268 results about "Optimal test" patented technology

Methods and apparatus for testing of the efficacy of therapeutic stimulation of pelvic nerves or musculature to alleviate one of incontinence or sexual dysfunction are disclosed. A therapy delivery device is operable in a therapy delivery mode and a test mode and an evoked response detector is employed in the test mode to detect the evoked response to applied test stimuli. The test stimuli parameters of the test stimulation regimen are adjusted prior to delivery of each test stimulation regimen, and the evoked responses to the applied test stimulation regimens are compared to ascertain an optimal test stimulation regimen. The therapy stimulation regimen parameters are selected as a function of the test electrical stimulation parameters causing the optimal evoked response.

The invention provides an SAR image terrain classification method based on a depth RBF network. The method mainly solves the problem of the prior art that the accuracy of classification is low. The method comprises the steps of (1) extracting the texton features of an SAR image; (2) training the texton features of the SAR image through a first-layer RBF neural network of the depth RBF network to obtain the advanced features of the image; (3) training the advanced features through a second-layer sparse autocoder network SAE of the depth RBF network to obtain more advanced features of the image; (4) training the more advanced features through a third-layer RBF neural network of the depth RBF network to obtain the terrain classification features of the image; (5) comparing the terrain classification features of an image test sample with a test sample label, adjusting the parameters of each layer of the depth RBF network, and obtaining an optimal test classification accuracy. The method is high in classification accuracy and can be used for complicated image classification.

The invention discloses an analog circuit dynamic online failure diagnosing method based on GSD-SVDD, belonging to the technical field of analog circuit failure diagnosis. In an offline test process, a KFCM algorithm is adopted to calculate a failure resolution value of each testable node and an optimal test node set is selected according to the failure resolution value. In an online diagnosis process, a failure diagnosis model is established by adopting an SVDD single classification approach based on a map spatial distance positive and negative sample weighting, test samples are diagnosed by a layered diagnosis method, and a failure class library and the diagnosis model are renewed dynamically. The method effectively reduces the drill and online diagnosis time of the diagnosis model, guarantees the real-time property of the online diagnosis and improves the precision of the failure diagnosis and can dynamically renew parameters of the diagnosis model so as to enable the a diagnosis system to have the self-adaption capability.

A system and method are provided for the training and testing of prediction algorithms. According to an exemplary embodiment of the invention the method generates optimum training, testing and / or validation data sets from a common general database by applying a genetic algorithm to populations of testing and training subsets used in connection with a given prediction algorithm. In exemplary embodiments the prediction algorithm operated upon is an artificial neural network. As well, in preferred exemplary embodiments, the most predictive independent variables of the records of the common database are automatically selected in a pre-processing phase. Such preprocessing phase applies a genetic algorithm to populations of prediction algorithms which vary as to number and content of input variables, where the prediction algorithms representing the selections of input variables which have the best testing performances and the minimum input variables are promoted for the processing of the new generations according to a defined selection algorithm.

A system and method are provided for the training and testing of prediction algorithms. According to an exemplary embodiment of the invention the method generates optimum training, testing and / or validation data sets from a common general database by applying a genetic algorithm to populations of testing and training subsets used in connection with a given prediction algorithm. In exemplary embodiments the prediction algorithm operated upon is an artificial neural network. As well, in preferred exemplary embodiments, the most predictive independent variables of the records of the common database are automatically selected in a pre-processing phase. Such preprocessing phase applies a genetic algorithm to populations of prediction algorithms which vary as to number and content of input variables, where the prediction algorithms representing the selections of input variables which have the best testing performances and the minimum input variables are promoted for the processing of the new generations according to a defined selection algorithm.

The invention discloses an optimization design method for a step stress accelerated degradation test based on a Bayesian theory, and is applied to the technical field of the accelerated degradation test. The optimization design method comprises the steps as follows: firstly, determining product performance degradation and acceleration models, and based on the historical data, giving prior distribution of model parameters; secondly, determining an optimization design space, and forming a test scheme set; thirdly, creating an expected utility function or an expected loss function, determining optimization goals, and based on a Markov Chain Monte Carlo method, determining optimization goal values of designs in the test scheme set; and lastly, finding the optimal test scheme by using a curve fitting method. According to the optimization design method, the shortcoming of high possibility of larger deviation due to the implementation of the traditional (local) test optimization design method when the values of the model parameters are supposed to be known is avoided, and the optimization scheme obtained in the implementation of the test optimization design when the prior distribution of the model parameters is given is more reasonable and more actual.

The invention discloses a matrix-model-based software testing method. The matrix-model-based software testing method comprises the following steps: a) dividing a software system according to function modules; b) splitting and combining the function modules to form layer-level function test points; c) establishing a test case set by structuring a covering matrix for all layer-level function test points, so that each valid value of any pair of input parameters in each level of function test point is coated with at least one test case, wherein in the step c), for the function test point with less than or equal to three input parameters and valid values, the two-coverage test case set is directly established by Latin square. In the matrix-model-based software testing method, by extracting the function test points and matrixing the function test points, the optimal test case set is obtained through matrix calculation, so that the coverage rate, the testing efficiency and the testing accuracy can be improved all around, a testing need of a large software system can be met and the testing cost can be reduced.

A method for optimizing a test sequence to diagnose a failure mode of a device, such as a vehicle, is provided. At least one symptom of a fault of the device is received, and a plurality of taxonomies is generated. The taxonomies include a device component taxonomy, a fault taxonomy, and a diagnostic taxonomy, and each taxonomy has a plurality of nodes. At least one diagnostic test sequence, based on the symptom and the taxonomies, is generated, costs associated with the diagnostic test sequence are determined, and a cost optimal test sequence, based on the costs and the diagnostic test sequence, is generated.

This invention permits selectively bypasses serial scan chains. Constant or low toggle data is directed to the bypassed serial scan chain, thus reducing power consumption. The number and identity of serial scan chains bypassed during a particular test can be changed dynamically dependent upon the semiconductor process variations of a particular integrated circuit. This enables an optimal test to be preformed for integrated circuits having differing semiconductor process variations.

A novel approach to test-suite reduction based on network maximum flows. Given a test suite T and a set of test requirements R, the method identifies a minimal set of test cases which maintains the coverage of test requirements. The approach encodes the problem with a bipartite directed graph and computes a minimum cardinality subset of T that covers R as a search among maximum flows, using the classical Ford-Fulkerson algorithm in combination with efficient constraint programming techniques. Test results have shown that the method outperforms the Integer Linear Programming (ILP) approach by 15-3000 times, in terms of the time needed to find the solution. At the same time, the method obtains the same reduction rate as ILP, because both approaches compute optimal solutions. When compared to the simple greedy approach, the method takes on average 30% more time and produces from 5% to 15% smaller test suites.

A method to optimize software testing is disclosed. The method includes generating a set of software testcases for testing a software product, creating a testcase coverage matrix comprising testcase identifiers corresponding to the set of testcases and source code line identifiers corresponding to the lines of source code tested thereby, selecting all testcases that uniquely test a line of source code, marking all source code line identifiers covered by the selected testcases, prioritize the testcases of testcase identifiers associated with unmarked source code identifiers, and selecting one or more testcases of testcase identifiers that corresponds to each unmarked source code identifier to determine an optimal set of testcases for software testing.

A method for optimizing a test sequence to diagnose a failure mode of a device, such as a vehicle, is provided. At least one symptom of a fault of the device is received, and a plurality of taxonomies is generated. The taxonomies include a device component taxonomy, a fault taxonomy, and a diagnostic taxonomy, and each taxonomy has a plurality of nodes. At least one diagnostic test sequence, based on the symptom and the taxonomies, is generated, costs associated with the diagnostic test sequence are determined, and a cost optimal test sequence, based on the costs and the diagnostic test sequence, is generated.

A computer system that adjusts an internal temperature of a hard disk drive (HDD) during HDD testing. An HDD test program under the control of the computer system is performed within a pre-determined optimal test temperature range. The HDD is kept within this pre-determined test temperature range by the computer system switching HDD operation modes back and forth between a higher heat generating Rapid Seek Mode and a lower heat generating IDLE mode. The HDD is thus kept within the optimal test temperature range without the use of external heating and / or cooling devices.

A method and system for selecting an optimal set of S number of calibration patches for an image producing system. The method of selecting the S number of calibration patches includes acquiring a set of K number of basis eigen vectors and model parameters which represent the image producing system having G number of colors and computing the optimal set of S number of colors selected from the set of G number of colors. Each one of the computed set of S number of colors is used for one of the S number of calibration patches.

The invention discloses an analog circuit test node selecting method based on dynamic feedback neural network modeling. The method comprises the steps of selecting the frequency of a test signal, inputting the test signal into a circuit to be tested, simulating various typical fault conditions, collecting the voltage values of a normal sample and a fault sample of the circuit on a test node to be selected of the circuit to be tested so as to construct a fault dictionary table; according to a fault fuzzy voltage interval, analyzing a fuzzy fault set and obtaining a fault integer encoding table; constructing an initial training sample set, training an initial dynamic feedback neural network, and utilizing the dynamic feedback neural network for fitting the nonlinear mapping relation between the test node and the fault; and according to the target function calculated by the genetic algorithm output by the network, obtaining the optimal test node set by utilizing the genetic optimization algorithm. In the method, a fault dictionary is analyzed by the intelligent algorithm, so that the global optimum test node set can be found, and the subsequent diagnostic accuracy can be further improved.

The present invention describes a method and system for optimizing a test flow within each ATE (Automated Test Equipment) station. The test flow includes a plurality of test blocks. A test block includes a plurality of individual tests. A computing system schedule the test flow based one or more of: a test failure model, test block duration and a yield model. The failure model determines an order or sequence of the test blocks. There are at least two failure models: independent failure model and dependant failure model. The yield model describes whether a semiconductor chip is defective or not. Upon completing the scheduling, the ATE station conducts tests according to the scheduled test flow. The present invention can also be applied to software testing.

The invention discloses an optimal position calibration method of a static drifting zero and primary acceleration related term error model of a flexible gyroscope, which acquires an optimal test position by adopting a D-optimal test design method. In the invention, the output of the flexible gyroscope is effectively improved by carrying out measured value compensation on acquired optimal space quadrature-12 position drifting coefficients and an acquired flexible gyro static error compensation model G0 under the optimal space quadrature-12 position; the drifting coefficients are acquired by respectively adopting a traditional 8-position method, a full-space quadrature-24 position method and an optimal space quadrature-12 position method in the flexible gyro test process in an inertial navigation center; and the residual square sum of gyro testing values can shows that a solved result of the drifting coefficients after being compensated by utilizing the optimal space quadrature-12 position test design method of the flexible gyroscope is improved by 4 to 5 times compared with the traditional 8-position method, the precision is improved and the test time is shortened by half compared with the full-space quadrate-24 position test method.

The invention discloses a deep neural network-based SAR (Synthetic Aperture Radar) texture image classification method, and aims to mainly solve the problem of low accuracy of SAR texture image classification with a larger number of samples and more characteristic dimensions in the prior art. The method is implemented by the following steps: (1) extracting low-level characteristics of an SAR image; (2) training the low-level characteristics of the SAR image to obtain advanced characteristics of the image by virtue of a first layer of RBF (Radial Basis Function) neural network of a deep neural network; (3) training the advanced characteristics to obtain more advanced characteristics of the image by virtue of a second layer of RBM (Restricted Boltzmann Machine) neural network of the deep neural network; (4) training the more advanced characteristics to obtain image texture classification characteristics by virtue of a third layer of RBF neural network of the deep neural network; (5) comparing texture classification characteristics of an image test sample with a test sample tag, and regulating parameters of each layer of the deep neural network to obtain the optimal test classification accuracy. The method is high in classification accuracy, and can be used for target identification or target tracking.

A method to optimize software testing is disclosed. The method includes generating a set of software testcases for testing a software product, creating a testcase coverage matrix comprising testcase identifiers corresponding to the set of testcases and source code line identifiers corresponding to the lines of source code tested thereby, selecting all testcases that uniquely test a line of source code, marking all source code line identifiers covered by the selected testcases, prioritize the testcases of testcase identifiers associated with unmarked source code identifiers, and selecting one or more testcases of testcase identifiers that corresponds to each unmarked source code identifier to determine an optimal set of testcases for software testing.

The invention discloses a method and a device for testing the beat length of a polarization maintaining optical fiber, which establish a numerical model for the test of the beat length of the polarization maintaining optical fiber according to the spectrum modulation property of a transmission spectrum of a Sagnac interferometer consisting of an optical fiber coupler and a to-be-tested polarization maintaining optical fiber and the extreme point property of the transmission spectrum to test the wavelength difference between the adjacent extreme points of the transmission spectrum obtained by using a spectrum test device to realize the test of the beat length. The method and the device optimize the length parameters of the to-be-tested polarization maintaining optical fiber, establish a mathematical model for acquiring the optimal test length of the optical fiber and precisely test the beat length of the optical fiber at the optimal test length. The method for testing the beat length of the polarization maintaining optical fiber of the invention is simple in theory and achieves a precision of 0.01 millimeter of the beat length test performed at the optimal test length. The test device adopts a full optical fiber structure, and is low in cost, high in adaptability, strong in interference resisting capability and free from limitation on the beat length of the to-be-test optical fiber. The test method and the test device are suitable for the tests of beat lengths in various ranges of the polarization maintaining optical fibers. The device is simple in structure and convenient in operation.

In a defect inspecting apparatus, having contrast, brightness and appearance of a target for inspection and detection sensitivity of a defect changed depending on optical system conditions, and adapted to perform inspection by selecting an optimal test condition, even an unskilled user can easily select an optimal optical condition by quantitatively displaying evaluation values side by side when optical system conditions are changed. Moreover, by selecting an evaluation item having highest satisfaction based on a result of a series of test inspection, an optimal test condition can be automatically selected.

The invention discloses a domain concept extraction method based on Deep Learning. The method includes extracting samples in a training corpus, adopting word frequency, document frequency, inverse document frequency, word length, word frequency variance and domain consensus as feature vectors, training and acquiring a deep network model, which is capable of representing the complex mapping correspondence between the word-type filed concept multi-dimensional feature vectors and class labels, on the basis of the Deep Learning technology, and finally comparing the deep network model established on the basis of the Deep Learning technology, an optimized BP neural network model and mainstream KNN and SVM models in the testing step. According to the tests, the optimal test effect is acquired through the deep network model established on the basis of the Deep Learning technology.

The present invention is directed to a system and method for test target selection in conjunction with dynamic test pattern generation. In the invention, a test pattern page(s) is composed using an optimal set of test targets, which can be accommodated or adjusted to fit within size constraints of the test pattern. The method of the present invention makes use of layout optimization to ensure that related and optimized test targets are accommodated on a single test pattern. For example, it may be preferable to “squeeze in” a smaller-than-normal uniform area target, rather than not to print it at all during a test.

The invention discloses a GPS (Global Position System) position method and device. The speed and the accuracy rate of GPS position are increased by optimizing the communication speed between a mobile phone and a relevant GPS server. Particularly, network packet loss of multiple servers is tested; the server with an optimal test result is selected as the server for the current position operation, so that the situation of a poor position effect caused by the inappropriate server is avoided; and the method and the device are automatic without manual setting of a user.

In a defect inspecting apparatus, having contrast, brightness and appearance of a target for inspection and detection sensitivity of a defect changed depending on optical system conditions, and adapted to perform inspection by selecting an optimal test condition, even an unskilled user can easily select an optimal optical condition by quantitatively displaying evaluation values side by side when optical system conditions are changed. Moreover, by selecting an evaluation item having highest satisfaction based on a result of a series of test inspection, an optimal test condition can be automatically selected.

The invention discloses a test task scheduling method based on critical paths and tabu search, belonging to the field of automatic testing system parallel test task scheduling. The method comprises the following steps of: firstly determining and analyzing a test task, initializing parameter setting, subsequently determining an initial test task sequence by adopting a priority coding mode, finding an optimal test scheme selection set under the test task sequence by using a method of tabu combination critical path so as to find an optimal test task sequence and a corresponding test scheme selection set through iteration of multiple times. According to the method, an initial task sequence which meets the constraint is provided while the tabu search is applied to solve a test task scheduling problem, an adjacent domain search range of the tabu is simplified, the redundant adjacent domain search operation is reduced, and the operation efficiency and optimizing efficiency of the test task scheduling method are improved ultimately.

A hard disk drive (HDD) capable of controlling its own internal temperature during testing. A test program embedded in the HDD is run only within a pre-determined optimal test temperature range. The internal temperature of the HDD is kept within this pre-determined test temperature range by switching HDD operation modes back and forth between a higher heat generating Rapid Seek Mode and a lower heat generating IDLE mode. The HDD is thus kept within the optimal test temperature range without the use of external heating and / or cooling devices.

The invention belongs to the field of pattern recognition, particularly relates to an object detection method and system based on dynamic sample selection and loss consistency, and aims to solve the problems of insufficient object recognition accuracy and performance. The method comprises the following steps: firstly, acquiring a test image, dynamically selecting a positive sample and a negative sample in a training process, introducing a non-maximum suppression loss, and acquiring a prediction frame position of the test image and a probability that a prediction frame belongs to each categoryby an object detection model; and acquiring the target category and the prediction box position of the optimal test image through non-maximum suppression. Each annotation box generates the same numberof positive samples, the optimizer can fairly treat each training sample, and the regression loss function is re-weighted by predicting a IOU of each prediction box through dynamic sample selection,so that the optimal detection result is more accurate, and the detection accuracy is improved. In the training stage, a non-maximum suppression loss function is introduced to punish false detection generated in training, so that the false detection is reduced in the test stage.

A computer system that adjusts an internal temperature of a hard disk drive (HDD) during HDD testing. An HDD test program under the control of the computer system is performed within a pre-determined optimal test temperature range. The HDD is kept within this pre-determined test temperature range by the computer system switching HDD operation modes back and forth between a higher heat generating Rapid Seek Mode and a lower heat generating IDLE mode. The HDD is thus kept within the optimal test temperature range without the use of external heating and / or cooling devices.