Improving Eye Motion Sequence Recognition Using Electrooculography Based on Context-Dependent HMM

Table 2

An example of the use of mono-, bi-, and tri-eye motion units to represent the motion sequence “up, down, up, center.” “p − t” means that “p” is the motion preceding the target motion “t” and “t + s” means that “s” is the motion succeeding “t.”

Type of unit	Corresponding representation
Mono	Up, down, up, center
Bi	Up, up-down, down-up, up-center
Tri	Up + down, up-down + up, down-up + center, up-center