ARMY PUBLIC SCHOOL, KOTA

PRE-BOARD EXAMINATION (2024-25)

CLASS- X (ARTIFICIAL INTELLIGENCE) SET: II
Time: 3 Hrs Max. Marks: 50

Section A: Objective Type Questions

Q -1 Answer any 4 out of given 6 questions on Employability skills. (1 x 4=4)

i. __________ is a force within an individual which drives people to do the things. 1

(Answer: Motivation)

ii. Shiv has selected a folder in D: drive. He clicked on the folder and hold mouse button down then moved
it to new location then he released the mouse button. Here Shiv has performed which of the following mouse
action? 1
a) Hover
b) Double click
c) Drag and Drop
d) Selection
(Answer: c)

iii. Assertion (A): Prajakta has her own beauty saloon in her local areas. She hired two women in her saloon.
Reason(R): She is helping society to grow. 1
(a) Both A and R are correct and R is the correct explanation of A
(b) Both A and R are correct but R is NOT the correct explanation of A
(c) A is correct but R is not correct
(d) A is not correct but R is correct
(Answer: a)

iv. Dhruvin is preparing for exam. He avoids time wasters like chatting on phone, surfing gossip sites etc.
and focus on more important things. This is one of the steps of effective time management, identify the
same: 1
a) Organizing
b) Prioritising
c) Controlling
d) Tracking
(Answer: b)

v. Avee is working as team leader. He sent a message on WhatsApp for a short meeting after their dispersal
in office. But many of his team members not attended the meeting. This is an example of __________ 1
a) Physical Barrier
b) Cultural Barrier
c) Organization Barrier
d) Linguistic Barrier
(Answer: d)

vi. _____________ is the development that satisfies the needs of the present without compromising the
capacity of future generations, guaranteeing the balance between economic growth, care for the environment
and social well-being. 1
a) Social Development
b) Sustainable Development
c) Financial Development
 d) Cultural Development
(Answer: a/b)

Q – 2 Answer any 5 out of the given 6 questions (1 x 5 = 5)

i. Assertion (A): Life without machine is unimaginable today.

Reason(R): Machines are made with an intent of irritating humans. 1
(a) Both A and R are correct and R is the correct explanation of A
(b) Both A and R are correct but R is NOT the correct explanation of A
(c) A is correct but R is not correct
(d) A is not correct but R is correct
(Answer: c)

ii. Kriza is planning for a trip in Kerala in winter break. She searched hotels for the same. After that she is
getting notification about the same and advertisements in websites, apps and many more. Which of the
following term is perfectly match with this example? 1
a) AI Access
b) Data Privacy
c) AI Ethics
d) AI Manners
(Answer: a)

iii. A ____________ is essentially a system of organizing machine learning algorithms to perform certain
tasks. 1
a) Natural Networks
b) Neutral Networks
c) Neural Networks
d) Neuron Networks
(Answer: c)

iv. In neural network __________ layers, the processing occurs.

a) Input
b) Hidden
c) Output
d) Top
(Answer: b)

v. __________ is a domain-specific language used in programming and is designed for managing data held
in different kinds of data structure. 1
a) CSV
b) Python
c) Spreadsheet
d) SQL
(Answer: d)

vi. Which of the following text normalization step considers every word, number or special character
separately? 1
a) Sentence Segmentation
b) Tokenization
c) Stemming
d) Lemmatization
(Answer: b)

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

i. Statement A - In today’s time, every technology around us is AI.
Statement B - An AI machine too gets trained first on the training data and then optimises itself according to
its own experiences. 1
a) A is correct
b) B is correct
c) Both are correct
d) Both are incorrect

(Answer: b)

ii. In most of the virtual assistants female voices are more preferred over any other voice. This is an example
of _______________ 1
a) AI Bias
b) Gender Specification
c) Voice Filter
d) Neural Network
(Answer: a)

iii. Which of the following domain of AI is working around alphanumeric information, numbers and
statistics? 1
a) Data Science
b) NLP
c) CV
d) Neural Network
(Answer: a)

iv. As humans have eyes, so they can see anything and analyse it. Select an appropriate option which adds a
functionality like that in machines? 1
a) Natural Language Processing
b) Computer Vision
c) Data Science
d) Evaluation
(Answer: b)

v. All the virtual assistants like Alexa, Google Assistants, Siri etc. can taken as _____________ 1
a) Smart Bot
b) Script Bot
c) Robot
d) Programming Bot
(Answer: a)

vi. The recorded result of comparison between prediction and reality is known
as __________ 1
a) Precision
b) F1 Score
c) Confusion Matrix
d) Accuracy
(Answer: c)

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

i. Which of the following states intention of machine learning? 1

a) Ability to machine to recognize human’s face, move objects and understand, command given by
humans then perform the tasks
 b) Enable machines to learn by themselves using the data provided and make accurate
predictions/Decisions
c) Machine is trained with huge amounts of data which helps to train data
d) Enable machines to write algorithm
(Answer: b)

ii. Which of the following is the final stage of AI Project cycle? 1

a) Problem Scoping
b) Data Acquisition
c) Evaluation
d) Data Exploration
(Answer: c)

iii. Extracting data can be offense. 1

a) Yes
b) No
c) May be
d) None
(Answer: a/c)

iv. Every photograph is in digital form is made up of _______ 1

a) Lines
b) Dots
c) Pixels
d) Graphs
(Answer: c)

v. Spam filtering is an example of 1

a) Text Classification
b) Automatic Summarization
c) Sentiment Analysis
d) Bag of words
(Answer: a)

vi. Observe the given images: 1

In above diagram, what the dots represents:

a) Actual Output
b) Samples
c) Model Efficiency
d) None of these

(Answer: b)
Q – 5 Answer any 5 out of the given 6 questions (1 x 5 = 5)

i. In Computer vision, input to machine can be 1

a) Numeric & Alphanumeric
b) Photographs, Videos
c) Spoken words only
d) Text
(Answer: b)

ii. The condition which predicts all predictions as No and reality is also No. this condition in known as
________ 1
a) True Negative
b) False Negative
c) Negative True
d) All Negative
(Answer: a)

iii. Which of the following domain of AI is used by the airlines companies for strategic areas of
improvements: 1
a) Data Science
b) Computer Vision
c) Natural Language Processing
d) Neural Network
(Answer: a)

iv. Which of the following is the first step of bag of words algorithm? 1
a) Create Dictionary
b) Text Normalization
c) Create Document vectors
d) Stemming
(Answer: b)

v. Which of the process removes the affixes from the corpus? 1

a) Overfitting b) Stemming c) Underfitting d) Accuracy

(Answer: b)

vi. Which one of the following scenario result in a high false negative cost? 1
(a) Viral Outbreak
(b) Spam Filter
(c) flood
(d) Mining

(Answer: a)

Section B: Subjective Type Questions

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

Answer each question in 20-30 words.

Q – 6 What are the various elements of communication cycle? 2

(Answer: The communication cycle involves a series of steps or elements that facilitate effective
communication between a sender and a receiver. The key elements of the communication cycle are Sender,
Message, Encoding, Channel, Receiver, Decoding, Feedback and Noise.)

Q – 7 Mr E Shreedharan, Former Managing Director, Delhi Metro Rail corporation Ltd, was a self-
motivated and energetic person. What are the steps for building self-motivation? 2

(Answer: Building self-motivation involves developing habits and mindsets that inspire and sustain
personal drive and action. Here are the key steps to build self-motivation:

1. Set Clear and Achievable Goals

2. Find Your "Why"
3. Visualize Success
4. Create a Positive Environment
5. Take Small Steps
6. Maintain Discipline and Consistency
7. Stay Focused on the Present
8. Develop a Growth Mindset
9. Reward Yourself
10. Track Your Progress)

Q – 8 Enlist and explain the major type of computer viruses in short. 2

(Answer: Boot Sector Virus: These viruses infect the master boot record (MBR) or boot sector of a hard
drive or removable media (e.g., USB drives). They get activated when the computer is booted from the
infected device.
Trojan Horse: A Trojan horse masquerades as a legitimate program or file to deceive users into executing
it. Once activated, it can cause harm, steal data, or provide unauthorized access.
Worm: Worms are self-replicating viruses that spread without needing to attach to a host program. They
often exploit vulnerabilities in network security and can spread rapidly through systems connected to the
internet.
Ransomware: Ransomware is a type of malware that encrypts the victim’s files or locks them out of their
system and demands a ransom to restore access to the files or system.
Spyware: Spyware is software that secretly collects information about a user’s activities, often without their
knowledge or consent. It can track browsing habits, keystrokes, and personal data.
)

Q – 9 How entrepreneur helps society? What they do when they run business? 2
(Answer: Entrepreneurs play a crucial role in helping society in various ways. Their actions in running a
business go beyond just creating products or services; they contribute to the economy, social well-being, and
overall progress. Here's how they help society:
1. Creating Jobs:
2. Economic Growth:
3. Innovation and New Solutions:
4. Fostering a Competitive Market:
5. Wealth Creation:
6. Addressing Social Issues:
7. Contributing to the Local Community:
8. Increasing Tax Revenue:

What Entrepreneurs Do When They Run a Business:

Identify Opportunities: Entrepreneurs spot gaps in the market, identify consumer needs, and develop
innovative solutions to fill those gaps.
Develop a Business Plan: They create detailed plans that outline the vision, mission, strategy, financial
projections, and goals of the business.
Risk Management: Entrepreneurs take calculated risks, often using their own resources or seeking external
funding. They deal with uncertainties and find ways to manage or mitigate risks.
Market and Promote: Entrepreneurs develop marketing strategies, create brand awareness, and engage
customers through various channels to promote their products or services.
Scale and Grow: Entrepreneurs look for opportunities to expand their business, whether by entering new
markets, increasing production capacity, or diversifying their product range.
Leadership and Team Building: Entrepreneurs lead their teams, build strong company cultures, and make
key decisions that shape the direction of the business.
)

Q – 10 What do you mean by organic farming? Explain in short. 2

(Answer: Organic farming refers to a method of farming that involves growing crops and raising livestock in
an environment-friendly and sustainable manner, without the use of synthetic chemicals, pesticides, or
fertilizers. It emphasizes the use of natural processes and resources to promote soil health, biodiversity, and
ecosystem balance.)

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

Q – 11 Identify the intelligence demonstrating by the people: 2

a) Shreshthi is very good dancer. She is using her body for perfect moves
b) Krishna is writing poems. He is able to find the meaning words, the orders of words, inflection
and meter of words.
c) Dev is an accountant in a multinational company. He is very talented in the field of accounts and
managing the company’s finance effectively.
d) Mr. Shivanand is a politician. He has good ability to interact to others.
(Answer: a) Bodily-Kinesthetic Intelligence
b) Linguistic Intelligence
c) Logical-Mathematical Intelligence
d) Interpersonal Intelligence)

Q – 12 Observe the below given graph and explain the model in short. 2

(Answer: A classification model is a type of machine learning model that is used to predict the category or
class to which a given data point belongs. The goal of classification is to assign labels (classes) to new
observations based on a trained model.
Example of a Classification Problem: Email Classification: Classifying emails into two categories: "spam"
or "not spam." The input features could be the words in the email, and the model would predict whether the
email belongs to the "spam" class or the "not spam" class.)
Q – 13 How data science is useful in genetics and genomics? 2
(Answer: Data science plays a crucial role in genetics and genomics by helping researchers and healthcare
professionals analyze and interpret the vast amounts of data generated in these fields. Genetics and genomics
involve studying the DNA, genes, and genomes of living organisms, which requires managing, analyzing,
and drawing insights from large, complex datasets. Here's how data science is useful in these areas:
Genomic Sequencing: With advances in technology, large-scale genomic sequencing (e.g., whole genome
sequencing, RNA sequencing) generates massive datasets.
Predicting Disease Risk: Data science models, particularly machine learning, can predict an individual's
susceptibility to genetic disorders by analyzing their genetic makeup.)

Q – 14 Computer vision plays a vital role in making the home smarter. How? 2
(Answer: Computer Vision plays a crucial role in making homes smarter by enabling devices and systems to
visually perceive, interpret, and understand the environment around them.
1. Home Security and Surveillance:
Facial Recognition: Computer vision systems can recognize and authenticate individuals at the
entrance of a home, improving security. For example, smart doorbells
Intruder Detection: Security cameras equipped with computer vision can detect unusual movements,
differentiate between people and animals, and send alerts if an intruder is detected.
2. Gesture and Motion Control:
Gesture Recognition: Smart home devices like lights, TVs, or thermostats can be controlled using
gestures. For example, a user can wave their hand to turn on the lights or adjust the TV volume.
Motion Detection: Motion sensors powered by computer vision can be used for automatic lighting,
ensuring lights turn on when someone enters a room and off when the room is empty, thus saving
energy.)

Q – 15 Explain text classification with example. 2

(Answer: Text classification is a Natural Language Processing (NLP) task that involves categorizing a given
text into predefined categories or classes. The goal of text classification is to assign one or more labels to a
piece of text based on its content. It is a supervised machine learning problem, where a model is trained on
labeled data (i.e., text that has already been classified) to learn patterns and make predictions on new, unseen
data. Examples are
Sentiment Analysis: Classifying text as positive, negative, or neutral based on sentiment.
Spam Detection: Identifying whether an email is spam or not.)

Q - 16 What is accuracy? Explain along with formula. 2

(Answer: Accuracy is one of the most common and straightforward evaluation metrics used in machine
learning to assess the performance of a model. It measures the overall correctness of a model by comparing
the number of correct predictions to the total number of predictions made.

TP = True Positive
TN = True Negative
FP = False Positive
FN = False Negative
)

Answer any 3 out of given 5 questions in 50-80 words each: (4 x 3 = 12)

Q – 17 Explain any 4 applications of Artificial Intelligence around us.

(Answer: Here are four major applications of AI that are commonly found around us:
1. Virtual Assistants
Virtual assistants are AI-powered systems that use natural language processing (NLP) and machine learning
(ML) algorithms to understand and respond to human commands. They are widely used in smartphones,
smart speakers, and other connected devices to provide a range of services. (e.g., Siri, Alexa, Google
Assistant)
2. Recommendation Systems
Recommendation systems use AI and machine learning algorithms to analyze users' past behavior (like
watching history, purchase patterns, or browsing habits) to predict and recommend products, movies, music,
etc., that users might like. (e.g., Netflix, YouTube, Amazon)
3. Autonomous Vehicles
Self-driving cars use a combination of AI technologies, including computer vision, deep learning, and sensor
fusion, to navigate the roads and make driving decisions without human intervention. These vehicles can
process data from their surroundings to understand the environment and make decisions like stopping at
traffic lights, avoiding obstacles, or following traffic rules. (e.g. Self-Driving Cars)
4. Healthcare and Medical Diagnosis
AI is revolutionizing healthcare by enabling faster and more accurate diagnoses, personalized treatment
plans, and drug discovery. Machine learning algorithms analyze vast amounts of medical data, such as
patient records, lab results, medical imaging, and genetic information, to assist doctors in making informed
decisions.)

Q – 18 Nitya wants to acquire data from various sources for her new AI model. Explain her following:
a) Data Features b) Sources to collect data
(Answer: For Nitya to build her AI model, she needs to understand the following aspects of data acquisition:

a) Data Features
Data features refer to the individual measurable properties or characteristics of the data that will be used as
inputs for the model. These features are crucial for training the AI model and directly influence its ability to
make accurate predictions.
Examples of data features:
Numerical features: Quantitative data such as age, price, temperature, etc.
Categorical features: Qualitative data such as gender, country, product category, etc.
Text features: Data that contains text, such as customer reviews or social media posts.
Image features: Pixels or specific objects within an image (e.g., edges, colors).
Temporal features: Time-related data such as timestamps, dates, or time of day.
Geospatial features: Location-related data, such as latitude, longitude, or regions.

b) Sources to Collect Data

Nitya can collect data from several sources, depending on the nature of the AI model and the type of data
she needs. Here are some common sources:

Web Scraping:
Nitya can gather data by scraping websites using tools like BeautifulSoup, Scrapy, or Selenium. This is
useful for extracting data like product information, reviews, or news articles from publicly available
websites.
Example: Scraping news websites for article titles or scraping e-commerce sites for product information.

APIs:
Many platforms provide public APIs that allow developers to collect data programmatically. For example,
social media platforms like Twitter, Facebook, or Instagram offer APIs to access user-generated content.
Example: Using the Twitter API to collect tweets on specific topics or hashtags.

Surveys and Interviews:

Nitya can create surveys or conduct interviews to collect raw data directly from respondents. This approach
is suitable when she requires specific insights from a target group.
Example: Conducting a survey to gather customer opinions on a new product.

Company or Private Databases:

Many organizations store their internal data in databases, which can be accessed through direct queries or
with proper permissions. This includes transactional data, customer databases, or sales data.
Example: Accessing sales and customer information from a company’s CRM system to build a predictive
model for customer behavior.

Crowdsourcing:
Platforms like Amazon Mechanical Turk allow users to collect data by outsourcing tasks to a large number
of workers. This can be useful for labeling data, collecting user feedback, or gathering information from
various sources.
Example: Crowdsourcing data labeling for image classification tasks.

Sensor and IoT Data:

If working with a physical environment, Nitya can collect data using sensors or IoT devices that track things
like motion, temperature, pressure, etc.
Example: Collecting environmental data for smart city projects or monitoring equipment for predictive
maintenance.)

Q – 19 Observe the following images and explain the related models:

(Answer: A regression data model is a type of predictive modeling technique used in statistics and machine
learning to analyze and predict the relationship between a dependent (target) variable and one or more
independent (predictor) variables. The goal is to model this relationship so that you can make predictions or
understand the underlying patterns in the data.
Applications of Regression Models
Predicting future trends, such as stock prices, house prices, or sales forecasts.
Understanding relationships between variables (e.g., how marketing spend affects sales).
Risk assessment and decision-making in various industries (e.g., finance, healthcare, etc.).)

Q – 20 Explain the following with respect to normalization with example:

a) Sentence Segmentation b) Tokenisation
(Answer: Normalization in the context of natural language processing (NLP) involves standardizing text
data to improve the consistency and quality of the input for machine learning models.

a) Sentence Segmentation
Definition: Sentence segmentation is the process of splitting a given text into individual sentences. It's a
crucial first step in many NLP tasks because it allows models to process the text at the sentence level rather
than the paragraph or document level. This helps in understanding and analyzing the structure of the text
more effectively.
Normalization in Sentence Segmentation: During sentence segmentation, normalization typically involves:
Identifying sentence boundaries, such as punctuation marks (periods, exclamation marks, question marks).
Example: Consider the following text:

Original Text: "Dr. Smith went to the store. He bought some groceries."

After Sentence Segmentation:

Sentence 1: "Dr. Smith went to the store."

Sentence 2: "He bought some groceries."
Here, sentence segmentation splits the text at the period (".") while avoiding splitting on the abbreviation
"Dr.".

b) Tokenization
Definition: Tokenization is the process of breaking text into smaller units, called tokens. Tokens are
typically words, subwords, or characters. Tokenization is one of the most fundamental tasks in NLP because
it enables models to work with a sequence of words rather than raw text.

Normalization in Tokenization: Tokenization involves normalizing the text in the following ways:

Splitting the text into tokens.

Removing irrelevant characters (like extra spaces, special symbols, etc.).
Converting words to a consistent format (like converting all letters to lowercase or handling contractions).
Example: Consider the sentence:

Original Text: "I can't believe it's raining!"

After Tokenization:

Tokens: ["I", "can't", "believe", "it", "'s", "raining", "!"]

In this example, tokenization splits the text into individual words and punctuation marks, including breaking
down contractions ("can't" into "ca" and "n't").

Q – 21 An AI model made the following match winning prediction for a cricket match:

Reality(T) Reality(F)
Prediction(T) 23 22
Prediction(F) 11 12

a) Identify the correct predictions and wrong predictions made by machine

b) Calculate precision, recall and F1 score.

(Answer:
a) Correct and Incorrect Predictions:
True Positives = 23
False Positives =22
False Negatives = 11
True Negatives = 12
Summary:
Correct Predictions = True Positives (23) + True Negatives (12) = 35
Wrong Predictions = False Positives (22) + False Negatives (11) = 33

b) Precision, Recall, and F1 Score Calculation:

Precision: Precision is the fraction of correctly predicted positive instances out of all instances predicted as
positive.

Recall: Recall is the fraction of correctly predicted positive instances out of all actual positive instances
(Reality T).

F1 Score: The F1 score is the harmonic mean of precision and recall, providing a balance between the two.