Search Results (1 - 15 of 15 Results)

Sort By  
Sort Dir
 
Results per page  

Chippa, Mukesh KGoal-seeking Decision Support System to Empower Personal Wellness Management
Doctor of Philosophy, University of Akron, 2016, Computer Engineering
Obesity has reached epidemic proportions globally, with more than one billion adults overweight with at least three hundred million of them clinically obese; this is a major contributor to the global burden of chronic disease and disability. This can also be associated with the rising health care costs; in the USA more than 75\% of health care costs relate to chronic conditions such as Diabetes and Hypertension. While there are various technological advancements in fitness tracking devices such as Fitbit, and many employers offer wellness programs, such programs and devices have not been able to create societal scale transformations in the life style of the users. The challenge in keeping healthy people healthy and helping them to be intrinsically motivated to manage their own health is at the focus for this investigation on Personal Wellness Management. In this dissertation, this problem is presented as a decision making under uncertainty where the participant takes an action at discrete time steps and the outcome of the action is uncertain. The main focus is to formulate the decision making problem in the Goal-seeking framework. To evaluate this formulation, the problem was also formulated in two classical sequential decision-making frameworks --- Markov Decision Process and Partially Observable Markov Decision Process. The sequential decision-making frameworks allow us to compute optimal policies to guide the participants' choice of actions. One of the major challenges in formulating the wellness management problem in these frameworks is the need for clinically validated data. While it is unrealistic to find such experimentally validated data, it is also not clear that the models in fact capture all the inconstraints that are necessary to make the optimal solutions effective for the participant. The Goal-seeking framework offers an alternative approach that does not require explicit modeling of the participant or the environment. This dissertation presents a software system that is designed in the Goal-seeking framework. The architecture of the system is extensible. A modular subsystem that is useful to visualize exercise performance data that are gathered from a Kinect camera is described.

Committee:

Shivakumar Sastry, Dr (Advisor); Nghi Tran, Dr (Committee Member); Igor Tsukerman, Dr (Committee Member); William Schneider IV, Dr (Committee Member); Victor Pinheiro, Dr (Committee Member)

Subjects:

Computer Engineering

Keywords:

decision support system, personalized wellness management, Goal seeking paradigm, markov decision process, partially observable markov decision process

Pantelopoulos, Alexandros A.¿¿¿¿¿¿¿¿¿¿¿¿PROGNOSIS: A WEARABLE SYSTEM FOR HEALTH MONITORING OF PEOPLE AT RISK
Doctor of Philosophy (PhD), Wright State University, 2010, Computer Science and Engineering PhD
Wearable Health Monitoring Systems (WHMS) have drawn a lot of attention from the research community and the industry during the last decade. The development of such systems has been motivated mainly by increasing healthcare costs and by the fact that the world population is ageing. In addition to that, RandD in WHMS has been propelled by recent technological advances in miniature bio-sensing devices, smart textiles, microelectronics and wireless communications techniques. These portable health systems can comprise various types of small physiological sensors, which enable continuous monitoring of a variety of human vital signs and other physiological parameters such as heart rate, respiration rate, body temperature, blood pressure, perspiration, oxygen saturation, electrocardiogram (ECG), body posture and activity etc. As a result, and also due to their embedded transmission modules and processing capabilities, wearable health monitoring systems can constitute low-cost and unobtrusive solutions for ubiquitous health, mental and activity status monitoring. The majority of the currently developed WHMS research prototypes and products provide the basic functionality of continuously logging and transmitting physiological data. However, WHMS have the potential of achieving early detection and diagnosis of critical health changes that could enable prevention of health hazardous episodes. To do that, they should be able to learn individual user baselines and also employ advanced information processing algorithms and diagnostics in order to discover problems autonomously and detect alarming health trends, and consequently, inform medical professionals for further assistance. In an effort to advance the capabilities of a wearable system towards these goals, we focus in this dissertation on the development of a novel WHMS, called Prognosis. The developed prototype platform includes the following innovative features, which constitute the main research contributions of this work: a) a novel and highly accurate methodology for classifying ECG recordings on a resource constrained device which is based on the Matching Pursuits algorithm and a Neural Network, b) a physiological data fusion scheme based on a fuzzy regular formal language model, whereby the current state of the corresponding fuzzy Finite State Machine signifies the current health state and context of the patient, c) the extension of the decision making methodology based on a modified Fuzzy Petri Net (FPN) model, d) the integration of a user-learning strategy based on a neural-fuzzy extension of the FPN, e) the incorporation of a system-patient dialogue interaction in order to capture non-measurable patient symptoms such as chest pain, dizziness, malaise etc and finally f) the prototyping of the system based on a smart-phone that runs multi-threaded J2ME software for handling multiple simultaneous Bluetooth connections with off-the-shelf wireless bio-sensors.

Committee:

Nikolaos Bourbakis, PhD (Advisor); Soon Chung, PhD (Committee Member); Yong Pei, PhD (Committee Member); Arnab Shaw, PhD (Committee Member); Larry Lawhorne, PhD (Committee Member)

Subjects:

Computer Science; Engineering; Health Care; Information Systems

Keywords:

wearable health monitoring system; ECG classification; ECG denoising; medical decision support system; smart-phone

PAEZ, OMAR ROLANDOPERFORMANCE TRACKING THROUGH THE WORK COMPATIBILITY VISUAL TOOL
MS, University of Cincinnati, 2004, Engineering : Industrial Engineering
Objective: This study proposes a decision-support framework to track the state of the human-at-work system on an operational basis. The work compatibility model provides a multi-dimensional diagnostic of the human-at-work system. By integrating the work compatibility model into a visual framework, management can make informative decisions that contribute to the improvement of human performance Background: Examples of multidimensional models can be found in performance measuring systems and human performance measures. Performance measuring systems, either hierarchical or balanced models, are focused on the reduction of operational variables to financial performance. Human performance measures rely on respondents to weigh different factors and define the best rules for aggregation. In the work compatibility model, respondents rate work-factors as energizers and demands on the system. An expert model uses a matrix function to quantify the degree of compatibility. Based on the matrix output, operating zones determine how far the system is from the optimum performance. Conceptual model: The matrix function of the expert solution is transformed into a plane with two regions set along the compatibility line. Work factors are aggregated into two vectors, one on each region of the plane, and the resultant of the two vectors provides two indexes: the yield ratio, a relative measure of the magnitude of vector, and the efficiency ratio, a relative measure of the angle between the two vectors. A Visual Basic application is developed to implement the proposed quantitative methods. The continuous model is tested with data from a manufacturing company to analyze the behavior of the response function. Case study: The yield ratio follows a normal distribution, and the efficiency ratio follows a chi-square distribution. An analysis of variance shows that the yield ratio provides a performance levels similar to those of the expert solution. The decision process starts by setting targets are for each department based on core competencies. The diagnostic shows that the Manufacturing Department has a low yield ratio and the Sales Department has an medium yield ratio. Both departments have a high efficiency ratio, which means that all dimensions are well balanced. A top-down approach identifies work factors that require immediate improvement: conflict, perceived risk/benefit, dissatisfaction and muscular activities. The work compatibility principles can be applied to low performing factors in order to set a course of action. Enablers such as job design, self-managed teams and performance communication are recommended to correct under-performing work factors. Conclusions: The proposed model is capable of monitoring slight improvements in the human-at-work system that will not be noticed by the expert model. The proposed indexes allow performance comparisons across respondents and across dimensions. By using a unified approach to all subsystems, decision-makers are more likely to grasp the behavior of the human-at-work system and provide actions that effectively improve human performance.

Committee:

Dr. Ash Genaidy (Advisor)

Subjects:

Engineering, Industrial

Keywords:

Work compatibility; Performance measurement; Decision-support system

Schafer, Sarah E.A GIS Connection between Brownfield Sites, Transportation and Infrastructure: An Economic Redevelopment Tool for Toledo-Lucas County, Ohio
Master of Arts, University of Toledo, 2011, Geography
This thesis documents the design and development of a web-based data distribution system for brownfield site redevelopment in Toledo-Lucas County, Ohio. The system is designed to advance smart growth initiatives for economic redevelopment and the sustainable utilization of brownfield sites in the region. As with many Midwestern cities, industrial decline has lead to an abundance of brownfield sites in the area. A lack of data resources is one major barrier to redevelopment of these sites. The system developed here seeks to reduce that barrier by providing a user interface and information delivery system to support the identification and reuse of brownfield sites; in addition it can be replicated for use in other regions. Detailed here is the development and implementation of an interactive web-based geographic information system (GIS) designed as a user-centered decision support tool to augment policymakers’ and stakeholders’ site selection and infrastructure capital investment decisions to support brownfield redevelopment. This system thus provides not only a comprehensive data delivery tool and decision support system but also serves as a template for application in other urban regions.

Committee:

Peter Lindquist, PhD (Advisor); Daniel Hammel, PhD (Committee Member); Sujata Shetty, PhD (Committee Member)

Subjects:

Geographic Information Science

Keywords:

Web based GIS; brownfields; Decision support system development

Young, William AlbertA Team-Compatibility Decision Support System to Model the NFL Knapsack Problem: An Introduction to HEART
Doctor of Philosophy (PhD), Ohio University, 2010, Industrial and Systems Engineering (Engineering and Technology)

Many tangible and intangible factors are considered when making a hiring decision in the National Football League (NFL). One difficult decision that executives must make is whom they will select in the NFL Draft or which NFL Free Agent they will sign in the offseason. Mathematical models can be developed to aid humans in their decision-making process because they are able to find non-obvious relationships within numeric data. HEART, or Heuristic Evaluation of Artificially Replaced Teammates, is a mathematical model that utilizes machine learning and statistical-based methodologies to aid managers with their hiring decisions. HEART is not intended to be a ‘decision tool,' or a tool that explicitly states who a team should hire. A ‘decision tool' would need to encompass not only the tangible information available to hiring managers but also intangible aspects that are difficult or impossible for mathematical model to capture accurately. HEART is a ‘decision support tool' that provides additional information for hiring managers to use in conjunction with other available resources.

The goal of HEART is to determine an Expected and Theoretical Contribution Value for a potential hiring candidate, which represents a player's ability to increase or decrease the estimated number of games won by a particular team in an upcoming season. This value is significant because it represents a player's level of compatibility with potential teammates and considers the effect that aging has on players' physiological ability to play football. HEART is also designed to allow direct comparisons of players from any playing position as well as players from either college or professional leagues.

From a quantitative standpoint, the results of the HEART methodology were statistically validated using both parametric and nonparametric testing procedures. This validation procedure analyzed the results collected from a convenient sample of experts who participated in a survey instrument. The validation results show that the HEART methodology provided at least ‘Useful' results, and at times ‘Very Useful' results, using a five-point Likert scale for a case study involving the 2007 NFL Draft Class and Free Agent Players.

Committee:

Gary Weckman, PhD (Advisor); Masel Dale, PhD (Committee Member); Kaya Savas, PhD (Committee Member); Snow Andrew, PhD (Committee Member); Genaidy Ashraf, PhD (Committee Member)

Subjects:

Artificial Intelligence; Engineering; Industrial Engineering; Management

Keywords:

Team Compatibility; Decision Support System; NFL Draft; NFL Free Agency; Performance Aging Curves; Combine; Theoretical and Expected Contribution Values; League-Wide, Team-Specific; Quantitative Analysis in Sports

Horne, Susan ElaineA Seasonal Shelf Space Reorder Model Decision Support System
PHD, Kent State University, 2010, College of Business Administration / Department of Management and Information Systems

The traditional newsvendor model results in a decision to reorder an item whenever the expected profit from the reorder is positive. Candidates for reorder include all items selling more quickly than had been anticipated during preseason forecasts and ordering. Retailers must also decide how to allocate shelf space in order to optimize store profit; any item reordered must be the most profitable option among all items competing for the same shelf space. Overall store profit calculations must incorporate the impact on sales of related items, the cost of stock outs, and characteristics of the reordered item. Seasonal products’ abbreviated sales windows and style products’ short life cycles add urgency and complexity to the reorder decision. Lack of product availability may limit how much of the most profitable item can be ordered; in these cases, the next most profitable item is the most likely candidate for the remaining available shelf space.

In this paper we extend the work of Corstjens and Doyle (1981) and Gallego and Moon (1993) and develop a model encompassing each of these elements: the newsvendor reorder decision, seasonal goods, style goods, multiple discounts, shortage costs, expediting, and shelf space allocation incorporating cross product elasticity. The shelf space allocation is an extension of the knapsack problem requiring not only that the profit calculations include effects on sales of related items, but that the requisite space to hold these related items is available.

The model is implemented and validated as a decision support system (DSS). Corstjens and Doyle’s (1981), Gallego and Moon’s (1993), and the classic newsvendor models are also implemented in the DSS for comparison purposes. Scenario analysis, testing the model’s sensitivity of the decision to managers’ assumptions, is incorporated as are tools to derive the range of values for which the decision is valid.

Committee:

Marvin Troutt, PhD (Committee Chair); Alan Brandyberry, PhD (Committee Member); Alfred Guiffrida, PhD (Committee Member); Milton Harvey, PhD (Committee Member)

Subjects:

Business Administration; Information Systems; Management; Marketing

Keywords:

shelf space; newsvendor; seasonality; style goods; fashion; space elasticity; cross product elasticity; decision support system; DSS; simulation; innovative products; expert validation; verification

Mekonnen, Addisu DerejeWind Farm Site Suitability Analysis in Lake Erie Using Web-Based Participatory GIS (PGIS)
Master of Science (MS), Bowling Green State University, 2014, Geology
This study presents the design and implementation of a web-based Participatory Geographic Information System (PGIS) framework intended for offshore wind suitability analysis. The PGIS prototype presented here integrates GIS and decision-making tools that are intended to involve different stakeholders and the public for solving complex planning problems and building consensus. Public involvement from the early planning stage of projects with a spatial nature is very important for future legitimacy and acceptance of these projects. Therefore, developing and executing a system that facilitates effective public involvement for resolving contentious issues can help fostering long-lasting agreements. The prototype here is a distributed and asynchronous PGIS that combines a discussion forum, mapping tool and decision tool. The PGIS is implemented following a thin-client server environment with three-tier architecture and the potential strengths and benefits of this PGIS are demonstrated in a hypothetical case study in Lake Erie, northern Ohio. In the hypothetical case study, participants evaluate the importance of three decision alternatives using different evaluation criteria for expressing their individual preferences. The individual preferences are aggregated by the Borda Count (BC) method for generating the group solution, which is used for synthesizing the different evaluation aspects such as the importance of criteria, ranking of the decision alternatives and planning issues related to environmental and socio-economic concerns from the participants.

Committee:

Peter Gorsevski, Ph.D. (Advisor); Kurt Panter, Ph.D. (Committee Member); Margaret Yacobucci, Ph.D. (Committee Member)

Subjects:

Geographic Information Science

Keywords:

PGIS; spatial decision support system; offshore wind farm suitability; Borda method; decision alternatives; and multiple criteria evaluation

SINGH, ARUN K.ELECTRONIC SIMULATION IN CONSTRUCTION
MS, University of Cincinnati, 2002, Engineering : Civil Engineering
There are many excellent 3D CAD, Virtual Reality and Mathematical simulation system hardware and software systems available today. Most suppliers sell basic tools for these systems. But they may not provide the expertise on how to use the tools or what to build with them. Without this expertise it is almost impossible to know what is the most appropriate equipment and software, or even whether these systems are really an appropriate solutions for a company. In this research, effort is made to find state of art, state of practice and state of future for 3D CAD, Virtual Reality and Mathematical simulation system. The technology and use of system solutions available to the industry were reviewed and investigated. A number of accepted results from the industry were discovered. Some critical considerations for the effective utilization of electronic simulation to improve construction benefits were determined which bring value to the implementers business. Real time data was collected from vendors, academic researchers and industries. Data was analyzed and relevant data was used to develop a database for the supplier/ product information. A web based Decision Aid was developed to help businesses make decisions with respect to (i) analyzing the need for these modern technologies in their line of business, (ii) the supplier products available in 3D CAD, Virtual Reality and Mathematical simulation system categories, and (iii) similarities and differences between the available products.

Committee:

Dr. Makarand Hastak (Advisor)

Subjects:

Engineering, Civil

Keywords:

simulation; decision support system; web; virtual reality; mathematical simulation

Matz, Thomas W.A decision support system for synchronizing manufacturing in a multifacility production system
Master of Science (MS), Ohio University, 1989, Industrial and Manufacturing Systems Engineering (Engineering)

This thesis describes the design of a decision support system for planning sign production at the Ohio Department of Transportation. The process of maintaining Ohio's rural roadways with visible traffic signs can be viewed as a 2- stage geographically, distributed manufacturing process; the first stage being sign manufacture at a central facility, and the second stage being sign installation at one of twelve districts. A strategy utilizing state space representation is proposed for finding low cost sign production and installation plans that are feasible for both the central shop and the twelve districts.

The continual production of signs is necessary because of the fact that signs out on the road are constantly deteriorating. When the reflectivity of a sign diminishes to a certain level (as set by ODOT), the sign must be replaced. Replacement of signs is carried out by roadway crews in each district. In addition to sign replacement, roadway crews are responsible for erecting detours, installing RPM's, and painting lines. Thus the capacity of the districts to replace signs is dependent on the demand for these other activities.

The development of the DSS is part of a major software project for the Department of Transportation. The state of Ohio is currently in the process of upgrading its sign management system. This involves development of sign field inventory data bases in each district and a sign replacement candidate identification system. The latter is a group of models that queries the field inventory data base and determines whether a sign should be replaced. Its list of candidate signs becomes input to the DSS.

The functions of the DSS are to plan the activities of the roadway crews in each district and to plan production at the sign shop. As with any manufacturing system, low inventories are maintained by synchronizing the two stages in the process. Signs are not produced unless they have been designated as replacements, and no replacements are planned unless the respective signs can be produced in time. In addition to inventory cost, labor cost is considered.

The generation of sign installation and production plans is carried out by two subsystems in the DSS: the Roadway Crew Activity Planning System and the Production Planning System. Both systems contain algorithms that use search with a state space representation. In both algorithms, demons and constraint rules are used to maintain feasibility by pruning the search space of infeasible solutions. The ability to share results across the search space is made possible by an underlying truth maintenance system. Once the state space is completely generated, alternative contexts can be evaluated.

Committee:

Robert Terry (Advisor)

Subjects:

Engineering, Industrial

Keywords:

Decision Support System; Synchronizing Manufacturing; Multifacility Production System

LI, YUPLANNING DECISION SUPPORT SYSTEM WITH GIS AND VIRTUAL REALITY
MCP, University of Cincinnati, 2001, Design, Architecture, Art, and Planning : Community Planning
This project applies the concepts of computer-based decision support system (DSS) to a planning project, Interstate 71 Corridor Study in Metropolitan Cincinnati Area. The final product will be a planning decision support system for two major issues in transportation planning: congestion control and emission-concentration estimation. This DSS will consist a geographic information system (GIS) of study area and a set of Graphic User Interface (GUI). It will allow planners and other decision-makers to select planning alternatives for specific areas and compare results. Four methodologies will be used: 1) geographic information system applications, 2) virtual reality technology, 3) quantitative analysis with mathematical models, and 4) object-oriented programming.

Committee:

Dr. Xinhao Wang (Advisor)

Subjects:

Urban and Regional Planning

Keywords:

DECISION SUPPORT SYSTEM; GIS; I-71; TRANSPORTATION; EMISSION CONCENTRATION

Spencer, MalikCHRISTINE: A Flexible Web-Based Clinical Decision Support System
MS, University of Cincinnati, 2010, Engineering and Applied Science: Computer Engineering
In today’s health care environment, clinicians are under intense pressure to provide high quality care for an ever-increasing array of ailments. The time requirements associated with caring for many patients often impact the time available for staying current with new research on therapies and other treatment options. Clinical decision support systems (CDSSs) offer a way to improve clinical outcomes by giving clinicians access to a universe of timely and relevant information in a way that builds upon his or her existing knowledge. In this thesis we describe the creation of one such CDSS (we call CHRISTINE) starting with a description of the problem space then continuing with search for existing solutions, our solution and its implementation, a case study of how our solution would be used on an example patient, an evaluation of our solution, and an interview with a clinician about our CDSS and the future of clinical decision support.

Committee:

Karen Davis, PhD (Committee Chair); Carla Purdy, C, PhD (Committee Member); John Pestian, PhD (Committee Member)

Subjects:

Computer Science

Keywords:

Clinical Decision Support System;Expert System;Web Application

Liu, XiaohuiWeb-Based Multi-Criteria Evaluation of Spatial Trade-Offs between Enivironmental and Economic Implications from Hydraulic Fracturing in a Shale Gas Region in Ohio
Master of Science (MS), Bowling Green State University, 2014, Geology
Planning of shale gas infrastructure and drilling sites for hydraulic fracturing has important spatial implications. The evaluation of conflicting and competing objectives requires an explicit consideration of multiple criteria as they have important environmental and economic implications. This study presents a web-based multi-criteria spatial decision support system (SDSS) prototype with a flexible and user-friendly interface that could provide educational or decision-making capabilities with respect to hydraulic fracturing site-selection in eastern Ohio. One of the main features of this spatial decision support system is to emphasize potential trade-offs between important factors of environmental and economic implications from hydraulic fracturing activities using a weighted linear combination (WLC) method. WLC is a simple approach that integrates users' preferences into an overall assessment and offers a rationale for trade-offs between decision criteria and objectives. In the prototype, the GIS-enabled analytical components allow spontaneous visualization of available alternatives on maps which provide value-added features for decision support processes and derivation of final decision maps. The SDSS prototype exhibits a straightforward decision-making procedure with easy-to-use web interface and facilitates non-expert participation capabilities. It comprises of a mapping module, decision-making tool, group decision data statistics, and social media sharing tools. The system architecture combines a variety of closely related components using Silverlight, ArcGIS API for Silverlight, ArcGIS Server, and ArcSDE for SQL Server software. During the decision-making process, users are guided through a logical flow of successively presented forms and standardized criteria maps to generate visualization of trade-off scenarios and alternative solutions tailored to their personal preferences. Finally, the results and the preferences from all users are graphed for visualization and subsequent decision-making making.

Committee:

Peter Gorsevski (Advisor); Charles Onasch (Committee Member); Margaret Yacobucci (Committee Member)

Subjects:

Geographic Information Science

Keywords:

Spatial decision support system; hydraulic fracturing site-selection; multivariate criteria evaluation; weighted linear combinition; and ArcGIS API for Silverlight

ABU HAMAD, AYMAN ABDALLAHA DECISION SUPPORT SYSTEM FOR MANUFACTURED HOUSING PRODUCTION PROCESS PLANNING AND FACILITY LAYOUT
PhD, University of Cincinnati, 2003, Engineering : Civil Engineering
Productivity improvement of manufactured housing (MH) production systems has been a great concern to manufacturers and production managers. The evaluation of the production system efficiency in the factory is essential for meeting the growing demand of customers with respect to design and size of the manufactured housing product (MH). The purpose of this research is to resolve some of the problems of the MH production system. The problems of the existing system are identified in the masters thesis, Abu Hammad 2001, as follows: i) process bottlenecks hindering productivity, ii) unbalanced processes, and iii) layout limitations to the production capacity. Moreover, a lack of technology is observed in the existing MH operations. Existing production systems employing the traditional production line have low throughput and are inefficient. This dissertation research explores alternative layout designs that are proven via simulation to be more efficient and productive. Additionally, an advanced MH production system employing recent theories in technology and manufacturing is addressed in this research. The major contribution of this dissertation is to develop a decision support system (DSS), which provides the MH industry with an efficient tool to streamline the performance of existing MH facilities. This dissertation investigates the interrelation impact of multiple factors on the productivity of four modules: (i) market, (ii) factory, (iii) manufactured housing processes, and (iv) production system layout. The following objectives have been achieved in support of the stated goal: 1.Develop a streamlined MH process; 2.Develop optimization models to streamline the activities and predict relevant parameters; 3.Develop advanced layout designs employing recent theories in manufacturing (i.e., lean production theory). The DSS provides assistance in the following decisions: (i) selecting an efficient system layout matching user requirements, (ii) streamlining activities and operations of the overall production system, and (iii) predicting the productivity and product sizes based on the organizational requirements. Finally, a feedback from the manufacturers has indicated that the DSS meets a crucial need for streamlining the system operations. The proposed DSS is a practical, simple, and accurate tool for scheduling and planning the operations, resources, and material requirements of the production system.

Committee:

Dr. Ossama Salem (Advisor)

Keywords:

Decision Support System; Manufactured Housing; Facility Layout; Production System; Simulation Modeling; Optimization; Productivity improvent; System efficiency

Regmi, Hem KantaA Real-Time Computational Decision Support System for Compounded Sterile Preparations using Image Processing and Artificial Neural Networks
Master of Science, University of Toledo, 2016, Electrical Engineering
The purpose of this research is to design a computational decision support system (DSS) for compounded sterile preparations (CSP). Error-free compounding is dependent on the proper selection of components and adherence to procedure during compounding. A material selection system (MSS) based on a graphical user interface (GUI), coupled with a barcode scanner and back-end database, has been developed and tested for proper selection of items involving three different medication orders (MO). A video processing system (VPS) has been implemented in MATLAB that evaluates the live video feed from the compounding hood to monitor the compounding procedure when compounding the MO’s. Surf detection is used to detect and locate compounding items placed in the hood. Various algorithms have been developed and tested to enhance the accuracy and robustness of the VPS. The Decision Support System (DSS) is further improved with integration of another digital camera to ensure that correct volume of medicine with appropriate syringe is performed during the whole compounding process. The template matching and SURF object detection application on the digital image of the syringe, along with minimum distance classifier and artificial neural networks (ANNs) on the previously collected data from several experimental observations, were explored in classification and volume measurement of a syringe. The MSS was tested for all items used in compounding the MO’s and performed error-free. The VPS evolved to VPS.03 from VPS.01 and VPS.02. The greatest accuracy and ability for real-time realization were seen in VPS.03. All deliberate mistakes made when compounding the tested medication orders were captured by VPS.03. Leur-lock syringes of different sizes from 1 mL to 30 mL were tested, and an accuracy of 95+ % was obtained with very high precision. The new computational decision support system facilitates error-free selection of components and is able to monitor and evaluate the compounding process and correct volume measurement in real time. The platform may be used in CSP compounding rooms to audit techniques and procedures as well as in training or educational settings.

Committee:

Vijay Devabhaktuni, Dr. (Committee Chair); Jerry Nesamony, Dr. (Committee Co-Chair); Devinder Kaur, Dr. (Committee Member); Ezzatollah Salari, Dr. (Committee Member)

Subjects:

Electrical Engineering

Keywords:

Compounding Sterile Preparations, Graphical User Interface, Artificial Neural Networks, Image Processing, Video Processing, Decision Support System, Medication Order, Object Detection, Correlation Calculation, Connected Component Analysis

Thomassin Singh, DanieleIncorporating solution process monitoring tools into current decision support system architecture
Doctor of Philosophy, Case Western Reserve University, 1994, Management Information and Decision Systems
The objective of DSS research is to provide computer-based support for managerial decision making. In order to do this, a DSS needs to (a) support a manager's task-related needs by providing information about a specific decision situation and models to assist in structuring the situation, and (b) support a manager's cognitive abilities by providing information about the decision making process and models to assist in structuring the process. Most DSS research to date has focused on task-related support exclusively, revealing an implicit, and mostly unarticulated, assumption that the latter kind of support is either unnecessary, or impossible to provide. Research in decision making and cognitive psychology, however, indicates that such support should significantly benefit the manager's decision making process. This dissertation examines how computer-based tools may support the cognitive abilities decision makers draw upon when using a DSS, and, whether such tools demonstrate the potential to improve the quality of their decision making processes. The study concentrates on providing support for one type of cognitive ability, namely solution process monitoring, or, the ability to monitor the execution of a planned solution strategy. Solution process monitoring support w as built into a DSS designed to support product pricing and budgeting decisions of marketing managers. The study was designed as a 2 (presence vs. absence of strategy complexity support) by 2 (presence vs. absence of information load support) by 2 (simple vs. complex strategy) full-factorial laboratory experiment. Significant findings from the study indicate that, in general, the higher the level of computerized monitoring support, the lesser the time taken to solve the decision task and the fewer the number of unintentional deviations from planned strategy. A process analysis found that computerized solution process monitoring significantly reduced the number of actions performed that were (a) unnecessarily repeated, (b) involuntarily omitted, and (c) unintended. Additionally, the results of a protocol analysis indicated that computerized solution process monitoring support also favorably impacted subjects' ability to recuperate from unintended errors in implementing the solution strategy. While further validation is recommended, these findings strongly suggest that DSS researchers and designers may benefit from the inclusion of decision-maker support in their frameworks.

Committee:

Michael Ginzberg (Advisor)

Keywords:

solution process monitoring tools; current decision; support system architecture