16results about How to "Optimize detection results" patented technology

The invention belongs to the technical field of network security, and discloses a feature enhanced community detection-based APT attack discovery method, which comprises the following steps of: collecting log data and constructing an origin graph; the source graph is segmented into a plurality of sub-graphs, a feature association vector set and a weight set are generated for each sub-graph, the sub-graphs with feature association vectors and weights are reconstructed, each reconstructed sub-graph comprises a plurality of triads, and the feature association vectors and the weights exist among the triads; performing feature enhanced community detection on each reconstructed sub-graph; and performing rule matching on the communities in each reconstructed sub-graph to obtain attack communities, and according to the timestamp attribute of each reconstructed sub-graph, connecting the attack communities in each reconstructed sub-graph to complete APT attack discovery. According to the method, the origin graph is constructed by using the collected logs, and accurate division of attack communities is performed by performing feature enhanced community detection on the origin graph.

The invention provides a track checking interval and back protection distance detection method, which comprises a positioning extraction step, a contour combination step, a track piece identification step, a checking interval acquisition step and a back protection distance acquisition step, according to the method, a predetermined detection position is automatically positioned through profile data collected by a high-precision line laser sensor and corresponding mileage data, profile data of the position are extracted, then the profile data of the multiple line laser sensors are combined, profiles of the heads of the multiple rail pieces are automatically recognized and extracted from combined profile lines, and the accuracy of detection is improved. Due to the fact that the arrangement of the rail pieces at the preset detection position is fixed, the profiles of the guard rail head, the guard rail pair side wing rail head and the point rail can be conveniently and rapidly obtained, then the accurate checking interval value and the back protection distance value are rapidly obtained based on profile analysis and calculation, operation is convenient, detection precision is high, the calculation amount is small, and the detection accuracy is high. And a detection result can be quickly obtained on a track detection site.

The invention provides a method for identifying fires in electric equipment based on a multi-parameter recursive graph, and relates to the technical field of electrical fire detection. The method comprises: using a smoothing filtering technology to pre-process monitoring video images, and creating a fire identification algorithm model based on artificial intelligence to detect and identify fire images in suspicious areas; the fire identification algorithm model identifies the hidden danger electrical monitoring data of the detection position, calculates the target feature vector corresponding to the trace features of the target video image, and builds a deep neural network sub-model and a power heterogeneous multi-parameter fusion model; then using a recursive algorithm module to arrange the power time series parameters into a recursive matrix, and constructing a graph convolutional neural network based on a multi-parameter recursive graph to extract features; using a fire warning judgment module to segment the suspicious unknown areas of the image sequence where the fire occurs, and timely predict and process them, and after identification and confirmation, automatically start a multi-parameter warning judgment program, and accelerate the issuance of warning signals by a background warning system.

The present application belongs to the technical field of computer vision, video anomaly detection and video anomaly detection model design, and particularly relates to a video anomaly detection method, comprising: acquiring segment feature data of a video to be detected; inputting the segment feature data into a video anomaly detection model to acquire a detection result, wherein the video anomaly detection model comprises: an anomaly feature enhancement model, an anomaly score calculation model, an anomaly positioning model based on classification guidance and an anomaly score optimization model. The present application enhances the feature data of the video to be detected by the anomaly feature enhancement model in terms of time sequence information and motion information, so that it is more suitable for the anomaly detection task, and according to the anomaly positioning model based on classification guidance, parameters in the video anomaly process classification are mined and the anomaly score obtained by the anomaly score calculation model is optimized, so that a detection result with higher accuracy is obtained. Meanwhile, the anomaly positioning model based on classification guidance is convenient to use and can be installed in a memory for use as plug as needed.

The application belongs to the field of biological drugs, and discloses a quality detection method of protein polymer, which comprises at least one of reverse phase HPLC detection, SDS-PAGE analysis, mass spectrometry detection, particle size detection, exosome surface marker detection, sterility detection and endotoxin detection. The quality detection method of some examples of the application can effectively realize the separation of components in the protein polymer sample by optimizing the HPLC condition, achieve better detection results, and establish the quality control standard of the protein polymer.

The invention discloses a tower crane worker fatigue detection method based on EEG and video signal fusion, and relates to the technical field of fatigue detection, and the method comprises the steps: S1, data collection and marking: employing a motion camera to collect face video data of an operator, and employing an EEG sensor to collect EEG signals of the operator; carrying out subjective evaluation on the psychological fatigue of the operator by adopting NASA-TLX scores; s2, data preprocessing: preprocessing the collected face video data and EEG signals respectively, then segmenting the preprocessed video and EEG data by using a sliding window, and ensuring time axis alignment; and S3, multi-modal feature extraction, fusion and fatigue classification. According to the method, automatic extraction and fusion of data features are realized through the neural network, artificial subjective errors are reduced, the efficiency of processing large-scale data is greatly improved, and the complexity of manual feature selection is avoided.

The application discloses a remote sensing image target detection method and system based on an optimized SSD algorithm, first, inputting a to-be-detected remote sensing image into an efficient remote sensing image target feature extraction network to extract key features, and obtaining a required feature map; then inputting the obtained feature map into a forward and reverse iterative fusion multi-scale feature network to perform feature fusion, and generating a new feature map; finally, utilizing an anchor box matching network based on a clustering algorithm to perform anchor box clustering matching on different categories of targets in the image according to the new feature generated by fusion, so that each to-be-detected target obtains the most suitable anchor box as a target detection result; the original feature extraction network VGG16 in the SSD algorithm is optimized, an improved RFB module and an efficient attention mechanism are added into the network, the feature extraction capability of the network is improved, the anchor box matching network based on the clustering algorithm is integrated into the algorithm, the accuracy of the anchor box matching target of the algorithm is improved, and therefore the detection capability is improved.

The present invention relates to a remote sensing image cloud detection method based on a multi-scale convolutional neural network, comprising the following steps: step 1, establishing a multi-scale U-net neural network; the multi-scale U-net neural network comprises an encoder, a decoder and an SPP U-net network structure; step 2, collecting a number of remote sensing images containing clouds, performing cropping, channel selection, cloud annotation and data augmentation, and obtaining a training data set and a test data set required for training the multi-scale U-net neural network; step 3, using the training data set, using the BCELoss loss function and the SGD optimizer to train and update the parameters of the multi-scale U-net neural network; step 4, inputting the cloud-containing remote sensing image to be detected into the trained multi-scale U-net neural network for cloud detection, and the output result is a cloud detection binary image. The present invention performs feature multi-scale improvement on the ordinary U-Net network structure, adopts spatial pyramid pooling to improve the cloud detection accuracy, and can greatly improve the detection effect of small cloud areas and cloud segmentation edges.

This invention relates to a method for analyzing the behavior of stored grain pests based on YOLOv5 and an improved SORT algorithm, belonging to the technical field of stored grain pest behavior analysis methods. This method utilizes a camera to collect and filter videos of stored grain pests crawling, and processes the videos frame by frame. First, each frame is preprocessed using OpenCV to detect the outline of the stored grain pests and extract target coordinate data. When target overlap or loss occurs in a frame, resulting in detection failures for certain stored grain pests, the frame is segmented and fed into the YOLOv5 target detection network for re-detection, optimizing the detection results. This method solves the problems of low accuracy, susceptibility to environmental factors, and poor detection performance when overlap occurs in existing stored grain pest behavior analysis methods, making it particularly suitable for the needs of stored grain pest behavior analysis.

The utility model discloses a low-voltage surge protector connecting conductor wire diameter detector, which relates to the technical field of low-voltage surge protectors and comprises a comparator, and a standard sample area, a technical standard requirement area and an instruction area are arranged on the front surface of the comparator. The standard sample area is provided with six connecting conductor samples with different wire diameters, and the connecting conductor samples are fixedly mounted on the front surface of the comparator through wire clamps; the technical standard requirement area is engraved with a technical standard requirement of a surge protection device connecting conductor; and instructions and processes of the device are engraved in the instruction area. The low-voltage surge protection device connecting conductor wire diameter detector provided by the utility model meets the actual work requirements of field detection of a surge protection device connecting conductor, and solves the problems that direct measurement cannot be performed and electric shock risks exist.

The embodiment of the present invention discloses a model generation method, a target detection method, a device, an electronic device and a medium. The model generation method includes: training the original detection model based on multiple groups of teacher training samples including a first sample image and sample annotation results of known targets in the first sample image to obtain a teacher network; using the first sample image and the first detection result obtained after the first sample image is input into the teacher network as the first training sample, and using the second sample image and the second detection result obtained after the second sample image is input into the teacher network as the second training sample; training a student network with the same network type as the teacher network based on multiple groups of first training samples and multiple groups of second training samples to generate a target detection model. The technical solution of the embodiment of the present invention achieves the effect of improving the generalization performance of the target detection model without increasing the cost of manual annotation.

A fluorescence-magnetic resonance dual-modality contrast agent, a preparation method thereof and the use thereof. The contrast agent has the following structure: X-L-Y, wherein: formula (I); R1, R2, R3, R4, R5, R6, R7, R8, R9, R10, R11, and R12 are each independently selected from H, halogen, OH, NH2, COOH, CONH2, NO2, CN, and low alkyl groups, the low alkyl groups can be substituted with halogen, OH, NH2, COOH, CONH2, SO3H, NO2, and CN, wherein R3 and R4, taken together with the carbon atoms to which they are attached, may form a phenyl group or a heterocyclic group; R7 and R8, taken together with the carbon atoms to which they are attached, may form a phenyl group or heterocyclic group; L is a linking group; and Y is a metal chelate.

The application discloses an infrared dim small target detection method based on a deep sparse low-rank neural network, and belongs to the field of infrared data processing in remote sensing digital image processing. Due to the small volume and low brightness of the infrared dim small target, the target is difficult to be detected from an image, and therefore, the application is proposed to improve the performance of an infrared dim small target detection algorithm in small target detection and solve the problem of inaccurate target detection result in a clutter background. Specifically, the original infrared image is segmented into a series of infrared image blocks by using a sliding window; a target detection model based on target sparse representation and background low-rank constraint is established; each variable of the target detection model is solved by using an alternating direction multiplier method after the infrared image block is input; the model is expanded into a convolutional neural network, and relevant parameters in the model are continuously updated; a target detection result in the obtained reconstructed infrared image block is obtained; and the target detection result of the infrared image is output. The application can obtain good detection results for infrared targets with different attributes in different background environments.

The invention discloses a grounding tool and method for detecting an outer anticorrosive coating of a pipeline under a complex earth surface condition. The grounding tool comprises a bottom end, a body, a funnel and a handheld end, the bottom end is installed at one end of the body, the handheld end is installed at the other end of the body, the funnel is installed on the body, the bottom end is arranged to be of a semicircular angled wedge-shaped structure, the interior of the body is of a hollow structure, and a plurality of kidney-shaped holes are formed in the body. The grounding device is simple in structure and convenient to operate, can adapt to a complex ground surface environment, can realize reliable grounding in a high-resistance ground surface environment, and ensures smooth detection.

The application belongs to the technical field of user detection, and particularly relates to an abnormal user detection method and system based on multiple feature layers, which effectively fuse user behavior patterns, user attributes and user tweet features in social data, summarize social network user data into four levels of user statistical attributes, user behavior attributes, user network attributes and high-dimensional attributes, and use a composite neural network model based on an attention mechanism to classify and predict normal users and abnormal users, so that better abnormal user detection results can be obtained.

The utility model discloses a noise testing device for an automobile exhaust tail pipe, which relates to the technical field of automobile exhaust detection and comprises a detection handle, a fixing unit is arranged on the outer surface of the detection handle, and a protective cover is arranged at one end of the detection handle. According to the device, through cooperation of the detection handle, the detection head, the adjusting block, the protective cover, the sleeve and the clamping groove, the detection head can be protected in the detection process, the influence of dust on the detection result is prevented, the protective cover is also convenient to disassemble, assemble and clean, the protective effect is maintained, and the detection efficiency is improved. And through the cooperation of the adjusting screw rod, the connecting piece, the movable ring, the second connecting rod, the first connecting rod and the supporting block, the device can be conveniently connected and fixed with the automobile tail pipe during detection, and the device is small in size, convenient and flexible to move and rapid to disassemble and assemble, so that the detection flexibility is improved, the detection time is saved, and the detection efficiency is improved.