Electroencephalogram　(EEG)　is　a　nonlinear　signal　that　reflects　the　physio-logical　state　of　the　brain　at　different　times,　containing　rich　information.　However,　the　possible　interference　during　the　collection　and　transmission　process　often　leads　to　a　large　amount　of　unnecessary　noise　in　the　EEG　signal.　Traditional　denoising　methods　may　face　difficulties　in　high-dimensional　data　processing　and　the　inability　to　effectively　handle　different　types　of　Gaussian　white　noise.　To　better　eliminate　the　interference　of　Gaussian　white　noise,　this　article　specifically　adopts　the　Hierarchical　Rauch-Tung-Striebel　Smoother　(HRTS)　method.　This　method　can　effectively　integrate　the　learned　structural　prior　EEG　signals　into　the　state　space　model,　thereby　describing　the　relationship　between　EEG　signals　and　noise.　Capture　the　spatiotemporal　characteristics　of　EEG　signals　through　hierarchical　modeling,　and　optimize　the　components　of　EEG　signals　through　estimation　and　prediction　of　hidden　variables.　Finally,　the　mean　square　error　(MSE)　is　used　as　an　evaluation　indicator　to　compare　and　evaluate　the　denoising　results.　Empirical　research　has　shown　that　the　HRTS　algorithm　can　not　only　effectively　reduce　runtime　and　better　process　high-dimensional　data,　but　also　significantly　improve　the　quality　of　EEG　signals,　effectively　suppress　noise　interference,　and　more　accurately　reflect　the　characteristics　of　brain　activity.　Compared　to　denoising　algorithms　such　as　Kalman　filtering　and　Kalman　wavelet　filtering,　the　HRTS　algorithm　has　more　advantages　in　denoising　EEG　signals.　©　2024,　J.　Network　Intell.　All　rigjts　reserved.