Active and dynamic multi-sensor information fusion method based on Dynamic Bayesian Networks

2009 ◽  
Author(s):  
Pengxin Han ◽  
Rongjun Mu ◽  
Naigang Cui
Keyword(s):  
Bayesian Networks ◽  
Information Fusion ◽  
Dynamic Bayesian Networks ◽  
Fusion Method ◽  
Sensor Information

Sensor Data Fusion for Location Awareness

2007 ◽  
pp. 863-869
Author(s):  
O. Sekkas ◽  
S. Hadjiefthymiades ◽  
E. Zervas
Keyword(s):  
Data Fusion ◽  
Bayesian Networks ◽  
Dynamic Bayesian Networks ◽  
Sensor Data ◽  
Rfid Tags ◽  
Location Awareness ◽  
The Past ◽  
Accuracy And Precision ◽  
Multiple Sensor ◽  
Sensor Information

During the past few years, several location systems have been proposed that use multiple technologies simultaneously in order to locate a user. One such system is described in this article. It relies on multiple sensor readings from Wi-Fi access points, IR beacons, RFID tags, and so forth to estimate the location of a user. This technique is known better as sensor information fusion, which aims to improve accuracy and precision by integrating heterogeneous sensor observations. The proposed location system uses a fusion engine that is based on dynamic Bayesian networks (DBNs), thus substantially improving the accuracy and precision.

A Smart Recognition Method for Otological Drill Milling through a Bone Tissue Wall

2014 ◽  
Vol 571-572 ◽  
pp. 331-338
Author(s):  
Xi Sheng Li ◽  
Yong Ming Xie ◽  
Zhi Qiang Gao ◽  
Guo Dong Feng
Keyword(s):  
Bone Tissue ◽  
Information Fusion ◽  
Recognition Rate ◽  
Fusion Method ◽  
Recognition Method ◽  
Ear Surgery ◽  
Minimally Invasive Operation ◽  
Average Recognition Rate ◽  
Sensor Information ◽  
Medical Equipments

Surgeons are striving to achieve higher quality results in minimally invasive operation. Intelligent medical equipments are able to improve operation safety. Otological drill milling through a bone tissue wall is a common milling fault in ear surgery. In this paper a multi-sensor information fusion method for identifying milling faults is presented. Five surgeons experimented on calvarian bones using the intelligent otological drill. The average recognition rate of milling faults was 91%, and only 0.8% of normal millings were identified as milling faults.

Sign in / Sign up

Export Citation Format

Share Document