40results about How to "Improve evaluation ability" patented technology

The invention pertains to the field of the image fusion technology in image process, which relates to a quality comprehensive evaluation method of fusion images based on fuzzy neural network and comprises the following steps: a sample set of fusion images is established, and each group of samples comprises a subjective evaluation grade sample of fusion images and two or more than two objective evaluating indicator samples obtained by evaluating the fusion image objectively; a quality evaluation module of fusion images based on fuzzy neural network is established; the obtained samples are trained, and the subjective evaluation grade sample of fusion images is adopted as expected output, and the correlation parameters for evaluating indicator weighing and fuzzy membership function are generated through network learning; the objective evaluating indicator of fusion images to be evaluated is calculated, and the evaluation grade result is generated by taking advantage of the established fusion image quality evaluation module. The method of the invention has comparatively good flexibility, and in the way of network training, novel fusion image quality evaluating indicator is learnt, so as to expand network evaluation ability and realize completely automatic evaluation.

The invention relates to a real-time classroom evaluation achieving system based on the network technology. The system comprises student identity cards, a teacher hand-held terminal and a server-side module, wherein the student identity cards are used for identifying student identities, the teacher hand-held terminal is used for identifying the student identities according to the student identity cards and sending a control instruction, and the server-side module is used for receiving the control instruction sent by the teacher hand-held terminal and converting the control instruction into actual operation. The invention further relates to a real-time classroom evaluation achieving method based on the network technology. By the adoption of the real-time classroom evaluation achieving system and method based on the network technology of the structure, a teacher can conveniently and rapidly evaluate students in class in the elementary education stage, data are immediately recorded and transferred through the mobile network, the vivid and immediate effect display is achieved, the classroom evaluation actions of the teacher on the students can be sufficiently recorded, relevant data are accumulated, meanwhile, the evaluation result is displayed on a screen, the evaluation effect is enhanced, and the application range is wider.

The invention belongs to a flight test-flight technique and relates to a flight simulating method for flight quality and operating characteristics of a transport plane test pilot. The flight simulating method comprises the following steps: taking a certain type of transport plane as a prototype and establishing a dynamic simulating model for different quality characteristics of the transport plane; confirming pneumatic parameters under the quality characteristics according to to-be-simulated different quality characteristics, and resolving an operation response of the airplane in real time according to the pneumatic parameters; performing flight quality modal parameter calibration on the resolved dynamic simulating model for the different quality characteristics, thereby meeting the expected quality and operating characteristics. By utilizing the method provided by the invention, the test pilot can experience a standard and continuous change process of the airplane operation and quality characteristics, so that the evaluating capacity of the test pilot for a task can be promoted; the operation and quality characteristics of the presently simulated airplane can be graphically displayed in real time by combining flight quality standard evaluation indexes; the flight quality level can be directly given; the physical significance is clear; the training for the level evaluation habit of the test pilot is benefited.

The invention relates to a real-time classroom teaching evaluation achieving system and method based on the Internet of Things technology. The system comprises a student identification device, a teacher hand-held terminal device, an evaluation information local client side and an evaluation information remote server. The method comprises the steps that the teacher hand-held terminal device reads coded information in the student identification device, sends an evaluation instruction to the evaluation information local client side and displays the returned evaluation result, the evaluation information local client side transmits the evaluation information to the evaluation information remote server and displays the corresponding evaluation result, and the evaluation information remote server returns the evaluation result and carries out follow-up extension application operation according to the evaluation information. By the adoption of the real-time classroom teaching evaluation achieving system and method based on the Internet of Things technology, the classroom evaluation actions of a teacher on students can be recorded, relevant data are accumulated, the evaluation effect is enhanced, the classroom teaching informationization degree is improved, and powerful support is provided for educational reform and instructional strategy adjustment.

The invention provides a method for dynamically detecting a program third-party library and carrying out security evaluation. The method specifically comprises the following steps: obtaining vulnerability lists of an authority information security vulnerability library and a custom information security vulnerability library; scanning the program third-party library according to the authority information security vulnerability library and the vulnerability list of the custom information security vulnerability library to obtain vulnerability information of the program third-party library; performing security assessment on the program third-party library according to the vulnerability information of the program third-party library, wherein the custom information security vulnerability librarycomprises a custom information security vulnerability library set for a non-open-source third-party library. The pertinence of the vulnerability list can be enhanced through the vulnerability list obtained by the custom information security vulnerability library; meanwhile, an interface can be set at will in the vulnerability list of the custom information security vulnerability library, so thatthe method is combined with user behaviors, convenient to expand, good in expansibility and high in flexibility; and the detection efficiency of the third-party library security evaluation based on the file system software review is improved.

The invention discloses a tensor space-based no-reference high dynamic range image objective quality evaluation method. From image data, a colorful high dynamic range image is represented with a three-order tensor; then a distorted high dynamic range image is subjected to tensor decomposition through a Tucker decomposition algorithm in tensor decomposition to obtain three characteristic images, namely, a first characteristic image, a second characteristic image and a third characteristic image are obtained, wherein the three characteristic images fuse color information of the high dynamic range image; a manifold structure characteristic of the first characteristic image and perception detail contrast characteristics of the second and third characteristic images are extracted; and an objective quality evaluation value of the distorted high dynamic range image is calculated by utilizing a support vector regression method in machine learning, so that the objective quality evaluation of the no-reference colorful high dynamic range image is realized, the evaluation effect is remarkably improved, and the correlation between an objective evaluation result and subjective perception is effectively improved.

The invention discloses a student online class learning state evaluation method based on facial recognition. The method comprises the steps of obtaining a facial image of a student, a student questionanswering situation and student information; obtaining a question answering result of the student according to the comparison condition of the question answering condition of the student and a reference answer; standardizing the acquired face image into consistent picture information, and inputting the picture information into a trained micro-expression recognition convolutional neural network model to obtain an online lesson listening comprehension degree state of the student; obtaining the concentration degree of the student according to the comparison condition of the ratio of the face length and width of the student to a preset standard face length-width ratio and the comparison condition of the eye opening height of the student to a preset standard face eye opening height; and takingthe question answering result of the student, the online lesson listening comprehension degree state and the concentration degree as the online lesson learning state evaluation result of the student.According to the method, the recognition efficiency can be improved, and the evaluation effect is improved.

The invention relates to a preparation method and application of a 20 (R)-ginsenoside Rg3 / soya bean lecithin / cholesterol / folic acid lipidosome medicine and belongs to the field of medicine health care products.By optimizing the ratio of soya bean lecithin, cholesterol and an encapsulation medicine to obtain 20 (R)-ginsenoside Rg3 lipidosome, the grain diameters of the 20 (R)-ginsenoside Rg3 lipidosome are reduced, and meanwhile the stability of the lipidosome medicine is enhanced; folic acid is used for conducting target modification on the encapsulated 20 (R)-ginsenoside Rg3 medicine lipidosome, and then target medicine delivery of cancer cells is achieved.Experimental results show that the encapsulation rate of the 20 (R)-ginsenoside Rg3 lipidosome can be up to 90% or above.The preparation method of the composite lipidosome medicine is simple and efficient.The prepared composite lipidosome is low in cytotoxicity, has the slow release feature and is capable of prolonging the curative effect, safe, efficient and high in targeting, good evaluating effects are obtained in physical representation and extracorporeal biological study, and a new approach is provided for research and development of anti-cancer medicines.

The invention discloses an opto-acoustic and ultrasonic dual-mode osteoporosis detection method and a detection device. The detection device is composed of two parts, namely a host machine and a probe, wherein the host machine comprises a laser device, a laser modulator, a collimating and coupling unit, a display module, an opto-acoustic mode changeover switch, an ultrasonic signal driver and a processor; the probe is composed of an acoustic emission focusing probe, a pre-amplifier, an ultrasonic transducer array and a transparent colloid; and the transparent colloid is attached on human skin. The device disclosed by the invention integrates opto-acoustic and ultrasonic advantages and solves the problem that an existing bone quality assessment DXA (dual X ray absorptiometry) cannot provide bone collagen information, while bone quality is determined by bone density and bone collagen, in which the bone density determines bone strength and the content of the bone collagen determines bone toughness; and a bone quality assessment capacity can be significantly improved by virtue of an opto-acoustic / ultrasonic imaging technology. The detection method and the detection device disclosed by the invention have the obvious advantages of being noninvasive, free from radiation, low in detection cost, accurate in assessment and the like.

The invention provides a tone mapping image quality evaluation method based on gradient magnitude similarity, and belongs to the field of image processing. The method provided by the invention comprises the following steps: 1) calculating gradient maps of a high dynamic image and a tone mapping image converted by a tone mapping device; 2) carrying out dynamic range adjustment based on a human visual system on the gradient maps corresponding to the high dynamic image and the tone mapping image; 3) calculating the similarity of the gradient maps, and using a tone mapping amplitude as a weight; 4) calculating a natural value of the tone mapping image by means of contrast, brightness and detail description; and 5) merging the similarity value with the natural value. The method provided by the invention is reasonable in design, and can be used for effectively evaluating the quality of the tone mapping image by adopting the gradient magnitude similarity feature capable of effectively capturing image distortion and further referring to the natural features (the image must looknatural) of the image, and thus the evaluation performance is improved.

The invention discloses an objective colorful image quality evaluation method based on online manifold learning. According to the method, taking consideration of the relationship between significance and objective image quality evaluation, a visual significance detection algorithm is utilized, the largest fusion significance graph is acquired through solving a respective significance graph of a reference image and a distortion image, a significance difference value of a reference image block and a corresponding distortion image block can be balanced on the basis of the largest significance of an image block of the largest fusion significance graph by utilizing an absolute difference value, so a reference visual significance image block and a distortion visual significance image block are extracted through screening, an objective quality evaluation value of the distortion image can be calculated by utilizing manifold characteristic vectors of the reference visual significance image block and the distortion visual significance image block, the evaluation effect is substantially improved, and pertinence between an objective evaluation result and subjective perception is high.

The invention provides a stereo image objective quality evaluation method integrating manifold and binocular features. Based on human eye manifold perception, an orthogonal local preserving projection algorithm is used to acquire a matrix after dimensionality reduction and albefaction from a natural scene plane image for training to acquire an optimal mapping matrix. In order to improve the accuracy and stability of evaluation, image blocks which are not important to visual perception are removed. The manifold feature vector of selected image blocks is extracted through the optimal mapping matrix. Structure distortion of a distortion image is measured through manifold feature similarity. The influence of the image brightness variation on a human eye is considered. The brightness distortion of the distortion image is calculated based on the mean of the image blocks. After the manifold similarity and the brightness similarity are acquired, a binocular contention model is used to carry out linear weighting on the quality values of left and right viewpoint images to acquire the quality value of a distortion stereo image. An evaluation result is highly consistent with the subjective perception evaluation result of the human eye.

The invention provides a comprehensive evaluation method and device for an intelligent park energy utilization scheme. The method comprises the following steps that: according to the evaluation matrixof a pre-established evaluation index system, constructing a standard evaluation matrix; according to the standard evaluation matrix, using an entropy weight method to calculate the weight of each index; according to the weight of each index, calculating a comprehensive effect index; and analyzing and comparing relative proximity indexes in the comprehensive effect index of each scheme to comprehensively evaluate each scheme. The evaluation device comprises an index system creating unit, an evaluation matrix construction unit, a standard processing unit, an entropy weight calculation unit andan analysis and comparison unit. By use of the technical scheme provided by the method, the effect indexes of different properties and different dimensions are combined into the relative proximity index, and the relative proximity index is analyzed and compared to realize the evaluation of the comprehensive effects of different energy utilization schemes.

The invention provides a phase-based partial discharge generation device and a phase-based partial discharge generation method with adjustable discharge capacity and density. The phase-based partial discharge generation device comprises a main control unit, a PWM circuit, a filtering circuit, a pulse generation circuit, a phase shaping circuit, a key and a knob switch, wherein the pulse generationcircuit is used for generating a discharge pulse according to an instruction of the main control unit; the PWM circuit is used for generating a pulse voltage according to the instruction of the maincontrol unit, after the pulse voltage is stabilized and smoothed into a DC voltage by means of the filtering circuit, inputting the DC voltage into the pulse generation circuit to perform voltage regulation on the pulse generation circuit, and further outputting stable discharge voltage; and the phase shaping circuit is used for shaping a phase pulse output from the main control unit into a sinusoidal signal to serve as a phase output signal. The phase-based partial discharge generation device and the phase-based partial discharge generation method can realize verification and performance evaluation of a partial discharge monitoring system and equipment thereof, thereby guaranteeing the safe operation of the partial discharge monitoring system, finally guaranteeing the safe operation of cables, and guaranteeing the stability and reliability of power supply.

The invention discloses a method for evaluating bone elasticity moduli by using photoacoustic time-domain signals. The method comprises the following steps of: firstly, regulating parameters of different bone trabecular materials to obtain cancellous bone models at different bone elasticity moduli; then simulating the cancellous bone models at different bone elasticity moduli to obtain corresponding photoacoustic time-domain signals; and performing preprocessing, including noise reduction and signal correction, on the photoacoustic time-domain signals; then quantizing the corrected photoacoustic time-domain signals to obtain the relationship between quantized parameters and the bone elasticity moduli; and finally, performing photoacoustic effect excitation on the cancellous bone to be detected to obtain the corresponding photoacoustic time-domain signals; and performing calculation according to the relationship between the quantized parameters and the bone elasticity moduli to obtain the bone elasticity modulus of the cancellous bone to be detected. The method has the advantages of no invasion, no radiation, low detection cost and operation convenience.

The invention discloses a steel pipeline online ultrasonic detection device and method. The device mainly comprises a water collecting tank, a driving device, a support rolling platform, a coupling device, an ultrasonic probe, a control system, an ultrasonic detector and a data collection system. The driving device drives the ultrasonic detection device to automatically move and detection along the surface of the detected pipeline through the control of the control system, thereby avoiding the problem of pipeline quality defect caused by the missing detection of the traditional non-continuously point-by-point measurement check method. The device is high in measurement precision, the measurement result is more accurately, the manpower labor is saved at the same time; the device is suitablefor the high-speed requirement of the online detection and can be extensively applied to the occasion needing the online detection.

The present invention relates to an eye fundus image quality evaluation device and method using transfer learning, and more particularly, to an eye fundus image quality evaluation device and method using transfer learning, which evaluate the quality of an eye fundus image after performing data preprocessing on an acquired eye fundus image using transfer learning using a convolutional neural network (CNN) model. Therefore, low-quality images are discarded, only high-quality images are applied to learning, and the convolutional neural network is an image classification artificial intelligence model for learning general images.

The invention discloses a three-dimensional image quality evaluation method based on a sparse binocular fusion convolutional neural network, and the method comprises the following steps: S1, constructing a three-dimensional image quality evaluation network based on the binocular fusion convolutional neural network, and the network comprises left and right branches and a fusion branch; and S2, applying a structured sparse constraint to each layer of the binocular fusion convolutional neural network, wherein an objective function of network optimization is shown as a formula (1). The three-dimensional image quality evaluation method of the patent is more accurate and efficient, better fits the human eye perception quality, is higher in operation speed, and promotes the development of a three-dimensional imaging technology to a certain extent.

The invention discloses a photoacoustic and ultrasonic dual-mode osteoporosis detection method and device, which consists of two parts, namely a host and a probe, wherein the host includes a laser, a laser modulator, a collimation coupling unit, a display module, an optical An acoustic mode switching switch, an ultrasonic signal driver and a processor; the probe is composed of an acoustic emission focusing probe, a preamplifier, an array of ultrasonic transducers, and a transparent colloid, and the transparent colloid is pasted on human skin. The reported device combines the advantages of photoacoustics and ultrasound, and solves the problem that the existing bone quality evaluation DXA cannot provide collagen information, and bone quality depends on bone density and bone collagen, in which bone density determines bone strength, and bone collagen content determines bone quality. Toughness, photoacoustic / ultrasound imaging will significantly improve the ability to evaluate bone quality. The invention has the obvious advantages of no trauma, no radiation, low detection cost, accurate evaluation and the like.

The invention belongs to the technical field of sperm quantitative detection and analysis and particularly relates to a sperm DNA fragmentation number fluorescence detection method, a detection kit and application thereof. Based on defects of an existing SDF detection method and incomplete evaluation index DFI, the application aims at the current situation that an accurate quantitative evaluation for sperm DNA fragmentation degree, which can directly measure DNA damage, is convenient and rapid to realize and has simple requirements, is lacked at present, and aims to meet national requirements. According to the invention, the number of sperm DNA breaking sites is creatively used as an index for evaluating the integrity of sperm DNA and introduced into a PCR detection platform, and an enzyme-assisted sperm DNA breaking point number fluorescence detection kit and a detection method are developed.

The invention relates to a tongue picture image evaluation method, which comprises the following steps of: 1, acquiring tongue picture images of an object at different periods, and acquiring tongue picture image characteristic indexes; S; step 2, selecting a first tongue picture image of the object, and obtaining a first tongue picture image feature index point A; S; step 3, selecting a second tongue picture image of the object, and obtaining a second tongue picture image feature index point B; 4, establishing a tongue picture image feature index coordinate system, and selecting a reference tongue picture image feature index point C; S; step 5, connecting AB and AC, and acquiring a projection point D of B on the AC; S; step 6, evaluating the second tongue image according to a formula (shown in the specification), wherein the formula (shown in the specification) of the second tongue image is shown in the specification, and the formula (shown in the specification) of the second tongue image is shown in the specification; 7, judging whether S is greater than 0 or not, and if S is greater than 0, determining that the second tongue image is good; O; otherwise, t, the difference is determined;. The method has the advantages that the tongue image image is quantized through a formula, t, the change trend of the tongue image is reflected, and qualitative analysis is carried out on the tongue image; A; and the evaluation effect is objective, t, the practicability is high, and the application range is wide.

The invention discloses a video action quality evaluation method and system based on group-sensitive contrastive regression, wherein the method includes: selecting a corresponding example video and example video score according to the current video; Perform spatio-temporal feature extraction and construct merged features; build a group-sensitive regression tree network to regress the merged features to get the final difference score, and combine the final difference score with the sample video score to get the current video score. This method obtains the final target action score by modeling the gap between the target action and the example action, which improves the accuracy of the model's action quality evaluation.

The invention provides a method for dynamically detecting a program third-party library and carrying out security evaluation. The method specifically comprises the following steps: obtaining vulnerability lists of an authority information security vulnerability library and a custom information security vulnerability library; scanning the program third-party library according to the authority information security vulnerability library and the vulnerability list of the custom information security vulnerability library to obtain vulnerability information of the program third-party library; performing security assessment on the program third-party library according to the vulnerability information of the program third-party library, wherein the custom information security vulnerability librarycomprises a custom information security vulnerability library set for a non-open-source third-party library. The pertinence of the vulnerability list can be enhanced through the vulnerability list obtained by the custom information security vulnerability library; meanwhile, an interface can be set at will in the vulnerability list of the custom information security vulnerability library, so thatthe method is combined with user behaviors, convenient to expand, good in expansibility and high in flexibility; and the detection efficiency of the third-party library security evaluation based on the file system software review is improved.

The invention discloses a method and device for evaluating bone collagen content based on a resonance state, which includes a laser, a laser controller, a display module, an ultrasonic transducer, a preamplifier, a lock-in amplifier and a coupling agent. The coupling Pasted on human skin, the device reported in the present invention can realize the detection of bone collagen content, solve the problem that in the existing evaluation of bone quality, only rely on the single evaluation value of bone density, and at the same time realize the control of collagen content on the bone surface. influence of the signal. The invention has the obvious advantages of no trauma, no radiation, low detection cost, accurate evaluation and the like.

The invention discloses a detection performance testing device of an array sensing well detection instrument. The method includes the following steps that a system for testing the detection performance of the array sensing well detection instrument is composed of three devices, wherein the three devices are the array sensing well instrument scale device, the array sensing well detection instrument radial detection depth testing device and the array sensing well detection instrument lengthwise resolution testing device. The system for testing the detection performance of the array sensing well detection instrument can be used for carrying out an instrument detection performance test on the array sensing well detection instrument. According to the detection performance testing device of the array sensing well detection instrument, the detection performance of the array sensing well detection instrument can be accurately tested, measurement errors by the instrument are reduced, the well detection quality of the instrument when the instrument is used on a spot is improved and the stratum comprehensive evaluation effect can be easily improved.

The invention pertains to the field of the image fusion technology in image process, which relates to a quality comprehensive evaluation method of fusion images based on fuzzy neural network and comprises the following steps: a sample set of fusion images is established, and each group of samples comprises a subjective evaluation grade sample of fusion images and two or more than two objective evaluating indicator samples obtained by evaluating the fusion image objectively; a quality evaluation module of fusion images based on fuzzy neural network is established; the obtained samples are trained, and the subjective evaluation grade sample of fusion images is adopted as expected output, and the correlation parameters for evaluating indicator weighing and fuzzy membership function are generated through network learning; the objective evaluating indicator of fusion images to be evaluated is calculated, and the evaluation grade result is generated by taking advantage of the established fusion image quality evaluation module. The method of the invention has comparatively good flexibility, and in the way of network training, novel fusion image quality evaluating indicator is learnt, so as to expand network evaluation ability and realize completely automatic evaluation.

The invention discloses a biomedical health service evaluation system and method based on big data, and belongs to the technical field of biomedical treatment. The method comprises the following steps: Step 1, a health service platform analyzes health data uploaded by a user, judges a health service type requested by the user, and processes the health data uploaded by the user based on a judgment result; 2, the hospital terminal evaluates the deterioration degree of the health state of the user based on the transmitted health data, the health data are transmitted to a matched doctor terminal according to the evaluation result, and a doctor analyzes the health data at the doctor terminal; 3, the user side receives analysis results and suggestions fed back by the health service platform and regularly sends health feedback data to the health service evaluation terminal; and Step 4: the health service evaluation terminal performs comprehensive evaluation on the health service of the health service platform to ensure that the user knows the health service evaluation value of the health service platform in real time, so that the service experience of the user is improved.

The invention discloses an objective evaluation method of image quality based on the similarity of manifold features, which first adopts two strategies of visual salience and visual threshold to remove image blocks that are not important to visual perception, that is, image block rough selection and fine selection process After completing the block selection, use the best mapping matrix to extract the manifold feature vector of the image block selected from the original undistorted natural scene image and the distorted image to be evaluated, and then measure the distorted image by the similarity of the manifold feature Structural distortion; after considering the impact of image brightness changes on the human eye, the brightness distortion of the distorted image is calculated based on the average value of the image block; finally, the quality score is obtained according to the structural distortion and brightness distortion, which makes this method have higher evaluation accuracy , also expands its ability to evaluate various types of distortion, and the evaluation performance is not affected by the image content and distortion type, and has a high consistency with the subjective perception quality of the human eye.