Target Motion Sequence Detection Using Hidden Markov Models
Zhengxiang Ma, Xu Zhang, Hongchuan Wei, Shuping Dang, Rakinder Kalsi · International Journal of Hybrid Information Technology · 2017
This paper assesses the application of Hidden Markov Models (HMMs) in obtaining the most likely sequence of distributions one target chooses in the problem of a geometric, transversal approach to optimizing the probability of tracking maneuvering targets.Several factors that might affect the performance of the HMMs are considered in this paper.These include the number of time intervals, the overlapping of distributions, the symmetry of distributions, the number of distributions per time interval, the numbers of the types of distribution the target chooses from, and the dependence of distributions between time intervals.It is shown that the effects of these factors on the performance of HMMs by comparing the outcomes of problems whose settings are the same against the factor considered in that instance.