861 results about "Support vector machine" patented technology

The invention discloses a rotating machine fault diagnosis method, which comprises the following steps of: acquiring vibration, temperature, acoustic emission and current signals at key parts of a rotating machine, and extracting characteristic parameters such as time domain and frequency domain after preprocessing such as filtering and noise reduction; and inputting the characteristic parameters into machine learning models such as a support vector machine, combining deep learning models such as a convolutional neural network and a long-short-term memory network, performing comparative analysis by using a digital twin model, and fusing diagnosis results to output fault types, positions, severity and maintenance suggestions. The method overcomes single diagnosis limitation, multi-source signal complementation, multi-model collaboration, accurate fault diagnosis and diagnosis reliability improvement, provides a scientific basis for equipment maintenance, and is of great significance for guaranteeing safe operation of rotating machinery, reducing maintenance cost and promoting industrial intelligent development.

A machine learning-based fraud detection system (100) for financial transactions, comprising the following: a data collection and preprocessing module configured to capture transaction data from financial institutions, payment gateways and bank modules, and to perform data cleansing, normalization and format conversion; a module for creating user profiles and behavioral analyses, configured to create dynamic user profiles based on historical transaction patterns, spending habits, device usage, and geographic location; an anomaly detection and risk assessment module configured to use machine learning algorithms to detect deviations from normal transaction patterns and assign a dynamic risk rating to each transaction; a fraud detection module configured to classify transactions as legitimate or fraudulent based on supervised and unsupervised learning techniques, including decision trees, support vector machines (SVMs), and deep learning models; a rule-based and hybrid fraud detection module configured to integrate predefined rule-based fraud detection mechanisms with AI-driven anomaly detection to improve fraud detection accuracy; a real-time fraud detection and warning module configured to monitor transactions in real time and generate security alerts via SMS, email or mobile app when suspicious activity is detected; a transaction verification and multi-factor authentication (MFA) module configured to implement adaptive authentication measures, including biometric verification, one-time passwords (OTP), and challenge-response authentication for high-risk transactions; a self-learning and model-updating module configured to dynamically update fraud detection models using reinforcement learning and federated learning techniques; a data encryption and security module configured to protect transaction data using encryption techniques, including AES-256 and RSA, to prevent unauthorized access and data breaches; and A dashboard and reporting module configured to provide real-time analytics, visualizations, and fraud detection reports for financial institutions to monitor, track, and mitigate fraudulent activity.

The invention discloses a low-carbon city subjective and objective mixed planning interval entropy weighting evaluation method, and relates to the technical field of city management and low-carbon evaluation, and the method comprises the steps: collecting and preprocessing index data in real time, building a user behavior prediction model according to the index data, and predicting the index data of a user; dynamically adjusting weight distribution of subjective and objective evaluation indexes based on the predicted index data, and constructing a comprehensive evaluation model to calculate a comprehensive score of each region in the city; and formulating optimization measures of each region according to the comprehensive score. A prediction model is established by using a support vector machine, an evaluation result is highly matched with real-time data through dynamic weight adjustment, the hysteresis problem of traditional static evaluation is avoided, and more accurate and flexible low-carbon city evaluation is realized through dynamic adjustment of weight distribution and construction of a comprehensive evaluation model. And the comprehensive score of the urban area is calculated by adopting a nonlinear transformation function, so that the marginal effect change of the evaluation index under different load conditions can be better reflected.

The present invention relates to the field of geothermal resource development technology, specifically a geothermal well monitoring and maintenance management system and method based on the Internet of Things; the method steps are: through a denoising method combining adaptive fuzzy clustering and deep convolutional neural network, the real signal of sensor data is restored; by generating a check mark, the integrity of the collected geothermal well monitoring data is checked; combined with LSTM time series modeling and deep reinforcement learning for fault prediction and optimization, support vector machine is used for fault type identification, and maintenance strategies are formulated according to the prediction results, the appropriate maintenance type and timing are selected, and resource scheduling optimization is performed to generate a detailed maintenance plan; data and maintenance information are visualized and pushed to on-site staff in real time, and the staff performs operations according to the maintenance plan, and automatically records and updates the health status of the equipment. The present invention improves the monitoring and maintenance efficiency of geothermal wells through intelligent data processing and decision support.

The invention belongs to the technical field of data exception identification, and particularly relates to a main transformer operation multi-mode data exception identification method, which comprises the following steps: step 1, data acquisition: collecting various data in operation of a main transformer, including current, voltage, temperature, vibration and noise; step 2, data preprocessing: cleaning and sorting the collected data, including noise removal, missing value filling and data smoothing operation; step 3, feature extraction: extracting key features, including statistical features and frequency domain features, from the preprocessed data, and converting the original data into a form for analysis; step 4, modeling and training: utilizing a machine learning or deep learning model to train the features, wherein the model comprises a decision tree and a support vector machine; according to the invention, through a multi-level and multi-dimensional anomaly detection and processing mechanism, the safety and reliability of the operation of the transformer are improved, and the efficiency and cost of operation and maintenance management are optimized.

The invention discloses a sensitive word auditing method, which belongs to the field of auditing, and comprises the following steps of: firstly, preprocessing an input text, such as removing spaces, symbols, stop words and the like, so as to generate a word segmentation result; thirdly, constructing a dynamic synonym and a deformation word library, combining user behaviors and NLP technology updating, and expanding word meanings by applying a word vector model Word2Vec; then, based on BERT, a text context is analyzed, and metaphors and biguan languages are detected. Performing sensitive word primary screening and secondary screening by using a static word bank and an SVM (Support Vector Machine), and analyzing complex semantics by LSTM (Long Short Term Memory); the model is optimized based on a feedback self-learning mechanism, difficult contents are manually checked, an analysis report is generated, and finally a word bank and an algorithm are periodically updated to adapt to hotspots. The method has the beneficial effects that sensitive word auditing is improved through a self-learning mechanism, synonyms and deformed word banks can be dynamically updated, and private expressions are identified. BERT and LSTM model multi-level auditing are adopted, secondary screening is carried out in combination with SVM, and recognition of complex contexts and biguan languages is improved.

The invention provides a sewage treatment plant terminal effluent carbon source quality detection and evaluation method, which realizes full-flow dynamic evaluation and regulation of carbon source quality through on-line monitoring and intelligent algorithm fusion. According to the method, an online water quality full-spectrum detector is used for collecting original spectrum data flow, and after preprocessing such as variational mode decomposition denoising and mutual information feature selection, organic matter content quantification, variation trend analysis and anomaly detection are completed in combination with algorithms such as a support vector machine and an autoregressive moving average model. An entropy weight method is introduced to dynamically adjust the weight of the evaluation model, model parameters are optimized based on a gradient descent algorithm, a process adjustment instruction is generated through reinforcement learning and fuzzy logic, and an automatic system is linked to execute regulation and control. According to the method, the problems of hysteresis and singleness of traditional offline analysis are solved, multi-dimensional real-time evaluation, abnormal quick response and process dynamic optimization of the quality of the carbon source are realized, the sewage treatment efficiency and the effluent quality stability are improved, and a technical support is provided for continuous standard reaching of the quality of the carbon source.

The invention discloses a hydraulic system throttling control method based on a hydraulic control one-way valve, which relates to the technical field of throttling control, and comprises the following steps of: in an initialization stage of starting a hydraulic system, setting an optimal initial throttling opening for a throttling valve based on flow data of current oil; the method comprises the following steps: performing high-frequency real-time acquisition on flow state data of oil through a sensor deployed at the upstream of a throttling area, and establishing a set of flow state data system based on a time sequence; continuously collected flow state data are divided according to time windows, and an analysis set of oil flow data is constructed. According to the method, the dynamic flowing state of oil is monitored and deeply analyzed in real time, the load state is intelligently predicted in combination with a support vector machine model, and the opening degree of the throttling valve is adjusted in real time; the problems that in the prior art, response of a throttling control strategy to a high-load working condition is delayed, and oil temperature rise and viscosity abnormal reduction are caused by serious local pressure loss of a throttling area are effectively solved.

The invention discloses an intelligent classification method and system for defects of a strain clamp of a power transmission line based on a two-dimensional image, and belongs to the field of defect classification of the strain clamp, and the method comprises the steps: carrying out the preprocessing of the two-dimensional image of the strain clamp, extracting related features, and constructing a defect region candidate set; the method comprises the following steps: firstly, acquiring edge information by using an edge detection algorithm, and calculating curvature and roughness to generate a morphological feature vector; then, training a support vector machine model based on the defect sample set, and classifying the first candidate set to obtain a first defect classification result; thirdly, density feature correction is carried out on wire clamp images of different materials, gray gradient features are extracted, a second candidate set is obtained, and the second candidate set is input into the trained SVM model for second defect classification; and finally, integrating the first classification result and the second classification result to generate a final defect classification result. According to the method, morphological characteristics and material characteristics are effectively combined, and the accuracy and robustness of defect detection are improved.

The invention discloses a submarine cable insulation multi-field aging prediction method and system, and relates to the technical field of material science and engineering. An existing model has the problems that parameter interaction effect analysis is insufficient, feature weight distribution is not scientific, a data standardization method is insufficient, and the capacity of capturing dynamic response and nonlinear aging behaviors is weak. The method comprises the steps of multi-physics field accelerated aging experiment design and data acquisition, key characteristic parameter screening through grey correlation analysis, support vector machine modeling and optimization, dynamic aging behavior evaluation and service life prediction and feedback adjustment. According to the technical scheme, aging behaviors are comprehensively captured through a multi-physics field cooperation experiment, key parameters are scientifically screened in combination with grey correlation analysis, a nonlinear relation is optimized through support vector machine modeling, long-term prediction precision is improved through dynamic feedback adjustment, and reliability is enhanced through quantitative life evaluation; the aging characteristics of the submarine cable insulating material in multiple physical fields are comprehensively and accurately reflected, and a scientific basis is provided for multi-dimensional evaluation of the aging performance of a high polymer material.

The invention relates to the technical field of physical education teaching, in particular to an interactive physical education teaching method based on a large model, and aims to realize real-time monitoring and personalized training guidance of the motion state of a student through an advanced sensor technology and a machine learning model. The method comprises the following steps: firstly, collecting motion data of a student in real time through a camera and a depth sensor, including motion posture, speed, response time, heart rate and other information; then, the collected data are input into a pre-trained large model, the model comprises a convolutional neural network, a support vector machine and a random forest model which are respectively used for evaluating the action standard, the exercise intensity and the fatigue degree of students, the large model automatically generates personalized training items, and the exercise postures of the students are captured in real time; according to the motion deviation correcting system and method, by comprehensively applying various technical means, the scientificity and individuation level of physical education are improved, and the motion deviation correcting system and method have wide application prospects.

The invention relates to the technical field of synchronous reluctance motor structure optimization, in particular to a permanent magnet auxiliary synchronous reluctance motor structure parameter multi-objective optimization method. The method comprises the steps that motor structure optimization parameters are selected, and the change range of the parameters is determined; carrying out comprehensive sensitivity analysis according to the selected optimization target; performing hierarchical processing on the optimization variables according to the comprehensive sensitivity index, dividing the optimization variables into a strong sensitive layer and a weak sensitive layer, and taking parameters in the strong sensitive layer as to-be-optimized parameters of the next algorithm; comparing the prediction precision of the back propagation neural network, the radial basis, the extreme learning machine, the support vector machine and the kernel extreme learning machine, and selecting an agent model with an optimal prediction effect; combining the established high-precision agent model with a fast non-dominated sorting genetic algorithm, and searching an optimal combination of to-be-optimized parameters; and finally, carrying out single parameterization scanning determination on parameters in the weak sensitive layer by utilizing finite element simulation so as to obtain optimal structural parameters of the permanent magnet auxiliary synchronous reluctance motor.

The invention relates to the technical field of blockchain network security monitoring, and particularly discloses a blockchain-based network security monitoring method and system, the system collects transaction data, block data and intelligent contract execution results from a plurality of blockchain nodes, the analysis technology calculates the abnormal degree of each time window, the change rate of data inconsistency is quantified, and the data security monitoring accuracy is improved. If a relatively high data inconsistent change rate is detected, further comparing consensus results of the nodes, calculating consensus verification differences of the nodes, identifying the nodes deviating from normal consensus behaviors, constructing a machine learning model of a support vector machine, evaluating the safety states of the nodes, and according to a result output by the model, determining the inconsistent change rate of the nodes. The safety states of the nodes are divided into normal, slight abnormality and serious abnormality, for the nodes marked as slight abnormality, the system analyzes the abnormality trend and deviation of the nodes through a time sequence, automatically marks high-priority concerned nodes and generates a review task list to remind an operator to intervene.

The invention relates to the technical field of medical emergency monitoring, in particular to an ICU emergency response system which comprises a preliminary risk assessment module, an emergency recognition module, a treatment scheme optimization module, a vital sign monitoring module, an emergency response coordination module, a disease evolution prediction module, a resource allocation management module and a medical decision support module. According to the method, feature engineering and logistic regression analysis are combined with medical history and real-time vital signs of a patient, emergency medical events are recognized by applying pattern recognition and natural language processing, a treatment scheme is optimized by using a support vector machine and a decision tree, personalized treatment suggestions are provided, and the time sequence and a biometric method are used for finely monitoring the vital signs; health risks are early warned, resources are reasonably allocated in emergency response through a resource scheduling algorithm and a priority queue, illness state prediction is assisted through machine learning and probability statistics, resource utilization is improved through linear programming and a resource optimization strategy, and waste is reduced.

The invention discloses an AR glasses control system and method, and belongs to the field of artificial intelligence and AR glasses application, and the method comprises the steps: capturing a user face image, combining a voice assistant, collecting user voiceprint data, and carrying out the matching through a recurrent neural network; constructing a three-dimensional environment model, positioning and marking obstacles and interactive objects, and identifying objects in the environment; the method comprises the following steps of: tracking a gesture, acquiring a key point coordinate by adopting an OpenPose algorithm, identifying a predefined gesture by utilizing a support vector machine, and mapping the gesture into a specific operation instruction; analyzing the user intention based on natural language processing, and calling a corresponding function module according to an analysis result; acquiring a gazing direction of a user by using an eye movement tracking sensor, calculating a screen focus position through an algorithm, and dynamically highlighting options or displaying information according to a gazing point position; through multi-modal data fusion, gestures, voices and fixation point input are analyzed in a unified manner. By accurately understanding the intention of the user, the interaction precision of the AR glasses is improved, and the user experience is optimized.

The invention discloses a stone cultural relic disease identification method based on a hyperspectral image, and aims to solve the problem that stone cultural relic disease investigation depends on artificial experience and is time-consuming and labor-consuming. The method comprises the steps that a hyperspectral image of a stone cultural relic to be explored is collected and preprocessed; extracting spectral features; selecting a central wave band of three wave bands of blue light, green light and red light to construct a true color image; extracting texture features and color features of the true color image; fusing the spectral features, the texture features and the color features to obtain combined features; establishing a typical disease feature database; training a disease classification model by using a random forest, a support vector machine, a gradient elevator and a convolutional neural network; carrying out typical disease identification by using the intelligent identification model and drawing a disease cloud picture; and calculating the typical disease area proportion of the to-be-detected area to carry out disease evaluation. According to the invention, in-situ, lossless and rapid identification of stone cultural relic diseases is realized, manpower and material resources are saved, and an intelligent identification method is provided for cultural relic protection exploration work.

The invention discloses a burn and damaged skin recovery degree evaluation method based on skin image recognition, and the method comprises the steps: obtaining a visible light image and an infrared thermal imaging image of a skin burn patient, carrying out the preprocessing, and fusing into a skin burn image; performing feature extraction, recognition and segmentation to obtain a burn area image; constructing a static feature set based on the burn feature parameters, constructing a three-dimensional model of the burn wound based on the burn area image and the depth image, and constructing a dynamic feature set; and inputting the extracted static and dynamic features into the optimized deep learning-support vector machine fusion model for training, carrying out final classification on a recovery stage, and calculating the time required for complete healing. The method provided by the invention not only can effectively capture the static feature information of the burn area, but also can dynamically monitor the recovery change trend of the wound in real time, accurately predict the time required for complete healing, and can significantly improve the accuracy and personalized assistance of burn diagnosis and treatment.

A data-centric system for analyzing agricultural crops, consisting of: a data acquisition module configured to capture images of agricultural fields using cameras, unmanned aerial vehicles (UAVs) or sensors, with the sensors collecting data on soil moisture, temperature, light, humidity and pH; a data preprocessing module configured to: resize the acquired images to a standardized dimension suitable for input to a deep learning model; apply noise reduction using a Gaussian filter; improve image contrast through histogram equalization; and perform image magnification through rotation, reflection, and scaling transformations; a feature engineering module configured to extract the following features: color features, which include color histograms, mean, and standard deviation of color channels; texture features using Gray-Level Co-occurrence Matrix (GLCM) properties, which include contrast, dissimilarity, homogeneity, energy, angular moment (ASM), and correlation; shape features, which include contour area, perimeter, aspect ratio, and roundness; and other features, which include the green pixel ratio and edge density; a classification module configured to: implement deep learning-based classification models selected from the group consisting of Support Vector Machine (SVM), Artificial Neural Network (ANN), Convolutional Neural Network (CNN), ResNet18, Random Forest (RF), SegNet, VGGNet, Naive Bayes (NBG), Decision Tree (DT), K-Nearest Neighbors (KNN), and DeepLab; detecting and classifying weed species in the images of agricultural fields; and diagnosing plant diseases based on the features extracted from the images of agricultural fields; an output module comprises a user interface configured to display the classification and recognition results; and a recommendation module configured to suggest treatment solutions for diagnosed plant diseases through the output module's user interface.

The invention relates to the technical field of winter wheat growth and development recognition, in particular to a winter wheat growth and development recognition method based on a satellite remote sensing image, and the method comprises the following steps: S1, carrying out the preprocessing of the satellite remote sensing image; according to the method, satellite remote sensing images are preprocessed, including radiation correction, atmospheric correction, geometric correction and the like, so that noise and distortion in the images are eliminated, image quality is improved, planting and phenological characteristics of winter wheat are investigated and analyzed, specific planting phenological characteristics of winter wheat are obtained, extracted characteristics are classified and identified by using a support vector machine (SVM), and the winter wheat planting phenological characteristics are identified. Winter wheat areas in the images are judged, characteristics related to the wheat development stage can be extracted by analyzing the spectral reflectivity of wheat in different growth stages, the growth condition of winter wheat is evaluated, and the health condition of winter wheat and whether the problems of diseases and insect pests, water stress, nutrient deficiency and the like exist or not are analyzed according to the evaluation result. And corresponding management suggestions are provided accordingly.

The invention discloses a mechatronics product detection system based on an artificial intelligence image recognition technology, and relates to the technical field of artificial intelligence and mechatronics, and the mechatronics product detection system comprises an image acquisition module, a preprocessing module, a feature extraction module, a defect recognition module, a data management module, a result output module and a system control module, the preprocessing module has the functions of adaptive zooming and intelligent obstacle avoidance, and processes images by using a deep learning algorithm and a quantum filtering technology; a deep convolutional neural network is used for feature extraction, SVM and CNN are combined for defect recognition, a meta-learning mechanism is introduced, a distributed database and federated learning are adopted for data management, AR navigation and gesture interaction is used for result output, and a block chain intelligent contract is used for system control to deploy resources. The method has obvious advantages and high detection precision, and can accurately identify tiny and hidden defects; efficiency is greatly improved, and edge and cloud computing are combined to reduce processing time; operation is convenient, VR, AR and voice interaction are used, and the maintenance efficiency is improved.

The invention discloses a hydraulic power plant automatic debugging system with a self-adaptive communication function. The system comprises a processing unit, a storage unit, a communication module, an input / output interface, a task classification module, a model architecture configuration module and other functional modules. The use method comprises the following steps: analyzing task complexity and high-dimensional features of input data through a task classification module, and grading by adopting algorithms such as principal component analysis and a support vector machine; the model architecture configuration module is used for matching a model architecture according to the complexity level and determining an initial calculation path; the dynamic path adjustment module optimizes a calculation path in combination with real-time data, and the resource distribution module redistributes resources when the calculation power exceeds the limit; the model compression module generates a compression model adaptive to the edge device through pruning and quantization algorithms; the parameter fine tuning module is used for jointly optimizing model parameters for a multi-task scene; according to the method, the adaptability and efficiency bottleneck of an existing debugging tool in a complex scene is effectively solved, and the intelligent debugging level of an automatic system of a hydraulic power plant is improved.

The invention discloses a fire-fighting fireproof door alarm information transmission device and method based on the Internet of Things, and relates to the technical field of fire-fighting alarm, and the method comprises the following steps: carrying out the multi-band continuous scanning of a wireless communication environment of a fireproof door alarm device deployment region after a fire emergency mode is started, identifying a target communication protocol frequency band used by the fireproof door alarm device, and obtaining spectrum parameter information of each frequency band to form a to-be-analyzed communication frequency band set; and extracting a working frequency band used by the peripheral wireless equipment based on a pre-established environment wireless equipment frequency band database. Frequency spectrum mapping is constructed through frequency spectrum scanning and an environment database, intelligent interference prediction is realized in combination with a support vector machine, coding parameters are dynamically adjusted based on interference intensity, the transmission reliability of key alarm information in a high-interference environment is improved, feedforward recognition and closed-loop regulation and control capabilities are achieved, and the method is suitable for popularization and application. And the problems of slow response and unstable transmission of a traditional system are effectively solved.

The invention discloses a data-driven fault detection and protection method and system for a low-voltage AC / DC power distribution network. The method comprises the following steps: acquiring electrical quantity data, equipment operation state parameters, environment data and user behavior data of each node of the low-voltage AC / DC power distribution network in real time; fusing various types of data to form a fused data set, and extracting correlation information of the fused data set and the fault detection indexes; building a hybrid intelligent model based on a convolutional neural network, a long-short-term memory network and a support vector machine, and carrying out fault feature extraction and classification diagnosis; establishing a time sequence model of fault development, and predicting the future development situation of the fault; determining a fault position by considering an electrical quantity change characteristic, an equipment physical position and a communication network topology; and making a protection strategy according to the fault type, the future fault development situation, the fault position and the current operation state of the power distribution network. According to the invention, the accuracy and reliability of fault detection of the low-voltage AC / DC power distribution network can be improved, and the operation state of the power distribution network can be comprehensively and accurately mastered.

The invention discloses a casting density optimization system and method based on cooperative regulation and control of molding sand moisture and clay blue absorption amount, and relates to the technical field of casting control. According to the method, a self-cleaning wear-resistant alloy probe is used for synchronously collecting a molding sand high-frequency eddy current signal and a multi-spectrum near-infrared signal in the sand mixing process; inputting a pre-training support vector machine regression signal fusion model to obtain a real-time moisture content and a clay blue absorption amount; a preset density target threshold value is combined, a density-molding sand parameter association database is inquired to determine a parameter target interval, a regulation and control instruction is generated after a deviation value is calculated, and a water adding device and a clay conveying device are controlled to adjust the use amount; the density of the casting after regulation and control is detected, if the density does not reach the standard, model output weight iteration optimization is corrected until the density reaches the standard, the system comprises a detection module, a signal processing module, a regulation and control execution module, a density detection and correction module and a central control module, closed-loop control is achieved, and the density stability of the casting is improved.

The invention relates to the technical field of fault prediction and health management, in particular to a primary and secondary fusion complete ring main unit fault diagnosis method and system. Comprising the following steps: acquiring three-phase instantaneous voltage and current signals in real time, and converting the signals into digital transient data; performing time window preprocessing on the digital transient data, and executing wavelet packet decomposition to generate a transient feature vector; calculating and analyzing the transient feature vector through a transient zero-sequence power direction method and a support vector machine model to generate a local diagnosis result; when the local diagnosis result is that cooperative positioning needs to be started, a transient current similarity coefficient and a transient waveform intensity difference coefficient are calculated based on the digital transient data, and a comprehensive positioning result is generated; determining a fault line according to the comprehensive positioning result, and generating a remote control command; and executing a fault isolation operation based on the remote control command, and executing a PHM process. According to the method, the double local transient diagnosis and the cross-terminal cooperative positioning are deeply fused, so that the high-precision determination of the boundary of the fault section is realized.

The invention discloses a railway LEU-transponder transmission system lightning stroke fault risk assessment method, and the method comprises the steps: determining a lightning current invasion path through building a lightning stroke transient electromagnetic disturbance calculation model of an electromagnetic sensitive equipment port, and calculating the voltage and current at the port when incoming waves invade. And building an electromagnetic sensitivity test experiment platform of the railway signal system based on the lightning current invasion path and the voltage and current at the port. And performing label category prediction on the to-be-predicted sample point through each support vector machine model in the target model set, and voting each prediction result. According to the invention, a complex transmission relation between lightning transient electromagnetic disturbance and equipment failure risk is established through deep learning. The fault risk of the signal system under the lightning transient electromagnetic disturbance action is predicted through transient electromagnetic effect experimental data of real equipment of the railway signal system, and powerful support is provided for improving the electromagnetic sensitivity of the signal system and guaranteeing stable operation of a railway.

The invention discloses a blood, urine and body fluid collecting, detecting, analyzing and uploading system based on multi-sensor integration, which comprises the following modules: a blood collecting module for collecting a blood sample; the urine collection module is used for detecting urine; the body fluid collecting module is used for detecting body fluid; the data processing module is used for preprocessing data; the feature extraction and classification module is used for constructing a multi-modal feature matrix based on a neural structure search network, a support vector machine and a random forest algorithm; the anomaly detection module is used for generating a weighted anomaly score in combination with an isolated forest and a depth anomaly detection model; the time sequence analysis module is used for analyzing the health trend by using a variational auto-encoder-generative adversarial network; the health portrait and risk assessment module is used for constructing a health map by adopting a graph convolutional network; and the encryption and uploading management module is used for encrypting by using AES and RSA and managing the data access authority based on the intelligent contract. According to the invention, a multi-modal sensor and an intelligent algorithm are integrated, and collection, detection, analysis, encryption and uploading of blood, urine and body fluid are realized.

Disclosed are twin-based systems and methods for predicting solar power generation and optimizing power generation and distribution processes. Employed are a digital twin model of a solar power plant, which includes detailed representations of various components, such as solar panels, inverters, and transformers, as well as real-time weather data and historical data. This advantageously allows for accurate simulations of plant performance under various weather conditions and operational scenarios. Our systems and methods Incorporate novel machine learning algorithms that are trained on historical and real-time data from the digital twin model, weather data, solar power generation data, and other relevant factors. These algorithms utilize an advanced ensemble learning approach, which combines multiple predictive models, such as deep learning, support vector machines, and decision trees, to achieve higher accuracy and robustness in predicting solar power generation

A system may receive request electronic data messages and counter-request electronic data messages from various network participant nodes within a defined time interval. The system may extract data from the electronic data messages to generate input codes including indicators that characterize execution values and imputed variability levels for the electronic data messages and / or characterize the message types of the electronic data messages. The input codes are used to generate a time-interval-specific support vector machine for the defined time interval. The system may then generate dummy data including execution value and imputed variability level tuples. The dummy data is used to map boundary levels from the time-interval-specific support vector machine versus execution values.

The invention provides an imperfect soybean hyperspectral imaging classification method based on deep learning. Efficient and accurate classification is realized by fusing spectrum and image features. Acquiring spectrum and image data by using a hyperspectral imaging system; the data quality is improved through a preprocessing method; and constructing a dual-channel feature fusion model, and reinforcing key feature extraction in combination with an attention mechanism. According to the method, the classification precision of 95.13% and 94.00% in the visible light-near infrared band and the short wave infrared band is achieved, and compared with a traditional support vector machine and a convolutional neural network method, the classification precision is remarkably improved. The model deeply digs spectral image features through a deep learning network, analyzes the association between the spectral image features and soybean quality, and enhances the robustness and generalization ability of the model. The method has the advantages of being high in precision, rapid in detection, high in adaptability and the like, is suitable for different varieties and large-scale detection scenes, and provides an efficient solution for agricultural product quality monitoring, automatic sorting and agricultural scientific research.