Operations Research, Systems Engineering and Industrial Engineering Commons^™

Densenet For Anatomical Brain Segmentation, Ram Deepak Gottapu, Cihan H. Dagli

Engineering Management and Systems Engineering Faculty Research & Creative Works

Automated segmentation in brain magnetic resonance image (MRI) plays an important role in the analysis of many diseases and conditions. In this paper, we present a new architecture to perform MR image brain segmentation (MRI) into a number of classes based on type of tissue. Recent work has shown that convolutional neural networks (DenseNet) can be substantially more accurate with less number of parameters if each layer in the network is connected with every other layer in a feed forward fashion. We embrace this idea and generate new architecture that can assign each pixel/voxel in an MR image of the …

Early Detection Of Disease Using Electronic Health Records And Fisher's Wishart Discriminant Analysis, Sijia Yang, Jian Bian, Zeyi Sun, Licheng Wang, Haojin Zhu, Haoyi Xiong, Yu Li

Engineering Management and Systems Engineering Faculty Research & Creative Works

Linear Discriminant Analysis (LDA) is a simple and effective technique for pattern classification, while it is also widely-used for early detection of diseases using Electronic Health Records (EHR) data. However, the performance of LDA for EHR data classification is frequently affected by two main factors: ill-posed estimation of LDA parameters (e.g., covariance matrix), and "linear inseparability" of the EHR data for classification. To handle these two issues, in this paper, we propose a novel classifier FWDA -- Fisher's Wishart Discriminant Analysis, which is developed as a faster and robust nonlinear classifier. Specifically, FWDA first surrogates the distribution of "potential" inverse …

Analysis Of Parkinson's Disease Data, Ram Deepak Gottapu, Cihan H. Dagli

Engineering Management and Systems Engineering Faculty Research & Creative Works

In this paper, we investigate the diagnostic data from patients suffering with Parkinson's disease (PD) and design classification/prediction model to simplify the diagnosis. The main aim of this research is to open possibilities to be able to apply deep learning algorithms to help better understand and diagnose the disease. To our knowledge, the capabilities of deep learning algorithms have not yet been completely utilized in the field of Parkinson's research and we believe that by having an in-depth understanding of data, we can create a platform to apply different algorithms to automate the Parkinson's Disease diagnosis to certain extent. We …

Elm-Som: A Continuous Self-Organizing Map For Visualization, Renjie Hu, Venous Roshdibenam, Hans J. Johnson, Emil Eirola, Anton Akusok, Yoan Miche, Kaj Mikael Björk, Amaury Lendasse

Engineering Management and Systems Engineering Faculty Research & Creative Works

This Paper Presents a Novel Dimensionality Reduction Technique: Elm-Som. This Technique Preserves the Intrinsic Quality of Self-Organizing Maps (Som): It is Nonlinear and Suitable for Big Data. It Also Brings Continuity to the Projection using Two Extreme Learning Machine (Elm) Models, the First One to Perform the Dimensionality Reduction and the Second One to Perform the Reconstruction. Elm-Som is Tested Successfully on Six Diverse Datasets. Regarding Reconstruction Error, Elm-Som is Comparable to Som While Bringing Continuity.

Study Of Cost Overrun And Delays Of Department Of Defense (Dod)'S Space Acquisition Program, Nazareen Sikkandar Basha, Benjamin J. Kwasa, Christina Bloebaum

Engineering Management and Systems Engineering Faculty Research & Creative Works

Defense and Aerospace Systems Acquisition projects, just like any other Large-Scale Complex Engineered Systems (LSCES) experience delays and cost overrun during the acquisition process. Cost overrun and delays in LSCES are due, in part, to high complexity, size of the project, involvement of various stakeholders, organizations, political disruptions, changes in requirements and scope. These uncertainties, due to the exogenous factors, have cost the federal government billions of dollars and delays in completion of the programs. Cost estimation of federal programs is usually based on previous generations of systems produced and almost all the time the costs are underestimated. Underestimation of …

A Web Page Classifier Library Based On Random Image Content Analysis Using Deep Learning, Leonardo Espinosa Leal, Amaury Lendasse, Kaj Mikael Björk, Anton Akusok

Engineering Management and Systems Engineering Faculty Research & Creative Works

In This Paper We Present a Methodology and the Corresponding Python Library1 for the Classification of Webpages. the Method Retrieves a Fixed Number of Images from a Given Webpage, and based on Them Classifies the Webpage into a Set of Established Classes with a Given Probability. the Library Trains a Random Forest Model Built Upon the Features Extracted from Images by a Pre-Trained Neural Network. the Implementation is Tested by Recognizing Weapon Class Webpages in a Curated List of 3859 Websites. the Results Show that the Best Method of Classifying a Webpage among the Classes of Interest is to Assign …

A Retention Model For Community College Stem Students, Jennifer Snyder, Elizabeth A. Cudney

Engineering Management and Systems Engineering Faculty Research & Creative Works

The number of students attending community colleges that take advantage of transfer pathways to universities continues to rise. Therefore, there is a need to engage in academic research on these students and their attrition in order to identify areas to improve retention. Community colleges have a very diverse population and provide entry into science, technology, engineering, and math (STEM) programs, regardless of student high school preparedness. It is essential for these students to successfully transfer to universities and finish their STEM degrees to meet the global workforce demands. This research develops a predictive model for community college students for degree …

Data Driven Decision Making Tools For Transportation Work Zone Planning, Samareh Moradpour

Doctoral Dissertations

"This research provides tools and methods for integrating stakeholder input and crash data analytics to better guide transportation engineers in effective work zone design and management. Three key contributions are presented: the importance of stakeholder input in traffic management strategies, application of data mining and pattern recognition to identify high-risk drivers in work zones, and the use of multinomial logistic regression (MLR) as a tool to understand key findings from historic crash data. Work zone signage is mandated by the Manual on Uniform Traffic Control Devices (MUTCD), but the current configurations are often criticized by the driving public and state …

Analyzing Sensor Based Human Activity Data Using Time Series Segmentation To Determine Sleep Duration, Yogesh Deepak Lad

Masters Theses

"Sleep is the most important thing to rest our brain and body. A lack of sleep has adverse effects on overall personal health and may lead to a variety of health disorders. According to Data from the Center for disease control and prevention in the United States of America, there is a formidable increase in the number of people suffering from sleep disorders like insomnia, sleep apnea, hypersomnia and many more. Sleep disorders can be avoided by assessing an individual's activity over a period of time to determine the sleep pattern and duration. The sleep pattern and duration can be …

Analyzing Factors Affecting Patient Satisfaction Using The Kano Model, Tejaswi Materla

Doctoral Dissertations

"Customer needs associated with the healthcare sector are constantly evolving with the technological advancements, rising costs, and shifts in patient demographics. Challenges associated with understanding patient needs impact the quality of care and life, safety, and satisfaction. The objective of this research was to develop a methodology to collect and analyze the needs associated with healthcare units that differ based on the type of care and services and patient perceptions over time. The proposed methodology provides insights into the voice of the customer through visualization of the relationship between the performance of quality attributes and customer satisfaction. Cronbach's alpha is …

An Investigation Of The Economic Order Quantity Model With Quantity Discounts Under An Environmental Objective, Tiffanie Marie Toles

Masters Theses

"In a sustainable supply chain, retailers are the direct link between customers and products. Retailers play an important role by relaying feedback such as customer satisfaction, inventory improvement, or product improvement to the other key players in a supply chain. Their overall goal is to reduce supply chain costs, such as the cost of ordering product, transporting product, or holding product in inventory. Other costs associated in a supply chain can include environmental and operations costs. It is important to consider these costs due to the impact environmental operations play in the role of how sustainable a supply chain can …

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 …

Transmission Line Inspection Using Suspended Robot: Cost Effective Analysis And Operational Routing Identification, Balaji Rathinam Nagarajan

Masters Theses

"High voltage transmission lines form a crucial part of the energy infrastructure of a country. Effective maintenance is required to maintain its reliability and reduce the probability of the occurrence of the outage. Conventionally, the routine inspection of the transmission line was conducted by linemen with the assistance of hot stick and helicopter, which is considered dangerous, time-consuming, and expensive.

In this thesis, we focus on the initial study of seeking the state of the art robotics technology to by largely replace human beings in transmission line inspection. The existing robotics technologies that are interested by utility companies, as well …

Evaluating Microgrid Effectiveness In Transitioning Energy Portfolios, Jacob Marshal Hale

Masters Theses

"Microgrid energy systems have emerged as a potential solution to rising greenhouse gas emissions from dependence on fossil fuels. This research provides a framework for evaluating the utility of microgrids. Three key findings are presented: use of a state-of-the-art matrix (SAM) analysis to identify gaps in key research areas that inhibit wide-spread microgrid adoption, development of a system dynamics (SD) model, and a cost benefit analysis case study to evaluate microgrid feasibility in partially meeting the energy demand of a building. Governments play a central role in developing clean energy strategies. A SAM was developed to determine if key microgrid …

A Methodology To Predict Community College Stem Student Retention And Completion, Jennifer Lynn Snyder

Doctoral Dissertations

"Numerous government reports point to the multifaceted issues facing the country's capacity to increase the number of STEM majors, while also diversifying the workforce. Community colleges are uniquely positioned as integral partners in the higher education ecosystem. These institutions serve as an access point to opportunity for many students, especially underrepresented minorities and women. Community colleges should serve as a major pathway to students pursuing STEM degrees; however student retention and completion rates are dismally low. Therefore, there is a need to predict STEM student success and provide interventions when factors indicate potential failure. This enables educational institutions to better …

Reward/Penalty Design In Demand Response For Mitigating Overgeneration Considering The Benefits From Both Manufacturers And Utility Company, Md Monirul Islam, Zeyi Sun, Cihan H. Dagli

Engineering Management and Systems Engineering Faculty Research & Creative Works

The high penetration of renewable sources in electricity grid has led to significant economic, environmental, and societal benefits. However, one major side effect, overgeneration, due to the uncontrollable property of renewable sources has also emerged, which becomes one of the major challenges that impedes the further large-scale adoption of renewable technology. Electricity demand response is an effective tool that can balance the supply and demand of the electricity throughout the grid. In this paper, we focus on the design of reward/penalty mechanism for the demand response programs aiming to mitigate the overgeneration. The benefits for both manufacturers and utility companies …

Classification Of Rest And Active Periods In Actigraphy Data Using Pca, Isaac W. Muns, Yogesh Lad, Ivan G. Guardiola, Matthew S. Thimgan

Engineering Management and Systems Engineering Faculty Research & Creative Works

In this paper we highlight a clustering algorithm for the purpose of identifying sleep and wake periods directly from actigraphy signals. The paper makes use of statistical Principal Component Analysis to identify periods of rest and activity. The aim of the proposed methodology is to develop a quick and efficient method to determine the sleep duration of an individual. In addition, a robust method that can identify sleep periods in the accelerometer data when duration, time of day varies by individual. A selected group of 10 individual's sensor data consisting of actigraphy from an accelerometer (3-axis), near body temperature, and …

A General Algorithm For Assessing Product Architecture Performance Considering Architecture Extension In Cyber Manufacturing, Md Monirul Islam, Zeyi Sun, Cihan H. Dagli

Engineering Management and Systems Engineering Faculty Research & Creative Works

In modern manufacturing, the product architecture design options are usually restricted to those that can be produced with 100% confidence using those proven technologies to satisfy the existing customer requirement. As a result, the inefficiencies of architecture design are considerable due to such limitations. This issue is of particular interests in cyber manufacturing when exploring the tradeoff between generality and feasibility in product design and manufacturing. It can be expected that the improvement and extension of the existing product architecture may be required to meet new customer requirement when new technologies become available. An effective system performance assessment algorithm is …

Learning Curve Analysis Using Intensive Longitudinal And Cluster-Correlated Data, Xiao Zhong, Zeyi Sun, Haoyi Xiong, Neil Heffernan, Md Monirul Islam

Engineering Management and Systems Engineering Faculty Research & Creative Works

Intensive longitudinal and cluster-correlated data (ILCCD) can be generated in any situation where numerical or categorical characteristics of multiple individuals or study units are observed and measured at tens, hundreds, or thousands of occasions. The spacing of measurements in time for each individual can be regular or irregular, fixed or random, and the number of characteristics measured at each occasion may be few or many. Such data can also arise in situations involving continuous-time measurements of recurrent events. Generalized linear models (GLMs) are usually considered for the analysis of correlated non-normal data, while multivariate analysis of variance (MANOVA) is another …

Analysis Of Autonomous Unmanned Aerial Systems Based On Operational Scenarios Using Value Modelling, Akash Vidyadharan, Robert Philpott Iii, Benjamin J. Kwasa, Christina L. Bloebaum

Engineering Management and Systems Engineering Faculty Research & Creative Works

In recent years, the use of UAS (Unmanned Aerial Systems) has moved beyond the realm of military operations and has made its way into the hands of consumers and commercial industries. Although the applications of UAS in commercial industries are virtually endless, there are many issues regarding their operations that need to be considered before these valuable pieces of equipment are allowed for widespread civil use. Currently, UAS operations in the public domain are guided and controlled by the FAA Part 107 rules after overwhelming public pressure caused by the earlier 333 exemption. In order to approach such larger issues, …

Energy Consumption Modeling Of Stereolithography-Based Additive Manufacturing Toward Environmental Sustainability, Yiran Yang, Lin Li, Yayue Pan, Zeyi Sun

Engineering Management and Systems Engineering Faculty Research & Creative Works

Additive manufacturing (AM), also referred as three-dimensional printing or rapid prototyping, has been implemented in various areas as one of the most promising new manufacturing technologies in the past three decades. In addition to the growing public interest in developing AM into a potential mainstream manufacturing approach, increasing concerns on environmental sustainability, especially on energy consumption, have been presented. To date, research efforts have been dedicated to quantitatively measuring and analyzing the energy consumption of AM processes. Such efforts only covered partial types of AM processes and explored inadequate factors that might influence the energy consumption. In addition, energy consumption …

Chaotic Behavior In High-Gain Interleaved Dc-Dc Converters, Ahmad Alzahrani, Pourya Shamsi, Mehdi Ferdowsi, Cihan H. Dagli

Electrical and Computer Engineering Faculty Research & Creative Works

In this paper, chaotic behavior in high gain dc-dc converters with current mode control is explored. The dc-dc converters exhibit some chaotic behavior because they contain switches. Moreover, in power electronics (circuits with more passive elements), the dynamics become rich in nonlinearity and become difficult to capture with linear analytical models. Therefore, studying modeling approaches and analysis methods is required. Most of the high-gain dc-dc boost converters cannot be controlled with only voltage mode control due to the presence of right half plane zero that narrows down the stability region. Therefore, the need of current mode control is necessary to …

Solar Irradiance Forecasting Using Deep Neural Networks, Ahmad Alzahrani, Pourya Shamsi, Cihan H. Dagli, Mehdi Ferdowsi

Electrical and Computer Engineering Faculty Research & Creative Works

Predicting solar irradiance has been an important topic in renewable energy generation. Prediction improves the planning and operation of photovoltaic systems and yields many economic advantages for electric utilities. The irradiance can be predicted using statistical methods such as artificial neural networks (ANN), support vector machines (SVM), or autoregressive moving average (ARMA). However, they either lack accuracy because they cannot capture long-term dependency or cannot be used with big data because of the scalability. This paper presents a method to predict the solar irradiance using deep neural networks. Deep recurrent neural networks (DRNNs) add complexity to the model without specifying …

Modeling And Simulation Of Microgrid, Ahmad Alzahrani, Mehdi Ferdowsi, Pourya Shamsi, Cihan H. Dagli

Electrical and Computer Engineering Faculty Research & Creative Works

Complex computer systems and electric power grids share many properties of how they behave and how they are structured. A microgrid is a smaller electric grid that contains several homes, energy storage units, and distributed generators. The main idea behind microgrids is the ability to work even if the main grid is not supplying power. That is, the energy storage unit and distributed generation will supply power in that case, and if there is excess in power production from renewable energy sources, it will go to the energy storage unit. Therefore, the electric grid becomes decentralized in terms of control …

Design The Capacity Of Onsite Generation System With Renewable Sources For Manufacturing Plant, Xiao Zhong, Md Monirul Islam, Haoyi Xiong, Zeyi Sun

Computer Science Faculty Research & Creative Works

The utilization of onsite generation system with renewable sources in manufacturing plants plays a critical role in improving the resilience, enhancing the sustainability, and bettering the cost effectiveness for manufacturers. When designing the capacity of onsite generation system, the manufacturing energy load needs to be met and the cost for building and operating such onsite system with renewable sources are two critical factors need to be carefully quantified. Due to the randomness of machine failures and the variation of local weather, it is challenging to determine the energy load and onsite generation supply at different time periods. In this paper, …

Underwater Image Segmentation With Co-Saliency Detection And Local Statistical Active Contour Model, Yue Zhu, Baochen Hao, Baohua Jiang, Rui Nian, Bo He, Xinmin Ren, Amaury Lendasse

Engineering Management and Systems Engineering Faculty Research & Creative Works

Image Segmentation of Underwater Environment with Inhomogeneous Intensity Turns Out to Be One of the Most Challenging Topics These Years. in This Paper, We Try to Combine Co-Saliency Detection with Local Statistical Active Contour Model Together for Underwater Image Segmentation. the Cluster-Based Algorithm is First Taken for Co-Saliency Detection, Which Makes Salient Region in the Underwater Images Be Highlighted. the Local Statistical Active Contour Model, a Novel Region-Based Level Set Method, is Then Made Full Use of two Segment Underwater Images. It is Shown in Our Simulation Experiment that Our Proposed Scheme Could Achieve Great Segmentation Performance in Both Efficiency …

Underwater Object Tracking Strategy Via Multi-Scale Retinex And Partial Least Squares Analysis, Baochen Hao, Yue Zhu, Ruijie Chang, Rui Nian, Bo He, Lujie Cao, Amaury Lendasse

Engineering Management and Systems Engineering Faculty Research & Creative Works

Underwater Object Tracking is One of the Most Essential and Fundamental Tasks in Ocean Investigations Recent Years. in This Paper, We Try to Capture Multi-Scale Retinex (MSR) Model as Well as the Partial Least Square (Pls) Analysis for Underwater Object Tracking. We First Make Use of Multi-Scale Retinex Model to Evolve and Enhance the Partial Color Constancy from the Underwater Video Sequences, Which Could Provide a Versatile Automatic Strategy to Simultaneous Sharpening, Dynamic Range Compression and Color Rendition. the Partial Least Square Analysis is Further Taken to Capture the Trajectories of Underwater Objects by Learning a Set of Underwater Appearance …

Underwater Image Super-Resolution Reconstruction With Local Self-Similarity Analysis And Wavelet Decomposition, Xiaorun Wang, Rui Nian, Bo He, Bing Zheng, Amaury Lendasse

Engineering Management and Systems Engineering Faculty Research & Creative Works

Underwater Target Detecting is an Important Technique for the Development of the Ocean Engineering and Exploration Also a Significant Task of the Ocean Detecting. It Plays a Substantial Role Not Only for the Civil Economy but Also for the National Security. the Formation of the Super-Resolution Underwater Image is Significant Topic in Ocean Detecting Field. in Order to Enhance the Visual Quality of Images Obtained by Underwater Imaging Systems, Super Resolution (Sr) Reconstruction is Introduced, Including Single-Frame and Multi-Frame Sr Algorithms. Real-World Images Often Contain Singularities Such as Edges and High-Frequency Textured Regions. as a Result, These Methods Suffer from …

A Depth Estimation Model From A Single Underwater Image With Non-Uniform Illumination Correction, Shichang Zhang, Xiaofei Gong, Rui Nian, Bo He, Yaomin Wang, Amaury Lendasse

Engineering Management and Systems Engineering Faculty Research & Creative Works

Underwater Visual Understanding Tends to Be One of the Most Important Challenges in Ocean Investigations Recent Years. in This Paper, We Make an Attempt to Develop a Depth Estimation Approach from One Single Underwater Image with Non-Uniform Illumination Correction. First, We Try to Remove the Relatively Strong Reflection Layer from the Scene Layer in Those Underwater Images with Non-Uniform Illumination and Rely on the Saturation Detection to Characterize the Local Regions of the Artificial Illumination in Underwater Images for Compensation in Depth Estimation. Then We Try to Implement Underwater Dark Channel Prior and Basically Consider the Blue and Green Color …

Engineering Cyber Physical Systems: Preface, Cihan H. Dagli

Engineering Management and Systems Engineering Faculty Research & Creative Works

Multi-faceted systems of the future will entail complex logic with many levels of reasoning in intricate arrangement. The organization of these systems involves a web of connections and demonstrates self-driven adaptability. They are designed for autonomy and may exhibit emergent behavior that can be visualized.

Complex Adaptive Systems have dynamically changing meta-architectures. Finding an optimal architecture for these systems is a multi-criteria decision making problem often involving many objectives in the order of 20 or more. This creates "Pareto Breakdown" which prevents ordinary multi-objective optimization approaches from effectively searching for an optimal solution; saturating the decision maker with large sets …