Patrick R. Harrison

A knowledge-based expert system for inferring vegetation characteristics

Abstract The overall goal of the research is to develop a robust extraction technique for inferring physical and biological surface properties of vegetation using nadir and/or directional reflectance data as input. A prototype knowledge-based expert system VEG is described that concentrates on extracting spectral hemispherical reflectance using any combination of nadir and/or directional reflectance data as input. VEG is designed to facilitate expansion to handle other inferences regarding vegetation properties such as total hemispherical reflectance, per cent ground cover, leaf area index, biomass, and photosynthetic capacity. This approach is more accurate and robust than conventional extraction techniques developed by the investigator and others. VEG combines methods from remote sensing and Artificial Intelligence (AI), It integrates input spectral measurements with diverse knowledge bases available from the literature, data sets of directional reflectance measurements, and from experts, into an intell...

Learning class descriptions from a data base of spectral reflectance with multiple view angles

A program was developed to learn class descriptions from positive and negative training examples of spectral, directional reflectance data taken from natural surfaces such as bare soil, natural vegetation, or agricultural vegetation. The learning program combined a form of learning referred to as a learning by example with the generate and test paradigm to provide a robust learning environment that could handle error prone data. The learning program was tested by having it learn class descriptions of various categories of percent ground cover and plant height. These class descriptions were used to classify an array of targets. The class descriptions in this program comprised a series of different relationships between combinations of directional view angles, e.g., (30,50), (45,60), (10,180), etc. Where the values in parentheses are for zenith and relative azimuth view angles for a particular view. The program found the sequence of relationships that contained the most important information that distinguished the classes. The concept being learned was a sequence of relationships that optimized the discrimination of a class. >

Extension of off-nadir view angles for directional sensor systems

Abstract A knowledge-based system called VEG was expanded to infer nadir or any off-nadir reflectance(s) of a vegetation target given any combination of other directional reflectance(s) of the target. VEG determines the best techniques to use in an array of techniques, applies the techniques to the target data, and provides a rigorous estimate of the accuracy of the inference(s). The knowledge-based system, VEG, facilitates the use of diverse knowledge bases to be incorporated into the inference techniques. In this study, VEG used additional information to make more accurate view-angle extension techniques than the traditional techniques that only use spectral data from the unknown target. VEG used spectral data and a normalized difference technique to infer the percentage of ground cover of the unknown target. This estimate of percentage of ground cover of the unknown target along with information on the sun angle were then used to search a historical data base for targets that match the unknown target in these characteristics. This data captured the general shape of the reflectance distribution of the unknown target. This historical information was used to estimate the coefficients of the techniques for the conditions at hand and to test the accuracy of the techniques. The tests used in this study were difficult ones. For example, techniques were tested that make long angular extensions using one, two, or four input view angles to predict an unknown nadir value. Furthermore, a wide variety of unknown targets were tested. The errors (±proportional rms) obtained were on the order of 0.15. In addition techniques were tested that use seven or nine multiple view angles to predict the entire hemispherical reflectance distribution of an unknown target. The accuracy of these tests was relatively good considering the relatively dynamic and noisy nature of directional reflectance distributions. The accuracy of the techniques in this study depends on the smoothness of the historical reflectance distributions and the amount of historical data available that closely matches the unknown target.

Towards standards for the validation of expert systems

Abstract The paper provides a basis for the standardization of the validation of knowledge-based systems. The place of validation within the development process is discussed and a model is proposed. Knowledge-based system validation problems are decomposed using sequences of independent and dependent generic tasks. A model for validation of KBS causal processes as well as performance outcomes is presented. Practical applications to real systems are described.

Developing and maintaining an effective assessment program

The increased emphasis on assessment by regional accrediting bodies and the Computing Accreditation Commission of ABET has caused institutions of higher education and computer science departments to seriously consider the tools and techniques they are using to evaluate their programs effectiveness. The current shortage of computer science professors at many schools has greatly reduced the time available to develop and maintain an effective assessment program. Successful assessment programs require the development of a variety of carefully chosen and properly timed assessment instruments to be effective and yet avoid overburdening faculty. Successful assessment also requires a process model that carefully builds faculty support for the assessment process.

VEG: Intelligent workbench for studying earth's vegetation

Abstract The purpose of this paper is to describe VEG, an intelligent workbench for remote sensing scientists. VEG assists scientists in the analysis of optical reflectance data. VEG was designed to manage complexity, provide intelligent support, provide visualization tools, and contract the time required for a scientist studying the earths vegetation to run exploratory studies, test alternative hypotheses, do what if thinking, and manage large data sets. VEG organizes and provides coherence to a diverse set of techniques and tools that are used by these scientists. It codifies in knowledge-based system components, heuristic knowledge used by these scientists when doing scientific work. The VEG system saves the scientist many hours of laborious calculation, and it empowers the scientist by allowing him or her to work quickly at a higher level of abstraction without the need to focus attention on a multitude of low-level tasks. The VEG system includes rule-based components, data management tools, technique design and management tools, browsers, graphics support, a highly visual interface, and a system for organizing and managing problem histories.