Effat University Institutional Repository
Not a member yet
1865 research outputs found
Sort by
Demand Forecasting to Predict Future Demand of Sales Data: A Case Study from the Courier and Logistics Industry of Saudi Arabia
No full textThis research explores demand forecasting to predict future sales in the courier and logistics industry of Saudi Arabia, using Aramex as a case study. As e-commerce continues to expand rapidly across the Kingdom, accurate demand forecasting has become essential for maintaining efficiency, minimizing costs, and improving customer satisfaction. This quantitative research employs statistical forecasting models—specifically linear regression and moving averages—applied to real sales data provided by Aramex. Through Microsoft Excel, sales trends over a multi-year period were analyzed to identify seasonal fluctuations and forecast future demand patterns.
The findings revealed a clear upward trend in sales, with noticeable seasonality during specific months, notably in May and December. Among the techniques tested, the three-month moving average model yielded the most reliable short-term forecasts, whereas linear regression proved useful for identifying long-term growth patterns.
The study concludes that data-driven forecasting not only enhances strategic decision-making but also provides logistics firms with the agility to better align their operations with fluctuating market demands. This research contributes to the growing body of logistics literature in the Gulf region and offers actionable insights for companies aiming to implement or refine their forecasting strategies
A Pathway to Empowerment in Saudi Arabia
No full textThis research investigates the role of FinTech in enhancing financial inclusion in Saudi
Arabia and its broader impact on transforming the country’s financial sector. Financial
inclusion is essential for economic growth and social equity, yet many individuals remain
excluded from the financial system. In essence, FinTech solutions help to bridge this gap,
including digital payment platforms, crowdfunding platforms, and Buy Now Pay Later
(BNPL) services that provide new methods to enhance financial services accessibility,
along with affordability and efficiency. Using a quantitative approach, this study analyzed
survey data from 51 residents in Saudi Arabia to explore public perceptions, practical
experience, and suggestion for improving the FinTech sector. The research concludes that
FinTech is widely appreciated and known as a powerful tool since it offers both
accessibility features and service capabilities to underserved people, especially through
digital payment and BNPL platforms. However, several barriers and concerns over security
and privacy continue to hinder full adoption. Research results show that policymakers,
along with financial institutions and FinTech firms, should work together towards
developing digital infrastructure, promoting financial education programs, as well as
establishing inclusive regulatory frameworks. Overall, this research shows that FinTech
technology has the power to bridge the financial access gap, which falls in line with Saudi
Arabia’s Vision 2030 developmental framework
Is it about substituting an addiction with another? development and initial psychometric properties of the first heated tobacco products addiction questionnaire (HeaTPAQ).
No full textPublic health experts currently agree that heated tobacco products (HTPs) pose a significant health risk for their consumers. The same concentrations and speed of delivery of nicotine found for HTPs and conventional combustion cigarettes make it necessary to consider the addictiveness of HTPs, and provide precise diagnostic instruments to serve as the basis for effective treatment plans. Therefore, the main objectives of this study were to design a questionnaire for HTPs addiction called "Heated Tobacco Products Addiction Questionnaire (HeaTPAQ)" and to examine its psychometric properties.Adults from the general population of Lebanon (n = 754) were administered the HeatPAQ, along with the Fagerström test for nicotine dependence (FTND), the Caffeine Use Disorder Questionnaire, the Generalized Anxiety Disorder 7-item, and the Patient Health Questionnaire-9. We split the main sample into two subsamples; subsample 1 consisting of 33% of the participants used for the exploratory factor analysis (EFA) (n = 246; mean age 27.82 ± 9.38 years) and subsample 2 consisting of 67% of the participants used for the confirmatory factor analysis (CFA) (n = 508; mean age 27.81 ± 8.80 years).EFA then CFA analyses revealed a one-factor model consisting of 13 items with acceptable fit to the data. The HeaTPAQ reached excellent internal consistency coefficients, with both Cronbach's α and McDonald's ω values of 0.96. The one-dimensional structure of the HeaTPAQ was found to be invariant across sex groups. Convergent validity was demonstrated through significant positive correlation with FTND scores. Furthermore, HeaTPAQ scores correlated positively with measures of caffeine addiction, anxiety and depression, which suggests the adequate concurrent validity of the scale.Findings suggest that the HeatPAQ is a specific, short and simple-to-use self-report questionnaire to assess HTPs addiction reliably and validly. Pending future studies confirming our results, we hope that the HeatPAQ will facilitate routine screening for HTPs addiction, which is an essential step towards appropriate prevention and intervention efforts and to inform policy makers
Hybrid Energy Storage System with DC-DC Boost Converter and MPPT P&O Control for Optimized Photovoltaic Power Management
No full textThis paper presents the design and implementation of a Stand-alone Photovoltaic (PV) Battery-Supercapacitor Hybrid Energy Storage System (HESS) integrated with a DC-DC boost converter and a Maximum Power Point Tracking (MPPT) control strategy based on the Perturb and Observe (P&O) algorithm. The system aims to enhance energy efficiency and optimize power management in solar PV applications by efficiently storing excess energy generated during high irradiance and maintaining a stable power supply during periods of low irradiance. The hybrid approach combines high-energy-density batteries for continuous power supply with supercapacitors that deliver rapid bursts of power, reducing stress on the batteries and extending their lifespan. The DC-DC boost converter increases the PV panel output voltage to the required level for efficient charging of both storage devices. The MPPT P&O algorithm dynamically tracks the Maximum Power Point (MPP) of the PV panels to maximize energy extraction, adjusting the operating voltage in response to environmental changes such as irradiance and temperature. Simulation results using MATLAB/Simulink validate the proposed system's performance, demonstrating improved energy conversion efficiency and a significant reduction in battery degradation. The MPPT P&O technique, combined with the hybrid storage system, achieves an overall energy management efficiency of 98%, making it an ideal solution for off-grid solar energy applications. This work highlights the potential of hybrid energy storage systems in enhancing the reliability and longevity of renewable energy systems
Development of an AI-powered chatbot for Enhanced Customer Support at the Saudi National Bank
No full textThe increasing demand for efficient and accessible customer service in the financial sector has
driven institutions like the Saudi National Bank (SNB) to adopt cutting-edge technological
solutions. This thesis presents the comprehensive development of an AI-powered chatbot,
specifically designed to enhance customer support services at SNB. The chatbot aims to
autonomously handle routine inquiries, thereby reducing the need for human intervention and
optimizing resource allocation. The project’s objectives include improving customer satisfaction,
lowering support costs, and ensuring 24/7 availability of basic support services. Built on the
LLaMA2 architecture, enhanced with Retrieval-Augmented Generation (RAG), and integrated
into a web application using Python Flask and React, this chatbot represents a significant
advancement in SNB's customer service capabilities. This thesis details the end-to-end process of
designing, developing, testing, and deploying the chatbot, addressing both technical challenges
and strategic considerations. Additionally, the thesis explores a variety of use cases, illustrated
through UML diagrams, class diagrams, sequence diagrams, and data flow diagrams (DFDs),
providing a holistic view of the system’s architecture and functionality
Alcoholism Identification by Processing the EEG Signals Using Oscillatory Modes Decomposition and Machine Learning
No full textExcessive alcoholism has the potential to disturb the nervous system. A timely identification and prevention can cure it. This work proposes a novel approach to detect alcoholism by processing the electroencephalogram (EEG) signals. It is based on the signal processing and machine learning algorithm. We have used the oscillatory mode decompositions to decompose the EEG signals in modes. First six modes are considered for second order difference plots (SODPs). The central tendency measure, area, and mean are chosen as the three features from each intended SODP. Experiments are carried out by taking into account features collected from three different length time windows in order to establish an appropriate EEG signal segment length for the intended application. For classification, different machine learning algorithms are used
Feature extraction techniques for human-computer interaction
No full textThis work is financially supported by the Effat University.In order to improve communication and interaction between humans and machines/computers, the multimodal signal processing and Artificial Intelligence (AI) are vital tools. For a seamless Human-Computer Interaction (HCI), it integrates and analyzes the data from several sensory modalities. The objective is to develop more efficient, natural, and intuitive interfaces that can comprehend and react to human input more effectively. Usually, these modalities consist of visual and auditory kinds of sensor data. However, a latest trend is to employ the physiological signals for modeling and realizing the contemporary HCIs. In this context, the feature extraction methods play an important role. The aim of feature extraction is to achieve accurate representation for modeling or identifying critical elements or intentions in the human body systems using machine or deep learning techniques. Feature extraction facilitates the identification and interpretation of relevant information from input data streams. This chapter explores various feature extraction techniques employed in HCI applications, ranging from parametric model-based methods to more complex approaches. Traditional techniques encompass the signal processing methods such as digital filtering and Fourier transform. The intended parametric model-based methods are the autoregressive, Yule-Walker, covariance, and modified covariance. Further considered approaches are the subspace-based methods, eigenvector, and time-frequency analysis such as the short-time Fourier transform and different variants of wavelet transform. Additionally, the oscillatory mode decompositions and common spatial patterns are described. These methods are effective for extracting pertinent information from the input signals, and moreover, they enable the automated decision support through machine and deep learning methodologies for the contemporary HCIs.Effat Universit
ENHANCING GLAUCOMA DIAGNOSIS: FUNDUS IMAGE CLASSIFICATION/ANALYSIS APPROACH
No full textThis study presents an automated diagnostic system for early glaucoma detection using fundus imaging. The methodology integrates wavelet-based noise reduction, vessel removal, and watershed segmentation to enhance diagnostic accuracy. Validated on G1020 and HRF datasets, the system achieved an 85.75% accuracy, 89% precision, 92% recall, and 90.5% F1-score using SVM with Linear Discriminant Analysis (LDA). Designed for scalability, the system leverages open-source tools, making it cost-effective and applicable in resource-limited settings. Potential applications include telemedicine platforms and portable diagnostic kits, enabling early glaucoma screening and supporting Sustainable Development Goal 3. While challenges such as dataset variability remain, this work lays a foundation for advancing AIassisted ophthalmological diagnostics
Bee Colony-Reptile Search Optimization Technique for Blood Cell Cancer Detection
No full textThe biosystem is a crucial system grounded in classification and detection, utilizing Artificial Intelligence (AI) approaches or metaheuristic techniques. Currently, cancer of the blood cells is among the deadliest cancers in the world. Acute lymphoblastic leukemia (ALL) is a cancer of blood cells that causes excessive proliferation of lymphocytes. It is extremely time-consuming and expensive to conduct diagnostic calculations. The number of platelets in a patient's blood is computed by a platelet count. A lacking number of platelets can indicate cancer, infection, or other health problems. A patient with too many platelets is at risk for blood strokes. A single drop of blood includes tens of thousands of platelets. The main goal of this paper is how to detect the features of blood cells and classify with predicting cancer type based on platelets analysis by using Bee Colony followed by Reptile Search Optimization (BCRSO) technique. According to the results, BCRSO algorithm performed better in terms of classification efficacy and accuracy rate than other algorithms. Based on simulation results, the proposed method is more effective than previously published research for classification optimization
Harnessing Artificial Intelligence in Obesity Research and Management: A Comprehensive
No full textThis review aims to explore the clinical and research applications of artificial intelligence (AI), particularly machine learning (ML) and deep learning (DL), in understanding, predicting, and managing obesity. It assesses the use of AI tools to identify obesity-related risk factors, predict outcomes, personalize treatments, and improve healthcare interventions for obesity. Methods: A comprehensive literature search was conducted using PubMed and Google Scholar, with keywords including “artificial intelligence”, “machine learning”, “deep learning”, “obesity”, “obesity management”, and related terms. Studies focusing on AI’s role in obesity research, management, and therapeutic interventions were reviewed, including observational studies, systematic reviews, and clinical applications. Results: This review identifies numerous AI-driven models, such as ML and DL, used in obesity prediction, patient stratification, and personalized management strategies. Applications of AI in obesity research include risk prediction, early detection, and individualization of treatment plans. AI has facilitated the development of predictive models utilizing various data sources, such as genetic, epigenetic, and clinical data. However, AI models vary in effectiveness, influenced by dataset type, research goals, and model interpretability. Performance metrics such as accuracy, precision, recall, and F1-score were evaluated to optimize model selection. Conclusions: AI offers promising advancements in obesity management, enabling more personalized and efficient care. While technology presents considerable potential, challenges such as data quality, ethical considerations, and technical requirements remain. Addressing these will be essential to fully harness AI’s potential in obesity research and treatment, supporting a shift toward precision healthcare.This review aims to explore the clinical and research applications of artificial intelligence (AI), particularly machine learning (ML) and deep learning (DL), in understanding, predicting, and managing obesity. It assesses the use of AI tools to identify obesity-related risk factors, predict outcomes, personalize treatments, and improve healthcare interventions for obesity. Methods: A comprehensive literature search was conducted using PubMed and Google Scholar, with keywords including “artificial intelligence”, “machine learning”, “deep learning”, “obesity”, “obesity management”, and related terms. Studies focusing on AI’s role in obesity research, management, and therapeutic interventions were reviewed, including observational studies, systematic reviews, and clinical applications. Results: This review identifies numerous AI-driven models, such as ML and DL, used in obesity prediction, patient stratification, and personalized management strategies. Applications of AI in obesity research include risk prediction, early detection, and individualization of treatment plans. AI has facilitated the development of predictive models utilizing various data sources, such as genetic, epigenetic, and clinical data. However, AI models vary in effectiveness, influenced by dataset type, research goals, and model interpretability. Performance metrics such as accuracy, precision, recall, and F1-score were evaluated to optimize model selection. Conclusions: AI offers promising advancements in obesity management, enabling more personalized and efficient care. While technology presents considerable potential, challenges such as data quality, ethical considerations, and technical requirements remain. Addressing these will be essential to fully harness AI’s potential in obesity research and treatment, supporting a shift toward precision healthcare