Engineering Commons^™

Deep Neural Network Architectures For Modulation Classification Using Principal Component Analysis, Sharan Ramjee, Shengtai Ju, Diyu Yang, Aly El Gamal

The Summer Undergraduate Research Fellowship (SURF) Symposium

In this work, we investigate the application of Principal Component Analysis to the task of wireless signal modulation recognition using deep neural network architectures. Sampling signals at the Nyquist rate, which is often very high, requires a large amount of energy and space to collect and store the samples. Moreover, the time taken to train neural networks for the task of modulation classification is large due to the large number of samples. These problems can be drastically reduced using Principal Component Analysis, which is a technique that allows us to reduce the dimensionality or number of features of the samples …

Hierarchical Bayesian Data Fusion Using Autoencoders, Yevgeniy Vladimirovich Reznichenko

Master's Theses (2009 -)

In this thesis, a novel method for tracker fusion is proposed and evaluated for vision-based tracking. This work combines three distinct popular techniques into a recursive Bayesian estimation algorithm. First, semi supervised learning approaches are used to partition data and to train a deep neural network that is capable of capturing normal visual tracking operation and is able to detect anomalous data. We compare various methods by examining their respective receiver operating conditions (ROC) curves, which represent the trade off between specificity and sensitivity for various detection threshold levels. Next, we incorporate the trained neural networks into an existing data …

Tactile Sensing And Position Estimation Methods For Increased Proprioception Of Soft-Robotic Platforms, Nathan Mcclain Day

Theses and Dissertations

Soft robots have the potential to transform the way robots interact with their environment. This is due to their low inertia and inherent ability to more safely interact with the world without damaging themselves or the people around them. However, existing sensing for soft robots has at least partially limited their ability to control interactions with their environment. Tactile sensors could enable soft robots to sense interaction, but most tactile sensors are made from rigid substrates and are not well suited to applications for soft robots that can deform. In addition, the benefit of being able to cheaply manufacture soft …

Computational Analysis Of Developmental Disorders In Children, Siri Chandana Sambatur

Theses - ALL

Early developmental disorders are common in children between the ages of 3 through 17. These developmental disorders begin at early ages and affect the day-to-day activities of children. These disorders also impact the growth and lifestyle of children. Most of the time these developmental disorders co-exist in children. The main focus of our research lies in Autism Spectrum Disorder, Attention-Deficit/Hyperactivity Disorder, Deletion syndrome (22q) and their co-occurrences.

Most child psychologists and pediatricians diagnose these disorders in children through parent-based surveys. Our research uses three different parent-based reports: (1) Autism Diagnostic Interview (ADI), (2) Behavioral Assessment Schedule for Children (BASC), and …

Machine Learning Models For Context-Aware Recommender Systems, Yogesh Jhamb

Engineering Ph.D. Theses

The mass adoption of the internet has resulted in the exponential growth of products and services on the world wide web. An individual consumer, faced with this data deluge, is expected to make reasonable choices saving time and money. Organizations are facing increased competition, and they are looking for innovative ways to increase revenue and customer loyalty. A business wants to target the right product or service to an individual consumer, and this drives personalized recommendation. Recommender systems, designed to provide personalized recommendations, initially focused only on the user-item interaction. However, these systems evolved to provide a context-aware recommendations. Context-aware …

More Accurate Process Understanding From Process Characterization Studies Using Monte Carlo Simulation, Regularized Regression, And Classification Models, Cary Opel, Cerintha J. Hui, Patrick Y. Yang, Daniel J. Tien, Gayle E. Derfus, Rajesh Krishnan

Cell Culture Engineering XVI

Establishment of an appropriate control strategy with defined operating ranges (OR) predicted to meet a target product profile is a critical component of commercializing new biologics under the Quality by Design (QbD) approach. Process characterization (PC) studies are performed to expand process understanding by achieving two main goals: 1) determining which process parameters have significant effects on quality attributes and 2) establishing models describing the relationships between these critical process parameters (CPP) and critical quality attributes (CQA). Risk assessment and design of experiments (DOE) techniques are effectively deployed in the industry to identify parameters to study and build process understanding. …

Training Machine Learning Agents In A 3d Game Engine, Diego Calderon

Computer Science and Computer Engineering Undergraduate Honors Theses

Artificial intelligence (AI) and video games benefit from each other. Games provide a challenging domain for testing learning algorithms, and AI provides a framework to designing and implementing intelligent behavior, which reinforces meaningful play. Medium and small studios, and independent game developers, have limited resources to design, implement, and maintain agents with reactive behavior. In this research, we trained agents using machine learning (ML), aiming to find an alternative to expensive traditional algorithms for intelligent behavior used in video games. We use Unity as a game engine to implement the environments and TensorFlow for the neural network training.

Machine Learning For Omics Data Analysis., Ameni Trabelsi

Electronic Theses and Dissertations

In proteomics and metabolomics, to quantify the changes of abundance levels of biomolecules in a biological system, multiple sample analysis steps are involved. The steps include mass spectrum deconvolution and peak list alignment. Each analysis step introduces a certain degree of technical variation in the abundance levels (i.e. peak areas) of those molecules. Some analysis steps introduce technical variations that affect the peak areas of all molecules equally while others affect the peak areas of a subset of molecules with varying degrees. To correct these technical variations, some existing normalization methods simply scale the peak areas of all molecules detected …

Baseline Data From Servo Motors In A Robotic Arm For Autonomous Machine Fault Diagnosis, Jacob Brown

Mechanical Engineering Undergraduate Honors Theses

Fault diagnosis can prolong the life of machines if potential sources of failure are discovered and corrected before they occur. Supervised machine learning, or the use of training data to enable machines to discover these faults on their own, makes failure prevention much easier. The focus of this thesis is to investigate the feasibility of creating datasets of various faults at both the component and system level for a servomotor and a compatible robotic arm, such that this data can be used in machine learning algorithms for fault diagnosis. The faults induced at the component level in different servomotors include: …

Evolution Of Mg Az31 Twin Activation With Strain: A Machine Learning Study, Andrew D. Orme

Undergraduate Honors Theses

Machine learning is being adopted in various areas of materials science to both create predictive models and to uncover correlations which reveal underlying physics. However, these two aims are often at odds with each other since the resultant predictive models generally become so complex that they can essentially be described as a black box, making them difficult to understand. In this study, complex relationships between microstructure and twin formation in AZ31 magnesium are investigated as a function of increasing strain. Supervised machine learning is employed, in the form of J-48 decision trees. In one approach, strain is incorporated as an …

An Unsupervised Cluster: Learning Water Customer Behavior Using Variation Of Information On A Reconstructed Phase Space, Michele Rae Bizub Malinowski

Dissertations (1934 -)

The unsupervised clustering algorithm described in this dissertation addresses the need to divide a population of water utility customers into groups based on their similarities and differences, using only the measured flow data collected by water meters. After clustering, the groups represent customers with similar consumption behavior patterns and provide insight into ‘normal’ and ‘unusual’ customer behavior patterns. This research focuses upon individually metered water utility customers and includes both residential and commercial customer accounts serviced by utilities within North America. The contributions of this dissertation not only represent a novel academic work, but also solve a practical problem for …

Enhanced Grain Partitioning Of X-Ray Microtomography Segmented Images, Nicholas C. Skrivanos Ii

LSU Master's Theses

In the field of petroleum engineering, rock samples are often taken from wells during the drilling process. Grain partitioning of digital three-dimensional microtomography segmented images obtained from these samples provides valuable in-situ properties and statistics that allow for accurate particle and structure characterization. This information can be used directly in detailed production and reservoir analysis, and can also be used to generate realistic packing models for advanced simulation. Additionally, the partitioned image can be used as a building block for realistic hydraulic fracture modeling. This technology has applications in other fields as well, such as core analysis in soil sciences …

Predicting The Vote Using Legislative Speech, Aditya Budhwar

Master's Theses

As most dedicated observers of voting bodies like the U.S. Supreme Court can attest, it is possible to guess vote outcomes based on statements made during deliberations or questioning by the voting members. In most forms of representative democracy, citizens can actively petition or lobby their representatives, and that often means understanding their intentions to vote for or against an issue of interest. In some U.S. state legislators, professional lobby groups and dedicated press members are highly informed and engaged, but the process is basically closed to ordinary citizens because they do not have enough background and familiarity with the …

Integrated Strategies For Sustainable Wastewater-Based Algal Biofuel Production And Environmental Mitigation In The Us, Javad Roostaei

Wayne State University Dissertations

Integration of algae cultivation with wastewater treatment has received increasing interest as a cost-effective strategy for biofuel production. However, there has been no full assessment of algal biofuel production with wastewater on macro-scale by taking into account wastewater resources, land availability, CO2 emission resources, and geographic variation. This research addressed and evaluated the use of wastewater for algae cultivation, in terms of modeling and laboratory experiments. The first goal of this research was to develop a spatially explicit lifecycle model, by integrating life cycle assessment (LCA), and Geographic Information Systems (GIS) analysis, for the evaluation of the environmental and economic …

Machine Learning Based Neural Network Solving Methods For The Fdtd Method, He Ming Yao, Li (Lijun) Jun Jiang

Electrical and Computer Engineering Faculty Research & Creative Works

In this paper, two novel computational processes are proposed to solve Finite-Difference Time-Domain (FDTD) based on machine learning deep neural networks. The field and boundary conditions are employed to establish recurrent neural network FDTD (RNN-FDTD) model and convolution neural network FDTD (CNN-FDTD) model respectively. Numerical examples from scalar wave equations are provided to benchmark the performance of the proposed methods. The results demonstrate that the newly proposed methods could solve FDTD steps with satisfactory accuracy. According to our knowledge, these are unreported new approaches for machine learning based FDTD solving methods.

Data-Driven Predictive Framework For Modeling Complex Multi-Physics Engineering Applications, Arturo Schiaffino Bustamante

Open Access Theses & Dissertations

Computational models are often encountered in multiple engineering application, such as structural design, material science, heat transfer and fluid dynamics. These simulations offer the engineers the capability of understanding complex physical situations before putting them to practice, either through experimentation or prototyping. The current advances in computational sciences, hardware architecture, software development and big data technology, have allowed the construction of sturdy predicting frameworks for analyzing a wide array of natural phenomena across different disciplines, either through the implementation of statistical methods, such as big data, and uncertainty quantification, or through high performance computing of a numerical model. The objective …

Application Of Machine Learning On Fracture Interference, Dennis Wayne Chamberlain Jr.

Graduate Theses, Dissertations, and Problem Reports (ETD)

A method has been developed that locates and determines well-to-well hydraulic fracture interference (frac-hit) in shale plays using hard data. This method uses Artificial Neural Networks (ANN) with designated parameters and target outputs in conjunction with graphs of gas flowrate, tubing pressure, and cumulative gas prediction. The method was created to address the significant increase in frac-hit occurrences due to the infill wells being completed in shale plays. The production data of the well is first cleaned to eliminate outliers in the initial timeframe of the well and periods of no production so that the ANN model can be accurately …

Can Machine Learning Beat Physics At Modeling Car Crashes?, Gavin Byrne

Dissertations

This study aimed to look at a traditional method used for measuring the severity and principle direction of force of a car crash and see if it could be improved on using machine learning models. The data used was publicly available from the NHTSA database and included descriptions of the vehicle, test and sensors as well as the accelerometer data over the period of the crashes. The models built were SVM classifiers and multinomial regression models. Although the SVM and Regression models were built successfully and gave higher levels of accuracy than the momentum models in terms of the severity, …

Computational Intelligence Methods For Predicting Fetal Outcomes From Heart Rate Patterns, Vinayaka Nagendra Harikishan Gude Divya Sampath

Masters Theses

"In this thesis, methods for evaluating the fetal state are compared to make predictions based on Cardiotocography (CTG) data. The first part of this research is the development of an algorithm to extract features from the CTG data. A feature extraction algorithm is presented that is capable of extracting most of the features in the SISPORTO software package as well as late and variable decelerations. The resulting features are used for classification based on both U.S. National Institutes of Health (NIH) categories and umbilical cord pH data. The first experiment uses the features to classify the results into three different …

Implementing Large Eddy Simulation To Numerical Simulation Of Optical Wave Propagation, Diego Alberto Lozano Jimenez

Open Access Theses & Dissertations

In this study, we want to simulate long-range laser propagation in atmospheric turbulence. The numerical simulations are carried out to study the impact of strong atmospheric turbulence in spatial, temporal, and related spectral domains. The first section of this study will be concerned with modeling this numerical simulation in Kolmogorov and non-Kolmogorov spectrum. To validate our numerical simulation, we will compare the statistical parameter to theoretical approximation in both Kolmogorov and non-Kolmogorov spectrums. Once the code is validated, we want to integrate Large Eddy Simulation (LES) turbulence modeling. LES simulations allowa us to study strong fluid turbulence and can predict …

Learning Convolutional Neural Network For Face Verification, Elaheh Rashedi

Wayne State University Dissertations

Convolutional neural networks (ConvNet) have improved the state of the art in many applications. Face recognition tasks, for example, have seen a significantly improved performance due to ConvNets. However, less attention has been given to video-based face recognition. Here, we make three contributions along these lines.

First, we proposed a ConvNet-based system for long-term face tracking from videos. Through taking advantage of pre-trained deep learning models on big data, we developed a novel system for accurate video face tracking in the unconstrained environments depicting various people and objects moving in and out of the frame. In the proposed system, we …

Digital Forensic Tools & Cloud-Based Machine Learning For Analyzing Crime Data, Majeed Kayode Raji

College of Graduate Studies: Theses & Dissertations

Digital forensics is a branch of forensic science in which we can recreate past events using forensic tools for legal measure. Also, the increase in the availability of mobile devices has led to their use in criminal activities. Moreover, the rate at which data is being generated has been on the increase which has led to big data problems. With cloud computing, data can now be stored, processed and analyzed as they are generated. This thesis documents consists of three studies related to data analysis. The first study involves analyzing data from an android smartphone while making a comparison between …

Use Of Adaptive Mobile Applications To Improve Mindfulness, Wiehan Boshoff

Browse all Theses and Dissertations

Mindfulness is the state of retaining awareness of what is happening at the current point in time. It has been used in multiple forms to reduce stress, anxiety, and even depression. Promoting Mindfulness can be done in various ways, but current research shows a trend towards preferential usage of breathing exercises over other methods to reach a mindful state. Studies have showcased that breathing can be used as a tool to promote brain control, specifically in the auditory cortex region. Research pertaining to disorders such as Tinnitus, the phantom awareness of sound, could potentially benefit from using these brain control …

A Framework To Understand Emoji Meaning: Similarity And Sense Disambiguation Of Emoji Using Emojinet, Sanjaya Wijeratne

Browse all Theses and Dissertations

Pictographs, commonly referred to as `emoji’, have become a popular way to enhance electronic communications. They are an important component of the language used in social media. With their introduction in the late 1990’s, emoji have been widely used to enhance the sentiment, emotion, and sarcasm expressed in social media messages. They are equally popular across many social media sites including Facebook, Instagram, and Twitter. In 2015, Instagram reported that nearly half of the photo comments posted on Instagram contain emoji, and in the same year, Twitter reported that the `face with tears of joy’ emoji has been tweeted 6.6 …

Offline And Online Density Estimation For Large High-Dimensional Data, Aref Majdara

Dissertations, Master's Theses and Master's Reports

Density estimation has wide applications in machine learning and data analysis techniques including clustering, classification, multimodality analysis, bump hunting and anomaly detection. In high-dimensional space, sparsity of data in local neighborhood makes many of parametric and nonparametric density estimation methods mostly inefficient.

This work presents development of computationally efficient algorithms for high-dimensional density estimation, based on Bayesian sequential partitioning (BSP). Copula transform is used to separate the estimation of marginal and joint densities, with the purpose of reducing the computational complexity and estimation error. Using this separation, a parallel implementation of the density estimation algorithm on a 4-core CPU is …

Fault Classification And Location Identification On Electrical Transmission Network Based On Machine Learning Methods, Vidya Venkatesh

Theses and Dissertations

Power transmission network is the most important link in the country’s energy system as they carry large amounts of power at high voltages from generators to substations. Modern power system is a complex network and requires high-speed, precise, and reliable protective system. Faults in power system are unavoidable and overhead transmission line faults are generally higher compare to other major components. They not only affect the reliability of the system but also cause widespread impact on the end users. Additionally, the complexity of protecting transmission line configurations increases with as the configurations get more complex. Therefore, prediction of faults (type …

Automated Cleaning Of Identity Label Noise In A Large-Scale Face Dataset Using A Face Image Quality Control, Mohamad Al Jazaery

Graduate Theses, Dissertations, and Problem Reports (ETD)

For face recognition, some very large-scale datasets are publicly available in recent years which are usually collected from the internet using search engines, and thus have many faces with wrong identity labels (outliers). Additionally, the face images in these datasets have different qualities. Since the low quality face images are hard to identify, current automated identity label cleaning methods are not able to detect the identity label error in the low quality faces. Therefore, we propose a novel approach for cleaning the identity label error more low quality faces. Our face identity labels cleaned by our method can train better …

Video Quality Prediction Under Time-Varying Loads, Obinna Izima, Ruairí De Fréin, Mark Davis

Conference papers

We are on the cusp of an era where we can responsively and adaptively predict future network performance from network device statistics in the Cloud. To make this happen, regression-based models have been applied to learn mappings between the kernel metrics of a machine in a service cluster and service quality metrics on a client machine. The path ahead requires the ability to adaptively parametrize learning algorithms for arbitrary problems and to increase computation speed. We consider methods to adaptively parametrize regularization penalties, coupled with methods for compensating for the effects of the time-varying loads present in the system, namely …

Data Fusion Techniques For Biomedical Informatics And Clinical Decision Support, Peng Guo

Doctoral Dissertations

"Data fusion can be used to combine multiple data sources or modalities to facilitate enhanced visualization, analysis, detection, estimation, or classification. Data fusion can be applied at the raw-data, feature-based, and decision-based levels. Data fusion applications of different sorts have been built up in areas such as statistics, computer vision and other machine learning aspects. It has been employed in a variety of realistic scenarios such as medical diagnosis, clinical decision support, and structural health monitoring. This dissertation includes investigation and development of methods to perform data fusion for cervical cancer intraepithelial neoplasia (CIN) and a clinical decision support system. …

Machine Learning Techniques Implementation In Power Optimization, Data Processing, And Bio-Medical Applications, Khalid Khairullah Mezied Al-Jabery

Doctoral Dissertations

"The rapid progress and development in machine-learning algorithms becomes a key factor in determining the future of humanity. These algorithms and techniques were utilized to solve a wide spectrum of problems extended from data mining and knowledge discovery to unsupervised learning and optimization. This dissertation consists of two study areas. The first area investigates the use of reinforcement learning and adaptive critic design algorithms in the field of power grid control. The second area in this dissertation, consisting of three papers, focuses on developing and applying clustering algorithms on biomedical data. The first paper presents a novel modelling approach for …