DocumentCode :
3284272
Title :
Evaluating Fisher Information From Data for Task-Driven Data Compression
Author :
Fowler, Mark L. ; Chen, Mo
Author_Institution :
Dept. of Electr. & Comput. Eng., SUNY, Binghamton, NY
fYear :
2006
fDate :
22-24 March 2006
Firstpage :
967
Lastpage :
972
Abstract :
Sensor networks and other multi-sensor systems collect data upon which estimations are based. How a particular sensor´s data is to be used within the sensor system depends on the quality of that sensor´s data relative to the other sensor´s data. Because Fisher information (FI) is a natural way to assess the quality of a sensor´s data, it is desirable to be able to numerically compute the FI for a collected set of data for a specific estimation task. We explore this issue for the specific scenario of FI-driven data compression for a sensor system tasked with estimating an RF emitter´s location. The data compression scheme uses sub-band coding and therefore for FI-driven data compression it is important to numerically assess the FI of each filter bank output sample. However, as we demonstrate, an orthogonal filter bank well-suited to the compression task seems ill-suited to the FI-assessment task. Alternatively we demonstrate that the STFT is well-suited to FI-assessment but-as is well known-is ill-suited to the compression task. This leads to a hybrid structure for the sub-band coding scheme that uses the STFT for time-frequency domain assessment of the FI but retains the orthogonal filter bank for the compression processing.
Keywords :
Fourier transforms; channel bank filters; data compression; sensor fusion; time-frequency analysis; Fisher information; STFT; orthogonal filter bank; sensor network; short-term Fourier transform; subband coding; task-driven data compression; time-frequency domain assessment; Data compression; Data Compression; Filter Banks; Fisher Information; TDOA/FDOA Emitter Location;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Information Sciences and Systems, 2006 40th Annual Conference on
Conference_Location :
Princeton, NJ
Print_ISBN :
1-4244-0349-9
Electronic_ISBN :
1-4244-0350-2
Type :
conf
DOI :
10.1109/CISS.2006.286606
Filename :
4067947
Link To Document :
بازگشت