Time Allowed: 2 hours

Maximum 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):
This section has 05 questions.
Marks allotted are mentioned against each question/part.
There is no negative marking.
Do as per the instructions given.

7. Section B : subjective type questions (26 marks):

This section has 16 questions.
A candidate has to do 10 questions.
Do as per the instructions given.
Marks allotted are mentioned against each question/part.

Section A : Objective Type Questions

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

(i) “Despite facing failures, John stayed focused and continued working on his vision for electric cars and
space exploration”. Which self-management skill does this statement highlight? [1]
Answer:
Persistence

(ii) What is the term used when you quickly click the left mouse button twice? [1]
(A) Hover
(B) Drag and drop
(C) Double clicking
(D) Moving
Answer:
(C) Double clicking

Explanation:
Double clicking is an action in which the user clicks quickly twice on an icon, usually to open it.

(iii) Assertion(A): In a free market, entrepreneurs bring change in technology, trends and markets.
Reason(R): Entrepreneurs are often at the forefront of technological innovation. [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:
(B) Both A and R are correct but R is NOT the correct explanation of A.

Explanation:
Entrepreneurs are catalysts for change in free markets, driving technological advancements, shaping
consumer trends and redefining market dynamics through their innovative endeavours. Their ability to
adapt, innovate and create value fuels economic progress and drives societal development.

(iv) High expectations from oneself can leave one with chronic anxiety and stress, thus leading to stress.
[1]
(A) physical
(B) emotional
(C) mental
(D) financial
Answer:
(C) mental

Explanation:
High expectations from self, setting unrealistic goals and exerting oneself beyond one’s capabilities
leads to mental stress.

(v) Anna, a project manager at a marketing firm, is tasked with presenting a new marketing strategy to
her team. To ensure its effectiveness, she follows a structured communication process. She drafts a
clear message, holds a team meeting to present the strategy, and then sends a follow-up email
summarising key points and next steps. This ensures the strategy is well understood and executed
effectively. Which stage of the communication cycle does Anna focus on when she drafts the message
about the new marketing strategy? [1]
(A) Encoding
(B) Decoding
(C) Feedback
(D) Transmission
Answer:
(A) Encoding

(vi) “Programs are implemented to promote the use of public transportation, reducing greenhouse gas
emissions and traffic congestion”. Which terminology suits best for this action?
Which SDG can you relate this statement to? [1]
(A) Sustainable cities and communities
(B) Affordable and clean energy
(C) Climate action
(D) Good health and well-being
Answer:
(A) Sustainable cities and communities

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

Question 2.
(i) Assertion(A): Different individuals can excel in different areas of intelligence.
Reason(R): Multiple intelligences theory explains that individuals have various types of intelligences,
which function independently of each other. [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) Both A and R are correct and R is the correct explanation of A.

(ii) AI developers must consider which ethical issue when creating algorithms that could potentially make
decisions about human lives in areas like healthcare and law enforcement? With an increase in the
number of neurons in each layer, the model’s accuracy.
(A) AI Access
(B) Data Privacy
(C) AI Bias
(D) AI Ethics
Answer:
(D) AI Ethics

(iii) Statement 1: The input layer of a neural network receives the initial data for processing.
Statement 2: The output layer is responsible for transforming input data into hidden representations.
(A) Both Statement 1 and Statement 2 are correct.
(B) Both Statement 1 and Statement 2 are incorrect.
(C) Statement i is correct but Statement 2 is incorrect.
(D) Statement 2 is correct but Statement 1 is incorrect.
Answer:
(C) Statement i is correct but Statement 2 is incorrect.

Explanation:
The input layer indeed receives the initial data, while hidden layers process the data to make predictions;
the final predictions are made in the output layer.

(iv) Identify the correct observation based on the graph:

With an increase in the number of neurons in each layer, the model’s accuracy ______.
Answer:
Increases

(v) _______ file format is commonly used for storing and exchanging data in a structured, tabular form?
[1]
(A) mp3
(B) pdf
(C) csv
(D) gif
Answer:
(C) csv

(vi) In a corpus of 10 documents, the word ‘sun appears 8 times across all documents. How would you
classify the
word sun? Ill
(A) Stop word
(B) Rare word
(C) Frequent word
(D) Removable word
Answer:
(C) Frequent word

Answer any 5 out of the given 6 questions (1 × 5 = 5 marks)

Question 3.
(i) Which of the following is an example of AI in daily life?
i. A photocopy machine duplicating documents
ii. Google Translate translating languages instantly
iii. A washing machine with a pre-set timer
iv. A chatbot answering customer questions
(A) i, ii, and iii
(B) ii and iv
(C) i, iii, and iv
(D) ii and iii
Answer:
(B) ii and iv

(ii) A decision-making process in AI that mimics the structure of the human brain is known as a ___
network.
Answer:
Neural

(iii) In which scenario is data science applied for predictive analysis?

(A) Weather forecasting
(B) Spell checking in documents
(C) Playing video games
(D) Formatting text in a document
Answer:
(A) Weather forecasting

(iv) _____ is the technique used to categorise an entire image into predefined classes.
(A) Instance segmentation
(B) Object detection
(C) Classification
(D) Image segmentation
Answer:
(C) Classification
Explanation: Classification assigns a label to an entire image based on its content, helping systems
understand the overall context, such as identifying an image as a “cat” or “dog”.

(v) Identify the chatbot type: It uses voice-based interactions, converting spoken language into text,
processing the query and delivering a spoken response. [1]
Answer:
Voice assistant chatbot

(vi) What does a high FI Score indicate about a model’s performance? [1]
(A) High Precision and low Recall
(B) Low Precision and high Recall
(C) A good balance between Precision and Recall
(D) Only good accuracy
Answer:
(C) A good balance between Precision and Recall

Answer any 5 out of the given 6 questions (1 × 5 = 5 marks)

Question 4.
(i) Rohan is studying AI concepts but struggles to remember the term that describes algorithms that
enable machines to learn from data without explicit programming. What is the term he is looking for? [1]
Answer:
Machine Learning refers to a subset of AI that involves algorithms allowing computers to learn patterns
from data and improve their performance on tasks without being explicitly programmed for each one.

(ii) Statement 1: A false positive means the model incorrectly predicts a positive outcome when it is
actually negative. Statement 2: A true negative indicates that the model has made an error in predicting a
negative outcome.
(A) Both Statement 1 and Statement 2 are correct.
(B) Both Statement 1 and Statement 2 are incorrect.
(C) Statement 1 is correct but Statement 2 is incorrect.
(D) Statement 2 is correct but Statement 1 is incorrect.
Answer:
(C) Statement 1 is correct but Statement 2 is incorrect.

Explanation:
A false positive is an incorrect positive prediction, whereas a true negative correctly identifies a negative
outcome with no errors.

(iii) Suresh is building a weather prediction model using weather data from the past five years. He knows
he must splif the data for training and testing. What is the purpose of using testing data? [1]
(A) To improve the model’s efficiency
(B) To check the accuracy of predictions
(C) To clean the data
(D) To collect more data for training
Answer:
(B) To check the accuracy of predictions

(iv) What is the purpose of image segmentation in computer vision? [1]

Answer:
Image segmentation divides an image into regions to simplify analysis and object detection.

(v) Which feature in NLP helps classify text into predefined categories like spam or non-spam? [1]
(A) Sentiment Analysis
(B) Text Classification
(C) Machine Translation
(D) summarisation
Answer:
(B) Text Classification

(vi) Meena created a model to classify plants by using data from her local garden. When tested on plants
from different regions, it couldn’t classify them accurately. What is the issue here? [1]
Answer:
Lack of a diverse dataset

Question 5.
Answer any 5 out of the given 6 questions. (1 x 5 = 5 marks)
(i) Nisha built an AI tool that helps doctors diagnose diseases by analysing medical images. This tool is
an example of which AI domain? [1]
(A) Data Science
(B) Robotics
(C) Computer Vision
(D) Natural Language Processing
Answer:
(C) Computer Vision
(ii) Which evaluation metric is particularly useful for imbalanced datasets? [1]
Answer:
FI Score balances precision and recall to provide a more informative measure of model performance.

(iii) A image uses shades of gray to represent variations in brightness, typically containing 256 levels of
intensity. [1]
(A) colour
(B) monochrome
(C) grayscale
(D) bitmap
Answer:
(C) grayscale

Explanation:
Grayscale images represent light intensity using shades from black to white. With 256 levels of intensity,
each pixel can represent a unique shade, allowing for detailed representation of brightness without
colour.

(iv) Which AI concept involves simulating human conversations? [1]

(A) Image Recognition
(B) Natural Language Understanding
(C) Reinforcement Learning
(D) Predictive Analytics
Answer:
(B) Natural Language Understanding

(v) Which technique involves converting text into a format that is easier for algorithms to process by
standardising it?
(A) Tokenisation
(B) Text normalisation
(C) Stop word removal
(D) Lemmatisation
Answer:
(B) Text normalisation

Explanation:
Text normalisation standardises text by converting it to a consistent format (e.g., lowercasing removing
punctuation), making it more manageable for analysis and improving the accuracy of NLP models.

(vi) If a model’s false positive rate is high, what might be a potential consequence? [1]
(A) More true positives
(B) Unnecessary resource allocation
(C) Increased customer satisfaction
(D) Higher accuracy
Answer:
(B) Unnecessary resource allocation

Section B : Subjective Type Questions

Answer any 3 out of the given 5 questions on Employability Skills.

Answer each question in 20-30 words.
Question 6.
Rohan is a customer service representative dealing with a frustrated customer who received a defective
product.Despite Rohan’s efforts to assist, the customer becomes increasingly agitated. How can Rohan
apply the principles of effective communication to diffuse the situation and provide satisfactory
assistance? What strategies can he use to address the customer’s concerns respectfully and effectively?
[2]
Answer:
Rohan can demonstrate consideration by actively listening to the customer’s grievances without
interrupting and acknowledging their frustration empathetically. He can use polite language and assure
the customer that their concerns are being taken seriously. Additionally, Rohan can offer solutions or
alternatives to resolve the issue promptly, demonstrating his commitment to providing excellent customer
service.

Question 7.
Explain the importance of taking nature walks. [2]
Answer:
Taking nature walks is important because they help reduce stress and improve our mood by connecting
us with the outdoors. Being in nature can boost creativity and increase our focus, making us feel more
refreshed. Additionally, it promotes physical activity, which is good for our health and well-being.

Question 8.
What is the role of the Start menu in Windows? What are its different sections? [2]
Answer:
The Start Menu is the main gateway to the programs, folders and settings on your computer. The Start
Menu can be used to do common activities such as start programs, open frequently used folders, search
for files, folders and programs, adjust computer settings, get help with the Windows operating system,
turn off the computer and log off from Windows or switch to a different user account.

Question 9.
It is believed that Entrepreneurs are high risk takers. Explain. [2]
Answer:
Entrepreneurs, often characterised as high-risk takers, embrace uncertainty and leverage opportunities,
potentially reaping substantial rewards from their ventures This risk-taking propensity enables them to
innovate, seize competitive advantages and ultimately drive growth and success in their enterprises.

Question 10.
Identify two agricultural activities that lead to soil erosion and discuss their effects on land fertility. [2]
Answer:
Two agricultural activities that lead to soil erosion are intensive ploughing and deforestation for farming.
Intensive ploughing disrupts the soil structure, making it more susceptible to erosion by wind and water.
Deforestation for farming removes vegetation that stabilises the soil, increasing erosion. Both activities
deplete the topsoil, which is crucial for nutrient-rich land, leading to reduced land fertility and lower
agricultural productivity.

Answer any 4 out of the given 6 questions in 20-30 words each. (2 × 4 = 8 marks)
Question 11.
Social media platforms use AI to suggest new friends or connections. What type of algorithm helps
identify these
potential connections? [2]
Answer:
Graph-based algorithms and machine learning techniques like collaborative filtering help suggest new
friends or connections.

Question 12.
Dinesh is training a machine to identify different plant species from images, but he doesn’t have enough
labelled data for all species. What type of AI learning can Dinesh use to improve the model’s
performance with limited labelled data? [2]
Answer:
Dinesh can use semi-supervised learning, which combines a small amount of labelled data with a large
amount of unlabelled data to improve accuracy.
Question 13.
Rohan is selecting a dataset for his AI model. What two factors should he consider regarding the quality
of the data? [2]
Answer:
1. The data should be complete without missing values.
2. The data must be accurate and free of noise.

Question 14.
What is “grayscale” in computer vision, and can you provide an example?. [2]
Answer:
Gray scale refers to a range of shades of gray without distinct colours, representing the intensity of light
in an image. For example, when processing an image for facial recognition, a gray scale conversion is
often performed.

Question 15.
Identify two stop words that are important in this sentence: “Please let us know whether you prefer email
notifications or phone calls”. [2]
Answer:
“whether” is essential as it introduces the choice between two alternatives, clarifying the nature of the
request. “or” explicitly connects the two options of notifications, ensuring the reader understands that
both are valid preferences.

Question 16.
Construct the confusion matrix for a scenario with true positives = 120, false positives = 40, true
negatives = 70, and false negatives = 30.
Answer:
True Positives (TP): 120
False Negatives (FN): 30
False Positives (FP): 40
True Negatives (TN): 70

Predicted Positive Predicted Negative

Actual Positive 120 30

Actual Negative 40 70

Answer any 3 out of the given 5 questions in 50-80 words each. (4 x 3 = 12 marks)
Question 17.
You tell your younger sibling that video streaming platforms suggest videos based on AI. Can you
explain how AI
suggests videos? [4]
Answer:
AI looks at the types of videos you’ve watched before, how long you watched them, and even what
others with similar tastes are watching. It then recommends videos it thinks you’ll enjoy. This process is
called collaborative filtering, where the system learns from users’ behaviour and preferences to suggest
content that matches their interests. It’s like when a friend suggests a movie because they know what
you like.

Question 18.
You are tasked with building an AI model to predict house prices based on location, size and other
features.
(A) How will you structure the problem using the 4W Problem Canvas?
Answer:
(a) What: Predict house prices using an AI model. Why: Provide better insights for buyers and sellers,
improving decision-making.
Who: Real estate agents, buyers and sellers.
Where: Urban areas where house sales frequently occur.

(B) What kind of data will you need to acquire for the solution?
Answer:
Data needed:

1. House attributes (size, bedrooms, bathrooms).

2. Location data (neighborhood, proximity to amenities).
3. Historical price trends.
4. Macroeconomic indicators (e.g., interest rates).

Question 19.
Analyse the two figures below and explain the type of learning approach being demonstrated in each
case. I don’t know what givve me, It dant know you gave me,
Answer:
Figure 1: This figure represents supervised learning, where the input data comes with labels. The
labelled examples, such as “Dog” and “Cat”, help the model learn how to classify future inputs. When an
unknown animal (a dog) is given to the machine, it predicts correctly by matching it to the labelled
examples it has already seen.

Figure 2: This figure demonstrates unsupervised learning, which operates on unlabelled data. Without
any prior labels or knowledge of the categories, the model identifies patterns or similarities in the input
data. It groups the animals into two clusters two animals on the left and two on the right—based on their
shared features, even though it doesn’t know the exact labels. This clustering approach highlights how
unsupervised learning reveals hidden structure’s in data.

Question 20.
Meena uses a language learning app powered by AI. She types the sentence “I am going to the bank”
and the app
corrects it by suggesting “I am going to the river bank” instead of “bank” as a financial institution. Why
might this misunderstanding happen in an AI model? [4]
Answer:
This misunderstanding occurs due to ambiguity in language. The word ‘bank” has multiple meanings,
and the AI model likely chose the more common or contextually frequent usage, which in this case was
“river bank”. NLP models rely on patterns found in the data they are trained on, and if the model has
encountered ‘bank” in the context of nature more often than finance, it may incorrectly suggest that
context. AI needs better disambiguation mechanisms that consider the broader sentence context and
use, world knowledge to make more accurate predictions about word meaning.

Question 21.
A healthcare system predicts if a patient has a certain disease. The confusion matrix is given below: [4]
Answer:

Reality: Disease Reality: No Disease

Prediction: Disease 40 25
Prediction: No disease 15 120

(i) Calculate the system’s false negative rate (FNR).

Answer:
False Negative Rate (FNR)
FN 15
FN+TP
= FN+TP = 15
55
≈ 0. 273

(ii) What is the precision of the system?

Answer:
40 40
Precision = 40+25 = 65 ≈ 0.615