Byron Marshall

A case-based reasoning framework for workflow model management

In order to support efficient workflow design, recent commercial workflow systems are providing templates of common business processes. These templates, called cases, can be modified individually or collectively into a new workflow to meet the business specification. However, little research has been done on how to manage workflow models, including issues such as model storage, model retrieval, model reuse and assembly. In this paper, we propose a novel framework to support workflow modeling and design by adapting workflow cases from a repository of process models. Our approach to workflow model management is based on a structured workflow lifecycle and leverages recent advances in model management and case-based reasoning techniques. Our contributions include a conceptual model of workflow cases, a similarity flooding algorithm for workflow case retrieval, and a domain-independent AI planning approach to workflow case composition. We illustrate the workflow model management framework with a prototype system called Case-Oriented Design Assistant for Workflow Modeling (CODAW).

Convergence of knowledge management and e-learning: the GetSmart experience

The National Science Digital Library (NSDL), launched in December 2002, is emerging as a center of innovation in digital libraries as applied to education. As a part of this extensive project, the GetSmart system was created to apply knowledge management techniques in a learning environment. The design of the system is based on an analysis of learning theory and the information search process. Its key notion is the integration of search tools and curriculum support with concept mapping. More than 100 students at the University of Arizona and Virginia Tech used the system in the fall of 2002. A database of more than one thousand student-prepared concept maps has been collected with more than forty thousand relationships expressed in semantic, graphical, node-link representations. Preliminary analysis of the collected data is revealing interesting knowledge representation patterns.

Extracting gene pathway relations using a hybrid grammar: the Arizona Relation Parser

MOTIVATION Text-mining research in the biomedical domain has been motivated by the rapid growth of new research findings. Improving the accessibility of findings has potential to speed hypothesis generation. RESULTS We present the Arizona Relation Parser that differs from other parsers in its use of a broad coverage syntax-semantic hybrid grammar. While syntax grammars have generally been tested over more documents, semantic grammars have outperformed them in precision and recall. We combined access to syntax and semantic information from a single grammar. The parser was trained using 40 PubMed abstracts and then tested using 100 unseen abstracts, half for precision and half for recall. Expert evaluation showed that the parser extracted biologically relevant relations with 89% precision. Recall of expert identified relations with semantic filtering was 35 and 61% before semantic filtering. Such results approach the higher-performing semantic parsers. However, the AZ parser was tested over a greater variety of writing styles and semantic content. AVAILABILITY Relations extracted from over 600 000 PubMed abstracts are available for retrieval and visualization at http://econport.arizona.edu:8080/NetVis/index.html.

EBizPort: collecting and analyzing business intelligence information

To make good decisions, businesses try to gather good intelligence information. Yet managing and processing a large amount of unstructured information and data stand in the way of greater business knowledge. An effective business intelligence tool must be able to access quality information from a variety of sources in a variety of forms, and it must support people as they search for and analyze that information. The EBizPort system was designed to address information needs for the business/IT community. EBizPorts collection-building process is designed to acquire credible, timely, and relevant information. The user interface provides access to collected and metasearched resources using innovative tools for summarization, categorization, and visualization. The effectiveness, efficiency, usability, and information quality of the EBizPort system were measured. EBizPort significantly outperformed Brint, a business search portal, in search effectiveness, information quality, user satisfaction, and usability. Users particularly liked EBizPorts clean and user-friendly interface. Results from our evaluation study suggest that the visualization function added value to the search and analysis process, that the generalizable collection-building technique can be useful for domain-specific information searching on the Web, and that the search interface was important for Web search and browse support.

Analyzing and visualizing criminal network dynamics: A case study

Dynamic criminal network analysis is important for national security but also very challenging. However, little research has been done in this area. In this paper we propose to use several descriptive measures from social network analysis research to help detect and describe changes in criminal organizations. These measures include centrality for individuals, and density, cohesion, and stability for groups. We also employ visualization and animation methods to present the evolution process of criminal networks. We conducted a field study with several domain experts to validate our findings from the analysis of the dynamics of a narcotics network. The feedback from our domain experts showed that our approaches and the prototype system could be very helpful for capturing the dynamics of criminal organizations and assisting crime investigation and criminal prosecution.

Matching knowledge elements in concept maps using a similarity flooding algorithm

Concept mapping systems used in education and knowledge management emphasize flexibility of representation to enhance learning and facilitate knowledge capture. Collections of concept maps exhibit terminology variance, informality, and organizational variation. These factors make it difficult to match elements between maps in comparison, retrieval, and merging processes. In this work, we add an element anchoring mechanism to a similarity flooding (SF) algorithm to match nodes and substructures between pairs of simulated maps and student-drawn concept maps. Experimental results show significant improvement over simple string matching with combined recall accuracy of 91% for conceptual nodes and concept →link → concept propositions in student-drawn maps.

Visualization in law enforcement

Visualization techniques have proven to be critical in helping crime analysis. By interviewing and observing Criminal Intelligence Officers (CIO) and civilian crime analysts at the Tucson Police Department (TPD), we found that two types of tasks are important for crime analysis: crime pattern recognition and criminal association discovery. We developed two separate systems that provide automatic visual assistance on these tasks. To help identify crime patterns, a Spatial Temporal Visualization (STV) system was designed to integrate a synchronized view of three types of visualization techniques: a GIS view, a timeline view and a periodic pattern view. The Criminal Activities Network (CAN) system extracts, visualizes and analyzes criminal relationships using spring-embedded and blockmodeling algorithms. This paper discusses the design and functionality of these two systems and the lessons learned from the development process and interaction with law enforcement officers.

Topological Analysis of Criminal Activity Networks: Enhancing Transportation Security

The security of border and transportation systems is a critical component of the national strategy for homeland security. The security concerns at the border are not independent of law enforcement in border-area jurisdictions because the information known by local law enforcement agencies may provide valuable leads that are useful for securing the border and transportation infrastructure. The combined analysis of law enforcement information and data generated by vehicle license plate readers at international borders can be used to identify suspicious vehicles and people at ports of entry. This not only generates better quality leads for border protection agents but may also serve to reduce wait times for commerce, vehicles, and people as they cross the border. This paper explores the use of criminal activity networks (CANs) to analyze information from law enforcement and other sources to provide value for transportation and border security. We analyze the topological characteristics of CAN of individuals and vehicles in a multiple jurisdiction scenario. The advantages of exploring the relationships of individuals and vehicles are shown. We find that large narcotic networks are small world with short average path lengths ranging from 4.5 to 8.5 and have scale-free degree distributions with power law exponents of 0.85-1.3. In addition, we find that utilizing information from multiple jurisdictions provides higher quality leads by reducing the average shortest-path lengths. The inclusion of vehicular relationships and border-crossing information generates more investigative leads that can aid in securing the border and transportation infrastructure.

Element matching in concept maps

Concept maps (CM) are informal, semantic, node-link conceptual graphs used to represent knowledge in a variety of applications. Algorithms that compare concept maps would be useful in supporting educational processes and in leveraging indexed digital collections of concept maps. Map comparison begins with element matching and faces computational challenges arising from vocabulary overlap, informality, and organizational variation. Our implementation of an adapted similarity flooding algorithm improves matching of CM knowledge elements over a simple string matching approach.

Aggregating automatically extracted regulatory pathway relations

Automatic tools to extract information from biomedical texts are needed to help researchers leverage the vast and increasing body of biomedical literature. While several biomedical relation extraction systems have been created and tested, little work has been done to meaningfully organize the extracted relations. Organizational processes should consolidate multiple references to the same objects over various levels of granularity, connect those references to other resources, and capture contextual information. We propose a feature decomposition approach to relation aggregation to support a five-level aggregation framework. Our BioAggregate tagger uses this approach to identify key features in extracted relation name strings. We show encouraging feature assignment accuracy and report substantial consolidation in a network of extracted relations