air traffic control system

36
Air Traffic Control System and Review on Expert Systems Arijit Roy & Sathyanarayana Kompala Kalahastri

Upload: coventry

Post on 20-Feb-2023

0 views

Category:

Documents


0 download

TRANSCRIPT

Air  Traffic  Control  System  and  Review  on  Expert  Systems  Arijit  Roy  &  Sathyanarayana  Kompala  Kalahastri  

 

   

Table  of  Contents  

PART  1:  .............................................................................................................................................................................  3  

SECTION  A:  ..........................................................................................................................................................................  3  AIR  CONTROLLED  TRAFFIC  SYSTEM  ....................................................................................................................................  3  PRE  FLIGHT  .....................................................................................................................................................................................  3  DEPARTURE  ....................................................................................................................................................................................  4  EN-­‐ROUTE  AND  DESCENT  ...................................................................................................................................................................  5  APPROACH  .....................................................................................................................................................................................  6  LANDING  ........................................................................................................................................................................................  6  ATC  ON  GRIDSIM:  .................................................................................................................................................................  7  DATA  FLOW  DIAGRAM  OF  ATC:  ................................................................................................................................................  9  SECTION  B:  .........................................................................................................................................................................  10  TASK  1:  CREATION  OF  GRID  USERS  AND  GRID  RESOURCES  .......................................................................................................................  10  Example  1:  ................................................................................................................................................................................  10  Class  Diagram  of  Example  1:  .....................................................................................................................................................  10  Description  –  Example  1:  ..........................................................................................................................................................  10  Example  2:  ................................................................................................................................................................................  11  Class  diagram  of  Example  2:  .....................................................................................................................................................  11  Description  –  Example  2:  ..........................................................................................................................................................  11  Example  3:  ................................................................................................................................................................................  12  Class  Diagram  of  Example  3:  .....................................................................................................................................................  13  Description-­‐  Example  3:  ............................................................................................................................................................  13  Example  4:  ................................................................................................................................................................................  14  Description  –  Example  4:  ..........................................................................................................................................................  15  Example  5:  ................................................................................................................................................................................  15  Class  Diagram  of  Example  5:  .....................................................................................................................................................  17  Description  –  Example  5:  ..........................................................................................................................................................  17  TASK  II:    SELECTION  OF  AT  LEAST  TWO  SCHEDULING  POLICIES  ....................................................................................................................  17  Scheduling  Policies  ...................................................................................................................................................................  17  Challenges  in  Scheduling  by  Grid  computing:  ..........................................................................................................................  18  Scheduling  Policies  ...................................................................................................................................................................  19  Adaptive  Scheduling  .................................................................................................................................................................  19  Resource  Adaptation:  ...............................................................................................................................................................  19  Dynamic  performance  Adaptation:  ..........................................................................................................................................  19  Application  Adaptation:  ............................................................................................................................................................  20  Task  Dependency  on  Scheduling  ..............................................................................................................................................  20  TASK  III)  DISCUSSION  ON  TASK  DEPENDENCY  ON  SCHEDULING  ..................................................................................................................  21  Task  Dependency  on  Scheduling  ..............................................................................................................................................  21  Independent  Task  Scheduling:  ..................................................................................................................................................  22  MET:  .........................................................................................................................................................................................  22  MCT:  .........................................................................................................................................................................................  22  Min-­‐min:  ...................................................................................................................................................................................  22  Max-­‐min:  ..................................................................................................................................................................................  22  XSuffrage:  .................................................................................................................................................................................  22  Task  Grouping:  ..........................................................................................................................................................................  23  Dependent  Task  Scheduling  .....................................................................................................................................................  23  TASK  IV:  GUI  OF  THE  ATC  SYSTEM  ....................................................................................................................................................  24  

PART  2:  REVIEW  OF  A  SCIENTIFIC  PUBLICATION  ..............................................................................................................  29  

KNOWLEDGE  BASED  SYSTEMS:  .................................................................................................................................................  31  RULE  BASED  SYSTEMS  ...........................................................................................................................................................  32  NEURAL  NETWORKS  .............................................................................................................................................................  33  NEURAL  NETWORKS  EXAMPLE  AND  ITS  USES:  ................................................................................................................................  34  REFERENCES  .......................................................................................................................................................................  35    

PART  1:    

Section  A:  

AIR  CONTROLLED  TRAFFIC  SYSTEM  

Air controlled Traffic is a facility provided by controllers in ground who direct an aircraft in ground and in air. The main purpose of ATC is to avoid aircrafts from being collided and provide info to the pilot. In Brazil ATC is mainly used in defence purpose where as in United states of America ATC is used in both security and defence.

There are two types of airspace:

1. Controlled airspace 2. Uncontrolled airspace

When the controllers involve in separating aircrafts from collision it is known as controlled airspace.

When aircrafts fly without help of ATC is known as uncontrolled airspace.

An aircraft follows through 7 stages for travelling from the starting point to the designation. Those steps are below:

a. Pre flight b. Take off c. Departure d. En route e. Descent f. Approach g. Landing

Pre  flight  

When the baggage checking for the passengers are being done the pilot will inspect the plane and files the flight plan with tower 30 minutes before the pushing back from the gate. The pilot then checks the weather on the route of travel and files it. The flight plan includes airline name, flight number, type, equipment, intended air speed, altitude and route of flight. The flight data person in the

tower reviews weather and flight plan and flight plan is entered in FAA host computer. Throughout the travel flight progress strip will be passed from controller. The flight progress strip is constantly updated giving all necessary information for tracking the plane.

The flight data person gives clearance to the pilot once the plan is approved and the strip is passed to ground controller in tower. The ground controller is accountable for ground traffic, from taxing the aircraft from gates to take off runways and from landing runways to gates. The ground controller uses ground radar to track all the runways to ensure that no place crosses the active runway or interface with ground vehicle. The ground controller gives instruction to the pilot by radio such as which way to taxi and runway should be used for take-off. The ground controller passes control to local controller once the plane reaches the designated run way.

The local controller uses surface radar to track the aircraft and watches the skies in the tower to maintain safe distance between the planes as they take off. The local controller gives final clearance to the pilot and provides new radio frequency to departure controller. The pilot then will decide on whether it’s safe to take off, if he feels that’s its safe he rides the planes to the runway. As the planes leaves the ground the local controller passes the control to departure controller at TRACON (Terminal radar approach control).

Departure      

The transponder device inside the aircraft is activated once the plane is take off. The amplified the incoming radar signal. The transponder provides the information like aircrafts flight number, altitude, airspeed and destination. The controller can track the plane with the acquired information.

The TRACON facility is in departure controller have several airports within its airspace. The aircrafts are monitored using radar and must maintain safe distance between ascending aircrafts. The departure controller gives instructions to follow ascent corridors at TRACON airspace. The departure controller passes the plane to centre controller (Air route traffic control system ARTCC) when the plane leaves TRACON airspace.

En-­‐route  and  Descent  

When the plane enters ARTCC airspace after leaving the TRACON, it’s monitored by at least two air traffic controllers. The radar associate controller receives the signal after the plane enters ARTCC. The radar associate controller co-ordinates with all other sectors and responsible for maintaining safe separation of aircraft by providing air to ground communication. The controller will supervise the plane at high and low altitude.

The centre controller provides information on air traffic, updated weather, speed, altitude and maintain safe separation between aircraft within the sector. The control is passed to another sector once the planes leaves early sector. The plane will be monitored until it leave a particular sector.

The radar handoff control helps radar controller during heavy traffic, they support to maintain smooth traffic. Instructions will be given to pilot when there is bad weather or heavy traffic, change of route will be informed to the pilot to ensure safe journey. The centre controller directs all the aircrafts approaching designation to move to higher to lower altitudes and merges the descending aircraft to a single line towards the airport. The controller will place the plane in holding pattern depending on traffic conditions.

In TRACON air space the controller gives information to the pilot.

Approach  

When the plane reached the TRACON space at the designation station, the control is passed to approach controller. The approach controller directs aircraft to adjust speed and altitude to line up and prepare to reach standard corridors. The pilot aligns the aircraft to the runway, the approach controller passes the control to local controller in airport tower.

Landing  The local controller at the tower checks the weather and runway by using binoculars and

surface radars. The local controller provides updated whether to the pilot and gives clearance to pilot, local controller also maintains safe distance between aircrafts. The local controller directs the plane to exit taxiway and passed to the control to ground controller with a new frequency.

The ground controller uses radar to ensure that taxing aircraft doesn’t collide with the active aircrafts or other ground vehicles. Ground controller provides signal to direct plane to reach the appropriate gate. The ground personal use hand signal to park the plane at the gate.

ATC  on  Gridsim:    

  Gridsim  provides  the  feature  of  combining  many  tasks  in  to  a  single  screen  for  handling  all  the  resources  in  one  screen.  Gridsim  has  the  advantage  of  handling  many  system  remotely  in  a  single  screen.  Schedulers  in  gridsim  are  known  as  resource  broker,  schedulers  will  manage  the  application  in  a  single  domain.  All  scheduler  will  be  connected  to  central  scheduler  so  that  if  any  changes  required  in  all  the  schedulers,  the  changes  are  made  in  central  scheduler  which  will  reflect  in  individual  schedulers.  This  concept  is  very  effective  when  an  update  is  released  and  it  needs  to  be  implemented  in  all  the  resources.  This  will  also  increase  the  overall  system  utilization.    

Some  of  the  key  features  of  Gridsim  in  ATC  are  mentioned  below:  

• Resource  can  be  modelled  in  time  shared  mode.  • Different  platform  applications  can  be  simulated.    • Simulation  of  static  and  dynamic  is  supported.  • Network  speed  between  the  resources  can  be  tracked.  

The  flow  between  the  user  and  resource  is  explained  in  the  below  flow  diagram.  

 

(Rajkumar  :  2008)  

Simulation  in  environment  requests  all  entities  and  time  dependent  interaction  in  real  system.  The  response  function  can  either  be  current,  past  or  future  entity.  Independent  task  may  require  varying  processing  time  and  varying  file  size,  such  tasks  can  be  generated  and  the  necessities  are  defined  by  Gridlet  objects.  Gridlet  is  an  object  which  contains  all  details  regarding  a  job  and  information  related  to  it,  some  of  the  informations  like  job  processing  time  (in  milliseconds),  disk  I/O  operations,  input  and  output  file  size  and  originator.  

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

Data  Flow  Diagram  of  ATC:  

Pilo t

T ra n sp on d er  C od e  –  C rea t ion

Predict  A rea

Prod u ce  A la rm

Gen era te  F l ig h t  P la n s

F ilter  T ra ck

C on troller

C h eck  T ra ck  fo r  Mult ip le  fl ig h ts

C rea te  T ra ck

T ra ck  F i le

D ro p  o r  d ele te  T ra ck

Up d ate  o r  ch an g e  track

Rada r  C on troller

A ct iva te  A lte rn a te  fl ig h t  p la n

C h eck  W heth er  s ta tus

D ro p  o r  d ele te  fl ig h t  p la n

Wea th e r  F i le

F lig h t  P la n  fi le

R ecord  F l ig h t  P lan

Wea th e r  F i le

F ilter  t rack  reused

E x ist in g  T rack

C on fl icted  T ra ckT ra ck  In fo

T ra ck  In fo

Up d ate  T rack

T ra ck  In fo

D ro pp ed  T rack

C rea ted  T rack  In fo

A ct ive  P la n

C rea ted  T rack  In fo

C rea ted  T rack  In fo

C on flicted  R eg io n  or  T ra ck

T ran sp on d er  C od e

T ra n sp on d er  C od e

A d v ised  T rac k

T ra ck  In fo

A ltern a te  F l ig h t  P la n

Bad  W ea th er

C rea ted  T rack  In fo

Wea th e r  In fo

F orecasted  W eath e r  Sta tus

Bad  W ea th er  C on d it ion

D ro p  o r  d ele ted  F lig h t  p la n

F lig h t  P la n

Record ed  F lig h t  P lan

Wea th e r  In fo

A ct iva ted  A ltern a tiv e  F l ig ht  P la n

Gen era ted  F lig h t  P la n

Bad  W ea th er  C on d it ion

A la rm  In fo

Section  b:  

Task  1:  Creation  of  Grid  users  and  Grid  resources  

Example  1:    

Run:  Example  of  how  to  create  one  Grid  resource  Initializing  GridSim  package  Initializing...  Starting  to  create  one  Grid  resource  with  3  Machines...  Creates  a  Machine  list  Creates  the  1st  Machine  that  has  4  PEs  and  stores  it  into  the  Machine  list  Creates  the  2nd  Machine  that  has  4  PEs  and  stores  it  into  the  Machine  list  Creates  the  3rd  Machine  that  has  2  PEs  and  stores  it  into  the  Machine  list    Creates  the  properties  of  a  Grid  resource  and  stores  the  Machine  list  Finally,  creates  one  Grid  resource  and  stores  the  properties  of  a  Grid  resource  Finish  the  1st  example  BUILD  SUCCESSFUL  (total  time:  0  seconds)    

Class  Diagram  of  Example  1:    

 

 

Description  –  Example  1:  This Example is made to explain how to create a grid resource with one Grid resource, first to

use grid sim we need to initialize grid sim package. To do this we call the method gridsim.init and pass the required parameters. And then we create an object of grid resource, after creating a grid resource we need a list of machines available in a grid resource, for that we create an object of machinelist.

We create 3 machines with 2, 3 and 4 PE’s respectively, which have a constant mips rating of 377 (which is stored in the field “mipsRating”) After creating machinelist we need to specify the characteristics of the grid resource, in this example we create an object of ResourceCharacteristics called resConfig which will store the characteristics of the resource like architecture, operating system, machine list, time shared (time on which resource is available), time zone and cost.

Finally we declare fields with values, which will be used in the grid resource, and then we create a grid resource using these values and return the grid resource.

Example  2:  

Run:  Starting  example  of  how  to  create  Grid  users    Creating  8  Gridlets  Creating  3  Grid  users    Gridlet  ID        User  ID        length          file  size        output  size          0                        0                3500                300                300          1                        0                5000                500                500          2                        0                9000                900                900          3                        1                17824                121                226          4                        1                18123                136                357          5                        1                30632                116                342          6                        2                30572                96                326          7                        2                20413                145                250  Finish  the  example  BUILD  SUCCESSFUL  (total  time:  0  seconds)    

Class  diagram  of  Example  2:  

Description  –  Example  2:  

This Example 2 demonstrates how to create grid users, first program creates a gridlet list to store the gridlets created then it creates a grid user list so that all the users can be stored in that list.

GridletList (): This method creates gridlets so that they can be used by the gridusers it first makes 3 gridlets manually, Then we create 5 gridlets using gridsimrandom() method and GridSimStandardPE()

Gridsimrandom creates a standard PE and MIPS rating by using GridSimStandard first, then the method then initialises three fields to store maximum range, minimum range and number of gridlets to be created in count.

The variable count determines how many times the for loop will execute, since the loop creates one gridlet every time it runs, the count field determines how many gridlets will be created. In the end the method adds each gridlet to the list and after completing the loop returns the control back to main method.

The main method then creates an Object of ResourceUserList and calls createGridUser and passes the list of gridlets to this method. The CreateGridUser method it creates a list of ResourceUserList and adds three users to the list, after doing this the method initializes a for loop which assigns three users to 8 grid resources and returns userList.Then the main method calls the printGridletList() method to print the grid list and the assigned users.

When the printGridletList() is called it creates an indent variable which is used to give equal space to the table in which the output will be displayed, Then this method initializes a for loop which prints each element of the gridletlist and returns the control the main method which then stops the program.

Example  3:  

Run:  Starting  Example3    Initializing  GridSim  package  Initialising...  Creating  8  Gridlets  ...  Creating  a  new  Test  object  Starting  GridSim  version  5.0  Entities  started.  Inside  Example3.body()  =>  Sending  Gridlet  0  GridInformationService:  Notify  all  GridSim  entities  for  shutting  down.  ...  Inside  Test.body()  =>  Receiving  Gridlet  0  from  Example3  object  Inside  Example3.body()  =>  Receiving  Gridlet  0  Inside  Example3.body()  =>  Sending  Gridlet  1  ...  Inside  Test.body()  =>  Receiving  Gridlet  1  from  Example3  object  Inside  Example3.body()  =>  Receiving  Gridlet  1  Inside  Example3.body()  =>  Sending  Gridlet  2  ...  Inside  Test.body()  =>  Receiving  Gridlet  2  from  Example3  object  Inside  Example3.body()  =>  Receiving  Gridlet  2  Inside  Example3.body()  =>  Sending  Gridlet  3  ...  Inside  Test.body()  =>  Receiving  Gridlet  3  from  Example3  object  Inside  Example3.body()  =>  Receiving  Gridlet  3  Inside  Example3.body()  =>  Sending  Gridlet  4  ...  Inside  Test.body()  =>  Receiving  Gridlet  4  from  Example3  object  Inside  Example3.body()  =>  Receiving  Gridlet  4  Inside  Example3.body()  =>  Sending  Gridlet  5  ...  Inside  Test.body()  =>  Receiving  Gridlet  5  from  Example3  object  Inside  Example3.body()  =>  Receiving  Gridlet  5  Inside  Example3.body()  =>  Sending  Gridlet  6  ...  Inside  Test.body()  =>  Receiving  Gridlet  6  from  Example3  object  Inside  Example3.body()  =>  Receiving  Gridlet  6  

Inside  Example3.body()  =>  Sending  Gridlet  7  ...  Inside  Test.body()  =>  Receiving  Gridlet  7  from  Example3  object  Inside  Example3.body()  =>  Receiving  Gridlet  7  Sim_system:  No  more  future  events  Gathering  simulation  data.  Simulation  completed.    ==========  OUTPUT  ==========  Gridlet  ID        STATUS            0                SUCCESS          1                SUCCESS          2                SUCCESS          3                SUCCESS          4                SUCCESS          5                SUCCESS          6                SUCCESS          7                SUCCESS  Finish  Example3  BUILD  SUCCESSFUL  (total  time:  0  seconds)    

Class  Diagram  of  Example  3:    

 

Description-­‐  Example  3:  This example demonstrates the interaction between two gridsim entries, basically it creates

gridlets and sends it to the test class. The example class takes 3 parameters as input to receive the gridletlist from the test class, this method is also used to assign list to _recivelist list and then to create a new object of test class, which initializes the test class.

Then body method handles the communication between the Example class and the Test class, first this method gets the list size and stores it in integer then it creates two objects of Gridlet type. Then the body method creates a for loop which sends one gridlet at a time to the test class, then it receives the gridlet from the test class and stores it in gridlet object, then prints the received gridletID, after this received gridlet is stored in the receiveList_. At last it signals end of simulation to the entityName.

The test class waits and listens to the event simulation for the gridlet to arrive, when gridlet is passed into the test class it receives and then gives the gridlet back to the Example class as output, the function of this method is to test how any gridlet can be received as an input and send it back as an output.

The test method in this class calls for super () method and to get the name and communication rate for the gridlet and then prints that it has created a gridlet. The body method in this class. The main method first initializes the gridsim package, using Gridsim.init method and passing all the values to the method, thereafter it creates a list of gridlets by creating a list of GridletList type and assigning the values of method createGridlet(). After completing this process the main method creates an object of example type and passes its name, communication speed and list of gridlets.

Then the startGridSimulation() package is initialized to start the simulation, after the simulation is complete the program gets the list of objects by calling getGridletList () method and stores it in newList object, finally the printGridletList method is called to print the list of gridlets.

Example  4:  

Run:  Starting  Example4  Initializing  GridSim  package  Initialising...    Starting  to  create  one  Grid  resource  with  3  Machines  Creates  a  Machine  list  Creates  the  1st  Machine  that  has  4  PEs  and  stores  it  into  the  Machine  list  Creates  the  2nd  Machine  that  has  4  PEs  and  stores  it  into  the  Machine  list  Creates  the  3rd  Machine  that  has  2  PEs  and  stores  it  into  the  Machine  list  Creates  the  properties  of  a  Grid  resource  and  stores  the  Machine  list  Finally,  creates  one  Grid  resource  and  stores  the  properties  of  a  Grid  resource    Creating  a  grid  user  entity  with  name  =  Example4,  and  id  =  9  Creating  8  Gridlets  Starting  GridSim  version  5.0  Entities  started.  Received  ResourceCharacteristics  from  Resource_0,  with  id  =  5  Sending  Gridlet_0  to  Resource_0  with  id  =  5  Receiving  Gridlet  0  Sending  Gridlet_1  to  Resource_0  with  id  =  5  Receiving  Gridlet  1  Sending  Gridlet_2  to  Resource_0  with  id  =  5  Receiving  Gridlet  2  Sending  Gridlet_3  to  Resource_0  with  id  =  5  Receiving  Gridlet  3  Sending  Gridlet_4  to  Resource_0  with  id  =  5  Receiving  Gridlet  4  Sending  Gridlet_5  to  Resource_0  with  id  =  5  Receiving  Gridlet  5  Sending  Gridlet_6  to  Resource_0  with  id  =  5  Receiving  Gridlet  6  Sending  Gridlet_7  to  Resource_0  with  id  =  5  Receiving  Gridlet  7  GridInformationService:  Notify  all  GridSim  entities  for  shutting  down.  Sim_system:  No  more  future  events  Gathering  simulation  data.  Simulation  completed.    ==========  OUTPUT  ==========  Gridlet  ID        STATUS        Resource  ID        Cost          0                SUCCESS                5                27.851458885941646          1                SUCCESS                5                39.78779840848807          2                SUCCESS                5                71.6180371352786  

       3                SUCCESS                5                12.260185925286578          4                SUCCESS                5                32.160803970344375          5                SUCCESS                5                26.989166622345806          6                SUCCESS                5                16.721823905496365          7                SUCCESS                5                20.974565689486667  Finish  Example4  BUILD  SUCCESSFUL  (total  time:  0  seconds)    

Description  –  Example  4:  

This Example demonstrates how a user can give its gridlet (Task) to a grid resource for execution. In the first step the constructor calls for super () method and passes it the value for gridlet name and communication speed, then it gets the ID for this entitety and assigns it to this.ID field. Then the constructor creates a list of gridlets and assigns it to this.list_.

The body method handles all the communication needs of the program, in this method first initializes some fields and linked list to store the resources then creates an object of type ResourceCharacters.

Then it initializes a while loop for receiving the resources, then checks if the resource is available. If the resource is available then it initializes the resourceID and sends the resource to the calls the super.send method with appropriate parameters. Then the method calls the super.receiveEventObject method to receive the resource and stores it in the resChar object and stores resource name into the resourceName object.

Then this method initializes a for loop to get gridlets one at a time and send it to a grid resource entity, first this loop gets one gridlet from Gridlet and stores it in gridlet object and then sends the object to the resource specified in the resourceID.After this process the loop waits to receive the gridlet, when gridlet is received it is stored in the gridlet object and then adds the gridlet to the list of gridlets.

The main method first initializes the gridsim package, then creates a grid resource. After creating the gridsim resource it creates an object of example with parmeters for its name and communication rate, then the grid sim simulation is started. At last the printGridletList() is invoked to print the output of all the gridlets.

Example  5:  

Run:  Starting  Example5  Initializing  GridSim  package  Initialising...    Starting  to  create  one  Grid  resource  with  3  Machines  Creates  a  Machine  list  Creates  the  1st  Machine  that  has  4  PEs  and  stores  it  into  the  Machine  list  Creates  the  2nd  Machine  that  has  4  PEs  and  stores  it  into  the  Machine  list  Creates  the  3rd  Machine  that  has  2  PEs  and  stores  it  into  the  Machine  list  Creates  the  properties  of  a  Grid  resource  and  stores  the  Machine  list  Finally,  creates  one  Grid  resource  and  stores  the  properties  of  a  Grid  resource      

Starting  to  create  one  Grid  resource  with  3  Machines  Creates  a  Machine  list  Creates  the  1st  Machine  that  has  4  PEs  and  stores  it  into  the  Machine  list  Creates  the  2nd  Machine  that  has  4  PEs  and  stores  it  into  the  Machine  list  Creates  the  3rd  Machine  that  has  2  PEs  and  stores  it  into  the  Machine  list  Creates  the  properties  of  a  Grid  resource  and  stores  the  Machine  list  Finally,  creates  one  Grid  resource  and  stores  the  properties  of  a  Grid  resource      Starting  to  create  one  Grid  resource  with  3  Machines  Creates  a  Machine  list  Creates  the  1st  Machine  that  has  4  PEs  and  stores  it  into  the  Machine  list  Creates  the  2nd  Machine  that  has  4  PEs  and  stores  it  into  the  Machine  list  Creates  the  3rd  Machine  that  has  2  PEs  and  stores  it  into  the  Machine  list  Creates  the  properties  of  a  Grid  resource  and  stores  the  Machine  list  Finally,  creates  one  Grid  resource  and  stores  the  properties  of  a  Grid  resource    Creating  a  grid  user  entity  with  name  =  Example5,  and  id  =  17  Creating  8  Gridlets  Starting  GridSim  version  5.0  Entities  started.  Waiting  to  get  list  of  resources  ...  Waiting  to  get  list  of  resources  ...  Received  ResourceCharacteristics  from  Resource_2,  with  id  =  13  Received  ResourceCharacteristics  from  Resource_1,  with  id  =  9  Received  ResourceCharacteristics  from  Resource_0,  with  id  =  5  Sending  Gridlet_0  to  Resource_2  with  id  =  13  Receiving  Gridlet  0  Sending  Gridlet_1  to  Resource_0  with  id  =  5  Receiving  Gridlet  1  Sending  Gridlet_2  to  Resource_0  with  id  =  5  Receiving  Gridlet  2  Sending  Gridlet_3  to  Resource_0  with  id  =  5  Receiving  Gridlet  3  Sending  Gridlet_4  to  Resource_1  with  id  =  9  Receiving  Gridlet  4  Sending  Gridlet_5  to  Resource_1  with  id  =  9  Receiving  Gridlet  5  Sending  Gridlet_6  to  Resource_2  with  id  =  13  Receiving  Gridlet  6  Sending  Gridlet_7  to  Resource_1  with  id  =  9  Receiving  Gridlet  7  GridInformationService:  Notify  all  GridSim  entities  for  shutting  down.  Sim_system:  No  more  future  events  Gathering  simulation  data.  Simulation  completed.    ==========  OUTPUT  ==========  Gridlet  ID        STATUS        Resource  ID        Cost          0                SUCCESS                13                27.851458885941646          1                SUCCESS                5                39.78779840848807          2                SUCCESS                5                71.6180371352786          3                SUCCESS                5                12.260185925286578          4                SUCCESS                9                32.160803970344375          5                SUCCESS                9                26.989166622345806          6                SUCCESS                13                16.721823905496365          7                SUCCESS                9                20.974565689486667  Finish  Example5  BUILD  SUCCESSFUL  (total  time:  0  seconds)  

Class  Diagram  of  Example  5:    

 

Description  –  Example  5:  This program demonstrates how the users can assign one gridlet to many grid resource entity,

first the constructor is defined in the program which initializes the fields gets and ID for the entity. Then it creates a list of gridlets for this grid user.

The method body () initializes resourceID, resourceCost and resourceName fields, then it creates two objects for resource list and resource characteristics.Then the method starts a while loop to store resource list in resList object, then it starts a for loop to get all the resources available and stores in resChar object.

After the loop is complete the method starts another for loop to get a gridlet one at a time and sent it to a random grid entity and to receive a reply, first the loop sends one gridlet to a random grid resource and then repeats the process till it has completed sending all the gridlets. Creategrid method is used to create gridlets it generates 8 gridlets out of which 3 are manually generated and 5 are randomly generated, then it sends the list of gridlets back.

Main method first initliases the gridsim package then it makes three objects of gridresource type resource, then it creates an object of the example class and passes its name communication resource and total resource. After that the main method calls printGridletList() to print the output.

Task  ii:    Selection  of  at  least  two  scheduling  policies  

Scheduling  Policies  

Resources such as computers, storage space, instruments, software applications and data which are connected by means of internet, there would be a middle ware layer that provides services for security, monitoring and resources management. The administrative organization which makes use of the resources keeps in shared within the distributed companies under specifically defined policies and conditions. The logical architecture of grid scheduling process consists of three stages:

1. Resource discovering and filtering 2. Resource selecting and scheduling according to objectives 3. Job submission

The diagram below represents the model of grid scheduling in which two types of data flow are connected to the functional components,

• Resource or application information flow • Task or task scheduling command flow

(Dong : 2006)

Grid schedulers don’t connect to the resources directly, they work like brokers or tightly coupled with applications as application level scheduling scheme process. It is not required that they are located in the same domain with the resources. Status of the available resource are very crucial for grid scheduler for making a proper schedule especially when dealing with heterogeneous and dynamic nature of Grid. Grid Information service(GIS) provides information to the grid scheduler, GIS has the role of collecting and predicting the resources information such as memory size, CPU capacities, software availabilities and network bandwidth.

Challenges  in  Scheduling  by  Grid  computing:  

• Heterogeneity and Autonomy • Performance Dynamism • Computation Data separation • Resource selection.

Scheduling  Policies   Some of the scheduling policies which are followed by the administrative organisations are below:

• Adaptive scheduling • Task dependency on application • Data scheduling • Non Traditional Approach for Grid task scheduling. • Scheduling under QOS Constraints • Strategies treating dynamic resource performance

Adaptive  Scheduling   Adaptive scheduling depends on the terms, parameters and make scheduling decisions change dynamically depending on the resources available at present and future resource status. The request for scheduling adaption comes from three points.

• Heterogeneity of candidate resource • Dynamism of resource performance • Diversity of applications

http://ftp.qucis.queensu.ca/TechReports/Reports/2006-504.pdf

Resource  Adaptation:   For achieving high performance and to reduce the cost, discovering the available resource and choosing the appropriate resource are very critical, this is due to the fact of resource heterogeneity and application diversity. The resources are first ranked according to memory size and computational power, the appropriate sized resource is selected from the sorted list. This also involves selecting set of nodes and to maximise the minimum available bandwidth between the nodes to determine the performance on full load which will determine its efficiency and performance on fully load.

Dynamic  performance  Adaptation:   The adaptation of dynamic are mainly allocated by:

i) Changing scheduling policies and rescheduling by switching between static scheduling algorithms which makes use of anticipated information and dynamic one which make use of static scheduling results.

ii) Distribution of workload according to application specific performance models. iii) Strategies for dividing a particular work and allocation individual work to the

resource so that result can be obtained much faster.

In this approach the main task is divided in to subtasks and the subtasks are distribute to the available resources, this will increase the performance and utilization of all available resource and prevents the resource to reach ideal stage.

Application  Adaptation:   The application scheduler are usually tightly coupled with application and are not applied to other applications. This will increase the performance to the high level. One of the main feature to implement decoupling is by recording the application characteristics which are discovered specialized compilers and grid enabled libraries. The characteristics of applications are connected by well-defined interfaces to schedulers so that the service can be general purpose and service can be continuous. When there is error in allocating the resource and when the time limit reaches the threshold value the scheduler will reallocate the tasks to another resource.

Task  Dependency  on  Scheduling  

Dependency vs Independency is a common dichotomy considered in Grid application. In this context dependency means that child task should start once the parent task is completed. Dependency are very important in scheduling critical time related tasks. Minimum Execution time (MET) and Minimum completion time (MCT) are the terms used to determine performance of the resource before it’s allocated to perform a particular task. MET will determine the amount of time required to execute the give task, this will determine the minimum amount of time which will give assumption to user the time required to set for the application for the task allocated to particular resource. MCT will determine the amount of time required to complete a task allocated to a resource. In computational grid the tasks are collected as a group and individual intensive task are assigned to individual member of the group. The processing time of the applications has the maximum cost in terms of scheduling and transmission to form grid resources. By this process the time for job launching is reduce and resource utilisation is increased.

Grid systems also support dependent task scheduling, but there are some problems related to dependent task scheduling. They are

1. How tasks are scheduled 2. How to submit scheduled tasks.

The above two task must not violate the structure of original workflow. There are solutions

which will reduce the problems mentioned above. Grid flow generators solves the first problem, Grid workflow engines solves the second problem. The below two diagrams shows the block diagram of task without dependency and task with dependency.

The diagram shows the how tasks are dependent on each other. In first diagram there are time space between two tasks are not dependent on each other and both the task can take place independently, where as in second diagram shows that Task B is dependent on Task A which means that Task B can start only after the Task A is completed.

Task  iii)  Discussion  on  Task  Dependency  on  Scheduling  

Task  Dependency  on  Scheduling  

The work dependency clearly states that task are dependent on each other, i.e. execution of one task will depend on the execution of other task. If the scheduling is not timed in proper there are chances that tasks may hang or there is possibility of dead lock as one task may depend on other but in turn the second task may depend on first task. In task dependency the child task will always depend on parent task to complete first.

The dependency task scheduling is discussed by following dichotomy:

Independent  Task  Scheduling:   In independent task scheduling, each individual task are allocated to system and each task are performed individually the output are not dependent on each other. The execution of one output will not affects the performance of other, this will help the system to achieve high throughput Static approach with performance estimate:

The following terms will help to determine the performance of the system.

o Minimum Execution Time (MET) o Minimum Completion Time (MCT) o Min-min o Max-min o XSuffarage o Task Grouping o Problem of Heterogeneity

MET:     This will determine the best executed time for completing the task using a resource. The idea behind is give each task the best resource to perform the task so that it can achieve the best executed time for completion of task.

MCT:   It will indicate the completion time for a task to complete by the allocated resource. This will determine the task to be assigned to particular resource depending on the completion time by individual resources.

Min-­‐min:   If there are M tasks, Min-min will determine the minimum amount of time required for M task to get completed.

Max-­‐min:   This will determine the maximum time to perform M amount of task to get completed. The difference between Min-min and Max-min will determine the performance of the resource.

XSuffrage:   The logic behind suffrage is that each task is assigned to a particular host for the task to be performed. If the host doesn’t handle the task then it means the task is not handle by any of the resource. The Suffrage value is determined by the difference between the first and second MCT. If the nodes are clustered the system may face the problems, because if the nodes are clustered the performance is almost similar in every stage, in this case the difference between the best and second best MCT is taken.

Task  Grouping:   This policy is useful if the system is handling lot of lightweight jobs. In this case the overall processing will determine the performance by scheduling and transmission to or form Grid resources. Once the individual tasks are collected they are aligned and allocated to a particular resource and time is determined for the tasks to get completed. By this process of scheduling the job launching is reduced and resource utilization is increased.

Dependent  Task  Scheduling   When the jobs have the order to follow the execution process dependent task scheduling is

used. One of the popular model is directed acyclic graph (DAG) in which a node represents a task and the task are executed in precedence order. Some of the tool which use dependent task scheduling are Condor DAGMan, CoG, Pegasus, GridFlow and ASKALON. In dependent task scheduling there are two major problems which are handled, the problems are like how the task in workflow is scheduled, the problem is handled by Grid workflow generators. The second problem is how to submit the scheduled task to grid resources, this problem is handled by Grid workflow engines. The data scheduling task is done by the below flow:

In some systems certain systems are maintained a cycle for completion of a task depending on the start and finish of the task. The starting time will determine when the task has to be finished and in some system depending on the type of the job the finishing time is determined. for e.g. in task which must not be finishing at night in such systems the finishing time will be determined depending on the time of start. By taking some examples in to consideration the dependencies are divided in to four types below.

 

Task  IV:  GUI  of  the  ATC  system    

The  Gui  for  ATC  system  is  located  on  :  

https://drive.google.com/file/d/0B7HAuqrEaDecQS0zNl9leF9iQnM/edit?usp=sharing  

 

When  the  user  starts  the  simulation  part,  the  system  will  check  for  user  credentials.  Once  the  login  and  password  matches  with  the  credentials  stored  in  the  database  the  system  will  allow  user  further  for  doing  simulation.    

 

Once  user  able  to  login,  the  Grid  resource  creation  page  requests  user  to  enter  the  following  details.  

 

The system requests for user ID, size and no of user for creating the user.

Once the user is created, the gridlet is created for performing the operations required. Before creaing gridlet the following details are requrested from user.

After obtaining all the required information from the user for creating gridlet, the simulation is done

User will be able to enter or obtain further details by selecting particular option from specific drop down menu. This will help user to check with all the query required.

 

 

 

#  

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

Part  2:  Review  of  a  scientific  publication    

In  the  feature  article  “Expert  system  methodologies  and  applications—a  decade  review  from  1995  to  2004”   the   author,   Shu-­‐Hsien   Liao,   writes   a   review   about   different   types   of   Expert   systems  which  were  common  from  1995  to  2004.    

The  Author  first  uses  different  approaches  to  Expert  system  to  summarize  the  articles  collected  from  1995  to  2004,  and  gives  a   list  of  uses  for  each  approach,  this  article   is  divided  into  14  parts,  which  explains  11  types  of  approaches  to  Expert  systems  in  detail.  

The  Main  approaches  discussed  by  the  author  are  as  following:  

 

1. Rule  Based  System:   A   rule   based   system  obtains   rules   from  a   human  expert   and  uses  the  rules  to  perform  operations  on  data  and  get  conclusion,  These  rules  are  defined  as  IF   ELSE   conditions   in   the   system.   Some   of   the   examples   of   rule-­‐based   systems   are,   DNA  histogram  interpretation,  bio  separation  and  biochemical  nanotechnology.  

 

2. Knowledge  based  system:  These  systems  are  attempt  to  understand  and  initiate  human   knowledge   in   computer   systems,   This   kind   of   approach   is   useful   when   a   system  needs   to   manage   all   the   knowledge   assets   of   any   organization.   KBS   has   four   key  components;   Knowledge   base,   Interface   Engine,   Knowledge   engineering   tool   and   a   user  interface.  Medical  treatment,  chemical  process  control  and  chemical   incident  management  are  some  fields  in  which  KBS  is  used.  

 

3. Neural  networks:  When  a  neural  network   is   created  by  analyzing  biological  neural  network,   Artificial  Neural  Networks   (ANN)   are   used  where  massively   parallel   processing   is  required  for  example  software  simulations.  Like  a  biological  neuron  receives  electrochemical  signals,   similarly   an   artificial   neuron   receives   input.   Neural   networks   are   used   in  Machine  learning,  knowledge  learning  and  robotics  extensively.  

 

4. Fuzzy   expert   system:   Fuzzy   expert   systems   use   fuzzy   logic,   which   allows   the  computer   to   behave   less   precisely   and   can   be   used   for   decision  making   process   because  decision  making  is  not  always  about  accuracy,  sometimes  the  system  has  to  consider  other  aspects  which  indirectly  influence  a  decision.  Some  widely  used  examples  of  fuzzy  logic  are  power  load  forecasting,  water  supply  forecasting  and  power  system  diagnostics.  

   

5. Object   oriented   methodology:   This   methodology   classifies   the   parts   of   the  softwares   into   objects,   when   a   function   has   to   be   performed   then   the   object   required   is  called  by  the  program,    this  results  in  a  very  reusable  software  as  the  software  is  divided  into  objects  and  each  object  behaves  differently  instead  of  the  input  being  the  same.  Some  fields  in   which   this  methodology   is   popular   are   knowledge   representation,   knowledge   learning,  and  knowledge  engineering.  

 

6. Case  based  system:   In   this   type   of   system   the   computer   system   stores   different  scenarios  as  cases  in  its  knowledge  base,  when  it  is  given  a  problem  it  tries  to  compare  the  

problem   with   previous   problems   and   present   a   appropriate   solution.   If   the   solution   is  successful  then  this  solution  is  added  to  existing  list  of  cases  and  it  is  unsuccessful  then  it  is  stored  to  the  case  base  along  with  explanations  of  why  it  didn’t  work.  

 

7. Modeling   methodology:     This   methodology   combines   the   logical   models   and  knowledge  domains,  and  provides  AI  and  other  research  fields  a  platform  to  develop  Expert  Systems.   It   is  majorly  used   in   fields   such  as   transport  design,  medical   analysis   and  project  allocation.  

 

8. System  Architecture  of  ES:   The   architecture  of   any   system  defines  how   the  system  works,  and  defines  the  structure  of  the  system,  it  also  provides  the  user  capability  of  manipulating  system  function  on  system  architecture.  This  system  is  used  in  Computer  Aided  Design,  Ergonomics  design  and  training  simulators.  

 

9. Intelligent  Agent:   This   is   a   new   technology  which   is   a   autonomous   program,   it  enables  user   to  do   routine  computing   tasks,   Its  applications   includes  Tutoring  systems,  Air  pollution  control  and  Industry  simulation.  

 

10. Ontology:   It   is   a   vocabulary   system,   which   acts   as   a   communication   basis   between  domain  experts  and  knowledge  engineers,  Some  applications  of  ontology  are  in  the  field  of  Knowledge  reuse,  Chess  heuristic  pruning  and  preventive  control.  

 

11. Database  Methodology:   A   database   is   helpful   in   centralizing   the   entire   data   and  reduce   data   redundancy,   it   also   helps   in   analyzing   the   data   in   different  ways,  When   very  large  amounts  of  data  is  involved  and  the  data  analysis  becomes  computationally  extensive,  databases  use  data  mining  and  searching  approaches  to  find  the  relevant  information.  Some  examples   where   database   methodologies   is   used   are   Geographical   Informational   system,  sedimentary  rock  interpretation  and  power  system  planning.  

   At   last   the   author   discusses   about   the   broad   category   of   research   issues   in   Expert   systems   and  suggests  that  social  science  methodologies  and  statistical  methods  can  be  major  categories  in  future  works.  

 

Then   the   author   concludes   the   Expert   systems   application   domain   is   a   problem-­‐oriented   domain.  And   different   social   science  methodologies   such   as   psychology   and   cognitive   science   and   human  behavior  can  be  another  kind  of  methodology.  

The  three  major  systems  described  in  this  paper  are  Rule  based  systems;  Knowledge  based  system  and  Neural  Networks  

 

 

 

Knowledge  based  systems:      

In   todays   competitive  market   building   product   knowledge   and  managing   that   knowledge   using   a  knowledge  based   system   is   essential,   these   knowledge  based   systems   acquire  product   knowledge  then  help  to  achieve  efficient  product  knowledge  management,  decision  and  design  support.  

“Knowledge   is   a   combination   of   information   and   experience,   context,   interpretation   and  reflection”(Davenport  T.H.:  1998)  

Knowledge  based  system  consists  of  three  layers:  

 

a) Knowledge  base  layer:  This  layer  consists  of  all  the  acquired  knowledge  in  a  knowledge  base.  This  layer  models,  organizes  and  stores  the  product  knowledge  into  a  standardized  format.  

b) Interface   Engine:   This   part   of   the   knowledge-­‐based   system   consists   of   different   tools   to  acquire   the   knowledge   in   a   fast   and   efficient   manner   like   data   mining   and   knowledge  discovery  databases.  

c) Interface:  This  is  the  actual  user  interface,  which  is  presented  to  the  user;  this  is  generally  a  highly  customer-­‐oriented  communication   interface,  which   interacts  between  users  and  the  interface  engine.  

 

For   a   knowledge  based   system   to  work   efficiently   an   effective   knowledge  base   is   required,   this   is  achieved   by   managing   the   product   knowledge   and   organizing   it   to   prevent   knowledge   loss   and  efficient   knowledge   retrieval   in   future,   this   process   is   known   as   knowledge   representation   of  knowledge  management.  

 

Knowledge  modeling   is   separation  of   the  knowledge   that   is  available   in  documents  such  as  design  manuals,   datasheets   and   standard   specification.   This   knowledge   should  be   computer   readable,   so  this  knowledge  is  transformed  into  computer  interpretable  format.  

 

Finally,   I  would   like   to  conclude   that  nowadays  most  knowledge  based  systems  are  designed   for  a  specific  purposed  and  they  are  not  flexible,  for  example  a  KBS  designed  for  knowledge  reuse  will  fail  in  explicit  data  mining  jobs,  Web  based  approach  is  a  promising  field  in  these  systems,  but  it  requires  more  research  and  study.  

 

 

 

 

 

 

 

Rule  Based  Systems    

Rule  base  system  is  a  type  of  expert  system  which  uses  rules  to  make  choices  and  deductions,  This  kind   of   systems   can   be   useful   in   compilation   of   computer   programs   of   technologies   like   natural  language  processing.  

 

There  are  three  phases  of  rule-­‐based  systems  :  

 

1. Match:  in  this  stage  the  all  the  productions  are  matched  against  the  working  memory  and  a  conflict  set  is  is  produced.  

2. Conflict   resolution:   in  this  phase  one  product   instantiation   is  selected  from  the  conflict  set  and  is  executed.  

3. Act:  This  phase  is  the  last  phase  of  the  system,  In  this  stage  the  actions  from  the  productions  in  conflict-­‐resolution  phase  are  executed.  After  this  the  execution  returns  to  the  first  phase.  

 

Rule  based  systems  are  in  use  for  few  decades  now,  and  they  have  proven  their  usefulness  in  many  fields.   But   since   they   are   based   on   IF   ELSE   based   conditions   or   “Rules”   they   drew   quite   a   bit   of  criticism  because  getting  the  right  rules  for  every  system  was  a  difficult  task,  Moreover  some  of  the  rule  based  systems  grew  very  large  in  size  and  then  they  were  very  hard  to  maintain,  and  verification  and  validation  of  every  rule  in  a  rule  based  system  was  very  impractical,  as  a  result  many  algorithms  and   tools   were   developed   for   verification   and   validation   of   the   rule   based   system.   Nowadays  compact   and   efficient   rule   based   systems   are   preferred   instead   of   the   large   and   bulky   systems  because   they   are   easy   to  maintain   and   if   there   are   a   defined   set   of   rules   then   it   is   easy   for   the  company  or  organization  to  train  its  employees  for  the  system.    

 

While  creating  an  efficient  rule  based  system  many  approaches  can  be  used,  one  of  the  approaches  say  that  the  rules  that  are  not  in  use  they  should  be  eliminated.  While  this  idea  is  not  new  but  it  also  has  some  glitches,  first  one  is  that  it  cannot  be  applied  to  a  new  system  because  it  will  need  the  rule  usage  data   to  calculate  how  many   times  a   rule  was  used  and  second  problem   if  any   rule  which   is  critical  to  the  system  is  eliminated  because  it  was  not  used  frequently  can  cause  errors  in  the  future.  

 

Another  approach   to   create  a  better   rule-­‐based   system   is   known  as  Brief  Rule  Based   system.  This  approach   is   useful  when   the   “rule   based   system  needs   to   represent   different   types  of   knowledge  under   uncertainty”   (Chang   L:   2013).   One   of   the   most   important   applications   of   the   rule-­‐based  system   is   the   RIMER   approach,   which   stands   for   Rule-­‐base   Interface   Methodology   using   the  Evidential  Reasoning.  

 

By  using  a  brief  rule  based  system  RIMER  is  able  to  handle  different  kinds  of  uncertainty,  This  system  has   many   uses   like  Multiple   attribute   decision   analysis,   group   decision  making,   Risk   analysis   and  Military  capability  evaluation.  

Neural  Networks    

Artificial  neuron  networks  is  a  kind  of  system,  which  is  inspired  by  biological  neurons,  they  excel  in  the   fields   of   Machine   learning,   pattern   recognition   and   signal   processing.   In   this   system   all   the  processing  elements  or  nodes  are  interconnected  with  each  other,  different  learning  algorithms  and  training  determine  the  strength  of  the  connection.  

 

Most  of  the  artificial  neuron  networks  are  made  to  behave  like  neurons  (particularly  in  brain)  this  is  commonly   known   as   feed   forward   topology   this   include   perceptron,   radial   basis   functions,   back  propagation  networks  and  support  vector  machines.  

 

The  capacity  for  learning  and  generalization  in  a  neural  network  is  determined  by  its  choice  of  basis  functions,  and  mostly  these  basis  functions  are  inspired  by  transfer  functions   in  biological  systems.  There  are  two  distinct  classes  of  neural  functions  and  coding  streams.    

 

1. Value  Coding  2. Intensity  Coding.  

 

These  coding  methodologies  defines  the  generalization  and  learning  capabilities  of  a  neural  network  

 

One   of   the   approaches   of   using   ANN   is   to   use   its   recollection   and   prediction   capabilities,   This  approach  basically  allows  the  ANN  to  recollect  its  past  and  predict  the  future  according  to  the  data  gathered  in  the  past.  There  are  examples  of  some  feed  forward  networks  that  can  evolve  a  memory  like  function  (Chung  J.R.:  2009)    

 

One  of  the  demerits  of  the  neural  networks  is  that  it  requires  large  amount  of  training  and  learning  for   real-­‐   world   application,   This   is   common  with   all   the   learning   based  machines   as   they   need   a  variety   of   training   to   capture   the   underlying   mechanism,   which   will   allow   it   to   solve   new   cases.  There  is  always  a  issue  of  undertraining  and  overtraining,  If  we  undertrain  the  neural  network  then  it  wont  be  able  to  give  a  optimum  output,  and  if  we  overtrain  it  then  it  will  learn  the  training  methods,  if  this  happens  then  the  output  of  the  neural  network  will  be  very  similar  to  the  training  provided.  

 

Although  the  learning  methods  of  artificial  networks  are  difficult  to  analyze  but  by  research  of  this  technology   also   provides   insights   to   the   functions   and   genetic   principals   of   biological   neural  networks  and  its  workings.  

 

 

Neural  networks  example  and  its  uses:      

Neural  networks  have  a   variety  of  uses   like  Data  mining,  Automatic   speech   recognition  and   signal  processing.    

 

Artificial  Neural  networks  have  been  used  for  speech  recognition  since  1980’s    

(Curilem,  M:  2010)  a  single  ANN  is  used  to  map  speech  features  and  generates  phonemes,  which  are  then  converted  to  words.  This  approach  is  used  by  many  people  for  recognizing  phonemes  in  many  languages  like  Malay,  Hindi  and  Japanese.  

 

This  method   of   using   ANN   is   also   quite   effective   and   robust   against   noise;   Research   studies   have  shown   that   during   training   if   a   ASR   system   uses   clean   data.   However   there   is   a   problem   in   this  approach,  since  the  noise  produced  by  different  sources  differ  vividly  the  feature  set  generated  by  the  noise  can  adversely  affect  the  accuracy  of  speech  recognition.  

 

Method  of  Speech  Recognition:    

 

Speech   recognition   is   a   complex   process   so   there   are   a   variety   of   approaches   to   do   speech  recognition;  these  are  the  common  steps  involved  in  a  speech  recognition  system:  

 

1. Preprocessing:  The  Audio  signals  received  are  down  sampled  and  analyzed  so  that  only  the  part  containing  human  speech  is  filtered  and  processed,  this  reduces  noise  and  excess  data  and  increases  processing  time.  

2. Feature  Extraction:  by  using  MFCC  Mel-­‐frequency   cepstrum  coefficients,   in   the   input   layer  the   neurons   take   input   of   speech   tokens   and   extract   speech   features   then   by   using  techniques  like  Makarov  Toolkit  (HTK)  (  Young,  2006)  MFCC  can  be  normalized  before  they  are  fed  into  the  ANN.  

3. Feature  reduction:   in  this  step  the  features  are  reduced,  only  the  usable  features  are  kept.  ANN  helps   in   this   process   by   using   learning   algorithms   like   Self   Adjusting  Neural  Network  (SANN)(REF  NNA   3)   or   Time   delay   neural   network   (TDNN)   to   separate   the   useful   features  from  the  non-­‐useful  features.  

4. Feature  Generation:  Feature  selection  is  a  process  in  which  the  speech  signals  are  compared  to  a  corpus  or  a  dataset  like  acoustic-­‐phonetic  continuous  speech  corpus  (Garofolo:  1992)  to  recognize  the  words  and  phrases  and  generate  phonemes,  by  using  learning  algorithms  like  Self  Adjusting  Neural  Network  (SANN)(REF  NNA  3)  or  Time  delay  Neural  network  (TDNN)  an  ANN  or  a  SVM  (State  vector  machine)  is  able  to  compare  these  features  and  create  a  feature  set.  

 

Moreover   there   are   more   neural   network   approaches   like   and   Multi-­‐Network   Artificial   neural  networks  (Curilem,  M.),  which  combine  multiple  neural  networks  to  produce  more  effective  results  compared  to  single  neural  network  based  approach.  

References    

•  Aslaug  Haraldsdottir,  Principal  Investigator  Monica  S.  Alcabin  Alvin  H.  Burgemeister  Charles  G.  Lindsey  Nigel  J.  Makins  Robert  W.  Schwab  Arek  Shakarian  William  D.  Shontz  Marissa  K.  Singleton  Paul  A.  van  Tulder  Anthony  W.  Warren  (1997)  Air  Traffic  Management  Concept  Baseline  Definition,  China:  NEXTOR.    

•  Craig  Freudenrich,  Ph.D.  (2010)  How  Air  Traffic  Control  Works,  Available  at:http://science.howstuffworks.com/  (Accessed:  25  March  2014).    

•  Ajith  Abraham.  (2005).  Rule-­‐based  Expert  Systems.  Available:  http://2002.softcomputing.net/fuzzy_chapter.pdf.  Last  accessed  25th  Mar  2014.  

•  Oh-­‐han  Kang  Sang-­‐seong  Kang  (2006).  A  Web-­‐based  Toolkit  for  Scheduling  Simulation  Using  GridSim.  South  Korea:  Proceedings  of  the  Fifth  International  Conference  on  Grid  and  Cooperative  Computing  (GCC'06).  1  -­‐  3.    

•  Rajkumar  Buyya  and  Manzur  Murshed1.  (2008).  GridSim:  A  Toolkit  for  the  Modeling  and  Simulation  of  Distributed  Resource  Management  and  Scheduling  for  Grid  Computing.  Available:  http://arxiv.org/ftp/cs/papers/0203/0203019.pdf.  Last  accessed  1st  April  2014.    

•  Shinpei  Kato,  Karthik  Lakshmanan†  ,  and  Ragunathan  (Raj)  Rajkumar†  ,  Yutaka  Ishikawa.  (2008).  TimeGraph:  GPU  Scheduling  for  Real-­‐Time  Multi-­‐Tasking  Environments.  Available:  http://static.usenix.org/event/atc11/tech/final_files/Kato.pdf.  Last  accessed  20  Mar  2014.  

Dong,  F.,  Selim  G.  Akl  .  (2006).  Scheduling  Algorithms  for  Grid  Computing:  State  of  the  Art  and  Open  Problems  .  Technical  Report  No.  2006-­‐504  .  504  (0),  p1-­‐20.    T.H.   Davenport,   D.D.W.   Long,   M.C.   Beers,   Successful   knowledge   management   projects,   Sloan  Management  Review  1998  (1998)  43–58.  **  

Freiberg,   M.   (2012).   Extensible   Prototyping   for   pragmatic   engineering   of   knowledge-­‐based  systems.  Expert  Systems  with  Applications.  39  (11),  10177–10190.  

B.M.   Li,   S.Q.   Xie   ,   X.   Xu.   (2011).   Recent   development   of   knowledge-­‐based   systems,  methods   and  tools  for  One-­‐of-­‐a-­‐Kind  Production.Knowledge-­‐Based  Systems.  24  (7),  1108–1119.  

Rotolo,   A.   (2011).   Rule-­‐based   agents,   compliance,   and   intention   reconsideration   in   defeasible  logic.  Proceedings  of  RuleML,  Springer  

Ben-­‐David,   A.   (2008).   Rule   effectiveness   in   rule-­‐based   systems:  A   credit   scoring   case   study.  Expert  Systems  with  Applications.  34  ,  2783–2788.  

Chang,   L,   Zhou,   Y,   Jiang,   J,   Li,   M,   Zhang   X..   (2011).   Structure   learning   for   belief   rule   base   expert  system:  A  comparative  study.  Knowledge-­‐Based  Systems.  39  (3),  159-­‐172.  

Young,  S.,  Evermann,  G.,  Gales,  M.,  Hain,  T.,  Kershaw,  D.,  Liu,  X.,  Moore,  G.,  Odell,  J.,  Ollason,  D.,  Povey,  D.,  Valtchev,  V.,  Woodland,  P.,  .  (2006).  The  HTK  Book  (for  version  HTK  3.4).  Cambridge  University  Engineering  Department,  Cambridge.  

Garofolo,  J.S.,  Lamel,  L.F.,  Fisher,  W.M.,  Fiscus,  J.G.,  Pallett,  D.S.,  Dahlgren,  H.L.,  Zue,  V.,  .  (1992).  The  DARPA  TIMIT  acoustic  phonetic  continuous  speech  corpus  CDROM,  NTIS  order  no.  PB91-­‐100354..    

 

Chung,  J.R.,  Kwon,  J.,  Choe,  Y..  (2009).  Evolution  of  Recollection  and  Prediction  in  Neural  Networks.  Proceedings  of  International  Joint  Conference  on  Neural  Networks,  Atlanta,  Georgia,  USA.  19  ,  p571-­‐577.  

Curilem,  M.  Chacón,  M.  ;  Acuña,  G.  ;  Ulloa,  S.  ;  Pardo,  C.  ;  Defilippi,  C.  ;  Madrid,  A.M..  (2010).  Comparison  of  Artificial  Neural  Networks  an  Support  Vector  Machines  for  Feature  Selection  in  Electrogastrography  Signal  Processing.  32nd  Annual  International  Conference  of  the  IEEE  EMBS  Buenos  Aires,  Argentina.  0  (0),  p2774  -­‐  2777.  

Manette,  O.F.,  Inserm,  P.,  Maier,  M.A..  (2006).  Back  to  Results  TempUnit:  A  bio-­‐inspired  neural  network  model  for  signal  processing.International  Joint  Conference  on  Neural  Networks  Sheraton  Vancouver  Wall  Centre  Hotel,  Vancouver,  BC,  Canada.  p3144  -­‐  3151.  

Shahamiri  ,S.R.,  Salim,  S.S.B..  (2014).  Real-­‐time  frequency-­‐based  noise-­‐robust  Automatic  Speech  Recognition  using  Multi-­‐Nets  Artificial  Neural  Networks:  A  multi-­‐views  multi-­‐learners  approach.Neurocomputing.  129,  p199-­‐207.  

Siniscalchi,  S.M.,  Yu,  D.,  Deng,  L.,  Lee,  C.H..  (2013).  Exploiting  deep  neural  networks  for  detection-­‐based  speech  recognition.Neurocomputing.  106  (0),  p148-­‐157.  

Ting,  H.N.,  Yong,  B.F.,  Mirhassani,  S.M..  (2013).  Self-­‐Adjustable  Neural  Network  for  speech  recognition.  Engineering  Applications  of  Artificial  Intelligence.  26  (0),  2022–2027.