5results about How to "Strong memory" patented technology

The present invention relates to the technical field of sleep diagnosis, and in particular to a sleep staging method based on deep learning, the method comprising: collecting a number of target physiological signals, preprocessing each target physiological signal to obtain a number of standard physiological signals; synchronously aligning and integrating each standard physiological signal in turn to obtain a standard sleep data set; determining the actual correlation between each physiological signal to be integrated in the standard sleep data set, and determining an actual signal combination strategy according to the actual correlation; generating an actual sleep data set according to the actual signal combination strategy, and extracting features from the actual sleep data set to generate actual feature parameters; inputting the actual feature parameters into a deep learning model to determine the actual sleep state; analyzing the actual sleep state, and performing corresponding sleep intervention according to the analysis results. The present invention realizes low-cost non-intrusive sleep monitoring, thereby improving people's physical health.

The application belongs to the field of medical image recognition and relates to an esophageal lesion image recognition method based on a deep neural network, which comprises the following steps: step 1, processing actual digestive endoscopy video data to construct training data; step 2, constructing a deep neural network model and training the deep neural network model through the training data to obtain an early esophageal cancer recognition model; step 3, inputting digestive endoscopy video data to be detected into the early esophageal cancer recognition model, and the early esophageal cancer recognition model judging whether there is a suspected esophageal cancer lesion and outputting a lesion judgment result; the lesion judgment result comprising a spatial position and a progression stage of the lesion; the method models the time sequence dynamics of lesion characteristics in the endoscopy recognition process, and combines a graph neural network to depict the feature correlation of early esophageal squamous cell carcinoma under multi-view conditions, so as to improve the recognition accuracy, consistency and robustness of the model in a real clinical application scenario.

The invention discloses a solar-blind ultraviolet photoelectric artificial visual synaptic device based on an aluminum-yttrium-nitrogen thin film and a preparation method of the solar-blind ultraviolet photoelectric artificial visual synaptic device, and relates to the field of novel micro-nano electronic materials and functional devices. The synaptic device comprises a substrate, a bottom electrode, a solar blind ultraviolet light response resistive layer and a top electrode, the bottom electrode is arranged on the substrate and is used for introducing a solar blind ultraviolet light signal; the solar blind ultraviolet light response resistive layer is arranged between the bottom electrode and the top electrode and used for simulating synaptic plasticity. Wherein the solar-blind ultraviolet light response resistance change layer is made of an aluminum-yttrium-nitrogen film with a photoconductive effect, and has photoresponse to solar-blind ultraviolet light with the wavelength of 200-280nm; the bottom electrode is a transparent conductive electrode; an electric signal is input through the top electrode and the bottom electrode, and a solar blind ultraviolet light signal is input through the transparent conductive bottom electrode; the synaptic device provided by the invention can realize various photoelectric synaptic plasticity under the excitation of an electric signal and a solar-blind ultraviolet light signal, so that the simulation of an artificial visual function is realized on the basis of the synaptic device.

The invention discloses a method for generating a remote sensing image based on a text. NLP (Natural Language Processing) and CV (Computer Vision) technologies are fused. According to the method, a high-quality remote sensing image is generated by analyzing text description and carrying out hierarchical prototype learning and dynamic prototype learning by utilizing a dynamic hierarchical prototype block. Specifically, a text image pair is processed by an encoder to obtain a text image mark, a joint mark formed by splicing the text image pair and the text image mark is input into a dynamic hierarchical prototype layer to extract features, and the method enhances the memory and information retrieval capability of a model by combining a Hopfield network and a self-attention mechanism. Therefore, the richness and accuracy of remote sensing image feature representation are improved. Besides, a dynamic prototype learning strategy is adopted, so that the model can gradually learn and adapt to more prototypes, and higher robustness and accuracy are shown when complex data are processed. Finally, the method can generate a remote sensing image which is visually consistent with the text description and has high-quality details.

The present application relates to the field of automatic driving strategy evolution, and in particular to an end-to-end automatic driving strategy evolution method based on supervised-reinforcement joint fine-tuning, wherein the data samples of the user using the automatic driving system are divided into performance defect samples, physiological and psychological feedback samples, partial intervention samples and complete takeover samples according to feedback levels, the end-to-end automatic driving strategy evolution is realized by using a reinforcement learning fine-tuning method for the performance defect samples and the physiological and psychological feedback samples, the end-to-end automatic driving strategy evolution is realized by using a supervised learning fine-tuning method for the partial intervention samples and the complete takeover samples, a dynamic sample library is established, the memory samples are dynamically updated according to the difference degree of the samples, the memory sample loss is weighted and calculated according to the difference degree between the memory samples and the samples currently used for fine-tuning training, and finally the memory sample loss is used to perform soft constraint on the reinforcement learning fine-tuning and the supervised learning fine-tuning. The present application makes full use of multi-scene data sample flow and can continuously learn.