of e-services, several model are developed. However, most models concentrated on technological and social dimensions. Moreover, none of the former studies has made any further effort to develop and validate a unified model of e-government includes all the micro-environmental factors affecting e-government adoption. Consequently, this research develops a conceptual model based on PESTLE framework to address the effect of these factors with considering the moderated effect of government support. Taking into account, the effect of PESTLE factors significantly contributes to manage expenses, mitigate risks and attain competitive benefits.
All Rights Reseved © 2025 - Developed by: Prof. Mohammed M. Abu Shquier Editor: Ali Zreqat
