ALBERT

Description: Coded-aperture imaging is a technique for imaging sources that emit high-energy radiation. This type of imaging involves shadow casting and not reflection or refraction. High-energy sources exist in x ray and gamma-ray astronomy, nuclear reactor fuel-rod imaging, and nuclear medicine. Of these three areas nuclear medicine is perhaps the most challenging because of the limited amount of radiation available and because a three-dimensional source distribution is to be determined. In nuclear medicine a radioactive pharmaceutical is administered to a patient. The pharmaceutical is designed to be taken up by a particular organ of interest, and its distribution provides clinical information about the function of the organ, or the presence of lesions within the organ. This distribution is determined from spatial measurements of the radiation emitted by the radiopharmaceutical. The principles of imaging radiopharmaceutical distributions with coded apertures are reviewed. Included is a discussion of linear shift-variant projection operators and the associated inverse problem. A system developed at the University of Arizona in Tucson consisting of small modular gamma-ray cameras fitted with coded apertures is described.

Description: Certification trails are a recently introduced and promising approach to fault-detection and fault-tolerance. A comprehensive attempt to assess experimentally the performance and overall value of the method is reported. The method is applied to algorithms for the following problems: huffman tree, shortest path, minimum spanning tree, sorting, and convex hull. Our results reveal many cases in which an approach using certification-trails allows for significantly faster overall program execution time than a basic time redundancy-approach. Algorithms for the answer-validation problem for abstract data types were also examined. This kind of problem provides a basis for applying the certification-trail method to wide classes of algorithms. Answer-validation solutions for two types of priority queues were implemented and analyzed. In both cases, the algorithm which performs answer-validation is substantially faster than the original algorithm for computing the answer. Next, a probabilistic model and analysis which enables comparison between the certification-trail method and the time-redundancy approach were presented. The analysis reveals some substantial and sometimes surprising advantages for ther certification-trail method. Finally, the work our group performed on the design and implementation of fault injection testbeds for experimental analysis of the certification trail technique is discussed. This work employs two distinct methodologies, software fault injection (modification of instruction, data, and stack segments of programs on a Sun Sparcstation ELC and on an IBM 386 PC) and hardware fault injection (control, address, and data lines of a Motorola MC68000-based target system pulsed at logical zero/one values). Our results indicate the viability of the certification trail technique. It is also believed that the tools developed provide a solid base for additional exploration.

Description: Computational grids provide users with many possible places to execute their applications. We wish to help users select where to run their applications by providing predictions of the execution times of applications on space shared parallel computers and predictions of when scheduling systems for such parallel computers will start applications. Our predictions are based on instance based learning techniques and simulations of scheduling algorithms. We find that our execution time prediction techniques have an average error of 37 percent of the execution times for trace data recorded from SGI Origins at NASA Ames Research Center and that this error is 67 percent lower than the error of user estimates. We also find that the error when predicting how long applications will wait in scheduling queues is 95 percent of mean queue wait times when using our execution time predictions and this is 57 percent lower than if we use user execution time estimates.