Engineering Commons^™

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 …

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 …

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 …

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 …

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 …

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 …

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 …

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 …

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 …

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 …

Predictability Improvement Of Scheduled Flights Departure Time Variation Using Supervised Machine Learning, Deepudev Sahadevan, Palanisamy Ponnusamy Dr, Manjunath K. Nelli Mr, Varun P. Gopi Dr

International Journal of Aviation, Aeronautics, and Aerospace

The departure time uncertainty exacerbates the inaccuracy of arrival time estimation and demand for arrival slots, particularly for movements to capacity constrained airports. The Estimated Take-Off Time (ETOT) or Estimated Departure Time(ETD) for each individual flight is currently derived from Air Traffic Flow Management System (ATFMS), which are solely determined based on individual flight plan Estimated Off Block Time(EOBT) or subsequent delays updated by Airline. Even if normal weather conditions prevail, aircraft departure times will differ from ETOTs determined by the ATFMS due to a number of factors such as congestion, early/delayed inbound flight (linked flights), reactionary delays and air …

Underestimation Bias And Underfitting In Machine Learning, Padraig Cunningham, Sarah Jane Delany

Conference papers

. Often, what is termed algorithmic bias in machine learning will be due to historic bias in the training data. But sometimes the bias may be introduced (or at least exacerbated) by the algorithm itself. The ways in which algorithms can actually accentuate bias has not received a lot of attention with researchers focusing directly on methods to eliminate bias - no matter the source. In this paper we report on initial research to understand the factors that contribute to bias in classification algorithms. We believe this is important because underestimation bias is inextricably tied to regularization, i.e. measures to …

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 …

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 …

Circuit Topology Estimation In An Adaptive Protection Platform, Daniel Ruiz

Electrical and Computer Engineering ETDs

Modern electric power systems, power system protections and controls have experienced a significant change, thanks to the introduction of new technologies, such as microprocessors, GPS, communication, etc. These technologies brought an increased amount of measured-data and information flow on power grids. Adaptive protection systems have been introduced to increase the reliability, selectivity, and sensitivity of the traditional protection systems. An adaptive protection system highly relies on the communication system infrastructure to identify the latest status of power grid (e.g., circuit topology or generation level of distributed energy resources). However, when the communication links to some of the equipment are outaged …

Well Oiled Machine: Classifying Machinery Performance Reductions Using Work Order Data, Jacob Brionez, Amber Burnett, Cho Kim, Scott M. Whitney, Thomas N. Anderson, Sumeet Treehan

SMU Data Science Review

Work Order (WO) data from System Applications and Products in Data Processing (SAP) software contains valuable information about what WOs intend to accomplish. Using SAP work order data, with time-series machinery sensor data combined into the same dataset, provides an opportunity to optimize prediction models to increase performance. Ideally, WO data can be utilized to help predict machinery's anticipated performance and can help prioritize a WO among others based on the anticipated machinery performance. It is possible to identify anomalies in pump sensor data using the Isolation Forest algorithm as the method for anomaly detection. The relationship between the sensor …

Representational Learning Approach For Predicting Developer Expertise Using Eye Movements, Sumeet Maan

School of Computing: Dissertations, Theses, and Student Research

The thesis analyzes an existing eye-tracking dataset collected while software developers were solving bug fixing tasks in an open-source system. The analysis is performed using a representational learning approach namely, Multi-layer Perceptron (MLP). The novel aspect of the analysis is the introduction of a new feature engineering method based on the eye-tracking data. This is then used to predict developer expertise on the data. The dataset used in this thesis is inherently more complex because it is collected in a very dynamic environment i.e., the Eclipse IDE using an eye-tracking plugin, iTrace. Previous work in this area only worked on …

Proportional Voting Based Semi-Unsupervised Machine Learning Intrusion Detection System, Yang G. Kim, Ohbong Kwon, John Yoon

Publications and Research

Feature selection of NSL-KDD data set is usually done by finding co-relationships among features, irrespective of target prediction. We aim to determine the relationship between features and target goals to facilitate different target detection goals regardless of the correlated feature selection. The unbalanced data structure in NSL-KDD data can be relaxed by Proportional Representation (PR). However, adopting PR would deny the notion of winner-take-all by attracting a majority of the vote and also provide a fairly proportional share for any grouping of like-minded data. Furthermore, minorities and majorities would get a fair share of power and representation in data structure …

Emocolor : Fine-Grained Emotion Recognition From Skin Color Information, Maria Guadalupe Jimenez Velasco

Open Access Theses & Dissertations

In everyday human-to-human communication, emotions play a fundamental role. Emotions represent the affective behavior of humans that is multi-modal, subtle, and complex. Previous approaches based on conventional computer vision explicitly used shape information. Modern approaches based on deep learning implicitly exploit all information available in the image, but by their nature make it difficult to assess the contributions of each source of information. In addition, skin color as a unimodal technique to recognize emotions has been explored to recognize only three coarse-grained emotions in valence space.To the best of our knowledge, this work presents the first approach to fine-grained emotion …

A Big Data Approach For Improving Nebraska Cycling Routes, Fadi Alsaleem, Ali Al-Ramini, Mohammad Ali Takallou, Daniel P. Piatkowski

Nebraska Department of Transportation: Research Reports

More people are becoming interested in creating healthy lifestyle habits for themselves. It has been proved that cycling has several health benefits. Therefore, governments are planning towards more cycling-friendly infrastructures and environments. To understand the cycling activities in Nebraska, we analyze Strava data for the last three years, providing valuable insight into cycling activities for urban planning purposes.

We analyze commute and recreational cycling patterns varying between weekdays and weekends to identify peak hours. Moreover, we study the effect of weather on cycling activity patterns for the last three years. Also, we use the impact of the outside temperature as …

Comparison Of Classification Algorithms And Undersampling Methods On Employee Churn Prediction: A Case Study Of A Tech Company, Heather Cooper

Master's Theses

Churn prediction is a common data mining problem that many companies face across industries. More commonly, customer churn has been studied extensively within the telecommunications industry where there is low customer retention due to high market competition. Similar to customer churn, employee churn is very costly to a company and by not deploying proper risk mitigation strategies, profits cannot be maximized, and valuable employees may leave the company. The cost to replace an employee is exponentially higher than finding a replacement, so it is in any company’s best interest to prioritize employee retention.

This research combines machine learning techniques with …

A Python-Based Brain-Computer Interface Package For Neural Data Analysis, Md Hasan Anowar

Theses and Dissertations

Anowar, Md Hasan, A Python-based Brain-Computer Interface Package for Neural Data Analysis. Master of Science (MS), December, 2020, 70 pp., 4 tables, 23 figures, 74 references.

Although a growing amount of research has been dedicated to neural engineering, only a handful of software packages are available for brain signal processing. Popular brain-computer interface packages depend on commercial software products such as MATLAB. Moreover, almost every brain-computer interface software is designed for a specific neuro-biological signal; there is no single Python-based package that supports motor imagery, sleep, and stimulated brain signal analysis. The necessity to introduce a brain-computer interface package that …

Health Monitoring Using Deep Learning Of Acoustic And Speech Signals, Eric E. Hamke

Electrical and Computer Engineering ETDs

The focus of the research is to identify stress markers in a firefighter's speech. These markers include changes in breathing patterns and changes in the fundamental frequency of an individual’s voice. The breathing patterns are characterized using the number of breaths taken in a minute and the time spent inhaling. These measures are estimated using a Restricted Boltzmann Machine to process a firefighters’ SCBA regulator sounds, as open and closed. The classifications are then combined into continuous intervals. Observing the length of the intervals and the number of interval-starts represents time spent inhaling and the breathing rates (breaths per minute). …

A Bibliometric Survey Of Smart Wearable In The Health Insurance Industry, Apeksha Shah, Swati Ahirrao, Shraddha Phansalkar, Ketan Kotecha

Library Philosophy and Practice (e-journal)

Smart wearables help real-time and remote monitoring of health data for effective diagnostic and preventive health care services. Wearable devices have the ability to track and monitor healthcare vitals such as heart rate, physical activities, BMI (Body Mass Index), blood pressure, and keeps an individual notified about the health status. Artificial Intelligence-enabled wearables show an ability to transform the health insurance sector. This would not only enable self-management of individual health but also help them focus from treatments to the preventions of health hazards. With this customer-centric approach to health care, it will enable the insurance companies to track the …

Using Spatial Analysis And Machine Learning Techniques To Develop A Comprehensive Highway-Rail Grade Crossing Consolidation Model, Samira Soleimani

LSU Doctoral Dissertations

The safety of highway-railroad grade crossings (HRGC) is still an issue in the United States of America (USA). The grade crossing is where a railroad crosses a road at the same level without any over or underpass. To improve the safety of crossings, the crossings’ condition should be explored from several aspects such as engineering design (speed limit, warning signs, etc.), road condition (number of lanes, surface markings, etc.), rail design (the type of track, ballast, etc.), temporal variables (weather, visibility, time of day, lightning, etc.), social variables (population, race, etc.), and last but not least, spatial variables (the type …

Forecasting Vegetation Health In The Mena Region By Predicting Vegetation Indicators With Machine Learning Models, Sachi Perera, Wenzhao Li, Erik Linstead, Hesham El-Askary

Mathematics, Physics, and Computer Science Faculty Articles and Research

Machine learning (ML) techniques can be applied to predict and monitor drought conditions due to climate change. Predicting future vegetation health indicators (such as EVI, NDVI, and LAI) is one approach to forecast drought events for hotspots (e.g. Middle East and North Africa (MENA) regions). Recently, ML models were implemented to predict EVI values using parameters such as land types, time series, historical vegetation indices, land surface temperature, soil moisture, evapotranspiration etc. In this work, we collected the MODIS atmospherically corrected surface spectral reflectance imagery with multiple vegetation related indices for modeling and evaluation of drought conditions in the MENA …

Machine Learning Techniques For Credit Card Fraud Detection, Hossam Eldin Mohammed Abd El-Hamid Ahmed Abdou, Wael Khalifa, Mohamed Ismail Roushdy, Abdel-Badeeh M. Salem

Future Computing and Informatics Journal

The term “fraud”, it always concerned about credit card fraud in our minds. And after the significant increase in the transactions of credit card, the fraud of credit card increased extremely in last years. So the fraud detection should include surveillance of the spending attitude for the person/customer to the determination, avoidance, and detection of unwanted behavior. Because the credit card is the most payment predominant way for the online and regular purchasing, the credit card fraud raises highly. The Fraud detection is not only concerned with capturing of the fraudulent practices, but also, discover it as fast as they …