Page 207 - AI Ver 1.0 Class 9
P. 207

On receiving the data, you realise that it is not uniform. The images are of varied size and types, with or
                 without mask, etc. Also, some images are missing while some have multiple copies. Thus, you think of
                 putting all the data received in a simplified format for which you choose one:
                 a.  Will try to remember all the faces in the images.
                 b.  Place all the photographs in a graph and try to interpret a pattern out of it.

                 c.  Create a database to store the image data.

                 d.  Make a table and put the names of people whose photographs are with you.
                 After analysing the data, now you know that you need to develop a system, which can detect the face of
                 a person entering the plane and match it with the existing image database you have in the system. For
                 this, you put all the data into the AI-enabled model and train it in such a way that it alerts the officials if
                 any unauthorised person tries to enter the plane. To implement this, list down the components of your
                 system below:

                 1.
                 2.

                 3.
                 4.

                 5.
                 Your  security  system  is  now  ready,  and  you  test  it  by  sending  a  combination  of  authorised  and
                 unauthorised people to the plane. You achieve the result of 78% accuracy. After evaluating your model,
                 you work on other AI algorithms shortlisted by you.

                 You test the algorithms to:






                 After proper testing, you deploy your security system at the Airport around all the entrances of the
                 plane. The criminals, who intended to carry out the escape plan, got caught as they were not aware of
                 the security system deployed by you. You were successful in averting the escape and helped take the
                 criminal to his home country to be tried for his wrong doings.

                 Congratulations! Mission Completed!



                    Summary—AI Project Cycle


            We discussed all the stages of an AI project cycle in detail. The project cycle starts with identification of a problem
            and ends at the deployment of a successful model. The whole cycle can be summarised in the following manner:

            1.  Firstly, identify the problem for which an AI model needs to be made.
            2.  Acquire data from various reliable and authentic sources that will be the base of your project as it will help in
               understanding the requirements.




                                                                                      AI Project Cycle  205
   202   203   204   205   206   207   208   209   210   211   212