Multiple-Choice Questions (MCQs)

1. What is the primary goal of a Capstone project?

a) To showcase knowledge by solving a real-world problem
b) To complete a theoretical exam
c) To attend a lecture
d) To focus on programming skills only
2. Which skill is emphasized during a Capstone project?
a) Rote memorization
b) Teamwork and collaboration
c) Using only one technology
d) Avoiding feedback from users
3. In a Capstone project, which of the following is an important consideration?
a) Ignoring ethical concerns when using data
b) Using data without user consent
c) Ethical data collection and usage
d) Focusing only on individual work
4. What type of model would be used in a Stock Prices Predictor?
a) Image classification model
b) Regression model
c) Sentiment analysis model
d) Object detection model
5. Which AI technique is most useful for a Sentiment Analyzer?
a) Natural Language Processing (NLP)
b) Convolutional Neural Networks (CNNs)
c) Reinforcement learning
d) Time series analysis
6. What is the main challenge in developing a Sentiment Analyzer?
a) Handling sarcasm and context
b) Analyzing large video datasets
c) Predicting stock prices
d) Recognizing facial expressions
7. What type of dataset might be used for a Human Activity Recognition project?
a) Customer review dataset
b) Smartphone sensor data
c) Movie ticket price data
d) Text data from social media
8. What is a key challenge in a Classifying Humans and Animals in a Photo
project?
a) Handling noisy audio data
b) Handling a variety of animals and environmental factors
c) Analyzing user feedback
d) Predicting numerical values
9. Which of the following is a skill learned during a Capstone project?
a) How to memorize large textbooks
b) How to brainstorm and select solutions
c) How to ignore user feedback
d) How to avoid data collection
10. Which of the following is an example of an AI Capstone project?
a) Learning to code
b) Developing a Movie Ticket Price Predictor
c) Writing an essay
d) Reading a book

Short Answer Questions

1. What is the main objective of a Capstone project in AI?

2. What skill is essential when brainstorming solutions for a Capstone project?
3. How can user feedback improve the Capstone project outcome?
4. What does ethical data usage mean in the context of a Capstone project?
5. What AI technique is most useful for creating a stock price prediction model?
6. Why is it important to handle noisy data in a Human Activity Recognition project?
7. How does a Sentiment Analyzer model benefit from Natural Language Processing
(NLP)?
8. Why is it necessary to test the prototype in a Capstone project?
9. What are the main challenges when classifying humans and animals in an image?
10. Why is teamwork important in completing a Capstone project?

Long Answer Questions

1. Explain how a Capstone project allows students to demonstrate their AI expertise and
problem-solving abilities.
2. Discuss the ethical considerations that must be made when gathering and using data in
an AI project.
3. How do you determine which AI model (e.g., regression, classification, etc.) to use
for a given Capstone project?
4. Describe the steps involved in developing a Sentiment Analyzer and the challenges it
might face.
5. Discuss how feedback from users can help improve a Capstone project prototype.
6. Explain the process of handling noisy data in Human Activity Recognition projects
and why it is important.
7. How would you approach the development of a stock price prediction model using
machine learning?
8. What are the key features of a good Capstone project, and how can students ensure
they meet these features?
9. How would you tackle the challenge of predicting movie ticket prices using machine
learning?
10. What are the benefits and potential drawbacks of working as part of a team on a
Capstone project?

Answers

Multiple-Choice Questions Answers:

1. a) To showcase knowledge by solving a real-world problem
2. b) Teamwork and collaboration
3. c) Ethical data collection and usage
4. b) Regression model
5. a) Natural Language Processing (NLP)
6. a) Handling sarcasm and context
7. b) Smartphone sensor data
8. b) Handling a variety of animals and environmental factors
9. b) How to brainstorm and select solutions
10. b) Developing a Movie Ticket Price Predictor

Short Answer Questions Answers:

1. The main objective of a Capstone project in AI is to apply the knowledge gained

throughout the course to solve a real-world problem, demonstrating expertise in AI
techniques and problem-solving.
2. Essential skills for brainstorming solutions include critical thinking, creativity, and the
ability to consider multiple options before selecting the most suitable one.
3. User feedback helps refine the prototype, ensuring it better meets the needs of the
target audience and works as intended.
4. Ethical data usage means obtaining data legally, ensuring privacy and security, and
using it in a way that benefits the project without causing harm or bias.
5. Regression models are commonly used for stock price prediction because they help
forecast numerical values based on historical data.
6. Noisy data can introduce errors in model predictions. Proper data cleaning and
filtering are necessary for accurate analysis in Human Activity Recognition projects.
7. NLP allows Sentiment Analyzers to process, understand, and interpret human
language, extracting meaningful insights from text data.
8. Testing a prototype ensures that the model works as intended and provides valuable
insights for making improvements.
9. The main challenges include accurately detecting and classifying animals in diverse
environments and under various conditions.
10. Teamwork is essential because it encourages collaboration, pooling diverse skills and
perspectives, which leads to better problem-solving and solution development.

Long Answer Questions Answers:

1. A Capstone project allows students to demonstrate their AI expertise by solving real-

world problems through research and the application of learned skills. By developing
solutions that address specific issues, students showcase their abilities in AI
techniques, data analysis, and ethical considerations. The process of designing,
testing, and refining solutions highlights a student's problem-solving skills and
preparedness to apply their knowledge in the professional world.
2. Ethical considerations in data gathering and usage in an AI project include ensuring
the data is collected legally, obtaining informed consent where necessary, and
protecting the privacy of individuals. It also involves avoiding biases in data, which
can lead to unfair or inaccurate results, and ensuring transparency in how data is used
and shared. Ethical AI development also considers the potential impact on society and
the environment.
3. Choosing an AI model depends on the problem's nature. For a regression problem like
predicting stock prices, a regression model is appropriate. For classification tasks,
such as categorizing images of animals and humans, a classification model is used.
The data type (e.g., time series, image, text) and the project's goals (prediction,
classification, clustering) help guide the decision. Testing different models through
experimentation can also help determine the best fit.
4. Developing a Sentiment Analyzer involves several steps: data collection (e.g., social
media or reviews), preprocessing (removing irrelevant data), applying NLP
techniques (like tokenization and stemming), training a machine learning model (such
as Naive Bayes or LSTM), and evaluating the model's performance. Challenges
include handling context, sarcasm, and the variety of language, making accurate
sentiment detection difficult.
5. Feedback from users is vital for improving a Capstone project prototype. User
feedback identifies pain points, issues with usability, or areas where the solution can
be more effective. Iterative testing with real users allows developers to refine their
models, making them more robust, user-friendly, and aligned with the needs of the
target audience.
6. Handling noisy data is critical in Human Activity Recognition projects because it can
significantly affect the model's accuracy. Noise may come from inaccurate sensor
readings, user errors, or environmental factors. Data cleaning techniques like filtering,
smoothing, and normalizing are employed to reduce the impact of noise, ensuring the
model can recognize activities accurately.
7. To develop a stock price prediction model, start by collecting historical stock data.
Preprocess the data, handle missing values, and perform feature engineering. A
regression model is typically used for prediction, and the model is trained using
historical data. Evaluation metrics like Mean Squared Error (MSE) help measure
accuracy. It’s crucial to address overfitting and consider factors like market trends and
news.
8. A good Capstone project should focus on solving a real-world problem, demonstrate
the application of learned skills, and result in a tangible solution or prototype. To
ensure this, students should choose a problem they are passionate about, thoroughly
research the topic, collaborate effectively in teams, and iterate based on user
feedback.
9. The movie ticket price predictor project involves identifying factors that influence
ticket prices, such as movie genre, release time, and popularity. By collecting and
analyzing relevant data, a regression model can predict ticket prices. Challenges
include collecting accurate data and avoiding overfitting the model to historical
trends.
10. Team