Engineering Commons^™

A Hybrid Data And Hypothesis-Driven Model For Software Development In Support Of The Machine-Learning Paradigm, Anthony D. Bowman

All ETDs from UAB

istorically, research has often been conducted in a hypothesis-driven manner with software development methodologies created to support those efforts. However, in recent years data-driven approaches to research have seen a dramatic rise in prominence. While software development methodologies such as agile development, extreme programming, and the waterfall model have allowed developers to tackle increasingly complex problems, they were not designed to efficiently support data-driven approaches such as the machine learning paradigm. To address the need to support the different programmatic requirements of both classical, hypothesis-driven as well as data-driven development, novel development strategies are warranted. In this research, we adapted …

A Convolutional Neural Network (Cnn) For Defect Detection Of Additively Manufactured Parts, Musarrat Farzana Rahman

Masters Theses

“Additive manufacturing (AM) is a layer-by-layer deposition process to fabricate parts with complex geometries. The formation of defects within AM components is a major concern for critical structural and cyclic loading applications. Understanding the mechanisms of defect formation and identifying the defects play an important role in improving the product lifecycle. The convolutional neural network (CNN) has been demonstrated to be an effective deep learning tool for automated detection of defects for both conventional and AM processes. A network with optimized parameters including proper data processing and sampling can improve the performance of the architecture. In this study, for the …

Few-Shot Malware Detection Using A Novel Adversarial Reprogramming Model, Ekula Praveen Kumar

Browse all Theses and Dissertations

The increasing sophistication of malware has made detecting and defending against new strains a major challenge for cybersecurity. One promising approach to this problem is using machine learning techniques that extract representative features and train classification models to detect malware in an early stage. However, training such machine learning-based malware detection models represents a significant challenge that requires a large number of high-quality labeled data samples while it is very costly to obtain them in real-world scenarios. In other words, training machine learning models for malware detection requires the capability to learn from only a few labeled examples. To address …

Design Of Composite Joints Using Machine Learning Approaches, Natalie Richards

Williams Honors College, Honors Research Projects

Adhesively bonded joints have an advantage in joining dissimilar engineering materials due to their high structural efficiency and being lightweight. These joints are either between two opposite laminates or between a composite laminate and a metal structure. The aerospace and automotive industries have seen an increase in utilizing these adhesive joints in their engineering applications. Joint strength along with the failure mode (adhesive, delamination, etc.) is the most important parameter to evaluate when understanding the capability of the adhesive joint. In this paper, a regression and a classification machine learning (ML) model are utilized to predict the failure load and …

Non-Parametric Stochastic Autoencoder Model For Anomaly Detection, Raphael B. Alampay, Patricia Angela R. Abu

Department of Information Systems & Computer Science Faculty Publications

Anomaly detection is a widely studied field in computer science with applications ranging from intrusion detection, fraud detection, medical diagnosis and quality assurance in manufacturing. The underlying premise is that an anomaly is an observation that does not conform to what is considered to be normal. This study addresses two major problems in the field. First, anomalies are defined in a local context, that is, being able to give quantitative measures as to how anomalies are categorized within its own problem domain and cannot be generalized to other domains. Commonly, anomalies are measured according to statistical probabilities relative to the …

Reconfigurable Array Control Via Convolutional Neural Networks, Garrett A. Harris

Browse all Theses and Dissertations

A method for the beam forming control of an array of reconfigurable antennas is presented. The method consists of using two parallel convolutional neural networks (CNNs) to analyze a desired radiation pattern image, or mask, and provide a suggestion for the reconfigurable element state, array shape, and steering weights necessary to obtain the radiation pattern. This research compares beam forming systems designed for three distinct element types: a patch antenna, a reconfigurable square spiral antenna restricted to a single reconfigurable state, and the fully reconfigurable square spiral. The parametric sweeps for the design of the CNNs are presented along with …

Explainable Data-Driven Motor Condition Monitoring And Fault Disgnosis, Yuming Wang

Theses and Dissertations--Electrical and Computer Engineering

Industrial motors are widely used in various fields such as power generation, mining, and manufacturing. Motor faults and time-consuming maintenance process will lead to serious economic losses in this context. To monitor motor faults and detect motor conditions, different types of sensors that can test vibration and current signals are mounted on motors. However, the main challenge was how to use information gained by sensors to analyze or diagnose motor conditions.

Machine learning is a popular technology in recent years, and it's very suitable for crunching and analyzing data. As an important subset of machine learning, deep learning is suitable …

Security Concerns On Machine Learning Solutions For 6g Networks In Mmwave Beam Prediction, Ferhat Ozgur Catak, Murat Kuzlu, Evren Catak, Umit Cali, Devrim Unal

Engineering Technology Faculty Publications

6G – sixth generation – is the latest cellular technology currently under development for wireless communication systems. In recent years, machine learning (ML) algorithms have been applied widely in various fields, such as healthcare, transportation, energy, autonomous cars, and many more. Those algorithms have also been used in communication technologies to improve the system performance in terms of frequency spectrum usage, latency, and security. With the rapid developments of ML techniques, especially deep learning (DL), it is critical to consider the security concern when applying the algorithms. While ML algorithms offer significant advantages for 6G networks, security concerns on artificial …

A Citizen-Science Approach For Urban Flood Risk Analysis Using Data Science And Machine Learning, Candace Agonafir

Dissertations and Theses

Street flooding is problematic in urban areas, where impervious surfaces, such as concrete, brick, and asphalt prevail, impeding the infiltration of water into the ground. During rain events, water ponds and rise to levels that cause considerable economic damage and physical harm. The main goal of this dissertation is to develop novel approaches toward the comprehension of urban flood risk using data science techniques on crowd-sourced data. This is accomplished by developing a series of data-driven models to identify flood factors of significance and localized areas of flood vulnerability in New York City (NYC). First, the infrastructural (catch basin clogs, …

Similitude, Scaling, And Prediction Of Stream Dissolved Oxygen Across The Contiguous U.S., Aron Gebreslase

Graduate Theses, Dissertations, and Problem Reports (ETD)

Dissolved oxygen (DO) is a general indicator of stream water quality and ecosystem health. However, the concentration of in-stream DO is controlled by various climatic, land use/cover, hydrologic, biochemical, and ecological drivers. Observational data for stream DO are often unavailable at the desired temporal and spatial scales. Accurate and reliable prediction of stream DO concentration based on a small set of environmental drivers is important to guide the water managers and policymakers to achieve and maintain healthy streams. This dissertation focused on identifying the dominant controls of stream DO and understanding the mechanisms and environmental regimes by employing machine learning, …

Machine Learning Land Cover And Land Use Classification Of 4-Band Satellite Imagery, Lorelei Turner, Torrey J. Wagner, Paul Auclair, Brent T. Langhals

Faculty Publications

Land-cover and land-use classification generates categories of terrestrial features, such as water or trees, which can be used to track how land is used. This work applies classical, ensemble and neural network machine learning algorithms to a multispectral remote sensing dataset containing 405,000 28x28 pixel image patches in 4 electromagnetic frequency bands. For each algorithm, model metrics and prediction execution time were evaluated, resulting in two families of models; fast and precise. The prediction time for an 81,000-patch group of predictions wasmodels, and >5s for the precise models, and there was not a significant change in prediction time when a …

Automatically Classifying Familiar Web Users From Eye-Tracking Data:A Machine Learning Approach, Meli̇h Öder, Şükrü Eraslan, Yeli̇z Yesi̇lada

Turkish Journal of Electrical Engineering and Computer Sciences

Eye-tracking studies typically collect enormous amount of data encoding rich information about user behaviours and characteristics on the web. Eye-tracking data has been proved to be useful for usability and accessibility testing and for developing adaptive systems. The main objective of our work is to mine eye-tracking data with machine learning algorithms to automatically detect users' characteristics. In this paper, we focus on exploring different machine learning algorithms to automatically classify whether users are familiar or not with a web page. We present our work with an eye-tracking data of 81 participants on six web pages. Our results show that …

Stressed Or Just Running? Differentiation Of Mental Stress And Physical Activityby Using Machine Learning, Yekta Sai̇d Can

Turkish Journal of Electrical Engineering and Computer Sciences

Recently, modern people have excessive stress in their daily lives. With the advances in physiological sensors and wearable technology, people?s physiological status can be tracked, and stress levels can be recognized for providing beneficial services. Smartwatches and smartbands constitute the majority of wearable devices. Although they have an excellent potential for physiological stress recognition, some crucial issues need to be addressed, such as the resemblance of physiological reaction to stress and physical activity, artifacts caused by movements and low data quality. This paper focused on examining and differentiating physiological responses to both stressors and physical activity. Physiological data are collected …

Depression Of Pyrite In Polymetallic Sulfide Flotation Using Chitosan-Grafted-Polyacrylamide Polymers, Keitumetse Cathrine Monyake

Doctoral Dissertations

“In this work, Chitosan-grafted-Polyacrylamides (Chi-g-PAMs) were studied, for the first time, as selective depressants of pyrite in the flotation of base metal sulfides. Fundamental studies of the adsorption behavior of Chi-g-PAM on model sulfide minerals indicated that Chi-g-PAM was more selective to pyrite’s surfaces as compared to base metal sulfides. Results suggested that the adsorption of Chi-g-PAM at pyrite-water interface was a chemisorption in nature which involved the amine, amide, and hydroxyl groups of Chi-g-PAM. Batch flotation studies of complex sulfide ore of Mississippi Valley Type (MVT) showed that Chi-g-PAM outperformed other pyrite’s depressants at producing less pyrite-diluted concentrates. Statistical …

Groundwater Withdrawal Estimation Using Integrated Remote Sensing Products And Machine Learning, Sayantan Majumdar

Doctoral Dissertations

"The rising demands for water, food, and energy primarily driven by the increasing global population constitute a pressing issue worldwide. Therefore, the water-food-energy nexus plays a substantial role in developing globally applicable sustainable solutions. Recent technological advancements, including the earth observation programs using spaceborne remote sensing platforms, have enabled us to monitor various critical components affecting the globe. Groundwater, which comprises the world's 30% freshwater, is one such key component of the global water resources and supplies nearly half of the global drinking water.

Despite groundwater overdraft in many parts of the world, including the United States (US), there are …

Part I - Ai And Data As Medical Devices, W. Nicholson Price Ii

Other Publications

It may seem counterintuitive to open a book on medical devices with chapters on software and data, but these are the frontiers of new medical device regulation and law. Physical devices are still crucial to medicine, but they – and medical practice as a whole – are embedded in and permeated by networks of software and caches of data. Those software systems are often mindbogglingly complex and largely inscrutable, involving artificial intelligence and machine learning. Ensuring that such software works effectively and safely remains a substantial challenge for regulators and policymakers. Each of the three chapters in this part examines …

Facial Landmark Feature Fusion In Transfer Learning Of Child Facial Expressions, Megan A. Witherow, Manar D. Samad, Norou Diawara, Khan M. Iftekharuddin

Electrical & Computer Engineering Faculty Publications

Automatic classification of child facial expressions is challenging due to the scarcity of image samples with annotations. Transfer learning of deep convolutional neural networks (CNNs), pretrained on adult facial expressions, can be effectively finetuned for child facial expression classification using limited facial images of children. Recent work inspired by facial age estimation and age-invariant face recognition proposes a fusion of facial landmark features with deep representation learning to augment facial expression classification performance. We hypothesize that deep transfer learning of child facial expressions may also benefit from fusing facial landmark features. Our proposed model architecture integrates two input branches: a …

Srf Cavity Fault Classification And Prediction At Jefferson Lab, Chris Tennant, Adam Carpenter, Lasitha Vidyaratne, Md. Monibor Rahman, Khan Iftekharuddin

Electrical & Computer Engineering Faculty Publications

Over the last few years several machine learning projects at Jefferson Lab have had a common focus to optimize operation of superconducting RF (SRF) cavities in the Continuous Electron Beam Accelerator Facility (CEBAF). In this talk we highlight work to identify and classify types of faults from C100-type cavities and then to extend those capabilities to provide real-time fault prediction. Early prediction may enable mitigation strategies to prevent some types of faults. In our approach we apply a two-step fault prediction pipeline. In the first step, a model distinguishes between faulty and normal signals. In the second step, signals flagged …

Understanding Structure/Process-Property Relationships To Optimize Development Lifecycle In Yttria-Stabilized Zirconia Aerogels For Thermal Management, Rebecca C. Walker

Theses and Dissertations

Aerogels are mesoporous materials with unique properties, including high specific surface area, high porosity, low thermal conductivity, and low density, increasing these materials’ effectiveness in applications such as catalyst supports, sorption media, and electrodes in solid oxide fuel cells. Zirconia (ZrO₂) aerogels have special interest for high-temperature applications due to the high melting point of ZrO₂ (2715°C) and stability between 600°C and 1000°C, where other aerogel systems often begin to sinter and densify. These properties and unique pore structure make zirconia aerogels advantageous as thermal management systems, especially in aeronautics and aerospace applications. However, to be effective …

A Hybrid Machine Learning Technique For Feature Optimization In Object-Based Classification Of Debris-Covered Glaciers, Shikha Sharda, Mohit Srivastava, Hemendra Singh Gusain, Naveen Kumar Sharma, Kamaljit Singh Bhatia, Mohit Bajaj, Harsimrat Kaur, Hossam Zawbaa, Salah Kamel

Articles

Object-based features like spectral, topographic, and textural are supportive to determine debris-covered glacier classes. The original feature space includes relevant and irrelevant features. The inclusion of all these features increases the complexity and renders the classifier’s performance. Therefore, feature space optimization is requisite for the classification process. Previous studies have shown a rigorous exercise in manually selecting the best combination of features to define the target class and proven to be a time consuming task. The present study proposed a hybrid feature selection technique to automate the selection of the best suitable features. This study aimed to reduce the classifier’s …

Development Of Machine Learning Algorithm To Identify High-Emitters From On-Road Data For Heavy-Duty (Hd) Vehicles, Filiz Kazan

Graduate Theses, Dissertations, and Problem Reports (ETD)

The process of on-road, heavy-duty engine family certification is regulated by the United States Environmental Protection Agency (US EPA). Currently, the US EPA 2010 emissions standards require the threshold from the Federal Testing Procedure (FTP) engine dynamometer cycle to be at or below a brake-specific NO_x (bs-NO_x) value of 0.20 g/bhp-hr for heavy-duty (HD) engines. The engine manufacturers are also required to conduct in-use portable emission measurement system (PEMS) testing to prove their products' compliance. The selected vehicles are required to satisfy not-to-exceed (NTE) analysis under normal driving conditions in the heavy-duty in-use testing (HDIUT) program. California …

Probabilistic Space Weather Modeling And Forecasting For The Challenge Of Orbital Drag In Space Traffic Management, Richard J. Licata Iii

Graduate Theses, Dissertations, and Problem Reports (ETD)

In the modern space age, private companies are crowding the already-congested low Earth orbit (LEO) regime with small satellite mega constellations. With over 25,000 objects larger than 10 cm already in LEO, this rapid expansion is forcing us towards the enterprise on Space Traffic Management (STM). STM is an operational effort that focuses on conjunction assessment and collision avoidance between objects. While the equations of motion for objects in orbit are well-known, there are many uncertain parameters that result in the uncertainty of an object's future position. The force that the atmosphere exerts on satellite - known as drag - …

An Intelligent Approach For Predicting The Strength Of Geosynthetic-Reinforced Subgrade Soil, Muhammad Nouman Amjad Raja, Sanjay K. Shukla, Muhammad Umer Arif Khan

Research outputs 2014 to 2021

In the recent times, the use of geosynthetic-reinforced soil (GRS) technology has become popular for constructing safe and sustainable pavement structures. The strength of the subgrade soil is routinely assessed in terms of its California bearing ratio (CBR). However, in the past, no effort was made to develop a method for evaluating the CBR of the reinforced subgrade soil. The main aim of this paper is to explore and appraise the competency of the several intelligent models such as artificial neural network (ANN), least median of squares regression, Gaussian processes regression, elastic net regularisation regression, lazy K-star, M-5 model …

Artificial Intelligence-Based Material Discovery For Clean Energy Future, Reza Maleki, Mohsen Asadnia, Amir Razmjou

Research outputs 2022 to 2026

Artificial intelligence (AI)-assisted materials design and discovery methods can come to the aid of global concerns for introducing new efficient materials in different applications. Also, a sustainable clean future requires a transition to a low-carbon economy that is material-intensive. AI-assisted methods advent as inexpensive and accelerated methods in the design of new materials for clean energies. Herein, the emerging research area of AI-assisted material discovery with a focus on developing clean energies is discussed. The applications, advantages, and challenges of using AI in material discovery are discussed and the future perspective of using AI in clean energy is studied. This …

Physical Layer Authentication Using Ensemble Learning Technique In Wireless Communications, Muhammad Waqas, Shehr Bano, Fatima Hassan, Shanshan Tu, Ghulam Abbas, Ziaul Haq Abbas

Research outputs 2022 to 2026

Cyber-physical wireless systems have surfaced as an important data communication and networking research area. It is an emerging discipline that allows effective monitoring and efficient real-time communication between the cyber and physical worlds by embedding computer software and integrating communication and networking technologies. Due to their high reliability, sensitivity and connectivity, their security requirements are more comparable to the Internet as they are prone to various security threats such as eavesdropping, spoofing, botnets, man-in-the-middle attack, denial of service (DoS) and distributed denial of service (DDoS) and impersonation. Existing methods use physical layer authentication (PLA), the most promising solution to detect …

Statistics-Based Anomaly Detection And Correction Method For Amazon Customer Reviews, Ishani Chatterjee

Dissertations

People nowadays use the Internet to project their assessments, impressions, ideas, and observations about various subjects or products on numerous social networking sites. These sites serve as a great source of gathering information for data analytics, sentiment analysis, natural language processing, etc. The most critical challenge is interpreting this data and capturing the sentiment behind these expressions. Sentiment analysis is analyzing, processing, concluding, and inferencing subjective texts with the views. Companies use sentiment analysis to understand public opinions, perform market research, analyze brand reputation, recognize customer experiences, and study social media influence. According to the different needs for aspect granularity, …

On Resource-Efficiency And Performance Optimization In Big Data Computing And Networking Using Machine Learning, Wuji Liu

Dissertations

Due to the rapid transition from traditional experiment-based approaches to large-scale, computational intensive simulations, next-generation scientific applications typically involve complex numerical modeling and extreme-scale simulations. Such model-based simulations oftentimes generate colossal amounts of data, which must be transferred over high-performance network (HPN) infrastructures to remote sites and analyzed against experimental or observation data on high-performance computing (HPC) facility. Optimizing the performance of both data transfer in HPN and simulation-based model development on HPC is critical to enabling and accelerating knowledge discovery and scientific innovation. However, such processes generally involve an enormous set of attributes including domain-specific model parameters, network transport …

Exploiting Building Demand Flexibility Through Machine Learning For Building-To-Grid Integration, Hannah Charlene Fontenot

Dissertations - ALL

Demand flexibility – the ability to adjust a building's load profile across different timescales – is a key aspect of the ongoing effort to increase interconnectivity between buildings and the power grid. By harnessing their demand flexibility, buildings can provide significant benefits to the grid and bolster grid resilience and reliability. To facilitate the transition toward the "smart grid", new and intelligent control approaches are required that can seamlessly integrate building, occupant, and grid data and effectively control multiple building assets to provide grid services while maintaining occupants' required thermal comfort levels and reducing the building's overall energy consumption and …

Nondestructive Detection Of Codling Moth Infestation In Apples Using Pixel-Based Nir Hyperspectral Imaging With Machine Learning And Feature Selection, Nader Ekramirad, Alfadhl Y. Khaled, Lauren E. Doyle, Julia R. Loeb, Kevin D. Donohue, Raul T. Villanueva, Akinbode A. Adedeji

Electrical and Computer Engineering Faculty Publications

Codling moth (CM) (Cydia pomonella L.), a devastating pest, creates a serious issue for apple production and marketing in apple-producing countries. Therefore, effective nondestructive early detection of external and internal defects in CM-infested apples could remarkably prevent postharvest losses and improve the quality of the final product. In this study, near-infrared (NIR) hyperspectral reflectance imaging in the wavelength range of 900–1700 nm was applied to detect CM infestation at the pixel level for three organic apple cultivars, namely Gala, Fuji and Granny Smith. An effective region of interest (ROI) acquisition procedure along with different machine learning and data processing …

Machine-Learning Algorithms For Forecast-Informed Reservoir Operation (Firo) To Reduce Flood Damages, Manizhe Zarei, Omid Bozorg-Haddad, Sahar Baghban, Mohammad Delpasand, Erfan Goharian, Hugo A. Loaiciga

Faculty Publications

Water is stored in reservoirs for various purposes, including regular distribution, flood control, hydropower generation, and meeting the environmental demands of downstream habitats and ecosystems. However, these objectives are often in conflict with each other and make the operation of reservoirs a complex task, particularly during flood periods. An accurate forecast of reservoir inflows is required to evaluate water releases from a reservoir seeking to provide safe space for capturing high flows without having to resort to hazardous and damaging releases. This study aims to improve the informed decisions for reservoirs management and water prerelease before a flood occurs by …