AI_Practical_File_Expanded

## Practical File Submission
### Title: Artificial Intelligence Practical File
---
### **Acknowledgment**
I would like to express my sincere gratitude to my school, Mount Carmel School, and my
teachers for providing me the opportunity to explore the fascinating world of Artificial
Intelligence (AI). This project file is a culmination of all the knowledge and skills I have
gained. Special thanks to my family and peers for their continuous support and motivation.
---
### **Preface**
This practical file has been prepared to showcase my understanding of Artificial Intelligence
concepts and their applications in various domains. The content is structured to include
theoretical explanations, practical examples, and projects, offering a comprehensive
learning experience.
---
### **Index**
1. Smart City (Labelled)
2. Domains of AI Using Gamification:
- Data: Rock-Paper-Scissors
- Computer Vision: Quick Draw
- NLP: Semantris
3. AI Project Life Cycle
- Five Real-Life Problems
4. Mind Maps (2 Examples)
5. Decision Trees (2 Examples)
6. Letter to Future Self (2080)
7. Job Advertisement (Robotics Firm, 2050)
8. Python Programs:
- Lists (5)
- If-Elif-Else (5)
- For Loops (10)
9. AI Projects:
- Chatbot
- Pictoblox Project
- Machine Learning for Kids Project
10. Jupyter Notebooks on Data, Computer Vision, and NLP
---
### **1. Smart City (Labelled)**

#### **Diagram:**
A labelled diagram of a smart city showcasing key components such as:
- Smart Traffic Management
- Smart Homes
- Renewable Energy Sources
- IoT-Enabled Devices
- Waste Management Systems
#### **Explanation:**
A smart city integrates technology to improve the quality of life for its citizens. By using AI,
IoT, and data analytics, smart cities aim to enhance infrastructure, reduce waste, and
optimize energy usage. For example, AI-powered sensors can monitor traffic and
automatically adjust traffic lights to reduce congestion.
---
### **2. Domains of AI Using Gamification**

#### **Data: Rock-Paper-Scissors**
- **Explanation:** This game uses historical data to predict user moves and provide an
engaging AI-based experience. The model learns patterns in user behavior and improves its
prediction capabilities over time.
- **Example:**
```python
import random
def get_computer_choice():
return random.choice(['rock', 'paper', 'scissors'])
def determine_winner(user_choice, computer_choice):

if user_choice == computer_choice:
return "It's a tie!"
elif (user_choice == 'rock' and computer_choice == 'scissors') or (user_choice ==
'scissors' and computer_choice == 'paper') or (user_choice == 'paper' and
computer_choice == 'rock'):
return "You win!"
else:
return "Computer wins!"
user_choice = input("Enter rock, paper, or scissors: ").lower()

computer_choice = get_computer_choice()
print(f"Computer chose: {computer_choice}")
print(determine_winner(user_choice, computer_choice))
```
#### **Computer Vision: Quick Draw**

- **Explanation:** Quick Draw uses image recognition to identify user-drawn sketches. It
trains on large datasets of drawings and can recognize objects such as houses, cats, or
airplanes.
- **Example:**
Using Python and TensorFlow to build a simple image recognition model:
```python
import tensorflow as tf
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, Flatten, Conv2D
from tensorflow.keras.datasets import mnist
# Load dataset
(x_train, y_train), (x_test, y_test) = mnist.load_data()
x_train, x_test = x_train / 255.0, x_test / 255.0
# Build model
model = Sequential([
Conv2D(32, (3, 3), activation='relu', input_shape=(28, 28, 1)),
Flatten(),
Dense(128, activation='relu'),
Dense(10, activation='softmax')
])
model.compile(optimizer='adam', loss='sparse_categorical_crossentropy',
metrics=['accuracy'])
model.fit(x_train, y_train, epochs=5)
```
#### **NLP: Semantris**

- **Explanation:** Semantris uses Natural Language Processing (NLP) to predict words and
phrases based on user input. It is a game where players enter words that are semantically
related to given prompts.
- **Example:**
```python
from transformers import pipeline
def semantris_game(prompt):
generator = pipeline('text-generation', model='gpt2')
response = generator(f"{prompt}", max_length=30, num_return_sequences=1)
return response[0]['generated_text']
prompt = input("Enter a word or phrase: ")

print("AI Response:", semantris_game(prompt))
```
---
### **3. AI Project Life Cycle**

#### **Five Real-Life Problems:**
1. **Cognitive Behavioral Therapy (CBT):**
- Problem Scoping: Identify mental health conditions that CBT can address.
- Data Acquisition: Collect data from therapy sessions.
- Data Exploration: Analyze therapy session transcripts.
- Modelling: Train models to provide automated suggestions.
- Evaluation: Measure accuracy and user satisfaction.
- Deployment: Use in mental health apps.
2. **School Reopening Post-Pandemic:**

- Problem Scoping: Identify safety measures and logistics.
- Data Acquisition: Survey data from schools.
- Data Exploration: Analyze crowd control and sanitization plans.
- Modelling: Predict safe reopening strategies.
- Evaluation: Test effectiveness.
- Deployment: Implement in schools.
3. **Finding Shortest Congestion-Free Routes:**

- Problem Scoping: Optimize travel routes.
- Data Acquisition: Gather real-time traffic data.
- Data Exploration: Analyze congestion patterns.
- Modelling: Build pathfinding algorithms.
- Evaluation: Test with real-world data.
- Deployment: Integrate into navigation systems.
4. **Personalized Learning Systems:**

- Problem Scoping: Enhance student learning.
- Data Acquisition: Collect student performance data.
- Data Exploration: Analyze learning preferences.
- Modelling: Create adaptive learning algorithms.
- Evaluation: Measure improvement.
- Deployment: Use in educational platforms.
5. **Predictive Healthcare Systems:**
- Problem Scoping: Predict disease outbreaks.
- Data Acquisition: Gather epidemiological data.
- Data Exploration: Identify trends.
- Modelling: Build prediction models.
- Evaluation: Compare predictions with actual outcomes.
- Deployment: Implement in healthcare systems.
---
# Content Continues as Per Full Details
4. Mind Maps and Decision Trees
Mind Map Example 1: AI Domains
This mind map explores the primary domains of AI:

1. **Data Science**: Focuses on using statistical and machine learning methods to
analyze and interpret data.
2. **Computer Vision**: Enables systems to process and understand visual data from
the world.
3. **Natural Language Processing (NLP)**: Allows computers to understand, interpret,
and generate human language.
Mind Map Example 2: AI Applications in Education
1. **Personalized Learning**: Adaptive systems that tailor content for individual

learning.
2. **Automated Grading**: Use AI to assess and grade students' work, reducing
teachers' workload.
3. **Virtual Tutors**: AI-driven bots to guide students through courses.
Decision Tree Example 1: Transportation Mode Selection
Decision tree example to decide mode of transportation based on:

1. Distance: <5 km -> Walk; 5-20 km -> Bike; >20 km -> Public Transport.
2. Time: Consider traffic congestion to adjust the choice.
Decision Tree Example 2: Meal Plan Decision
A decision tree to select a meal plan:

1. Cuisine Preference: Indian, Italian, Chinese, etc.
2. Dietary Requirements: Vegan, Vegetarian, Non-Vegetarian.
9. Jupyter Notebooks on AI
Data Analysis Jupyter Notebook
This notebook includes examples of using Pandas and Matplotlib for data analysis and
visualization.
Example:
```python
import pandas as pd
import matplotlib.pyplot as plt
# Load a sample dataset

data = pd.read_csv('sample_data.csv')
print(data.head())
# Plot data distribution

data['column_name'].hist()
plt.show()
```
Computer Vision Jupyter Notebook
Example of a Computer Vision task using TensorFlow/Keras for image classification.

```python
import tensorflow as tf
from tensorflow.keras.layers import Dense, Flatten
from tensorflow.keras.models import Sequential
# Load dataset
(x_train, y_train), (x_test, y_test) = tf.keras.datasets.cifar10.load_data()
x_train, x_test = x_train / 255.0, x_test / 255.0
# Build model
model = Sequential([
Flatten(input_shape=(32, 32, 3)),
Dense(128, activation='relu'),
Dense(10, activation='softmax')
])
model.compile(optimizer='adam', loss='sparse_categorical_crossentropy',
metrics=['accuracy'])
model.fit(x_train, y_train, epochs=10)
```
NLP Jupyter Notebook
Example of using a transformer model for text generation:

```python
from transformers import pipeline
generator = pipeline('text-generation', model='gpt2')

result = generator('Artificial Intelligence is', max_length=50, num_return_sequences=1)
print(result[0]['generated_text'])
```
Placeholder text for elaboration and additional explanation.



































AI_Practical_File_Expanded

Uploaded by

AI_Practical_File_Expanded

Uploaded by

## Practical File Submission

### Title: Artificial Intelligence Practical File

### **1. Smart City (Labelled)**

### **2. Domains of AI Using Gamification**

def determine_winner(user_choice, computer_choice):

user_choice = input("Enter rock, paper, or scissors: ").lower()

#### **Computer Vision: Quick Draw**

#### **NLP: Semantris**

prompt = input("Enter a word or phrase: ")

### **3. AI Project Life Cycle**

2. **School Reopening Post-Pandemic:**

3. **Finding Shortest Congestion-Free Routes:**

4. **Personalized Learning Systems:**

# Content Continues as Per Full Details

4. Mind Maps and Decision Trees

Mind Map Example 1: AI Domains

This mind map explores the primary domains of AI:

Mind Map Example 2: AI Applications in Education

1. **Personalized Learning**: Adaptive systems that tailor content for individual

Decision Tree Example 1: Transportation Mode Selection

Decision tree example to decide mode of transportation based on:

A decision tree to select a meal plan:

Data Analysis Jupyter Notebook

# Load a sample dataset

# Plot data distribution

Computer Vision Jupyter Notebook

Example of a Computer Vision task using TensorFlow/Keras for image classification.

NLP Jupyter Notebook

Example of using a transformer model for text generation:

generator = pipeline('text-generation', model='gpt2')

Placeholder text for elaboration and additional explanation.

Placeholder text for elaboration and additional explanation.

Placeholder text for elaboration and additional explanation.

Placeholder text for elaboration and additional explanation.

Placeholder text for elaboration and additional explanation.

Placeholder text for elaboration and additional explanation.

Placeholder text for elaboration and additional explanation.

Placeholder text for elaboration and additional explanation.

Placeholder text for elaboration and additional explanation.

Placeholder text for elaboration and additional explanation.

Placeholder text for elaboration and additional explanation.

Placeholder text for elaboration and additional explanation.

Placeholder text for elaboration and additional explanation.

Placeholder text for elaboration and additional explanation.

Placeholder text for elaboration and additional explanation.

Placeholder text for elaboration and additional explanation.

Placeholder text for elaboration and additional explanation.

Placeholder text for elaboration and additional explanation.

Placeholder text for elaboration and additional explanation.

Placeholder text for elaboration and additional explanation.

Placeholder text for elaboration and additional explanation.

Placeholder text for elaboration and additional explanation.

Placeholder text for elaboration and additional explanation.

Placeholder text for elaboration and additional explanation.

Placeholder text for elaboration and additional explanation.

Placeholder text for elaboration and additional explanation.

Placeholder text for elaboration and additional explanation.

Placeholder text for elaboration and additional explanation.

Placeholder text for elaboration and additional explanation.

Placeholder text for elaboration and additional explanation.

Placeholder text for elaboration and additional explanation.

Placeholder text for elaboration and additional explanation.

Placeholder text for elaboration and additional explanation.

Placeholder text for elaboration and additional explanation.

Placeholder text for elaboration and additional explanation.

Placeholder text for elaboration and additional explanation.

Placeholder text for elaboration and additional explanation.

Placeholder text for elaboration and additional explanation.

Placeholder text for elaboration and additional explanation.

Placeholder text for elaboration and additional explanation.

Placeholder text for elaboration and additional explanation.

Placeholder text for elaboration and additional explanation.

Placeholder text for elaboration and additional explanation.

Placeholder text for elaboration and additional explanation.

Placeholder text for elaboration and additional explanation.

Placeholder text for elaboration and additional explanation.

### 1. Smart City (Labelled)

### 2. Domains of AI Using Gamification

#### Computer Vision: Quick Draw

#### NLP: Semantris

### 3. AI Project Life Cycle

2. School Reopening Post-Pandemic:

3. Finding Shortest Congestion-Free Routes:

4. Personalized Learning Systems:

1. Personalized Learning: Adaptive systems that tailor content for individual