Leonard Brown

Tree-Based Indexes for Image Data

As in conventional database management systems (DBMSs), to allow users to efficiently access and retrieve data objects, a multimedia database management system (MMDBMS) must employ an effective access method such as indexing and hashing. This paper provides a survey of tree-based multidimensional indexing techniques for MMDBMSs that maintain image data represented as feature vectors. These techniques support such data while maintaining desirable characteristics of a B-tree, an index structure most commonly used in traditional DBMSs. In this survey, we provide descriptions of each tree as well as give examples of the different data organization schemes. We also describe the advantages and disadvantages of using each technique. In addition, we provide classifications of the trees using several different properties. These classifications should assist researchers in identifying the strengths and weaknesses of any new indexing technique they develop as well as help users determine the most appropriate data structure for their applications.

A stochastic dynamic programming approach for the equipment replacement optimization under uncertainty

In this paper, a stochastic dynamic programming (SDP) based optimization model is formulated for the equipment replacement optimization (ERO) problem that can explicitly account for the uncertainty in vehicle utilization. The Bellman approach is developed and implemented to solving the ERO SDP problem. Particular attention is paid to the SDP state-space growth and special scenario reduction techniques are developed to resolve the “curse of dimensionality” issue that is inherent to the dynamic programming method to ensure that the computer memory and solution computational time required will not increase exponentially with the increase in time horizon. SDP software computer implementation techniques, functionalities and the Graphical User Interfaces (GUI) are discussed. The developed SDP-based ERO software is tested and validated using the current Texas Department of Transportation (TxDOT) vehicle fleet data. Comprehensive numerical results, such as statistical analyses, the software computational time and solution quality, are described and substantial cost-savings have been estimated by using this ERO software. Finally, future research directions are also suggested.

Performing colour-based similarity searches in multimedia database management systems augmented with derived images

In order to improve the robustness of systems that perform similarity searching, it may be necessary to augment a collection of images in a Multimedia DataBase Management System (MMDBMS) with an additional set of edited images. Previous research has demonstrated that space can be saved in such a system by storing the edited images as sequences of editing operations instead of as large binary objects. The existing approaches for performing similarity searching in an MMDBMS, however, typically assume that the data objects are stored as binary objects. This paper proposes algorithms for performing colour-based similarity searches of images stored as editing operations and provides a performance evaluation illustrating their respective strengths and weaknesses.

Prediction from regional angst A study of NFL sentiment in Twitter using technical stock market charting

To predict NFL game outcomes, we examine the application of technical stock market techniques to sentiment gathered from social media. From our analysis we found a

Speeding up Color-Based Retrieval in Multimedia Database Management Systems that Store Images as Sequences of Editing Operations

14.84 average return per sentiment-based wager compared to a

Issues in augmenting image databases to improve processing content-based similarity searches

12.21 average return loss on the entire 256 games of the 20152016 regular season if using an odds-only approach. We further noted that wagers on underdogs (i.e., the less favored teams) that exhibit a golden cross pattern in sentiment (e.g., the most recent sentiment signal crosses the longer baseline sentiment), netted a

Issues in using specifications to improve content-based search of multimedia data

48.18 return per wager on 41 wagers. These results show promise of cross-domain research and we believe that applying stock market techniques to sports wagering may open an entire new research area. Gathered NFL tweet sentiment to predict outcomes and wagering decisionsUsed difference in moving averages for optimal wagering return (

Testing a Set of Image Processing Operations for Completeness

14.84/game)Sentiment exhibiting a golden cross netted

A Stochastic Dynamic Programming Approach for the Equipment Replacement Optimization with Probabilistic Vehicle Utilization

48.18/game returnsFans were able to signal winning teams by their change in sentiment.

Database research at the University of Oklahoma

Typically, multimedia database management systems process content-based image retrieval queries by extracting a set of features from each data object as it is inserted into the underlying database. By expressing queries that are based upon these features, users are able to retrieve the data objects back from the database. Previous research has demonstrated that one method of improving the effectiveness of similarity searches in such systems is to augment the underlying database with a set of edited images to allow more flexible matching. Space can be saved by storing the additional images as sequences of editing operations instead of as large binary objects. This paper proposes an approach for processing retrieval queries in such an environment and presents the results of a performance evaluation demonstrating the effectiveness of the approach.