Engineering Commons^™

Software Engineering Approach To Enhancing Privacy Protection: Automated Face Blurring Using Deep Learning In Arab Social Media, Yasmin Makki Mohialden, Nadia Mahmood Hussien, Mostafa Abdulghafoor Mohammed

Iraqi Journal for Computer Science and Mathematics

In the age of digital media, securing personal identities in shared material, especially on social media, has become a significant challenge. This research leverages software engineering to automate face blurring in photographs of Arab social media personalities. It proposes a system that integrates sophisticated deep-learning algorithms with standard image processing within a robust software architecture. This modular system is scalable, maintainable, and compatible with digital media platforms. Gaussian blur is applied to protect privacy once convolutional neural networks (CNNs) identify faces. The system’s efficiency and accuracy are enhanced by OpenCV and NumPy. In experiments, this system consistently identifies and blurs …

Two-Factor Authentication Software For Bluetooth Pairing Between Mobile And Pc Operating Systems, Sundos A. Hameed Alazawi, Abbas A. Abdulhameed, Mostafa Abdulghafoor Mohammed, Thekra Abbas

Iraqi Journal for Computer Science and Mathematics

Bluetooth devices actively broadcast software when pairing to connect. Even during the connection process, the connection can be monitored to view information about the transmission. Using this information, anyone can hijack your existing connection and steal data. Bluetooth connections can be single or multiple. Thus, while connecting to a device, the same device could be simultaneously connected to another device. To avoid this problem, a new software is proposed to support the ID-based authentication process for paired devices by integrating an authentication method based on the biometric features of the device owner. The proposed two-factor security authentication system for pairing …

Retracted: Evaluating The Performance Of The Dbscan Algorithm's Using Number Of External Scores Measures, Rajaa Hasan Abbas, Huda Qusay Hashim, Huda Karem Nasser

Iraqi Journal for Computer Science and Mathematics

The emergence of more informative clustering methods than classical representations is important, so the density-based spatial clustering for applications with noise (DBSCAN) technique can yield an accurate statistical idea of clusters. DBSCAN is becoming more and more popular. On the other hand, if we are aware of actual datasets so that we can make comparisons with these datasets, we aim to determine the accuracy with which the partitioning is estimated using the density-based method. Therefore, in order to compare the success of the partitioning found by the density-based approach under different models, some external scores measures (Adjusted Rand, F-measure, and …

Ontology Features-Based Arabic Text Augmentation Using Word2vec, Enas Tariq Khudair, Onsa Lazzez, Mourad Zaied, Tarek M. Hamdani, Ahmed T. Sadiq, Habib Chabchoub, Adel M. Alimi

Iraqi Journal for Computer Science and Mathematics

Text augmentation plays a major role when data is scarce. In this context, there are few Arabic news texts for specific purposes, and hence, there is a dire need to generate Arabic text, especially news. This paper presents an enhanced approach to Arabic text augmentation based on Arabic ontology features. The Arabic part of speech, particularly adjectives, verbs, and prepositions, and the ontology properties regarding such parts to create new texts, make up the first stage of the system, which has multiple stages. Word2Vector (Word2Vec) plays a pivotal role in giving Arabic ontology features to the specific Arabic Part of …

Transparent Eeg Analysis: Leveraging Autoencoders, Bi-Lstms, And Shap For Improved Neurodegenerative Diseases Detection, Badr Mouazen, Ahmed Bendaouia, Omaima Bellakhdar, Khaoula Laghdaf, Aya Ennair, El Hassan Abdelwahed, Giovanni De Marco

Manufacturing & Industrial Engineering Faculty Publications

Highlights

• Novel hybrid architecture: Combined autoencoders with bidirectional LSTM networks for enhanced EEG signal classification, achieving 98% accuracy in distinguishing AD, FTD, and healthy controls.

• Explainable AI integration: Implemented SHAP (SHapley Additive exPlanations) framework to enhance model transparency and identify entropy as the most influential feature for neurodegenerative disease detection.

• Optimal temporal segmentation: Demonstrated that 5-s EEG windows with 50% overlap provide the best balance between classification accuracy and computational efficiency.

• Comprehensive feature extraction: Utilized Power Spectral Density (PSD) analysis across standard frequency bands (Delta, Theta, Alpha, Beta, Gamma) following autoencoder-based dimensionality reduction.

• Superior performance validation: Outperformed traditional machine learning …

  ---

  Go to article

Leveraging Computational Modelling/Simulation, Machine Learning, And Additive Manufacturing For Customized Design Of Periodontal And Bone Tissue Scaffolds, Rakesh Pemmada

All ETDs from UAB

The current dissertation presents an overarching pipeline for the development and production of custom-made scaffolds for periodontal tissue regeneration using finite element analysis (FEA), machine learning (ML), and additive manufacturing (AM).CAD anatomically realistic scaffolds were generated from CT-based maxilla and mandible models. The FEA simulation results under masticatory (100 N), parafunctional (500–550 N), and traumatic (800–850 N) loads showed region-specific distribution of stresses and strains, which guided structural reinforcement strategies. Over 1000 3D-printed PCL scaffolds were printed using various pore diameters (200–300 µm) and filament diameters. Five ML models were constructed for predicting print quality based on process factors. Classification …

From Model To Behavior: Methodological Challenges In Using Fuzzy Cognitive Maps To Represent Mental Models, Catherine Elizabeth Moore

Dissertations and Theses

This dissertation examines the use of Fuzzy cognitive maps (FCMs) as representations of mental models and how these representations connect to individual behavior. Fuzzy cognitive maps (FCMs) are semi-quantitative models that encode cause-and-effect structures as directed graphs. They are frequently used to represent individuals' knowledge structures/mental models and should in theory correlate to actions and decisions of individuals; however, this correlation has yet to be explored in a systematic manner. This dissertation represents the first step in experimental research on the connection between FCMs and individual behavior. It examines two theories of how humans use mental models, one based on …

Self-Organization In Metal Plasticity: An Ilg Update †, Avraam Konstantinidis, Konstantinos Spiliotis, Amit Chattopadhyay, Elais C. Aifantis

Michigan Tech Publications

In a 1987 article of the last author dedicated to the memory of a pioneer of classical plasticity Aris Philips of Yale, the last author outlined three examples of self-organization during plastic deformation in metals: persistent slip bands (PSBs), shear bands (SBs) and Portevin Le Chatelier (PLC) bands. All three have been observed and analyzed experimentally for a long time, but there was no theory to capture their spatial characteristics and evolution in the process of deformation. By introducing the Laplacian of dislocation density and strain in the standard constitutive equations used for these phenomena, corresponding mathematical models and nonlinear …

Energy-Aware Optimal Reconfiguration Of A Heterogeneous Connected And Automated Vehicle Cohort On A Limited-Access Highway, Pruthwiraj Santhosh, Darrell Robinette, Daniel Knopp, Jeffrey Naber, Jungyun Bae

Michigan Tech Publications

This paper presents an optimized vehicular reordering methodology designed to minimize energy consumption within heterogeneous cohorts operating at constant velocity on limited-access highways. The approach addresses the challenge of optimizing vehicle sequencing by considering both aerodynamic drag reduction benefits and the energy costs of reconfiguring a cohort from a stochastic initial state. This study provides empirical validation through on-road vehicle tests, demonstrating significant energy savings, achieving up to 10% reduction in axle energy for optimally configured cohorts compared to independent operation. A System of Systems (SoS) simulation environment, integrating micro-traffic, validated powertrain, and aerodynamic drag reduction models, was developed to …

Terra Lunaris: Assessment Of A Lunar Habitat For Scientific Astronauts, Space Miners, Or Space Tourists, Dirk Schumann, Robert A. Goehlich

Publications

This conceptual paper explores ground- based habitable space modules for various applications. The Terra Lunaris concept serves as the baseline and is evaluated in comparison to existing and theoretical studies in this field. Terra Lunaris is a compact hybrid habitat that expands to offer nearly four times its transport volume by combining rigid modules with an inflatable shell. With most interior elements pre-installed and foldable, setup time and complexity are minimized. The design integrates technical zones, living quarters, and shared spaces, while also supporting psychological well-being under extreme conditions. The paper provides both qualitative and quantitative analyses of lunar habitation …

Developing Workflows For Passive Acoustic Detection Of Bedload Transport, Quinn Morgan

Dissertations and Theses

Bedload transport is defined as the amount of sediment, including gravel and rocks, traveling down stream. Monitoring bedload transport is important for river safety, hydrological studies and conservation efforts. Existing methods of directly measuring bedload transport (or bedload flux) involve lowering a collection device into a river and measuring the sediment collected; which can be expensive and time consuming. Hydroacoustic sensors, such as hydrophones, have had success tracking bedload flux remotely. This works by measuring the relatively high frequency of sediment impacts to map onto total bedload transported. No perfected method for detection of sediment generated noise (SGN) currently exists. …

Ferric Metal-Organic Frameworks (Mofs)-Based Electrospinning Fibers For Supercapacitors, Samar A. Salim, Hani Nasser Abdelhamid

Nanotechnology Research Centre

Ferric-based metal-organic frameworks (Fe-MOFs) were synthesized and incorporated into poly(methyl methacrylate) (PMMA) using electrospinning to produce PMMA_Fe-MOF nanofibers. The materials were analyzed using X-ray diffraction (XRD), attenuated total reflectance Fourier-transform infrared spectroscopy (ATR-FTIR), and scanning electron microscopy (SEM). The electrospun materials were directly integrated into nickel foam (NF) electrodes for energy storage applications, e.g., supercapacitors. The electrochemical performance was assessed using cyclic voltammetry (CV), galvanostatic charge-discharge curves (GCDC), linear sweep voltammetry (LSV), and electrochemical potentiokinetic reactivation (EPR). The PMMA_Fe-MOF electrodes exhibited outstanding capacitive performance, achieving specific capacitances of up to 1017.5 F/g at 1 A/g for the 2.5 % Fe-MOF …

Nitric Oxide Radiometer Development, Deron Scott, Phil Scott, Trent Newswander, Marty Mlynczak

Space Dynamics Laboratory Publications

SDL developed a small satellite payload to support the NICEcube mission concept capable of measuring vertical profiles of infrared radiance at 5.3 µm from nitric oxide (NO) in the atmospheric limb (100-250 km). These radiance measurements can be directly inverted to achieve vertical profiles of infrared cooling rates which are crucial to understanding the density response to the thermosphere in times of elevated geomagnetic activity. The payload was designed to fit on a 12U cube sat, function at low power and small mechanical envelope. Completed work includes building the telescope, integrating a representative detector, alignment, test planning, and initial testing. …

Underwater Acoustic Integrated Sensing And Communication: A Spatio-Temporal Freshness For Intelligent Resource Prioritization, Ananya Hazarika, Mehdi Rahmati

Electrical and Computer Engineering Faculty Publications

Underwater acoustic communication faces significant challenges including limited bandwidth, high propagation delays, severe multipath fading, and stringent energy constraints. While integrated sensing and communication (ISAC) has shown promise in radio frequency systems, its adaptation to underwater environments remains challenging due to the unique acoustic channel characteristics and the inadequacy of traditional delay-based performance metrics that fail to capture the spatio-temporal value of information in dynamic underwater scenarios. This paper presents a comprehensive underwater ISAC framework centered on a novel Spatio-Temporal Information-Theoretic Freshness metric that fundamentally transforms resource allocation from delay minimization to value maximization. Unlike conventional approaches that treat all …

Development Of Gelma-Based Hydrogel Scaffolds With Tunable Mechanical Properties For Applications In Peripheral Nerve Regeneration, Kylie M. Schmitz, Tanner L. Larson, Michael W. Borovich, Xianfang Wu, Geyou Ao, Megan Jack, Liqun Ning

Chemical & Biomedical Engineering Faculty Publications

Peripheral nerve injuries (PNIs) have a significant impact on the quality of life for patients suffering from trauma or disease. In injuries with critical nerve gaps, PN regeneration requires tissue scaffolds with appropriate physiological properties that promote cell growth and functions. Hydrogel scaffolds represent a promising platform for engineering soft tissue constructs that meet key physiological requirements. Nonetheless, ongoing innovation remains essential, as current designs continue to fall short of replicating the functional performance of autografts in bridging critical-sized nerve defects. In this study, gelatin methacrylate (gelMA)-based hydrogels are evaluated to fully characterize their pore structure, compressive stiffness, viscoelasticity, and …

A Polar Turbulence Invariant Map With Applicability To Realisable Machine Learning Turbulence Models, James G. Wnek, Christopher Schrock, Eric M. Wolf, Mitch Wolff

Mechanical and Materials Engineering Faculty Publications

Invariant maps are a useful tool for turbulence modelling, and the rapid growth of machine learning-based turbulence modelling research has led to renewed interest in them. They allow different turbulent states to be visualised in an interpretable manner and provide a mathematical framework to analyse or enforce realisability. Current invariant maps, however, are limited in machine learning models by the need for costly coordinate transformations and eigendecomposition at each point in the flow field. This paper introduces a new polar invariant map based on an angle that parametrises the relationship of the principal anisotropic stresses, and a scalar that describes …

09.08.2025 Ored Connect, Liz Williamson

ORED Newsletter

• Researcher training opportunities
• Project to increase PhD student success
• ORED online training opportunities

Detecting Electrical Submersible Pump (Esp) Failures And Estimating Run Life Using Artificial Neural Networks, Mostafa Ahmed Sobhy

Theses and Dissertations

Electric Submersible Pumps (ESPs) are one of the important artificial lift methods for sustaining production in mature and high-water-cut wells; but may suffer frequent failures due to mechanical, electrical, hydraulic, chemical, and operational failures. These failures can yield substantial deferred production and intervention costs. Plenty of ESP installations are fitted with downhole sensors. Yet, it is observed that the current industry practice underutilizes the wealth of available sensor and operational data and lacks standardized, explainable failure-type identification and classification.

In this thesis, a comprehensive Machine Learning (ML) and Deep Learning (DL) framework was introduced for ESPs that simultaneously estimates remaining …

Impact Of Composite Materials Research On Underrepresented Communities, Neil Mahesh Bedagkar, Ramanan Sritharan, Wyatt Barnes

Mechanical Engineering

This research assesses how advancements in composites material research affect communities from lower socioeconomic backgrounds, using a dual track strategy to quantitatively and qualitatively examine their impact. A keyword-based classification algorithm was applied to a sample of research papers from ScienceDirect spanning the last 24 years to quantify which engineering industries benefit most from this research. The findings indicate that the construction industry benefits the most, followed by the automotive, defense, renewable energy, and biomedical sectors. A broader qualitative analysis of the social implications of these industries was also conducted to provide context. Each sector were found to have either …

Evaluation Of User Interactions And Preferences Of Shared Bicycle And Pedestrian Transit Platforms, Nathan Mcneil, Sirisha Kothuri, Jennifer Dill, Chris Monsere, Elizabeth Yates, Julia Plotts

Civil and Environmental Engineering Faculty Publications and Presentations

Shared bike and bus platforms have been deployed in an effort to minimize conflicts between bicycles and buses (and other motor vehicles) on streets with bike lanes and bus transit service. This paper assesses bicycle/micromobility user and pedestrian behavior in shared bicycle and transit platforms along a bus rapid transit corridor in Portland, OR. Research objectives include understanding interactions between these users and potential conflicts between people on foot (or wheelchair/mobility devices) who are waiting for, boarding, and/or alighting a bus and people on bicycles riding in the bike lane. The research also assessed how well the shared transit platforms …

Activity Design Principles To Support Engineering Engagement For Families With Preschool-Age Children From Low-Income English-And Spanish-Speaking Communities, Scott A. Pattison, Smirla Ramos Montañez, Viviana López Burgos, Gina Svarovsky, María Quijano, Amy Corbett, Catherine Wagner, Diana Contreras

Journal of Pre-College Engineering Education Research (J-PEER)

Existing evidence highlights the significance of family STEM learning experiences during early childhood. However, there is a lack of research specific to early childhood family-based learning in the field of engineering, especially with preschool-age children (three to five years old). To address this gap and inform engineering education programs for young children, we conducted a design-based research study in collaboration with 15 Spanish-and English-speaking families with preschool-age children from low-income communities. Our study aimed to develop and test a series of family-based engineering design activities while also identifying underlying design principles. Guided by an asset-based family learning framework, which acknowledges …

A Test Rig For An Aircraft Propeller Powered By Battery Motor, C. M. Vigneswaran, J. Induja, K. S. Bharath, M. J. Spoorthi, R. Chethana

Journal of Aviation Technology and Engineering

The propeller test rig is a crucial component in aeronautical engineering that plays a vital role in the development, testing, and optimization of propeller systems for aircraft. This research outlines the design, development, and performance evaluation of a state-of- the- art propeller test rig developed for research and testing purposes. The primary objective of this project is to enhance the understanding of propeller dynamics and efficiency, leading to the improvement of aircraft propulsion systems. The test rig provides a controlled environment to evaluate and compare multiple propeller designs, aiding engineers in making informed decisions during the design process. An advanced …

A Framework For Test Planning Of A Vision System Supporting Aerial Refueling, Jonathon K. Parry, Donald H. Costello, Michael D. M. Kutzer, Charles J. Doherty, Sarah M. Hubbard

Journal of Aviation Technology and Engineering

This essay presents a framework for evaluating a computer vision system providing perception for an uncrewed aircraft completing the automated air-to-air refueling (A3R) task. As the Department of Defense acquires capabilities that exhibit increasing levels of autonomy, the test and evaluation community must adapt the current framework to provide airworthiness officials the information required to accurately access the risks associated with the system underdoing testing. Following a brief introduction to A3R, this essay lays out a testing framework that leverages dendritic analysis and effectively deconstructs the critical issue into measurable data elements that can be used to support test and …

Valuing Fruit Tree Lease Contracts Under Uncertainty: A Probabilistic Framework For Fair Pricing, Abdurakhman Abdurakhman, Agus Sihabuddin, Kurniawan Chandra Wijaya, Evita Purnaningrum, Di Asih I Maruddani

Iraqi Journal for Computer Science and Mathematics

Fruit tree lease contracts are a prevalent economic practice in Indonesia, especially within rural communities. This study addresses the challenge of establishing equitable contract prices for both lessees and tree owners, specifically by integrating the inherent uncertainties associated with crop yield and fruit price fluctuations. To achieve this, we develop and employ two distinct models: Fixed-Time Discount Model (FTD) and the Dynamic-Time Discount Model (DTD). Each model is mathematically formulated, leveraging a Poisson distribution to capture yield uncertainty and a Uniform distribution to represent fruit price variability. Through computations, we evaluate the impact of key parameters - average yield ( …

Ada-Application Of Decision Analysis For Developing A Healthcare System To Predict Fetal Health, Melfi Alrasheedi, Theyazn.H.H Aldhyani

Iraqi Journal for Computer Science and Mathematics

A fatal health condition involves an unborn baby that persists throughout the embryonic stage until delivery. The fetus grows and develops during each trimester of pregnancy. Obstetricians may detect fetal anomalies and select medical interventions based on cardiotocogram (CTG) data. However, the obstetrician's visual assessment of CTG data can sometimes be subjective or inaccurate. Therefore, automated analysis using machine learning approaches for CTG data is essential. This research employs decision analysis techniques, including decision trees (DT), gradient boosting (GB), and type-2 fuzzy neural networks (FNN), for prenatal analysis and prediction. The system was tested using a standard dataset consisting of …

Retracted: Hotspot Issue Handling And Reliable Data Forwarding Technique For Ocean Underwater Sensor Networks, Omar Adil Mahdi, Yusor Rafid Bahar Al-Mayouf, Sameer Sami Hassan Al-Obaidi, Bourair Al-Attar, Hamed Balogun, Suleman Khan

Iraqi Journal for Computer Science and Mathematics

Underwater Wireless Sensor Networks (UWSNs) have emerged as a promising technology for a wide range of ocean monitoring applications. The UWSNs suffer from unique challenges of the underwater environment, such as dynamic and sparse network topology, which can easily lead to a partitioned network. This results in hotspot formation and the absence of the routing path from the source to the destination. Therefore, to optimize the network lifetime and limit the possibility of hotspot formation along the data transmission path, the need to plan a traffic-aware protocol is raised. In this research, we propose a traffic-aware routing protocol called PG-RES, …

Event-Based Sensor Noise Modeling For Space-Based Space Domain Awareness, Rachel Oliver, Brian Mcreynolds, Dmitry Savransky

Faculty Publications

Building off the foundation of a physics-based end-to-end model for event-based vision sensors (EVS) observing resident space objects (RSOs), we apply new techniques to model realistic low-light sensor noise. While previous approaches simulate memorized current leakage and apply temporal noise models, our methods improve on these approaches and additionally account for current-following noise as an event source. These improvements are key components for accurate event-generating simulators which can advise requirements and concepts of operations for dedicated event-based Space Domain Awareness (SDA) architectures. The EVS pixel’s independent and asynchronous recording of changes in photocurrent produces data with high temporal resolution and …

The Green Approach Of Arabic Gum-Based Adsorbent In Wastewater Treatment, Atheel H. Alwash

AUIQ Technical Engineering Science

The natural polysaccharide Arabic gum is a multifunctional, sustainable material used widely in wastewater treatment technology. Its active functional groups such as hydroxyl, carboxyl, and amino groups facilitate the efficient removal of heavy metals, dyes, pesticides, pharmaceuticals, and persistent organic pollutants. The high surface area and active functional groups facilitate its modification to form various structures such as hydrogels, nanocomposites, or biochar integrated into hybrid adsorption–photocatalysis systems. This review highlights the most familiar forms of Arabic gum in wastewater treatment technology, such as hydrogels, hydrogels nanocomposite, stabilizing agents, coating agents, and bio-activated carbon derived from Arabic gum using different preparation …

Memf-Net: A Mega-Ensemble Of Multi-Feature Cnns For Classification Of Breast Histopathological Images, Alaa Hussein Abdulaal, Ali H. Abdulwahhab, Aqeel Majeed Breesam, Zahra Hasan Oleiwi, Riyam Ali Yassin, Morteza Valizadeh, Saja Nafea Mohsin

Iraqi Journal for Computer Science and Mathematics

Pathological anatomical images play a pivotal role in diagnosing diseases, notably breast cancer, which affects women globally. These images, obtained through biopsies or post-mortem examinations, are preserved to maintain their structural integrity. Software tools, like computer-aided diagnosis, aid doctors in early detection and treatment planning, contributing to reduced mortality rates. In this context, convolutional neural networks (CNNs) have emerged as valuable tools for diagnosing benign and malignant breast cancers. This paper introduces a Mega Ensemble Net method, leveraging multi-scale combination features on the breast histopathology dataset. Three fine-tuned deep learning models, namely ResNet-18, ResNet-34, and ResNet-50, are integrated into this …

Retracted: Capsule Network Model For Detecting Spoofing Attack In The Internet Of Medical Things (Iomt), Mohammad A. Alsharaiah, Mohammed Amin Almaiah, Mansour Obeidat, Rami Shehab

Iraqi Journal for Computer Science and Mathematics

The Internet of Medical Things (IoMT) has transformed healthcare delivery through real-time monitoring and data exchange. However, this integration of smart medical devices has also introduced critical cybersecurity threats, particularly spoofing attacks, which can compromise patient safety and system reliability. Conventional Intrusion Detection Systems (IDS) often fail to address IoMT-specific challenges such as class imbalance, computational constraints, and the need for real-time adaptability. This study proposes a Capsule Network (CapsNet)-based IDS that leverages spatial dependency modeling and hierarchical feature relationships to detect spoofing attacks in IoMT environments. Using the CICIoMT2024 dataset, we implemented a binary classification framework where spoofing instances …