2551 results about "Supervised learning" patented technology

A system for AI-supported leak detection and localization in water distribution infrastructures, consisting of: a large number of distributed sensor nodes mounted along a water pipe, each sensor node comprising the following: a pressure sensor configured to measure local hydraulic pressure fluctuations within the pipeline with a resolution of at least 0.01 bar; a flow sensor configured to measure the volume flow within the pipeline with an accuracy of at least ±0.5% of the measured value; an acoustic sensor configured to detect vibration signatures caused by leaks in a frequency range between 50 Hz and 20 kHz; an embedded microcontroller with integrated analog-to-digital conversion circuitry for digitizing sensor outputs; a wireless communication module configured to transmit time-synchronized sensor data to a cloud-based processing platform; and a local energy subsystem with a rechargeable battery and an optional circuit for generating photovoltaic energy; the cloud-based processing platform includes an artificial intelligence engine that comprises the following: a data acquisition module configured to receive and decode the transmitted sensor data and to perform time alignment; a supervised learning module that is trained on historical data of flagged leaks and non-leaks to classify incoming sensor patterns; an unsupervised learning module configured to detect anomalies by modeling normal operating baselines of the pipeline; and a topology-aware localization module configured to determine leak coordinates using the topology of the pipeline network, modeling the propagation of hydraulic waves, and estimating the arrival time difference from multi-node acoustic detections; and wherein the system is configured to provide real-time leak alerts and georeferenced visualization via a remote monitoring interface.

The invention discloses a network security threat research and judgment method, system and device and a storage medium, and the method comprises the following steps: S1, obtaining network traffic, terminal logs, application program interface calling records and threat intelligence data in real time, carrying out the standardized cleaning and format conversion of the data, and building a unified data lake; s2, matching, identifying and determining threats through a preset known threat feature library, constructing a normal behavior baseline by using an unsupervised learning algorithm, and marking suspicious events deviating from the baseline; s3, for the suspicious event marked in the step S2, mining a potential attack path and an attack intention by combining knowledge graph technology associated asset information, a historical attack chain and a homologous IP address; and S4, based on the attack success probability, the influence asset importance and the diffusion speed, calculating a threat level by adopting a fuzzy comprehensive evaluation model, and generating a research and judgment report containing disposal suggestions.

The invention discloses a power equipment fault diagnosis method and system based on a dynamic knowledge graph and large model collaborative reasoning, and the method comprises the steps: achieving the automatic extraction of an entity relationship through a weak supervision entity relationship extraction mechanism in combination with a power field dictionary and a remote supervision technology, and obtaining a weak supervision entity relationship; constructing a time sequence knowledge graph to capture a dynamic evolution rule of the fault propagation chain; structured knowledge graph embedded representation is fused with a large model input layer through a knowledge injection layer, a two-stage reasoning process is generated by adopting a graph retrieval enlarged model, and finally a diagnosis conclusion containing a structured evidence chain is generated. According to the method, the fusion of weak supervised learning and sequential relation modeling is realized, and the automatic extraction and dynamic updating capability of the knowledge in the electric power field is remarkably improved; through a knowledge injection layer and a two-stage joint reasoning mechanism, the structured reasoning advantage of a knowledge graph and the semantic generation capability of a large model are effectively combined, and the diagnosis accuracy, the time sequence reasoning capability and the interpretability are greatly enhanced.

The invention relates to the technical field of printed circuit board assembly quality detection, and discloses a PCBA anomaly detection method and system based on three-dimensional modeling and AI fusion, and a medium. The method comprises the following steps: acquiring three-dimensional point cloud data of a PCBA board to be detected; generating a reference three-dimensional digital twin model according to a standard PCBA design drawing; carrying out spatial registration on the three-dimensional point cloud data and the reference three-dimensional digital twin model, obtaining the three-dimensional point cloud data, carrying out hierarchical processing on the obtained three-dimensional point cloud data, extracting geometric features of a welding spot region, contour features of an element region and surface features of a substrate region, and carrying out fusion to generate a feature vector group; constructing a generative adversarial model based on a preset semi-supervised learning framework and the normal PCBA sample vector group; and inputting the feature vector group into a generative adversarial model, and examining the abnormal vectors, the corresponding three-dimensional coordinates and the abnormal types in the feature vector group by the generative adversarial model to complete the abnormal detection of the PCBA board. The method is suitable for quality control of a high-density and miniaturized PCBA.

A robotic surgical system includes one or more robotic actuators configured to interact with biological tissue during a surgical procedure. A plurality of sensors include at least one of fiber Bragg grating sensors, piezoelectric strain sensors, or magnetostrictive sensors to capture real-time mechanical, elasticity, or deformation data from biological tissues. deep learning engine trained on a dataset comprising tissue mechanical responses across multiple tissue types, pathological states, and patient demographics. Pre-contact predictive adjustment profiles are generated for anticipated tissue interactions using preoperative imaging data registered to intraoperative coordinates. Intraoperative deviations are detected from predicted mechanical behavior and autonomously recalibrate actuator forces. Upcoming surgical maneuvers are anticipated based on prior task sequences and adjust actuator stiffness or damping properties in preparation for anticipated contact. An emergency override of actuator forces is provided via an anomaly detection module when real-time sensor data deviates beyond a threshold from the predicted safe mechanical response range. A feedback loop iteratively refines the deep learning engine during the procedure using supervised learning updates, anomaly detection, and reinforcement learning strategies. The reinforcement learning model is optionally shared across procedures to optimize distributed actuator force patterns for minimizing localized and cumulative tissue stress.

The invention relates to the technical field of optical lens defect detection, and particularly discloses an optical lens laser-induced damage on-line detection method and system, a linear polarizer and a narrow-band filter are connected in series in a detection laser light path, non-target polarized light is filtered through polarization direction matching, meanwhile, interference of the environment and scattered light is inhibited through the narrow-band filter, and the laser-induced damage on-line detection system is obtained. According to the method, external source noise such as ambient light and non-target polarized light is reduced through polarization matching and narrow-band filtering, randomness of speckle noise is offset through multi-angle collection and signal fusion in a visual detection mode, exposure is dynamically adjusted, an image is fused to improve the signal-to-noise ratio, noise and real signals are decoupled through self-supervised learning, and the real-time performance of the system is improved. Dust interference is removed in combination with morphological operation; a deep learning reasoning model enhances the damage identification capability in a noise environment, defocusing blur caused by mechanical vibration is eliminated through phase conjugate correction, and the influence of photoelectric conversion noise, dust interference and the like on the detection efficiency and accuracy is remarkably reduced through multi-link linkage.

The invention provides a semi-supervised image semantic segmentation method and system based on a visual basic model, and the method comprises the steps: constructing a multi-task model which comprises a visual basic model and a depth estimation basic model, and the visual basic model is connected with a task solution head, an adapter parameter efficient fine tuning module and a multi-modal cross fusion module; the task solution head comprises a semantic segmentation head and a depth estimation head; extracting semantic hierarchy features and a depth feature map of the RGB image, performing cross attention fusion on the semantic hierarchy features and the depth feature map, and inputting obtained fusion features into a semantic segmentation head and a depth estimation head respectively; semi-supervised learning is adopted to train a multi-task model, only parameters in the adapter parameter efficient fine tuning module and the multi-modal cross fusion module are trained, and a multi-task loss function is adopted. The image semantic segmentation model obtained through training can improve semantic segmentation performance, reduce training cost and is suitable for different tasks.

The invention relates to a power distribution network data intelligent analysis method based on data consanguinity and multi-modal fusion learning. The method comprises the following steps: S1, constructing a dynamically evolved data consanguinity topological graph; s2, designing a label-guided graph neural network architecture, embedding historical abnormal knowledge into a graph learning process, and outputting a deep semantic feature vector; s3, constructing a multi-modal fusion analysis framework, performing multi-dimensional feature fusion and data quality analysis, and identifying abnormal nodes; s4, designing a semi-supervised and incremental learning combined mixed training normal form, and performing model training and strategy optimization; and S5, based on the dynamic consanguinity topology constructed in the step S1 and the identified abnormal nodes, constructing a probabilistic reasoning framework, and fusing the model parameters obtained by optimization in the step S4 to realize quality abnormality root positioning and full-link visualization so as to form a complete data intelligent analysis scheme. According to the invention, efficient and accurate management of the topological data quality of the power distribution network is realized.

The invention discloses a big data-based power distribution network protection setting decision system and method, and relates to the technical field of power distribution network protection, and the system comprises a multi-source data collection module which collects the operation data of a power distribution network; the big data feature processing module is used for carrying out feature extraction and constructing a multi-dimensional feature vector library containing time sequence features and frequency domain features; the protection setting model module is used for constructing a protection setting decision model based on a deep learning framework and carrying out supervised learning training by utilizing historical fault data and a setting scheme; the multi-scene simulation verification module is used for constructing a power distribution network digital simulation model; and the scheme evaluation optimization module is used for establishing an evaluation index system and outputting an optimal protection setting scheme. According to the method, deep learning and historical data are combined, an optimal protection setting scheme is automatically generated, faults are recognized through wavelet transform and Fourier transform, protection parameters are adjusted in real time, mistaken and leaked protection is reduced, timeliness is improved through edge calculation, the strategy is optimized, and the safety of the power distribution network is enhanced.

The invention discloses an efficient denoising power transmission line point cloud processing method and system, and relates to the technical field of three-dimensional point cloud data processing and intelligent analysis, and the method comprises the steps: carrying out the segmentation processing of original power transmission line point cloud data, dividing the point cloud into power equipment parts, carrying out the local density analysis of the segmented point cloud, and generating a density distribution diagram; based on the density distribution diagram and the local geometric features of the point clouds, multi-stage filtering is carried out, denoising model parameters are optimized, a statistical filtering method is combined to remove noise points, curvature features and normal vector consistency features of the point clouds are extracted, classification feature vectors are generated, and based on the classification feature vectors, fine classification is carried out on the point clouds. Through data preprocessing, multi-stage filtering, self-supervised learning, feature extraction and refined classification, the technical defects of insufficient multi-modal feature fusion efficiency and poor equipment feature adaptability in power transmission line point cloud denoising are effectively solved.

A method for training a machine learning (ML) model using a large language model (LLM) is provided. A system for detecting fraud which utilizes the LLM-trained ML model trained is also provided. An artificial intelligence (AI)-based method for monitoring alerts is also provided. The method for training an ML model using an LLM includes receiving tabular data for training the ML model, generating one or more natural-language strings comprising information from the tabular data, generating, via a base LLM, one or more prompts and completions based on the one or more generated natural-language strings, pre-training the base LLM using a plurality of generated prompts and completions, updating the base LLM via supervised learning using a cross-entropy loss function with ground-truth labels, and fine-tuning the updated LLM via reinforcement learning with human feedback using a reward model and a proximal policy optimization model to produce the LLM-trained ML model.

A computer implemented method for training a whole medical image foundation model, including: receiving a plurality of medical image datasets; extracting local sections of image data from the plurality of medical image datasets; obtaining one or more causal variables associated with the local sections and / or patient; training one or more self-supervised learning models based on the local sections of image data and the causal variables; combining the one or more trained self-supervised learning models with a deep learning network configured to combine a latent representation of the local sections of image data from the one or more trained self-supervised learning models into a patient-level representation; and combining, with the one or more trained self-supervised learning models and the deep learning network, at least one further network or function configured to accept the patient-level representation as input, the at least one further network or function operable to perform one or more patient-specific prediction tasks.

The invention provides an equipment state deviation identification method based on self-supervision and incremental learning, and the method comprises the steps: S1, obtaining time sequence data of equipment in a fault-free state, and constructing a normal state model; s2, during operation, deviation detection is carried out on real-time data through the normal state model, and a deviation degree index is obtained; s3, comparing the deviation degree index with a preset threshold value, and judging an abnormal event; s4, determining new normal state data by manually verifying the abnormal event; and S5, updating the normal state model according to the new normal state data. The method does not need to depend on a fault sample, establishes an equipment normal behavior model through self-supervised learning, introduces a deviation index to quantify a state difference, and combines manual feedback and incremental learning to form a closed loop, so that the model has self-adaptability and long-term evolution ability.

The invention discloses an abnormal traffic detection method and system based on deep learning and a generative adversarial network, and relates to the technical field of network security and artificial intelligence. In order to solve the core problems of scarcity of annotated data, unbalanced categories, difficulty in feature extraction and the like in abnormal traffic detection, the invention aims to construct a self-supervision-generation-attention three-layer collaborative detection architecture: general features are extracted from unannotated traffic through a self-supervision feature representation learning module, and the problem of annotation dependence is solved; a VAE-GAN generation enhancement module is used for generating high-quality samples for minority class abnormal traffic, and class balance is achieved; packet-level, flow-level and session-level multi-modal features are dynamically fused based on a multi-head attention mechanism, accurate detection is carried out in combination with a Transform-CNN-LSTM hybrid model, and interpretable analysis is provided. The method is characterized in that end-to-end high-precision abnormal flow detection is realized systematically through organic cooperation of data acquisition and preprocessing, self-supervised learning, generation enhancement, attention detection and a result output module.

The invention provides a semi-supervised target detection method for a visible light-infrared multi-mode fusion scene. The method comprises the following steps: constructing a semi-supervised visible light-infrared multi-modal image data set based on an LLVIP data set; on the basis of a YOLOv11 model architecture, constructing a target detection model oriented to multi-modal image feature fusion, and training the target detection model by using a semi-supervised visible light-infrared multi-modal image data set in a deep learning end-to-end mode to obtain a trained target detection model; and inputting a to-be-detected multi-modal image into the trained target detection model, and outputting a target detection result of the to-be-detected multi-modal image by the trained target detection model. The method is based on a semi-supervised learning normal form, so that the precision and robustness of target detection in a multi-modal fusion scene are improved, and the requirements for high efficiency and reliability of target recognition in practical application scenes such as intelligent traffic and intelligent security and protection are met.

The invention discloses a prefabricated cabin welding seam quality detection method based on self-supervised learning, and the method comprises the following steps: collecting a multi-source welding seam image and process parameters, carrying out the synchronous calibration, and constructing a multi-modal observation matrix; the image is input into a DINOv2 model based on a visual Transform, dense features are obtained, and inter-frame registration and sequence reconstruction are completed; performing difference analysis on adjacent frames, extracting spatial changes and marking potential defects; the dense features and the process parameters of the corresponding time periods are fused, joint features are constructed and classified according to rules, and a preliminary result is output; inputting the defect area and the process parameters into an improved DEER model, extracting an influence path and amplitude, and generating a sensitivity score and a confidence coefficient; final judgment is given in combination with the preliminary result, the sensitivity and the confidence coefficient, and feedback is formed according to judgment and process difference. According to the method, high-precision and explainable detection and process optimization of weld defects are realized, and the method is suitable for online / offline quality control and tracing.

The invention provides a coherent signal arrival direction estimation method and device based on a deep convolutional network, and belongs to the field of array signal processing. The method comprises the following steps: receiving a to-be-detected signal containing a coherent signal by using a uniform linear array antenna to obtain an array receiving data matrix and extract a covariance matrix; forming an input feature vector by right upper triangular elements divided from a diagonal line in the covariance matrix, inputting the input feature vector into a covariance estimation model formed by a deep convolutional network, obtaining an estimation value of the right upper triangular elements under an ideal incoherent condition, and reconstructing the estimation value to obtain a covariance matrix estimation value; and performing characteristic decomposition on the covariance matrix estimation value, and generating a spatial spectrum by using a MUSIC algorithm to obtain an estimation result of the signal arrival direction. According to the method, the noise-containing mixed signal covariance matrix is mapped into the ideal incoherent noise-free signal covariance matrix through a physical constraint supervised learning framework, so that the estimation precision and robustness of the MUSIC algorithm in a coherent scene are improved.

The invention provides a distributed optical fiber temperature sensing logging data blind denoising method and system based on physical self-supervised learning. The method comprises the following steps: acquiring original noisy distributed temperature sensing (DTS) logging data, and generating a self-supervised training sample through a space-time alternating downsampling strategy by using the space-time coherence of the original noisy distributed temperature sensing (DTS) logging data; constructing a physical self-supervised blind denoising network model by using a simplified structure, and inputting a self-supervised training sample for training; in the training process, a multi-physical constraint loss function optimization model is introduced until a loss function converges, and a denoising model is obtained; and inputting to-be-processed complete DTS logging data into the denoising model to obtain denoised DTS logging data. According to the method, manual labeling and large-scale labeling of the data set are not needed, the inherent physical characteristics and structural information of the DTS data can be fully utilized, efficient and accurate blind denoising of the DTS logging data is achieved, and the problem that an existing deep learning denoising method needs to depend on a large amount of labeled data is solved.

The invention belongs to the technical field of aero-engine state monitoring and intelligent fault diagnosis, and discloses a multi-modal information fusion bearing fault diagnosis method based on self-supervised learning. The method comprises the following steps: firstly, through mask reconstruction self-supervision pre-training, extracting stable feature representation insensitive to mask disturbance from an unlabeled multi-modal signal, and dynamically updating each modal feature reference point by using an index moving average algorithm; in a downstream fault diagnosis task, a multi-modal joint decision model comprising a pre-training encoder, a single-modal classifier and a fusion classifier is constructed, and adaptive weighted fusion of multi-modal decision is realized through contribution degree calculation based on a cooperative game Shapley value in combination with a deviation degree of modal features and a reference point. According to the method, the dependence of the deep neural network on fault labeling data is effectively reduced, the accuracy and robustness of the diagnosis system in a multi-modal signal diagnosis scene are improved through a dynamic fusion mechanism, and the method is suitable for industrial scenes with limited sample label resources.

The invention relates to the technical field of self-supervised learning, in particular to a target detection pre-training method based on Transform. A CL-MAE (Control Learning-Masked Autocoder) self-supervised pre-training method is designed, an original image and an enhanced image are processed by adopting a double-branch architecture, branch parameters of the original image are frozen, enhanced branch parameters are updated by using index moving average, and multi-view contrast learning is introduced, so that the problem of'lazy 'of an encoder is effectively prevented, namely, a reconstruction task is completed by depending on a decoder. The method comprises the following steps of: pre-training a target detection network based on a PVT (Pyramid Vision Transfer), transferring the weight of a Vision Transfer) encoder to the target detection network based on the PVT after the pre-training is completed, and realizing the conversion from self-supervised pre-training to target detection in cooperation with FPN (Feature Pyramid Networks) feature fusion and a special detection head. According to the method, the problem that a traditional target detection model depends on annotation data is solved, and meanwhile, the problem of lazy during self-supervision pre-training of a mask auto-encoder is avoided. Compared with a non-pre-training model, the method achieves better target detection precision and convergence speed.

The invention discloses a digital archive online management system based on big data. The digital archive online management system comprises a digital acquisition layer which is used for carrying out semantic perception and structured extraction on heterogeneous archives; and the intelligent classification layer is used for mapping the collected archive entities, attributes and relationships to a dynamically expanded domain knowledge graph based on a knowledge graph construction technology and a graph neural network, realizing association mining and dynamic classification of cross-modal archives through node embedding and link prediction, adapting to evolution requirements of archive themes in combination with a weak supervised learning mechanism, and realizing dynamic classification of the cross-modal archives. A classification system with causal interpretation is formed; the storage retrieval layer is used for encoding the generation time, the space trajectory and the event causal chain of the archive into space-time causal metadata; the archive utilization layer is used for actively pushing associated archives and generating a personalized analysis report by analyzing user behavior preferences and scene requirements; and the backup layer is used for dynamically sensing the threat type and calling an evolutionary algorithm to adjust the backup frequency, the storage position and the recovery path.

The invention discloses a traffic network toughness diagnosis method under flood disasters based on a space-time diagram neural network, and relates to the crossing field of traffic engineering and artificial intelligence. The method comprises the following steps: collecting traffic topology, flood monitoring and traffic flow data, and carrying out space-time alignment; a flood coupling dynamic space-time diagram is constructed, a water depth-traffic capacity response mechanism is introduced, and real-time mapping from a disaster physical state to a network topology is realized by utilizing an attenuation function meeting physical monotonicity constraint and dynamically updating an edge weight of a diagram structure according to real-time water depth; inputting the dynamic graph into a pre-trained space-time graph neural network model, extracting space-time evolution characteristics and outputting a toughness diagnosis result; model training adopts a toughness label generated based on an anti-fact baseline to carry out supervised learning, and introduces a physical constraint loss function. According to the method, the problems of decoupling of disaster features and graph structures and unavailability of toughness labels in the prior art are solved, and the physical consistency and accuracy of diagnosis are improved.

The invention discloses a multi-mode emotion continuous recognition method for medical treatment, belongs to the technical field of artificial intelligence and medical treatment information, and mainly aims to simulate the dynamic change process of emotion by establishing a Neural ODEs framework and overcome the static property and discreteness of emotion modeling in a traditional method. Through a causal inference technology, emotional features are separated from individual-independent physiological differences, and the generalization ability across individuals is improved. A self-supervised learning method is utilized, the synergistic effect between the EEG and the eye movement signal is improved through cross-modal contrast learning, and the emotion recognition precision is enhanced. The calculation complexity is reduced through a dynamic sparse attention mechanism, and meanwhile, focusing is performed on a key time slice in emotion recognition. Through multi-task joint learning, the model learns multiple tasks such as emotion intensity regression and tested identity recognition during emotion classification, and the personalized emotion recognition capability is improved.

The invention discloses a semi-supervised underwater image enhancement system and method based on wavelet transform and a diffusion model. The semi-supervised underwater image enhancement system comprises an image decomposition module used for obtaining a low-frequency component and a high-frequency component of an image to be enhanced by using discrete wavelet transform; the low-frequency diffusion module is used for gradually and sequentially denoising the randomly generated pure noise image by using a trained neural network model in a semi-supervised underwater enhanced image model through taking the low-frequency component as condition guidance to obtain an enhanced low-frequency component; the high-frequency repairing module is used for obtaining an optimized high-frequency component; and the inverse discrete wavelet transform module is used for fusing the optimized high-frequency component and the enhanced low-frequency component through inverse discrete wavelet transform to obtain a reconstructed enhanced image. According to the method, the wavelet transform is fused into the diffusion model, and the image enhancement process is optimized by utilizing the semi-supervised learning model and cooperatively utilizing the annotated data and the annotated data, so that the problem that the data scale is limited is solved, and the calculation efficiency in the image enhancement process is improved.

The invention discloses a user security feature recognition method based on behavior pattern analysis, and aims to solve the problems of inaccurate recognition of power utilization security features of power consumers and insufficient robustness in the prior art. The method comprises the following steps: preprocessing and segmenting original power consumption time sequence data; then, a self-supervised learning model based on an expert hybrid architecture is constructed, the architecture integrates five neural networks to construct an expert model, expert weights are dynamically distributed through a gating network, and a power utilization mode deep embedding vector is output through self-supervised training; clustering the embedded vectors by using a clustering algorithm, determining an optimal clustering number in combination with an elbow method and a contour coefficient method, generating a user portrait, and performing visualization and feature analysis; and finally, according to the user portrait data, carrying out transaction behavior pattern recognition on the input to-be-recognized user data, and outputting a security feature recognition result. The method can comprehensively and accurately identify the power utilization safety characteristics of the user, and is suitable for scenes such as intelligent power grid safety monitoring.

The invention belongs to the technical field of image processing, tracking and recognition, and relates to a multi-mode re-recognition method based on semantic-style decoupling distillation. The method depends on a multi-modal re-identification model which comprises a multi-modal feature extractor comprising a teacher branch module and a student branch module, a decoupling distillation module and a hierarchical self-supervised learning module, and comprises the following steps: constructing a mixed multi-modal feature extractor sharing a shallow layer and an independent deep layer to extract mixed features; performing dual supervision of semantic distillation and style distillation, modeling modal-invariant semantic information and modal-specific style information, and realizing effective decoupling of a feature space; a hierarchical self-supervised learning space is constructed, and in combination with intra-modal and cross-modal comparative learning, images under local damage and style disturbance conditions are scrambled; according to the method, recognition performance and reasoning efficiency are both considered, semantic features and modal specificity styles are effectively separated, semantic consistency, feature robustness and network learning efficiency are cooperatively improved, and modal specificity is also reserved.

The invention discloses a winter wheat LAI and SPAD estimation method based on a lightweight semi-supervised model, and relates to the technical field of agricultural remote sensing monitoring, and the method comprises the steps: obtaining multispectral image data of a winter wheat key growth period, and carrying out the preprocessing of the multispectral image data to generate a standardized multichannel vegetation index image; the method comprises the following steps: constructing a lightweight semi-supervised model MCVI-SANet, and carrying out self-supervised training on the MCVI-SANet by adopting a semi-supervised training strategy driven by VICReg; and inputting the multi-channel vegetation index image into the trained MCVI-SANet, and outputting quantitative estimation results of the LAI and SPAD of the winter wheat. Through combination of a saturation perception mechanism and semi-supervised learning, estimation deviation caused by dense canopy vegetation index saturation and data noise is effectively eliminated, and the estimation precision and generalization ability in a complex agricultural scene are improved while the lightweight deployment characteristic of the model is ensured.

The invention relates to a computer security protection system based on artificial intelligence, which comprises a data acquisition layer, a data processing and feature engineering layer, an AI model layer, a real-time detection and response layer, a feedback and self-adaption layer and a management visualization layer. According to the method, multiple learning paradigms are fused, the problems of model outdated, attack bypassing and alarm fatigue can be solved, the robustness and the optimization accuracy can be improved, a decision-making basis is generated by adopting tools such as SHAP, the interpretability is improved, man-machine cooperation is achieved, key decisions are reserved for manual auditing, and the safety is improved.

The invention discloses a spectrum aliasing decoupling and concentration inversion method under the cross influence of multi-source environmental factors, belongs to the field of industrial process control and environment monitoring, and constructs an environment-spectrum collaborative fusion decoupling model for concentration prediction. The method specifically comprises the following steps: respectively collecting absorption spectrum signals of specified mixed gas at different temperatures, pressures and known concentrations, meanwhile, collecting environmental parameter data, constructing a multi-source data set, and carrying out denoising, dimension reduction and preprocessing on the multi-source data set; constructing a self-supervised feature extraction network for adaptive modulation of environmental parameters to realize deep fusion of spectrum and environmental information; the feature expression capability and generalization performance of the self-supervised feature extraction network are improved by using a self-supervised learning mechanism; and constructing a BPBO-GRNN self-adaptive concentration inversion optimization model for realizing inversion of mixed gas concentration and self-adaptive optimization of model parameters. According to the invention, high-precision concentration inversion and stable detection of the aliasing gas can be realized.

The invention discloses a deeply-forged face video frame-level positioning method and system based on weak supervised learning, and the method comprises the steps: firstly constructing a training set with a video as a unit, carrying out the data enhancement of a frame-level sample, and generating an enhanced view pair; secondly, splicing the enhanced view pair and inputting the spliced enhanced view pair into a depth forgery detection model to obtain and generate fusion enhanced frame-level features; then, intra-class contrast learning loss, time sequence consistency constraint loss and frame weight loss are constructed, and a deep forgery detection model is trained based on fusion-enhanced frame-level feature joint optimization. And finally, inputting a video to be detected into the deep counterfeiting detection model to output the frame-level confidence, judging whether the video is a forged video or not, and realizing frame-level counterfeiting positioning. According to the method, video-level detection and frame-level positioning are effectively realized, meanwhile, the influence of label noise in part of forged videos is relieved, and the generalization and robustness of the system are improved.