Functional　electrical　stimulation　(FES)　provides　an　effective　way　for　foot　drop　(FD)　correction.　To　overcome　the　redundant　and　blind　stimulation　problems　in　the　state-of-the-art　methods,　this　study　proposes　a　closed-loop　scheme　for　an　adaptive　electromyography　(EMG)-modulated　stimulation　profile.　The　developed　method　detects　real-time　angular　velocity　during　walking.　It　provides　feedbacks　to　a　long　short-term　memory　(LSTM)　neural　network　for　predicting　synchronous　tibialis　anterior　(TA)　EMG.　Based　on　the　prediction,　it　modulates　the　stimulation　intensity,　taking　into　account　of　the　subject-specific　dead　zone　and　saturation　of　the　electrically　evoked　activation.　The　proposed　method　is　tested　on　ten　able-bodied　participants　and　six　FD　subjects　as　proof　of　concept.　The　experimental　results　show　that　the　proposed　method　can　successfully　induce　the　dorsiflexion　of　the　ankle　joint,　and　generate　an　activation　pattern　similar　to　a　natural　gait,　with　the　mean　Correlation　Coefficient　of　0.9021.　Thus,　the　proposed　method　has　the　potential　to　help　patients　to　retrieve　normal　gait.