A-mode　ultrasound,　like　other　biological　signals,　has　a　certain　deviation　in　the　signals　obtained　by　performing　the　same　gesture　at　different　arm　positions.　This　problem　hinders　the　clinical　application　of　gesture　recognition　based　on　A-mode　ultrasound.　To　tackle　this　problem,　we　propose　the　linearly　enhanced　training　(LET)　procedure　to　compensate　for　the　deviation　of　gesture　signals　after　forearm　position　changes.　The　training　set　does　not　contain　the　gesture　data　of　the　new　position,　so　no　additional　training　is　required.　Instead,　we　determine　the　scale　parameters　to　construct　enhanced　features　for　the　new　positions　by　the　original　position　gesture　features.　We　tested　the　method　on　10　gestures　after　the　forearm　angle　is　changed.　Results　show　that　the　classification　accuracy　can　be　improved　by　7.8%　and　9.4%　after　the　forearm　bent　and　stretched　40　degrees　respectively.　Since　the　LET　procedure　is　a　step　between　feature　extraction　and　model　construction,　it　is　suitable　for　various　features　and　algorithms,　offering　a　multi-scene　solution　based　on　wearable　A-mode　ultrasound.