Open Access. Powered by Scholars. Published by Universities.®
Operations Research, Systems Engineering and Industrial Engineering
- Keyword
-
- Engineering education (18)
- Adaptive systems (16)
- Students (16)
- Curricula (13)
- Learning (Artificial Intelligence) (12)
-
- Neurocontrollers (12)
- Neural Nets (11)
- Neural Networks (11)
- Lyapunov Methods (10)
- Nonlinear Control Systems (10)
- Adaptive Control (9)
- Teaching (9)
- Closed Loop Systems (8)
- Control System Synthesis (8)
- Neural Network (8)
- Complex networks (7)
- Learning systems (7)
- Systems engineering (7)
- Adaptive Systems (6)
- Discrete-time systems (6)
- Forecasting (6)
- Neural networks (6)
- Scheduling (6)
- System of systems (6)
- Architecture (5)
- Artificial Intelligence (5)
- Artificial intelligence (5)
- Backpropagation (5)
- Deep learning (5)
- Discrete Time Systems (5)
- Publication Year
- Publication
-
- Engineering Management and Systems Engineering Faculty Research & Creative Works (228)
- Electrical and Computer Engineering Faculty Research & Creative Works (65)
- UMR-MEC Conference on Energy / UMR-DNR Conference on Energy (24)
- Computer Science Faculty Research & Creative Works (6)
- Civil, Architectural and Environmental Engineering Faculty Research & Creative Works (4)
-
- Business and Information Technology Faculty Research & Creative Works (3)
- Mechanical and Aerospace Engineering Faculty Research & Creative Works (3)
- Geosciences and Geological and Petroleum Engineering Faculty Research & Creative Works (1)
- Mathematics and Statistics Faculty Research & Creative Works (1)
- Psychological Science Faculty Research & Creative Works (1)
Articles 31 - 60 of 336
Full-Text Articles in Engineering
A System-Of-Systems Model To Simulate The Complex Emergent Behavior Of Vehicle Traffic On An Urban Transportation Infrastructure Network, Rayan Assaad, Cihan H. Dagli, Islam H. El-Adaway
A System-Of-Systems Model To Simulate The Complex Emergent Behavior Of Vehicle Traffic On An Urban Transportation Infrastructure Network, Rayan Assaad, Cihan H. Dagli, Islam H. El-Adaway
Engineering Management and Systems Engineering Faculty Research & Creative Works
Transportation agencies face escalating challenges in forecasting the traffic demand. Traditional prediction methods focused on individual transportation sectors and failed to study the inter-dependencies between the different transportation systems. Hence, there is a need for more advanced and holistic modeling techniques. To this end, this paper models and analyses an urban transportation system-of-systems incorporating seven various systems: population and GDP, CO2 emission, gasoline price and total vehicle trips, traffic demand, public and private transportation, transportation investment, and traffic congestion. Accordingly, this research simulates transportation networks as a collection of task-oriented systems that combine their resources to form a complex …
Agent Based Modeling For Flood Inundation Mapping And Rerouting, Vinayaka Gude, Steven Corns, Cihan H. Dagli, Suzanna Long
Agent Based Modeling For Flood Inundation Mapping And Rerouting, Vinayaka Gude, Steven Corns, Cihan H. Dagli, Suzanna Long
Engineering Management and Systems Engineering Faculty Research & Creative Works
Natural disasters like earthquakes and floods can have a serious impact on road networks, which are critical to supply chain infrastructure and to provide connectivity. These extreme events can result in isolating people in the affected area from hospitals and emergency response. This paper presents an agent-based model for understanding flood propagation and developing inundation mapping. The results from the mapping are used to identify the roads prone to floods based on elevation data and flood simulation. A simulation environment was set up in SUMO, and the costs associated with the traffic disruption are evaluated. This paper discusses the integration …
An Agent-Based Approach To Artificial Stock Market Modeling, Samuel Vanfossan, Cihan H. Dagli, Benjamin J. Kwasa
An Agent-Based Approach To Artificial Stock Market Modeling, Samuel Vanfossan, Cihan H. Dagli, Benjamin J. Kwasa
Engineering Management and Systems Engineering Faculty Research & Creative Works
Consumer stock markets have long been a target of modeling efforts for the economic gains anticipatorily enabled by well-performing models. Aimed at identifying strategies capable of achieving desired returns, many modeling approaches have attempted to capture the innumerable and intricate complexities present within these adaptive socio-technical systems. Decreasingly constrained by available computation power, contemporary models have grown in sophistication to include several of the features present in de facto market systems. However, these models require extensive effort to dictate the variety of states, behaviors, and adaptations that entities of the system may exhibit. Mandating the development of complex formulas and …
Efficient Architecture Search For Deep Neural Networks, Ram Deepak Gottapu, Cihan H. Dagli
Efficient Architecture Search For Deep Neural Networks, Ram Deepak Gottapu, Cihan H. Dagli
Engineering Management and Systems Engineering Faculty Research & Creative Works
This paper addresses the scalability challenge of automatic deep neural architecture search by implementing a parameter sharing approach with regularized genetic algorithm (RGE). The key idea is to use a regularized genetic algorithm (RGE) on a pre-determined template and discover a high-performance architecture by searching for the optimal chromosome. During evolution, each model corresponding to a discovered chromosome is trained for a fixed number of epochs to minimize a canonical cross-entropy loss on a given training dataset. Meanwhile, the performance of the trained model on validation dataset is used as a fitness value to perform the evolutions. Because of parameter …
An Agent-Based Model To Study Competitive Construction Bidding And The Winner's Curse, Amr Elsayegh, Cihan H. Dagli, Islam H. El-Adaway
An Agent-Based Model To Study Competitive Construction Bidding And The Winner's Curse, Amr Elsayegh, Cihan H. Dagli, Islam H. El-Adaway
Engineering Management and Systems Engineering Faculty Research & Creative Works
Reverse auction theory is the basis for competitive construction bidding process. The lowest bid method is utilized for selecting contractors in public projects. The winning contractor having the lowest bid value could be cursed when the submitted bid value results in negative profits. This is caused by many factors such as the contractor's estimation accuracy and markup. This is addressed in this paper by providing a model simulating the construction competitive bidding and the occurrence of the winner's curse. To this end, the authors show the extent to which the winner's curse affects the status of contracting companies. The objectives …
Preface To The Special Issue: "Complex Adaptive Systems," Malvern, Pennsylvania, November 13-15, 2019, Nil Kilicay-Ergin, Cihan H. Dagli
Preface To The Special Issue: "Complex Adaptive Systems," Malvern, Pennsylvania, November 13-15, 2019, Nil Kilicay-Ergin, Cihan H. Dagli
Engineering Management and Systems Engineering Faculty Research & Creative Works
No abstract provided.
A System Dynamics Model For Construction Safety Behavior, Mohamad Abdul Nabi, Islam H. El-Adaway, Cihan H. Dagli
A System Dynamics Model For Construction Safety Behavior, Mohamad Abdul Nabi, Islam H. El-Adaway, Cihan H. Dagli
Civil, Architectural and Environmental Engineering Faculty Research & Creative Works
Construction Industry has always been reputed by its high incident rates and poor safety performance. Construction accidents are, in most cases, resulted from the unsafe behaviors of construction workers on site. The study of workers' behavior is crucial in order to understand the causation of unsafe behaviors. Therefore, the objective of this paper is to simulate construction safety behavior in order to predict the number of safety incidents and better understand their causation factors. The simulation model illustrates how construction system influences construction labors on site in terms of unsafe behavior. The standard leading indicators of safety performance are first …
Exploring The Relationship Between Sustainable Projects And Institutional Isomorphisms: A Project Typology, Rakan Alyamani, Suzanna Long, Mohammad Nurunnabi
Exploring The Relationship Between Sustainable Projects And Institutional Isomorphisms: A Project Typology, Rakan Alyamani, Suzanna Long, Mohammad Nurunnabi
Engineering Management and Systems Engineering Faculty Research & Creative Works
With the increase in awareness about the wide range of issues and adverse effects associated with the use of conventional energy sources came an increase in project management research related to sustainability and sustainable development. Part of that research is devoted to the development of sustainable project typologies that classify projects based on a variety of external factors that can significantly impact these projects. This research focuses on developing a sustainable project typology that classifies sustainable projects based on the external institutional influences. The typology explores the influence of the coercive, normative, and mimetic institutional isomorphisms on the expected level …
Flood Prediction And Uncertainty Estimation Using Deep Learning, Vinayaka Gude, Steven Corns, Suzanna Long
Flood Prediction And Uncertainty Estimation Using Deep Learning, Vinayaka Gude, Steven Corns, Suzanna Long
Engineering Management and Systems Engineering Faculty Research & Creative Works
Floods are a complex phenomenon that are difficult to predict because of their non-linear and dynamic nature. Therefore, flood prediction has been a key research topic in the field of hydrology. Various researchers have approached this problem using different techniques ranging from physical models to image processing, but the accuracy and time steps are not sufficient for all applications. This study explores deep learning techniques for predicting gauge height and evaluating the associated uncertainty. Gauge height data for the Meramec River in Valley Park, Missouri was used to develop and validate the model. It was found that the deep learning …
Real-Time Assembly Operation Recognition With Fog Computing And Transfer Learning For Human-Centered Intelligent Manufacturing, Wenjin Tao, Md Al-Amin, Haodong Chen, Ming-Chuan Leu, Zhaozheng Yin, Ruwen Qin
Real-Time Assembly Operation Recognition With Fog Computing And Transfer Learning For Human-Centered Intelligent Manufacturing, Wenjin Tao, Md Al-Amin, Haodong Chen, Ming-Chuan Leu, Zhaozheng Yin, Ruwen Qin
Mechanical and Aerospace Engineering Faculty Research & Creative Works
In a human-centered intelligent manufacturing system, every element is to assist the operator in achieving the optimal operational performance. The primary task of developing such a human-centered system is to accurately understand human behavior. In this paper, we propose a fog computing framework for assembly operation recognition, which brings computing power close to the data source in order to achieve real-time recognition. For data collection, the operator's activity is captured using visual cameras from different perspectives. For operation recognition, instead of directly building and training a deep learning model from scratch, which needs a huge amount of data, transfer learning …
Hedge Fund Replication Using Strategy Specific Factors, Sujit Subhash, David Lee Enke
Hedge Fund Replication Using Strategy Specific Factors, Sujit Subhash, David Lee Enke
Engineering Management and Systems Engineering Faculty Research & Creative Works
Hedge funds have traditionally served wealthy individuals and institutional investors with the promise of delivering protection of capital and uncorrelated positive returns irrespective of market direction, allowing them to better manage portfolio risk. However, the financial crisis of 2008 has heightened investor sensitivity to the high fees, illiquidity, lack of transparency, and lockup periods typically associated with hedge funds. Hedge fund replication products, or clones, seek to answer these challenges by providing daily liquidity, transparency, and immediate exposure to a desired hedge fund strategy. Nonetheless, although lowering cost and adding simplicity by using a common set of factors, traditional replication …
Predicting The Daily Return Direction Of The Stock Market Using Hybrid Machine Learning Algorithms, X. Zhong, David Lee Enke
Predicting The Daily Return Direction Of The Stock Market Using Hybrid Machine Learning Algorithms, X. Zhong, David Lee Enke
Engineering Management and Systems Engineering Faculty Research & Creative Works
Big data analytic techniques associated with machine learning algorithms are playing an increasingly important role in various application fields, including stock market investment. However, few studies have focused on forecasting daily stock market returns, especially when using powerful machine learning techniques, such as deep neural networks (DNNs), to perform the analyses. DNNs employ various deep learning algorithms based on the combination of network structure, activation function, and model parameters, with their performance depending on the format of the data representation. This paper presents a comprehensive big data analytics process to predict the daily return direction of the SPDR S&P 500 …
Better Beware: Comparing Metacognition For Phishing And Legitimate Emails, Casey I. Canfield, Baruch Fischhoff, Alex Davis
Better Beware: Comparing Metacognition For Phishing And Legitimate Emails, Casey I. Canfield, Baruch Fischhoff, Alex Davis
Engineering Management and Systems Engineering Faculty Research & Creative Works
Every electronic message poses some threat of being a phishing attack. If recipients underestimate that threat, they expose themselves, and those connected to them, to identity theft, ransom, malware, or worse. If recipients overestimate that threat, then they incur needless costs, perhaps reducing their willingness and ability to respond over time. In two experiments, we examined the appropriateness of individuals' confidence in their judgments of whether email messages were legitimate or phishing, using calibration and resolution as metacognition metrics. Both experiments found that participants had reasonable calibration but poor resolution, reflecting a weak correlation between their confidence and knowledge. These …
Correction To: Better Beware: Comparing Metacognition For Phishing And Legitimate Emails (Metacognition And Learning, (2019), 14, 3, (343-362), 10.1007/S11409-019-09197-5), Casey I. Canfield, Baruch Fischhoff, Alex Davis
Correction To: Better Beware: Comparing Metacognition For Phishing And Legitimate Emails (Metacognition And Learning, (2019), 14, 3, (343-362), 10.1007/S11409-019-09197-5), Casey I. Canfield, Baruch Fischhoff, Alex Davis
Engineering Management and Systems Engineering Faculty Research & Creative Works
The article "Better beware: comparing metacognition for phishing and legitimate emails", written by Casey Inez Canfield, Baruch Fischhoff and Alex Davis, was originally published electronically on the publisher's internet portal (currently SpringerLink) on 20 July 2019 without open access.
Opportunities And Challenges For Rural Broadband Infrastructure Investment, Casey I. Canfield, Ona Egbue, Jacob Hale, Suzanna Long
Opportunities And Challenges For Rural Broadband Infrastructure Investment, Casey I. Canfield, Ona Egbue, Jacob Hale, Suzanna Long
Engineering Management and Systems Engineering Faculty Research & Creative Works
Insufficient internet access is holding back local economies, reducing educational outcomes, and creating health disparities in rural areas of the U.S. At present, federal and state funding is available for rural broadband infrastructure deployment, but existing efforts have not invested in analytical work to maximize efficiency and minimize cost. In this study, we use a state-of-the-art matrix (SAM) to identify key challenges and opportunities facing rural broadband infrastructure from previous research and government reports. We focus on six themes: (1) technology, (2) hardware costs, (3) financing, (4) adoption, (5) regulatory/legal, and (6) management. We highlight key issues to be addressed …
A Mixed Method Study Of Infrastructure Resilience Education And Instruction, John Richards, Suzanna Long
A Mixed Method Study Of Infrastructure Resilience Education And Instruction, John Richards, Suzanna Long
Engineering Management and Systems Engineering Faculty Research & Creative Works
As the frequency and severity of natural and man-made disasters increases, the importance of improving the resilience of complex infrastructure systems in an uncertain environment is increasingly critical. Proper training and education are key components to addressing this issue, but it is unclear how and where modeling under uncertainty, infrastructure systems management, and resilient systems are integrated into the standard undergraduate and graduate engineering management curriculum. This research uses a mixed method to determine whether and at what level engineering managers receive instruction regarding the implementation of tools and techniques to improve infrastructure resilience. A review of current courses and …
Flood Management Deep Learning Model Inputs: A Review Of Necessary Data And Predictive Tools, Jacob Hale, Suzanna Long, Steven Corns, Tom Shoberg
Flood Management Deep Learning Model Inputs: A Review Of Necessary Data And Predictive Tools, Jacob Hale, Suzanna Long, Steven Corns, Tom Shoberg
Engineering Management and Systems Engineering Faculty Research & Creative Works
Current flood management models are often hampered by the lack of robust predictive analytics, as well as incomplete datasets for river basins prone to heavy flooding. This research uses a State-of-the-Art matrix (SAM) analysis and integrative literature review to categorize existing models by method and scope, then determines opportunities for integrating deep learning techniques to expand predictive capability. Trends in the SAM analysis are then used to determine geospatial characteristics of the region that can contribute to flash flood scenarios, as well as develop inputs for future modeling efforts. Preliminary progress on the selection of one urban and one rural …
Risk Awareness Enhancement Systems For Hazmat Transportation: Prototyping And Technology Evaluation, Jian Xue, Katherine Linville, Yu Li, Pranav Nitin Godse, Suzanna Long, Ruwen Qin
Risk Awareness Enhancement Systems For Hazmat Transportation: Prototyping And Technology Evaluation, Jian Xue, Katherine Linville, Yu Li, Pranav Nitin Godse, Suzanna Long, Ruwen Qin
Engineering Management and Systems Engineering Faculty Research & Creative Works
Workers of hazardous material (hazmat) transportation have a higher chance than other workers to be exposed to various risks in their workplace. Assisting them to safely operate in their workplace in a near real-time manner is in particular need. This paper presents a study of designing, prototyping and developing feedback systems to help increase the risk awareness of workers in the loading and uploading phases of hazmat transportation. The first system was prototyped on an Arduino board, serving as the reference for system development. Then, the second system, named a Bluetooth Low Energy (BLE) beacon based system, was designed as …
Preface, Cihan H. Dagli, Gursel A. Suer
Preface, Cihan H. Dagli, Gursel A. Suer
Engineering Management and Systems Engineering Faculty Research & Creative Works
No abstract provided.
System Of Systems (Sos) Architecture For Digital Manufacturing Cybersecurity, Lirim Ashiku, Cihan H. Dagli
System Of Systems (Sos) Architecture For Digital Manufacturing Cybersecurity, Lirim Ashiku, Cihan H. Dagli
Engineering Management and Systems Engineering Faculty Research & Creative Works
Technology advancements of real time connectivity and computing powers has evolved the way people manage activities triggering heavy reliance on smart devices. This has reshaped the ability to memorize crucial information, instead accumulate the information into devices allowing real-time fingertip access when needed. Inability to access such information when needed is routinely assumed with device malfunctioning bypassing the probability of compromise, but what if the information is now being accessed by adversaries depriving the data-owner access to crucial information? Cyber manufacturing systems are not immune from these issues. It is possible to approach this problem as generating SoS meta-architecture. In …
Action Recognition In Manufacturing Assembly Using Multimodal Sensor Fusion, Md. Al-Amin, Wenjin Tao, David Doell, Ravon Lingard, Zhaozheng Yin, Ming-Chuan Leu, Ruwen Qin
Action Recognition In Manufacturing Assembly Using Multimodal Sensor Fusion, Md. Al-Amin, Wenjin Tao, David Doell, Ravon Lingard, Zhaozheng Yin, Ming-Chuan Leu, Ruwen Qin
Computer Science Faculty Research & Creative Works
Production innovations are occurring faster than ever. Manufacturing workers thus need to frequently learn new methods and skills. In fast changing, largely uncertain production systems, manufacturers with the ability to comprehend workers' behavior and assess their operation performance in near real-time will achieve better performance than peers. Action recognition can serve this purpose. Despite that human action recognition has been an active field of study in machine learning, limited work has been done for recognizing worker actions in performing manufacturing tasks that involve complex, intricate operations. Using data captured by one sensor or a single type of sensor to recognize …
A Framework Of Integrating Manufacturing Plants In Smart Grid Operation: Manufacturing Flexible Load Identification, Md. Monirul Islam, Zeyi Sun, Wenqing Hu, Cihan H. Dagli
A Framework Of Integrating Manufacturing Plants In Smart Grid Operation: Manufacturing Flexible Load Identification, Md. Monirul Islam, Zeyi Sun, Wenqing Hu, Cihan H. Dagli
Engineering Management and Systems Engineering Faculty Research & Creative Works
In the deregulated electricity markets run by Independent System Operator (ISO), a two-settlement (day-ahead and real-time) process is typically used to determine the electricity price to the end-use customers at different buses. In the day-ahead settlement, the demand is predicted at each bus based on the previous consumption behavior of the consumers and thus, Locational Marginal Price (LMP) can be determined and shared to the consumers. A significant gap is usually observed between the planned and real-time demands due to the uncertainties of the weather (temperature, wind-speed etc.), the intensity of business, and everyday activities. Therefore, a large price variation …
Joint Manufacturing And Onsite Microgrid System Control Using Markov Decision Process And Neural Network Integrated Reinforcement Learning, Wenqing Hu, Zeyi Sun, Y. Zhang, Y. Li
Joint Manufacturing And Onsite Microgrid System Control Using Markov Decision Process And Neural Network Integrated Reinforcement Learning, Wenqing Hu, Zeyi Sun, Y. Zhang, Y. Li
Mathematics and Statistics Faculty Research & Creative Works
Onsite microgrid generation systems with renewable sources are considered a promising complementary energy supply system for manufacturing plant, especially when outage occurs during which the energy supplied from the grid is not available. Compared to the widely recognized benefits in terms of the resilience improvement when it is used as a backup energy system, the operation along with the electricity grid to support the manufacturing operations in non-emergent mode has been less investigated. In this paper, we propose a joint dynamic decision-making model for the optimal control for both manufacturing system and onsite generation system. Markov Decision Process (MDP) is …
Vision Sensor Based Action Recognition For Improving Efficiency And Quality Under The Environment Of Industry 4.0, Zipeng Wang, Ruwen Qin, Jihong Yan, Chaozhong Guo
Vision Sensor Based Action Recognition For Improving Efficiency And Quality Under The Environment Of Industry 4.0, Zipeng Wang, Ruwen Qin, Jihong Yan, Chaozhong Guo
Engineering Management and Systems Engineering Faculty Research & Creative Works
In the environment of industry 4.0, human beings are still an important influencing factor of efficiency and quality which are the core of product life cycle management. Hence, monitoring and analyzing humans' actions are essential. This paper proposes a vision sensor based method to evaluate the accuracy of operators' actions. Each action of operators is recognized in real time by a Convolutional Neural Network (CNN) based classification model in which hierarchical clustering is introduced to minimize the effects of action uncertainty. Warnings are triggered when incorrect actions occur in real time and applications of action analysis of workers on a …
System Architecting Approach For Designing Deep Learning Models, Ram Deepak Gottapu, Cihan H. Dagli
System Architecting Approach For Designing Deep Learning Models, Ram Deepak Gottapu, Cihan H. Dagli
Engineering Management and Systems Engineering Faculty Research & Creative Works
Deep Learning (DL) models have proven to be very effective in solving many challenging problems, especially, those related to computer vision, text, and speech. However, the design of such models is challenging because of the vast search space and computational complexity that needs to be explored. Our goal in this paper is to reduce the human effort required to design architectures by using a system architecture development process that allows the exploration of large design space by automating certain model construction, alternative generation, and assessment. The proposed framework is generic and targeted at all deep learning architectures that can be …
Supply Chain Infrastructure Restoration Calculator Software Tool -- Developer Guide And User Manual, Akhilesh Ojha, Bhanu Kanwar, Suzanna Long, Thomas G. Shoberg, Steven Corns
Supply Chain Infrastructure Restoration Calculator Software Tool -- Developer Guide And User Manual, Akhilesh Ojha, Bhanu Kanwar, Suzanna Long, Thomas G. Shoberg, Steven Corns
Engineering Management and Systems Engineering Faculty Research & Creative Works
This report describes a software tool that calculates costs associated with the reconstruction of supply chain interdependent critical infrastructure in the advent of a catastrophic failure by either outside forces (extreme events) or internal forces (fatigue). This tool fills a gap between search and recover strategies of the Federal Emergency Management Agency (or FEMA) and construction techniques under full recovery. In addition to overall construction costs, the tool calculates reconstruction needs in terms of personnel and their required support. From these estimates, total costs (or the cost of each element to be restored) can be calculated. Estimates are based upon …
Analysis Of Parkinson's Disease Data, Ram Deepak Gottapu, Cihan H. Dagli
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 …
Densenet For Anatomical Brain Segmentation, Ram Deepak Gottapu, Cihan H. Dagli
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
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 …
Multi-Objective Evolutionary Neural Network To Predict Graduation Success At The United States Military Academy, Gene Lesinski, Steven Corns
Multi-Objective Evolutionary Neural Network To Predict Graduation Success At The United States Military Academy, Gene Lesinski, Steven Corns
Engineering Management and Systems Engineering Faculty Research & Creative Works
This paper presents an evolutionary neural network approach to classify student graduation status based upon selected academic, demographic, and other indicators. A pareto-based, multi-objective evolutionary algorithm utilizing the Strength Pareto Evolutionary Algorithm (SPEA2) fitness evaluation scheme simultaneously evolves connection weights and identifies the neural network topology using network complexity and classification accuracy as objective functions. A combined vector-matrix representation scheme and differential evolution recombination operators are employed. The model is trained, tested, and validated using 5100 student samples with data compiled from admissions records and institutional research databases. The inputs to the evolutionary neural network model are used to classify …