Effat University Institutional Repository
Not a member yet
1865 research outputs found
Sort by
Artificially intelligent detection of retinal pigment sign using P3S-Net for retinitis pigmentosa analysis
No full textImage segmentation is a major and crucial problem in medical imaging. It is the foundation for clinical diagnostic methods, treatments, and computer-assisted disease diagnosis (CAD). An ocular condition known as retinal pigmentosa (RP) first results in night blindness and persistent degradation of the retinal pigment. An advanced deep learning method for computer-aided disease diagnosis that detects pigment signs (PS) in RP patients, enabling ophthalmologists to identify and treat the condition on or before schedule. Many researchers now use costly CAD approaches; however, the suggested solution, which uses a fundus image dataset, is quick, easy, and affordable. This paper presents a large kernel pigment sign semantic segmentation network (P3S-Net) to enhance segmentation performance and provide a useful receptive field. P3S-Net is a residual network with less trainable parameters due to its large kernel architecture. Moreover, these large-kernel receptive fields yield improved segmentation results with early, intermediate, and late feature information fusion. P3S-Net has an order of magnitude less trainable parameters of 155k in certain scenarios and is smaller than current medical image segmentation techniques. Utilizing the publicly available Retinal Images for Pigment Signs (RIPS) dataset for retinal pigment detection and segmentation, 4-fold cross-validation tests were conducted to assess the suggested P3S-Net. The performance of the suggested network is frequently better and more competitive when compared to cutting-edge techniques
Comparing the Differences between Conventional Finance and Islamic Finance through banking in the KSA
No full textLeap Hub : Jeddah's Digital Playground
No full textDeveloping an E-sports center in Jeddah represents an important project aimed at giving the
gaming community an opportunity to host local competitions and train their skills as well as
providing a place to host matches. Furthermore, it aims to serve as an interesting tourist attraction
for those interested in exploring the world of games. The center will also create job opportunities,
both direct and indirect, in the region. It will also provide an opportunity for local businesses to
partner with the center to gain exposure and promote their products and services. The focus of this
pre-design research is to gain a comprehensive understanding of the fundamental elements and
principles that are crucial to the successful realization of an e-sports center in Jeddah. An integrated
approach is employed in this research, which includes case studies of e-sports centers and arenas
around the world, field visits to existing gaming lounges, interviews with employees and gamers,
site selection and analysis, formulation of a building program tailored to local needs, and the
establishment of standards governing the elements and spaces within a e-sports. Furthermore, in
order to maximize efficiency and functionality, the research focuses on integrating diverse
systems. It provides insight into the requirements for a potential e-sports center project and is
comprehensive and highly beneficial. It ensures that the project is aligned with the broader goals
of entertainment and tourism in Jeddah by providing an understanding of its intricacies. This study
used observational research methods and meta-analysis. By using this approach, it is possible to
examine e-sport center projects thoroughly, obtain valuable insights, identify practices, and adapt
those principles to the local context. Predesign research for an e-sports center in Jeddah offers a
solution for the pressing issue of e-sports athletes not having adequate facilities but also serves as
a catalyst for tourism growth. In the end, the results of this research could help ensure that the E sport project is implemented efficiently and successfully, enhancing the city's tourism and
environmental infrastructure
Artificial Intelligence Applications for Brain–Computer Interfaces
No full textArtificial Intelligence Applications for Brain-Computer Interfaces focuses on the advancements, challenges, and prospects of future technologies involving noninvasive brain-computer interfaces (BCIs). It includes the processing and analysis of multimodal signals, integrated computation-acquisition devices, and implantable neuro techniques.
This book not only provides cross-disciplinary research in BCI but also presents divergent applications on telerehabilitation, emotion recognition, neuro-rehabilitation, cognitive workload assessments, and ambient assisted living solutions.
In 15 chapters, this book describes how BCIs connect the brain with external devices like computers and electronic gadgets. It analyzes the neural signals from the brain to obtain insights from the brain patterns using multiple noninvasive wearable sensors. It gives insight into how sensor outcomes are processed through machine-intelligent models to draw inferences. Each chapter starts with the importance, problem statement, and motivation. A description of the proposed methodology is provided, and related works are also presented.
Each chapter can be read independently, and therefore, the book is a valuable resource for researchers, health professionals, postgraduate students, postdoc researchers, and academicians in the fields of BCI, prosthesis, computer vision, and mental state estimation, and all those who wish to broaden their knowledge in the allied field
Experimental Verification of Rotating Sliding Mode Control with Composite Reaching Law Approach for Voltage Source Inverters
No full textThis work is supported by the Effat University under the grant number (UC#9/3June2024/7.1-22(4)7)In modern power systems, power electronic interfaces like Voltage Source Inverters (VSIs) uses advanced control strategies to ensure high-quality voltage regulation, significantly enhancing system stability and reliability for various applications. This paper introduces a novel voltage regulation method for VSIs using Sliding Mode Control (SMC) under extreme load variations [1]. Besides robustness, SMC is prone to chattering, causing power losses, reduced efficiency, and compromised transient response. To address chattering, an adaptive sliding surface selection mechanism that utilizes the Rotating Sliding Surface (RSS) technique and a new reaching law based on state variable magnitudes, which dynamically adjusts the control gain is proposed here. This composite reaching law uses exponential, power, and difference functions to achieve rapid convergence and reduce chattering. The sliding surface is chosen with a time-varying slope based on error variables. Tests on a single-phase VSI with varying loads demonstrate that the C-ERL-RSS SMC achieves a well-regulated output voltage with just 0.25% THD, reduced chattering, and minimal tracking time. Additionally, implementing the C-ERL-RSS SMC and PRERL SMC on a two-level three-phase VSI under varying load conditions shows superior efficiency and stability, with a low THD of 1.1%. Experimental evaluation on MicroLabBox-dSPACE 1202 for VSIs under extreme conditions reveals that the proposed technique excels in voltage regulation, offering fast transient response and low THD of 1.12% and 2.1% for single-phase and three-phase VSIs, respectively.Effat Universit
An Intelligent Optimization Technique Of Automatic Speech Recognition For Smart Homes
No full textThe creation of new approaches to the design and configuration of smart buildings relies heavily on AI tools and Machine Learning (ML) algorithms, particularly optimization techniques. The
widespread use of electronic devices has sparked a strong desire to incorporate the Internet of Things (IoT) into houses, leading to the development of smart homes. As networked gadgets proliferate
rapidly, this phenomenon is characterized by rapid proliferation. In smart buildings, smart cities, smart grids, and smart homes, interconnected electronic devices are becoming more popular. The
objective of this paper is to enhance the functionality of home automation systems through the performance of speech recognition using the Bat-Salp Swarm Optimization (BSSO). This paper
investigates the notion of (BSSO), a data analysis methodology that facilitates the automated construction of analytical models. The implementation of BSSO provides an enhancement to the
feature selection process in speech recognition, providing an approximation solution that improves the accuracy of system decisions. The use of the BSSO technique improves the precision of the voice
recognition system and also incorporates an Artificial Neural Network (ANN) for the classification part. The findings substantiated the efficacy of the employed methodology
Enhanced Position-Aided Beam Prediction Using Real-World Data and Enhanced-Convolutional Neural Networks
No full textMillimeter-wave (mmWave) communication systems utilize narrow beamforming to ensure adequate signal power. However, beam alignment requires significant training overhead, especially in highmobility scenarios. Previous research has utilized synthetic data for position-aided beam prediction, which does not fully capture real-world complexities. In this work, an Enhanced Convolutional Neural Network
model (E-CNN) is proposed for optimal prediction of beam indices with the aid of real-world GPS position data. The proposed E-CNN model has been investigated across nine different scenarios from the DeepSense 6G dataset and compared against the conventional algorithms. For 64-beams Scenario 1, the E-CNN model showed an increase in average top-1 accuracy from 55.57% to 63.92%, and in case of 32-beams, the accuracy increased from 71.34 % to 82.06%. For 16-beams, the accuracy increased from 86.17% to 94.64 %, while for 8-beams, the accuracy increased from 90.24% to 97.11%. In addition, besides showing significant power loss reduction in various scenarios, the proposed E-CNN model has demonstrated robustness regarding real-word conditions and adaptability for various beam setups. The model realized as high as a 50% power loss reduction in arguably the most challenging graphs, which is an exercise in reliability. This research fills the existing gap between the simulated aid beam alignment and real-world position beam aided alignment, which can be useful in improving beamforming in the upcoming wireless networks
Al-Sulaiman Palace Revival
No full textThe Al-Sulaiman Palace, a historical edifice located in the sacred city of Makkah, stands as
a testament to our rich cultural heritage and Islamic legal history. Originally serving as an
Islamic legal court, this building encapsulates the essence of Makkah's spiritual and cultural
significance. As we approach the vision for 2030, which emphasizes innovation and
sustainability while preserving our rich cultural identity, the need to enhance and restore
such landmarks becomes paramount. This project aims to respect the heritage of the AlSulaiman Palace through a thoughtful extension that highlights its unique character while
ensuring its relevance in contemporary society
The Impact of COVID-19 on the Financial Markets, Energy Price and Exchange Rates of GCC Countries
No full textNo one denies that the COVID-19 health crisis has substantial impact on the financial markets of the globe. It is important to evaluate the performance of financial assets to understand the behaviour of financial markets during such significant event. Therefore, this research investigates the impact of COVID-19 on the GCC stock indices, currency exchange, and oil returns. By application of the event study (constant return Model) and standard Vector Auto-regression models, we examine the index returns of each country, oil price, and currency exchange before and after COVID-19 health crisis. We find that the COVID-19 has a short-term impact on the index returns of Saudi Arabia, and it has a short-term effect on the exchange returns of all GCC counties except Bahrain. However, the COVID-19 has no long-term impact on all selected variables of GCC. This study provides new insight into the financial market during external event which may have a direct or indirect effect on the performance of selected variables of GC
AI Enhanced Cyber Policy Assistant for IT Team
No full textSmall and medium-sized companies (SMCs) in Saudi Arabia face growing cyber-
security challenges due to limited in-house expertise, inadequate infrastructure, and
the increasing complexity of digital threats. Unlike large enterprises with dedicated
security teams, most SMCs rely on general IT sta↵ and lack the tools to e↵ectively
manage risks such as data breaches, ransomware, and regulatory non-compliance.
This project proposes a user-friendly, AI-powered web application specifically de-
signed to support Saudi Arabia’s SMCs in navigating cybersecurity policies and
practices. At its core is a chatbot that delivers personalized cybersecurity guid-
ance, helping users understand and meet the requirements of national regulations
particularly those set by the Saudi National Cybersecurity Authority (NCA)[10]
while also supporting alignment with international standards