Dr. Novobilski serves as a senior academic administrator in a small comprehensive university. In addition to his work as provost, he continues to pursue knowledge in the areas of higher ed administration, machine learning, and language design. Address: Gulf Shores, Alabama, United States
In 2014, the University of North Georgia committed to increasing opportunity for student / facult... more In 2014, the University of North Georgia committed to increasing opportunity for student / faculty participation by investing in the High Impact Practice of Undergraduate Research. Simultaneously, faculty development, undergraduate research, academic engagement, grant development and nationally competitive scholarships were consolidated into the Office of Research and Engagement. The synergy formed by bridging the touch-points between students, faculty, administration, and external opportunity within ORE led to new opportunities for student engagement. Ignited by a $1.3M five-year UNG Presidential Incentive Awards program, UNG increased nationally competitive scholarship awards, student faculty research opportunities, and competitive external awards from $1M / yr to $6 M in FY’18. Join us as we discuss the hidden bridges that can be tapped within our institutions to bridge opportunities for STEM students
44th AIAA Aerospace Sciences Meeting and Exhibit, 2006
This paper discusses an approach for interacting with geometry models in a true threedimensional ... more This paper discusses an approach for interacting with geometry models in a true threedimensional environment using an independent console to facilitate the computational analysis and design process. In the past, the viewing of three-dimensional models was restricted to a flat two-dimensional display. Using a new type of display, Actuality System’s Perspecta, three-dimensional geometry can be viewed and interacted with in a new way, allowing one to physically walk around and view the model as a volume. A brief discussion of three-dimensional viewing techniques is presented, followed by a discussion of the viewing hardware, the model generation process, the mesh creation process, and finally a discussion of the interface developed to interact with the model.
ABSTRACT Faculty from the University of Tennessee at Chattanooga and the University of Tennessee ... more ABSTRACT Faculty from the University of Tennessee at Chattanooga and the University of Tennessee College of Medicine, Chattanooga Unit, have used data mining techniques and neural networks to examine a set of fourteen features, data items, and HUMINT assessments for 2,148 emergency room patients with symptoms possibly indicative of Acute Coronary Syndrome. Specifically, the authors have generated Bayesian networks describing linkages and causality in the data, and have compared them with neural networks. The data includes objective information routinely collected during triage and the physician's initial case assessment, a HUMINT appraisal. Both the neural network and the Bayesian network were used to fuse the disparate types of information with the goal of forecasting thirty-day adverse patient outcome. This paper presents details of the methods of data fusion including both the data mining techniques and the neural network. Results are compared using Receiver Operating Characteristic curves describing the outcomes of both methods, both using only objective features and including the subjective physician's assessment. While preliminary, the results of this continuing study are significant both from the perspective of potential use of the intelligent fusion of biomedical informatics to aid the physician in prescribing treatment necessary to prevent serious adverse outcome from ACS and as a model of fusion of objective data with subjective HUMINT assessment. Possible future work includes extension of successfully demonstrated intelligent fusion methods to other medical applications, and use of decision level fusion to combine results from data mining and neural net approaches for even more accurate outcome prediction.
This paper describes two mutually enhancing technologies that will be used to evolve Bayesian net... more This paper describes two mutually enhancing technologies that will be used to evolve Bayesian network based forecasting models;. human/artificial cognition and Bayesian networks. A two tiered representation is introduced which mimics the way the human brain is thought to organize itself. This representation can be manipulated using genetic programming techniques to extract both attributes and organization of a Bayesian Network that models the underlying stochastic process for time series data. Experimental results are presented that demonstrate the effectiveness of the method in forecasting daily prices of stock issues.
Thesis (Ph. D.)--University of Texas at Arlington, 2000. Includes bibliographical references (lea... more Thesis (Ph. D.)--University of Texas at Arlington, 2000. Includes bibliographical references (leaves 85-93).
This paper explores the hypothesis that the depth cues and display quality of a 3D volumetric dis... more This paper explores the hypothesis that the depth cues and display quality of a 3D volumetric display provides advantages for learning simple tasks. Experimental data generated by human subjects using the Perspecta 3D Volumetric Display are compared to like data generated using a 2D flat screen liquid crystal display (LCD). These data show that the Perspecta display provides advantages over the LCD display with respect to peak performance of simple tasks.
One fascinating aspect of tool building for datamining is the application of a generalized datami... more One fascinating aspect of tool building for datamining is the application of a generalized datamining tool to a specific domain. Often times, this process results in a cross disciplinary analysis of both the datamining technique and the application of the results to the domain itself. This process of cross-disciplinary analysis often leads not only to improvements of the tool, but more importantly, to a better understanding of the underlying domain model for the domain experts involved. This paper presents the results of applying a datamining tool for identifying a Bayesian Network to represent a dataset of triage information taken from patients arriving at the emergency room with symptoms of Acute Coronary Syndrome. Specifically, a domain expert generated Bayesian Network and a mined Bayesian Network, both trained using the triage dataset, are compared for their accuracy in forecasting 30-day adverse outcomes for the patients represented in the dataset. The comparison, done using R...
One aspect of evolutionary computing as a method of data mining, is its intrinsic ability to driv... more One aspect of evolutionary computing as a method of data mining, is its intrinsic ability to drive model selection according to a mixed set of criteria. Based on natural selection, evolutionary computing utilizes evaluation of candidate solutions according to a ftness criteria that ~xfight or might not share the exact same implementation as the metric used to measure the performance of the selected solution. This paper presents the results of using four different fitness functions to evolve nai’ve Bayesian networks based on a combination of Mean Absolute Percent Error and Worst Absolute Percent Error values tbr individual population members. In addition to the error measurements tiom both the training and lbrecast evaluations, data is presented that shows APE lbr individual members during the tbrecast generation and evahtation phase.
Continuing improvements in computing power and high-speed Internet access have led to an explosio... more Continuing improvements in computing power and high-speed Internet access have led to an explosion in the popularity of multi-player online environments. In addition to providing a new form of entertainment, several of these environments have proven useful for educational activities. Specifically, the Second Life environment, which provides a physics and graphics engine for anyone to display 3D content, has received significant attention within the academic community. The University of Tennessee at Chattanooga recently used Second Life as a platform for a senior capstone project. We describe our experiences and evaluate Second Life as a virtual environment. The evaluation includes a discussion on several unique aspects of Second Life. Specifically, player ownership of virtual property and the express provision for transfers between real currency and the virtual Linden$; this raises some interesting unresolved financial and legal questions for future projects.
In 2014, the University of North Georgia committed to increasing opportunity for student / facult... more In 2014, the University of North Georgia committed to increasing opportunity for student / faculty participation by investing in the High Impact Practice of Undergraduate Research. Simultaneously, faculty development, undergraduate research, academic engagement, grant development and nationally competitive scholarships were consolidated into the Office of Research and Engagement. The synergy formed by bridging the touch-points between students, faculty, administration, and external opportunity within ORE led to new opportunities for student engagement. Ignited by a $1.3M five-year UNG Presidential Incentive Awards program, UNG increased nationally competitive scholarship awards, student faculty research opportunities, and competitive external awards from $1M / yr to $6 M in FY’18. Join us as we discuss the hidden bridges that can be tapped within our institutions to bridge opportunities for STEM students
44th AIAA Aerospace Sciences Meeting and Exhibit, 2006
This paper discusses an approach for interacting with geometry models in a true threedimensional ... more This paper discusses an approach for interacting with geometry models in a true threedimensional environment using an independent console to facilitate the computational analysis and design process. In the past, the viewing of three-dimensional models was restricted to a flat two-dimensional display. Using a new type of display, Actuality System’s Perspecta, three-dimensional geometry can be viewed and interacted with in a new way, allowing one to physically walk around and view the model as a volume. A brief discussion of three-dimensional viewing techniques is presented, followed by a discussion of the viewing hardware, the model generation process, the mesh creation process, and finally a discussion of the interface developed to interact with the model.
ABSTRACT Faculty from the University of Tennessee at Chattanooga and the University of Tennessee ... more ABSTRACT Faculty from the University of Tennessee at Chattanooga and the University of Tennessee College of Medicine, Chattanooga Unit, have used data mining techniques and neural networks to examine a set of fourteen features, data items, and HUMINT assessments for 2,148 emergency room patients with symptoms possibly indicative of Acute Coronary Syndrome. Specifically, the authors have generated Bayesian networks describing linkages and causality in the data, and have compared them with neural networks. The data includes objective information routinely collected during triage and the physician's initial case assessment, a HUMINT appraisal. Both the neural network and the Bayesian network were used to fuse the disparate types of information with the goal of forecasting thirty-day adverse patient outcome. This paper presents details of the methods of data fusion including both the data mining techniques and the neural network. Results are compared using Receiver Operating Characteristic curves describing the outcomes of both methods, both using only objective features and including the subjective physician's assessment. While preliminary, the results of this continuing study are significant both from the perspective of potential use of the intelligent fusion of biomedical informatics to aid the physician in prescribing treatment necessary to prevent serious adverse outcome from ACS and as a model of fusion of objective data with subjective HUMINT assessment. Possible future work includes extension of successfully demonstrated intelligent fusion methods to other medical applications, and use of decision level fusion to combine results from data mining and neural net approaches for even more accurate outcome prediction.
This paper describes two mutually enhancing technologies that will be used to evolve Bayesian net... more This paper describes two mutually enhancing technologies that will be used to evolve Bayesian network based forecasting models;. human/artificial cognition and Bayesian networks. A two tiered representation is introduced which mimics the way the human brain is thought to organize itself. This representation can be manipulated using genetic programming techniques to extract both attributes and organization of a Bayesian Network that models the underlying stochastic process for time series data. Experimental results are presented that demonstrate the effectiveness of the method in forecasting daily prices of stock issues.
Thesis (Ph. D.)--University of Texas at Arlington, 2000. Includes bibliographical references (lea... more Thesis (Ph. D.)--University of Texas at Arlington, 2000. Includes bibliographical references (leaves 85-93).
This paper explores the hypothesis that the depth cues and display quality of a 3D volumetric dis... more This paper explores the hypothesis that the depth cues and display quality of a 3D volumetric display provides advantages for learning simple tasks. Experimental data generated by human subjects using the Perspecta 3D Volumetric Display are compared to like data generated using a 2D flat screen liquid crystal display (LCD). These data show that the Perspecta display provides advantages over the LCD display with respect to peak performance of simple tasks.
One fascinating aspect of tool building for datamining is the application of a generalized datami... more One fascinating aspect of tool building for datamining is the application of a generalized datamining tool to a specific domain. Often times, this process results in a cross disciplinary analysis of both the datamining technique and the application of the results to the domain itself. This process of cross-disciplinary analysis often leads not only to improvements of the tool, but more importantly, to a better understanding of the underlying domain model for the domain experts involved. This paper presents the results of applying a datamining tool for identifying a Bayesian Network to represent a dataset of triage information taken from patients arriving at the emergency room with symptoms of Acute Coronary Syndrome. Specifically, a domain expert generated Bayesian Network and a mined Bayesian Network, both trained using the triage dataset, are compared for their accuracy in forecasting 30-day adverse outcomes for the patients represented in the dataset. The comparison, done using R...
One aspect of evolutionary computing as a method of data mining, is its intrinsic ability to driv... more One aspect of evolutionary computing as a method of data mining, is its intrinsic ability to drive model selection according to a mixed set of criteria. Based on natural selection, evolutionary computing utilizes evaluation of candidate solutions according to a ftness criteria that ~xfight or might not share the exact same implementation as the metric used to measure the performance of the selected solution. This paper presents the results of using four different fitness functions to evolve nai’ve Bayesian networks based on a combination of Mean Absolute Percent Error and Worst Absolute Percent Error values tbr individual population members. In addition to the error measurements tiom both the training and lbrecast evaluations, data is presented that shows APE lbr individual members during the tbrecast generation and evahtation phase.
Continuing improvements in computing power and high-speed Internet access have led to an explosio... more Continuing improvements in computing power and high-speed Internet access have led to an explosion in the popularity of multi-player online environments. In addition to providing a new form of entertainment, several of these environments have proven useful for educational activities. Specifically, the Second Life environment, which provides a physics and graphics engine for anyone to display 3D content, has received significant attention within the academic community. The University of Tennessee at Chattanooga recently used Second Life as a platform for a senior capstone project. We describe our experiences and evaluate Second Life as a virtual environment. The evaluation includes a discussion on several unique aspects of Second Life. Specifically, player ownership of virtual property and the express provision for transfers between real currency and the virtual Linden$; this raises some interesting unresolved financial and legal questions for future projects.
Uploads
Papers by Andy Novobilski