Welcome to the webpage of my classes. As the semester progresses, this page will be updated. Contact me to help you decide whether a class fits your needs. Keep in mind that typically my classes have a large project at the end to accommodate various student backgrounds.

Current Semester (Spring 2009)

• Principles of Remote Sensing (4cr) Syllabus
  Code: FEG 365/ ERE 565

  Description: The class provides a qualitative and quantitative introduction to the fundamentals of acquiring, analyzing and utilizing remote sensing data in the performance of natural resource inventories, environmental quality surveys, site development studies and land use analyses. The class describes the fundamentals of remote sensing and also covers introductory concepts and methods in digital image processing and photogrammetry.

• Digital Image Analysis (3cr) Syllabus
  Code: ERE 596, Section 11

  Description: Topics covered in this class include elements of digital image processing and analysis systems: Digital image representation, visual perception, sampling and quantization, pixel connectivity, Fourier transforms, image enhancement, filtering, image segmentation, edge detection, thresholding, representation schemes, descriptors, morphology, recognition and interpretation. General programming experience and quantitative background are required. Assignments will use Matlab software package, though no prior knowledge of Matlab is required.

Past Semesters

• Spatial Analysis (3cr) Syllabus
  Code: ERE 596, Section 08

  Description: Topics covered in this course include elements of spatial statistics and modeling as applied to various data formats: single point data, continuous data and area data. The triangle visualize-explore-model will be employed with emphasis in the modeling section. Examples of taught methods include: first/second order effects, complete spatial randomness, tessellation, kernel, covariograms and variograms, kriging, distance measures, correlation/correlogram and spatial regression models. General programming experience and quantitative background are required. Assignments will use Matlab software package, though no prior knowledge of Matlab is required.

• Artificial Intelligence in Geography (1cr)
  Code: ERE 796

  Description: This course focuses on theory and applications of artificial intelligence (AI) methods to geographic problems. Methods dicussed include decision trees, fuzzy logic, neural networks (backpropagation, radial basis function, self-organizing maps), genetic algorithms and agent-based modeling.