A Non-Kinetic Behavior Modeling for Pilots Using a Hybrid Sequence Kernel
Yerim Choi, Sungwook Jeon, Cheolkyu Jee, Jonghun Park, Dongmin Shin · Journal of the Korea Institute of Military Science and Technology · 2014
For decades, modeling of pilots has been intensively studied due to its advantages in reducing costs for trainingand enhancing safety of pilots. In particular, research for modeling of pilots??? non-kinetic behaviors which refer tothe decisions made by pilots is beneficial as the expertise of pilots can be inherent in the models. With the recentgrowth in the amount of combat logs accumulated, employing statistical learning methods for the modelingbecomes possible. However, the combat logs consist of heterogeneous data that are not only continuous or discretebut also sequence independent or dependent, making it difficult to directly applying the learning methods withoutmodifications. Therefore, in this paper, we present a kernel function named hybrid sequence kernel which addressesthe problem by using multiple kernel learning methods. Based on the empirical experiments by using combat logsobtained from a simulator, the proposed kernel showed satisfactory results.