Jon Sticklen

Knowledge-based segmentation of Landsat images

A knowledge-based approach for Landsat image segmentation is proposed. The image segmentation problem is solved by extracting kernel information from the input image to provide an initial interpretation of the image and by using a knowledge-based hierarchical classifier to discriminate between major land-cover types in the study area. The proposed method is designed in such a way that a Landsat image can be segmented and interpreted without any prior image-dependent information. The general spectral land-cover knowledge is constructed from the training land-cover data, and the road information of an image is obtained through a road-detection program. >

‘Deep’ models and their relation to diagnosis

Abstract In this paper we distinguish between deep models in the sense of scientific first principles and deep cognitive models where the problem solver has a qualitative symbolic representation of the system or device that accounts for how the system ‘works’. We analyze diagnostic reasoning as an information processing task, identifying the generic types of knowledge (and reasoning) needed for the task to be performed adequately. If these are available, an integrated collection of generic problem solvers can produce a diagnostic conclusion. The need for deep or causal models arises when some or all of these types of knowledge are missing in the problem solver. We provide a typology of different knowledge structures and reasoning processes that play a role in qualitative or functional reasoning and elaborate on functional representations as deep cognitive models for some aspects of causal reasoning in medicine.

Integrating classification-based compiled level reasoning with function-based deep level reasoning

Problem solving based on compiled associations between elements of the decision space and data is an efficient mode of reasoning for a large percentage of situations faced by an expert. But in some (usually small) percentage of cases, compiled associations are not enough by themselves to lead to correct results. Reasoning from “deeper” levels of understanding offers the advantage of producing correct results even in atypical cases, but at the cost of expanding more computational resources. Thus the trade-off between compiled level systems and deep level systems is between computational efficiency (at the compiled level) and problem-solving generality (at the deep level). We describe a hybrid system containing elements of both deep level reasoning and compiled level reasoning. More particularly, we propose a problem-solving architecture for category-based diagnostic problem solving which at the compiled level centers on classification problem solving and at the deep level uses a type of function-based reas...

Recommendation via Query Centered Random Walk on K-Partite Graph

This paper presents an algorithm for recommending items using a diverse set of features. The items are recommended by performing a random walk on the k-partite graph constructed from the heterogenous features. To support personalized recommendation, the random walk must be initiated separately for each user, which is computationally demanding given the massive size of the graph. To overcome this problem, we apply multi-way clustering to group together the highly correlated nodes. A recommendation is then made by traversing the subgraph induced by clusters associated with a users interest. Our experimental results on real data sets demonstrate the efficacy of the proposed algorithm.

Distributed causal reasoning

We describe an approach for understanding devices which provides leverage for the knowledge acquisition taks. In our functional approach , knowledge is acquired in three steps: the device is decomposed to an ensemble of subdevices, the functions/goals/purposes of each subdevice are stated abstractly, and finally, the way(s) each function/goal/purpose is accomplished is represented. The heart of our approach is a distribution of causal knowledge into fragments which are indexed by the functions/purposes/goals of the device. We show that the functional approach supports automated knowledge acquisition for diagnostic problem solving, and we argue that it also supports manual knowledge acquisition for device knowledge.

An integrated wheat crop management system based on generic task knowledge based systems and CERES numerical simulation

We discuss the development of an integrated problem solving architecture to capture all relevant aspects of a crop management system within one working computer program. Specifically we discuss the development of an expert system to support the management of irrigated wheat in Egypt on a regional level. Our system will capture local expertise for the management of irrigated wheat production through the integration of expert system technology and one of the premier crop simulation models used in agriculture. The system will address the various facets of management as follows: planting date selection; water utilization and management; pest monitoring, identification, and remediation; disease monitoring, identification, and remediation; and harvest management. The two major methodologies we integrate in our system are the generic task second generation expert systems methodology first developed by Chandrasekaran et al. (1986), and the CERES crop simulation methodology pioneered by Ritchie et al. (1985). The expected contributions of this research lie in two major areas. In agriculture, regional level management of cropping will allow better utilization of crop inputs, particularly water inputs. In knowledge-based systems, the major contributions of this research lie in proof of principle scale-up of a number of current problem solving templates and in the integration of expert system and quantitative simulation technologies.<<ETX>>

Multiple Design: An Extension of Routine Design for Generating Multiple Design Alternatives

Many engineering design situations require the generation of multiple designs to meet a common set of specifications. This research introduces an effective approach for generating multiple designs. The method developed utilizes and builds on the generic task approach to knowledge-based systems, as well as the specific design technique, known as Routine Design.

Integrating quantitative and qualitative computations in a functional framework

Abstract Model-based reasoning (MBR) is currently receiving widespread attention because it offers a way to circumvent the brittleness of reasoning systems built solely on associational knowledge. Initially MBR was explored under a general viewpoint of the envisonment process, although more recently, the field has broadened substantially. To date, most MBR approaches have focused on the use and manipulation of qualitative models. We report our experience in applying techniques of Functional Reasoning to the general problem of organizing quantitative calculations. As a testbed, a problem initially posed at the Model-based Diagnosis workshop held in Paris, in July, 1989 has been solved: representing an automotive cruise control system. The results show that the principles of the Functional Reasoning Approach can provide leverage in device domains characterized by quantitative data. The paper ends with a discussion of the current state of research in Model-based Reasoning.

A Framework for Developing Intelligent Tutoring Systems Incorporating Reusability

The need for effective tutoring and training is mounting, especially in industry and engineering fields, which demand the learning of complex tasks and knowledge. Intelligent tutoring systems are being employed for this purpose, thus creating a need for cost-effective means of developing tutoring systems. We discuss a novel approach to developing an Intelligent Tutoring System shell that can generate tutoring systems for a wide range of domains. Our focus is to develop an ITS shell framework for the class of Generic Task expert systems. We describe the development of an ITS for an existing expert system, which serves as an evaluation test-bed for our approach.

Fabricating composite materials-a comprehensive problem-solving architecture based on generic tasks

A problem-solving architecture that addresses the entire life cycle of composite-materials fabrication from a generic-task viewpoint is presented. Prototype systems that capture the experience-based static design of fabrication plans and the progress-control knowledge of cavity tuning for the microwave curing of composites are described. The capturing of compiled process planning in the plan design phase, the routine-design system, and monitoring, global replanning, and local reactive planning of the fabrication plan are discussed.<<ETX>>