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

856results about How to "Improve classification performance" patented technology

PCBA surface defect detection method and system based on image recognition

The invention provides a PCBA surface defect detection method and system based on image recognition, and the method comprises the steps: collecting and constructing a multi-class PCBA overall defect image data set, and carrying out the preprocessing; constructing a pre-training neural network model, and classifying the preprocessed PCBA overall defect image data set; constructing a local target identification method based on a YOLOX network according to an overall defect classification result; and carrying out local defect detection on the PCBA surface based on a local target identification method. According to the method, the overall classification and local detection strategies are comprehensively applied to reduce the burden of the model, and the detection precision and speed are improved. And an attention mechanism is introduced to improve the performance and generalization ability of the model. Data enhancement, consistency processing, classification labeling and the like are carried out on an image data set, and the defect detection effect of the model is improved. And multiple optimization strategies such as structure improvement, loss function improvement and pruning lightweight are adopted for the network model, so that the image target detection performance is effectively improved.
Owner:SHENZHEN FUYAN STAR TECH CO LTD

Equipment state sensing system based on peak shifting and danger situation sensing

The invention discloses an equipment state sensing system based on peak shifting and danger situation sensing, which relates to the technical field of electric digital data processing and comprises a data acquisition unit, a model training and optimizing unit, a situation sensing unit, a peak shifting regulation and control unit and a system interface and user interaction unit. According to the method, the device state data feature similarity is dynamically calculated by using the Gaussian kernel function, the similarity matrix is adjusted in combination with the gradient update item, dynamic weighting is performed in feature extraction, and redundant features are reduced by adopting the adaptive discarding probability, so that the feature extraction efficiency of the model in a high-dimensional feature space is improved; the problem that the dimension reduction effect is affected by too many redundant features of the equipment state data is solved. Equipment state features are extracted layer by layer through a deep forest algorithm of a multi-layer random forest structure, a decision tree is optimized in combination with a dynamic adjustment weight mechanism and a reinforcement learning strategy, and the classification capability of the model for equipment state changes and abnormal states is enhanced.
Owner:ZHEJIANG JOYCHINE IOT TECH CO LTD

RSVP type unbalanced electroencephalogram signal classification method based on adaptive channel mixed attention mechanism and decoupling learning

The invention provides an RSVP type unbalanced electroencephalogram signal classification method based on a self-adaptive channel mixed attention mechanism and decoupling learning, and aims to improve the feature extraction and classification performance of RSVP electroencephalogram signals. Firstly, collected RSVP electroencephalogram signals are preprocessed, including common average reference, band-pass filtering and standardization processing, and a training set and a test set are divided; then, multi-scale time and space features are extracted through a parallel convolution layer and a space convolution layer, and the features of different levels are fused through an interpolation method; the training process is decoupled into representation learning and classifier learning, the representation learning uses a triple loss function based on difficult sample sampling, and the classifier learning uses the optimized Focal Loss to perform feature learning and classifier optimization. A self-adaptive channel mixed attention mechanism is introduced, and the flexibility and robustness of the model are enhanced through dynamic weighting and multi-level feature fusion. According to the method, the problem of class imbalance in the RSVP task is solved.
Owner:BEIJING UNIV OF TECH

Intrusion detection method and device based on graph neural network, and medium

The invention discloses an intrusion detection method and device based on a graph neural network and a medium, and relates to the field of computer networks, and the method comprises the steps: constructing a graph structure according to network flow data in a current time window; the graph structure comprises a node set, an edge set, a node feature matrix, an edge feature matrix and an adjacent matrix; the adjacent matrix is used for representing a communication state between the nodes; inputting the graph structure corresponding to the current time window into a network node traffic type identification model to obtain the traffic type of each node; the network node traffic type identification model is obtained by training a preset graph neural network by adopting a training sample set; in a preset graph neural network, for an input graph structure, a Bi-LSTM layer is adopted to extract time feature information, and a graph convolution layer and a graph attention mechanism are combined to extract space feature information in a time dimension, so that a traffic type of each node is obtained. According to the invention, more accurate network intrusion detection is realized.
Owner:JILIN UNIVERSITY

Satellite remote sensing image cloud classification method based on space-time coding guidance

The invention discloses a satellite remote sensing image cloud classification method based on space-time coding guidance, and particularly relates to the technical field of satellite image processing and deep learning, and the method comprises the following steps: carrying out the preprocessing of the original data of a geostationary meteorological satellite and a Cloud Sat satellite; preprocessing operation such as cutting, projection conversion and feature selection is carried out on the geostationary meteorological satellite data, a top cloud type is selected for the Cloud Sat data to serve as a label, and space-time matching is carried out on the processed geostationary meteorological satellite data and the Cloud Sat data to obtain a training and testing data set; and establishing a GTCCT model, performing time and geocoding on the input data, inputting the coded feature data into a network for training, and finally obtaining the GTCCT model for cloud classification.
Owner:NANJING UNIV OF AERONAUTICS & ASTRONAUTICS

Integrated airborne communication antenna equipment and communication method

The invention relates to integrated airborne communication antenna equipment and a communication method. The method comprises the following steps: carrying out CSI data acquisition and space-time focus modulation on a communication channel to obtain CSI space-time characteristic data; performing residual vector quantization operation to generate a quantized data stream, and performing recursive coding processing to obtain a target data stream; mapping the target data stream to a three-dimensional tensor space, constructing a real value tensor model, and performing iterative operation to obtain a CSI feature vector; performing fractional order wavelet transform decomposition on the CSI feature vector to obtain a radio frequency feature set, and inputting the radio frequency feature set into a federal fractional scattering network for feature processing to obtain an identity authentication result; and calculating an amplitude-phase weight coefficient of the antenna array, generating a beam parameter, and performing compensation matrix operation on the beam parameter according to the CSI feature vector to obtain a pre-coded signal. According to the invention, the dynamic adjustment of the antenna beam parameters is realized, and the accuracy and anti-interference capability of beam forming are improved.
Owner:SHENZHEN ASIA PACIFIC AVIATION TECH CO LTD

Micro-expression recognition method and system based on state space model and double-flow fusion

The invention discloses a micro-expression recognition method and system based on a state space model and double-flow fusion, and relates to the technical field of expression recognition, and the method comprises the steps: extracting a starting frame image and a top frame image of a micro-expression continuous video frame sequence; inputting the initial frame image and the top frame image into a micro-expression recognition model based on a double-flow fusion network, extracting an optical flow image, and performing face key point detection and clipping operation on the top frame image and the optical flow image respectively; carrying out image block embedding operation to obtain texture features of the top frame image after cutting and motion features of the optical flow image; the two features learn the global dependency relationship and the local correlation between the image blocks from the positive direction and the negative direction through a parallel multi-layer bidirectional Mama fusion module, and deep image features and motion features are extracted after feature fusion; and the deep features of the two modes are interacted through a double-flow cross attention classification module, comprehensive features are learned, and a plurality of classifiers are combined to identify and output the micro-expression type more accurately.
Owner:QILU UNIVERSITY OF TECHNOLOGY (SHANDONG ACADEMY OF SCIENCES)

Fan blade inner cavity defect detection method based on image recognition and deep learning

The invention discloses a fan blade inner cavity defect detection method and system based on image recognition and deep learning. The method comprises the following steps: performing multi-angle and multi-position image acquisition on an inner cavity of a fan blade through imaging equipment; the collected fan blade inner cavity image data set is preprocessed; generating a primary defect sample by using the first-layer generative adversarial network model; generating a complex defect image by using the second-layer generative adversarial network model; a convolutional neural network model is used for training; inputting the preprocessed fan blade inner cavity image data set into the trained convolutional neural network model; generating a defect report based on a defect detection result; when a new defect type appears, the recognition capability of the new defect is continuously optimized. Compared with the existing single detection technology, the multi-network combination method disclosed by the invention has the advantage that the defect detection efficiency and the classification capability are remarkably improved.
Owner:HUANENG RENEWABLES CORP LTD HEBEI BRANCH

ICU patient dysphoria video identification method based on space-time motion detection

The invention relates to an ICU patient dysphoria video recognition method based on space-time motion detection. Compared with the prior art, the defect that dysphoria video recognition is difficult to carry out on an ICU patient is overcome. The method comprises the following steps: acquiring and preprocessing a data set; constructing an ICU patient dysphoria identification model; training an ICU patient dysphoria identification model; obtaining video stream data to be identified; iCU patient dysphoria atom action recognition; and performing dysphoria quantitative classification based on an RASS score table. According to the method, the Slowfast basic model is improved, the detection precision and speed of the model are remarkably improved, the dysphoria behavior of the patient is automatically and accurately detected and understood from the perspective of space-time motion detection, the dysphoria condition of the patient is automatically scored according to the RASS score table, and accurate recognition of the dysphoria video of the ICU patient is achieved.
Owner:ANHUI UNIV

Relationship extraction model construction method and system based on semantic enhancement and knowledge distillation

The invention provides a relation extraction model construction method and system based on semantic enhancement and knowledge distillation, relates to the technical field of relation extraction, and aims to solve the problem that in the prior art, when continuous learning is processed, a model is often difficult to keep memorizing an old relation when a new relation is learned, and forgetting is caused. Model overfitting is easily caused by excessive dependence on a small amount of data, so that a new relationship cannot be effectively generalized. The method comprises the steps of obtaining a relationship prototype of a training sample and a typical sample, performing semantic enhancement on the relationship prototype to obtain an expanded enhanced data set and an enhanced memory set, and performing feature extraction, relationship classification prediction and relationship extraction based on a student model and a multi-teacher model. According to the method, the overfitting problem caused by scarcity of small sample data is effectively relieved through a semantic enhancement technology, old relation forgetting caused by new relation learning in the continuous learning process is reduced through a multi-teacher knowledge distillation method, and the classification accuracy and generalization ability of the model facing different relations are improved.
Owner:SHANDONG NORMAL UNIV

Unmanned aerial vehicle target detection method based on feature fusion and detection head collaborative optimization

The invention discloses an unmanned aerial vehicle target detection method based on feature fusion and detection head collaborative optimization, and the method comprises the steps: obtaining a multi-scale feature map through employing a backbone network formed by stacking a convolution module CBS and a residual module C2f, sequentially transmitting the feature maps of various scales to a multi-level feature fusion module (ML-FFM), carrying out the feature fusion from a deep layer to a shallow layer, and carrying out the detection of a target target. Semantic information of shallow layer features is enhanced; inputting the fused feature map into a refined feature enhancement module (RFEM), eliminating position conflicts and redundant information based on a space-time attention mechanism, and optimizing details and positioning capability of deep features; and the enhanced feature map is sent to a prediction head based on Transform for detection, and target classification and positioning of the aerial image of the unmanned aerial vehicle are completed. According to the method, the problems that the unmanned aerial vehicle aerial image is large in scale change, and small targets are high in proportion and dense in distribution are solved, so that the precision of target detection in the unmanned aerial vehicle aerial image is improved. The modules proposed in the method can significantly reduce the calculation amount, and are suitable for the real-time detection scene of the unmanned aerial vehicle.
Owner:HOHAI UNIV +1

Method and device for training medical big language model

The invention discloses a method and device for training a medical large language model, and the method comprises the steps: obtaining a training medical data set, the training medical data set comprises a plurality of training prompt words, and each training prompt word comprises a training medical text; extracting medical text features of each training medical text; performing fine tuning on the reference large language model by using a low-rank adaptive method LoRA, determining a rank for a low-rank matrix according to the medical text features of each training medical text so as to obtain a first low-rank matrix and a second low-rank matrix, and fusing the first low-rank matrix and the second low-rank matrix with the reference large language model to obtain a fine tuning large language model; and training the fine-tuning large language model by using the training prompt word to obtain a trained medical large language model which is used for classifying the medical text. According to the method, the calculation burden during fine tuning of the large language model is reduced, and the generalization ability and adaptability of the large language model are improved.
Owner:SHANGHAI AISHA MEDICAL TECH CO LTD

ViT distillation training method, system and device and readable storage medium

The invention provides a ViT distillation training method, system and device and a readable storage medium, and the method comprises the steps: selecting a long-tail data set, and carrying out the preprocessing of the long-tail data set; training the convolutional neural network to generate a teacher model; generating a data sample based on the long-tail data set, inputting the data sample into a teacher model, and generating a soft label; constructing a student model based on a visual Transform, and configuring a knowledge distillation function and a loss function for the student model; generating a data sample based on the long-tail data set, inputting the data sample into a student model, generating a classification result, and optimizing student model parameters by using a loss function based on the classification result and the soft label to train the student model; and after training is completed, performing model verification and output on the student model. According to the method, the technologies of long-tail data set preprocessing, teacher network training, knowledge distillation, loss reweighting and the like are combined, so that the classification performance and generalization ability of the ViT model on the long-tail data set are effectively improved.
Owner:浪潮智慧科技有限公司 +1

Multi-level track disease identification system based on vehicle body vibration data

The invention discloses a multi-level track disease recognition system based on vehicle body vibration data, and particularly relates to the field of blasting auxiliary devices. Comprising the steps that a data acquisition module acquires heterogeneity data of a track environment; the environment adaptive module analyzes the correlation between the vehicle body vibration data and the heterogeneity data, constructs a dual-view similarity matrix, and realizes adaptive classification of the track environment through a spectral clustering method; the label enhancement module generates high-quality pseudo labels and forms a completely labeled sample set; the disease recognition module adopts an attention-guided multi-task cascade CNN architecture, and outputs a multi-level recognition result containing disease positions and severity. By the adoption of the technical scheme, the problem that an existing track state evaluation method cannot evaluate the real state of track diseases in a complex environment is solved, and good performance is achieved in the aspect of geometric and structural disease recognition.
Owner:BEIJING JIAOTONG UNIV

EVA high-concentration color master batch detection method based on multispectral imaging

The invention relates to an EVA high-concentration color master batch detection method based on multispectral imaging, which comprises the following steps: S1, arranging an adjustable multicolor LED light source on a production line, and acquiring a multispectral image of a color master batch by using a multispectral imager to obtain a spectral data set; s2, extracting spectrums from the spectral data set based on a color master batch component identification model, and identifying spectral characteristics of different components or impurities; s3, constructing a color master batch color difference detection model and a defect identification model, and respectively carrying out color difference detection and defect identification based on the spectral characteristics; s4, based on real-time image color difference detection and defect recognition results, feeding back and controlling a control system of a production line based on an intelligent agent, and realizing automatic adjustment; and S5, visualization is carried out based on color difference detection and defect identification results, so that an operator can obtain a real-time color master batch detection result, and alarm processing is carried out on unqualified products. According to the scheme, high-efficiency and accurate monitoring on the EVA high-concentration color master batch is realized, and production intelligence and high product quality are ensured.
Owner:FUZHOU YOUXING BIOTECHNOLOGY CO LTD

Semi-supervised multi-modal data classification method based on shared feature alignment

The invention discloses a semi-supervised multi-modal data classification method based on shared feature alignment. The method comprises the following steps: S101, inputting labeled and unlabeled hyperspectral images and laser radar images, and extracting domain sharing features and domain private features; s102, splicing domain sharing features of the hyperspectrum and the laser radar, generating fusion features of domain sharing, and supplementing semantic information in the fusion features; s103, aligning the feature distribution of the label data and the feature distribution of the label-free data; s104, identifying a label sample and a label-free sample, and selecting a valuable label-free sample; s105, designing a sample labeling strategy based on a class adaptive threshold value, designing different threshold values for each class according to the classification difficulty of the classes, and selecting a pseudo label sample with high confidence coefficient to re-train the model; and S106, training the established semi-supervised joint classification network model. According to the method, the domain self-adaption thought is introduced to capture the shared features of the label data and the label-free data, and the classification precision of the model is improved by iteratively selecting the high-value pseudo labels.
Owner:XIDIAN UNIV

Ship target type multi-mode identification method under local information loss condition

The invention discloses a ship target type multi-mode identification method under the condition of local information loss, and belongs to the technical field of data identification. According to the method, the type of a ship target is identified through a multi-modal type identification model; the multi-modal type identification model comprises a visible light image processing branch, an infrared image processing branch, a splicing module and an image neural network; the visible light image processing branch and the infrared image processing branch extract corresponding local key features from the visible light image and the infrared image of the same ship target respectively. According to the method, the local key features are extracted from the visible light modal image and the infrared modal image to serve as the graph model nodes, and then the graph neural network is utilized to fuse the extracted information nodes, so that the problem of information loss of a single visible light image in the environments of cloud, fog, rain, snow and the like is effectively solved, and the accuracy of classification and recognition is improved.
Owner:NAVAL AVIATION UNIV

Image segmentation method for mass spectrum imaging image of ESI source

The invention belongs to the field of mass spectrum imaging, and particularly provides an image segmentation method for a mass spectrum imaging image of an ESI source, and the method comprises the steps: (S1) dividing the mass spectrum imaging image into a plurality of mass spectrum imaging channels according to a mass-to-charge ratio; (S2) selecting a mass spectrum imaging channel where target ions are located, and preprocessing each pixel; (S3) carrying out preliminary segmentation on the spectrogram data; (S4) performing interval division on the mass spectrum data of the channel where the target ions of each pixel are located, calculating the lower area of each interval, selecting the central mass-to-charge ratio of each interval as the abscissa of the intensity value of each interval, and setting the intensity value of the interval with the ratio of the central mass-to-charge ratio to the highest intensity value lower than a set value as 0; (S5) analyzing, training and optimizing the transformed mass spectrum data; and (S6) the optimal combination model obtained in the step (S5) is used for classification of other pixel points of the mass spectrum imaging image, and an image segmentation result is obtained. The method has the advantages of accurate segmentation and the like, and is applied to mass spectrum imaging of the ESI source.
Owner:CHINA INNOVATION INSTR CO LTD

Database system log analysis and processing analysis method

A database system log analysis and processing analysis method belongs to the technical field of data processing, and comprises the following steps: S1, data acquisition and labeling; s2, performing sample generation by adopting a generative adversarial network based on adaptive noise suppression learning to realize data expansion; s3, inputting the expanded data into a feature extraction model for model training, and performing feature extraction by adopting a six-layer full-connection neural network; s4, inputting the data subjected to feature extraction into a feature dimension reduction model for model training, wherein an auto-encoder algorithm is specifically adopted; s5, inputting the data subjected to dimension reduction into a classifier for model training, wherein an extreme learning machine algorithm based on implicit neural representation is specifically adopted; and S6, log analysis and operation behavior identification. According to the method, a response can be made in real time when a new log record is faced, possible security threats or abnormal behaviors can be recognized, and an important basis is provided for security management and fault diagnosis of a database system.
Owner:SHANGHAI SHANGJIA INFORMATION TECH CO LTD

CAD drawing intelligent matching method and system based on multi-stage deep learning

The invention discloses a CAD drawing intelligent matching method and system based on multi-stage deep learning, and belongs to the field of image comparison, and the method mainly comprises the steps: S1, loading and preprocessing a CAD drawing, and constructing a triple data set through a data enhancement and sample balance technology; s2, constructing a target detection model and a target matching model, and training the target detection model and the target matching model by using the triple data set; wherein the target detection model adopts a YOLOv5 model, and the CAD drawing is detected in combination with sliding window detection and a non-maximum suppression technology; the target matching model adopts a double-end network structure; and S3, matching the CAD drawings to be identified by using the trained target detection model and target matching model. According to the invention, through a plurality of advanced technologies, intelligent matching and judgment of two or more CAD images in any different formats are realized.
Owner:ZHEJIANG QINGBEI INTELLIGENT TECHNOLOGY CO LTD

Hyperspectral image classification method based on state space model

The invention provides a hyperspectral image classification method based on a state space model. The problem that an existing method is poor in classification precision is mainly solved. According to the scheme, the method comprises the following steps: 1) inputting a hyperspectral image, and preprocessing the hyperspectral image; 2) eliminating spectrum variability by using a neighborhood spectrum fusion method, sensing spectrum detail differences by using a sub-spectrum scanning method, and obtaining image spectrum classification information; 3) constructing a spatial feature extraction network by using an SS2D layer, an improved spatial attention mechanism and a plurality of residual blocks, and acquiring spatial classification information of the hyperspectral image by using the network; and 4) fusing space and spectrum classification information at a decision layer to obtain a final classification result. According to the method, the influence caused by spectrum variability can be reduced in a relatively small range, local spectrum information is not ignored on the premise that comprehensive spectrum information can be perceived, and spatial information is combined, so that the classification effect of the hyperspectral image is effectively improved.
Owner:XIDIAN UNIV +1

Heterogeneous graph node classification method based on relation perception label propagation

The invention relates to the technical field of graph neural network and heterogeneous graph representation learning, in particular to a heterogeneous graph node classification method based on relation perception label propagation, which comprises the following steps of: firstly, according to a given heterogeneous network, carrying out type-specific linear transformation on different types of nodes, and then carrying out type-specific linear transformation on different types of nodes; the method comprises the following steps of: designing a relation sensing label propagation algorithm for target nodes in a heterogeneous network, generating a pseudo label through a relation sub-graph, performing information transmission by adopting a double-layer aggregation strategy based on a type attention mechanism, and effectively fusing multi-layer information of the nodes, so as to obtain a multi-layer information fusion model; and the node feature representation is richer and more accurate. According to the method, the pseudo labels are obtained by designing a relation perception label propagation method, heterogeneous message passing is carried out by utilizing double-layer aggregation based on a type attention mechanism, and the classification performance and robustness are remarkably improved in combination with a multi-objective optimization strategy.
Owner:CHINA UNIV OF MINING & TECH

Graph convolutional neural network-based state grid user classification method, system and device and storage medium

The invention relates to the technical field of big data processing, in particular to an online state grid user classification method, system and device based on a graph convolutional neural network and a storage medium. The invention discloses an online state grid user classification method based on a graph convolutional neural network. The method comprises the following steps: extracting user explicit and implicit features; the method specifically comprises the following steps: firstly, constructing a user graph model by taking online state grid user data as input, extracting feature information in graph data by using a stack network formed by a convolutional neural network, and propagating vector representations of aggregated users and neighbor users thereof by using a cyclic convolution operation; classifying users; according to the method, the graph convolutional neural network model is used for constructing the portrait of the state grid user on the Internet, dominant and implicit features of the user are deeply mined, and an accurate user feature vector is formed. Meanwhile, user vector subdivision is achieved according to probability representation output by the full connection layer, and potential user groups are effectively recognized.
Owner:国家电网有限公司客户服务中心

Driver distraction detection method based on ResPrompt and double cross attention

The invention discloses a driver distraction detection method based on ResPrompt and double cross attention, and the method comprises the steps: inputting a front / side visual angle image of a driver distraction behavior into a linear embedding module and a ResPrompt module, carrying out the partitioning of the image through the linear embedding module, generating a feature vector, and generating a prompt vector of the image through the ResPrompt module; performing multi-scale feature extraction on the feature vector of the front / side view angle image and the most matched prompt vector by using a Swindow-Transfomer module to generate each view angle feature; and fusing the double-view-angle features by using a double-cross attention module, inputting the double-view-angle features into a classifier fusing center loss, and performing behavior detection on the features to generate a final detection result. According to the method, the accuracy and robustness of detection can be effectively improved, and reliable technical support is provided for safe operation of semi-automatic and automatic driving vehicles.
Owner:JIANGSU UNIV

Coal rock identification method and system based on image and XRF spectral information fusion

The invention provides a coal rock recognition method and system based on image and XRF spectral information fusion, and relates to the technical field of geological rock recognition and classification, and the method comprises the steps: obtaining a to-be-detected coal rock image; inputting the coal rock image into an image detection model to obtain suspicious coal gangue and position information thereof; the method comprises the following steps: performing element testing on suspicious coal gangue, acquiring element information, inputting the element information and a suspicious coal gangue image into a fusion classification model, extracting element features through an element feature extraction module, extracting image features through an image feature extraction module, performing matrix multiplication on the image features and the element features in an initial fusion module, and performing fusion classification on the suspicious coal gangue; and performing deep fusion on the similarity matrix and the image features to obtain initial fusion features, and obtaining a classification result of the coal / coal gangue by using the initial fusion features.
Owner:SHANDONG UNIV

DNA binding protein and RNA binding protein classification method based on ESM-2 and dual-path neural network

ActiveCN119229982Aproportional balancequality improvementBiostatisticsBiological modelsA-DNANucleic acid binding protein
The invention provides a DNA binding protein and RNA binding protein classification method based on ESM-2 and a dual-path neural network, and particularly relates to a staged classification method combining the ESM-2 and the dual-path neural network, which is called DRBP-EDP. In the first stage training, the protein sequence is classified as a nucleic acid binding protein or a non-nucleic acid binding protein; further classifying the nucleic acid binding protein as a DNA binding protein or an RNA binding protein in the second stage of training; meanwhile, a fine data set construction method is further constructed, so that a high-quality protein classification data set is created, through the method, the DRBP-EDP model obtains good performance, the classification accuracy of the nucleic acid binding protein and the non-nucleic acid binding protein in the first stage is 90.03%, and the classification accuracy of the non-nucleic acid binding protein in the second stage is 90.03%. In the second stage, the classification accuracy of the DNA binding protein and the RNA binding protein is 89.56%, a new insight and a new method are provided for protein classification, an innovative tool is provided for research on protein functions, and therefore a new opportunity is provided for development of life science.
Owner:SANYA NATIONAL INSTITUTE OF SOUTHERN BREEDING CHINESE ACADEMY OF AGRICULTURAL SCIENCES +1

Railway track obstacle detection method and system

The invention relates to a railway track obstacle detection method and system. Camera and laser radar data are fused, and a semantic segmentation model is used to identify safe and dangerous areas in the image; optimizing point cloud filtering by using a fuzzy decision; projecting the point cloud to a safe and dangerous area to endow semantics; clustering is carried out in combination with the space coordinates, and three-dimensional coordinates and size information are obtained; using a target detection model to identify obstacle types and two-dimensional size information; and projecting three-dimensional obstacle information to a two-dimensional plane, fusing by using a fuzzy decision, and outputting an accurate obstacle detection result. As the laser radar can accurately measure the distance and coordinates of the obstacle in the three-dimensional space, the laser radar is used as a main sensor, and the high detection rate is ensured; a camera is used for identifying the type of an obstacle and a dangerous area, and providing semantics for the point cloud so as to improve the obstacle detection accuracy; fuzzy decision is used, dynamic adjustment is carried out according to different environments, and false detection and missing detection are reduced.
Owner:SOUTHWEAT UNIV OF SCI & TECH

Medical ICD coding classification method based on graph neural network

The invention belongs to the field of medical ICD automatic coding, and particularly relates to a medical ICD coding classification method based on a graph neural network, and the method comprises the steps: obtaining a data set, and carrying out the preprocessing of the data set, and obtaining a text vector matrix; constructing a graph structure according to the text vector matrix, wherein the graph structure comprises a node feature matrix and an adjacent matrix; inputting the graph structure into a graph neural network model, outputting a prediction ICD coding result, and training the model by adopting a multi-label loss function based on cross entropy; inputting to-be-coded medical record data into the trained graph neural network model to obtain a predicted ICD code; according to the method, the semantic similarity between the medical terms, the level distance between the ICD codes and the co-occurrence frequency relation are included into a graph structure, the complex relation between words and labels can be comprehensively captured, the potential relevance between the ICD codes is better utilized, and the context understanding ability and accuracy of a classification model are enhanced.
Owner:CHONGQING UNIV OF POSTS & TELECOMM

Structural damage detection system based on asymmetric multi-task learning

The invention discloses a structural damage detection system based on asymmetric multi-task learning, and relates to structural health monitoring. A new detection system, namely an asymmetric multi-task structure damage identification model, is provided, in a multi-task learning framework, identification of damage positions and sizes is regarded as two related tasks, the advantages of multi-task learning can be exerted, and meanwhile the performance of the two tasks is improved. By adopting the asymmetric method, the influence of a negative migration phenomenon existing in multi-task learning can be effectively reduced, and the identification performance of the damage position and size is improved. Besides, in order to improve the effective utilization of the damage position features, a position attention mechanism is also provided, the mechanism can adaptively allocate weights for the damage position features and the damage size features, and after the two features are weighted and summed, the damage size features containing rich position information can be extracted from the two features. Therefore, the effect of the damage size identification task is improved.
Owner:XIAMEN UNIV

City appearance environment early warning method and system based on AI intelligent garbage identification

The invention discloses a city appearance environment early warning method and system based on AI intelligent garbage identification, and relates to the technical field of artificial intelligence and garbage classification technologies. The method comprises the steps that firstly, garbage classification throwing stations are set; step 2, acquiring and processing image data; step 3, carrying out image frame selection and tracking; 4, setting a threshold value and generating prompt information; 5, scheduling the garbage trucks, connecting the garbage trucks in series according to the uploaded alarm stations, and designing a route; by monitoring the state of the garbage throwing station in real time, the system can timely find the situation that the number of the garbage cans reaches the standard, and automatically generate early warning information, so that an environmental sanitation management department can timely dispatch garbage trucks to carry out clearing and transportation, and environmental pollution and resource waste caused by long-time garbage accumulation are avoided; the dynamic adjustment function of the system ensures that the driving route of the garbage truck can be rapidly updated when the actual situation changes, for example, early warning is newly added, and the garbage treatment efficiency and the response speed are further improved.
Owner:GUANGZHOU QIAOYIN ENVIRONMENTAL PROTECTION TECH