Abstract: A method for extracting f wave from a single-lead electrocardiography signal is provided. The method includes: establishing a two-channel temporal convolutional neural network model, including two coding submodules, two mask estimation submodules, an information fusion module and two decoding submodules; constructing a training data set of ECG signals; training the two-channel temporal convolutional neural network model, and saving the trained model. The two-channel temporal convolution neural network encodes and decodes a QRST complex and the f wave respectively, and uses a mask of information fusion to estimate and construct regular items to restrict a distribution difference of QRST component coding features, so as to reduce the distortion of the QRST complex, select potential features of a QRST complex and f wave with high signal-to-noise ratio, and thus improve a detection accuracy of the f wave.

Abstract: The present invention belongs to the field of genetic engineering, and particularly relates to a genetically engineered dual-targeting chimeric antigen receptor. The present invention provides a genetically engineered dual-targeting chimeric antigen receptor and a host cell thereof in response to up-regulated expression of PD-L1 in tumor cells and immune cells after these cells are exposed to malignant serosal cavity effusion. The dual-targeting chimeric antigen receptor provided by the present invention competitively binds to PD-L1 to transform an inhibition signal of PD-L1 into an activation signal and to enhance the killing activity of T cells; meanwhile, 4-1BB introduced downstream thereof can promote proliferation and survival of T cells. In addition, the present invention also discloses a host cell expressing the above dual-targeting antigen receptor and a use thereof in preventing or treating solid tumors.

Abstract: A method for extracting f wave from a single-lead electrocardiography signal is provided. The method includes: establishing a two-channel temporal convolutional neural network model, including two coding submodules, two mask estimation submodules, an information fusion module and two decoding submodules; constructing a training data set of ECG signals; training the two-channel temporal convolutional neural network model, and saving the trained model. The two-channel temporal convolution neural network encodes and decodes a QRST complex and the f wave respectively, and uses a mask of information fusion to estimate and construct regular items to restrict a distribution difference of QRST component coding features, so as to reduce the distortion of the QRST complex, select potential features of a QRST complex and f wave with high signal-to-noise ratio, and thus improve a detection accuracy of the f wave.