23 results about "Multiclass classification" patented technology

In some embodiments, a method for classifying elements of a blood sample is provided, the method including: digitally staining an image of the blood sample using a trained machine learning model to generate a digitally stained image; extracting one or more intermediate features generated by the trained machine learning model during the digital staining of the image; providing the one or more extracted intermediate features to a trained multi-class classifier; and employing the trained multi-class classifier to classify at least one element in the blood sample based on the one or more extracted intermediate features. Many other embodiments are also provided.

The application discloses an open set image classification field self-adaption method based on self-step learning, first, the original image is preprocessed to obtain an image set, then a feature extraction module and a double multi-class classifier module are constructed and trained to align shared class features of source domain images and target domain images and separate target domain private class features, a multi-criteria cross-domain hybrid module is further constructed and trained, cross-domain hybrid images are generated by using the source domain images and the target domain images, and the shared class features are self-learned, and finally, a classification result of the target domain image is output. Compared with the existing open set image classification field self-adaption method, the application covers smooth and non-smooth class distribution, and does not need to empirically adjust the threshold for distinguishing common class images and private class images in the inference stage, so that the model has good robustness under different hyperparameters and experimental settings.

The invention provides a double-flow feature embedded driving fatigue detection system based on transfer learning, and relates to the technical field of machine vision and intelligent traffic, and the system comprises a facial feature extraction module which is used for receiving a driver facial image collected by a vehicle-mounted camera in an actual driving environment; the head posture estimation module is used for processing the head posture data set to capture the fatigue behavior performance of the driver; the migration fusion module is used for performing learnable fusion on the face visual feature vector and the head posture feature vector and converting the fusion into high-dimensional fusion feature representation; and the state classification and prompt feedback module performs multi-class classification, outputs a fatigue detection result, and is used for real-time driving state judgment and early warning. According to the method, the end-to-end heterogeneous feature embedding framework is constructed by fusing the facial representation and the three-dimensional head posture features. According to the method, efficient fusion of cross-source data features in a unified embedding space is realized, and high-reliability perception and early warning of driving fatigue behaviors are ensured.

The present disclosure describes apparatuses and methods of anomaly classification. In one embodiment, an apparatus performs binary classification of data samples in a dataset to classify the data samples into a normal group or an anomaly group; performs multiclass classification to classify the data samples in the anomaly group into anomaly classes, and identifies a first set of data samples in the anomaly group as false positives resulting from the binary classification when the multiclass classification fails to classify the data samples in the first set into one of the anomaly classes.

Machine learning techniques can be applied to distinguish attacks (including enumeration attacks and account-testing attacks) from normal transaction activity. An ensemble machine learning model can include at least two generative units, one of which is trained using normal transaction data and another of which is trained using attack transaction data. Each generative unit produces a reconstructed output from a given input in a manner that reflects latent patterns in either normal or attack transactions. The reconstructed outputs and the original transaction data can be provided to as inputs to a machine learning classifier, such as a multi-label (or multi-class) classifier, that determines probability scores to different transaction types (or labels), including a first label indicating normal transactions, a second label indicating attack transactions, or a third label indicating uncertain transaction type. Based on the probability scores, the transaction can be classified as normal or attack type.

The invention relates to the technical field of ecological system monitoring and evaluation, and discloses an ecological system health evaluation method based on machine learning. The method comprises the following steps: collecting multi-source continuous monitoring data of an ecological system, and carrying out integrity check and noise filtering to generate a standardized data set; performing multi-scale feature mining on the data set, and extracting ecological feature sequences of a time domain and a frequency domain; performing community discovery on the feature sequence by adopting a spectral clustering algorithm, and outputting a clustering result of the ecological health state; constructing a multi-class classification model according to the clustering result, and adjusting the weight of the model through iterative learning; and inputting the real-time ecological data flow into the trained multi-class classification model, performing probability prediction of the health state, and automatically generating a state evaluation chart. According to the method, the health state can be adaptively defined from the data, and objective and dynamic evaluation of ecological system health is realized.

Examples relate to an image process system for markerless patella-femoral joint identification, the system comprising: a. a machine learning interface to a multiclass classification deep learning model; the machine learning interface being arranged to receive an input vector; the input vector comprising at least one, or both, of: image information and depth information associated with a patella-femoral joint; the multiclass classification deep learning model being trained to generate multiclass classification data; the multiclass classification data comprising at least: i. semantically segmented image data comprising at least one mask corresponding to a respective at least one member (distal end of femur, proximal end of tibia, patella) of the knee joint one of which being the patella, and b. a machine learning output interface of the multiclass classification deep learning model; the machine learning output interface being arranged to output the multiclass classification data.

In various embodiments, systems and methods for quantum-based network traffic anomaly detection are disclosed. Embodiments for a network integrity monitor are disclosed that leverage a quantum computing-based network assessment function to evaluate network event data for the purposes of identifying and / or predicting anomalies indicative of network threats. To identify network anomalies, the network assessment function may treat the anomaly identification as a quantum search task by searching the task data using an amplitude amplification quantum search algorithm and / or using quantum machine learning models to infer a threat prediction that may include a single or multiclass classification characterizing the task data. Such classification(s) may be further assessed by the network integrity monitor as the basis to trigger one or more mitigating steps.

A method may include applying noise to a first real image to generate a first noisy image. Then, the method may include generating a first synthetic image corresponding to an estimate of a first class of synthetic image, and computing a guidance strength of the first synthetic image based on probabilities determined from a multi-class classifier, wherein the probabilities may include a first probability of the first class of synthetic image and a second probability of a second class of synthetic image, and denoising an amount of noise determined based on the guidance strength.

As described herein, a system, method, and computer program are provided for a multi-stage multi-class classification. A dataset having an imbalanced distribution of data across a plurality of classes is identified. The plurality of classes are grouped into a plurality of clusters, based on a defined criteria. A plurality of machine learning models are trained, each machine learning model of the plurality of machine learning models trained using a subset of the data in the dataset corresponding to a particular cluster of the plurality of clusters. The plurality of machine learning models are used, in stages, to predict a classification for a given input.

This disclosure relates to a method and system for multi-sensor fusion in the presence of missing and noisy labels. Prior methods for multi-sensor fusion do not estimate and correct labels for learning effective models in semi-supervised learning methods. Embodiments of the present disclosure provides a method for learning robust sensor-specific autoencoder based fusion model by utilizing a graph structure to perform label propagation and correction. In the disclosed Graph regularized AutoFuse (GAF) method latent representation for each sensor is learnt using the sensor-specific autoencoders. Further these latent representations are combined and fed to a classifier for multi-class classification. The disclosure presents a joint optimization formulation for multi-sensor fusion where label propagation and correction, sensor-specific learning and classification are executed together.

A multi-class classifier (MCC) is trained using annotated data. The annotated data comprises instances of sample data and associated label data. Creation of the annotated data and subsequent active learning by the MCC uses resources. A target-aware active learning system selects sample data for addition to an annotation queue based on factors such as current accuracy of a particular class determination and priority of that class. As each instance in the sample data in the annotation queue is annotated and used for subsequent training, accuracy of particular classes is improved until a specified accuracy for that class is attained. By being selective in the ordering of instances in the annotation queue, overall resource usage and corresponding costs associated with creating annotated data and training is reduced. Overall accuracy for all classes is improved using a smaller overall set of annotated data compared to naïve approaches.

In some embodiments, a method of classifying components of a blood sample is provided that includes digitally staining an image of a blood sample using a trained machine-learning model so as to generate a digitally-stained image; extracting one or more intermediate features generated by the trained machine-learning model during digital staining of the image; providing the one or more extracted intermediate features to a trained multi-class classifier; and employing the trained multi-class classifier to classify at least one component within the blood sample based on the one or more extracted intermediate features. Numerous other embodiments are provided.

Device type discovery for a private network can be performed based on network address translated (NAT′d) network traffic generated from the network. A security solution analyzes data of network traffic from network devices using a binary classifier to determine whether the network traffic is from a NAT device. A network traffic dataset for a first time interval is preprocessed to generate a feature vector for the binary classifier, the output of which indicates whether the traffic is NAT′d. For NAT′d traffic, the security solution analyzes subsets of the network traffic dataset of smaller intervals within the first time interval. The security solution determines feature values from each network traffic data subset and generates feature vectors which are input to a multiclass classifier to obtain a device classification for each network traffic data subset.

The invention relates to the technical field of data management, in particular to a communication data security management method and system based on artificial intelligence and big data, and the method comprises the steps: extracting information closely related to communication security risk identification from original communication data, and standardizing the information into input data required by subsequent semantic identification and behavior modeling, constructing a semantic feature vector from the input data through deep language representation, inputting the semantic feature vector into a multi-class classification network for security classification prediction, and outputting a security classification label; constructing an anomaly detection module, and outputting a modal deviation score through a modal deviation distance measurement function; inputting the modal deviation score into a joint risk scoring function, outputting a risk score through the joint risk scoring function, and performing hierarchical mapping on the risk score to generate a risk level label; and calling a basic strategy corresponding to the risk level from the template library according to the risk level label, carrying out nonlinear refinement on the basic strategy, and generating a safety control instruction.

A method may include obtaining a multi-dimensional training dataset that includes multiple datums. Each of the datums may correspond to a number of quantum bits (qubits) and may represent a quantum state. The method may also include generating, using a quantum computing device, a Gram matrix based on the multiple datums. In addition, the method may include determining, using a classical computing device, multiple operators according to a constraint defined by the Gram matrix. Each of the operators may be configured as a proxy for a corresponding datum. Further, the method may include assigning, using the classical computing device, each of the operators to a label.

The present disclosure is related to the field of machine learning (ML) based detection and classification. More specifically, the present disclosure provides computer implemented methods of detection and multi-class classification of objects of interest in an image, computer program product operable in a computer, and diagnostic methods thereof.

Systems and methods described herein extend Functional Neural Networks (FNNs) for time series dimension reduction and multi-class classification. Using functional encoders and decoders, the Bi-Functional Autoencoder (BFAE) reduces both the number of features and timepoints (two way) using basis expansion. FNN is also extended to facilitate time series multi-class classification, which enables detecting more than two classes in the data. The functional encoder uses the continuous neurons in the continuous hidden layer to derive a low-dimension latent representation of the data. This representation is then processed by functional decoder to reconstruct the original information. For multi-class classification, the system utilizes cross-entropy loss and a softmax activation function to effectively handle more than two classes to improve classification performance.

Systems and methods of the present disclosure are directed to a computer-implemented method for training a machine-learned multi-class object classification model with partially labeled training data. The method can include obtaining image data depicting objects and ground truth data comprising a subset of object class annotations respectively associated with a subset of object classes of a plurality of object classes. The method can include processing the image data with the machine-learned multi-class object classification model to obtain object classification data. The method can include evaluating a loss function that evaluates a multi-class classification loss and adjusting one or more parameters of the multi-class object classification model based on the loss function.

To diagnose the occurrence of unknown abnormality.SOLUTION: An abnormality diagnosis device according to one aspect of the present disclosure is an abnormality diagnosis device that, based on state data representing a state of a target device and a multi-class classification model created from labeled data by supervised learning, A first abnormality diagnosis unit configured to calculate a plurality of first probabilities that the state data is classified into each of a plurality of classes including a class representing a normal state and classes respectively representing one or more known abnormalities; A second abnormality diagnosis unit configured to calculate a second probability that the state data is classified into a class indicating normality, and an integration unit configured to calculate, based on the plurality of first probabilities and the second probability, a third probability that the state data is classified into a class indicating an abnormality and one or more fourth probabilities that are classified into one or more known classes indicating one or more abnormalities.SELECTED DRAWING: Figure 2

The invention discloses an image recognition robustness improvement method based on context enhancement and query disassembly and a storage medium, and the method comprises the steps: employing a context enhancement prompt structure, and introducing a natural language description of a target category or a semantic background in input, so as to assist a language model in analyzing visual content; a query decomposition mechanism is adopted, an original multi-class classification task is decomposed into a plurality of sub-problems based on existence judgment, and reasoning and decision making are carried out by integrating a plurality of sub-task results. A computer program used for executing the method is stored in the storage medium. The method has the advantages of being simple in principle, easy to implement, capable of remarkably enhancing robustness and the like.

The system and method described in the description of the present application extend a functional neural network (FNN) for time-series dimensionality reduction and multi-class classification. The present invention uses a functional encoder and decoder, and a bi-functional auto-encoder (BFAE) uses base expansion to reduce the number of both features and points in time (two directions). The FNN also facilitates time-series multi-class classification, thereby enabling three or more classes of data to be detected. The functional encoder derives a low-dimensional latent representation of the data by using the continuous neurons of a continuous hidden layer. The representation is then processed by the functional decoder in order to reconstruct the original information. In the case of multi-class classification, the system utilizes cross entropy loss and a softmax activation function to effectively handle three or more classes and improve classification performance.