VISVESVARAYA TECHNOLOGICAL UNIVERSITY

BELAGAVI-590018

An Internship Report on
(21INT68)

“Artificial Intelligence and Machine Learning”

Submitted in partial fulfillment for award of the degree of

Bachelor of Engineering in
Computer Science and Engineering
Submitted By

ANSHU KUMAR 1NC21CS012

Under the Guidance of
Internal Guide: External Guide:
Mrs.Prathibha Pujari Shamanna Mohan
Assistant Professor Founder & CEO
Dept. of CSE, NCET Aqmenz Automation
Private Limited

Department of Computer Science and Engineering

NAGARJUNA COLLEGE OF ENGINEERING AND TECHNOLOGY
(An Autonomous Institution Approved by AICTE, affiliated to VTU, Belagavi-590018)
Venkatagiri Kote, Devanahalli, Bengaluru-562110

2023-24

I
 Department of Computer Science and Engineering
NAGARJUNA COLLEGE OF ENGINEERING AND TECHNOLOGY
(An Autonomous Institution Approved by AICTE, affiliated to VTU, Belagavi-590018)
Venkatagiri Kote, Devanahalli, Bengaluru-562110

CERTIFICATE
This is to certify that “Internship report” submitted by ANSHU KUMAR
(1NC21CS012) is workdone by him/her and submitted during 2023-2024 academic
year, in partial fulfillment for award of the degree of BACHELOR OF
ENGINEERING IN COMPUTER SCIENCE AND ENGINEERING. Aqmenz
Automation Private Limited on Real time Project Development using AI & Data
Science Application –An End-to-End Development for a period of one month from
30/10/2023 to 29/11/2023.

Name & Signature of Name & Signature of the

the Co-ordinator HOD
Mrs.Prathibha Pujari Dr. Mallikarjuna Kodabagi
Assistant Professor Professor
Dept. of CSE, NCET Dept. of CSE, NCET

Internal/External Viva

Name of the Examiners Signature with date

1

II
Internship Completion Certificate

III
 ACKNOWLEDGEMENT

It is our proud privilege and duty to acknowledge the kind of help and guidance received from several
people in preparations of this internship. It would not have been possible to complete this internship, in
this form without their valuable help, cooperation and guidance.

I would like to thank NGI Management for constant support and facilities provided in the carrying out of
Internship.

I wish to record my sincere gratitude Dr. B V Ravishankar, Principal, Nagarjuna college of Engineering
and Technology for his constant support and encouragement in preparation of this Internship and for
providing library and laboratory facilities needed to complete this Internship.

I would like to thank Dr. Mallikarjuna Kodabagi , HOD, Department of CSE, Nagarjuna College of
Engineering and Technology for his valuable suggestions and guidance throughout the period of this
Internship.

I thank our Internship coordinator and guide Mrs.Prathibha Pujari, Assistant Professor, Department of
CSE, Nagarjuna college of Engineering and Technology for your valuable suggestions and all the
encouragement that leads towards completion of my Internship.

Last but not least, we would like to thank our parents, friends, teaching and non-teaching staff of NCET.

ANSHU KUMAR
1NC21CS012

IV
 ABSTRACT
This internship offers a hands-on introduction to the exciting field of Artificial Intelligence (AI) and
Machine Learning (ML). Each week, we will learn on a different module related to building
intelligent systems.
The rapid advancement in Artificial Intelligence (AI) and Machine Learning (ML) has
revolutionized various domains, from healthcare to finance, by enabling unprecedented predictive
capabilities. However, the complexity and opacity of these models often lead to challenges in
interpretability and trustworthiness, which are critical for their adoption in sensitive applications.
This study aims to bridge the gap between model performance and interpretability by integrating
Explainable AI (XAI) techniques with robust ML algorithms. We propose a novel framework that
leverages state-of-the-art XAI methods to elucidate the decision-making processes of complex
models while maintaining high predictive accuracy. Through extensive experimentation on diverse
datasets, our framework demonstrates significant improvements in model transparency and user
trust without compromising performance. Additionally, we address common issues such as data
imbalance, overfitting, and bias through advanced regularization techniques and ensemble learning.
Our findings underscore the importance of interpretability in fostering the ethical deployment of AI
systems and provide a pathway for developing more accountable and reliable AIsolutions. This
research contributes to the broader AI community by offering practical insights andmethodologies
for creating interpretable yet powerful ML models.

This might involve tasks like:

Data Exploration and Preparation: Similar to learning HTML and CSS, you'll gain foundational
knowledge in understanding and preparing data, the essential fuel for AI models.

Model Development and Training: Just like building interactive features with JavaScript, you'll
learn to develop and train machine learning models, equipping you with the ability to unlock
valuable insights from data.

Project Deployment and Sharing: Finally, we learn how to deploy your AI projects, similar to
launching your website on GitHub. This allows us to showcase your work and share it with others.

V
 ORGANIZATION PROFILE:
Formation of company:
Aqmenz Automation Private Limited is a private incorporated on 15th October 2018. It is
classified as Non-Govt Company and is registered at Registrar of companies, Bangalore.

Brief history of company:

Aqmenz Automation Pvt Ltd (AAPL) was started on October 2018. It is situated in northernpart of
Bangalore, RT Nagar Karnataka. AAPL provides Mechanical Design & Automation solutions to
their client companies. AAPL also involved in Open source Robotics and devel oped different
varieties of Robots. Aqmenz also started INDOSKILL, a separate platform for the students to get
training and work on various Real Time Industrial Projects. Indoskill offers skill-oriented hands-
ontraining through an online platform.Field of Expertise: Open-source Robotics, Industrial
Automation, Product Design, Python and Deep Learning and Embedded Systems.

Vision and mission:

Our Motto and Vision are to create awareness & training young generation to current and future jobs
demands and also help to current and future jobs demands; meanwhile help the students and
employees to meet the mandatory necessities of future human resources and skill demands. We are in
the 4th industrial revolution. The technological revolution is catastrophic like never before, hence
continues awareness for the up-gradation environment is much essential. Aqmenz Automation Pvt.
Ltd. is working to help and enhance the potential of studentsand employees. So that future human
resources will be very beneficial, purposeful and profitable to the nation.

Services offered:
• Provides Design & Automation solutions
• All type of automation projects to companies using PLC’s, SCADA embedded systems.
• We provide robots and robotic solutions to small and medium scale companies.
• Embedded solutions to companies like GE
• We conduct technical skill-oriented training programs to engineering colleges.
• We also provide robotics and automation lab equipment’s for colleges.

VI
 TABLE OF CONTENTS

CHAPTER
CHAPTER NAME PAGE NO
NO

Certificate II

Complete Certificate III

Acknowledgement IV

Abstract V

Organization Profile VI

Table of Contents VII

Chapter 1 Introduction 1

Chapter 2 Learning Objectives / Internship Objectives 2

Chapter 3 Overview of the work carried out 3

Chapter 4 Implementation / Learning outcome / Result

4-5
Discussion

Chapter 5 Importance and Applications 6

References 7

VII
CHAPTER 1
INTRODUCTION

Artificial Intelligence (AI) and Machine Learning (ML) are rapidly transforming various industries by
enabling the development of intelligent systems that can learn from data and make informed decisions.
AI encompasses a wide range of technologies designed to mimic human cognitive functions, while ML
focuses on developing algorithms that allow systems to learn patterns and insights from data.The
digital age has transformed how information is created, disseminated, and consumed. With the advent
of social media and digital news platforms, the spread of information has become rapid and
widespread. However, this has also led to the proliferation of fake news—misleading or false
information presented as news. Fake news has significant societal implications, including undermining
public trust, influencing elections, inciting violence, and disrupting economies.
Identifying and combating fake news has become a critical challenge. Traditional methods of fact-
checking and verification, while essential, are often slow and unable to keep up with the volume of
information generated daily. Consequently, there is a growing interest in leveraging machine learning
(ML) and natural language processing (NLP) techniques to develop automated systems for fake news
detection.Machine learning offers powerful tools to analyze large datasets, identify patterns, and make
predictions based on data. In the context of fake news detection, ML models can be trained to
distinguish between genuine and fabricated news articles by analyzing textual features and linguistic
cues. Natural language processing enhances this capability by providing techniques to preprocess text,
extract meaningful features, and understand the context and semantics of language.

This project aims to develop a robust fake news prediction system using Python, one of the most
popular programming languages for data science and machine learning. The system will employ
various NLP techniques to preprocess the text and extract features, which will then be used to train
several ML models. These models will be evaluated based on their accuracy, precision, recall, and F1-
score to identify the most effective approach.

1
CHAPTER 2
LEARNING OBJECTIVES / INTERNSHIP OBJECTIVES

Understanding AI and Data Science Fundamentals:

• Gain a thorough understanding of the fundamental concepts of AI and Data Science, including
machine learning algorithms, data preprocessing, and model evaluation metrics.

Hands-On Experience with Data Collection and Preparation:

• Learn to collect, clean, and preprocess data from various sources to ensure it is suitable for
analysis and model building.
• Understand techniques for handling missing data, data normalization, and feature engineering.

Model Development and Training:

• Develop and train machine learning models using popular frameworks such as TensorFlow,
PyTorch, or Scikit-learn.
• Experiment with different types of models (e.g., regression, classification, clustering) to solve
specific real-time project problems.

Implementation of Real-Time Data Processing Pipelines:

• Design and implement data processing pipelines for real-time data ingestion, processing, and
analysis.
• Use tools and platforms such as Apache Kafka, Apache Spark, or AWS Lambda for real-time
data processing.

Model Deployment and Integration:

• Learn how to deploy machine learning models into production environments.
• Integrate AI models with web or mobile applications using APIs and microservices architecture.

Real-World Problem Solving:

• Apply AI and Data Science techniques to solve real-world problems, gaining practical experience
and insights.

• Work on projects that have a tangible impact and contribute to organizational goals.

2
CHAPTER 3
OVERVIEW OF THE WORK CARRIED OUT
DATE DAY NAME OF THE TOPIC/MODULE COMPLETED
01-03-24 MONDAY PYTHON BASICS
1st WEEK

02-03-24 TUESDAY DATA STRUCTURES, LIST, TUPLES, SET

04-03-24 WEDNESDAY LOOPS, ITERABLES, FUNCTIONS, LAMBDA
05-03-24 THURSDAY FILE HANDLING
06-03-24 FRIDAY PYTHON MODULES, CLASS AND OBJECTS

DATE DAY NAME OF THE TOPIC/MODULE COMPLETED

08-03-24 MONDAY DATA SCIENCE INTRO(AIML)
2nd WEEK

09-03-24 TUESDAY PANDAS, NUMPY

11-03-24 WEDNESDAY MATPLOT, SCIKIT LEARN
12-03-24 THURSDAY SUPERVISED LEARNING(CLASSIFICATION)
13-03-24 FRIDAY SUPERVISED LEARNING(TIME SERIES DATA),
DATA ENGINEERING

DATE DAY NAME OF THE TOPIC/MODULE COMPLETED

15-03-24 MONDAY NEURAL NETWORK
3rd WEEK

16-03-24 TUESDAY DEEP LEARNING

18-03-24 WEDNESDAY TENSORFLOW
19-03-24 THURSDAY GPU, TPU
20-03-24 FRIDAY PROJECT

DATE DAY NAME OF THE TOPIC/MODULE COMPLETED

22-03-24 MONDAY BASICS HTML
4th WEEK

23-03-24 TUESDAY API, FLASK

25-03-24 WEDNESDAY DOCKER-IMAGE
26-03-24 THURSDAY CLOUD(DEPLOYMENT)
27-03-24 FRIDAY GIT,GITHUB

3
CHAPTER 4
IMPLEMENTATION / LEARNING OUTCOME / RESULT
DISCUSSION
Real-Time Project Development Using AI & Data Science Applications: An End-to-End Development
includes comprehensive data handling and preprocessing, robust model development and training, and
seamless deployment and integration into production environments. It also encompasses continuous
performance monitoring and maintenance, alongside ensuring model interpretability and deriving
actionable business insights.

1. Data Handling and Preprocessing

Effective data handling and preprocessing are foundational steps in developing AI and Data Science
applications. This involves collecting data from diverse sources, cleaning it to address missing values
and outliers, and transforming it through techniques such as normalization and feature engineering.
Proper preprocessing ensures that the data is in the best possible state for model training, which is critical
for achieving accurate and reliable predictions.

4
2. Model Development and Training
The development and training of a fake news prediction model encompass several crucial stages. Each
stage contributes to building a robust system capable of distinguishing between genuine and fabricated
news. Below, we provide a detailed approach to creating an effective fake news detection system using
Python, incorporating natural language processing (NLP) techniques and various machine learning
(ML) algorithms.

3. Model Deployment and Integration

Deploying machine learning models into production is a crucial step to enable real-time predictions.
Once the fake news prediction model has been developed and trained, the next critical phase is its
deployment and integration. This phase involves deploying the model into a production environment
and integrating it with a user interface to make it accessible and usable for end-users. Below is a
comprehensive guide to deploying and integrating the fake news prediction model:

4. Continuous Performance Monitoring and Maintenance

Once deployed, it is essential to continuously monitor the performance of machine learning models to
ensure they remain accurate and reliable over time. This includes setting up monitoring tools to track
model performance metrics and establishing automated retraining pipelines to update models with new
data. Continuous maintenance ensures that the models adapt to changing data patterns and maintain their
predictive power.

5. Interpretability and Business Insights

Model interpretability and the extraction of business insights are vital aspects of AI development.
Techniques such as SHapley Additive exPlanations (SHAP) values are used to explain model predictions
and ensure transparency. Understanding feature importance helps in explaining the model's decision-
making process, building trust with stakeholders, and making informed business decisions. By providing
clear insights into the factors driving model predictions, businesses can better align their strategies and
operations with data-driven insights.

5
CHAPTER 5
IMPORTANCE AND APPLICATIONS
IMPORTANCE:

Preserving Public Trust: Fake news undermines trust in media and institutions. Accurate fake news
prediction helps preserve credibility and trust in information sources.
Protecting Democracy: Misinformation can sway public opinion and electoral outcomes. Detecting
fake news is crucial for maintaining fair and transparent democratic processes.
Preventing Harm: Fake news can lead to real-world consequences, including social unrest and harm
to individuals. Early detection helps mitigate these risks.
Improving Media Literacy: By providing tools to identify fake news, the public becomes more
discerning consumers of information, enhancing overall media literacy.
Economic Stability: Misinformation in financial markets can lead to volatility and economic
instability. Accurate news verification can prevent such disruptions.

Public Health: During health crises, misinformation can lead to harmful behaviors. Fake news
prediction ensures accurate information dissemination, crucial for public health.

APPLICATIONS:

Social Media Platforms: Integrating fake news detection algorithms to filter or flag potentially
misleading content, enhancing the reliability of information shared.
News Aggregators: Implementing fake news prediction to prioritize and promote authentic news,
providing users with trustworthy sources.
Fact-Checking Organizations: Using machine learning models to streamline the fact-checking
process, making it faster and more efficient.
Government Agencies: Assisting in identifying and countering misinformation campaigns that
threaten national security and public safety.
Educational Tools: Developing applications that educate users on identifying fake news, contributing
to better media literacy.

6
 REFERENCES

[1] AQMENZ AUTOMATION PRIVATE LIMITED

https://www.tofler.in/aqmenz-automation-private-limited/company/U74999KA2018PTC117612

[2] PROJECT – FAKE NEWS PREDICTION IN PYTHON USING ML

https://www.kaggle.com/code/therealsampat/fake-news-detection

[3] BOOK
https://machinelearningmastery.com/

[4] PAPER
https://paperswithcode.com/

[5] Additional
https://towardsdatascience.com/
https://shap.readthedocs.io/en/latest/api.html