14 results about "Knn classifier" patented technology

The invention provides a medium-voltage line topology identification method based on a KNN classifier and a related device, and the method comprises the steps: collecting the signal power and noise power of topology identification equipment under different frequencies, and calculating the useful signal power of a self-transmitting and self-receiving micro-current and a self-transmitting and self-receiving micro-current; thirdly, in combination with an actual field shunting condition, taking frequency information, two types of useful signal power and shunting data as input, and training a KNN model; and finally, inputting frequency information of actual operation and two types of useful signal power into the model, adaptively outputting shunt judgment, and fusing non-shunt data to obtain actual topological information. According to the invention, through data training learning, the line shunting phenomenon is effectively identified, and the topology identification accuracy is improved.

The invention relates to the technical field of mechanical system fault diagnosis, and discloses an unbalanced Transform-based mechanical system fault zero sample positioning method, which comprises the following steps of: determining the type and the position of a shock absorber to be subjected to fault monitoring; vibration signals are collected and de-noised to divide samples of known and unknown fault position categories, and meanwhile, the samples of the known fault position categories are fitted to construct a training set and a test set; constructing a semantic description matrix containing a plurality of attributes; for each attribute, constructing a Transform model respectively, and performing training in combination with a training set input model to generate a mapping function set from the data to the attributes; constructing a paired sample, and inputting the paired sample into a KNN classifier for training; inputting each test sample into the mapping function set to obtain an attribute vector set of each test sample, inputting the attribute vector set into the trained KNN model for reasoning, and generating a fault positioning result of each test sample; according to the invention, accurate fault position identification under the condition that no fault position category sample participates in training is realized.

This invention relates to the field of attitude control technology, and more particularly to a complementary filter gain adjustment method based on a KNN classifier. The method includes: during the model training phase, acquiring triaxial accelerometer data; calculating the accelerometer output modulus and variance values ​​at each time step; constructing a dataset containing the modulus, variance, and adaptive threshold; inputting the training data into the KNN algorithm to construct a KNN model; during the real-time attitude calculation phase, calculating the modulus and variance values ​​using the real-time acquired triaxial accelerometer data, and then inputting them into the KNN model to obtain the adaptive threshold; multiplying the adaptive threshold by a scalar gain to obtain a corrected gain; and substituting the corrected gain into the final attitude estimation formula to calculate the attitude. This invention addresses the deficiency of existing complementary filter algorithms in accurately and adaptively adjusting the scalar gain during attitude calculation, leading to insufficient accuracy and reliability in attitude calculation.

A virtual power station false data injection attack cooperative defense method, in the offline stage, respectively construct and train KNN classifier containing feature construction unit, distance calculation unit, near neighbor voting unit and abnormal marking unit, and graph autoencoder containing graph signal mapping unit, node mask unit, graph encoder and graph decoder, in the real-time defense stage, through the trained KNN classifier, the measured vector polluted by false data injection attack (FDIA) is classified, the abnormal data node set is obtained, and the node set is mapped into graph signal, then through the trained graph autoencoder, data reconstruction is carried out according to the graph signal.The present application can accurately locate the aggregation unit node attacked after the system is attacked, and then restore the maliciously tampered measurement data, that is, reconstruct the operation state of the virtual power plant, effectively defend the false data injection attack, and fundamentally improve the situation awareness ability, survivability and safe operation level of the virtual power plant when it is attacked by the false data injection attack.

The invention is applicable to the technical field of air filtration, and discloses an air filtration method, system, equipment and medium, the method comprises the following steps: acquiring pollutants and operating parameters, and constructing pollutant state vectors; performing time window processing on the pollutant state vector to obtain a pollution trend structure vector; based on the pollution trend structure vector, a KNN classifier is adopted to construct a pollution trend identification model, and a trend label is obtained; an optimal filtering path combination and a current recommended wind speed are obtained by combining the pollutant state vector and the operation parameter through the trend label and are used for path switching and wind speed adjustment; after path switching and wind speed adjustment are completed, the blocking trend is judged according to the operation parameters; and based on the existence of the blockage trend, a blockage duration recording mechanism is adopted to evaluate the risk level, and a maintenance prompt is generated and executed, so that air filtration is realized, and the safety, stability and intelligent level of operation of the air filtration method are remarkably enhanced.

This invention belongs to the technical field of image classification and discloses a medical image classification method based on Lie group kernel learning. The method includes acquiring low-level image features and representing them as a Lie group matrix; obtaining the model parameters of an SVM classifier and the pivot point for each class through a training image set; and selecting either an SVM or KNN classifier to classify the images based on the geodesic distance between the class pivot point and each image to be classified, calculated using the Lie group kernel function on the Lie group manifold. This invention outperforms traditional image classification methods in terms of classification accuracy. Compared to artificial neural network methods, it has less dependence on training data and processes, and exhibits stronger generalization and deployability.

The present invention discloses a frequency domain-based image global manipulation forensics method, which relates to technical fields such as digital image processing, computer vision, signal processing, and machine learning. The specific steps are: 1) collecting and organizing public image samples; 2) performing one or more typical image operations on the public images to construct an image data set and obtain labels of the manipulated images through annotation. 3) performing forensic feature extraction based on the frequency domain of the image histogram and detail image; 4) using the trained model to test the forensic frequency features of global manipulation of multiple images to obtain the final classification results. This method utilizes the proposed forensic frequency features, combined with the model obtained by training the KNN classifier, to detect global manipulation of multiple images in reality, and can also detect images generated by the network. The invention has practical significance and shows good detection performance in subsequent forensic tasks.

The application discloses an Internet of Things intrusion detection method and system, and relates to the fields of information security and Internet of Things; the method comprises the following steps: carrying out feature selection, one-hot encoding, normalization, sample balancing and data cleaning preprocessing on Internet of Things traffic data; training a generative deep learning model AAE and BiGAN based on the preprocessed IoT-23 data set; after the real-time collected traffic is preprocessed, the AAE or BiGAN model is used to distinguish abnormal and normal traffic, and then a KNN classifier is used to determine the attack type; the abnormal traffic features are stored in an IoTDB time series database; according to the review results of a vulnerability library and a threat intelligence library, the TPR, TNR, FPR, FNR and unknown category proportion UNR are calculated, the AAE and BiGAN are switched according to the UNR, the model retraining is triggered according to the TPR-FPR difference or the TNR-FNR difference, and the sample balancing coefficient R is dynamically adjusted. Through the two-stage detection framework and the dynamic feedback mechanism, the application improves the Internet of Things intrusion detection accuracy and reduces the deployment cost.

A KNN-based lateral stability control method for heavy-duty AGVs is disclosed, characterized by the following steps: 1. Classifying AGV operating conditions into five categories based on different loads, and collecting motion state data of the AGV under different operating conditions using simulation software; 2. Establishing a K-nearest neighbor (KNN) classifier, and training and validating it using the collected dataset; 3. Designing a set of nonlinear sub-controllers based on fuzzy PID, calculating the required yaw moment, and distributing the torque to the four drive wheels according to the torque distribution rule; 4. Introducing an error judgment strategy, activating the controller based on the centroid sideslip angle error to control its lateral stability. This invention establishes a load KNN classifier for heavy-duty AGVs, which can monitor the centroid sideslip angle error in real time. If the error exceeds a threshold, the controller is activated, the classifier's classification result is matched to the corresponding sub-controller, and an additional yaw moment is calculated and applied to the AGV.

The application discloses a kind of wearable assembled building industry worker emotional intelligent monitoring method and device;Its technical points are in, S100, physiological signal is collected;The physiological signal includes: electrocardiogram signal;S200, the electrocardiogram signal obtained by S100 is carried out denoising processing;S300, extract heart rate variability HRV characteristics from electrocardiogram signal, including time domain feature and frequency domain feature;S400, the extracted HRV characteristics are passed through trained SVM-KNN classifier, to identify emotional category;S500, the identification result is output to handheld end.Using a kind of wearable assembled building industry worker emotional intelligent monitoring method and device, the emotion of industry worker can be effectively identified.

The invention discloses an Internet of Things intrusion detection method and system, and relates to the field of information security and Internet of Things. Comprising the steps of performing preprocessing of feature selection, one-hot coding, normalization, sample balance and data cleaning on Internet of Things traffic data; training a generative deep learning model AAE and a generative deep learning model BiGAN based on the preprocessed IoT-23 data set; after traffic collected in real time is subjected to the same preprocessing, an AAE or BiGAN model is firstly used for distinguishing abnormal and normal traffic, and then a KNN classifier is used for judging an attack type; abnormal traffic characteristics are stored in an IoTDB time sequence database; the method comprises the following steps: regularly calculating TPR, TNR, FPR, FNR and unknown category ratio UNR according to examination results of a vulnerability library and a threat intelligence library, switching between AAE and BiGAN according to the UNR, triggering model retraining according to a TPR-FPR difference value or a TNR-FNR difference value, and dynamically adjusting a sample balance coefficient R at the same time. Through a two-stage detection framework and a dynamic feedback mechanism, the Internet of Things intrusion detection accuracy is improved, and the deployment cost is reduced.

The present invention discloses a method for automatically assessing the average grain size of metal materials using the intercept method, which relates to the field of metallographic image analysis of metal materials. The method comprises the following steps: selecting a recognition model based on the material being tested; inputting an optical microscope image (pic) into a system equipped with the recognition model; extracting scale information from the input image (pic) using mask extraction and Hough line detection: first, extracting the scale area using a mask, then extracting the scale length using a Hough line detection algorithm, and finally extracting the scale value using a KNN classifier; identifying grain boundary pixels in the input image using the selected recognition model; classifying each pixel in the input optical microscope image (pic) using a UNet to determine whether it is a grain boundary pixel; and finally optimizing the image. The optimized grain boundary image is then graded using the intercept method, the number of intercepts per unit length is counted, and the grain size G is calculated. The present invention significantly improves the accuracy and consistency of grain size assessment.

The application provides an interpretable image classification method and system based on artificial features, and the method comprises the following steps: extracting color, brightness, edge, spot and corner features artificially designed for an input image; separating, normalizing and performing multi-threshold binaryzation on feature values; calculating sub-block level purity values and performing feature logic combination; optimizing storage by recording parent serial numbers and deleting new feature map data; screening features by using purity, area and expansion rate, calculating average response and splicing into a feature vector; and finally performing a classification task by constructing a KNN classifier through fixed-point processing and city distance.

The invention discloses an acoustic feature fusion-based Chinese zither playing skill intelligent identification method and system, and relates to the technical field of audio analysis. Comprising an acquisition and processing unit, a feature extraction unit, a feature fusion unit and a classification and identification unit, and through multi-domain acoustic feature fusion (time domain short-time energy, zero-crossing rate, frequency domain spectrum energy distribution and time-frequency domain wavelet energy proportion) and in combination with a KNN classifier, accurate and intelligent identification of the Chinese zither playing skill is realized. The constructed sample library covers a plurality of typical skills and is standard in marking, efficient in model training and high in recognition accuracy. In application, the method can assist in skill improvement of learners in music education and provide quantitative analysis basis for music appreciation; and in the technical level, reference is provided for intelligent identification research of other musical instruments or music elements, the development of music intelligent analysis technology is promoted, the application direction of acoustic signal processing in the art field is expanded, and practical value and scientific research popularization significance are achieved.