SACM - United States of America
Permanent URI for this collectionhttps://drepo.sdl.edu.sa/handle/20.500.14154/9668
Browse
8 results
Search Results
Item Restricted Detecting Makeup Activities using Internet-of-Things(University of Maryland Baltimore County, 2019-07) Alqurmti, Fatimah; Roy, NirmalyaThis thesis focuses on identifying human activities for rendering make-up activities using sensors’ data and a supervised machine learning approaches. We considered five make-up activities in our work, such as, applying cream, lipsticks, blusher, eyeshadow, and mascara. We collected the data from ten participants using two smart-watch built-in sensors, accelerometer and gyroscope. We preprocessed the data and trained with different predictive machine learning models and we evaluated make-up activity prediction built on using Naïve Bayes, Simple Logistic, k-nearest neighbors’, and the random forest algorithms. We investigated the models' performance on three different datasets that differ by the environment they were collected in. The first dataset was collected from the participants using a controlled environment. In this staged setting, we provided the participants specific instructions on how to perform the five make-up activities. The second dataset was collected from the participants in an uncontrolled environment. We did not inform the participants with any prior instructions on how to perform the five activities and therefore, naturally they performed the make-up activities in their own way. Third, we synthetically generated a dataset by combining the existing datasets from the participants who were under both controlled and uncontrolled environments. Our results showed a 92.7 % accuracy for the controlled environment case given by the Gradient Boosting classifier and an 89.20 % accuracy for the uncontrolled environment case shown by the Random Forest classifier. Finally, Random Forest classifier registered the highest accuracy 92%, for the hybrid case where both the datasets from controlled and the uncontrolled environments were combined. We believe that this early work on recognizing and discovering a multitude of make-up activities has potential application in assessing and training the performance of various stakeholders in the future work of fashion industry.8 0Item Restricted Detecting Makeup Activities using Internet-of-Things(University of Maryland Baltimore County, 2019-07-30) Alqurmti, Fatimah; Roy, NirmalyaThe make-up market is one of the most furnished fashion markets in product retailing and training demands. Each of the makeup activities involves very delicate movements of hands and requires good amount of training and practice for perfection. The available choices in the make-up training industry depends on practical workshops by professionalinstructors, and still evaluating the perfection of makeup activities lacks certainty. In this work, we introduced a novel application for human activity recognition using sensors’ data and a supervised machine learning approaches for rendering make-up activities. We considered five make-up activities in our work, such as, applying cream, lipsticks, blusher, eyeshadow, and mascara and collected data from ten participants. We built supervised make-up activity recognition using different predictive machine learning algorithms i.e. Naïve Bayes, Simple Logistic, k-nearest neighbors’, and the random forest algorithms. We investigated the models' performance for detecting five make-up activities with or without instructions. Our results show that shallow machine learning algorithms achieve up to 92% accuracy in detecting make-up activities.20 0Item Restricted Applications of Continuous Flow Reactors Towards Screening Catalytically Active Nanoparticle Syntheses(USC Digital Library, 2023) Madani, Majed; Malmstadt, NoahThe dissertation presented herein is structured into chapters that delve into various research domains within milli- and microfluidic systems. Part of this dissertation includes collaborative authorship. Chapter 1 introduces the fundamentals of fluid mechanics. In this chapter, some highlights of the important physical phenomena that are dominant in milli- and microscale flow systems are presented, focusing on flow dynamics, diffusion, and computational fluid dynamics simulations. It emphasizes the importance of fluid behavior in microscale systems and introduces a case study on microfluidics applications in biomolecular systems in which a portion of a manuscript I participated in as a third author is presented. Chapter 2 covers applications of continuous flow synthesis of colloidal nanoparticles using milli-and microfluidics systems, highlighting the advantages of miniaturized systems in reaction-based nanoparticle syntheses. Chapter 3 is adapted from a published manuscript in which I am a joint primary author. Chapter 3 describes the use of continuous flow methods for screening the reaction parameters of catalytically active molybdenum carbide nanoparticle synthesis with an emphasis on throughput optimization using a Design of Experiment approach. Chapter 4 introduces machine learning-assisted spectrophotometry, showcasing the integration of machine learning algorithms for the kinetic analysis of ionic liquid-based platinum nanoparticle synthesis. Chapter 5 introduces in-situ characterization for continuous flow reactors with a particular objective of studying the nucleation and growth kinetics of nanoparticle synthesis using X-ray scattering. This chapter provides a critical evaluation of flow reactor designs for in situ X-ray scattering analysis, focusing on the synthesis of ionic liquid-based Pt nanoparticles.30 0Item Restricted Machine learning applications for the optimization of renewable energy systems(Saudi Digital Library, 2023-10-10) Maghfuri, Abdullah M.; Wright, Mark MbaThis thesis aims to establish the sectors and applications of renewable energy. The applications of sustainable energy have grown every year in different uses. Three separate studies stand out as a source of creativity. Together, they point the way to a better and more accountable future. Each study explores an important aspect of energy optimization and environmental stewardship and offers remarkable insights and responses. This thesis begins with climate simulation, concentrating on projected solar irradiation and wind patterns in the following decades. These estimations emphasize preemptive energy management. This study compares Saudi Arabia's metropolitan solar power systems to wind and fossil fuel infrastructure. Current and future climates are analyzed. The company's recent solar energy strategy shows its ability to produce sustainable energy and reduce climate change. Wastewater is the topic of the second part of this thesis. Wastewater treatment is a priority due to rising water needs and environmental concerns. Here, renewable energy sources and electrochemical technologies are combined to improve wastewater treatment efficiency and save operational costs. The study uses machine learning predictive models and extraction of high-value by-products from the treatment process blends technology and ecology, enabling sustainable water management. The third study project, which explores the complicated field of predictive modeling, is essential to prioritize the accurate projection of energy output given the rising importance of renewable energy. This research paper thoroughly examines the effectiveness of statistical and machine-learning approaches in predicting renewable energy generation. The findings demonstrate the prevalence of machine learning techniques, which bring a sense of innovation and efficacy to the realm of renewable energy fields.57 0Item Restricted Environmental Influences on Food Access And Their Impacts in Turn on Health Conditions in Guilford County, NC(2023-02-24) Almalki, Abrar; Gokaraju, BalakrishnaFood access is a major key component in food security, as it is every individual’s right to proper access of nutritious and affordable food supply. Low access to healthy food sources influences people's diet and activity habits. Guilford County in North Carolina has a high ranking in low food security, and a high rate of health issues, such as high blood pressure, high cholesterol, and obesity. Therefore, the primary objective of this study was to investigate the geospatial correlation between health issues and food access areas. The secondary objective was to quantitatively compare food access areas and heath issues’ descriptive statistics. The tertiary objective was to compare several machine learning techniques and find the best model that fits health issues against various food access variables with the highest performance accuracy. In this study, we adopted a food-access perspective to show that communities, where residents had equitable access to healthy food options, were typically less vulnerable to health-related disasters. We proposed a methodology to help policymakers toward lowering the amount of health issues in Guilford County by analyzing them via correlation with respect to food access. Specifically, we conducted a geographic information system mapping methodology to examine how access to healthy food options influenced health and mortality outcomes in one of the largest counties in the state of North Carolina. We created geospatial maps representing food deserts, i.e., areas with scarce access to nutritious food; food swamps, i.e., areas with more availability of unhealthy food options compared to healthy food options; and food oases, i.e., areas with relatively higher availability of healthy food options than unhealthy. Our results presented a positive correlation coefficient with R2= 0.819 among Obesity and independent variables, transportation access, income, and population. The correlation coefficient matrix2 analysis helped to identify a strong negative correlation between obesity and median income. Overall, this study offers valuable insights that can help health authorities develop preemptive preparedness for healthcare disasters. COVID-19, or SARS-CoV-2, is considered as one of the greatest pandemics in our mod-ern time. It affected people’s health, education, employment, the economy, tourism, and trans-portation systems. It will take a long time to recover from these effects and return people’s lives back to normal. The main objective of this study is to investigate the various factors in health and food access, and their spatial correlation and statistical association with COVID-19 spread. The minor aim is to explore regression models on examining COVID-19 spread with these variables. To address these objectives, we are studying the interrelation of various socio-economic factors that would help all humans to better prepare for the next pandemic. One of these critical factors is food access and food distribution as it could be high-risk population density places that are spreading the virus infections. More variables, such as income and people density, would influence the pandemic spread. In this study, we produced the spatial extent of COVID-19 cases with food outlets by using the spatial analysis method of geographic information systems. The methodology consisted of clustering techniques and overlaying the spatial extent mapping of the clusters of food outlets and the infected cases. Post-mapping, we analyzed these clusters’ proximity for any spatial variability, correlations between them, and their causal relationships. The quantitative analyses of the health issues and food access areas against COVID-19 infections and deaths were performed using machine learning regression techniques to understand the multi-variate factors. The results indicate a correlation between the dependent variables and independent variables with a Pearson correlation R2-score = 0.44% for COVID-19 cases and R23= 60% for COVID-19 deaths. The regression model with an R2-score of 0.60 would be useful to show the goodness of fit for COVID-19 deaths and the health issues and food access factors.25 0Item Restricted DEEP LEARNING MODELS FOR MOBILE AND WEARABLE BIOMETRICS(Saudi Digital Library, 2023-04-27) Almadan, Ali; Rattani, AjitaThe mobile technology revolution has transformed mobile devices from communication tools to all-in-one platforms. As a result, more people are using smartphones to access e-commerce and banking services, replacing traditional desktop computers. However, smartphones are more prone to being lost or stolen, requiring e ective user authentication mechanisms for securing transactions. Ocular biometrics o ers accuracy, security, and ease of use on mobile devices for user authentication. In addition, face recognition technology has been widely adopted in intelligence gathering, law enforcement, surveillance, and consumer applications. This technology has recently been implemented in smartphones and body-worn cameras (BWC) for surveillance and situational awareness. However, these high-performing models require significant computational resources, making their deployment on resource-constrained smartphones challenging. To address this challenge, studies have proposed compact-size ocular-based deep-learning models for on-device deployment. In this context, we conduct a thorough analysis of existing neural network compression techniques applied standalone and in combination for ocular-based user authentication and facial recognition.16 0Item Restricted LEARNING-BASED EVALUATION FRAMEWORK FOR ATTACK DETECTION ALGORITHMS IN POWER SYSTEMS(2023-02-16) Sayghe, Ali; Anubi, OlugbengaOver the last decade, the number of cyberattacks targeting power systems and causing physical and economic damages has increased rapidly. Among them, False Data Injection Attacks (FDIAs) is a class of cyberattacks against power grid monitoring systems. Adversaries can successfully perform FDIAs in order to manipulate the power system State Estimation (SE) by compromising sensors or modifying system data. SE is an essential process performed by the Energy Management System (EMS) towards estimating unknown state variables based on system redundant measurements and network topology. SE routines include Bad Data Detection (BDD) algorithms to eliminate errors from the acquired measurements, e.g., in case of sensor failures. FDIAs can bypass BDD modules to inject malicious data vectors into a subset of measurements without being detected; and thus, manipulate the results of the SE process. In order to overcome the limitations of traditional residual-based BDD approaches, data-driven solutions based on machine learning algorithms have been widely adopted for detecting malicious manipulation of sensor data due to their fast execution times and accurate results. Machine learning algorithms have been proposed as a promising solution for detecting FDIAs, as they can automatically learn patterns and anomalies in the data that are indicative of an attack. However, these algorithms are also vulnerable to adversarial examples, which are maliciously crafted inputs that are designed to mislead the model into making a wrong decision. In this dissertation, we focus on evaluating the vulnerability of machine learning algorithms against adversarial examples in the context of FDIAs. Specifically, we study six different cases of adversarial attacks, including Adversarial Label Flipped Attack on SVM, Targeted Fast Gradient Sign Method Attack on MLP, Limited-memory BFGS Attack on MLP, Jacobian-based Saliency Attack on MLP, Carlini and Wagner Adversarial Attack, and Zeroth Order Optimization-based Attack. We implement these attacks on a simulated power system, and evaluate the performance of the machine learning algorithms in detecting them. The results of this study provide insights into the strengths and weaknesses of different machine learning algorithms in detecting FDIAs and adversarial examples. We also provide recommendations on how to improve the robustness of these algorithms against adversarial examples. The findings of this research are useful for practitioners in the field of power systems and machine learning, as well as for researchers working on the security of cyber-physical systems. This dissertation is organized into several chapters, starting with background, literature review, objective, adversarial examples, adversarial examples on power systems state estimation, evasion attacks with adversarial deep learning against power system state estimation, adversarial machine learning designs against learning-based attack detection algorithms in power systems and a summary of the work and future work.32 0Item Restricted Partial Discharge Characteristics in Aerospace Applications Under High dv/dt Square-Wave Voltage Pulses(The Ohio State University, 2023) Alkhalid, Khalid; Wang, JinThe aviation industry faces a growing imperative to decrease greenhouse gas emissions and transition towards more electric aircraft (MEA) and all-electric aircraft (AEA). One key requirement for a successful transition is increasing the power density and efficiency of onboard power converters. Wide-bandgap (WBG) power switching devices, such as silicon carbide (SiC), present a promising solution due to their high voltage capability and rapid switching speed. However, these devices also pose a challenge as their fast switching speed can adversely affect insulation systems. This dissertation aims to investigate and offer a deeper understanding of, as well as solutions to, the challenges related to partial discharge (PD) in aircraft power wiring under high dv/dt voltage pulses generated by SiC devices. The dissertation begins with an overview of the significant technical challenges related to PD that arise from using SiC device-based variable speed drives (VSD). It then discusses existing studies addressing these challenges and the failure of insulation systems due to PD. The literature review highlights disagreements in current research and the absence of comprehensive investigations into PD behavior caused by high dv/dt square-wave voltage pulses and their impact on the premature failure of insulation systems. Subsequently, the dissertation delves into the challenges associated with the PD phenomenon in aviation wires, explaining the factors that influence PD behavior, accurate PD detection methods, and the extraction of meaningful features to quantify PD intensity. This is followed by an experimental study of PD-induced aging under various conditions to explore the effects of different variables on PD behavior and the failure mechanism of aviation wires. The experimental conditions are chosen to examine voltage rise time, voltage amplitude, ambient pressure, ambient temperature, and the dielectric material of aviation wires. The experimental results reveal the complexity of PD behavior and the associated degradation process, highlighting the need for artificial intelligence (AI) and machine learning (ML) to interpret and predict insulation status. The dissertation then presents the implementation of ML, showcasing feature extraction, data preparation, model training, and the successful prediction of remaining service life. Finally, the dissertation concludes with a summary of key findings and recommendations for future research.20 0