Patents
Literature
Hiro is an intelligent assistant for R&D personnel, combined with Patent DNA, to facilitate innovative research.
Hiro

41 results about "Test adequacy" patented technology

Abstract. The specification of test adequacy is important as it sets limits on the amount of testing that is judged to be sufficient. It also sets a level of confidence that can be associated with the testing. Different approaches to measures of test adequacy are discussed, and guidelines on the use of test adequacy criteria are presented.

Convolutional neural network-oriented mutation coverage test method and computer storage medium

The invention discloses a convolutional neural network-oriented mutation coverage test method and a computer storage medium, and the method comprises the following steps: 1) setting n mutation operators, and respectively injecting the n mutation operators into a to-be-tested convolutional neural network program P to obtain a mutation program set {P1, P2, P3,and the like, Pn}; 2) training the variation program set {P1, P2, P3, and the like, Pn} by using a training data set D to obtain a variation model set {M1, M2, M3, and the like, Mn}; 3) testing the original model M and the variation model set {M1, M2, M3, and the like, Mn} by using a test data set T; and 4) comparing the test accuracy of all the models, and selecting the model with the highest accuracy. According to the invention, the defect that the traditional test method is difficult to ensure the test sufficiency of the convolutional neural network application program is solved. The test sufficiency of the convolutional neural network can be effectively improved, the method is more effective in neural network model testing, the local optimal model can be found out according to the test accuracy, and the quality and safety ofthe convolutional neural network application program are effectively guaranteed.
Owner:ARMY ENG UNIV OF PLA

Modelling method of strip-shaped single-particle imaging noise

ActiveCN108805887AImprove test adequacyHigh similarityImage analysisParticle imagingModel method
The invention provides a modelling method of strip-shaped single-particle imaging noise. The content is as follows: the single-particle slantly shines to an imaging chip, so that the implicated pixelalong the single-particle linear trajectory is in high-gray value or saturation; the gray assignment of the trajectory implicated pixel is based on the area of the smaller part after cutting the pixelalong the trajectory; when the linear trajectory passes through a pixel center, the gray assignment is the highest; the linear trajectory passes through the pixel angular point, and the gray assignments of the pixels at two sides are the lowest; or the square value of the length, cut by the pixel, of the trajectory line is used as the basis of the gray assignment, or the length value, cut by thepixel, of the trajectory line is used as the basis of the gray assignment. The single-particle noise imaging generated through the method disclosed by the invention and the simulated image are superposed as the input, the simulation experiment is performed for a camera or a star sensor, the similarity of the single-particle interference imaging working condition simulation can be improved, the working condition coverage range of the model testing is enlarged, and the testing sufficiency of the camera or the star sensor embedded system is improved.
Owner:BEIHANG UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products