John D. Hastings

Evaluating the effectiveness of exploration and accumulated experience in automatic case elicitation

Non-learning problem solvers have been applied to many interesting and complex domains. Experience-based learning techniques have been developed to augment the capabilities of certain non-learning problem solvers in order to improve overall performance. An alternative approach to enhancing pre-existing systems is automatic case elicitation, a learning technique in which a case-based reasoning system with no prior domain knowledge acquires knowledge automatically through real-time exploration and interaction with its environment. In empirical testing in the domain of checkers, results suggest not only that experience can substitute for the inclusion of pre-coded model-based knowledge, but also that the ability to explore is crucial to the performance of automatic case elicitation.

CARMA A Case-Based Rangeland Management Adviser

CARMA is an advisory system for rangeland grasshopper infestations that demonstrates how AI technology can deliver expert advice to compensate for cutbacks in public services. CARMA uses two knowledge sources for the key task of predicting forage consumption by grasshoppers: (1) cases obtained by asking a group of experts to solve representative hypothetical problems and (2) a numeric model of rangeland ecosystems. These knowledge sources are integrated through the technique of model-based adaptation, in which case-based reasoning is used to find an approximate solution, and the model is used to adapt this approximate solution into a more precise solution. CARMA has been used in Wyoming counties since 1996. The combination of a simple interface, flexible control strategy, and integration of multiple knowledge sources makes CARMA accessible to inexperienced users and capable of producing advice comparable to that produced by human experts. Moreover, because CARMA embodies diverse forms of expertise, it has been used in ways that its developers did not anticipate, including pest management research, development of industry strategies, and in-state and federal pest-management policy decisions.

CARMA: Assessing Usability through a Non-Biased Online Survey Technique

CARMA is an advisory and research support tool for grasshopper infestations. Designed with usability as a primary goal, CARMA presents an interface so intuitive that it completely eliminates the need for a user manual. To achieve this goal, CARMA interacts with the user through a goal-oriented, guided style reminiscent of a natural conversation between an advice seeker and an expert. Usability is furthered by its modeling of four important characteristics of human expert problem solving (speed, graceful degradation, explanations, and opportunism). In order to gain non-biased user feedback about CARMAs interface, we surveyed a group of novice users not previously familiar with CARMA. Positive survey results suggest that CARMAs approach to usability is a success. Furthermore, our survey approach illustrates a simple anonymous online technique which elicits candid non-biased feedback from participants about a product, and is particularly applicable to practitioners short on staff or time.

Sustainability of Grasshopper Management and Support through CARMA

CARMA is an advisory system for grasshopper infestations that has been successfully used since 1996. During CARMA’s history, grasshopper control has increasingly focused on environmentally friendly and sustainable strategies. In order to keep pace with and support emerging strategies, CARMA’s functionality has been enhanced in a manner which both improves maintainability and which expands CARMA beyond its original role as a grasshopper infestation advisor into that of a grasshopper research support tool. This paper details efforts to develop sustainable grasshopper management strategies and the role that CARMA has played and continues to play in supporting the development and implementation of those strategies.

A cross-curricular approach to fostering innovation such as virtual reality development through student-led projects

As the Computer Science (CS) Curricula 2013 report states, CS programs should prepare students “for the workforce in a more holistic way than simply conveying technical facts. Indeed, soft skills (such as teamwork, verbal and written communication, time management, problem solving, and flexibility) and personal attributes (such as risk tolerance, collegiality, patience, work ethic, identification of opportunity ...) play a critical role in the workplace.” It also states that CS programs must “expose students to multiple programming languages, tools, paradigms, and technologies as well as the fundamental underlying principles”. Meeting all of these curricular goals is a challenge, especially for small CS programs, where resources are limited. This paper describes a model for enabling student innovation through the use of student-led projects, across the CS curriculum, within several foundational CS courses and as part of the senior design course. To illustrate how this model incorporates emerging technologies, sample student-led Virtual Reality (VR) projects are described. Results show student-led projects promote learning and help students express creativity and innovation while developing their soft skills and personal attributes. Additionally, this approach instills a culture of creativity and innovation embraced by the CS student body, where advanced students assist newer students as they embark on their journey; and it has had a significant impact on retaining CS students.

Early Assessment of an Approach to Determining the Predictive Coverage of Case-Based Reasoning with Adaptation through CARMA

CARMA is a decision-support system for managing grasshopper infestations which uses an approach called approximate-model-based adaptation whereby case-based reasoning (CBR) provides an approximate solution and model-based reasoning adapts this approximation into a precise solution. CARMAs predictive accuracy on a set of known cases confirmed the ability of the technique. The evaluation was not expanded beyond the initial set of known cases due to the human effort involved in constructing such cases. We provide an overview of CARMA, and detail initial attempts to establish a process for the automatic evaluation of such systems in order to identify potential gaps in predictive coverage using Monte Carlo methods. We propose that any generated situation which produces large adjustments in prediction during adaptation suggests a potential gap in the predictive ability of a CBR system. This represents an extension of prior CBR work which considers only the matching stage when evaluating predictive coverage.