Patents
Literature
Patsnap Eureka AI that helps you search prior art, draft patents, and assess FTO risks, powered by patent and scientific literature data.

12results about How to "Reliable classification" patented technology

Software vulnerability type identification method based on long-tail incremental learning

ActiveCN119646822Areliable classificationmitigation of catastrophic forgettingBiological modelsPlatform integrity maintainanceData streamData set
The invention provides a software vulnerability type identification method based on long-tail incremental learning, and belongs to the technical field of software engineering. The technical problem that the vulnerability type recognition precision is reduced due to disastrous forgetting and long tail problems when an existing method is used for dealing with dynamic data streams is solved. According to the technical scheme, the method comprises the following steps: (1) searching a vulnerability type identification data set, and performing task division according to vulnerability publishing time; (2) selecting typical vulnerability samples from the old task data by using mixed playback; (3) designing a mixed prompt template and a mapping method, fusing source codes and vulnerability descriptions, and inputting the fused source codes and vulnerability descriptions into CodeT5 for model and prompt template training; (4) introducing an EWC regularization item; and (5) fusing the vulnerability code and description by means of the mixed prompt template to predict the vulnerability type. The method has the beneficial effect that the problems of disastrous forgetting and long tails are relieved.
Owner:NANTONG UNIV

Software vulnerability assessment method based on continuous learning

ActiveCN119026138Amitigation of catastrophic forgettingeasy to digBiological modelsPlatform integrity maintainanceData setData stream
The invention provides a software vulnerability assessment method based on continuous learning, and belongs to the technical field of software engineering. The technical problem that the evaluation precision is reduced due to catastrophic forgetting when the dynamic data flow is dealt with is solved. According to the technical scheme, the method comprises the following steps: (1) collecting and processing a data set related to vulnerability severity prediction, and dividing the data set into several tasks; (2) replaying the number of old tasks by using the model confidence; (3) fusing source codes and vulnerability descriptions, and inputting the fused source codes and vulnerability descriptions into CodeT5 for model and prompt template training; (4) introducing an EWC regularization item, and ensuring that parameters do not have large deviation when a new task is trained; and (5) fusing the source code and the vulnerability description by means of a mixed prompt template, inputting the model and completing the prediction of the severity. The method has the advantages that by means of prompt fine adjustment and fusion of source codes and vulnerability description, vulnerability assessment is conducted according to dynamic data of real projects, and the problem of disastrous forgetting is relieved.
Owner:NANTONG UNIV

Open set across network node classification method and apparatus

ActiveCN119939320Baccurate classificationreliable classificationBiological modelsEngineeringA domain
The application discloses an open set cross-network node classification method and device, relates to the field of machine learning, and designs a framework of separating first and then adapting to a domain. First, an unknown class and a known class are separated by constructing a rough boundary through adversarial learning, and then a pseudo label is allocated to iteratively train a model in a self-training manner, so that a more accurate boundary is gradually generated for separating the known class and the unknown class. Secondly, in the domain adaptation stage, a negative domain adaptation coefficient is allocated to the nodes of the unknown class, and a positive domain adaptation coefficient is allocated to the nodes of the known class, so that the nodes of the known class of the target network are aligned with the source network, and the nodes of the unknown class of the target network are pushed away from the source network, thereby realizing the adversarial domain alignment excluding the unknown class, and further realizing the classification of the open set cross-network node with high accuracy.
Owner:HAINAN UNIV

Image analysis processing system and method based on thought control

The invention relates to the field of brain image processing, in particular to an image analysis processing system and method based on thought control, and the system comprises an electroencephalogram signal collection system which is used for collecting and preprocessing electroencephalogram signals of a user; the thought analysis system is used for extracting features from the preprocessed electroencephalogram signals and then carrying out thought classification and instruction mapping; the image acquisition and processing system is used for acquiring image information according to the mind control instruction of the user and performing image processing; the VR display system is used for converting the processed image into a format suitable for VR equipment display and providing interactive feedback; and the control and communication system is used for converting the mind state into a control instruction and realizing data transmission and communication among the systems. The EEG signals and the fNIRS signals are acquired through the multi-mode signals, the defect of a single signal in the aspect of reflecting the brain activity is overcome, and therefore brain activity information corresponding to the thought is more accurately interpreted.
Owner:HANGZHOU JIUSHU TECHNOLOGY CO LTD

Blood sample analyzer and rapid sample analysis system and method

The invention discloses a blood sample analyzer and a rapid sample analysis system and method. The blood sample analyzer comprises a sampling needle, an RBC / HGB test solution preparation pool and at least two DIFF pools. Blood sample collection and separate injection are completed through the sampling needle, the number of the reaction units is strictly controlled, the occupied time of the sampling needle for executing sample separate injection to the reaction units is correspondingly shortened, continuous and rapid detection of constant blood samples and trace blood samples is achieved, and the highest detection speed is larger than or equal to 200 T / h. Meanwhile, the blood sample analyzer is low in sample consumption demand, and the consumption of the required reaction reagent can be reduced along with the reduction of the sample size, so that the detection cost can be reduced. Meanwhile, the optical detector only carries out DIFF channel detection once, the flow of sample liquid can be controlled to be below 8uL / s, the pressure of sheath liquid needing to be matched can be less than 120kpa, and the problems of high process difficulty and high cost of existing rapid blood analysis are well solved.
Owner:ZYBIO INC

Unbalanced malware detection enhancement method based on cwgan-gp data augmentation and textcnn-transformer fusion

PendingCN122508577AImprove enhancement qualityMitigating bias
This invention discloses an imbalanced malware detection enhancement method based on the fusion of CWGAN-GP data augmentation and TEXTCNN–TRANSFORMER, comprising the following steps: S1, data acquisition and preprocessing: running an executable file in a controlled sandbox environment to dynamically capture its API call sequence, standardizing the API call sequence, and mapping it into a dense vector sequence; S2, data augmentation based on Conditional Wasserstein Generative Adversarial Network (CWGAN-GP) with gradient penalty mechanism: constructing a CWGAN-GP model conditioned on the category labels of minority malware classes, the model including a conditional generator G and a discriminator D with gradient penalty; inputting the minority malware samples obtained in step S1 and their corresponding category labels into the CWGAN-GP model for adversarial training until the model converges. The advantages of this invention are: high-quality data augmentation with semantic fidelity; comprehensive and complementary feature extraction; significant end-to-end performance improvement, especially in minority class identification; and strong model robustness and generalization ability.
Owner:GUIZHOU UNIV

An open-set cross-domain diagnosis method, device, medium and product based on a purity-aware orthogonal decoupling network

PendingCN122508276AImprove efficiencyImprove stabilityDiagnostic dataFailure semantics
The application discloses an open set cross-domain diagnosis method and device based on purity perception orthogonal decoupling network, a medium and a product, and relates to the field of mechanical fault diagnosis.The method comprises the following steps: inputting a sample into a purity-guided orthogonal decoupling architecture to obtain fault semantic features and a sample purity coefficient; taking the sample purity coefficient as prior knowledge, adopting a purity self-adaptive joint optimization strategy to carry out clustering optimization of same-class aggregation and different-class exclusion based on the fault semantic features, training in the purity-guided orthogonal decoupling architecture through an uncertainty perception dynamic joint optimization mechanism, combining an open set identification strategy based on the purity perception dynamic cosine extreme value theory to construct an open set cross-domain diagnosis model, inputting to-be-diagnosed data into the model, and realizing known-class classification and unknown-class rejection of the to-be-diagnosed data.The application can accurately classify known faults and reliably isolate and reject unknown faults under the double challenges of complete invisibility of a target domain and distribution deviation and new class emergence.
Owner:BEIJING INST OF TECH

Drug user brain magnetic resonance image classification method, system and storage medium

PendingCN122736981AImprove classification accuracyReduce the amount of model parameters
The application relates to the technical field of image recognition, in particular to a drug user brain magnetic resonance image classification method and system and a storage medium. A CNN-Mamba hybrid deep learning model with a double-branch parallel structure is used to extract and fuse the features of the brain magnetic resonance image to be classified, and whether the left prefrontal cortex region, the left insular region and the left reward loop related region in the obtained aggregated features meet a preset classification condition is identified; if yes, the brain magnetic resonance image is classified, and reliable classification of the brain magnetic resonance image is realized. The application aims to solve the problem of how to classify drug users according to brain magnetic resonance images.
Owner:YUNNAN UNIV

Intelligent water and fertilizer integration-based precise regulation and control system and method for nutrition and reproductive growth balance of litchi

PendingCN118985251ARealize the function of automatic water and fertilizer irrigationAvoid abnormal execution resultsLiquid fertiliser distributionAgricultural scienceNutrition
The invention discloses a litchi nutrition and reproductive growth balance precise regulation and control system and method based on intelligent water and fertilizer integration, and relates to the field of litchi planting. Comprising a water and fertilizer irrigation module composed of a water supply unit and a fertilizer supply unit and used for providing a water source and a fertilizer for litchi production; the sensor module is used for monitoring litchi growth environment information and litchi growth information; the healthy growth model is a healthy model used for storing environment information and growth information in the litchi growth process; and the central processing module is used for processing the data acquired by the sensor module and comparing the data with a healthy growth model. According to the invention, actual parameters are obtained through the sensor module, then the actual parameters are compared with the healthy growth model through the central processing module, so that the control instruction is formed, and then the water and fertilizer irrigation module is subjected to execution control, so that the function of automatic water and fertilizer irrigation is realized.
Owner:POMOLOGY RES INST GUANGDONG ACADEMY OF AGRI SCI

Metalearning diagnosis method for sensing working condition of drive motor of fly-by-wire actuator

PendingCN121997168Areliable classificationImprove explicit modeling capabilitiesElectric motor controlBiological modelsTelexDiagnosis methods
The embodiment of the invention discloses a telex actuator driving motor working condition sensing meta learning diagnosis method, which comprises the following steps of: acquiring a feature embedding function value through a working condition encoder module, acquiring a class prototype of a fault class based on a prototype network, and training the prototype network based on prototype loss, establishing center loss and establishing a joint loss function to obtain a fault class model; and based on the trained prototype network, fault diagnosis in the actual working process is carried out. According to the method, high-robustness diagnosis on composite working condition changes under the condition of few samples is realized, the explicit modeling capability on operation conditions is remarkably improved, and the diagnosis precision is greatly improved. According to the method, the discrimination of the fault features in the embedding space is remarkably enhanced. The method has strong small sample rapid adaptive capability, so that when a new fault diagnosis task is encountered, rapid adaptation can be realized without retraining or only a small number of new samples, and the practicability and deployment flexibility of the method are greatly improved.
Owner:SICHUAN UNIV

Monitoring system and food preparation system

A monitoring system for a food preparation system includes a sensor unit having at least one sensor for determining current sensor data of food being loaded or unloaded to or from a food processing chamber of the food preparation system; the processing unit is used for determining current feature data according to the current sensor data; the classification unit is used for determining characteristic data of food in the food processing chamber according to the current characteristic data; and a control unit for controlling at least one actuator adapted to notify or alert a user or to set operating parameters of the food preparation system based on the determined characteristic data of the food present within the food processing chamber.
Owner:INTERPRODUCTEC CONSULTING GMBH & CO KG