Internship report on AI , ML & IIOT and project responses full docs

i
An Internship Report on
ARTIFICIAL INTELLIGENCE, MACHINE LEARNING & IIOT Systems
Submitted in the Partial Fulfillment of the
Requirements
for the Award of the Degree of
BACHELOR OF TECHNOLOGY
IN
ELECTRONICS AND COMMUNICATION ENGINEERING
Submitted
By
A. Rakesh 19885A0419
Under the Esteemed Guidance of
Dr. D. Krishna
Associate Professor
Department of Electronics and Communication Engineering
VARDHAMAN COLLEGE OF ENGINEERING, HYDERABAD
Autonomous institute, affiliated to JNTUH
2020 - 2021

ii
ACKNOWLEDGEMENT
The satisfaction that accompanies the successful completion of the task would be put incomplete
without the mention of the people who made it possible, whose constant guidance and encouragement crown
all the efforts with success.
I wish to express my deep sense of gratitude to Mr. Ajay Kumar Co-Founder & CEO, and
Cognibot for his able guidance and useful suggestions, which helped me in completing the internship in
time and also to Department Mentor Dr. D. Krishna
I am particularly thankful to Dr G.A.E Satish Kumar, Professor & Head, Department of Electronics
and Communication Engineering for his guidance, intense support and encouragement, which helped us to
mould my internship into a successful one.
I show gratitude to my honorable Principal Dr. J. V. R. Ravindra, for having provided all the
facilities and support.
I avail this opportunity to express my deep sense of gratitude and heartful thanks to Dr Teegala
Vijender Reddy, Chairman and Sri Teegala Upender Reddy, Secretary of VCE, for providing congenial
atmosphere to complete this internship successfully.
I also thank all the staff members of Electronics and Communication Engineering department for
their valuable support and generous advice. Finally, thanks to all my friends and family members for their
continuous support and enthusiastic help.
A. Rakesh
(19885A0419)

iii
VARDHAMAN COLLEGE OF ENGINEERING, HYDERABAD
Autonomous institute, affiliated to JNTUH
Department of Electronics and Communication Engineering
CERTIFICATE
This is to certify that the Internship Report entitled “Artificial Intelligence, Machine Learning & IIOT
Systems” carried out by Mr.A.Rakesh, Roll Number 19885A0419, at Cognibot and submitted to the
Department of Electronics and Communication Engineering, in partial fulfillment of the requirements for the
award of degree of Bachelor of Technology in Electronics and Communication Engineering during the
year 2020-21.
Name & Signature of the HOD
Dr. G. A. E. Satish Kumar
HOD, ECE
Name & Signature of the Mentor
A. Vijaya lakshmi
Associate Professor

v
LEARNING OBJECTIVES or INTERNSHIP OBJECTIVES
Main Objectives:-
 Understanding The Importance of AI , ML & IIOT Systems.
 Python Programming.
 Understanding python modules which are used for ML concepts.
 Analysis of various types of ML.
 Statistical Math for the Algorithms.
 Learning to solve statistics and mathematical concepts.
 Applications & Future Scope of AI , ML & IIOT.
 Understanding the available major sections of IOT architectural environment.
 Differentiating IOT with IIOT supply chain monitor and management.
 Key features and Four distinct components of IIOT Systems.
 Different Levels and characteristics of IIOT Systems.
 Understanding how the things are meeting scientific goals.
 Potential Frame Works that are used for complex Analysis.
 Learn Practical skills using real world examples and projects.
 Familiarity of tools which are used in the process of implementing concepts which are related to AI,
ML and IIOT Systems.

vi
WEEKLY OVERVIEW OF INTERNSHIP ACTIVITIES
Week 1
Date Day
Session
(FN/AN)
Name of The Topic/Module Learned
18-05-2020 Monday FN Introduction to python programming and its Installation
19-05-2020 Tuesday FN List Comprehension, slicing, dictionaries, Tuples & sets
20-05-2020 Wednesday FN Loops For, While and Functions
21-05-2020 Thursday FN Classes and Basics of OOPs
22-05-2020 Friday FN Files and Try block , Exceptions ,Finally block
23-05-2020 Saturday FN
Modules Scikit-learn, Pandas, keras, TensorFlow and
Matplotlib.
Week 2
Date Day
Session
(FN/AN)
25-05-2020 Monday FN Introduction to AI & its Aspects ML & DL
26-05-2020 Tuesday FN Weak & Strong AI
27-05-2020 Wednesday FN Supervised & Unsupervised Learning
28-05-2020 Thursday FN Reinforcement Learning
29-05-2020 Friday FN Linear & Logistic Regression Implementation
30-05-2020 Saturday FN Decision Tree Implementation

vii
Week 3
Date Day
Session
(FN/AN)
01-06-2020 Monday FN
Introduction to Neural Networks ,BP NN &
Convolutional NN
02-06-2020 Tuesday FN Activation Functions & Input/Output/Hidden Layer
03-06-2020 Wednesday FN Filters, Padding & pooling
04-06-2020 Thursday FN Data Augmentation
05-06-2020 Friday FN Recurrent Neural Network
06-06-2020 Saturday FN
Applications of AI Image recognition, Speech
recognition ,self-driving car
Week 4
Date Day
Session
(FN/AN)
08-06-2020 Monday FN Introduction to IIOT & LabVIEW Tool Installation
09-06-2020 Tuesday FN Salient features of LabVIEW and NI Hardware
10-06-2020 Wednesday FN Major sections of IIOT architectural environment
11-06-2020 Thursday FN
Sensors , Connectivity , data processing and a user
interface
12-06-2020 Friday FN Levels of IOT Systems
13-06-2020 Saturday FN Applications of IIOT Systems

viii
LIST OF FIGURES
Fig No. Name of the Figure Page No.
1 Different Domains of The Company 1
2 The IBM a computer used by the first generation of AI researchers 7
3 An example of a semantic network 8
4 Example illustration of Supervised Learning 9
5 Example illustration of Unsupervised Learning 9
6 Example illustration of Reinforcement Learning 10
7 Weights 10
8 Neuron 10
9 Activation Function 11
10 Input/Output/Hidden Layer 11
11 Multi-Layer perceptron 11
12 Gradient decent 12
13 Convolutional neural network 13
14 Block Diagram of Machine Learning Process 14
15 Classification of Machine Learning 15
16 Divisions in Artificial Intelligence 15
17 Applications of AI 18
18 Applications of IIOT 18
19 Results/Observations 22

ix
LIST OF TABLES
ABBREVIATIONS
Abbreviation Expansion
AI Artificial Intelligence
ML Machine Learning
DL Deep Learning
IOT Internet of Things
IIOT Industrial Internet of Things
NN Neural Network
CNN Convolutional Neural Network
CTR Collaborative Topic Regression
Table
. No.
Name of the Table Page No.
1 Filters 12
2 Pooling 13
3 Padding 13

x
OUTLINE
Acknowledgements (ii)
Learning Objectives (v)
Weekly overview of Internship Activities (vi)
List of Figures (vii)
List of Tables (viii))
Abbreviations (ix)
1 Executive summary/Abstract 1
1.1 The company 1
1.2 The problem or opportunity 3
1.3 Methodology 5
1.4 Benefits to the company/institution through your report. 6
2 Introduction 7
2.1 History 7
2.2 Definitions 9
2.3 Architecture/Block Diagrams 14
2.4 Configuring/Installing Peripherals 16
2.5 Applications 18
2.6 Advantages & Disadvantages 19
3 Internship Discussion 20
3.1 How the objectives achieved? 20
3.2 What skills (scientific and professional) were learned during the internship? 21
3.3 Results/observations/work experiences get in the internship 22
3.4 What challenges did you experience during the internship? 23
4 Conclusions 24
Bibliography
(Include references to books, articles, reports referred to in the report)
25

AI, ML & IIOT
Cognibot Dept. of ECE 11
CHAPTER 1
EXECUTIVE SUMMARY/ABSTRACT
1.1 The company (Profile)
715-A, 7th Floor, Spencer Plaza,
Suite No.678, Mount Road, Anna Salai, Chennai - 600 002
+914428505171, contactus@cognibot.ml
Reach us at - https://www.cognibotrobotics.com/
Fig-1. Different Domains of The Company
We offer consultation and product development in multiple aspects of building a
factory of the future.
We use AI & robotics to deliver
 Accelerated automated testing
 Rapid and robust visual inspection
 Fully autonomous robots
 Collaborative robots to boost human productivity
 Predictive maintenance
 Zero defect manufacturing
 Intuitive insights using Augmented Reality

AI, ML & IIOT
Our Portfolio
We have deployed more than 40 systems for customers in US and India. We have
successful deployments across various domains including
 Automotive manufacturing
 Aerospace development
 Pharmaceutical manufacturing
 Biomedical research
 FMCG manufacturing
 Big physics
Our Team
We are a young dynamic team passionate about technology, eager to take on new
challenges.
We bring all-round prowess from deep hardware expertise to cutting edge AI knowledge
to build systems that can face the toughest challenges in a modern factory.
Our team has a unique blend of extensive experience in industrial automation and
Artificial Intelligence and is well equipped to bring AI to your organization.

AI, ML & IIOT
1.2 The problem or opportunity or area of Internship work
The focus of our robotics area is the design, modeling and control of systems that
observe, move within, interact with, and act upon their environment. Such systems
include mobile robots, micro-aerial vehicles and large active sensor networks. The
application domains within this research cluster include bipedal and hex pedal robot
locomotion, winged and rotor-based micro-aerial vehicle control, robot navigation, multi-
robot coordination and distributed sensor network optimization.
Research in the Artificial Intelligence tends to be highly interdisciplinary, building on
ideas from computer science, linguistics, psychology, economics, biology, controls,
statistics, and philosophy. In pursuing this approach, faculty and students work closely
with colleagues throughout the University. This collaborative environment, coupled with
our diverse perspectives, leads to a valuable interchange of ideas within and across
research groups.
We are working on
Emergency Assistance Robots
A practical field of researchis focused on developing robots for emergency assistance. Robots
can be trained to assist people in disaster recovery, perform rescue missions in hazardous
conditions, or simply go places that humans can’t go. A well-known example is Mars rover.
Rover robots are built to explore extraterrestrial terrains and searchfor signs of habitability. Its
purpose is for researchand development, but there are other applications as well. For example,
a team of engineers at Carnegie Mellon University recently dispatched robots to help with
rescue missions after an Earthquake. The robots could access places that are difficult for people
to get to, detect objects, and deliver supplies.
Home Robots:
Home robots are generally developed for consumer convenience. They are programmed to help
people with everyday tasks, for example, cleaning a home without human supervision. The
Neato D7 is the latest vacuuming robot that has embedded sensors to help it map the layout of a
home and remember no-go zones and areas that have alreadybeen cleaned. According to Neato
developers, there is more roomfor improvement in how home robots learn about and respond
to their environment. Other home robots are developed to interact with humans. MIT Media
Lab has a Personal Robots Group that specializes in human-robot interaction. One of their goals
is to create robots to help children learn, assist kids in hospitals, and facilitate parent-children
interaction.

AI, ML & IIOT
Biomedical research
Developing most AI, ML, and deep neural network tools requires access to big data—
another concept with multiple meanings. For data scientists, it implies using more data
than one computer can handle with significant attendant analytical and computational
challenges and opportunities; for clinicians and biomedical researchers, it refers to
complex datasets with numerous structured and unstructured data fields, such as those
typically found in electronic health records. Reinforcement learning is a notable
exception to the use f big data to train AI. It is an approach to building AI tools based
only on feedback. For example, DeepMind program AlphaGo Zero became the most
powerful Go program in the world solely by playing against itself. Thus far,
reinforcement learning in health care has been developed using historical data
representing decisions and feedback. If (when) AI starts to make and test clinical
decisions, algorithms will have the capacity to learn on their own.
FMCG Manufacturing
Challenges of Adopting AI & ML in the FMCG Sector
Inconsistencies within food products can manifest difficulties in applying robotics
technology to food processing plants. Similarly, the cost of investment in robotics
technology or artificial intelligence software is significant, and at the moment only big
businesses can afford the investment in technology that is designed to significantly
improve the output and increase the efficiency of companies operating within the Fast-
Moving Consumer Goods sector. Similarly, disperse operations centres make the
application of company-wide technology difficult. Some level of convergence is needed
before every business is able to operate on a cross-location basis with artificial
intelligence and machine learning technology.

AI, ML & IIOT
1.3 Methodology
The methodology has been used in the development of a number of successful robotic
systems ranging from teleoperated to highly autonomous systems. The development
process is split into two parts - design and implementation. These are two discrete phases
in developing telerobotic systems. A hierarchical control structure, combined with a
component-based software implementation approach serves to simplify and accelerate
control system development.
This work focuses on using machine learning methods and algorithms in order to evaluate
translations of technical documentation. There are two different problems that will be
solved within this thesis. First, translations of technical documents will be classified and
evaluated with the machine learning algorithm having access to the original document. In
the second attempt, an algorithm will be optimized on the same task without having
knowledge of the original. The planned procedure for our master thesis is the following:
Based on research on existing methods and metrics, an iterative knowledge discovery
process will be started to answer the given research questions. This process includes the
determination of quality criteria for translated documents, the implementation of needed
metrics and algorithms as well as the optimization of the machine learning approaches to
solve the given task optimally. It is important to note that this process is of iterative
nature, since the criteria and attributes as well as their impact on translation quality and
classification possibilities will be determined by evaluating the algorithms’ results using a
database of technical documents and their translations. The used data set will range from
automated translations of technical documents using computerized translation systems to
manual and professional translations. Furthermore, during this iterative process, the
methods and algorithms used will be continually changed and optimized to achieve the
best possible results. Finally, the process and results will be critically reviewed, evaluated
and compared to one another. The limits of automated translations with the current state
of the art will be pointed out and a prospect for possible further developments and studies
on this topic will be given.

AI, ML & IIOT
13.1 Benefits to the company/institution through your report.
 For a company, there is a benefit that knowing about the company profile will
increase the growth of the company.
 It’s not about the company’s sales or an offers kind of things it’s all about the
company’s non-physical benefits for an instance company’s goodwill, company’s
copyrights etc.
 Through articles publishments and reports the company profile will reach many
domain related enthusiasts. And they try to rebuilt the things and get in touch with
company’s community members.
 Through company’s report , society will know the particular technology is been
used in real time as well. And also it explain about the company’s strategy as
analyzing company’s profitability through some techniques from management
domain.

AI, ML & IIOT
CHAPTER 2
INTRODUCTION
2.1 History
Fig-2. The IBM 702: a computer used by the first generation of AI researchers.
The history of Artificial Intelligence (AI) began in antiquity, with myths, stories and
rumors of artificial beings endowed with intelligence or consciousness by master
craftsmen. The seeds of modern AI were planted by classical philosophers who attempted
to describe the process of human thinking as the mechanical manipulation of symbols.
This work culminated in the invention of the programmable digital computer in the
1940s, a machine based on the abstract essence of mathematical reasoning. This device
and the ideas behind it inspired a handful of scientists to begin seriously discussing the
possibility of building an electronic brain.
The field of AI research was founded at a workshop held on the campus of Dartmouth
College during the summer of 1956.[1] Those who attended would become the leaders of
AI research for decades. Many of them predicted that a machine as intelligent as a human
being would exist in no more than a generation, and they were given millions of dollars to
make this vision come true.
Eventually, it became obvious that they had grossly underestimated the difficulty of the
project. In 1973, in response to the criticism from James Lighthill and ongoing pressure
from congress, the U.S. and British Governments stopped funding undirected research
into artificial intelligence, and the difficult years that followed would later be known as
an "AI winter". Seven years later, a visionary initiative by the Japanese Government
inspired governments and industry to provide AI with billions of dollars, but by the late
80s the investors became disillusioned and withdrew funding again.

AI, ML & IIOT
Investment and interest in AI boomed in the first
decades of the 21st century when machine
learning was successfully applied to many
problems in academia and industry due to new
methods, the application of powerful computer
hardware, and the collection of immense data
sets.
Fig-3. An example of a semantic network
The birth of artificial intelligence 1952–1956(1952–1956)
In the 1940s and 50s, a handful of scientists from a variety of fields (mathematics,
psychology, engineering, economics and political science) began to discuss the possibility
of creating an artificial brain. The field of artificial intelligence research was founded as
an academic discipline in 1956.
Natural language
An important goal of AI research is to allow computers to communicate in natural
languages like English. An early success was Daniel Bobrow's program STUDENT,
which could solve high school algebra word problems.
A semantic net represents concepts (e.g. "house”, “door") as nodes and relations among
concepts (e.g. "has-a") as links between the nodes. The first AI program to use a semantic
net was written by Ross Quillian and the most successful (and controversial) version was
Roger Schank's Conceptual dependency theory.[67]
Joseph Weizenbaum's ELIZA could carry out conversations that were so realistic that
users occasionally were fooled into thinking they were communicating with a human
being and not a program. But in fact, ELIZA had no idea what she was talking about. She
simply gave a canned response or repeated back what was said to her, rephrasing her
response with a few grammar rules. ELIZA was the first chatterbot
.

AI, ML & IIOT
2.2 Definitions
Supervised Learning
Supervised learning as the name indicates the presence of a supervisor as a teacher.
Basically supervised learning is a learning in which we teach or train the machine using
data which is well labeled that means some data is already tagged with the correct answer.
After that, the machine is provided with a new set of examples (data) so that supervised
learning algorithm analyses the training data (set of training examples) and produces a
correct outcome from labeled data.
Fig-4. Example illustration of Supervised Learning
Unsupervised Learning
Unsupervised learning is the training of machine using information that is neither classified
nor labeled and allowing the algorithm to act on that information without guidance. Here
the task of machine is to group unsorted information according to similarities, patterns and
differences without any prior training of data.
Unlike supervised learning, no teacher is provided that means no training will be given to
the machine. Therefore machine is restricted to find the hidden structure in unlabeled data
by our-self.
Fig-5. Example illustration of Unsupervised Learning

AI, ML & IIOT
Reinforcement Learning
Reinforcement learning is an area of Machine Learning. It is about taking suitable action to
maximize reward in a particular situation. It is employed by various software and machines
to find the best possible behavior or path it should take in a specific situation.
Reinforcement learning differs from the supervised learning in a way that in supervised
learning the training data has the answer key with it so the model is trained with the correct
answer itself whereas in reinforcement learning, there is no answer but the reinforcement
agent decides what to do to perform the given task.
Fig-6. Example illustration of Reinforcement Learning
Basics of Neural Networks
1) Weights – When input enters the neuron, it is multiplied by a weight. For example, if a
neuron has two inputs, then each input will have has an associated weight assigned to it.
We initialize the weights randomly and these weights are updated during the model
training process. The neural network after training assigns a higher weight to the input it
considers more important as compared to the ones which are considered less important. A
weight of zero denotes that the particular feature is insignificant.
2) Neuron- Just like a neuron forms the basic element of our brain, a neuron forms the
basic structure of a neural network. Just think of what we do when we get new
information. When we get the information, we process it and then we generate an output.
Similarly, in case of a neural network, a neuron receives an input, processes it and
generates an output which is either sent to other neurons for further processing or it is the
final output.
Fig-7. Weights Fig-8. Neuron

AI, ML & IIOT
3) Activation Function – Once the
linear component is applied to the input,
a non-linear function is applied to it.
This is done by applying the activation
function to the linear combination. The
activation function translates the input
signals to output signals. The output after
application of the activation function
would look something like f(a*W1+b). .Fig 9. Activation Function
In the above diagram we have “n” inputs given as X1 to Xn and
corresponding weights Wk1 to Wkn. We have a bias given as bk. The weights are first
multiplied to its corresponding input and are then added together along with the bias. Let
this be called as u.
u=∑w*x+b
4) Input / Output / Hidden Layer – Simply as the name suggests the input layer is the
one which receives the input and is essentially the first layer of the network. The output
layer is the one which generates the output or is the final layer of the network. The
processing layers are the hidden layers within the network. These hidden layers are the
ones which perform specific tasks on the incoming data and pass on the output generated
by them to the next layer. The input and output layers are the ones visible to us, while are
the intermediate layers are hidden.
Fig-10. Input/Output/Hidden Layer
5) MLP (Multi-Layer perceptron) – A single neuron would not be able to perform
highly complex tasks. Therefore, we use stacks of neurons to generate the desired outputs.
In the simplest network we would have an input layer, a hidden layer and an output layer.
Each layer has multiple neurons and all the neurons in each layer are connected to all the
neurons in the next layer. These networks can also be called as fully connected networks.
Fig-11.Multi-Layer perceptron

AI, ML & IIOT
6) Gradient Descent – Gradient descent is an optimization algorithm for minimizing the
cost. To think of it intuitively, while climbing down a hill you should take small steps and
walk down instead of just jumping down at once. Therefore, what we do is, if we start
from a point x, we move down a little i.e. delta h, and update our position to x-delta h and
we keep doing the same till we reach the bottom. Consider bottom to be the minimum
cost point.
Fig-12. Gradient Descent
Convolutional Neural Networks
7) Filters – A filter in a CNN is like a weight matrix with which we multiply a part of
the input image to generate a convoluted output. Let’s assume we have an image of
size 28*28. We randomly assign a filter of size 3*3, which is then multiplied with
different 3*3 sections of the image to form what is known as a convoluted output.
The filter size is generally smaller than the original image size. The filter values are
updated like weight values during back propagation for cost minimization. Consider
the below image. Here filter is a 3*3 matrix which is multiplied with each
3*3 section of the image to form the convolved feature.
Table-1.Filters

AI, ML & IIOT
8) CNN (Convolutional neural network) – Convolutional neural networks are basically
applied on image data. Suppose we have an input of size (28*28*3), If we use a normal
neural network, there would be 2352(28*28*3) parameters. And as the size of the image
increases the number of parameters becomes very large. We “convolve” the images to
reduce the number of parameters (as shown above in filter definition). As we slide the
filter over the width and height of the input volume we will produce a 2-dimensional
activation map that gives the output of that filter at every position. We will stack these
activation maps along the depth dimension and produce the output volume.
You can see the below diagram for a clearer picture.
Fig-13. Convolutional neural network
9) Pooling – It is common to periodically introduce pooling layers in between the
convolution layers. This is basically done to reduce a number of parameters and prevent
over-fitting. The most common type of pooling is a pooling layer of filter size(2,2) using
the MAX operation. What it would do is, it would take the maximum of each 4*4 matrix
of the original image.
Table-2.Pooling
10) Padding – Padding refers to adding extra layer of zeros across the images so that
the output image has the same size as the input. This is known as same padding.
Table-3.Padding

AI, ML & IIOT
2.3 Architecture/Block Diagrams
Fig-14.Block Diagram of Machine Learning Process
Setting up an architecture for machine learning systems and applications requires a good
insight in the various processes that play a crucial role. The basic process of machine
learning is feed training data to a learning algorithm. The learning algorithm then
generates a new set of rules, based on inferences from the data. So to develop a good
architecture you should have a solid insight in:
• The business process in which your machine learning system or application is used.
• The way humans interact or act (or not) with the machine learning system.
• The development and maintenance process needed for the machine learning system.
• Crucial quality aspects, e.g. security, privacy and safety aspects.
In its core a machine learning process exist of a number of typical steps. These steps are:
• Determine the problem you want to solve using machine learning technology
• Search and collect training data for your machine learning development process.
• Select a machine learning model
• Prepare the collected data to train the machine learning model
• Test your machine learning system using test data
Principles for Machine learning
Key principles that are used for this Free and Open Machine learning reference
architecture are:
1. The most important machine learning aspects must be addressed.
2. The quality aspects: Security, privacy and safety require speciﬁc attention.
3. The reference architecture should address all architecture building blocks from
development till hosting and maintenance.
4. Translation from architecture building blocks towards FOSS machine learning solution
building blocks should be easily possible.

AI, ML & IIOT
Classification of Machine Learning
Fig-15. Classification of Machine Learning
 Supervised learning addresses the task of predicting targets given input data.
 The goal of this type of learning is to model data and uncover trends that are
not obvious nit’s original state. The input data given to the learning algorithm is
unlabeled, and the algorithm is asked to identify patterns in the input data.
 Reinforcement Learning is close to human learning. Reinforcement learning
differs from standard supervised learning in that correct input/output pairs are
never presented, nor sub-optimal actions explicitly corrected. Instead the focus is
on performance. Reinforcement learning can be seen as learning best actions
based on reward or punishment.
Divisions in Artificial Intelligence
Fig-16. Divisions in Artificial Intelligence
Deep Learning (DL) is a type of machine learning that enables computer systems to
improve with experience and data.
 Deep learning uses layers to progressively extract features from the raw input. For
example, in image processing, lower layers may identify edges, while higher
layers may identify the concepts relevant to a human such as digits or letters or
faces.

AI, ML & IIOT
2.4 Configuring/Installing Peripherals
 LabVIEW: Installation Instruction (Windows)
1. Log in to TigerWare to download.
2. Click the Lab view: Software Platform Bundle Download Tool (Windows) to
download the program.
3. Once the Software platform bundle opens, click Next at the bottom right corner
of the window.
4. You will now see the Enter Serial Numbers screen. Go back to TigerWare and
download the Lab view Serial Number program.

AI, ML & IIOT
5.After confirming your account via email, enter your account details and click Next at
the bottom of the window.
6. Installation will proceed. Once finished, click Next at the bottom of the window.
 Python (Online Interpreter)
 Google Colab (Cloud Space)
 Kaggle (Cloud Space)

AI, ML & IIOT
2.5 Applications
Applications of AI
 Optical character recognition.
 Handwriting recognition.
 Speech recognition.
 Face recognition.
 Artificial creativity.
 Computer vision.
 Virtual reality.
 Image processing.
 Automotive
Fig-17. Applications of AI
Applications of IIOT
 Wearables
 Health
 Traffic monitoring
 Fleet management.
 Agriculture
 Hospitality
Fig-18. Applications of IIOT

AI, ML & IIOT
2.6 Advantages & Disadvantages
Advantages
 AI drives down the time taken to perform a task. It enables multi-tasking and
eases the workload for existing resources.
 AI enables the execution of hitherto complex tasks without significant cost
outlays.
 AI operates 24x7 without interruption or breaks and has no downtime
 AI augments the capabilities of differently abled individuals
 AI has mass market potential; it can be deployed across industries.
 AI facilitates decision-making by making the process faster and smarter.
 Fast processing and real-time predictions
 Machine Learning in the Medical Industry
 Data Input From Unlimited Resources
 No Human Interference id required
 Continuous Improvement
 Automation for everything
Disadvantages
 Data acquisition
In ML, we constantly work on data. We take a huge amount of data for training
and testing. This process can sometimes cause data inconsistency. The reason is some
data constantly keep on updating.
 Time and resources
Many ML algorithms might take more time than you think. Even if it’s the best
algorithm it might sometimes surprise you. If your data is large and advanced, the
system will take time. This may sometimes cause the consumption of more CPU
power.
 Algorithm Selection
The selection of an algorithm in Machine Learning is still a manual job. We have
to run and test our data in all the algorithms. After that only we can decide what
algorithm we want. We choose them on the basis of result accuracy. The process is
very much time-consuming.
 Interpretation
 High error susceptibility

AI, ML & IIOT
CHAPTER 3
INTERNSHIP DISCUSSION
3.1 How the objectives achieved?
During the period of Internship the below concepts are observed and implemented
practically in the required tools.
Understand python modules which are used for MLconcepts.
Scikit-learn (formerly scikits.learn and also known as sklearn) is a free software machine
learning library for the Python programming language. It features various classification,
regression and clustering algorithms including support vector machines, random forests,
gradient boosting, k-means and DBSCAN, and is designed to interoperate with the
Python numerical and scientific libraries NumPy and SciPy.
Key features and four distinct components of IIOT Systems.
 Interaction with multiple user interfaces
 Body motion interactivity functions
 Predictive design
 Increased security
Components of IIOT
 Devices
 Data
 Analytics
 Connectivity
Different Levels and characteristics of IIOT Systems.
 Device
 Resource
 Controller Service
 Database
 Web service
 Analysis Component
 Application

AI, ML & IIOT
3.2 What skills (scientific and professional) were learned during the internship?
Skills learned during the internship:-
 Python Programming
Of late, Python has become the unanimous programming language for
machine learning. In fact, experts quote that humans communicate with
machines through Python language.
 Scikit-Learn module
 Numpy module
 Keras module
 Pandas module
 Tensorflow module
 Matplotlib module
This is a basic programming language that was used for simulation of various
engineering models.
 Probability Theory and statistics
 Combination
 Bayes’sTheorem
 Standard Distributions(Bernoulli, Binomial, Uniform and Gaussian)
 Neural Network Architectures
 Convolutional Neural Network
 Data Optimization & Problem Solving
 Team-work and planning/prioritizing

AI, ML & IIOT
3.3 Results/observations/work experiences get in the internship
Work experience
 During the internship observed decision tree implementation and many
machine learning models, F-score calculation, About ANNOVA Etc.
 Done a project on Building machine Learning model for Titanic data analysis
problem statement and implemented through Cloud Space interpreter Called
Colab.
Titanic Data Analysis Machine Learning Model below
At
https://github.com/Rakeshpro/Projects/blob/master/Titanic_Data_Analysis_proj
ect-%7C.ipynb
Results/observations
Fig-19. Results/Observations

AI, ML & IIOT
3.4 What challenges did you experience during the internship?
Challenges which I experienced during the internship
 During kaggle competition experienced a challenge to implement a machine
learning model for Titanic Data Analysis problem statement. After many attempts
of machine learning models I succeeded which is exactly synchronized to the
problem statement and got high accuracy results.
 During the above implementation of machine learning models one more challenge
I faced for collecting the Dataset even though many Datasets are available in the
kaggle Cloud space I just ignored and collected independent dataset for the model.

AI, ML & IIOT
CHAPTER 4
CONCLUSIONS
This Internship has introduced me to Machine Learning. Now, I know that
Machine Learning is a technique of training machines to perform the activities a
human brain can do, albeit bit faster and better than an average human-being.
Today we have seen that the machines can beat human champions in games
such as Chess, AlphaGO, which are considered very complex. I have seen that
machines can be trained to perform human activities in several areas and can
aid humans in living better lives.
Machine Learning can be a Supervised or Unsupervised. If I have lesser amount
of data and clearly labeled data for training, opt for Supervised Learning.
Unsupervised Learning would generally give better performance and results for
large data sets. If I have a huge data set easily available, better to go for deep
learning techniques. I also have learned Reinforcement Learning and Deep
Reinforcement Learning. now I know what Neural Networks are, their
applications and limitations.
Finally, when it comes to the development of machine learning models of my
own, I looked at the choices of various development languages, IDEs and
Platforms. Next thing that I need to do is start learning and practicing each
machine learning technique. The subject is vast, it means that there is width, but
if I consider the depth, each topic can be learned in a few hours. Each topic is
independent of each other. I need to take into consideration one topic at a time
and implement the algorithm/s in it using a language choice of mine. This is the
best way to start studying Machine Learning. Practicing one topic at a time, very
soon I would acquire the width that is eventually required of a Machine Learning
expert.

AI, ML & IIOT
REFERENCES
[Only in IEEE Format]
Google AI
[1] Google AI Education-Discover collections tools and
resources. https://ai.google/education/ [Accessed May 19 2020].
[2] Machine Learning guide-developer.
https://developers.google.com/machine-learning/guides
[Accessed Jun 7 2020].
[3] Deep Learning-guide geeks for geeks.
https://www.geeksforgeeks.org/introduction-deep-learning/
[Accessed Jun 13 2020].

Internship report on AI , ML & IIOT and project responses full docs

Recomendados

Recomendados

Más contenido relacionado

La actualidad más candente

La actualidad más candente (20)

Similar a Internship report on AI , ML & IIOT and project responses full docs

Similar a Internship report on AI , ML & IIOT and project responses full docs (20)

Último

Último (20)

Internship report on AI , ML & IIOT and project responses full docs