605 results about "Auto encoders" patented technology

A system and method for multi-scale temporal attention processing in multimodal technology deep learning systems. This system processes time-series, textual, sentiment, and structured tabular data across three hierarchically-organized temporal streams—quarterly, weekly, and intraday levels—with bidirectional cross-temporal information flow. Scale-specific attention mechanisms are optimized for respective temporal granularities, while an adaptive controller dynamically weights each temporal level based on real-time market volatility indicators. A multi-scale fusion processor integrates attention-weighted representations to generate temporally unified representations preserving both short-term market dynamics and long-term trends. This approach enables superior forecasting and risk assessment by leveraging temporal correlations across multiple time scales while automatically adapting to changing market conditions. The system facilitates interpretable AI analysis through attention visualization and enables synthetic scenario generation for model testing.

A method is provided for enhanced data routing in neural networks using Self-Organizing Maps (SOM) integrated with Autoencoder-GAN. The method comprises training an autoencoder to encode input data into a latent space representation; applying a Self-Organizing Map (SOM) to organize the latent space representation into a topological map; refining the latent space representation using a Generative Adversarial Network (GAN), wherein the generator generates enhanced latent space representations and the discriminator evaluates their quality; using the refined latent space representations to update the SOM topology dynamically; generating routing coefficients based on the updated SOM topology to guide data routing in a capsule network; and dynamically adjusting routing within the capsule network using the generated routing coefficients to enhance performance based on the refined latent representations.

A system and method for adaptive real-time multi-modal compression with dynamic resource allocation provides intelligent compression optimization based on continuously monitored device conditions. The system monitors battery level, CPU utilization, and memory availability while classifying incoming multi-modal data streams comprising image, audio, text, and sensor data to determine processing priorities. Multi-objective optimization balances compression efficiency, reconstruction quality, and energy consumption using evolutionary algorithms that generate optimal parameters for an adaptive variational autoencoder. The autoencoder features dynamically selectable processing complexity, adjustable latent space dimensionality, and modality-specific processing layers. The system automatically switches between operational modes including emergency mode triggered by resource constraints, which applies maximum compression settings and intelligent data triage. Continuous learning adapts compression parameters based on observed performance outcomes, improving future optimization decisions. The system enables homomorphic operations on compressed data and provides enhanced compression performance under varying resource constraints across diverse edge computing applications.

A neural network system is provided. The system includes an autoencoder configured to encode input data into a latent space representation; a generator neural network configured to receive a noise vector and the latent space representation and output a set of routing coefficients; a discriminator neural network configured to evaluate the effectiveness of the routing coefficients by measuring the performance of a capsule network utilizing said routing coefficients; and a capsule network comprising a first capsule layer and a second capsule layer, wherein the routing coefficients are used to dynamically route outputs from the first capsule layer to the second capsule layer.

The invention relates to the technical field of data processing, and discloses an anti-oxidation barrier layer performance degradation prediction method and system based on multi-source data. The method comprises the following steps: collecting and preprocessing multivariate data of a barrier layer environment, and constructing three-dimensional tensor data; indexes such as oxygen blocking efficiency and anti-permeability performance are calculated, and performance time sequence data are obtained; extracting multi-dimensional features and fusing the multi-dimensional features through an automatic encoder; applying a hybrid deep learning model to predict performance degradation; analyzing degradation curve characteristics, and executing mode clustering to obtain a risk matrix; and optimizing a maintenance decision scheme based on risk assessment. According to the invention, the hybrid deep learning model is utilized to capture the dependency relationship of time and space dimensions at the same time, and the prediction precision is significantly improved; based on degradation mode identification and risk level evaluation, accurate multi-scene maintenance decision is realized, environmental risk is reduced, and maintenance cost is optimized.

The invention relates to the technical field of RFID smart tags, and discloses an RFID smart tag positioning and tracking printing method and system, and the method comprises the steps: inputting an RFID tag radio frequency signal into a conditional variation automatic encoder for convolution processing and attention weighting, and obtaining an RFID tag global feature vector; establishing a layered sensor node network to perform multi-dimensional acquisition on environmental parameters to obtain an environmental spatio-temporal data set; inputting the global feature vector of the RFID tag and the environment spatio-temporal data set into a deep fusion network for feature fusion to obtain a multi-modal fusion feature; performing sequence modeling based on the multi-modal fusion features to obtain an article trajectory prediction model; the object track prediction model is applied to a target area grid coordinate system for density distribution calculation, a real-time object positioning heat map and a track database are obtained, an efficient object positioning heat map generation and track data management mechanism is established, and real-time position visualization and historical track query are facilitated for the system.

The invention belongs to the technical field of artificial intelligence, and discloses a PCB use fault early warning system based on artificial intelligence, which comprises a data acquisition module, a data processing module, an intelligent analysis module, a decision level fusion module, a self-adaptive modeling module, a multi-model cooperation module and a fault early warning module. The intelligent analysis module realizes double breakthrough of nonlinear feature capture and adaptive anomaly discrimination ability through a dynamic error threshold mechanism of an LSTM time sequence prediction engine and a depth autoencoder; an XGBoost-1DCNN hybrid classifier is constructed, a gradient boosting tree and multi-scale convolution features are fused in fault mode recognition, and the complex fault classification precision is remarkably improved; and the decision level fusion module constructs a multi-model decision conflict resolution mechanism based on an improved D-S evidence theory, and realizes great optimization of a false alarm rate through a confidence interval dynamic synthesis algorithm, thereby forming a closed-loop system with real-time response, multi-dimensional root cause analysis and intelligent hierarchical early warning.

The invention relates to the technical field of fault detection, and particularly discloses a prediction reconstruction framework causal perception space-time network for explaining anomaly monitoring in a complex industrial process, comprising the following steps: S01, constructing graph data E (V) and a causal graph; automatically adjusting the fusion proportion of the time-frequency characteristics according to the data characteristics so as to ensure that the model can comprehensively capture the information of the data in the time domain and the frequency domain; secondly, introducing a residual image attention network (RGAT), and converting the image data E (V) into image structure data G (S (V), E (V)); and S03, reconstructing a prediction error by adopting a variational automatic encoder (VAE), learning an error mode of normal data, providing an anomaly judgment AD (V) for anomaly detection, analyzing a causal relationship between data in combination with a causal graph, and positioning an anomaly reason according to an anomaly score, so as to form a prediction result. The network solves the problem that a traditional monitoring network is high in false alarm rate.

Communication devices and methods for determining channel state information (CSI) report based on artificial intelligence (AI) / machine learning (ML) are provided. The method for determining CSI report based on AI / MI performed by a communication device includes determining, by the communication device, one or more CSI reports according to an AI / ML based CSI feedback, wherein each of the one or more CSI reports contains an output of an auto-encoder, a compression ratio, a rank indicator, quantization levels, a ground truth of an enhanced CSI feedback, and / or an ML model monitoring outcome, and determining, by the communication device, priority rules for the CSI reports according to the AI / ML based CSI feedback.

The invention belongs to the technical field of artificial intelligence and information security crossing, and discloses a multi-modal false news detection method based on decoupling and cross-modal clue mining, and the method comprises the steps: employing a pre-training comparison model to extract text and image features in news, and mapping the text and image features to a unified embedding space; designing a multi-modal decoupling automatic encoder, decomposing each modal feature into modal common and modal specific representation, and obtaining a pure decoupling feature through confrontation constraint and reconstruction loss; a cross-modal clue mining module is constructed, modeling complementation is carried out from non-unhooked features, and conflicting semantic clues are enhanced; a self-adaptive attention aggregation module is introduced, and the modal features and the semantic clues are dynamically weighted and fused; and inputting the aggregated representations into a classifier for false news identification. According to the method, through modal decoupling and multi-source clue modeling, modal redundancy and specific information are effectively separated, association and conflicts between images and texts are deeply mined, and the detection accuracy is remarkably improved.

The invention relates to the technical field of network information security, discloses an information security management system based on big data, and aims to solve the defects of an existing system in the aspects of data acquisition, anomaly detection, threat prediction, risk assessment and the like. The system comprises a data acquisition module for collecting various types of data in real time; the abnormal detection model is used for identifying normal and abnormal behaviors by adopting an automatic encoder AE algorithm; the threat prediction module is used for predicting a future security threat type and probability by using a recurrent neural network (RNN) algorithm; the risk assessment module comprehensively assesses the system security risk through a random forest RF algorithm; and the response decision module is used for executing corresponding safety response measures according to the evaluation result. According to the system, the big data technology is utilized, comprehensive monitoring and accurate prediction of the network security state are achieved, the efficiency and accuracy of information security management are improved, and powerful support is provided for coping with novel and complex network attacks.

Provided is a method for token-based representation and learning of robotic perception data based on a graph neural network, comprising: obtaining a plurality of types of perception data of a robot; performing token-based representation according to types of the plurality of types of perception data; constructing an initial feature graph based on the plurality of types of perception data after the token-based representation; learning a compact representation of the initial feature graph based on an autoencoder and reconstructing a graph structure; after the autoencoder completes learning of the graph structure, fixing the graph structure; and converting the plurality of types of perception data into node feature vectors, constructing a feature graph based on the graph structure, and performing numerical encoding on each of the node feature vectors by utilizing the graph neural network to obtain a representation of high-dimensional feature vectors of the plurality of types of perception data.

The invention discloses an auxiliary film reading method and system based on artificial intelligence, and the method comprises the steps: 1, collecting a pathological WSI, an electronic medical record, detection data and equipment parameters, correcting the equipment difference through adaptive dyeing normalization, and constructing a structured data package associated with an ID-timestamp of a patient; 2, developing a dynamic branch CNN, migrating teacher model knowledge through knowledge distillation, and introducing federated learning; step 3, the edge generates a thermodynamic diagram to mark a suspicious area, and the cloud outputs a structured report; step 4, constructing a normal tissue feature space by the variational auto-encoder, detecting abnormal slices and triggering expert re-checking; a reverse automatic encoder generates a pseudo-health image to compare and position a pathological area, and dynamic weight adjustment balances the federal learning convergence speed; 5, integrating the thermodynamic diagram, the gene data and the clinical indexes by a three-dimensional platform, and supporting multi-dimensional superposition display; webGL realizes browser end rendering, and NLP automatically generates a report abstract marked with a key evidence chain and is in butt joint with an international diagnosis and treatment guide.

The invention discloses an image editing method and system based on diffusion model inversion and attention optimization, and relates to the technical field of image editing, and the method comprises the steps: mapping a source image to a potential space through a pre-trained automatic encoder, and obtaining an initial noise feature; an EF noise space inversion algorithm is adopted to process the initial noise features, a high-variance noise graph is generated, and an intermediate result under each time step is obtained through a decoder; constructing an improved U-Net network based on edit-friendly feature reweighting and an edit-friendly attention mechanism, fusing the target prompt information into a denoising process of the improved U-Net network through a cross attention mechanism, and performing feature optimization based on the improved U-Net network; and reconstructing the potential features through a U-Net decoder, and generating an edited image conforming to the target prompt information. On the low-cost premise that complex model fine tuning and retraining are not needed, the method is superior in text-guided controllable editing tasks, and the image generation quality is improved.

The invention relates to the technical field of air target prediction, in particular to an air target trend prediction method, which comprises the following steps: S1, multi-source heterogeneous data adaptive fusion filtering processing; s2, manifold learning is constructed in the high-dimensional spatial-temporal feature space; s3, performing semantic modeling on the dynamic behavior pattern recognition intention; and S4, multi-dimensional threat situation assessment warfare area modeling is carried out. According to the method, high-precision space-time synchronization and noise suppression of radar sensor data, infrared sensor data and other sensor data are achieved through the multi-source heterogeneous data self-adaptive fusion filtering technology, target micro-Doppler features are effectively reserved, missing data are repaired, and through the combination of third-order Savitzky-Golay differential filtering and short-time Fourier transform, high-precision space-time synchronization and noise suppression of radar sensor data and infrared sensor data are achieved. An 18-dimensional compression feature space containing kinematics and electromagnetic characteristics is constructed, a nonlinear topological relation is reserved through t-SNE and an automatic encoder, the signal-to-noise ratio and feature expression capacity of original data are remarkably improved through the function, and a high-precision and low-redundancy input basis is provided for follow-up behavior recognition and prediction.

The invention relates to an offshore wind power prediction method, and aims to improve the accuracy and reliability of prediction. The method comprises the following steps: (1) a data preprocessing stage: detecting an abnormal value in data by using a DBSCAN clustering algorithm, reconstructing the abnormal value by using a KNN interpolation method, detecting time sequence abnormity through an LSTM automatic encoder, and performing regression reconstruction by using LSTM to ensure the retention of time sequence features; (2) a feature engineering stage: screening out key features through correlation analysis, generating a label column through K-means clustering and wind direction classification, and extracting features such as wind direction change rate, time periodicity and wind speed interaction; and (3) a model construction stage: constructing a composite model in combination with multi-scale convolution (Inception), a bidirectional long short-term memory neural network (BiLSTM) and a multi-head self-attention mechanism, extracting local features through a convolution layer, capturing a time dependency relationship through a bidirectional LSTM layer, enhancing the attention of key features by using the multi-head self-attention mechanism, and finally realizing high-precision wind power prediction.

The invention discloses an electric power Internet of Things equipment anomaly detection method and system based on federal map learning. The method comprises the following steps: constructing graph structure data; in a client layer, using a graph neural network as a local node classifier of a downstream task, and using an adaptive graph interpolation generator to repair sub-graphs and lost cross-sub-graph connections; adopting a plurality of servers as central nodes, and uploading obtained model parameters to the central server of a local area after a client is locally trained to converge; in the server layer, potential global features of covered clients are obtained according to an automatic encoder, model parameters are allowed to be transmitted between adjacent servers, and a global model is obtained by adopting an aggregation algorithm and issued to each client; and after each client updates the model, the next round of training is continued until the optimal detection model is obtained. Potential connections between sub-graphs are mined by using an adaptive graph interpolation generator, and the blank of lack of cross-client topological information is filled.

A non-uniform video encoder system for generating a multi-depth encoding data for a scene is provided. The non-uniform video encoder system is configured to receive a sequence of video frames of a video of the scene and transform the sequence of video frames into series input data. The series input data is analyzed to identify changes in the evolution of the scene, by partitioning the series input data into a sequence of non-uniform segments. Each segment in the sequence of non-uniform segments is encoded by an encoder of an autoencoder architecture with non-uniform unrolling recursion to produce multi-depth encoding of the series input data. To encode a current segment at a current iteration to produce a current encoding, the non-uniform unrolling recursion combines the current segment with a previous encoding produced at a previous iteration and encodes the combination with the encoder.

The invention discloses a transformer fault detection method and device based on an automatic encoder and multi-scale feature fusion, and belongs to the technical field of power transformer fault detection.The method comprises the steps that sound signals during operation of a transformer are collected, and data frame division and normalization preprocessing are conducted on the collected sound signals; reconstructing the data of the collected sound signals by using an automatic encoder trained by normal sound data, and extracting the data coded by the automatic encoder as the implicit features of the sound signals; according to the error before and after reconstruction, sound abnormity judgment is carried out, and fault type detection is further carried out on abnormal data by using a classifier; and the classifier receives the collected sound data and the characteristic signal extracted by the automatic encoder as input, and classifies fault types. According to the method, the classifier is arranged, fault features are mined through the multi-scale features of the transformer sound signals, and the accuracy of transformer fault classification is improved.

A bidirectional autoencoder learns or approximates an identity mapping as it trains a single network with a version of the new bidirectional backpropagation algorithm. Ordinary unidirectional autoencoders find many uses in image processing and in large language models. But they use separate networks for encoding and decoding. Bidirectional autoencoders use the same synaptic weights for encoding and decoding. The forward pass encodes while the backward pass decodes. Bidirectional autoencoders improved network performance and significantly reduced memory usage and used fewer parameters. Simulations compared unidirectional with bidirectional autoencoders for image compression and denoising. The models trained on the MNIST handwritten-digit and CIFAR-10 image datasets. The performance measures were the peak signal-to-noise ratio and the index of structural similarity. Bidirectional autoencoders outperformed unidirectional autoencoders and still reduced the number of trainable synaptic parameters by about 50%.

Techniques for latent space based steganographic image generation are described. A processing device, for instance, receives a digital image and a secret that includes a bit string. A pretrained encoder of an autoencoder generates an embedding of the digital image that includes latent code. A secret encoder is trained and utilized to generate an embedding of the secret to act as a latent offset to the latent code. The processing device leverages a pretrained decoder of the autoencoder to generate a steganographic image based on the embedding of the secret and the embedding of the digital image. The steganographic image includes the secret and is visually indiscernible from the digital image. Further, the processing device is configured to recover the secret from the steganographic image, such as by training and leveraging a secret decoder to extract the secret.

The invention discloses a few-sample target detection method and system based on an aggregation variational prototype. The method comprises the steps of constructing a data set containing a base class and a new class, dividing the data set into a support set and a query set, generating a class prototype by utilizing a P-VAE module in combination with CLIP semantic features and a feature discriminator, realizing bidirectional fusion of the support set and the query set features by means of an MFM module, fusing the query features and the class prototype, and inputting the fused query features and the class prototype into a detection head to complete target detection. The system comprises a data set construction module, a priori variational automatic encoder P-VAE module, a mutual fusion module MFM, a feature fusion module and a target detection module. According to the scheme, by introducing semantic priori, optimizing prototype generation and feature interaction, the problems of data imbalance and insufficient new class feature representation in a few-sample scene are solved, improvement of new class detection precision is verified on PASCAL VOC, MS COCO and other data sets, and an effective solution is provided for target detection of sample scarce scenes such as medical images and rare species monitoring.

The invention discloses a commodity copywriting generation method based on a conditional variation automatic encoder and retrieval enhancement, which comprises the following steps: designing a reasoning module, a generation module, an evaluation module, a memory module and a prompt engineering module, aiming at user input content, based on a graph neural network, adopting path pruning and multi-hop reasoning, and generating a commodity copywriting in the reasoning module; pruning of a low-score path is achieved through path reasoning, the reasoning efficiency is improved, and an implicit relation is reasoned; the generation module introduces a layer-by-layer variational auto-encoder and enables the generated candidate commodity copywriting to meet specific condition requirements through conditional variables, the evaluation module performs comprehensive scoring on the candidate commodity copywriting, the memory module is constructed to store conversation between a user and the generation module, and the prompt engineering module performs iteration of a preset round based on a thinking tree structure. According to the method designed by the invention, the personalization and reality sense of the copywriting can be improved, and the generation of diversified advertisement copywriting with clear styles is realized.

Systems and methods for detecting and diagnosing machine faults are discussed. An exemplary system includes at least one sensor node to sense a signal indicative of an operation status of a machine part, and a machine health analyzer circuit to generate a computational machine fault model comprising an autoencoder (AE) network and an associative module. The AE network encodes the sensed signal into signal features in a latent feature space, and decodes the signal features to produce a reconstructed signal. The associative module transforms the encoded signal features into an associative output using a dynamically updatable codebook. The machine health analyzer circuit detects a presence or absence of fault in the machine part based on reconstruction losses determined respectively from the reconstructed signal and the associative output. The detected fault can be presented to a user or to a process such as fault diagnosis or fault correction.

In various examples, self-supervised learning may be used to pre-train an encoder network of a masked prediction model to reconstruct masked regions of an input representation of 3D detections such as LiDAR point cloud(s). Spatial and / or temporal masking may be applied to a projected representation of 3D detections (e.g., a two-dimensional (2D) projection image), and the masked prediction model (e.g., a masked auto-encoder or joint-embedding predictive architecture) may be used to reconstruct a representation of the masked regions (e.g., reflection characteristic(s) stored in corresponding pixels or cells of the projected representation, a latent representation of the reflection characteristic(s)) during iterations of self-supervised learning. As such, the pre-trained encoder network of the masked prediction model may be used as a foundation model and fine-tuned with a task-specific output head or its pre-trained weights may be used to initialize a task-specific model.

The invention discloses an scRNA-seq cell clustering method based on multi-scale feature fusion. The scRNA-seq cell clustering method comprises the following steps: 1, acquiring and preprocessing an scRNA-seq data matrix; 2, using a ZINB-based auto-encoder to extract global expression features, and constructing ZINB loss; 3, constructing a cell-cell adjacency matrix based on a Gaussian kernel function, extracting local structure features by using a graph automatic encoder, and constructing graph loss; and 4, fusing the global expression features from the ZINB auto-encoder and the local structure features from the graph auto-encoder by using a double-end attention mechanism. 5, the cells are clustered based on a self-optimization clustering method, and clustering loss is constructed. And 6, performing clustering result analysis by using t-SNE. According to the method, scRNA-seq data can be well processed, multi-scale features are fused, tag prediction is more accurate, and analysis of complex biological characteristics of single cell data is facilitated.

A system is provided for dynamic analysis and verification of smart contracts. The system includes an autoencoder configured to preprocess smart contract code to reduce noise and highlight critical features; a capsule network configured to analyze the preprocessed smart contract code, capturing hierarchical relationships and dependencies within the code; a generative adversarial network (GAN) configured to generate optimal routing coefficients for the capsule network, enhancing the efficiency and accuracy of the analysis; and a blockchain-based platform for deploying and executing smart contracts, wherein the platform utilizes the capsule network to continuously monitor the smart contracts for anomalies during execution.

The invention is applicable to the technical field of electroencephalogram emotion recognition, and provides an electroencephalogram emotion recognition method based on deep learning, which comprises the following steps: firstly, preprocessing electroencephalogram signals, including baseline noise removal, standardization, band-pass filtering and signal segmentation; then establishing a deep learning model, wherein the deep learning model sequentially comprises an automatic encoder, a dynamic graph convolutional neural network, a Transform and a classifier; training a deep learning model by using a cross entropy loss function in combination with regularization; and finally, performing emotion recognition on the preprocessed electroencephalogram signals based on the trained model, and outputting a result. According to the method, multiple deep learning models are fused, so that collaborative extraction of the dynamic spatial features and the long-range time dependence features in the electroencephalogram signals is realized. According to the method, the accuracy of electroencephalogram emotion recognition is greatly improved, and a more reliable and efficient emotion recognition technical support is provided for the man-machine interaction fields such as depression evaluation and affective disorder treatment.

A generative machine learning model, such as a convolutional neural network (CNN), can be trained with solutions from a topology optimization solver for a solution for a topology of a set of structures so that the generative machine learning model can generate a plurality of alternative designs for a structure that are alternative topology optimizations (for the structure) for a set of initial setup parameters. The generative model when being trained includes a generative network and a discriminator network. The generative model can be trained using outputs from a CNN autoencoder for densities and a CNN autoencoder for strain energies.

A system and method of creating 3D field data of at least one specimen of an engineering component includes obtaining a first set of 3D field data, defining at least one geometry parameter, training a variational autoencoder model (VAE), splitting the VAE into an encoder model and a decoder model, connecting a multilayer perceptron network model (MLP) to an input layer of the decoder model of the VAE to form a Hybrid Multilayer Perceptron-Variational Autoencoder model (MLP-VAE), training the MLP-VAE to map values, defining to at least partially define geometry data of at least one additional specimen of the engineering component, using the trained MLP-VAE to predict 3D field data related to the at least one additional specimen by directly mapping the respective at least one value of the at least one geometry parameter to respective predicted result data of the at least one specimen.