65results about How to "Reduce the possibility of missed detection" patented technology

The invention discloses a capsule endoscopy auxiliary film reading method, belonging to the biological image recognition technology field and comprising: downloading the image shoot by the capsule endoscopy to the image film reading workstation, before film reading, preprocessing the images by an auxiliary film reading system; in detail, firstly, training a focus site categorizer for preparing to recognize the focus site; secondly, applying the pattern recognition technology to delete the redundant frames with high similarity in the endoscopy image sequence, only retaining the image frame including most information, compressing the endoscope image sequence; finally, matching the compressed image sequence and the focus site categorizer based on the trained focus site categorizer, labeling the focus site therein. The auxiliary film reading system comprises a categorizer train module, a similar frame detection module and a focus characteristic analysis module. The categorizer train module finishes the train of the normal capsule endoscopy image characteristic categorizer and the focus site capsules endoscope image categorizer. The similar frame detection module finishes the image detection with high similarity, removes some redundant image. The focus characteristic analysis module judges whether the focus site is in the image and labels if there is.

The invention discloses a DTX detection method, device and base station. The DTX detection method includes the steps of: extracting information bits used for performing DTX detection from a feedback signal sent by an uplink terminal, and processing the extracted information bits according to different polarities; obtaining a DTX detection value according to information bits of different polarities; and comparing the DTX detection value with a preset DTX detection threshold value, and determining whether the uplink terminal is in a DTX state according to a comparison result. The scheme provided by the invention utilizes polarity characteristics of information bits to complete DTX detection, can greatly reduce possibilities of false detection and missing detection, and improves the precision of DTX detection, particularly under the condition of a small TBSize.

The invention discloses a linkable distributed network intrusion detection method based on behavior description, which achieves the real-time detection of abnormal flow in a network and timely makes a response by applying methods of the network behavior description and the feature extraction in a distributed detection system and linking with a fire wall, particularly comprising the steps of (a), a detection unit operation process and (b), a master control platform operation process: applying a detection strategy based on the behavior description on distributed detection units to effectively organize the distributed detection units to be an efficient organic whole, thus avoiding the low efficiency and the dispersibility of the existing system scheme, wherein the aim is to solve the low efficiency of the abnormal flow detection on a large network in the practical application and improve the whole detection ability and the protection effect of the detection system for the network.

The invention provides a kit for detecting of cancer sample polygene and multi-site mutation for mutation-frequent-occurring genes in cancers. The kit comprises primer pairs of zones of one or more exons for amplifying any two or three or all genes of BRAF, EGFR, KRAS and PIK3CA, for example, SEQ ID NO: 11 primer pairs shown by 1-22. The kit can be used for purposes of cancer diagnosis or auxiliary diagnosis, cancer prognosis monitoring or cancer therapy pharmacy guiding and the like. The invention further provides a corresponding detecting method.

The invention discloses a specific primer for diagnosing nosema antheraeae and an application of the primer. High-sensitivity specific detection for the nosema antheraeae is realized by an SYBR Green fluorescent quantitative PCR (polymerase chain reaction) method, the optimal reaction condition includes 95 DEG C and 30 seconds, circulation is performed for 40 times under the condition of 95 DEG C and 5 seconds and 62.5 DEG C and 30 seconds, and the melting curve condition includes 95 DEG C, 15 seconds, 60 DEG C, 60 seconds, 95 DEG C, 15 seconds, 60 DEG C and 15 seconds. Detection sensitivity is improved by two magnitude orders as compared with that of disclosed PCR technology, and lower detection limit includes that each reaction system contains 0.0046ng nosema genome DNA (deoxyribonucleic acid). Reliability of detection results is quantized by calculating primer amplification efficiency. The specific primer effectively solves the problems of low sensitivity, late detection period, easiness in leak detection, environmental pollution caused by conventional PCR nucleic acid coloring agents and the like, and has a wide application prospect in terms of antheraeae pebrine inspection and quarantine and cocoon quality improvement.

The invention discloses a full-automatic bubble cap visual detection mechanism. The full-automatic bubble cap visual detection mechanism comprises a conveying assembly, detecting assemblies and a turning assembly, the turning assembly comprises a rotating motor and a turning plate, the turning plate is installed on the rotating motor, the upper surface of the turning plate keeps horizontal with the upper surface of a second running device, and a positive-pressure air cock is installed on the second running device. The invention further discloses a full-automatic bubble cap visual detection method. The full-automatic bubble cap visual detection method comprises the following steps of front face examining, medicine plate turning, back face examining and defect medicine plate removing and counting. Therefore, the occupation space is small, defects on the bubble cap faces and the aluminum foil faces of medicine plates can be detected, the medicine plates detected to have problems can be automatically removed, secondary damage cannot be generated on the medicine plates in the detecting process, the detecting effectiveness is guaranteed, the leak detecting possibility is reduced, and human cost input is reduced.

The invention belongs to the technical field of pharmaceutical equipment and in particular relates to a lamp inspection machine for foreign matter detection after infusion bottle filling. The lamp inspection machine comprises a camera (3), a repeater (2) connected with the camera (3), and an upper computer (1) connected with the repeater (2), and also comprises a first conveyor belt (8) and a second conveyor belt (9) arranged in parallel, wherein a lifting and rotating device (6) for lifting infusion bottles (7) and rotating at a constant speed is arranged just above the middle of the first conveyor belt (8); a horizontal sliding cylinder (5) perpendicular to the operating direction of the first conveyor belt is arranged on the outer side of the middle of the first conveyor belt (8); a shifting block (11) with a circular arc-shaped notch is arranged at the end of a piston rod of the horizontal sliding cylinder (5); a detection probe is arranged above the horizontal sliding cylinder (5); and a discharging device (4) for discharging the infusion bottles (7) one by one is arranged on the outer side of the first conveyor belt (8) and in the rear of the horizontal sliding cylinder (5).

The embodiment of the invention provides a target detection method for a remote sensing image, and the method comprises the steps: obtaining a to-be-detected remote sensing image, inputting the to-be-detected remote sensing image into a pre-trained target detection model, and carrying out the target detection, and obtaining the position information of a first detection frame in the to-be-detected remote sensing image, wherein the confidence coefficient of the preset target in the first detection frame is higher than the first confidence coefficient; intercepting candidate images from the remote sensing image to be detected according to the position information of each first detection frame; inputting the candidate image into a target detection model for target detection, obtaining position information of a second detection frame in the candidate image and taking as a target detection result, wherein the confidence coefficient of a preset target in the second detection frame is higher than a second confidence coefficient, and the second confidence coefficient is higher than the first confidence coefficient. Thus, when target detection is carried out for the second time, the resolution of the candidate image is low, a good target detection effect can be obtained, and therefore high-precision target detection is carried out on the remote sensing image.

The invention discloses a background fraud detection method and device and electronic equipment. The method comprises the following steps: inputting a group of pictures to be detected into a pre-trained deep neural network to extract depth local features of each picture; calculating an interior point between the depth local features of every two pictures by using a random sampling consensus algorithm to obtain an interior point calculation result, wherein the inner points are used for representing that the depth local features of the pictures have consistency; constructing an adjacent matrix based on an interior point calculation result, wherein elements in the adjacent matrix are the number of interior points between the depth local features of the picture; clustering the adjacent matrixes by using an affinity diffusion clustering algorithm to obtain a plurality of clustering clusters, wherein each clustering cluster comprises a plurality of elements; determining whether background fraud exists in the group of pictures based on the plurality of clustering clusters. Picture background fraud can be effectively detected, and the possibility of false detection or missing detection isreduced.

The invention discloses a license plate number retrieval method based on a full-text search engine. The method comprises the steps that a front-end service system sends a retrieval request to a full-text search engine cluster server; after receiving the retrieval request, the full-text search engine cluster server retrieves the vehicle data meeting the retrieval condition from the database and takes the vehicle data as a result set; the license plate number retrieval plug-in compares the license plate number of each piece of vehicle data in the result set with a target license plate number andscores the matching degree of each piece of vehicle data in the result set, and the license plate number retrieval plug-in sends the result set and the matching degree score of each piece of vehicledata in the result set to the front-end service system; and the front-end service system selects the data of the license plate number with the matching degree score greater than a set threshold in thefinal result set as a retrieval result and displays the retrieval result at the front end.

The invention discloses a hard disk part detection device and a hard disk part detection method, which can realize detection of different types of defects of a hard disk part, improve the product yield level, and solve the problem that some defects can only be displayed in an image at a specific lighting angle. Therefore, an electric control rotary workpiece table, an electric control light sourcelifting table and a matched image analysis algorithm are specially designed, the detection automation level is improved, and missing detection is avoided; the workpiece table is controlled through software coordination to achieve rotation of a given angle value, and an angle image is collected; And registering of the images with different rotation angles is achieved by using the rotation angle value, a gravity center algorithm and an image correlation matching algorithm. Some defects can only be displayed in the images at a specific lighting angle, so that the registered images have difference in defect positions, and the gray value difference is extracted to realize defect detection.

The invention discloses an online monitoring device for a multi-parameter high-voltage bushing. The online monitoring device comprises a bushing adapter and a four-in-one bushing oil state sensor which are connected with a bushing state acquisition unit; the bushing adapter is used for monitoring leakage current of the bushing capacitor and high-frequency pulse to-ground partial discharge current signals of the bushing capacitor; the four-in-one casing oil state sensor is used for monitoring temperature, pressure, micro-water and hydrogen content signals of insulating oil in the casing; the casing state acquisition unit is used for acquiring signals monitored by the casing adapter and the four-in-one casing oil state sensor; and the analysis processing unit is used for diagnosing and pre-judging various faults in the casing pipe based on the signals acquired by the casing pipe state acquisition unit and the multi-state quantity. According to the invention, high-voltage bushing monitoring is carried out based on multiple state quantities, bushing faults are comprehensively analyzed and diagnosed, various faults of the bushing can be accurately and timely found, early warning intervention is timely carried out, and further expansion of accidents is avoided.

The invention discloses a multi-target tracking method based on multiple sensors. The multi-target tracking method comprises the following steps: updating and predicting the state of a tracked target;detecting target association and updating a tracked target set; updating and predicting the state of the tracked target, and updating the state value of the tracked target through the determined current sensor feedback state value of the tracked target; predicting a state value of the tracked target when the sensor feeds back the next time to obtain a state prediction value of the tracked target,the detection target association is association of a detection target and a tracked target, and the detection target matched with the tracked target is screened out from the detection targets; and updating the tracked targets in the tracked target set according to the final result of the detection target association. The invention also provides a multi-target tracking system based on multiple sensors. According to the invention, obstacles around the main vehicle can be accurately tracked, the possibility of false alarm and missing detection is greatly reduced, and the effectiveness of multi-target tracking is ensured, and the robustness is high.

The invention aims at providing an inflatable garment quality control rack which can lower the fatigue degree of workers and promote the quality of quality control. The inflatable garment quality control rack comprises a base and multiple rack bodies with different sizes, the rack bodies are made of transparent materials and vertically fixed to the base, and the rack bodies are internally provided with light sources. The method for conducting garment quality control through the inflatable garment quality control rack comprises the following steps that a to-be-detected garment is arranged on the rack bodies of the inflatable garment quality control rack in a sleeving mode, the light sources inside the rack bodies are started, a quality inspector can conduct detection with the help of the light sources located inside the garment, the quality inspector can sequentially put sleeves, the trunk of tops and trousers on the rack bodies in a sleeving mode, and after detection is completed, the sleeves, the trunk of the tops and the trousers are taken down and replaced with other parts of the garment for detection. Detection is conducted by selecting different rack bodies according to the positions of the garment, the garment can be supported, all positions of the garment can be illuminated by the light sources without deal corner, and the possibility of missing detection is lowered. In addition, the quality inspector does not need to support the garment with hands, and detection is easier.

The invention provides an expert mining method and system based on patent data, a storage medium and an electronic terminal. The method specifically comprises the following steps: constructing a patent pool of a target field; establishing a patent domain classification model for classifying the patents in the patent pool according to the sub-domains of the target domain; and value evaluation is carried out on patents in the sub-fields obtained based on the patent field classification model, and experts associated with the evaluated patents in the sub-fields are mined according to evaluation result information. The patent data is analyzed and mined based on the artificial intelligence technology, so that global scientific and technological expert information in the specific field can be efficiently obtained, the manual marking cost is greatly reduced, the probability of missed detection of the target patent is greatly reduced, and the problem that patent IPC classification is not suitable for the industry enough is solved.

The invention relates to the technical field of ceramic defect detection, and particularly discloses a ceramic surface defect detection device and a ceramic surface defect detection method. The ceramic surface defect detection device comprises a light source, an image collector and a data processor, wherein the light source is located above to-be-detected ceramic and sample ceramic, and is used for generating light and irradiating the to-be-detected ceramic or the sample ceramic; the image collector is positioned above the to-be-detected ceramic and the sample ceramic, and is used for collecting an image of the sample ceramic under light irradiation and collecting an image of the to-be-detected ceramic under light irradiation; and the data processor is electrically connected with the imagecollector, and is used for acquiring the image of the sample ceramic as a sample image, acquiring the image of the ceramic to be detected as a detection image and calculating and extracting a defectpart in the detection image according to the sample image. The ceramic surface defect detection device and the ceramic surface defect detection method have the advantages of low cost, very low misjudgment probability and very low missed detection possibility.

The invention relates to the field of microbiological analysis and detection, and particularly discloses a method for detecting clostridium perfringens in drinking natural mineral water. The inspection method comprises the following steps: a, filtering a water sample by adopting a filter membrane, then tightly placing the filter membrane on a bottom culture medium, paving a middle culture medium on the filter membrane, carrying out anaerobic inverted culture for 24-26h at the temperature of 35-37 DEG C, and counting the number of black bacterial colonies; and b, picking 3-5 black bacterial colonies, respectively inoculating the black bacterial colonies on a liquid thioglycolate culture medium, culturing for 18-24 hours at the temperature of 35-37 DEG C, and taking the black bacterial colonies to carry out a confirmation test. By means of the detection method, the black characteristic of the cultured bacterial colony is obvious, identification is easy, and the accuracy of the detection result is high.

The invention relates to a novel coronavirus detection kit. The novel coronavirus detection kit comprises an antigen component and a luminous component, the antigen component contains a novel coronavirus protein-magnetic bead compound, and the novel coronavirus protein-magnetic bead compound comprises an S1 protein-magnetic bead compound, an S2 protein-magnetic bead compound, an E protein-magnetic bead compound, an M protein-magnetic bead compound and an N protein-magnetic bead compound. The luminous component contains an anti-human IgG antibody, and a luminous marker is marked on the anti-human IgG antibody. The novel coronavirus detection kit disclosed by the invention is based on a two-step indirect immunoassay principle of direct chemiluminescence, the concentration of a novel coronavirus IgG antibody in a to-be-detected sample can be quickly judged by utilizing a corresponding chemiluminescence tester, and by coating all novel coronavirus antigens which possibly generate antibodies to the surfaces of magnetic beads, the missing detection caused by different antibodies generated in bodies of individual patients is avoided to the greatest extent.

The embodiment of the invention provides a target object detection method and device, electronic equipment and a computer storage medium, and the method comprises the steps: carrying out the target tracking of a target object when determining that a mechanical arm picks up the target object from any one turnover box, and the height of the target object is greater than the height of any one turnover box, and obtaining real-time position information of the target object; and when it is determined that the target object falls off from the mechanical arm according to real-time position information of the target object, determining the area where the falling point of the target object is located according to position information of the target object at the current moment and area position information, wherein the area position information comprises areas where all types of turnover boxes are located.

The invention discloses a DNA standard sample for transgenic component detection and application of the DNA standard sample. The DNA standard sample comprises DNA fragments shown as SEQ ID NO.1-7, andthe DNA fragments are specific fragments of components T-E9, T-NOS, P-CaMV35S(P-35S), PAT, T-PinII, P-Rbcs4, T-CaMV35S(T-35S). By detection of the seven targets, most of current commercial transgenicvarieties (at least 63) can be covered, and only a transgenic maize DAS40278 transformant and transgenic soybean DP305423 and CV127 transformants without exogenous components fail to be detected. According to detection, uniformity, stability, definite value and the like of the standard sample all meet requirements in detection, and the standard sample can be applied to quality control in daily detection of corresponding exogenous components, verification and evaluation of detection agents, laboratory proficiency testing activity and the like and is available for commercial popularization andapplication.

The invention discloses an ultrasonic detection method for defects at the middle parts of welding seams of an extra-large wall thickness SAWH steel pipe and relates to the technical field of ultrasonic flaw detection devices or methods. The ultrasonic detection method comprises the following steps: manufacturing artificial defects on the upper sides and the lower sides of the welding seams; respectively clamping one ultrasonic detection probe on the outer wall of a steel pipe on each of the left sides and the right sides of the welding seams, adjusting the distances from the probes to an upper side vertical hole or a lower side vertical hole well, slightly adjusting the probes and finding out defect reflection highest waves through an ultrasonic flaw detector; calibrating the ultrasonic flaw detector according to the reflection highest waves; detecting the welding seams of the steel pipe in batches by using the calibrated ultrasonic flaw detector. With the adoption of the method, the possibility of missing detection of defects in the middle region of the welding seams can be effectively reduced, the detection completeness of the steel pipe welding seams is improved, the missing detection probability of welding seams is reduced and the ex factory pass rate of the steel pipe is guaranteed, so that the product quality is improved.