RSS 1.0Computer Science
Sub-communities within this community
Collections in this community
Recent Submissions
-
Efficient Retrieval of Patient Data for Emergency Medical Care: A Biometric Integration ApplicationIn the high-pressure setting of ambulance-based care, conventional methods relying on verbal communication or identification documents often lead to errors and delays. To address these challenges, our proposal involves integrating biometric identification techniques using fingerprint scanning to retrieve patient data. The application ensures seamless integration with healthcare providers’ systems, guaranteeing rapid and secure access to essential patient data, particularly emphasizing its utility within the time-sensitive ambulance environment. This project is motivated by the urgent need to streamline patient data retrieval during medical emergencies, particularly for unconscious individuals. Existing systems are fragmented, causing delays and impeding healthcare providers from delivering timely and suitable treatment. By leveraging biometric technology, our goal is to significantly enhance response times and elevate patient care, ultimately saving lives. The significance of this project aligns with Saudi Arabia’s Vision 2030 goals of transforming the Kingdom’s healthcare system. It is also in harmony with the United Nations’ Sustainable Development Goals, particularly SDG 3, which seeks to ensure healthy lives and promote well-being for all. Anticipated outcomes of this project include the development of an advanced ambu lance application for efficient patient data retrieval during emergency medical care. This is expected to improve response times, enhance patient data security and privacy, and provide practical recommendations for real-world implementation.
-
Security and Privacy in Smart Cities Using Artificial Intelligence against Cyber Attacks Using LSTM ModellingA smart city is a city that uses sensors to collect information from environmental elements and analyze it in real time. A smart city improves social offices, transportation, and open spaces while advancing maintainability. This article aims to clarify cyber security and reveal insight into digital assurance, smart city examine-action, and boards, and give a few solutions to the various worries of residents who need digitization. It features questions related to metropolitan foundations, public prosperity, well-being, and promising responses to similar things, while also leveraging human reasoning and artificial intelligence. The significance of the present work is that the general population and the surface area of metropolitan regions are rapidly developing; this speedy advancement requires a collaborative organization to deal with the issues made. In the context of smart cities, security, and privacy are major issues. This work explores the use of LSTM modeling and artificial intelligence to overcome these problems. Utilizing the UNSW-15 dataset to create an intrusion detection system especially suited for smart city contexts is part of the study process. The sequential patterns in network traffic data are intended to be captured by the LSTM-based model architecture. With a test accuracy of 99.68% and a low test loss of 0.0112, the model demonstrates excellent accuracy and is useful for correctly recognizing and categorizing network threats. To secure sensitive information inside the network traffic data, anonymization, and encryption techniques are also used, which involve privacy considerations. The study demonstrates how LSTM-based models might improve security and privacy in smart cities, laying the groundwork for further investigation and advancements in this area.
-
Innovation, leadership, and education: How Effat University is paving the way for Vision 2030Higher education institutions like Effat University play a critical role in realizing the ambitious goals of Saudi Arabia’s Vision 2030, which emphasizes adaptability, agility, and sustainability in the educational sector. With the higher education landscape undergoing rapid transformation globally, institutions are compelled to rethink curricula and align more closely with the changing needs of students, industry, and the government. Effat University, situated at the confluence of Saudi Arabia’s Vision 2030 and the global Sustainable Development Goals (SDGs), shows adaptability, agility, and sustainability in the higher education sector. At the heart of Effat’s mission lies the IQRA core values, anchoring its academic and administrative endeavors and fostering graduates who are holistic, ethically grounded, and attuned to global challenges. This book chapter investigates Effat University’s distinctive approach, fortified by innovative initiatives, transformative leadership, expansive research activities, and the unwavering IQRA principles, as it positions itself to further the goals of Vision 2030 and the SDGs. Effat’s research, diverse in its scope and impact, ranges from cutting-edge technological advancements to interdisciplinary collaborations that address both local and global challenges. Using a mixed-method approach and drawing from internal data and insights from the university’s archives the chapter underscores Effat University’s commitment to innovation, interdisciplinary education, research excellence, international collaborations, and sustainable practices, all harmonized by the guiding IQRA values. These concerted efforts resonate deeply with Vision 2030 and the SDGs, setting the stage for sustained academic excellence and solid foundation for future academic and societal progress.
-
Enhancing Cybersecurity for IoT-Based DevicesThe Internet of Things (IoT), which has blended into modern society and revolutionized how we engage with technology in theoretical and practical contexts, has become an integral part of our daily lives. It has become a key player, actively helping to protect our devices and ensure their best performance. Our project intends to create a cutting-edge IoT-based security management system in response to the current issues in smart houses. Innovative solutions are required because protecting expensive equipment and the environment is becoming increasingly important. In this project, we embrace a wide range of solutions that make use of specialized tech nologies, such as visual monitoring systems, fire warning mechanisms, gas detection systems, water leak detection systems, and detecting sensors. These technologies col lectively contribute to creating a secure and responsive environment. The integrated system will include several crucial parts, including an embedded system, a database system, a thorough log system, and a flexible control program. Data collection for important factors including temperature, humidity, motion, smoke, the presence of water, and voltage fluctuations will be entrusted to a network of sensors. The data will then be processed and examined to guarantee the highest level of security and effectiveness. To further enhance the system’s responsiveness, we will implement an alert notification system to keep owners updated on any anomalies or potential dangers through email alerts and SMS messaging. It will enable prompt action to mitigate risks and preserve the integrity of the smart houses Our innovative IoT-based security management system for smart houses is being developed in line with the goal of fostering the global transition to smart homes by designing and developing sustainable, high-tech living environments. Achieving Sustainable Development Goal 11 (SDG 11), which is to make cities and human settlements inclusive, safe, resilient, and sustainable, is directly impacted by our work. Our goal is to create intelligent ii and secure living environments that foster harmony and well-being by leveraging IoT technologies to increase efficiency and security. Through the implementation of eco-friendly and energy-efficient solutions, our initiative also indirectly supports a number of other SDGs, including SDG 13 (climate action) and SDG 7 (affordable and clean energy). By guaranteeing the responsible use of resources in smart home opera tions, we also contribute to SDG 12 (responsible consumption and production).Our initiative directly contributes to Vision 2030’s objective of enhancing Saudi Arabia’s technological capabilities in the field of innovation and technology. By integrating IoT technologies into smart homes, we help achieve the vision’s objective of establish ing the nation as a center of innovation and a pioneer in cutting-edge technologies. Essentially, our creative strategy makes use of Internet of Things technology to offer smart homes a safe, secure, and intelligently controlled environment. In keeping with the vision of smarter and more resilient living spaces, we seek to improve the general quality of life for individuals and families in a sustainable and technologically advanced manner by protecting valuable assets and maximizing resource utilization.
-
Sudden Fall Detection and Prediction Using AI TechniquesFall prediction is a critical process in ensuring the safety and well-being of individuals, particularly the elderly population. This paper focuses on the development of a fall detection and prediction system using wearable sensors and machine learning algorithms. The system issues an alarm upon predicting the occurrence of falling and sends alerts to a monitoring centre for timely assistance. Wearable sensor devices, including Inertial Measurement Units (IMUs) equipped with accelerometers, gyroscopes, and magnetometers are utilized for data collection. UPFALL, a comprehensive online freely available dataset, had been utilized for training and verifying the proposed system. Several machine learning algorithms, such as K-Nearest Neighbours (KNN), Random Forest, Support Vector Machine (SVM), and Gradient Boosting, are implemented and evaluated. Among these algorithms, KNN demonstrates the highest effectiveness for fall detection having an accuracy of 93.5%. Furthermore, deep learning models, including Gated Recurrent Units (GRU), Long Short-Term Memory (LSTM), and Convolutional Neural Network (CNN), are employed. The GRU model exhibits superior performance among the deep learning approaches by having the least train and test loss of 0.219 and 0.267 respectively. An early fall prediction function is incorporated by establishing a threshold selection process based on logical analysis. The maximum voting concept is employed to determine the optimal threshold.
-
Developing a Messaging Application that Filters SMS Spam Messages Using Machine LearningThe increasing prevalence of SMS spam poses a significant challenge as mobile devices have become integral to daily life. Spam messages target individuals and can lead to high impacts, as they can evolve into phishing attacks or even social engineering. Our project holds significance in contributing to the safety of the community by reducing the number of spam victims. It aims to improve existing spam filtering solutions to provide a safer and more user-friendly experience, thereby reducing the vulnerability of users to spam and phishing attacks. Through state-of-the-art analysis, we identified a common gap: the lack of real-world application testing. In our methodology, we utilized the TensorFlow Lite Model Maker library to simplify the adaptation and deployment of an NLP neural network model text classification model on mobile devices. Our result is a meticulously designed user-friendly application that flags spam messages in real-time, o ering a safer messaging experience.
-
Federated Learning for Intrusion Detection in Internet of VehiclesThe Internet of Vehicles (IoV) is rapidly evolving, bringing vehicles into a unified network and revolutionizing connectivity and convenience. By enabling seamless communication between vehicles, infrastructure, and cloud services, IoV holds the potential to improve traffic management, road safety, and passenger experiences. However, this increased connectivity also exposes the IoV to new security challenges. Protecting against cyber-attacks on Vehicle-to-Everything (V2X) network communications is now more crucial than ever before. The objective of this senior project is to create an Intrusion Detection System (IDS) tailored for charging stations for electric vehicles, using federated learning (FL) and machine/deep learning methods to improve the detection of abnormal activities and cyber threats. To address IoV challenges, we require complex network traffic analysis and efficient machine learning algorithms for real-time cyber attack prediction. Scaling out a distributed IDS adds further complexity. Our project proposes an FL approach, that decentralizes training and preserves privacy. IoV components can update the intrusion detection model using local data without sharing sensitive information. The project aims to achieve two outcomes: first, developing an IDS capable of detecting and mitigating common vehicular network attacks effectively, with results including performance metrics; second, contributing significantly to advancing cybersecurity in the IoV domain by demonstrating the feasibility of FL for intrusion detection. The privacy-preserving nature of our approach aligns with emerging trends in decentralized cybersecurity solutions, ensuring data security and integrity in IoV environments. The project evaluated 20 machine learning algorithms that led to the selection of ExtraTreesClassifier as the optimal ML algorithm for our global model, which achieved an accuracy of 83.38%. While the specialized scenario-specific submodels attained very high accuracies ranging from 99.91% to 99.95%, the FL approach allowed for a comprehensive and adaptable solution capable of handling the complex and evolving IoV environment.
-
Machine Unlearning: An Overview of the Paradigm Shift in the Evolution of AIThe rapid advancements in artificial intelligence (AI) have primarily focused on the process of learning from data to acquire knowledge for smart systems. However, the concept of machine unlearning has emerged as a transformative paradigm shift in the field of AI, due to the amount of false information that have been learned over the past. Machine unlearning refers to the ability of AI systems to reverse or discard previously acquired knowledge or patterns, enabling them to adapt and refine their understanding in response to changing circumstances or new insights. This paper explores the concept of machine unlearning, its implications, methods, challenges, and potential applications. The paper begins by providing an overview of the traditional learning-based approaches in AI and the limitations they impose on system adaptability and agility. It then delves into the concept of machine unlearning, discussing various techniques and algorithms employed to remove or modify learned knowledge from AI models or datasets.
-
Metabolomic profiling reveals altered phenylalanine metabolism in Parkinson’s disease in an Egyptian cohortIntroduction: Parkinson’s disease (PD) is the most common motor neurodegenerative disease worldwide. Given the complexity of PD etiology and the different metabolic derangements correlated to the disease, metabolomics profiling of patients is a helpful tool to identify patho-mechanistic pathways for the disease development. Dopamine metabolism has been the target of several previous studies, of which some have reported lower phenylalanine and tyrosine levels in PD patients compared to controls.Methods: In this study, we have collected plasma from 27 PD patients, 18 reference controls, and 8 high-risk controls to perform a metabolomic study using liquid chromatography-electrospray ionization–tandem mass spectrometry (LC-ESI-MS/MS).Results: Our findings revealed higher intensities of trans-cinnamate, a phenylalanine metabolite, in patients compared to reference controls. Thus, we hypothesize that phenylalanine metabolism has been shifted to produce trans-cinnamate via L-phenylalanine ammonia lyase (PAL), instead of producing tyrosine, a dopamine precursor, via phenylalanine hydroxylase (PAH).Discussion: Given that these metabolites are precursors to several other metabolic pathways, the intensities of many metabolites such as dopamine, norepinephrine, and 3-hydroxyanthranilic acid, which connects phenylalanine metabolism to that of tryptophan, have been altered. Consequently, and in respect to Metabolic Control Analysis (MCA) theory, the levels of tryptophan metabolites have also been altered. Some of these metabolites are tryptamine, melatonin, and nicotinamide. Thus, we assume that these alterations could contribute to the dopaminergic, adrenergic, and serotonergic neurodegeneration that happen in the disease.
-
Statistical Analysis for Evaluation and Improvement of Computer Science EducationDeveloping well-prepared and competent graduates is one of the main goals of all university programs globally. Recently, Computer Science (CS) has achieved tremendous success among all career fields driven by the strong competence in the market and the rapid changes in technology. Our goal is to develop an automated framework that provides efficient management, evaluation and improvement of the CS students education, as well as a profound establishment of a successful study tree for CS university programs. Such a challenging goal comprises major factors that should be inclusively considered. High school (HS) students are expected to join CS university programs with different educational backgrounds and learning capabilities. The strength of association among several performance-related factors including the academic performance of students in HS is evaluated to gain insights and infer indicators in CS programs. The automatic correlational analysis of the prerequisites for each course is also investigated to assess the program structure and dependencies among several CS courses. In this comprehensive study, all these factors are efficiently analyzed in order to investigate the valid causes of low and high performance of both CS university students and programs. Experimental results have concluded several major findings with validated associations that assure and prioritize the importance of evaluation and improvement of CS education.
-
From Analysis to Implementation: A Comprehensive Review for Advancing Arabic-English Machine TranslationIn an increasingly interconnected world, the demand for accurate Arabic-English translation has surged, highlighting the complexities in handling Arabic's intricate morphology and diverse linguistic structures. This research delves into various translation models, including Convolutional Neural Networks (CNNs), LSTM, Neural Machine Translation (NMT), BERT, and innovative fusion architectures like the Transformer-CNN. Each model's strengths and limitations are scrutinized through comprehensive evaluations and comparisons, unveiling their potential to address translation challenges. The research then builds two models, the first based on LSTM and the second on BERT, and tests their performance in translating English to Arabic. The paper then conducts an in-depth analysis of the results. The comparative analysis provides insights into the landscape of Arabic-English translation models, guiding future research toward refining models, leveraging diverse datasets, and establishing standardized evaluation benchmarks to bridge existing gaps.
-
End to End Precision Password CrackingThe study of password-cracking techniques remains a fundamental pursuit within the realm of information security, primarily due to the ever-present threat posed by weak passwords. This project introduces cutting-edge approaches and methodologies aimed at improving password-cracking precision. It explores various techniques, including brute force, dictionary attacks, machine learning, and contextual word lists, with the primary objective of enhancing the e - ciency and precision of password bypassing. Specific goals include evaluating the performance of di↵erent cracking methods and technologies. The project outlines novel methodologies and approaches for password ex- ploitation, discusses their implementation, and provides insights from experi- mental results. The research addresses the pressing need for improved password security measures and contributes to digital forensics and criminal investiga- tions by enhancing password-cracking techniques. The findings of this study have practical implications for strengthening password security across various applications and platforms. By synthesizing insights from existing research and proposing innovative methods, this project aims to advance the state of the art in password cracking, ultimately leading to more robust security measures and better protection of sensitive information.
-
The challenges for the next generation digital health: The disruptive character of artificial intelligence and machine learningArtificial Intelligence is not a technology. Artificial Intelligence is a robust strategy for the digital transformation of anything. This bold characteristic of AI is the focus of this introductory chapter. We elaborate on the unique value proposition of AI and its contribution to the formulation of the emerging, next-generation value-based ecosystem for Digital Health. Then main discussion of the chapter is dedicated on disruptive scenarios and use case for AI-Enabled next-generation Generation Digital Health Services and Solutions. We aim by this short coverage and discussion to highlight bold directions for the utilization of AI in the eHealth context. We are also commenting on various technological, business, strategic and ethical aspects of AI. Last but not least, we convey the main message of the chapter: A robust, resilient strategy for the training and upskilling of stakeholders in healthcare in the foundations, models and strategy of AI is required. We are somehow carriers of a bold change in our societies and in our healthcare ecosystem. It is up to us, as humans with intuition and decision-making capability, to envision the way that the disruptive technology of AI will add value to healthcare, patients' health status and people' wellbeing in the next few years.
-
Chapter 14. Transformative leadership and sustainable innovation in higher education: Setting the context.Transformative leadership is a holistic and bold approach for the next generation of higher education. In this chapter, we provide an introductory, definitive discussion of the phenomenon and integrate it with the concept of sustainable innovation. In Section 1, we introduce a high-level integrated approach to transformative leadership in higher education institutions. We define and discuss diverse pillars. In Section 2, we propose a contextual framework for transformative leadership as a value space. In an effort to provide guidelines and principles for the crafting of a transformative leadership strategy, we propose indicative actions and initiatives for the deployment of transformative leadership in higher education. Finally, in Section 4, we summarized some simple designs for tools and instruments to support the documentation of the transformative leadership strategy, including the transformative leadership scorecard and the systematic overview of the portfolio of transformative educational programs. We also comment on the significance of social impact and research, innovation, and sustainability aspects of the strategy. The contribution of this chapter is multi-fold. It can be used as a reference document for administrators interested in the design and execution of transformative leadership in universities and colleges. It also provided guiding principles for researchers interested in further contributions in the domain.
-
Automated Recognition of Human Emotions from EEG Signals Using Signal Processing and Machine Learning TechniquesOne of the most difficult challenges in pattern recognition, machine learning, and artificial intelligence is emotion recognition. For automatic emotion recognition, voices, images, and electroencephalography (EEG) signals have been employed. Emotion recognition systems based on brain activity are extremely useful in a variety of sectors. In today’s computer age, providing reliable information on emotion recognition is a critical task. Because emotional activity is complicated, it is critical to apply cutting-edge technology and profit from signal processing and machine learning methods while learning about it. Although individuals have been interested in documenting emotional activities over the past decade, there are still fundamental issues that must be addressed in order to take advantage of technology in the understanding of emotion activity. In this chapter, we will go over the most recent signal processing and machine learning algorithms for detecting emotion activity information in the system. We will also cover the difficulties and significant considerations associated with emotion recognition. Several open concepts will be presented for future research to use in understanding the challenges with emotion recognition. Finally, we present some specific examples of emotion recognition using EEG signals employing various AI and signal processing techniques.
-
Artificial Intelligence-Enabled EEG Signal Processing-Based Detection of Epileptic SeizuresEpilepsy affects numerous people worldwide. Electroencephalography (EEG) is an important tool in the diagnosis of epilepsy. Real-time seizure onset detection is critical for accurate evaluation, presurgical assessment, seizure prevention, and emergency warnings and overall improving patients’ quality of life, but manually examining EEG signals is tedious and time-consuming. To assist neurologists, many automatic systems have been proposed to support neurologists utilizing conventional techniques, and these have performed well in detecting epilepsy. Big data applications, particularly biomedical signals, are becoming more appealing in this era as data collection and storage have expanded in recent years. Because data mining approaches are not adaptable to the new needs, big data processing to extract knowledge is difficult. In this chapter, we review AI-enabled signal processing-based approaches for detecting epileptic seizures using EEG signals including with examples.
-
Research and Education Skills as a core part of Digital Transformation in Healthcare in Saudi ArabiaThe adoption of digitalization technologies in healthcare systems is crucial for improving the delivery of medical services, facilitating patient access, and enhancing the overall patient experience. However, the experience and challenges of the Saudi healthcare system in adopting digital transformation have received little attention in the literature. Thus, this chapter aims to provide an overview of the digital transformation process in the Saudi healthcare system. The authors also shed light on the major challenges and suggested technology-based solutions. This chapter was written in light of the available global and local literature discussing the digitization of the health sector. Moreover, the Saudi governmental documents and official reports were utilized to include the latest updates and future plans for the local digital transformation strategy. In paving the way toward digital transformation, many challenges have been faced in areas such as medical records unification, technical infrastructure, and workforce capability. Solutions such as telemedicine applications, artificial intelligence, cybersecurity, and blockchain have been gradually applied to achieve the goal of transformation by 2030. Saudi Arabia's digital transformation began in 2018, with the implementation of the Vision 2030’s rapid digital change. With the emergence of the COVID-19 pandemic, a leap in utilizing digital health solutions has been noticed locally. Nevertheless, more action plans are needed to address the challenges and implement suitable solutions accordingly.
-
Chapter1. Digital transformation in higher education in times of artificial intelligence: Setting the emerging landscapeDigital transformation has become a top priority for Higher Education, driven by technological advances like: Artificial Intelligence (AI), Artificial General Intelligence (AGI), and Generative Open AI. It serves as a catalyst for the reshaping of mainstream processes in academic institutions, emphasising teamwork, collaborative projects, and critical thinking in research, learning, and assessment strategies. In this chapter, we contextualise the use of this digital transformation, highlighting its potential to improve learning experiences, business efficiency, and upskill students and faculty. Our holistic approach to Digital Transformation as an enabler of excellence in Higher Education is based on four pillars of excellence and impact: Business Process Reengineering, Learning Excellence & Skills Building, Research Capacity and Innovation, and Partnership & Outlook. Digital transformation needs the development of efficient, resilient, flexible and adaptable strategies and a strong collaboration between all the actors involved in the process, to ensure the coherence, the sustainability, and alignment of the objectives, means, and targets with the real needs of the learners, tutors, labour market, and society as whole. Our bold proposition consists of a model for the strategy design of digital transformation in universities and colleges organised in three dimensions: Understand, Strategize, Deploy & Exploit. Each dimension emphasises different stages of the process: understanding emerging technologies and their impact on higher education, collaboration between stakeholders, strategy and priorities formulation, roadmap of implementation, deployment and exploitation of digital technologies, etc. The ongoing digital transformation in Higher Education will continue to create an extensive shift in educational processes - learning, teaching, research, and management. Institutions around the world are taking bold initiatives to adapt to this rapidly changing environment, emphasizing the importance of readiness for technological changes, system development, inclusive, and sustainable transformation.
-
Digital health as a bold contribution to sustainable and social inclusive development.In this volume we tried to provide indicative complementary aspects of the Next Generation eHealth. In the concluding chapter of the book we elaborate with the capacity of Digital Health Ecosystem to serve as a bold enabler of the Sustainable Development Goals. We elaborate on the enabling technologies, the stakeholders and the emerging marketplace of digital health services as key determinants of the so-called Sustainable Health Ecosystem. We also discuss the Digital health as a pivotal pillar of Social Inclusive Development and we provide some directions. This chapter can serve as a reference for a contextual framework of Digital Health as a Sustainable Development enabler.
