Accurate　and　real-time　gesture　recognition　is　required　for　the　autonomous　operation　of　prosthetic　hand　devices.　This　study　employs　a　convolutional　neural　network-enhanced　channel　attention　(CNN-ECA)　model　to　provide　a　unique　approach　for　surface　electromyography　(sEMG)　gesture　recognition.　The　introduction　of　the　ECA　module　improves　the　model＇s　capacity　to　extract　features　and　focus　on　critical　information　in　the　sEMG　data,　thus　simultaneously　equipping　the　sEMG-controlled　prosthetic　hand　systems　with　the　characteristics　of　accurate　gesture　detection　and　real-time　control.　Furthermore,　we　suggest　a　preprocessing　strategy　for　extracting　envelope　signals　that　incorporates　Butterworth　low-pass　filtering　and　the　fast　Hilbert　transform　(FHT),　which　can　successfully　reduce　noise　interference　and　capture　essential　physiological　information.　Finally,　the　majority　voting　window　technique　is　adopted　to　enhance　the　prediction　results,　further　improving　the　accuracy　and　stability　of　the　model.　Overall,　our　multi-layered　convolutional　neural　network　model,　in　conjunction　with　envelope　signal　extraction　and　attention　mechanisms,　offers　a　promising　and　innovative　approach　for　real-time　control　systems　in　prosthetic　hands,　allowing　for　precise　fine　motor　actions.