Where are artificial neural networks applied?

The artificial neural networks have been applied to a number of problems in diverse fields such as engineering, finance, medical, physics, medicine, and biology and so on. 

- All these applications are based on the fact that these neural networks can simulate the human brain capabilities. 

- They have found a potential use in classification and prediction problems. 

- These networks can be classified under the non-linear data driven self adaptive approaches. 

- They come handy as a powerful tool when the underlying data relationship is not known. 

- They find it easy to recognize and learn the patterns and can correlate between the input sets and the result values.

- Once the artificial neural networks have been trained, they can be used in the prediction of the outcomes of the data. 

- They can even work when the data is not clear i.e., when it is noisy and imprecise. 

- This is the reason why they prove to be an ideal tool for modeling the agricultural data which is often very complex. 

- Their adaptive nature is their most important feature.

- It is because of this feature that the models developed using ANN is quite appealing when the data is available but there is a lack of understanding of the problem.

- These networks are particularly useful in those areas where the statistical methods can be employed. 

- They have uses in various fields:

    1. Classification Problems:

a)   Identification of underwater sonar currents.

b)   Speech recognition

c)   Prediction of the secondary structure of proteins.

d)   Remote sensing

e)   Image classification

f)    Speech synthesis

g)   ECG/ EMG/ EEG classification

h)   Data mining

i)     Information retrieval

j)    Credit card application screening

2. Time series applications:

a)   Prediction of stock market performance

b)   ARIMA time – series models

c)   Machine robot/ control manipulation

d)   Financial, engineering and scientific time series forecasting

e)   Inverse modeling of vocal tract

3. Statistical Applications:

a)   Discriminant analysis

b)   Logistic regression

c)   Bayes analysis

d)   Multiple regression

4. Optimization:

a)   Multiprocessor scheduling

b)   Task assignment

c)   VLSI routing

5. Real world Applications:

a)   Credit scoring

b)   Precision direct mailing

6. Business Applications:

a)   Real estate appraisal

b)   Credit scoring: It is used for determining the approval of a load as per the applicant’s information.

c)   Inputs

d)   Outputs

7. Mining Applications

a)   Geo-chemical modeling using neural pattern recognition technology.

8. Medical Applications:

a) Hospital patient stay length prediction system: the CRTS/ QURI system was developed using a neural network for predicting the number of days a patient has to stay in hospital. The major benefit of this system was that money was saved and better patient care. This system required the following 7 inputs:

Ø  Diagnosis

Ø  Complications and comorbidity

Ø  Body systems involved

Ø  Procedure codes and relationships

Ø  General health indicators

Ø  Patient demographics

Ø  Admission category

9. Management Applications: Jury summoning prediction: a system was developed that could predict the number of jurors that were actually required. Two inputs were supplied: the type of case and judge number. The system is known to have saved around 70 million.
10. Marketing Application: A neural network was developed for improving the direct mailing response rate. This network selected those individuals who were likely to respond to the 2^nd mailing. 9 variables were given as the input. It saved around 35 % of the total mailing cost.
11. Energy cost prediction: A neural network was developed that could predict the price of natural gas for the next month. It achieved an accuracy of 97%. 

What are file types used in Silk Test?

Silk test consists of many file types which have been discussed in this article. There are various types of files that are used by the silk test in the process of automation testing. 

Each of the files is used for a specific purpose or we can say function such as certain files are required by the silk test for the creation and execution of the tests. 

Now we shall discuss the different file types available one by one:

1. Test plan (.pln): This file type in silk test facilitates the creation of the test suites. But the test suites can be created lonely if this file type is combined with the test scripts.

Testone

          Script: test.t

          Test case: one

Testtwo

          Script: test.t

          Test case: second

Here in the above example the main test script file is test. t. on the other hand the ‘one’ and the ‘second’ are the names of the test cases in the main script file test.t. Whenever this file type is run the test cases one and second are automatically picked up by the main script file and executed.

2. Test script (.t): This file type in the silk test is used while writing the actual test scripts. Whenever such a file is in run session the test one and test two test cases are executed by it in a predefined order and at the end the note pad application is closed.
3. Frame file (.inc): The windows and the controls present in the AUT or application under test are defined by an abstraction layer. These windows as well as the controls are referenced later in .t files.
4. Result file (.res): This file type consists of all the test run results which have the names of all the passed as well as failed tests along with their suitable descriptions. These file types may or may not contain log messages.

Leaving out the result file (.res) type, almost all the other file types are based up on text. Therefore, the editing of all those files can be edited either using the silk test IDE or by using a text editor.

In the silk test version that was released in the year of 2006, the files can be saved in either of the two formats namely:

1. ANSI format or
2. The UTF – 8 format

5. Project (.vtp): This file type is saved with an extension of 'verify test project' and is used as storage for the locations as well as the names of the files that are currently in use by some project. With this file type there is another associated file type .ini extension since it is an initialization file.
6. Data driven script (.g.t): This file type stores the data driven test cases which are use to pull out data from the data bases.
7. Suite (.s): With the help of this file type the sequential execution of several test scripts is possible.  
8. Text file (.txt): This is an ascii file type and can be used for the following purposes:

a)   For storing a data that can be used for driving a test.

b)   For printing a file in some another document.

c)   The test automation file is accompanied by this file type as a read me file.

d)   For transformation of a tab delimited plan in to a silk test plan.

Entire above discussed source files are compiled and stored as the ‘pseudo code object files’ at either of the times:

1. When the files are loaded or
2. When any change has occurred in the file types. 

What is the Difference between Bitmap Check point & Image Check point in QTP?

There are two types of major check points that are provided by the quick test professional namely:

1. Bit map check point and
2. Image check point

What is Bitmap and Image Check Point?

- The expected bit map of an object is captured using the bitmap check point while the recording process is in progress. 

- While a run session is in progress and the actual bitmap matches, a pass to the test result is returned by the expected bitmap. 

- If the above is not the case, the test is said to have failed. 

- While the recording is in progress, it is better to insert the bitmap check point rather than inserting it in the active screen. 

- Inserting the check point in the active screen would pose the problem since the possibility is that the active screen may or may not have the latest bitmap updates and making changes to the screen at that time can cause the whole program to fail. 

- To know the difference in the scripts before and after inserting a check point, simply disable a button and run the script. 

- Then insert the check point, enable the button and run the script again. You would be able to see the difference for yourself. 

- For inserting the bitmap check point in to the test script open up a blank test in quick test professional and then open the application that you want to check and start recording. 

- You will get a record and run settings window, select the tab titled “windows application”, then “record and run test on any windows based application” and hit OK. 

- Go to the check point’s option in the insert menu and select the bitmap check point option and insert it where you want.  

- The bitmap check point properties can be changed. 

- Now when the test is run a pass in the test result is recorded by the quick test professional. 

- The basic use of the bitmap check points is in making comparisons between objects and images pixel by pixel. 

- The comparison is carried out for the following:

1. RGB color variations and
2. Total deviation in number of pixels.

- By matching the captured bitmaps one can the appearance of the elements in the application. 

- Bitmap check point has proved to be great help in checking bitmap of a full web page or an image. 

- On the other hand, an image check point cannot check the pixels and therefore it is basically employed in checking properties like source file location of a web site or web page. 

- The area of an application or a web page can be checked as a bitmap. 

- The area to be checked can be specified by selecting an object while creating a test. 

- The selected object is specified as a bitmap and then the check point can be inserted in the test. 

- This calls for a large disk space so in order to save space you have the option of saving only the selected area of the object.

- The bitmap check point also allows you to check the zooming property of the maps and they can be created for all supporting testing environments. 

- The results of the bit map check point may be affected by color settings, screen resolution and operating system but this is not so in the case of the image check points. 

- The properties of an image are verified by image check point under AUT whereas only an area of the AUT is verified as a bitmap by the bitmap checkpoint.