TY - GEN
T1 - Tradeoffs between quality of results and resource consumption in a recognition system
AU - DeVore, M.
AU - Chamberlain, R.
AU - Engel, G.
AU - O'Sullivan, J.
AU - Franklin, M.
N1 - Publisher Copyright:
© 2002 IEEE.
PY - 2002
Y1 - 2002
N2 - The implementation of computational systems to perform challenging operations often involves balancing the performance specification, system throughput, and available system resources. For problems of automatic target recognition (ATR), these three quantities of interest are the probability of classification error, the rate at which regions of interest are processed, and the capabilities of the underlying hardware (which is a function of the available computational resources and available power). An understanding of the inter-relationships between these factors can be an aid in making informed choices while exploring competing design possibilities. Combining characterizations of ATR performance, which yield probability of classification error as a function of target model complexity, with analytical models of computational performance, which yield throughput as a function of target model complexity and available resources, we can form a set of parametric curves which relate the quality of the results to the resources consumed.
AB - The implementation of computational systems to perform challenging operations often involves balancing the performance specification, system throughput, and available system resources. For problems of automatic target recognition (ATR), these three quantities of interest are the probability of classification error, the rate at which regions of interest are processed, and the capabilities of the underlying hardware (which is a function of the available computational resources and available power). An understanding of the inter-relationships between these factors can be an aid in making informed choices while exploring competing design possibilities. Combining characterizations of ATR performance, which yield probability of classification error as a function of target model complexity, with analytical models of computational performance, which yield throughput as a function of target model complexity and available resources, we can form a set of parametric curves which relate the quality of the results to the resources consumed.
KW - Analytical models
KW - Computer errors
KW - Energy consumption
KW - Error analysis
KW - Hardware
KW - Layout
KW - Power system modeling
KW - Synthetic aperture radar
KW - Target recognition
KW - Throughput
UR - https://www.scopus.com/pages/publications/84947938707
U2 - 10.1109/ASAP.2002.1030738
DO - 10.1109/ASAP.2002.1030738
M3 - Conference contribution
AN - SCOPUS:84947938707
T3 - Proceedings of the International Conference on Application-Specific Systems, Architectures and Processors
SP - 391
EP - 402
BT - Proceedings - IEEE International Conference on Application-Specific Systems, Architectures, and Processors, ASAP 2002
A2 - Schulte, Michael
A2 - Bhattacharyya, Shuvra
A2 - Burgess, Neil
A2 - Schreiber, Robert
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - IEEE International Conference on Application-Specific Systems, Architectures, and Processors, ASAP 2002
Y2 - 17 July 2002 through 19 July 2002
ER -