Multisensor Fusion and Integration in the Wake of Big Data, Deep Learning and Cyber Physical System by Sukhan Lee Hanseok Ko & Songhwai Oh

Author:Sukhan Lee, Hanseok Ko & Songhwai Oh
Language: eng
Format: epub
Publisher: Springer International Publishing, Cham

(4)

Step 5: Based on the final score obtained in Eq. (4), the final classification decision for the testing sample can be made according to Eq. (5):

(5)

When we finish the above steps, we can obtain all the class labels of the testing samples.

The classifier base on CTSP can use more information. Therefore, better classification performance can be expected. However, its output is only the class label, which has no more detailed information on the sample’s class belongingness.

To further improve the fusion of the outputs of member classifiers, we attempt to model the outputs in the measurement level. In step 4, we obtain a score value matrix , and we use it to represent the possibility of the testing sample belonging to the corresponding class. Then, the member classifier’s output is transformed from the abstract level into the measurement level. Furthermore, evidential reasoning based OWA approaches are used to implement the MCS and obtain the final classification result.

Download

Copyright Disclaimer:
This site does not store any files on its server. We only index and link to content provided by other sites. Please contact the content providers to delete copyright contents if any and email us, we'll remove relevant links or contents immediately.