Engineering Commons^™

Hamiltonian-Driven Adaptive Dynamic Programming With Efficient Experience Replay, Yongliang Yang, Yongping Pan, Cheng Zhong Xu, Donald C. Wunsch

Electrical and Computer Engineering Faculty Research & Creative Works

This article presents a novel efficient experience-replay-based adaptive dynamic programming (ADP) for the optimal control problem of a class of nonlinear dynamical systems within the Hamiltonian-driven framework. The quasi-Hamiltonian is presented for the policy evaluation problem with an admissible policy. With the quasi-Hamiltonian, a novel composite critic learning mechanism is developed to combine the instantaneous data with the historical data. In addition, the pseudo-Hamiltonian is defined to deal with the performance optimization problem. Based on the pseudo-Hamiltonian, the conventional Hamilton–Jacobi–Bellman (HJB) equation can be represented in a filtered form, which can be implemented online. Theoretical analysis is investigated in terms …

Time Series Classification Using Deep Learning For Process Planning: A Case From The Process Industry, Nijat Mehdiyev, Johannes Lahann, Andreas Emrich, David Lee Enke, Peter Fettke, Peter Loos

Engineering Management and Systems Engineering Faculty Research & Creative Works

Multivariate time series classification has been broadly applied in diverse domains over the past few decades. However, before applying the classification algorithms, the vast majority of current studies extract hand-engineered features that are assumed to detect local patterns in the time series. Therefore, the efficiency and precision of these classification approaches are heavily dependent on the quality of variables defined by domain experts. Recent improvements in the deep learning domain offer opportunities to avoid such an intensive hand-crafted feature engineering which is particularly important for managing the processes based on time-series data obtained from various sensor networks. In our paper, …

Evaluating Forecasting Methods By Considering Different Accuracy Measures, Nijat Mehdiyev, David Lee Enke, Peter Fettke, Peter Loos

Engineering Management and Systems Engineering Faculty Research & Creative Works

Choosing the appropriate forecasting technique to employ is a challenging issue and requires a comprehensive analysis of empirical results. Recent research findings reveal that the performance evaluation of forecasting models depends on the accuracy measures adopted. Some methods indicate superior performance when error based metrics are used, while others perform better when precision values are adopted as accuracy measures. As scholars tend to use a smaller subset of accuracy metrics to assess the performance of forecasting models, there is a need for a concept of multiple accuracy dimensions to assure the robustness of evaluation. Therefore, the main purpose of this …

Determination Of Rule Patterns In Complex Event Processing Using Machine Learning Techniques, Nijat Mehdiyev, Julian Krumeich, David Lee Enke, Dirk Werth, Peter Loos

Engineering Management and Systems Engineering Faculty Research & Creative Works

Complex Event Processing (CEP) is a novel and promising methodology that enables the real-time analysis of stream event data. The main purpose of CEP is detection of the complex event patterns from the atomic and semantically low-level events such as sensor, log, or RFID data. Determination of the rule patterns for matching these simple events based on the temporal, semantic, or spatial correlations is the central task of CEP systems. In the current design of the CEP systems, experts provide event rule patterns. Having reached maturity, the Big Data Systems and Internet of Things (IoT) technology require the implementation of …

Character-Based Automated Human Perception Quality Assessment In Document Images, Tayo Obafemi-Ajayi, Gady Agam

Electrical and Computer Engineering Faculty Research & Creative Works

Large degradations in document images impede their readability and deteriorate the performance of automated document processing systems. Document image quality (IQ) metrics have been defined through optical character recognition (OCR) accuracy. Such metrics, however, do not always correlate with human perception of IQ. When enhancing document images with the goal of improving readability, e.g., in historical documents where OCR performance is low and/or where it is necessary to preserve the original context, it is important to understand human perception of quality. The goal of this paper is to design a system that enables the learning and estimation of human perception …

Service Learning At Cincinnati: Researching Water Treatment For Emerging Economies, Sarah I. Pumphrey, Anna Hoessle, Daniel B. Oerther

Civil, Architectural and Environmental Engineering Faculty Research & Creative Works

Of the nearly six billion human inhabitants of planet earth, nearly two thirds lack access to sufficient quantities of potable water and access to basic sanitation. These appalling conditions result in the deaths of millions of children each year from preventable waterborne diarrheal disease. At the University of Cincinnati, two female graduate students have undertaken MS degrees with the specific objective of performing service learning where the research focus of their respective degrees is validating and deploying appropriate technology for water quality treatment in developing countries. This presentation will highlight the results of these research projects as well as the …

Penn State University Nsf Gk-12 Project: Using Web-Based Education And Interaction With K-12 And College Freshman To Promote Science And Engineering, Elana M. Chapman, Angela D. Lueking, Robin A. Tallon, Philip H. Henning, William S. Carlsen, Daniel C. Haworth

Chemical and Biochemical Engineering Faculty Research & Creative Works

Penn State University has hosted an NSF-sponsored GK-12 Outreach project for the past five years, and has just begun the second phase of the project. The Penn State project utilizes the talents of many science and engineering graduate students as teachers, mentors and role models for the K-12 classrooms. The project focuses on developing skills of students in the areas of science, technology, engineering and mathematics through the use of Advanced Transportation Technologies. A new project component was devised and implemented-the interaction of K-12 students with college freshman via a website project. The college freshmen were asked to create a …

A Matter Of Priorities: Effects Of Increased Opportunities For Extracurricular And Non-Traditional Learning Experiences On Student Time Management And Attitudes, David Spurlock, Daniel J. Bailey, Susan L. Murray, Andrew S. Ricke

Engineering Management and Systems Engineering Faculty Research & Creative Works

Many schools are emphasizing non-traditional and extracurricular learning experiences for undergraduate engineering students. These include activities such as incorporating servicelearning projects into the classroom, involving students in design competitions (e.g., solar car, formula car races), and promoting involvement in traditional campus organizations. Often this emphasis is in response to changes in ABET requirements, desires of future employers, and needs to improve student retention. What are the effects of emphasizing these sorts of activities on student attitudes and time management decisions? We examine the influences on students' priorities for allocating their time and their perceptions of the relative importance of available …

Nsf Ccli: Developing A Molecular Biology Lab Course In Environmental Engineering And Science, Daniel B. Oerther

Civil, Architectural and Environmental Engineering Faculty Research & Creative Works

A new course and associated short course, to teach molecular biology skills to undergraduate and graduate students in environment engineering and practitioners of environmental engineering across the state of Ohio and around the world, is developed. Environmental engineers use microorganisms as biocatalysts to degrade pollutants in sewage as well as in the sites undergoing bioremediation. A series of courses to introduce engineering students to the principles of biology, at the University of Cincinnati are developed. These courses include, 'introduction to environmental engineering', required for all third year civil engineering students.

Environmental Sustainability Education At The University Of Michigan: Collaboration With Industry To Provide Experiential Learning Opportunities, Angela D. Lueking, Deborah A. Ross, Walter Weber Jr

Chemical and Biochemical Engineering Faculty Research & Creative Works

The Concentrations in Environmental Sustainability (ConsEnSus) Program at the University of Michigan is a new multi-disciplinary opportunity for graduate students in the College of Engineering to pursue interests in environmental sustainability white obtaining a traditional engineering Master's degree. Students from several engineering departments complement traditional disciplinary course requirements with courses in environmental regulations, policies, and technology. A required case studies course of the ConsEnSus Program brings practicing engineers together with students to discuss real-world sustainability problems. The industrial participants interactively present relevant case studies, and provide opportunities for experiential learning through classroom activities and term projects. This paper …

Incorporating Web-Based Homework Problems In Engineering Dynamics, Ralph E. Flori, David B. Oglesby, Timothy A. Philpot, Nancy E. Hubing, Richard H. Hall, Vikas Yellamraju

Geosciences and Geological and Petroleum Engineering Faculty Research & Creative Works

We are involved in a project funded by the Department of Education (FIPSE) which focuses on developing interactive software to improve the teaching and learning of engineering statics, dynamics, and mechanics of materials. This paper presents an overview of this project, discusses its objectives, and focuses on one particular aspect of the project.the use of web-based homework problems as assessment tools to evaluate student learning. The overall project includes creating, for all three engineering mechanics courses, the following web-based learning tools: (a) Animated theory modules, using Macromedia.s Flash development software, which display basic theory and example problems in an engaging, …

Interactive Virtual Laboratory For Experience With A Smart Bridge Test, Elizabeth C. Eckhoff, Vicki M. Eller, Steve Eugene Watkins, Richard Hall

Electrical and Computer Engineering Faculty Research & Creative Works

Virtual laboratory experiments can be cost effective, convenient instructional resources that have appeal to a wide range of learning styles. Expensive, time-consuming laboratory tests can be experienced repeatedly and remotely using interactive simulations and original video footage or animations. A virtual experiment can incorporate meaningful exercises, procedural options, and background hyperlinks to create a comprehensive "hands on" environment. Also, it may be used as preliminary training for the actual experiment.

An interactive LabVIEW-based laboratory for a load test simulation of an existing demonstration bridge was created. This smart truss bridge is instrumented with fiber optic strain sensors situated on the …

Retention Of Female Faculty Members, Susan L. Murray, Mariesa Crow, Suzanna M. Rose

Engineering Management and Systems Engineering Faculty Research & Creative Works

The recruitment and the retention of female undergraduate and graduate students into engineering courses is discussed. A similar challenge lies in recruiting female faculty member from the limited pool of candidates in several fields at most universities. It is found that about half the females who were hired did not stay at the university. It is suggested that programs should be introduced to encourage mentoring and career development as such improvements would benefit all faculty members both female and male.

The Effectiveness Of An On-Line Graduate Engineering Management Course, Rosemarie Maffei Evans, Madison Daily, Susan L. Murray

Engineering Management and Systems Engineering Faculty Research & Creative Works

In the summer of 1997, the Engineering Management Department of the University of Missouri-Rolla's (UMR) began offering its first Internet-based graduate level course. This course, Advanced Production Management, was designed to utilize a combination of Internet-based tools, such as EMail and Chat rooms to create a alternative means for the delivery of course material. This paper will draw these following conclusions from more than a year of research, which included over 100 students in six different course offerings. First, the Internet-based students performed equally as well as the control group students. Second, students tend to have exaggerated time requirement expectations …

A Technology Assessment Survey For Web Based Higher Education Programs, Earl A. Evans, Susan L. Murray

Engineering Management and Systems Engineering Faculty Research & Creative Works

Advances in communications and computer technology, as well as in human-computer interfaces, have enabled concurrent advances in Web-based education. A number of case studies concerning applications of Web-based education for both distance learning and on-campus programs have been published. Primarily, these studies have focused on individual assessments of the web-based technologies. In contrast, this paper will provide a broad based assessment of applied web-based technology for higher education. This research was conducted via a survey completed by university and college faculty from numerous 4-year institutions. To gain an effective assessment, eleven categories of web-based course delivery tools, such as chatrooms …

A Recursive Least Squares Training Algorithm For Multilayer Recurrent Neural Networks, Q. Xu, K. Krishnamurthy, Bruce M. Mcmillin, Wen Feng Lu

Mechanical and Aerospace Engineering Faculty Research & Creative Works

Recurrent neural networks have the potential to perform significantly better than the commonly used feedforward neural networks due to their dynamical nature. However, they have received less attention because training algorithms/architectures have not been well developed. In this study, a recursive least squares algorithm to train recurrent neural networks with an arbitrary number of hidden layers is developed. The training algorithm is developed as an extension of the standard recursive estimation problem. Simulated results obtained for identification of the dynamics of a nonlinear dynamical system show promising results.

Identification Of Cutting Force In End Milling Operations Using Recurrent Neural Networks, Q. Xu, K. Krishnamurthy, Bruce M. Mcmillin, Wen Feng Lu

Mechanical and Aerospace Engineering Faculty Research & Creative Works

The problem of identifying the cutting force in end milling operations is considered in this study. Recurrent neural networks are used here and are trained using a recursive least squares training algorithm. Training results for data obtained from a SAJO 3-axis vertical milling machine for steady slot cuts are presented. The results show that a recurrent neural network can learn the functional relationship between the feed rate and steady-state average resultant cutting force very well. Furthermore, results for the Mackey-Glass time series prediction problem are presented to illustrate the faster learning capability of the neural network scheme presented here