Data fusion technologies for multisensor biological agent detection. Final report, October 1993-February 1994
This report surveys some important data fusion technologies that are applicable to biological agent detection. Data fusion is the automation of processes to combine diverse sets of sensed information. In a multiple-instrument environment, automation of the data processing is required in order to avoid overwhelming the operator with instrumental output and to produce conclusions in a timely manner. Sensor output can be fused at different levels. At the data level, the outputs of different sensors are directly combined. Other methods fuse feature vectors. If data is not available to create fused feature vectors, decision-level algorithms can be used, but it is preferable to fuse at the earliest possible level. Knowledge-based systems provide an alternate approach to the data fusion problem, especially when non-numerical data is available. Blackboard architectures are a useful framework for the integration of multiple algorithms and methods.
- Research Organization:
- Edgewood Research, Development and Engineering Center, Aberdeen Proving Ground, MD (United States)
- OSTI ID:
- 7125209
- Report Number(s):
- AD-A-282633/7/XAB; ERDEC-TR--167
- Country of Publication:
- United States
- Language:
- English
Similar Records
A hierarchical structure approach to MultiSensor Information Fusion
A hierarachical data structure representation for fusing multisensor information
Related Subjects
450600* -- Military Technology
Weaponry
& National Defense-- Chemical & Biological-- (1990)
99 GENERAL AND MISCELLANEOUS
990200 -- Mathematics & Computers
BIOLOGICAL WARFARE AGENTS
COMPUTER CALCULATIONS
DETECTION
DOCUMENT TYPES
KNOWLEDGE BASE
PROGRESS REPORT
TECHNOLOGY ASSESSMENT
WEAPONS