The　capability　of　constructing　structural　features　of　EEG　stream　has　long　been　pursued　to　track　the　events　and　abnormalities　correlating　multiple　data　domains　in　a　variant　time　scale,　thus　their　evolution　and/or　causality　may　be　better　interpreted　in　connection　with　the　EEG　monitoring　scenarios.　However,　how　to　adapt　to　the　increasingly　uncertain　complexity　of　an　up　-scaling　EEG　tensor　still　remains　an　open　issue　in　the　derivation　of　the　feature　factors.　This　study　then　develops　a　framework　of　Component　-Increased　Dynamic　Tensor　Decomposition　for　this　task　(namely　CIDTD　),　which　centers　on　an　algorithm　fusing　existing　feature　factors　and　the　features　of　the　increment　at　each　examination　point:　(1)　complementing　missing　feature　factors　(increase　in　rank　),　and　(2)　optimizing　temporal　factor　matrix　and　non　-temporal　factor　matrices　alternately　based　on　the　increment　regulated　by　factor　matrices　of　other　modes.　Benchmark　experiments　have　been　conducted　to　validate　CIDTD　＇s　ability　to　handle　variable　-length　incremental　windows　during　one　single　trial.　In　terms　of　performance,　the　results　demonstrate　that　CIDTD　outperforms　its　counterparts　by　achieving　up　to　a　6.51%　improvement　in　fitness　and　faster　average　runtime　per　examination　point　compared　to　state-of-theart　algorithms.　A　case　study　on　the　CHB-MIT　dataset　shows　that　the　feature　factors　constructed　by　CIDTD　can　better　characterize　the　epileptic　EEG　dynamics　than　counterparts　do,　in　particular　with　emerging　abnormalities　well　captured　by　new　feature　factors　in　an　up　-scaled　examination.　Overall,　the　proposed　solution　excels　in　(1)　supporting　general　streaming　tensor　decomposition　when　rank　has　to　increase　and　(2)　capturing　abnormalities　in　EEG　streams　with　high　accuracy,　robustness,　and　interpretability.