▎ 摘　　要

NOVELTY - The method (1500) involves obtaining multiple electrical signals from an array of electrodes implanted on multiple cortical local regions of a brain at multiple frequency bands during a time interval (1510). The average brain activity is determined for individual cortical local regions corresponding to first cortical local regions and second cortical local regions different from first cortical local regions based on the electrical signals (1520). The cortex-wide brain activity is reconstructed with pixel-level spatial resolution including a brain activity for the first and second cortical local regions at a first point in time during the first time interval using weighting scores of independent components that are obtained based on the electrical signals (1530). Electrical signals include electrocorticography (ECoG) signals. The electrodes include transparent graphene microelectrodes. The neural network algorithm includes a sequential stacking of a linear hidden layer. USE - Method for performing neural activity imaging, particularly virtually reconstructing brain-wide neural activity from local electrophysiological recordings using a recurrent neural network. ADVANTAGE - The electroencephalography (EEG) provides a broader frequency range and higher temporal and spatial resolution with spatial coverage depending on the size of the craniotomy. The decomposition provides the good demixing of cortex-wide brain activity and enables a tractable mapping from ECoG responses, which is learned by the decoding network model. DETAILED DESCRIPTION - An INDEPENDENT CLAIM is included for a device for performing neural activity imaging. DESCRIPTION OF DRAWING(S) - The drawing shows a flow diagram of the method for performing neural activity imaging. 1500Method for performing neural activity imaging 1510Obtaining multiple electrical signals from array of electrodes implanted on multiple cortical local regions of brain at multiple frequency bands during time interval 1520Determining average brain activity for individual cortical local regions corresponding to first cortical local regions and second cortical local regions different from first cortical local regions based on the electrical signals 1530Reconstructing cortex-wide brain activity with pixel-level spatial resolution including brain activity for first and second cortical local regions at first point in time during first time interval using weighting scores of independent components that are obtained based on electrical signals