SAMPLE QUESTION PAPER

ARTIFICIAL INTELLIGENCE (417)

Class X (Session 2022-2023)
Max. Time: 2 Hours Max. Marks: 50

General Instructions:

1. Please read the instructions carefully.

2. This Question Paper consists of 21 questions in two sections: Section A & Section B.

3. Section A has Objective type questions whereas Section B contains Subjective type questions.

4. Out of the given (5 + 16 =) 21 questions, a candidate has to answer (5 + 10 =) 15 questions in the

allotted (maximum) time of 2 hours.

5. All questions of a particular section must be attempted in the correct order.

6. SECTION A - OBJECTIVE TYPE QUESTIONS (24 MARKS):

i. This section has 05 questions.

ii. Marks allotted are mentioned against each question/part.

iii. There is no negative marking.

iv. Do as per the instructions given.

7. SECTION B - SUBJECTIVE TYPE QUESTIONS (26 MARKS):

i. This section has 16 questions.

ii. A candidate has to do 10 questions.

iii. Do as per the instructions given.

iv. Marks allotted are mentioned against each question/part.

Section A: OBJECTIVE TYPE QUESTIONS

Q. 1 Answer any 4 out of the given 6 questions on Employability Skills (1 x 4 = 4 marks)

i. _____________ installs itself on the computer without the user’s knowledge and monitors
confidential information and forward it to the malicious owner of such program.

a. Spam b. Pharming

c. Spyware d. Firewall

ii. Shreya is able to adapt to the changing situations and manage time accordingly, deliver with short
timelines and knows how to utilise time effectively. Which of the following skills does she have?
a. Communication and negotiation b. Handling failure

c. Knowing oneself d. Agility

iii. Mr. Sharma is a stock broker, he is always in a fear of impending disaster of financial loss that leads
to insomnia and chronic anxiety. Which type of stress is he suffering from?

a. Internal distress b. Eustress

c. Surrounding distress d. All of these

iv. Raman is the owner of the space rocket company; he decided to send an unmanned rocket to
Mars but he failed to do so. He apologised to the employees of his company and said that he will
plan better next time. He showed which of the following qualities?
a. Take responsibility b. Do not give up
c. Impatient d. Both a & b

v. Mohan is the founder of an IT company which deals in developing web applications. He has a
creative and skillful team, but there is always a conflict of reward among the team members. Which
of the following quality he must have to resolve the conflict?
a. Risk-taking b. Empathetic
c. Open to knowledge d. Confidence

vi. Which of the following virus changes its program structure every time it makes a copy to avoid
detection?
a. Macro b. Stealth
c. File d. Boot sector
Q. 2 Answer any 5 out of the given 6 questions (1 x 5 = 5 marks)

i. Anurag is a retrospective, self-evaluating person and interested in philosophy. Which of the

following types of intelligence does he have?

a. Linguistic b. Kinaesthetic

c. Intrapersonal d. Interpersonal

ii. Ethical principles serve as a guideline to distinguish between ___________ and _____________.

a. Wrong, right b. Pass, fail

c. Success, failure d. None of these

iii. Products and services can be recommended to the user by an AI-enabled system depending on
the users __________________________.

a. Day b. Time of the day

c. Location d. All of these

iv. Which of the following is/are not the application of artificial intelligence?

a. Analyses customer feedback d. Digital marketing

c. Segregate email d. Promote cyber bullying

v. Sam frequently uses voice interface based assistants for playing music and other web searches. He
is using a ___________ artificial intelligence.

a. Narrow b. Generalised

c. Strong d. all of these

vi. A/An _______________________ is capable of learning and retaining knowledge by constant

exposure of data.

a. Artificial neuron b. 128-neuron system

c. Artificial brain d. None of these

Q. 3 Answer any 5 out of the given 6 questions (1 x 5 = 5 marks)

i. In the data set, the amount paid is not there in some records. These values are _______________
values and can be ________________.

a. Numeric, calculated b. Missing, omitted

c. Missing, calculated d. Numeric, omitted

ii. Data exploration is necessary because data available from data _______________ cannot be used
directly for machine learning.

a. Scoping b. Acquisition

c. Analysis d. Processing

iii. Raw acquisition gives us ______________ data while data exploration provides us __________
data.

a. Raw, training b. Raw, testing

c. Clean, graphical d. Clean, dynamic

iv. For a computer system, every piece of data has to be represented in some form of _________
expression.

a. Mathematical b. Artificial

c. Pixel d. Logical

v. in which of the following approaches, machines are on their own to analyse data and see trends
and patterns in it?

a. Rule b. Learning

c. Both a) and b) d. None of these

vi. In regression, correlation is not found if values of predicted variable _____________ with the
change in the predictor variable.

a. Increases b. Decreases

c. Both a) and b) d. Does not change

Q. 4 Answer any 5 out of the given 6 questions (1 x 5 = 5 marks)

i. Varun is a busy entrepreneur and every morning he is in too much of a hurry to read all the news.
His friend suggested him to install an app on his phone which presents the latest news in short bullet
points on his device which helps him to keep abreast of the latest happenings. Then, he can decide to
later read the news of his interest in detail. Which of the following applications help Varun in this?

a. CV with Image summarization b. NLP with text summarization

c. Machine translation d. Chatbot

ii. An online banking service needs its customers to avail unattended, zero-human-intervention
features in which customers are helped instantly with their common queries. Which is the most
suitable way to achieve this?

a. Call center b. Help videos

c. Chatbot d. Blog

iii. In a corpus of 10 documents, a term appears a total 50 times in overall 5 documents. Which of
the following combinations of calculations is correct.

a. DF=5, IDF=2 b. DF=50, IDF=5

c. DF=2, IDF=5 d. DF=10, IDF=50

iv. Interaction between humans and machines through the exchange of speech and voice is enabled
by the techniques of __________________.

a. Data Sciences b. NLP

c. CV d. ML

v. Which of the following in an NLP application is not concerned with normalising the text for the
purpose of document classification?

a. Syntax of the text b. Semantics of the text

c. Both a) and b) d. Number of documents

vi. Which of the following is correct about tokens with higher frequency in a corpus?

a. Tokens with higher frequency have lower value.

b. Tokens with higher frequency have higher value.

c. Tokens with higher frequency have higher DF.

d. Tokens with higher frequency have lower DF.

Q. 5 Answer any 5 out of the given 6 questions (1 x 5 = 5 marks)

i. A model was deployed to predict extreme low temperatures in the far northern region of India. It
predicted sub-zero temperatures all the time and 98% of the predictions matched reality. What kind
of predictions are these?

a. False Positive b. True Positive

c. False Negative d. True Negative

ii. Which of the following does precision calculation of a model not take into consideration?

a. True positives b. False negatives

c. True negatives d. False positives

iii. There are 100 patients examined for heart disease. Out of that, 60 patients actually have heart
disease. The model correctly predicted heart disease for 40 patients and incorrectly predicted heart
disease for 10 patients. What will be the precision of this scenario?

a. 0.9 b. 80

c. 90 d. 0.8

iv. In case of a flood to be predicted, loss of lives and property may occur if which of the following is
overlooked in evaluating the prediction model?

a. False negative b. False positive

c. True negative d. True positive

v. Which of the following statements is not correct about precision?

a. Precision takes into account True Positives as well as False Positives.

b. Low precision leads to false alarms in case of predicting a disaster or calamity.

c. Both a) and b)

d. Precision does not take into account the false prediction cases.

vi. When a model predicts that an email is a spam and it is a spam in reality then in which of the
following parts of the confusion matrix should this be recorded?

a. At the intersection of Yes of Prediction and Yes of Reality

b. At the intersection of Yes of Prediction and No of Reality

c. At the intersection of No of Prediction and No of Reality

d. At the intersection of No of Prediction and Yes of Reality

SECTION B: SUBJECTIVE TYPE QUESTIONS

Answer any 3 out of the given 5 questions on Employability Skills (2 x 3 = 6 marks)

Answer each question in 20 – 30 words.

Q. 6 What do you mean by the term self-management?

Ans. Managing oneself in order to achieve desired goals and targets is called self-management. Every
task we do has a thought process behind it. This gives birth to a plan to follow in order to accomplish
that task. Self-management.
Q. 7 List 2 tips to manage environmental stress.

Ans. a. Take nature walks or early morning walks to relax your mind and re-energise your body.

b. Participate in community activities that help in improving environment and surroundings like
anti-pollution drive, swachhta abhiyaan activities etc.

Q. 8 List any 2 practices to keep your computer work smoothly for a longer time?

Ans. a. Regularly maintain computer by running computer maintenance utilities, anti-viruses and
operating system updates.

b. Use genuine software and avoid accessing unknown resources, websites and emails when online.

Q. 9 What is the coordination role of an entrepreneur?

Ans. An entrepreneur coordinates many things such as factors of production, delegated tasks,
smooth functioning across different business departments, timely delivery of inputs and outputs etc.
and makes use of under-utilized resources in an economy.

Q. 10 What do you understand about the term ‘ Becoming Franchisee’?

Ans. Many businesses follow a franchising framework to grow their business. Advantages of taking a
franchisee of a business that you save a lot of time and effort in establishing the business. As a
franchisee, you get a ready setup with facilities like training, sales support, branding and guidance
with flexible payment options.

Answer any 4 out of the given 6 questions in 20 – 30 words each (2 x 4 = 8 marks)

Q. 11 What is the difference between interpersonal and intrapersonal intelligence?

Ans. Interpersonal intelligence enables the person socially more interactive as compared to the
person who has intrapersonal intelligent. Interpersonal intelligence tends to be more communicative,
outgoing and having a large circle of friends. Intrapersonal intelligence tends to be retrospective and
reflective. Such persons are quiet and thinkers.

Q. 12 What is an ANN?

Ans. Artificial neural network is composed of input layer, output layer and one or multiple hidden
layers which process the output coming from input layer and other layers. The output is finally
passed on to output layer.

Q. 13 What do you mean by problem scoping?

Ans. A problem scope is mutual understanding of all stakeholders about what is to be done to solve
that problem. Problem scoping gives a clear vision of the problem which is otherwise very abstract
and undefined. It also distinctly defines what will be the outcomes of entire problem-solving
exercise.
Q. 14 What do you mean by the term NLP?

Ans. NLP stands for Natural Language Processing - the third domain of artificial intelligence. It deals
with the natural language-based interaction between humans and machines or between two
machines. In this domain the machines with ability to process and learn from natural language data
are developed.

Q. 15 What is the basic difference in the working of a script-bot and smart bot?

Ans. A script-bot runs on a predefined script hence it has a limited functionality and it lacks language
processing capability so it cannot learn from the interactions and data. On the other hand, smart bot
is AI-based loaded with algorithm trained and tested with data and is capable to process natural
language to learn from more data for better performance.

Q. 16 What is the significance of calculating IDF?

Ans. For any term the IDF is calculated as: Document count in the corpus / Document Frequency of
that term. E.g. if a term hunger appears in 5 documents and there are 20 documents in the corpus
then IDF will be 20/5 = 4. IDF is important to calculate TF-IDF of the terms to determine their
importance in the document.

Answer any 3 out of the given 5 questions in 50– 80 words each (4 x 3 = 12 marks)

Q. 17 Write a note explaining the terms - ethics, ethical AI and unethical AI.

Ans. A set of governing moral principles is called ethics. The principles and morals that govern
someone’s behaviour is referred to ethics for that individual. Ethical principles serve as a guideline to
distinguish between wrong and right while making decisions. An ethical AI system must be developed
around the ethical guidelines of a society or people it is going to influence. An ethical reference is a
must in place while developing intelligent machines and conceiving their relationships with humans.
An ethical AI system is not-biased, it sets 38 the accountability correctly for responsible people, it is
transparent, it maintains security about data and identity. It respects people’s privacy and rights. An
ethical AI system takes care of human dignity and values. An AI system that does not care for above
things is an unethical AI.

Q. 18 Describe the role of AI in Electronic industry or Research and Development.

Ans. Electronics Industry: This generation is 5th generation (5G) of AI-based micro-processors
enabling features like self-fault-diagnostic, self-alert systems, television that adapts to our channel
choice, cars with better safety features and fuel efficiency etc. Such devices would be able to
connect with a network for better performance - this is termed as Internet of Things (IoT). Robotics
is also a primary field for many industries like automotive, hospital and defence as major players.

Research and Development: AI has tremendous potential to impact research and development in
all the fields. AI systems are capable to process big data faster and generate useful patterns and
predictions. The Natural Language Processing capability can help in voice-based search and process
audio and sound inputs. Computer Vision capability helps in processing visual data and
image-based research and intelligent predictions. Deep Learning can revolutionize visual search,
photograph recognition, 3D designs and physical world design to aid in intelligent research.
Q. 19 Describe briefly any 5 data quality features.

Ans. Five data quality features are:

a. Relevance: Data should not be out of context. Only the data values relevant to the problem must
be acquired.

b. Accuracy: Data values should be correct and without missing values.

c. Volume: Higher the volume of data, better would be the training of the machine. There will be
sufficient data for testing the model also.

d. Format: In many AI applications different data formats also help in better training of the machine.
AI system needs a variety of combination of data depending on the domain and problem scoping.

e. Data source: Data accuracy depends on the source from which the data is collected. For example,
data collected from public domain like Internet may not be authentic while data collected from an
authorised source such as a government or certified organisation.
Q. 20 A school has observed a decline in the performance of the average-performing students in
previous 3 monthly tests in Math. The better-performing students have performed satisfactorily.
School needs a system to predict the performance of all the students in Math by analysing the
performance data of previous tests.

Consider the above scenario and answer the following questions:

a. Who are the stakeholders? What do we know about them?

b. What is the exact problem?

c. How the solution will add value to the school system?

d. Create the 4W framework template.

Ans. a. Stakeholders: Students and school. Average-performing students are underperforming but
better performing students are doing fine.

b. In the past 3 monthly tests of Math, the performance of average-performing students has declined
more.

c. The early warning from the predictions will help the school to devise corrective measures to help
students prepare well for tests and improve in overall result.

d. 4W Framework:

Our students WHO

are facing problem that In past 3 monthly tests of Math, the WHAT

performance of average-performing students

has declined more.

Occurs when students write tests for Math WHERE

The ideal solution would be A system that predicts performance of all WHY

the students in Math by analysing the previous

performance data.
Q. 21 With reference to the confusion matrix given here, explain the following:

a. True Positive

b. True Negative

c. False Positive

d. False Negative

Ans. a. True
positive means the
predicted event
actually occurred in
real as it was predicted. E.g. Model predicted that customer will return the product and customer did
so (the first square).

b. True negative means the predicted event actually did not occur in real as it was predicted not to
occur. E.g. Model predicted that customer will not return the product and customer did not return
the product.

c. False positive means the predicted event actually did not occur in real as it was predicted to occur.
E.g. Model predicted that customer will return the product but actually customer did not do so.

d. False negative means that the predicted event did occur while it was predicted not to occur by the
model. E.g. Model predicted that customer will not return the product but customer returned the
product.
 For Visually Impaired Students

Q. 21 Consider the confusion matrix given here. Answer the following questions:

a. Calculate accuracy.

b. Calculate precision

c. Calculate recall

d. Calculate F1 score

e. Discuss whether this model should be deployed or not.

Ans. a. Accuracy = (20 + 100) / (20 + 12 + 45 + 100) = 120/177 = 0.677

b. Precision = 20 / (20 + 12) = 20 / 32 = 0.625

d. F1 score = 2 * (0.625 * 0.307) / (0.625 + 0.307) = 0.4

c. Recall = 20 / (20 + 45) = 20 / 65 = 0.307

e. F1 score is very low (max should be 1.0) so model cannot be deployed.