Engineering Commons^™

Prediction Of Self-Diffusion Constants In Model And Real Systems Using Machine Learning, Joshua P. Allers

Chemical and Biological Engineering ETDs

Understanding diffusion of chemical compounds is important for the design and optimization of many chemical engineering and energy processes. Recent modifications to the Darken equation allow for accurate prediction of Maxwell-Stefan (MS) diffusion in mixtures. Still, there are few practical applications due to the requirement of individual self-diffusion constants. A reliable predictive model for self-diffusion constants would be highly valuable when used in conjunction with the modified Darken equation. Here, we show that Machine Learning (ML) can be used to develop generalized models for self-diffusion in Lennard Jones (LJ) systems and real systems of pure solutions. The use of Artificial …

How The Power Of Machine – Machine Learning, Data Science And Nlp Can Be Used To Prevent Spoofing And Reduce Financial Risks, Sasibhushan Rao Chanthati

Harrisburg University Other Works

This paper discusses the potential of machine learning, data science, and natural language processing (NLP) in mitigating the incidence of spoofing and financial risks hinged on cyber threats. Another one is spoofing; it is the act of impersonating legitimate entities to gain unauthorized information and it is indeed a threat to the public and companies to some extent. The research introduces two primary methodologies to combat spoofing: an email filtering system using a machine learning algorithm and an encryption and decryption system using a Caesar Cipher and Python programming language. It distinguishes between approved domains and unapproved domains by using …

Fiber Optic Sensor Embedded Smart Helmet For Real-Time Impact Sensing And Analysis Through Machine Learning, Yiyang Zhuang, Qingbo Yang, Taihao Han, Ryan O'Malley, Aditya Kumar, Rex E. Gerald Ii, Jie Huang

Electrical and Computer Engineering Faculty Research & Creative Works

Background: Mild traumatic brain injury (mTBI) strongly associates with chronic neurodegenerative impairments such as post-traumatic stress disorder (PTSD) and mild cognitive impairment. Early detection of concussive events would significantly enhance the understanding of head injuries and provide better guidance for urgent diagnoses and the best clinical practices for achieving full recovery. New method: A smart helmet was developed with a single embedded fiber Bragg grating (FBG) sensor for real-time sensing of blunt-force impact events to helmets. The transient signals provide both magnitude and directional information about the impact event, and the data can be used for training machine learning (ML) …

Deep Reinforcement Learning Applied To Spacecraft Attitude Control And Moment Of Inertia Estimation Via Recurrent Neural Networks, Nathaniel A. Enders

Theses and Dissertations

This study investigated two distinct problems related to unknown spacecraft inertia. The first problem explored the use of a recurrent neural network to estimate spacecraft moments of inertia using angular velocity measurements. Initial results showed that, for the configuration examined, the neural network can estimate the moments of inertia when there is a known external torque. The second problem trained a reinforcement learning agent, via proximal policy optimization, to control the attitude of a spacecraft. The results demonstrated that reinforcement learning may be a viable option for guidance and control solutions where the spacecraft model may be unknown. The trained …

Pain Recognition Performance On A Single Board Computer, Iyonna L. Tynes

USF Tampa Graduate Theses and Dissertations

Emotion recognition is a quickly growing field of study due to the increased interest in building systems which can classify and respond to emotions. Recent medical crises, such as the opioid overdose epidemic in the United States and the global COVID-19 pandemic has emphasized the importance of emotion recognition applications is areas like Telehealth services. Considering this, this thesis focuses specifically on pain recognition. The problem of pain recognition is approached from both a hardware and software perspective, as we propose a real-time pain recognition system, from facial images, that is deployed on an NVIDIA Jetson Nano single-board computer. We …

Reinforcement Learning-Based Access Schemes In Cognitive Radio Networks, Ehab Maged Elguindy

Theses and Dissertations

In this thesis, we propose different MAC protocols based on three Reinforcement Learning (RL) approaches, namely Q-Learning, Deep Q-Network (DQN), and Deep Deterministic Policy Gradient (DDPG). We exploit the primary user (PU) feedback, in the form of ARQ and CQI bits, to enhance the performance of the secondary user (SU) MAC protocols. Exploiting the PU feedback information can be applied on the top of any SU sensing-based MAC protocol. Our proposed model relies on two main pillars, namely, an infinite-state Partially Observable Markov Decision Process (POMDP) to model the system dynamics besides a queuing-theoretic model for the PU queue; the …

Source Localization With Machine Learning, Arjun Gupta

Electrical and Computer Engineering ETDs

Source localization with sensor arrays have found applications across domains beginning with radar and sonar, astronomy, acoustics, bio-medical devices and more recently in autonomous cars and adaptive communication systems. The knowledge of the spatial spectrum not only provide information about the source and interference but also assists in increasing signal integrity and avoid interference. This provides an added degree of freedom in the form of spatial diversity. This research investigates spatial spectrum estimation of waveforms from the signals sampled by arbitrarily distributed sensors. Conventional high resolution algorithms such as root-MuSiC fails to perform accurate source localization due to the reliance …

Time Series Data Analysis Using Machine Learning-(Ml) Approach, Mvv Prasad Kantipudi Dr., Pradeep Kumar N.S Dr., S.Sreenath Kashyap Dr., Ss Anusha Vemuri Ms

Library Philosophy and Practice (e-journal)

Healthcare benefits related to continuous monitoring of human movement and physical activity can potentially reduce the risk of accidents associated with elderly living alone at home. Based on the literature review, it is found that many studies focus on human activity recognition and are still active towards achieving practical solutions to support the elderly care system. The proposed system has introduced a joint approach of machine learning and signal processing technology for the recognition of human's physical movements using signal data generated by accelerometer sensors. The framework adopts the concept of DSP to select very descriptive feature sets and uses …

Diabetes Prediction Using Machine Learning : A Bibliometric Analysis, Vijayshri Nitin Khedkar, Sina Patel

Library Philosophy and Practice (e-journal)

Diabetes Mellitus is a chronic disease which can be deadly if undetected for longer time. Artificial intelligence is helping in healthcare industry to a great extent by helping professionals to derive useful information and patterns from data available in various formats: Survey data, electronic health records, laboratory data.. Diabetes, if predicted at an early stage can help many people to save lives and cost for healthcare. Decision-making, diagnosing and predicting diabetes have become an increasing trend in recent years. There are numerous publications in diabetes prediction and yet it’s an ongoing research topic with availability of new data and methods. …

Machine Learning Morphisms: A Framework For Designing And Analyzing Machine Learning Work Ows, Applied To Separability, Error Bounds, And 30-Day Hospital Readmissions, Eric Zenon Cawi

McKelvey School of Engineering Graduate Student Theses & Dissertations

A machine learning workflow is the sequence of tasks necessary to implement a machine learning application, including data collection, preprocessing, feature engineering, exploratory analysis, and model training/selection. In this dissertation we propose the Machine Learning Morphism (MLM) as a mathematical framework to describe the tasks in a workflow. The MLM is a tuple consisting of: Input Space, Output Space, Learning Morphism, Parameter Prior, Empirical Risk Function. This contains the information necessary to learn the parameters of the learning morphism, which represents a workflow task. In chapter 1, we give a short review of typical tasks present in a workflow, as …

A Literature Survey And Bibliometric Analysis Of Application Of Artificial Intelligence Techniques On Wireless Mesh Networks, Smita R. Mahajan Mrs., Harikrishnan R Dr., Ketan Kotecha Dr.

Library Philosophy and Practice (e-journal)

Recent years have seen a surge in the use of technology for executing transactions in both online and offline modes. Various industries like banking, e-commerce, and private organizations use networks for the exchange of confidential information and resources. Network security is thus of utmost importance, with the expectation of effective and efficient analysis of the network traffic. Wireless Mesh Networks are effective in communicating information over a vast span with minimal costs. A network is evaluated based on its security, accessibility, and extent of interoperability. Artificial Intelligence techniques like machine learning and deep learning have found widespread use to solve …

Medical Surge Capability: Performance Modeling Of Hospital Emergency Departments, Egbe-Etu Emmanuel Etu

Wayne State University Dissertations

Hospitals are faced with significant challenges during and after natural or human-caused disasters. Surge planning is a critical component of every healthcare facility’s emergency plan and response system. The process of managing and allocating scarce resources by tackling the vulnerability inherent to patients means that defining improvement priorities is one of the main challenges healthcare systems face when responding to a medical surge event (e.g., COVID-19). The consequences of these challenges include increased patient mortality, ambulance diversion, long wait times, and unavailability of beds. Previous efforts in hospital operations management have successfully applied operations research techniques in analyzing and optimizing …

Computational Analysis And Prediction Of Intrinsic Disorder And Intrinsic Disorder Functions In Proteins, Akila I. Katuwawala

Theses and Dissertations

COMPUTATIONAL ANALYSIS AND PREDICTION OF INTRINSIC DISORDER AND INTRINSIC DISORDER FUNCTIONS IN PROTEINS

By Akila Imesha Katuwawala

A dissertation submitted in partial fulfillment of the requirements for the degree of Engineering, Doctor of Philosophy with a concentration in Computer Science at Virginia Commonwealth University.

Virginia Commonwealth University, 2021

Director: Lukasz Kurgan, Professor, Department of Computer Science

Proteins, as a fundamental class of biomolecules, have been studied from various perspectives over the past two centuries. The traditional notion is that proteins require fixed and stable three-dimensional structures to carry out biological functions. However, there is mounting evidence regarding a “special” class …

Estimating Affective States In Virtual Reality Environments Using The Electroencephalogram, Meghan R. Kumar

Theses and Dissertations

Recent interest in high-performance virtual reality (VR) headsets has motivated research efforts to increase the user's sense of immersion via feedback of physiological measures. This work presents the use of electroencephalographic (EEG) measurements during observation of immersive VR videos to estimate the user's affective state. The EEG of 30 participants were recorded as each passively viewed a series of one minute immersive VR video clips and subjectively rated their level of valence, arousal, dominance, and liking. Correlates between EEG spectral bands and the subjective ratings were analyzed to identify statistically significant frequencies and electrode locations across participants. Model feasibility and …

Cascaded Deep Learning Network For Postearthquake Bridge Serviceability Assessment, Youjeong Jang

Electronic Theses and Dissertations

Damages assessment of bridges is important to derive immediate response after severe events to decide serviceability. Especially, past earthquakes have proven the vulnerability of bridges with insufficient detailing. Due to lack of a national and unified post-earthquake inspection procedure for bridges, conventional damage assessments are performed by sending professional personnel to the onsite, detecting visually and measuring the damage state. To get accurate and fast damage result of bridge condition is important to save not only lives but also costs.
There have been studies using image processing techniques to assess damage of bridge column without sending individual to onsite. Convolutional …

Neural Network Supervised And Reinforcement Learning For Neurological, Diagnostic, And Modeling Problems, Donald Wunsch Iii

Masters Theses

“As the medical world becomes increasingly intertwined with the tech sphere, machine learning on medical datasets and mathematical models becomes an attractive application. This research looks at the predictive capabilities of neural networks and other machine learning algorithms, and assesses the validity of several feature selection strategies to reduce the negative effects of high dataset dimensionality. Our results indicate that several feature selection methods can maintain high validation and test accuracy on classification tasks, with neural networks performing best, for both single class and multi-class classification applications. This research also evaluates a proof-of-concept application of a deep-Q-learning network (DQN) to …

Implementing Artificial Intelligence And Machine Learning Into Advanced Qualification Programs, Jennifer R. Herr

Journal of Aviation/Aerospace Education & Research

Since its start, the Advanced Qualification Program (AQP) has encouraged new and innovative strategies for training airline crewmembers. The foundation of AQP is to train crew the way they fly and to find new and innovative ways to increase safety through training. By using data collected through the AQP process, training methods can be refined and improved. New technologies, such as artificial intelligence (AI) and machine learning can make data analysis and training more effective and efficient. This paper will explore these concepts and how AI and machine learning could be implemented in the AQP process to make training more …

A Compact Wavelength Meter Using A Multimode Fiber, Ogbole Collins Inalegwu

Masters Theses

“Wavelength meters are very important for precision measurements of both pulses and continuous-wave optical sources. Conventional wavelength meters employ gratings, prisms, interferometers, and other wavelength-sensitive materials in their design. Here, we report a simple and compact wavelength meter based on a section of multimode fiber and a camera. The concept is to correlate the multimodal interference pattern (i.e., speckle pattern) at the end-face of a multimode fiber with the wavelength of the input lightsource. Through a series of experiments, specklegrams from the end face of a multimode fiber as captured by a charge-coupled device (CCD) camera were recorded; the images …

Visualization For Solving Non-Image Problems And Saliency Mapping, Divya Chandrika Kalla

All Master's Theses

High-dimensional data play an important role in knowledge discovery and data science. Integration of visualization, visual analytics, machine learning (ML), and data mining (DM) are the key aspects of data science research for high-dimensional data. This thesis is to explore the efficiency of a new algorithm to convert non-images data into raster images by visualizing data using heatmap in the collocated paired coordinates (CPC). These images are called the CPC-R images and the algorithm that produces them is called the CPC-R algorithm. Powerful deep learning methods open an opportunity to solve non-image ML/DM problems by transforming non-image ML problems into …

Feature Fusion Of Raman Chemical Imaging And Digital Histopathology Using Machine Learning For Prostate Cancer Detection, Trevor Doherty, Susan Mckeever, Nebras Al-Attar, Tiarnán Murphy, Claudia Aura, Arman Rahman, Amanda O'Neill,, Stephen P. Finn, Elaine Kay, William M. Gallagher, William G. Watson, Aoife Gowen, Patrick Jackman

Articles

The diagnosis of prostate cancer is challenging due to the heterogeneity of its presentations, leading to the over diagnosis and treatment of non-clinically important disease. Accurate diagnosis can directly benefit a patient’s quality of life and prognosis. Towards addressing this issue, we present a learning model for the automatic identification of prostate cancer. While many prostate cancer studies have adopted Raman spectroscopy approaches, none have utilised the combination of Raman Chemical Imaging (RCI) and other imaging modalities. This study uses multimodal images formed from stained Digital Histopathology (DP) and unstained RCI. The approach was developed and tested on a set …

Novel Machine Learning And Wearable Sensor Based Solutions For Smart Healthcare Monitoring, Rajdeep Kumar Nath

Theses and Dissertations--Electrical and Computer Engineering

The advent of IoT has enabled the design of connected and integrated smart health monitoring systems. These health monitoring systems can be utilized for monitoring the mental and physical wellbeing of a person. Stress, anxiety, and hypertension are the major elements responsible for the plethora of physical and mental illnesses. In this context, the older population demands special attention because of the several age-related complications that exacerbate the effects of stress, anxiety, and hypertension. Monitoring stress, anxiety, and blood pressure regularly can prevent long-term damage by initiating necessary intervention or clinical treatment beforehand. This will improve the quality of life …

Ordinary Differential Equations With Machine Learning For Prediction Of Smart Composite Fracture Toughness, Relebohile George Qhobosheane, Muthu Ram Prabhu Elenchezhian, Vamsee Vadlamudi, Kenneth Reifsnider, Rassel Raihan

Institute of Predictive Performance Methodologies (IPPM-UTARI)-Archive

This work in on the development of an ordinary differential equation (ODE) model coupled with statistical methods for the prediction of fracture toughness of a magnetostrictive, piezoelectric smart self-sensing Fiber Reinforced Polymer (FRP) composite. The smart composite with sensing properties encompasses Terfenol-D alloy nanoparticles and Single Walled Carbon NanoTubes (SWCNT). To explore various configurations the of nanoparticle constituents’ effect on fracture toughness within the FRP composite, the ODE model developed within a finite element analysis (FEA) environment is considered to attain fracture observations across the solution space. The acquired FEA data is then used to feed the machine-learning (ML) algorithms …

Next-Generation Re-Entry Aerothermodynamic Modeling Of Space Debris Using Machine Learning, Nicholas Sia

Graduate Theses, Dissertations, and Problem Reports (ETD)

The number of resident space objects re-entering the atmosphere is expected to rise with increased space activity over recent years and future projections. Predicting the survival and impact location of the medium to large sized re-entering objects becomes important as they can cause on ground casualties and damage to property. Uncertainties associated with the re-entry process makes necessary a probabilistic approach, which can be computationally expensive when using high-fidelity numerical methods for estimating aerothermodynamic properties. To date, object-oriented analysis is the dominant tool used for atmospheric re-entry modeling and simulation, where aerothermodynamic coefficients are used to determine the risk a …

Learning-Based Predictive Control Approach For Real-Time Management Of Cyber-Physical Systems, Roja Eini

Theses and Dissertations

Cyber-physical systems (CPSs) are composed of heterogeneous, and networked hardware and software components tightly integrated with physical elements [72]. Large-scale CPSs are composed of complex components, subject to uncertainties [89], as though their design and development is a challenging task. Achieving reliability and real-time adaptation to changing environments are some of the challenges involved in large-scale CPSs development [51]. Addressing these challenges requires deep insights into control theory and machine learning. This research presents a learning-based control approach for CPSs management, considering their requirements, specifications, and constraints. Model-based control approaches, such as model predictive control (MPC), are proven to be …

Data Driven Analysis And Characterization Of Modern Android Malware, Qian Han

Dartmouth College Ph.D Dissertations

Google’s Android operating system was first announced to the public in 2007 and was installed on more than three billion mobile devices by 2019. With the prevalence of Android OS, Android malware has since proliferated. Android malware is malicious software designed to exploit Android operating systems running on smart devices. Some variants of Android malware have the capability of disabling the device, allowing a malicious actor to remotely control the device, track the user’s activity, lock the device, and so on. Moreover, the evolution and sophistication of modern Android malware obfuscation and detection bypassing methods have significantly improved in recent …

Weakly Supervised Learning For Multi-Image Synthesis, Muhammad Usman Rafique

Theses and Dissertations--Electrical and Computer Engineering

Machine learning-based approaches have been achieving state-of-the-art results on many computer vision tasks. While deep learning and convolutional networks have been incredibly popular, these approaches come at the expense of huge amounts of labeled data required for training. Manually annotating large amounts of data, often millions of images in a single dataset, is costly and time consuming. To deal with the problem of data annotation, the research community has been exploring approaches that require less amount of labelled data.

The central problem that we consider in this research is image synthesis without any manual labeling. Image synthesis is a classic …

Deep Models For Improving The Performance And Reliability Of Person Recognition, Sobhan Soleymani

Graduate Theses, Dissertations, and Problem Reports (ETD)

Deep models have provided high accuracy for different applications such as person recognition, image segmentation, image captioning, scene description, and action recognition. In this dissertation, we study the deep learning models and their application in improving the performance and reliability of person recognition. This dissertation focuses on five aspects of person recognition: (1) multimodal person recognition, (2) quality-aware multi-sample person recognition, (3) text-independent speaker verification, (4) adversarial iris examples, and (5) morphed face images. First, we discuss the application of multimodal networks consisting of face, iris, fingerprint, and speech modalities in person recognition. We propose multi-stream convolutional neural network architectures …

Prediction Of Tensile Behaviors Of L-Ded 316 Stainless Steel Parts Using Machine Learning, Israt Zarin Era

Graduate Theses, Dissertations, and Problem Reports (ETD)

Directed energy deposition (DED) is a rising field in the arena of metal additive manufacturing and has extensive applications in aerospace, medical and rapid prototyping. The process parameters, such as laser power, scanning speed and specimen height, play a great deal in controlling and affecting the properties of DED fabricated parts. Nevertheless, both experimental and simulation methods have shown constraints and limited ability to generate accurate and efficient computational predictions on the correlations between the process parameters and the final part quality. In this work, a data driven machine learning model XGBoost has been built and applied to predict the …

Identification Of Moving Bottlenecks In Production Systems, Funmilayo Mofoluwasola Adeyinka

Graduate Theses, Dissertations, and Problem Reports (ETD)

Manufacturing sector have been plagued by bottlenecks from time immemorial, leading to loss of productivity and profitability, various research effort has been expended towards identifying and mitigating the effects of bottlenecks on production lines. However, traditional approaches often fail in identifying moving bottlenecks. The current data boom and giant strides made in the machine learning field proffers an alternative means of using the large volume of data generated by machines in identifying bottlenecks. In this study, a hierarchical agglomerative clustering algorithm is used in identifying potential groups of bottlenecks within a serial production line.

A serial production line with five …

Evaluation Of Supervised Deep-Learning For Improved Pneumonia Diagnosis, Andrew Kalaani

College of Graduate Studies: Theses & Dissertations

Pneumonia is one of the leading causes of infections in the lung area and deaths worldwide. The mortality rate is 24.8% for patients over 70 years of age due to other health complications present along with it. In least fortunate countries, pneumonia can often times go untreated because of how cost extensive it is to diagnose, especially severe cases that cannot be seen by a plain X-ray. Other scanning methods can find the lung abnormality but are time-extensive and not cost effective. An autonomous approach however can help aid diagnosing pneumonia with a plain X-ray scan due to the structural …