In this paper, we describe an effort to preserve the semantics and relationships between Digital Objects content. As the system ingests the content, it has to understand and parse structures of files and packages that hold bundles of digital content. It also has to map the content to an ontology that captures domain knowledge, allowing for preservation of the relationships among incoming data while improving data access and retrieval at the later time.

The use of commercial-off-the-shelf (COTS) / government-off-the-shelf (GOTS) applications as components in software systems is increasingly prevalent. The critical step of tool selection for an integrated suite is usually based on identifying the tools that best match the functionality requirements needed. Other factors tangential to technical performance are playing a more important role in the tool selection process and making the mapping of customer needs to technical requirements less obvious. This paper suggests a shift from the traditional "best tools" selection approach, where tools are selected for their performance to a more holistic "end-to-end" approach, where customer concerns, business and cost benefits, and technical performance are weighed concurrently. The end-to-end methodology was applied to an integrated suite for the intelligence analysis process and was compared to a theoretical system employing a best tools approach. This showed that the end-to-end approach resulted in significant software related cost reductions

Rule based reasoning and case based reasoning have emerged as two important and complementary reasoning methodologies in artificial intelligence (AI). We describe the approach for the development of CORMS AI, a decision support system which employs rule-based and case-based reasoning to assist National Ocean Service watch standing personnel in monitoring the quality of incoming and outgoing marine environmental data and information. CORMS AI has proven to be robust, extendable, and cost effective. It is estimated that CORMS AI save government over one million dollars per year when its full range of quality control monitoring capabilities is implemented.

The decision support tool market has seen exponential growth in recent years, with the introduction of different tools for various applications and domains. These include tools for data mining, on-line analysis and reporting, and expert systems (rule-based and case-based systems). This paper presents an approach for evaluating and selecting intelligent decision supports tools suitable for capturing expert's knowledge and deploying this knowledge where applicable.

Multiple approaches have been developed for improving predictive performance of a system by creating and combining various learned models. There are two main approaches to creating model ensembles. The first is to create a set of learned models by applying an algorithm repeatedly to different training sample data, while the second approach applies various learning algorithms to the same sample data. The predictions of the models are then combined according to a voting scheme. This paper presents a method for combining models that was developed using numerous samples, modeling algorithms, and modelers and compares it with the alternate approaches. The results of the model combination methods are evaluated with respect to sensitivity and false alarm rates and are then compared against other approaches.

We address the problem of crafting visual routines for detection tasks. Emphasis is placed on both competition and learning to help with specific visual tasks involved in localization and identification. Crafting of visual routines presents difficult optimization problems and leads to evolutionary computation using a hybrid genetic architecture consisting of natural selection, learning, and their beneficial interactions. Base features representations and visual routines for detection represented as decision trees are evolved. The visual routine considered is that of eye detection. The experimental results reported herein prove the feasibility of our approach in terms of feature selection (data compression) and the corresponding eye detection (pattern recognition).

This paper describes a hybrid methodology that integrates genetic algorithms (GAs) and decision tree learning in order to evolve useful subsets of discriminatory features for recognizing complex visual concepts. A GA is used to search the space of all possible subsets of a large set of candidate discrimination features. Candidate feature subsets are evaluated by using C4.5, a decision tree learning algorithm, to produce a decision tree based on the given features using a limited amount of training data. The classification performance of the resulting decision tree on unseen testing data is used as the fitness of the underlying feature subset. Experimental results are presented to show how increasing the amount of learning significantly improves feature set evolution for difficult visual recognition problems involving satellite and facial image data. In addition, we also report on the extent to which other more subtle aspects of the Baldwin effect are exhibited by the system.

This paper describes an approach being explored to improve the usefulness of machine learning techniques to classify complex, real world data. The approach involves the use of genetic algorithms as a "front end" to a traditional tree induction system (ID3) in order to find the best feature set to be used by the induction system. This approach has been implemented and tested on difficult texture classification problems. The results are encouraging and indicate significant advantages of the presented approach.

Selecting a set of features which is optimal for a given task is a problem which plays an important role in wide variety of contexts including pattern recognition, adaptive control and machine learning. Experience with traditional feature selection algorithms in the domain of machine learning leads to an appreciation for their computational efficiency and a concern for their brittleness. The authors describe an alternative approach to feature selection which uses genetic algorithms as the primary search component. Results are presented which suggested that genetic algorithms can be used to increase the robustness of feature selection algorithms without a significant decrease in compuational efficiency.

An approach being explored to improve the usefulness of machine learning techniques for generating classification rules for complex, real-world data is described. The approach involves the use of genetic algorithms as a front end to a traditional rule induction system in order to identify and select the best subset of features to be used by the rule induction system. This approach has been implemented and tested on difficult texture classification problems. The results are encouraging and indicate that there are significant advantages to the approach in this domain.>