CN114792371B - Method, device, equipment and medium for determining wire real-time segmentation and identification algorithm - Google Patents
Method, device, equipment and medium for determining wire real-time segmentation and identification algorithm Download PDFInfo
- Publication number
- CN114792371B CN114792371B CN202210508826.3A CN202210508826A CN114792371B CN 114792371 B CN114792371 B CN 114792371B CN 202210508826 A CN202210508826 A CN 202210508826A CN 114792371 B CN114792371 B CN 114792371B
- Authority
- CN
- China
- Prior art keywords
- algorithm
- weight
- features
- fuzzy
- feature
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/217—Validation; Performance evaluation; Active pattern learning techniques
- G06F18/2193—Validation; Performance evaluation; Active pattern learning techniques based on specific statistical tests
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Probability & Statistics with Applications (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Image Analysis (AREA)
Abstract
The present disclosure provides a method, apparatus, device and medium for determining an algorithm for real-time wire segmentation and identification. The method comprises the following steps: establishing a hierarchical structure model based on the decision target, the algorithm to be selected and the characteristics; constructing a comparison matrix based on the hierarchical structure model and the triangular fuzzy scale, and determining fuzzy numbers and fuzzy geometric values corresponding to each feature; determining fuzzy weights of the features based on the fuzzy geometric values, and performing defuzzification treatment on the fuzzy weights to obtain weight values; carrying out normalization processing on the weight values to obtain normalized weights of the features; constructing a decision matrix of the algorithm to be selected relative to each feature, and determining a normalization weight corresponding to each algorithm to be selected when each feature is used as a standard; and calculating a weight result of each algorithm to be selected based on the normalized weight of the features and the normalized weight of the algorithm to be selected, and evaluating the algorithm to be selected based on the weight result. The method and the device can accurately and efficiently evaluate the algorithm to be selected, reduce the evaluation cost and improve the credibility of the evaluation result.
Description
Technical Field
The disclosure relates to the technical field of real-time segmentation and recognition algorithms, and in particular relates to a method, a device, equipment and a medium for determining a wire real-time segmentation and recognition algorithm.
Background
In addition, the real-time segmentation algorithm can obtain a very good effect on the processing of streaming media data, and the real-time segmentation and recognition algorithm is one of very important algorithms in the field of artificial intelligence at present. For example, taking the smart grid field as an example, real-time segmentation and recognition of the electric wire can be realized by using a real-time segmentation and recognition algorithm, however, the schemes of the existing real-time segmentation and recognition algorithm are numerous, so how to evaluate the real-time segmentation and recognition algorithm selected by the user, and thus determine the most efficient real-time segmentation and recognition algorithm, which is one of the important concerns in the field.
In the prior art, when the real-time segmentation and recognition algorithm is evaluated, the following method is generally adopted, namely various real-time segmentation and recognition algorithms to be evaluated are evaluated based on a traditional expert system, when an algorithm evaluation index system is established by utilizing the expert system, the weights of various indexes are calculated according to a large amount of basic data in an expert system database and by combining a model based on a convolutional neural network, so that the various real-time segmentation and recognition algorithms are evaluated according to the index weights. The existing method for evaluating the real-time segmentation and recognition algorithm has the problems of low evaluation efficiency, high evaluation cost, low accuracy of evaluation results, incapability of determining the most effective solution based on the evaluation results, and the like.
Disclosure of Invention
In view of the above, the embodiments of the present disclosure provide an algorithm evaluation method, apparatus, device, and medium based on fuzzy analytic hierarchy process, so as to solve the problems of low evaluation efficiency, high evaluation cost, and low accuracy of the evaluation result in the prior art.
In a first aspect of an embodiment of the present disclosure, an algorithm evaluation method based on fuzzy analytic hierarchy process is provided, including: acquiring characteristics for evaluating an algorithm to be selected, and establishing a hierarchical structure model for evaluating the algorithm to be selected based on a preset decision target, the algorithm to be selected and the characteristics; constructing a comparison matrix based on the hierarchical structure model and a preset triangular fuzzy scale, calculating the fuzzy number of the features in the comparison matrix to obtain the fuzzy number corresponding to each feature, and calculating a fuzzy geometric value corresponding to each feature by using the fuzzy number; determining fuzzy weights corresponding to each feature based on the fuzzy geometric values, and performing defuzzification processing on the fuzzy weights to obtain weight values corresponding to each feature; judging the weight sum of the features, and carrying out normalization processing on the weight values of the features according to the judging result to obtain normalization weights respectively corresponding to the features; respectively constructing a decision matrix of each candidate algorithm relative to each feature so as to determine a normalization weight corresponding to each candidate algorithm when each feature is used as a standard based on the decision matrix; and calculating a weight result of each candidate algorithm based on the normalized weight corresponding to the feature and the normalized weight corresponding to the candidate algorithm, and evaluating the candidate algorithm based on the weight result.
In a second aspect of the embodiments of the present disclosure, an algorithm evaluation device based on fuzzy analytic hierarchy process is provided, including: the acquisition module is configured to acquire characteristics for evaluating the algorithm to be selected, and establishes a hierarchical structure model for evaluating the algorithm to be selected based on a preset decision target, the algorithm to be selected and the characteristics; the construction module is configured to construct a comparison matrix based on the hierarchical structure model and a preset triangular fuzzy scale, calculate fuzzy numbers of the features in the comparison matrix to obtain fuzzy numbers corresponding to each feature, and calculate fuzzy geometric values corresponding to each feature by using the fuzzy numbers; the processing module is configured to determine fuzzy weights corresponding to each feature based on the fuzzy geometric values, and perform defuzzification processing on the fuzzy weights to obtain weight values corresponding to each feature; the judging module is configured to judge the weight sum of the features, and normalize the weight values of the features according to the judging result to obtain normalized weights respectively corresponding to the features; the determining module is configured to respectively construct a decision matrix of the algorithm to be selected relative to each feature so as to determine a normalization weight corresponding to each algorithm to be selected respectively when each feature is taken as a standard based on the decision matrix; the evaluation module is configured to calculate a weight result of each algorithm to be selected based on the normalized weight corresponding to the feature and the normalized weight corresponding to the algorithm to be selected, and evaluate the algorithm to be selected based on the weight result.
In a third aspect of the disclosed embodiments, an electronic device is provided, including a memory, a processor, and a computer program stored on the memory and executable on the processor, the processor implementing the steps of the above method when the processor executes the program.
In a fourth aspect of the disclosed embodiments, a computer-readable storage medium is provided, which stores a computer program which, when executed by a processor, implements the steps of the above-described method.
The above-mentioned at least one technical scheme that the embodiment of the disclosure adopted can reach following beneficial effect:
establishing a hierarchical structure model for evaluating the algorithm to be selected based on a preset decision target, the algorithm to be selected and the characteristics by acquiring the characteristics for evaluating the algorithm to be selected; constructing a comparison matrix based on the hierarchical structure model and a preset triangular fuzzy scale, calculating the fuzzy number of the features in the comparison matrix to obtain the fuzzy number corresponding to each feature, and calculating a fuzzy geometric value corresponding to each feature by using the fuzzy number; determining fuzzy weights corresponding to each feature based on the fuzzy geometric values, and performing defuzzification processing on the fuzzy weights to obtain weight values corresponding to each feature; judging the weight sum of the features, and carrying out normalization processing on the weight values of the features according to the judging result to obtain normalization weights respectively corresponding to the features; respectively constructing a decision matrix of each candidate algorithm relative to each feature so as to determine a normalization weight corresponding to each candidate algorithm when each feature is used as a standard based on the decision matrix; and calculating a weight result of each candidate algorithm based on the normalized weight corresponding to the feature and the normalized weight corresponding to the candidate algorithm, and evaluating the candidate algorithm based on the weight result. The technical scheme of the method and the device can accurately and efficiently evaluate the algorithm to be selected, reduce the evaluation cost and improve the credibility of the evaluation result.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the drawings that are required for the embodiments or the description of the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present disclosure, and other drawings may be obtained according to these drawings without inventive effort for a person of ordinary skill in the art.
FIG. 1 is a flow chart of an algorithm evaluation method based on fuzzy analytic hierarchy process provided by an embodiment of the present disclosure;
FIG. 2 is a schematic illustration of a hierarchical model for algorithm evaluation provided by an embodiment of the present disclosure;
fig. 3 is a schematic structural diagram of an algorithm evaluation device based on fuzzy analytic hierarchy process according to an embodiment of the present disclosure;
fig. 4 is a schematic structural diagram of an electronic device according to an embodiment of the present disclosure.
Detailed Description
In the following description, for purposes of explanation and not limitation, specific details are set forth, such as particular system configurations, techniques, etc. in order to provide a thorough understanding of the disclosed embodiments. However, it will be apparent to one skilled in the art that the present disclosure may be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present disclosure with unnecessary detail.
In a computer-aided system, real-time device segmentation is an indispensable module in the computer-aided system, and a real-time segmentation and recognition algorithm used for the real-time device segmentation is also widely used in various fields. For example, in the streaming media data segmentation technology, a real-time segmentation and recognition algorithm is used for segmenting and recognizing streaming media data on a website, and for example, a real-time segmentation and recognition algorithm of wires in a mobile terminal is widely used in the field of smart grids, and proved by practice, the real-time segmentation and recognition algorithm is very helpful to automatically detect wire faults and is very effective. The following describes several existing real-time segmentation and recognition algorithms with reference to specific scenarios and contents, and may specifically include the following:
1) Among real-time contactless Fall detection systems RT-Fall based on commercial WiFi devices, RT-Fall is an immediate, contactless, cheaper but correct indoor Fall identification system using commercial WiFi devices. RT-Fall utilizes the phase and amplitude of fine-grained Channel State Information (CSI) accessible in commercial WiFi equipment, and achieves the aims of real-time automatic segmentation and Fall detection for the first time, allows a user to perform daily activities, and does not need to wear any equipment on the body. First, in this fall detection system, the CSI phase difference on the two antennas is a more amplitude sensitive basis signal for activity recognition, and falls and fall-like activities can be segmented very reliably. Secondly, a sharp power distribution falling pattern of falling in the time-frequency domain is found, and new feature extraction and accurate falling segmentation and detection are further performed. The practical results in four different indoor situations show that the average sensitivity of RT-Fall is improved by 14% and the specificity is improved by 10%. ( Reference materials: H.Wang, D.Zhang, Y.Wang, J.Ma, Y.Wang, and S.Li, "RT-Fall: area-time and contactless Fall detection system with commodity WiFi devices," IEEE Transactions on Mobile Computing, vol.16, no.2, pp.511-526,2016. )
2) A real-time three-dimensional obstacle detection method comprises the steps of masking coordinates of point cloud data by using an external parameter matrix, supplementing missing data in original data by using an interpolation algorithm, eliminating the ground by using a RANSAC algorithm, and carrying out clustering segmentation on a point cloud fusion segmenter distance threshold value and angle threshold values of different distance intervals by using an enhanced DBSCAN clustering algorithm. The detection method eliminates the missing rate and improves the actual performance. Finally, practical results show that the method generates good-quality object detection on line through NVIDIA Jetson TX 2. ( Reference materials: Y.Liu, H.Zhu, B.Zhang, and y.su, "Real-Time Segmentation of Sparse 3D Point Clouds on a TX2," DEStech Transactions on Computer Science Engineering, no. cisnr,2020. )
3) Advanced deep learning methods are used for accurate, real-time segmentation of high resolution intravascular ultrasound images, and the goal of this study is to innovate and verify a deep learning procedure that automatically corrects the segmentation of intravascular ultrasound (IVUS) image arrangements in real-time. The developed deep learning method is verified on 20 blood vessels by using the estimation of two expert analysts as a reference standard, the innovative deep learning method works correctly, the high-resolution IVUS data set can be segmented, and the methods can improve the use of the IVUS in clinical experiments and analysis. ( Reference materials: bajaj et al, "Advanced deep learning methodology for accurate, real-time segmentation of high-resolution intravascular ultrasound images," International Journal of Cardiology, vol.339, pp.185-191,2021. )
4) The study proposes an effective image-based fault detection system that can automatically locate faults on the wire surface by using image processing methods and pattern recognition, and a damage detection algorithm combines the image improvement method with a principal component analysis algorithm. The analysis uses image improvement methods and denoising strategies to increase the overall value of the image. The proposed damage detection algorithm was verified by laboratory testing of 3 wires. Test results indicate that the proposed system can be used to diagnose a failure condition of a link chain. ( Reference materials: H. -n.ho, k. -d.kim, y. -s.park, and j. -j.lee, "An efficient image-based damage detection for cable surface in cable-supported bridges," Ndt E International, vol.58, pp.18-23,2013. )
In the smart grid field, a real-time segmentation and recognition algorithm is also used to automatically detect and remove a wire fault, for example, a wire real-time segmentation and recognition algorithm applied to a mobile terminal, by which a wire fault can be rapidly and effectively found and the cause and position of the wire fault can be recognized. Existing wire real-time segmentation and identification algorithms combine machine learning with artificial intelligence based frameworks and thus wire fault detection has become very advanced and efficient. Several known wire real-time segmentation and identification algorithms are described below in conjunction with the references, which may include the following:
1) In this article a live line based segmentation method is proposed which makes use of a comparison of equivalent object contours. This technique speeds up the segmentation mechanism, automatically converting the anchor points of the segmented reference contour into the undivided target slice. The segmentation is enhanced using automatic contour correction so that 51% to 73% interaction time can be maintained, making the live line value of the segmentation the same as before. (ref: M.J.Ehrhardt,and H.Handels,"Live-wire-based segmentation using similarities between corresponding image structures,"Computerized Medical Imaging Graphics,vol.31,no.7,pp.549-560,2007.)
2) Malmberg et al utilized a system of combined stereographic and haptic, which combined stereographic and haptic, simplifying the effectiveness of 3D collaboration. For segmentation of the volumetric image, the study proposes a new method based on a two-dimensional live line method. The proposed method comprises two parts: an interface for drawing 3D live wire arcs at the edges of objects in the volumetric image, and an algorithm that links 2 such arcs to form different surfaces. (ref. F.Malmberg, E.Vidholm, and I)."A 3D live-wire segmentation method for volume images using haptic interaction,"in International Conference on Discrete Geometry for Computer Imagery,2006,pp.663-673:Springer.)
3) This study proposes a new framework called Active Geometry Function (AGF) to solve the complex problem of real-time segmentation. AGF has the advantages of mathematical efficiency and computational complexity, as well as many reliable features similar to level set contours. The AGF can perform real-time segmentation within a few milliseconds per frame, and the segmentation result is equivalent to the result of manual searching and has the same performance as the manual searching. This real-time, segmentation capability simplifies diagnosis and workflow, and also allows innovative requests, such as interventional assistance and collaborative image acquisition for virtual segmentation. In applications involving online handwriting recognition, the actual performance is critical, however, conventional techniques typically wait until the entire arc is found before beginning the investigation, which certainly creates an interruption in the recognition mechanism. ( Reference materials: Q.Duan, E.D.Angelini, and A.F. Laine, "Real-time segmentation by active geometric functions," Computer methods programs in biomedicine, vol.98, no.3, pp.223-230,2010. )
4) Kour and Saabne propose an online Arabic character segmentation method based on real-time recognition. It defines some time consuming activities during writing, which is crucial for the segmentation mechanism. The proposed system has been structured and tested using an ADAB database with good results. ( Reference materials: kour and R.Saabne, "Real-time segmentation of on-line handwritten arabic script," in 2014 14th International Conference on Frontiers in Handwriting Recognition,2014,pp.417-422:IEEE. )
Based on the above disclosure, the existing wire real-time segmentation and identification algorithms are quite numerous, so that the existing wire real-time segmentation and identification algorithms need to be evaluated to determine the most efficient and best performing algorithm. The embodiment of the disclosure provides an algorithm evaluation method based on Fuzzy Analytic Hierarchy Process (FAHP), which evaluates real-time segmentation and recognition algorithms by adopting the Fuzzy Analytic Hierarchy Process (FAHP). FAHP is a simple and intuitive method for calculating the weights of alternatives, criteria, and ordering them to determine the most efficient solution. The disclosed embodiments rank multiple alternatives (i.e., candidate algorithms) using the FAHP method with fuzzy geometric mean, which is generally used for multi-decision cases involving ambiguity and uncertainty.
The conventional method for solving the multi-index decision evaluation problem is a hierarchical analysis AHP (Analytical Hierarchy Process), which generally comprises the steps of establishing a hierarchical structure model, constructing a judgment matrix, hierarchical single ordering and consistency check, hierarchical total ordering and consistency check, and the like, and finally carrying out weighted summation based on relative weights of indexes and normalized values of the indexes to finally obtain the comprehensive evaluation value of the system. Its range of applications is wide, but the following drawbacks still exist: the ambiguity of expert experience knowledge is not considered, and the scientificity of the index weight cannot be ensured; the implicit internal relation of each index is not considered, the traditional AHP method only carries out importance comparison on indexes of the same level, but cannot consider the influence relation among the indexes of the cross-level and the cross-category bottom layer; the information can be synthesized only after the evaluation of each evaluator is finished, and the information cannot be synthesized when the complementary judgment matrix is constructed.
The biggest problem of the analytic hierarchy process AHP is that when a certain level of evaluation indexes are many (such as more than four), the thinking consistency is difficult to ensure. In this case, the Fuzzy Analytic Hierarchy Process (FAHP) formed by combining the advantages of the fuzzy method and the analytic hierarchy process can solve the problem well. The basic idea and steps of the fuzzy analytic hierarchy process FAHP are basically consistent with those of AHP, but the following two aspects still have different points:
1. The established judgment matrix is different: in AHP, a consistency judgment matrix is established through element pairwise comparison, and in FAHP, a fuzzy consistency judgment matrix is established through element pairwise comparison;
2. the method for weighting the relative importance of each element in the matrix is different: the FAHP method improves the problems existing in the traditional analytic hierarchy process and improves the decision reliability. FAHP is based on fuzzy numbers, and fuzzy consistency matrices.
In the embodiment of the disclosure, a decision evaluation problem for solving the ambiguity of the real-time segmentation and recognition algorithm evaluation of the electric wires in the mobile terminal is provided, in order to realize the evaluation of the real-time segmentation and recognition algorithm, the embodiment of the disclosure applies the FAHP method to measure the weights of standard factors and alternatives and ranks the weights to determine the most efficient and effective algorithm, and simultaneously examines the effectiveness and efficiency of the real-time segmentation and recognition algorithm.
Fig. 1 is a flowchart of an algorithm evaluation method based on fuzzy analytic hierarchy process according to an embodiment of the present disclosure. The fuzzy analytic hierarchy process-based algorithm evaluation method of fig. 1 may be performed by a mobile terminal or a server. As shown in fig. 1, the method for evaluating an algorithm based on fuzzy analytic hierarchy process specifically includes:
S101, acquiring characteristics for evaluating an algorithm to be selected, and establishing a hierarchical structure model for evaluating the algorithm to be selected based on a preset decision target, the algorithm to be selected and the characteristics;
s102, constructing a comparison matrix based on the hierarchical structure model and a preset triangular fuzzy scale, calculating fuzzy numbers of features in the comparison matrix to obtain fuzzy numbers corresponding to each feature, and calculating fuzzy geometric values corresponding to each feature by using the fuzzy numbers;
s103, determining fuzzy weights corresponding to each feature based on the fuzzy geometric values, and performing defuzzification processing on the fuzzy weights to obtain weight values corresponding to each feature;
s104, judging the weight sum of the features, and carrying out normalization processing on the weight values of the features according to the judging result to obtain normalization weights respectively corresponding to the features;
s105, respectively constructing decision matrixes of the algorithms to be selected relative to each feature so as to determine normalization weights respectively corresponding to each algorithm to be selected when each feature is used as a standard based on the decision matrixes;
and S106, calculating a weight result of each algorithm to be selected based on the normalized weight corresponding to the feature and the normalized weight corresponding to the algorithm to be selected, and evaluating the algorithm to be selected based on the weight result.
Specifically, multiple evaluation indexes are involved in algorithm evaluation, so that the problem of multi-index decision evaluation for algorithm evaluation is full of ambiguity and uncertainty, and the FAHP method is an advanced version of the AHP method based on fuzzy logic theory. The FAHP method comprises a membership function and a conversion function from AHP scale number to fuzzy number, and is widely used for multi-index decision evaluation. In addition, the FAHP technique mainly solves the problem that the ambiguity and uncertainty are filled, resulting in difficult decision making, and in the embodiment of the present disclosure, the FAHP method is used to evaluate real-time wire segmentation and identification algorithms in mobile terminals.
Further, the decision target in the embodiment of the present disclosure refers to a problem to be solved by the FAHP method, that is, a target to be achieved by the FAHP method, where the decision target in the embodiment of the present disclosure is to evaluate a real-time segmentation and recognition algorithm; the algorithm to be selected refers to an alternative scheme in the FAHP method, namely various methods adopted for solving the problems, and in the embodiment of the disclosure, the algorithm to be selected is a wire real-time segmentation and identification algorithm; features refer to standard factors in the FAHP method, that is, factors, standards or conditions to be considered in evaluating the real-time segmentation and recognition algorithm, and features may also be considered as criteria for decision making, so that in the following embodiments of the disclosure, features may also be replaced by other terms, such as standards, factors, conditions, criteria, etc., where the substitution on terms does not constitute a limitation on the technical solutions of the disclosure.
Further, the features of the embodiments of the present disclosure are features obtained by means of feature extraction, raw data is obtained from related documents of existing wire real-time segmentation and recognition algorithms, and the raw data of the references is converted into digital features that can be processed while retaining the raw data information. These features are extracted from the raw data, and common features are selected from the extracted features and used as criteria for algorithmic evaluation. As shown in table 1, features extracted from the raw data are examples of the present disclosure.
TABLE 1 extracted features
In table 1, the numbers corresponding to the references are given, and common features are selected from all the features extracted in table 1 as criteria for evaluation, for example, sensitivity, specificity, quality, time, consistency, and stability may be selected as criteria.
In some embodiments, establishing a hierarchical model for evaluating the algorithm to be selected based on a preset decision goal, the algorithm to be selected, and the features includes: respectively taking a decision target as a highest layer, a to-be-selected algorithm as a bottommost layer, characteristics as a middle layer, and establishing a hierarchical structure model based on the highest layer, the bottommost layer and the middle layer; and evaluating the algorithm to be selected as a decision target, wherein the algorithm to be selected comprises a plurality of algorithms to be evaluated, and the characteristics comprise a plurality of standard factors for evaluating the algorithm to be selected.
Specifically, after determining the characteristics, the decision targets and the alternatives (i.e. the algorithms to be selected) in the algorithm evaluation, establishing a hierarchical structure model based on the FAHP method by utilizing the characteristics, the decision targets and the algorithms to be selected; FIG. 2 is a schematic diagram of a hierarchical model for algorithm evaluation provided by an embodiment of the present disclosure. As shown in fig. 2, the hierarchical structure model for algorithm evaluation may specifically include:
the highest layer in the hierarchical structure model is a decision target layer, wherein the decision target layer comprises a decision target for algorithm evaluation, namely, real-time segmentation and recognition algorithm evaluation is carried out; the lowest layer in the hierarchical structure model is a scheme layer, and the scheme layer comprises three alternative schemes, namely an algorithm-1, an algorithm-2 and an algorithm-3; the middle layer in the hierarchical model, namely a standard layer, also called a factor layer, a criterion layer, a feature layer and the like, contains some standards for algorithm evaluation, and the following six features are adopted as standards: sensitivity, specificity, quality, time, consistency, and stability.
In some embodiments, constructing the comparison matrix based on the hierarchical model and the predetermined triangular blur scale includes: based on all the features in the hierarchical structure model, a comparison matrix between the features is constructed by utilizing a triangular fuzzy scale, wherein the triangular fuzzy scale is used for representing the importance degree between any two features.
In particular, hierarchical Analysis (AHP) has been proposed to solve the difficulties by decomposing, classifying, and arranging the problems into a hierarchical framework. The AHP method relies on expert opinion, so the search decisions are susceptible to subjectivity. The fuzzy analytic hierarchy process theory is expanded, and the AHP method is used together with the FAHP method. In the fuzzy analytic hierarchy process FAHP, the scale in the analytic hierarchy process AHP is converted to a fuzzy triangle scale, and table 3 shows the fuzzy scale.
TABLE 3 fuzzy scale
In the fuzzy scale of Table 3, numbers 1-9 are used to represent the importance of the two factors to the decision target, and the method of fuzzy scaling is also known as fuzzy scaling or scaling.
Further, a comparison matrix between features is constructed by using a triangular fuzzy scale, and a pair of comparison matrices n is drawn.
Based on the extracted features, a comparison matrix, which may also be referred to herein as a decision matrix or a pair-wise comparison matrix, is constructed using the triangular blur scale. After the comparison matrix is constructed, a different value is set for each factor pair in the comparison matrix, where the value is used to represent the judgment of the importance of the decision target when the factors are compared in the factor layer.
TABLE 4 comparison matrix
In some embodiments, performing fuzzy number calculation on the features in the comparison matrix to obtain fuzzy numbers corresponding to each feature, and calculating fuzzy geometric values corresponding to each feature by using the fuzzy numbers, including: converting the language number between the feature pairs in the comparison matrix into triangular fuzzy numbers by using a preset conversion formula to obtain triangular fuzzy numbers respectively corresponding to each feature pair, and converting the comparison matrix into a fuzzy pairing comparison decision matrix according to the triangular fuzzy numbers; and calculating the fuzzy geometric value corresponding to each feature by using a preset fuzzy geometric value calculation formula based on the triangular fuzzy number of each feature pair in the pairing comparison decision matrix.
Specifically, after setting different values for each factor pair (feature pair) in the comparison matrix, a fuzzy number is assigned to each factor, i.e., the number of languages between the feature pairs in the comparison matrix is converted into a triangular fuzzy number from either one of the following two formulas:
A -1 ＝(l,m,u) -1
A -1 ＝(1/u,1/m,1/l)
where l represents the lower digit, m represents the median, and u represents the upper digit.
Further, after the language number is converted into the fuzzy number (i.e. the triangular fuzzy number) by using the above formula, a fuzzy pairing comparison decision matrix is obtained, as shown in table 5.
TABLE 5 fuzzy pair comparison decision matrix
Further, based on the triangular fuzzy number of each feature pair in the pairing comparison decision matrix, calculating a fuzzy geometric value corresponding to each feature by the following formula, wherein the fuzzy geometric value calculation formula is as follows:
where A represents the triangular blur number and n represents the number of features.
The blur geometry for each criterion (i.e., each feature) can be calculated using the above formula, as shown in table 6.
TABLE 6 fuzzy geometry values
Further, after obtaining the fuzzy geometric value of each standard, determining the fuzzy weight corresponding to each standard based on the fuzzy geometric value, and performing defuzzification processing on the fuzzy weight to obtain the weight value corresponding to each standard; for fuzzy weight W i The following formula was used for calculation:
W i ＝r i *(r 1 ,r 2 ,r 3 ,……,r 10 ) -1
wherein r is i Representing the blur geometry of each criterion.
When the fuzzy weight is subjected to defuzzification, the weight calculation can be performed by adopting the following formula:
(w i )＝l+m+u/3
wherein, (w) i ) A weight value representing each criterion;
by executing the above average formula, the weight W can be determined from the blur i Is obtained for each criterion (w i )。
In some embodiments, the determining the weight sum of the features, and normalizing the weight values of the features according to the determination result to obtain normalized weights corresponding to the features respectively includes: calculating the weight sum of the weights corresponding to all the features, and directly taking the weight corresponding to each feature as the normalized weight of the feature when the weight sum is smaller than or equal to 1; when the weight sum is greater than 1, converting the weight value of the feature into normalized weight so that the normalized weight sum corresponding to all the features is 1; and ranking the features based on the normalized weights corresponding to each feature.
Specifically, the weights of all the standards are summed, if the sum of the weights is greater than 1, the weight value needs to be converted into a normalized form, that is, the weight value is normalized, and the normalized weight can be calculated by using the following formula:as shown in Table 7, the blur geometry, blur weight, and normalized weight for each criterion are included, and the ranking for each criterion is also shown.
Further, a decision matrix of the candidate algorithms relative to each feature is respectively constructed, so that when each feature is used as a standard, the normalization weight corresponding to each candidate algorithm is determined based on the decision matrix. In practical application, the above embodiment is a process performed on a middle layer (i.e., a standard layer) of the hierarchical structure model, however, the FAHP method also needs to construct a judgment matrix of a scheme layer relative to the standard layer (i.e., a judgment matrix between the scheme and each standard), so as to obtain a scheme pairing decision matrix corresponding to each standard; the contents of the scheme pairing decision matrix under each standard will be described in detail below with algorithm-1, algorithm-2, algorithm-3 as alternatives. It should be noted that, the calculation process of the scheme pairing decision matrix is similar to the calculation process of the fuzzy pairing comparison decision matrix of the standard layer and the fuzzy geometric value, the fuzzy weight, the weight and the normalized weight in the above embodiment, and will not be described herein.
Table 8 lists the weights and normalized weights for each selection scheme based on sensitivity.
TABLE 8 scheme pairing decision matrix based on sensitivity criteria
Table 9 lists the weights and normalized weights for each selection scheme based on specificity.
TABLE 9 scheme pairing decision matrix based on specificity criteria
Table 10 lists the weights and normalized weights for each selection scheme based on quality.
TABLE 10 scheme pairing decision matrix based on quality criteria
Table 11 lists the weights and normalized weights for each option over time.
TABLE 11 scheme pairing decision matrix based on time criteria
Table 12 lists the weights and normalized weights for each selection scheme based on consistency.
TABLE 12 protocol pairing decision matrix based on consistency criteria
Table 13 lists the weights and normalized weights for each option based on stability.
TABLE 13 stability criterion based scheme pairing decision matrix
In some embodiments, calculating a weight result of each candidate algorithm based on the normalized weights corresponding to the features and the normalized weights corresponding to the candidate algorithms, and evaluating the candidate algorithms based on the weight results includes: and multiplying the normalized weight of the feature by the normalized weight of the algorithm to be selected calculated when the feature is taken as a standard to obtain a weight result corresponding to each algorithm to be selected, and ranking the algorithm to be selected according to the weight result so as to evaluate the algorithm to be selected according to the ranking.
Specifically, after normalized weights corresponding to each standard and normalized weights corresponding to the algorithms to be selected under each standard are sequentially processed by using the FAHP method, the weight result of each algorithm to be selected is calculated by the following formula:
where m represents the number of alternatives. By the above formula, the normalized weights corresponding to each criterion (i.e., the criterion weights in table 14) are multiplied by each row, the result of each alternative is calculated and ranked.
TABLE 14 weight results and algorithm rankings using FAHP method
From table 14, it can be seen that the decision result of each candidate scheme by using the FAHP method is that algorithm-2 is highest in rank, algorithm-1 is lowest in rank, and algorithm-3 is middle in rank, so it can be concluded that algorithm-2 is the most efficient algorithm among the three candidate algorithms. In practical applications, the candidate algorithms of the embodiments of the present disclosure include algorithms for real-time segmentation and identification of wires in images of mobile terminals.
Real-time segmentation is the activity of obtaining computationally efficient real-time segmentation (while maintaining substantial accuracy). Real-time segmentation and recognition algorithms are widely used in this modern society, real-time device segmentation being an essential module of computer-aided systems. These algorithms are very helpful and efficient for mobile terminal based wire fault detection. In the disclosed embodiments, the FAHP method is used to evaluate the real-time segmentation and recognition algorithm. The weights of the six criteria and three alternatives are measured and ranked according to their value. The highest weight of the sensitivity standard is obtained by calculating the weight of each standard, the weight value is 0.220, and the ranking is first; secondly, time, weight value is 0.214, rank second; the weight value of the quality is 0.200, and the third ranking is performed; the weight value of the consistency is 0.132, and the ranking is fourth; the weight value of the stability is 0.118, and the ranking is fifth; and the weight of the specificity is the lowest, the weight value is 0.113, and the ranking is sixth. Then, the weights of the alternative schemes (i.e., the algorithms to be selected) are sequentially measured according to each standard, and the result shows that the weight of the algorithm-2 is the highest and is 0.342, the weight of the algorithm-3 is 0.331, and the weight of the algorithm-1 is the lowest and is 0.322. Furthermore, the present disclosure effectively evaluates and discusses different uses of the real-time segmentation and recognition algorithm.
The following are device embodiments of the present disclosure that may be used to perform method embodiments of the present disclosure. For details not disclosed in the embodiments of the apparatus of the present disclosure, please refer to the embodiments of the method of the present disclosure.
Fig. 3 is a schematic structural diagram of an algorithm evaluation device based on fuzzy analytic hierarchy process according to an embodiment of the present disclosure. As shown in fig. 3, the algorithm evaluation device based on the fuzzy analytic hierarchy process includes:
the acquisition module 301 is configured to acquire characteristics for evaluating the algorithm to be selected, and establish a hierarchical structure model for evaluating the algorithm to be selected based on a preset decision target, the algorithm to be selected and the characteristics;
the construction module 302 is configured to construct a comparison matrix based on the hierarchical structure model and a predetermined triangular fuzzy scale, calculate a fuzzy number of the features in the comparison matrix to obtain a fuzzy number corresponding to each feature, and calculate a fuzzy geometric value corresponding to each feature by using the fuzzy number;
the processing module 303 is configured to determine a fuzzy weight corresponding to each feature based on the fuzzy geometric value, and perform defuzzification processing on the fuzzy weight to obtain a weight value corresponding to each feature;
the judging module 304 is configured to judge the weight sum of the features, and normalize the weight values of the features according to the judging result to obtain normalized weights respectively corresponding to the features;
A determining module 305, configured to respectively construct a decision matrix of the candidate algorithms relative to each feature, so as to determine, based on the decision matrix, a normalization weight corresponding to each candidate algorithm when each feature is used as a standard;
and the evaluation module 306 is configured to calculate a weight result of each algorithm to be selected based on the normalized weight corresponding to the feature and the normalized weight corresponding to the algorithm to be selected, and evaluate the algorithm to be selected based on the weight result.
In some embodiments, the acquisition module 301 of fig. 3 establishes a hierarchical structure model based on the highest layer, the lowest layer, and the middle layer, with the decision target as the highest layer, the algorithm to be selected as the lowest layer, the features as the middle layer, and the decision target as the highest layer, the algorithm to be selected as the lowest layer, and the features as the middle layer, respectively; and evaluating the algorithm to be selected as a decision target, wherein the algorithm to be selected comprises a plurality of algorithms to be evaluated, and the characteristics comprise a plurality of standard factors for evaluating the algorithm to be selected.
In some embodiments, the construction module 302 of FIG. 3 constructs a comparison matrix between features using a triangle blur scale based on all features in the hierarchical model, where the triangle blur scale is used to characterize the importance level between any two features.
In some embodiments, the construction module 302 of fig. 3 converts the number of languages between the feature pairs in the comparison matrix into a triangular fuzzy number by using a preset conversion formula, obtains a triangular fuzzy number corresponding to each feature pair, and converts the comparison matrix into a fuzzy pairing comparison decision matrix according to the triangular fuzzy number; and calculating the fuzzy geometric value corresponding to each feature by using a preset fuzzy geometric value calculation formula based on the triangular fuzzy number of each feature pair in the pairing comparison decision matrix.
In some embodiments, the determining module 304 of fig. 3 calculates a weight sum of the weights corresponding to all the features, and when the weight sum is less than or equal to 1, directly uses the weight corresponding to each feature as the normalized weight of the feature; when the weight sum is greater than 1, converting the weight value of the feature into normalized weight so that the normalized weight sum corresponding to all the features is 1; and ranking the features based on the normalized weights corresponding to each feature.
In some embodiments, the evaluation module 306 of fig. 3 multiplies the normalized weight of the feature by the normalized weight of the candidate algorithm calculated when the feature is taken as a standard, to obtain a weight result corresponding to each candidate algorithm, and ranks the candidate algorithms according to the weight results, so as to evaluate the candidate algorithms according to the ranks.
It should be understood that the sequence number of each step in the foregoing embodiment does not mean that the execution sequence of each process should be determined by the function and the internal logic of each process, and should not constitute any limitation on the implementation process of the embodiments of the disclosure.
Fig. 4 is a schematic diagram of an electronic device 4 provided by an embodiment of the present disclosure. As shown in fig. 4, the electronic apparatus 4 of this embodiment includes: a processor 401, a memory 402 and a computer program 403 stored in the memory 402 and executable on the processor 401. The steps of the various method embodiments described above are implemented by processor 401 when executing computer program 403. Alternatively, the processor 401, when executing the computer program 403, performs the functions of the modules/units in the above-described apparatus embodiments.
The electronic device 4 may be a desktop computer, a notebook computer, a palm computer, a cloud server, or the like. The electronic device 4 may include, but is not limited to, a processor 401 and a memory 402. It will be appreciated by those skilled in the art that fig. 4 is merely an example of the electronic device 4 and is not limiting of the electronic device 4 and may include more or fewer components than shown, or different components.
The processor 401 may be a central processing unit (Central Processing Unit, CPU) or other general purpose processor, digital signal processor (Digital Signal Processor, DSP), application specific integrated circuit (Application Specific Integrated Circuit, ASIC), field programmable gate array (Field-Programmable Gate Array, FPGA) or other programmable logic device, discrete gate or transistor logic device, discrete hardware components, or the like.
The memory 402 may be an internal storage unit of the electronic device 4, for example, a hard disk or a memory of the electronic device 4. The memory 402 may also be an external storage device of the electronic device 4, for example, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash Card (Flash Card) or the like, which are provided on the electronic device 4. Memory 402 may also include both internal storage units and external storage devices of electronic device 4. The memory 402 is used to store computer programs and other programs and data required by the electronic device.
It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-described division of the functional units and modules is illustrated, and in practical application, the above-described functional distribution may be performed by different functional units and modules according to needs, i.e. the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-described functions. The functional units and modules in the embodiment may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit, where the integrated units may be implemented in a form of hardware or a form of a software functional unit.
The integrated modules/units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the present disclosure may implement all or part of the flow of the method of the above-described embodiments, or may be implemented by a computer program to instruct related hardware, and the computer program may be stored in a computer readable storage medium, where the computer program, when executed by a processor, may implement the steps of the method embodiments described above. The computer program may comprise computer program code, which may be in source code form, object code form, executable file or in some intermediate form, etc. The computer readable medium may include: any entity or device capable of carrying computer program code, a recording medium, a U disk, a removable hard disk, a magnetic disk, an optical disk, a computer Memory, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), an electrical carrier signal, a telecommunications signal, a software distribution medium, and so forth. It should be noted that the content of the computer readable medium can be appropriately increased or decreased according to the requirements of the jurisdiction's jurisdiction and the patent practice, for example, in some jurisdictions, the computer readable medium does not include electrical carrier signals and telecommunication signals according to the jurisdiction and the patent practice.
The above embodiments are merely for illustrating the technical solution of the present disclosure, and are not limiting thereof; although the present disclosure has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the disclosure, and are intended to be included in the scope of the present disclosure.
Claims (9)
1. A method for determining a wire real-time segmentation and identification algorithm, comprising:
acquiring original data from related documents of an electric wire real-time segmentation and identification algorithm, converting the original data into digital features for retaining original data information, extracting features from the original data, selecting a plurality of common features from the extracted features, and taking the common features as features for evaluating an algorithm to be selected, wherein the algorithm to be selected comprises a plurality of algorithms for carrying out real-time segmentation and identification on the electric wire in an image of a mobile terminal, and the features for evaluating the algorithm to be selected comprise sensitivity, specificity, quality, time, consistency and stability;
Establishing a hierarchical structure model for evaluating the algorithm to be selected based on a preset decision target, the algorithm to be selected and the characteristics;
constructing a comparison matrix based on the hierarchical structure model and a preset triangular fuzzy scale, calculating fuzzy numbers of the features in the comparison matrix to obtain fuzzy numbers corresponding to each feature, and calculating fuzzy geometric values corresponding to each feature by using the fuzzy numbers;
determining a fuzzy weight corresponding to each feature based on the fuzzy geometric value, and performing defuzzification processing on the fuzzy weight to obtain a weight value corresponding to each feature;
judging the weight sum of the features, and carrying out normalization processing on the weight values of the features according to the judging result to obtain normalization weights respectively corresponding to the features;
respectively constructing a decision matrix of the algorithm to be selected relative to each feature so as to determine a normalization weight corresponding to each algorithm to be selected respectively when each feature is taken as a standard based on the decision matrix;
and calculating a weight result of each candidate algorithm based on the normalized weight corresponding to the feature and the normalized weight corresponding to the candidate algorithm, evaluating the candidate algorithm based on the weight result, and determining the candidate algorithm with the highest weight result as a wire real-time segmentation and identification algorithm.
2. The method of claim 1, wherein the establishing a hierarchical model for evaluating the candidate algorithm based on the preset decision goal, the candidate algorithm, and the feature comprises:
respectively taking the decision target as the highest layer, the algorithm to be selected as the lowest layer, the characteristics as the middle layer, and establishing the hierarchical structure model based on the highest layer, the lowest layer and the middle layer;
and evaluating the candidate algorithm as the decision target.
3. The method of claim 1, wherein the constructing a comparison matrix based on the hierarchical model and a predetermined triangular blur scale comprises:
and constructing a comparison matrix between the features by using the triangular blur scale based on all the features in the hierarchical structure model, wherein the triangular blur scale is used for representing the importance degree between any two features.
4. The method according to claim 1, wherein the calculating the blur number of the features in the comparison matrix to obtain a blur number corresponding to each of the features, and calculating the blur geometry value corresponding to each of the features using the blur number includes:
Converting the language number between the feature pairs in the comparison matrix into triangular fuzzy numbers by using a preset conversion formula to obtain triangular fuzzy numbers respectively corresponding to each feature pair, and converting the comparison matrix into a fuzzy pairing comparison decision matrix according to the triangular fuzzy numbers;
and calculating the fuzzy geometric value corresponding to each feature by using a preset fuzzy geometric value calculation formula based on the triangular fuzzy number of each feature pair in the pairing comparison decision matrix.
5. The method of claim 1, wherein the determining the weight sum of the features, normalizing the weight values of the features according to the determination result, to obtain normalized weights corresponding to the features, respectively, includes:
calculating the weight sum of all the weights corresponding to the features, and directly taking the weight corresponding to each feature as the normalized weight of the feature when the weight sum is smaller than or equal to 1; when the weight sum is greater than 1, converting the weight value of the feature into normalized weight so that the normalized weight sum corresponding to all the features is 1; and ranking the features based on the normalized weights corresponding to each feature.
6. The method according to claim 1, wherein calculating a weight result of each of the candidate algorithms based on the normalized weights corresponding to the features and the normalized weights corresponding to the candidate algorithms, and evaluating the candidate algorithms based on the weight results, comprises:
and multiplying the normalized weight of the feature by the normalized weight of the algorithm to be selected calculated when the feature is taken as a standard to obtain a weight result corresponding to each algorithm to be selected, and ranking the algorithm to be selected according to the weight result so as to evaluate the algorithm to be selected according to the ranking.
7. A wire real-time segmentation and identification algorithm determining device, comprising:
the acquisition module is configured to acquire characteristics for evaluating the algorithm to be selected from relevant documents of the algorithm to be segmented and identified in real time, wherein the algorithm to be selected comprises a plurality of algorithms for segmenting and identifying the electric wires in the mobile terminal image in real time, and the characteristics for evaluating the algorithm to be selected comprise sensitivity, specificity, quality, time, consistency and stability; establishing a hierarchical structure model for evaluating the algorithm to be selected based on a preset decision target, the algorithm to be selected and the characteristics;
The construction module is configured to construct a comparison matrix based on the hierarchical structure model and a preset triangular fuzzy scale, calculate fuzzy numbers of the features in the comparison matrix to obtain fuzzy numbers corresponding to each feature, and calculate fuzzy geometric values corresponding to each feature by using the fuzzy numbers;
the processing module is configured to determine a fuzzy weight corresponding to each feature based on the fuzzy geometric value, and perform defuzzification processing on the fuzzy weight to obtain a weight value corresponding to each feature;
the judging module is configured to judge the weight sum of the features, and normalize the weight values of the features according to the judging result to obtain normalized weights respectively corresponding to the features;
a determining module configured to respectively construct a decision matrix of the algorithm to be selected relative to each feature so as to determine a normalization weight respectively corresponding to each algorithm to be selected when each feature is taken as a standard based on the decision matrix;
the evaluation module is configured to calculate a weight result of each candidate algorithm based on the normalized weight corresponding to the feature and the normalized weight corresponding to the candidate algorithm, evaluate the candidate algorithm based on the weight result, and determine the candidate algorithm with the highest weight result as a wire real-time segmentation and identification algorithm.
8. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the method of any one of claims 1 to 6 when the program is executed.
9. A computer readable storage medium storing a computer program, characterized in that the computer program when executed by a processor implements the method according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210508826.3A CN114792371B (en) | 2022-05-10 | 2022-05-10 | Method, device, equipment and medium for determining wire real-time segmentation and identification algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210508826.3A CN114792371B (en) | 2022-05-10 | 2022-05-10 | Method, device, equipment and medium for determining wire real-time segmentation and identification algorithm |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114792371A CN114792371A (en) | 2022-07-26 |
| CN114792371B true CN114792371B (en) | 2023-07-25 |
Family
ID=82463671
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210508826.3A Active CN114792371B (en) | 2022-05-10 | 2022-05-10 | Method, device, equipment and medium for determining wire real-time segmentation and identification algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114792371B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2009026589A2 (en) * | 2007-08-23 | 2009-02-26 | Fred Cohen | Method and/or system for providing and/or analizing and/or presenting decision strategies |
| CN104636447A (en) * | 2015-01-21 | 2015-05-20 | 上海天呈医流科技股份有限公司 | Intelligent evaluation method and system for medical instrument B2B website users |
| CN107292534A (en) * | 2017-07-12 | 2017-10-24 | 国网福建省电力有限公司 | The yardstick competition evaluation method and device of urban power distribution network long term dynamics investment |
| CN109543737A (en) * | 2018-11-15 | 2019-03-29 | 国网四川省电力公司信息通信公司 | A kind of information system health degree appraisal procedure based on FAHP_FCA combination weighting |
| CN112164059A (en) * | 2020-10-20 | 2021-01-01 | 沈阳东软智能医疗科技研究院有限公司 | Focus detection method, device and related product |
| CN113592324A (en) * | 2021-08-05 | 2021-11-02 | 国网江苏省电力有限公司无锡供电分公司 | Cable terminal tower live-line work risk assessment method based on hierarchical analysis |
| CN113822538A (en) * | 2021-08-27 | 2021-12-21 | 长春工程学院 | AHP-CRITIC-based small and medium-sized earth and rockfill dam operation evaluation method |
| CN114266486A (en) * | 2021-12-24 | 2022-04-01 | 桂林电子科技大学 | AHP-FCE method-based risk evaluation method for whole-process cost consultation service |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160239766A1 (en) * | 2015-02-16 | 2016-08-18 | Nathan R. Cameron | Systems, methods, and user interfaces for evaluating quality, health, safety, and environment data |
-
2022
- 2022-05-10 CN CN202210508826.3A patent/CN114792371B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2009026589A2 (en) * | 2007-08-23 | 2009-02-26 | Fred Cohen | Method and/or system for providing and/or analizing and/or presenting decision strategies |
| CN104636447A (en) * | 2015-01-21 | 2015-05-20 | 上海天呈医流科技股份有限公司 | Intelligent evaluation method and system for medical instrument B2B website users |
| CN107292534A (en) * | 2017-07-12 | 2017-10-24 | 国网福建省电力有限公司 | The yardstick competition evaluation method and device of urban power distribution network long term dynamics investment |
| CN109543737A (en) * | 2018-11-15 | 2019-03-29 | 国网四川省电力公司信息通信公司 | A kind of information system health degree appraisal procedure based on FAHP_FCA combination weighting |
| CN112164059A (en) * | 2020-10-20 | 2021-01-01 | 沈阳东软智能医疗科技研究院有限公司 | Focus detection method, device and related product |
| CN113592324A (en) * | 2021-08-05 | 2021-11-02 | 国网江苏省电力有限公司无锡供电分公司 | Cable terminal tower live-line work risk assessment method based on hierarchical analysis |
| CN113822538A (en) * | 2021-08-27 | 2021-12-21 | 长春工程学院 | AHP-CRITIC-based small and medium-sized earth and rockfill dam operation evaluation method |
| CN114266486A (en) * | 2021-12-24 | 2022-04-01 | 桂林电子科技大学 | AHP-FCE method-based risk evaluation method for whole-process cost consultation service |
Non-Patent Citations (6)
| Title |
|---|
| A framework for evaluating image segmentation algorithms;Udupa J K等;《Computerized medical imaging and graphics》;第30卷(第2期);75-87 * |
| Decision support system for real-time segmentation and identification algorithm for wires in mobile terminals using fuzzy AHP method;Wang L等;《Soft Computing》;第26卷(第20期);10915-10926 * |
| Fuzzy Analytical Hierarchy Process (FAHP) using geometric mean method to select best processing framework adequate to big data;PFATB D;《Journal of Theoretical and Applied Information Technology》;第99卷(第1期);207-226 * |
| 图象分割质量评价方法研究;侯格贤;《中国图象图形学报》;第5卷(第1期);39-43 * |
| 基于FAHP的高层建筑火灾风险评价研究;米红甫等;《武汉理工大学学报（信息与管理工程版）》;第39卷(第2期);148-152 * |
| 基于层级识别模型的输电线路杆塔小金具缺陷识别方法;方志丹等;《电力信息与通信技术》;第18卷(第9期);16-24 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114792371A (en) | 2022-07-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110287932B (en) | Road blocking information extraction method based on deep learning image semantic segmentation | |
| EP3961484B1 (en) | Medical image segmentation method and device, electronic device and storage medium | |
| Laibacher et al. | M2u-net: Effective and efficient retinal vessel segmentation for real-world applications | |
| Laibacher et al. | M2U-Net: Effective and efficient retinal vessel segmentation for resource-constrained environments | |
| US8831311B2 (en) | Methods and systems for automated soft tissue segmentation, circumference estimation and plane guidance in fetal abdominal ultrasound images | |
| CN110321943B (en) | CT image classification method, system and device based on semi-supervised deep learning | |
| CN110544233A (en) | Depth image quality evaluation method based on face recognition application | |
| Hu et al. | PolyBuilding: Polygon transformer for building extraction | |
| Xiao et al. | Research on defect detection method of powder metallurgy gear based on machine vision | |
| CN115457001A (en) | Photovoltaic panel foreign matter detection method, system, device and medium based on VGG network | |
| CN117635543B (en) | Forward tracking and fault reverse positioning method and system for internal defects of metal | |
| CN114792371B (en) | Method, device, equipment and medium for determining wire real-time segmentation and identification algorithm | |
| CN117788810A (en) | Learning system for unsupervised semantic segmentation | |
| Li et al. | Brown rice germ integrity identification based on deep learning network | |
| Peng et al. | Improving the detection of the prostrate in ultrasound images using machine learning based image processing | |
| Kasturiwala et al. | Image superresolution technique: A novel approach for leaf diseased problems | |
| CN116310832A (en) | Remote sensing image processing method, device, equipment, medium and product | |
| CN116167936A (en) | Mountain shadow removing method and device for flood monitoring | |
| CN116310899A (en) | YOLOv 5-based improved target detection method and device and training method | |
| Berger et al. | Automated ice-bottom tracking of 2D and 3D ice radar imagery using Viterbi and TRW-S | |
| CN116359738A (en) | Method, device, equipment and storage medium for monitoring health state of battery | |
| CN114677530A (en) | Clustering algorithm effectiveness evaluation method, device and medium based on wavelet shape descriptor | |
| CN113436322A (en) | Three-dimensional reconstruction method, device, equipment and storage medium for fundus blood vessels | |
| Gonzalez-Huitron et al. | Jaccard distance as similarity measure for disparity map estimation | |
| Onpans et al. | Intravascular Ultrasound Image Composite Segmentation using Ensemble Gabor-spatial Features |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |