403 results about "Test tests" patented technology

The invention discloses a fruit and vegetable detection method based on deep learning. The method comprises the following steps that: S1: firstly, preprocessing data, and carrying out manual calibration on an original picture in advance to obtain a segmentation tag, wherein the calibration means the coordinates of the left upper angular point and the right lower angular point of a target frame in the original picture, and the tag is used for judging whether a target in each calibration frame is a fruit and vegetable and determining the category of the fruit and vegetable; S2: secondly, training the data, taking the original picture and the picture tag as a training set of a deep learning neural network, and combining with a RPN (Region Proposal Network) and a Fast R-CNN to train the data to obtain a final fruit and vegetable detection model; and S3: finally, testing test data, calling a final fruit and vegetable detection model and a test program, carrying out fruit and vegetable detection on a test picture, and analyzing a final fruit and vegetable detection model effect through the observation of a test result.

A system for coordinating the timing of a data strobe with data supplied by a memory module to the memory controller read data FIFO of a processor-based system, providing multiple calibration modes. A calibration PDL (programmable delay line) is used to reiteratively test the time taken for a test data strobe to traverse a portion of the memory controller circuit, and to generate a calibration value based upon the time taken. The calibration procedure may be initiated in any one of several modes, including: according to a predetermined schedule; implemented in software; in response to changes in environmental factors such as temperature or voltages sampled at one or more locations; in response to a software-driven trigger; or in response to a user-initiated trigger, communicated to a system of the invention either by input via a user interface to the processor-based system or by a software command.

Provide are systems methods and devices for diagnosing disease in medical images. In certain aspects, disclosed is a method for training a neural network to detect features in a retinal image including the steps of: a) extracting one or more features images from a Train_0 set, a Test_0 set, a Train_1 set and a Test_1 set; b) combining and randomizing the feature images from Train_0 and Train_1 into a Training data set; c) combining and randomizing the feature images from Test_0 and Test_1 into a testing dataset; d) training a plurality of neural networks having different architectures using a subset of the training dataset while testing on a subset of the testing dataset; e) identifying the best neural network based on each of the plurality of neural networks performance on the testing data set; f) inputting images from Test_0, Train_1, Train_0 and Test_1 to the best neural network and identifying a limited number of false positives and false negative and adding the false positives and false negatives to the training dataset and testing dataset; and g) repeating steps d)-g) until an objective performance threshold is reached.

An apparatus for testing semiconductor devices allows various testing processes, including a burn-in process, to be performed at the same testing stage. Test trays which contain the semiconductor devices are used throughout an in-line system so that an entire back-end process can be performed without loading / unloading the semiconductor devices between the various tests. The in-line system includes multiple test and burn-in apparatuses as well as a single sorting unit which performs a composite sorting operation after all the testing processes. A method for testing semiconductor devices in the in-line system includes testing the semiconductor devices in the test trays using the test and burn-in apparatus, transferring the test trays to a different testing apparatus for a second testing, and finally sorting the semiconductor devices after all testing processes have been performed based on a final sorting map created by combining test tray maps generated during each of the tests.

A test and burn-in apparatus for semiconductor chip package devices, an in-line system which includes the test and burn-in apparatus, and a test method which employs the in-line system are provided. A test and burn-in apparatus for testing semiconductor devices allows various testing processes, including a burn-in process, to be performed at the same testing stage. The apparatus employs test trays which contain the semiconductor devices. These test trays are used throughout the in-line system so that an entire back-end process can be performed without the need for loading / unloading the semiconductor devices into and from device trays between the various tests. The test and burn-in apparatus according to this invention can therefore occupy less space than the prior art testing apparatuses. The in-line system includes multiple test and burn-in apparatuses as well as a single sorting unit which performs a composite sorting operation after all the testing processes have been performed. Furthermore, the method for testing the semiconductor devices in the in-line system includes testing the semiconductor devices in the test trays using the test and burn-in apparatus, generating a test tray map corresponding to results of the test, transferring the test trays to a different testing apparatus for a second testing and test tray map generation process, and finally sorting the semiconductor devices in the sorting unit after all testing processes have been performed based on a final sorting map created by combining the test tray maps of each of the tests. The benefits of this invention are reduced time and space requirements because neither transferring the devices to device trays between tests nor performing multiple sorting steps are required.

A method for detecting one or more target bacteria in a raw sample where: 1) bacteriophage(s) specific to each target bacterium are added to the raw sample, 2) the test sample is incubated, and 3) the test sample is tested for the presence of each phage in sufficient numbers to indicate the presence of the associated target bacteria in the raw sample. In one embodiment, each phage is initially added to the raw sample in concentrations below the detection limit of the final phage detection process. In another embodiment, the parent phages are tagged in such a way that they can be separated from the progeny phage prior to the detection process. Preferred phage detection processes are immunoassay methods utilizing antibodies that bind specifically to each phage. Antibodies can be used that bind to the protein capsid of the phage. Alternatively, the phage can by dissociated after the incubation process and the sample tested for the presence of individual capsid proteins or phage nucleic acids. The invention can be used to test target bacteria for antibiotic resistance.

The invention belongs to the technical field of information, and provides an application software cloud testing system. The application software cloud testing system comprises a task submission subsystem, a task scheduling subsystem and a task execution subsystem. The task submission subsystem is used for testing test tasks submitted by testing personnel, the test tasks indicate the types of the test tasks, and the types of the testing tasks comprise compatibility testing, performance testing, and function testing or quality testing of application software. The task scheduling subsystem is used for conducting task scheduling according to the test tasks submitted by the task submission subsystem. The task execution subsystem is used for executing the test tasks according to the task scheduling condition of the task scheduling subsystem and collecting and generating corresponding testing reports according to the types of the testing tasks. According to the application software cloud testing system, based on the characteristics of the application software of a mobile terminal, testing content of four different types can be supported simultaneously, and therefore the comprehensiveness of the cloud testing result of the application software is guaranteed.

In a test case selection apparatus according to the present invention, a parameter setting unit 22 displays a test case selection dialogue 400, etc., on a display screen of a display section 40, and test cases that are tentatively determined to be tested in the current round of testing is selected based on various parameters received from the operator. A simulation executing unit 23 calculates a time period predicted to be required for testing test cases, and displays the prediction result in the form of a graph indicating a temporal change in the number of tests. With this configuration, the user can predict an achieved status of testing based on the prediction result, and repeat suitable changes to the various parameters, thereby suitably selecting test cases to obtain a preferably achieved status of testing.

Capability test programs are generated implementing the capability test test cases for the components, wherein component developers use the capability test programs to test components during the development and coding of the components. Documentation is generated describing component abstract test cases incorporating information on capability test test cases. Component test programs are generated implementing the component abstract test cases for the components and utilizing capability test programs, wherein each component test program tests one component for at least one test case specified in the component abstract test case documentation for the component. The capability test programs and component test programs are stored in a shared repository. A software development program is deployed to enable the developers and testers to execute groups of component test programs in the shared repository to test the components during different phases of the development of the software product.

Enterprise test configuration and data management systems and associated methods are disclosed for test, measurement and automation environments that allow management, configuration and analysis of test systems and associated data across enterprise-wide test operations. These systems and methods are directed to the production process from the test and test station point of view and provides a variety of mechanisms for test configuration and data management for test stations (or automated test equipment (ATEs)) including the capability of managing data about each test station, hardware resources, software resources, test configuration, test steps, acquired measurements, test execution, and / or other information related to the tests, the test stations or the units-under-test (UUT). Standardized interfaces are also contemplated for the test station (or ATE) software to communicate with server systems and other ATEs if needed, thereby greatly simplifying the coding required for these systems and allowing each test station (or ATE) to talk through the same standardized interface.

A computer system for generating a diagnostic tool by applying artificial intelligence to an instrument for diagnosis of a disorder, such as autism. For autism, the instrument can be a caregiver-directed set of questions designed for an autism classification tool or an observation of the subject in a video, video conference, or in person and associated set of questions about behavior that are designed for use in a separate autism classification tool. The computer system can have one or more processors and memory to store one or more computer programs having instructions for generating a highly statistically accurate set of diagnostic items selected from the instrument, which are tested against a first test using a technique using artificial intelligence and a second test against an independent source. Also, a computer implemented method and a non-transitory computer-readable storage medium are disclosed.

An automatic test system and method for a distributed comprehensive service are disclosed. The system has a client (101), a scheduling server (102) and testing subsystems (103) which are in a distributed deployment and used to test tested systems (104) that are also in a distributed deployment. The scheduling server (102) receives and analyzes test tasks sent from the client (101), schedules test items according to the logical relationship and distributes them to the corresponding testing subsystems (103). The test subsystems (103) analyze and execute the test items to test the tested systems (104), collect test item execution reports and send the execution reports to the scheduling server (102). The scheduling server (102) generates a test task report and sends to the client (101) for examination. The system supports complicated multi-service test scenarios and multi-test task execution.

A device, method and / or computer-readable medium for testing an application within a test framework includes a framework controller associated with the test framework installed on a master device and a test driver associated with the test framework installed on one or more client devices. The master device is connected to the one or more client devices and a virtual machine (VM) module is installed on each of the one or more client devices. VMs can be created on the client devices and the application is installed on at least one of the VMs. The application is executed on the VMs according to a test scenario file. The framework controller collects data to generate an output result.

The invention discloses a method and a device for preparing a silty soil triaxial-test test sample. The method comprises the following steps: adding distilled water into silty soil and stirring to enable soil samples to be in a flow plastic state, namely slurry; precipitating the slurry in a split round die under the action of self weight; applying dead loads to the upper part of the test sample, removing the dead loads at the upper part of the test sample and enabling the test sample to be further solidified by adopting a vacuum negative pressure of minus 40 kPa, wherein in the process of applying the dead loads, to guarantee that the slurry does not overflow, the loads are slowly and gradually loaded and a next-stage load is applied after the soil samples complete solidification and drainage under a current load; and finally, removing the negative pressure and the split round die and completing preparation of the test sample, so that triaxial test equipment can be assembled to carry out static triaxial or dynamic triaxial test. The method and the device are simple to operate; the technical method is easy to master; equipment required for preparing the test sample is very simple; required test sample preparation cost is low; uniformity inside the soil samples is very good; reproduction degree between the soil samples is high; a microstructure of a soil layer in the nature can be reproduced to a higher degree; the soil samples do not need to be cut; disturbance is reduced; and the test result has high credibility.

The invention discloses a testing method, device and system. The method comprises the steps of receiving test task information for testing an application program to be tested, wherein the test task information at least comprises an installation package of the application program to be tested; sending the test task information to a server; receiving a test result returned back by the server, wherein the test result is obtained by collection from a test device for executing the test task of the application program to be tested through the server; displaying the test result. By means of the technology, a developer can automatically complete testing of the application program through the server side just by providing the test task information to the server, and manpower and materials are saved.

A memory and method for access the memory are provided. A first test is used to test memory elements to determine a lowest power supply voltage at which all the memory elements will operate to determine a weak memory element. Redundancy is used to substitute a redundant memory element for the weak memory element. The weak memory element is designated as a test element. In response to receiving a request to change a power supply voltage provided to the memory elements, a second test is used to test the test element to determine if the test element will function correctly at a new power supply voltage. If the test element passes the second test, the memory elements are accessed at the new power supply voltage. If the test element fails the second test, the memory elements are accessed using an access assist operation.

The invention relates to an in-situ tester for the micromechanical property of a material under combined tension and torsion, and belongs to the field of precise instruments. The tester comprises a base, a tension and torsion loading unit, a test-piece clamping unit, and a displacement and loading force precision testing unit, wherein the torsion loading unit drives two-level worm wheel and worm driving mechanisms to apply a torsion load to one end of a moving clamp through a precision motor, so that the torsion load is applied to a tested test-piece sample; a fixed clamp end is arranged on a precision guide rail sliding block; one end of the moving clamp is provided with a precision tension and torsion sensor for used for detecting the tension and torsion born by a testing workpiece, and a motor encoder can detect the tension strain and torsion angle. The in-situ tester provided by the invention has the characteristics that the structure is compact and exquisite, the volume is small, the weight is light, in-situ testing in micro-nano precision for the micromechanical property of the material under combined tension and torsion can be realized, and a novel testing method is provided for analytical investigation of a material deformation damage mechanism under the serving approaching condition.

The invention discloses a test-piece support for a corrosion test. The test-piece support is composed of a circular ring, support rods, piece hanging rods and nuts. The test-piece support is characterized in that uniformly distributed positioning holes are arranged in the bottom of the circular ring; the support rods are inserted into the positioning holes to be connected with the circular ring for fixing by the nuts; uniformly distributed thread grooves are arranged in the side of the circular ring; one ends of the piece hanging rods are embedded in the thread grooves and the other ends of the piece hanging rods are used for hanging an corrosion test test-piece; and the other ends of the piece hanging rods are fixed by positioning pieces after hanging the test-piece. The test-piece support for the corrosion test is convenient to adjust and use, simple in structure, efficient in corrosion evaluation performance and favourable in insulativity and corrosion resistance.

The invention discloses software testing system and method. The system comprises one or more array servers, one or more testing servers, a central server and a communication module; the array servers are used for storing virtual image files corresponding to different testing environments, wherein the testing environments comprise operating systems and corresponding application programs; the central server is used for receiving and storing to-be-tested software and to-be-tested testing environment information and for loading and operating the corresponding virtual image files stored in the array servers in the testing servers according to the testing environment information; and the communication module is used for being loaded and operated in a corresponding testing server along with the virtual image files and communicates with the central server to download the to-be-tested software from the central server and operate the to-be-tested software in the testing server. According to the invention, no tester participates in the whole testing process, so that a great amount of manual operation can be avoided; and meanwhile, testing machines are not required to be in one-to-one correspondence with the testing environments, so that the implementation can be more flexile.

The invention relates to a testing device and a testing method for the thermal conductivity coefficient of a material. The testing device comprises a hot plate heating system, a cold plate cooling system, an electric lifting system, a heat flow metering system, an electrical control and measurement system and an industrial personal computer software control system. The hot plate heating system is horizontally arranged, a core plate, a preventive plate and a back plate of the hot plate heating system respectively comprise a heating resistance sheet and a metal panel, the external dimension of the preventive plate is 550mm*550mm, the electric lifting system comprises a fulcrum bar, a lifting bracket, a lead screw and a driving motor, the lifting fulcrum bar drives a hot plate to lift, and the lifting fulcrum bar and the hot plate can be detached. The testing device for the thermal conductivity coefficient of the material is suitable for testing test pieces with thicknesses less than 100mm, and a building slab type heat-insulating material with the thermal resistance more than 0.1m<2>.K / W, and is high in temperature control precision, short in detection period and accurate in test result, can effectively avoid the influence on the edge hot loss and the drift of a heat-flow meter, and flexible materials are easily tested.

An integrated circuit chip is provided that comprises on-chip memory and test circuitry. The test circuitry is configured to perform operational testing of the on-chip memory. The test circuitry comprises a controller which is configured to perform a selection out of a plurality of test algorithms to perform the operational testing. The plurality of test algorithms includes a fault detection test algorithm to perform operational testing of the on-chip memory in order to detect whether or not there is a memory fault, without locating the memory fault. The plurality of test algorithms further includes a fault location test algorithm to perform operational testing of the on-chip memory in order to detect and locate a memory fault. Further, a method to perform a memory built-in self test and an MBIST (Memory Built-In Self Test) control circuit template are provided.

The invention relates to a test case design efficiency promotion method and system. The test case design efficiency promotion method comprises the following steps: classifying a business system into a plurality of business categories according to the business type, respectively classifying each business category into a plurality of business subclasses, wherein each business subclass comprises a plurality of business modules; acquiring a plurality of test cases designed by each business module, wherein each test case respectively comprises a plurality of test attributes; establishing a public case library in a catalogue form by utilizing a case management tool according to the business category and the business subclass corresponding to each test case; selecting a test case to test the to-be-tested test module according to a test condition; updating the public case library when any test case is modified. The test case in the public test case library corresponding to the module involved by the demand needs to be called for the specific test demand task, the test case does not need to be repeatedly designed, and the test work efficiency can be greatly improved.

The invention relates to a novel mechanical structure design scheme, which is used for testing test pieces made of various metal and alloy materials at room temperature and bearing tension fatigue characteristic, fatigue life and fatigue crack expansion test of mechanical parts (such as various mechanical connecting pieces). According to the scheme, a motor drives a speed reducer to rotate, the spring is subjected to energy storage by an eccentric shaft coupler and a crank connecting rod mechanism, the spring is controlled by four guide wheels to do vertical reciprocating motion, the potential energy of the spring is converted into moment through a lever, and extension and compression of the spring are reinforced by a lever mechanism, so that tension bars are separated vertically and the stretching effect is achieved; and force amplitude is changed through connecting points at different positions of the lever, so that fatigue tension tests of different frequency and different amplitude are realized. The invention is simple in structure and low in manufacturing cost, adopts a mechanical structure, can meet the basic performance requirement of the fatigue tension test, and can be applied to the tensile fatigue test under the lab environment.

A method of testing and repairing an integrated circuit having a total number of fuses for effecting repair of the integrated circuit. The method including: testing a memory array with a set of tests and reserving a first number of the total number of fuses for use in repairing the memory array based on results of the first set of tests; and shmoo testing the memory array by incrementing, decrementing or incrementing and decrementing values of a test parameter until a minimum or maximum value of the test parameter is reached that utilizes a second number of the total number of fuses for use in repairing the memory array to operate at the minimum or maximum value of the test parameter.

The present invention relates to a clinic pathology data classification method based on combination of principal component analysis and an extreme learning machine. The classification method comprises the following steps of (1) normalizing clinic data, extracting features through principal component analysis, ordering characteristic values according to characteristic significance, removing data dimensions below a significance threshold, and achieving the purpose of data dimension reduction; (2) training a feedforward neural network classifier by using an extreme learning algorithm after data dimension reduction is carried out; and (3) using the trained feedforward neural network classifier to test test samples, and obtaining a classification result. According to the clinic pathology data classification method based on combination of the principal component analysis and the extreme learning machine, dimensions are effectively reduced, calculation is simplified, and the classification effect is good.

The embodiment of the invention provides a software testing method and device, relates to the technical field of information and has the advantages of improving the testing precision and reliability in tests aiming at financial software. The method concretely comprises the steps of acquiring a test case corresponding to a needed test scene from a test case database, wherein the test case database comprises at least one test case corresponding to different test scenes respectively; acquiring an expected test result parameter, a test condition parameter and a detection mode parameter of a test result, which correspond to the needed test scene according to the test case, wherein the test condition parameter comprises at least one item of database data and operation system data; testing the software to be tested according to the test case and the test condition parameter; detecting whether the tested test condition parameter is the same as the expected test result parameter according to the test mode parameter of the test result. The software testing method and device can be used in the test of the financial software.

The invention discloses an ERP software automated testing system. The ERP software automated testing system comprises an initialization module, a use case analysis module, a form processing module, a test scheduling module, an error monitoring module and a report integration module. The initialization module is used for reading configuration file information. The use case analysis module is used for loading test use cases according to the configuration file information and analyzing and testing test logic between an involved ERP form and various forms. The form processing module is used for loading and testing the involved ERP form and acquiring test objects and data in the form. The test scheduling module is used for scheduling the needed test objects and data for testing according to the test logic between the forms. The error monitoring module is used for monitoring and testing abnormal conditions in the scheduling execution process and determining whether to carry out processing or not, if yes, corresponding processing is carried out; and if not, the test objects and data in the last testing node is tested again. The report integration module is used for automatically generating test reports and distributing the reports to related interfaces according to the test results of the test scheduling module and combined with the abnormal conditions monitored by the error monitoring module.

Provided is a locomotive performance testing apparatus capable of testing the locomotive performance of a test subject while keeping the test subject at a suitable position on a treadmill. According to the locomotive performance testing apparatus (1), a robot (2) is moving its legs (22) toward a second direction on a plurality of endless belts (11) which are rotationally driven by a plurality of motors (12), respectively. In this situation, a positional deviation or the like of the robot (2) from a first desired position in a first direction different from a second direction is determined as a first deviation. Moreover, motions of the plurality of motors (12) are individually controlled to offset the first deviation.