6results about How to "Discriminating" patented technology

This invention provides a method, system, and storage medium for discriminating surface electromyography (EMG) signals in chronic low back pain based on a Fourier analysis neural network. First, a dataset is acquired, containing several EMG signals and their corresponding ground truth labels. The EMG signals are preprocessed to obtain preprocessed EMG signals. These preprocessed EMG signals are then input into a constructed Fourier analysis-based neural network to obtain a predicted label for each EMG signal. A loss function is constructed based on the ground truth labels and predicted labels, and the Fourier analysis-based neural network is trained to obtain a trained Fourier analysis-based neural network. The EMG signal to be detected is then input into the trained Fourier analysis-based neural network to obtain the corresponding predicted label. This invention, by constructing and training a Fourier analysis-based neural network, aims to extract discriminative latent periodic features, achieving automated discrimination of abnormal patterns in EMG signals of chronic low back pain, thus achieving more robust, generalizable, and efficient discrimination.

The application relates to a gait recognition network training method and system and a gait recognition method. The gait recognition network training method comprises the following steps: obtaining M groups of training data, one group of training data comprising two gait energy maps; horizontally dividing the gait energy maps into N parts; simultaneously extracting block features of the N parts of the gait energy maps through a basic convolution layer; sending the block features into a second convolution layer for processing; constructing a loss function based on the output results of the convolution layers, and supervising and training the gait recognition network through the loss function. Each image is horizontally divided and subjected to block convolution, so that even if the legs are blocked, the features of other parts are still distinguishable, and therefore the pedestrian gait recognition accuracy can be improved; the two images in each group are spliced, and block convolution is further performed on the spliced features, so that the loss function can make the features more discriminative, thereby improving the recognition accuracy of the model.

The present application relates to the technical field of pedestrian re-identification, and discloses an RGB-D cross-modal pedestrian re-identification method, system and medium based on joint cross attention, which first constructs joint RGB-D semantic representation and alignment processing to realize effective interaction between modes; a multi-stage cross attention learning strategy is introduced to gradually learn the features of each mode at multiple stages, and the interaction between modes at each stage is only realized through cross attention, and only in the last stage, the depth features of the visible light image and the visible light features of the depth image are connected, the intra-modal and inter-modal relationships are gradually modeled, and therefore more robust fused multi-modal pedestrian feature representation is obtained. Finally, the mean-max feature representation of the RGB-D mode is used to construct a joint representation at the semantic level, guide the obtained fine-grained cross-modal interaction features, and realize alignment at the semantic level. Furthermore, the heterogeneity of the cross-modal features is fitted, and more robust multi-modal pedestrian feature representation is obtained.

The invention discloses a pedestrian dangerous action recognition method based on feature enhancement, which comprises the following steps: acquiring and preprocessing a pedestrian image to be recognized through an input module to obtain initial image data, and designing a foreground enhancement module (FEM), the method can automatically highlight a key area in a worker action feature in a video monitoring scene, and reduces background noise and environmental interference. Compared with an existing method that the features of the whole image are directly input into the network, the method can achieve background suppression in the feature extraction stage, and the motion recognition model can more accurately pay attention to the motion of a worker. The improvement not only improves the accuracy of identification, but also effectively avoids the problems of erroneous judgment and missed judgment caused by a complex background, thereby improving the reliability of industrial safety monitoring.

The present application belongs to the technical field of intelligent video processing, and particularly relates to a future frame anomaly detection method based on meta learning and space-time relationship. The present application method proposes a meta learning module, and a model-based meta learning method enables the model to learn general features from multiple tasks, so that the system can learn more discriminative and generalizable feature representations from data. In different monitoring scenes and abnormal behaviors, the model can also accurately perform anomaly detection without overfitting or underfitting. The present application method introduces the meta learning module into the autoencoder, uses the learning characteristics of the meta learning module to extract, save and update the features extracted by the autoencoder, automatically acquires the feature importance of the input video frame through learning, and assigns important weights to the features that are more worthy of attention, which helps to improve the utilization rate of key features in the input stage of the future frame prediction network.

The invention discloses an indoor line series fault arc detection method based on multi-feature fusion, and the method comprises the steps: collecting a current signal at a main line of an indoor line, carrying out the normalization preprocessing of the current signal, and extracting a time domain, a frequency domain and multiple types of features of the time domain and the frequency domain, so as to comprehensively reflect the non-stationary features of the current signal. For samples under different working conditions, redundant features are removed by using an improved feature selection algorithm in combination with Pearson correlation analysis, and a final feature set with strong discrimination capability is constructed. Furthermore, an extreme learning machine model is introduced, rapid modeling and efficient classification are achieved based on a random initialization weight and a generalized inverse solution method, and high detection precision and real-time performance can be kept under complex working conditions and noise interference. The method has the advantages of being comprehensive in feature expression, efficient in model training, high in detection accuracy and high in robustness, the missing report rate and the false report rate of the indoor line series fault arc can be effectively reduced, and the safety and the reliability of an electrical system are improved.