Innovation (Projects on Python, Machine Learning & AI)

CHAPTER 1
COMPANY PROFILE
1.1 PROFILE
This chapter gives brief introduction about company its vision, mission values and inspirer of the
company. This also highlights the services offered, products developed by the company.

Fig 1 : Company logo

• Aqmenz Automation Private Limited was incorporated on 15th October 2018.

• It was founded by Mohan Shamanna and Mohammed Azhar Hussain
• INDOSKILL is a training platform, powered by Aqmenz Automation private limited, currently
providing Value-added Skill Development Courses to students on Current
• Trends & Real-time Industrial Projects.
• Our Motto and Vision are to create awareness & train the young generation to current and
future jobs demands
• We provide services to industries on Design, Software development & Automation
• Indoskill conducted 150+ Workshops and trained 20,000+ Engineering Students.

1.2 VISION AND GOALS

VISION
“Become a global leader in automation by leveraging cutting-edge technologies and best practices”

MISSION
“Deliver innovative and cost-effective automation solutions that enhance productivity, quality,
and safety of our customers”

Dept of CSE , RRIT 2023-24 1

Innovation (Projects on Python, Machine Learning & AI)

1.3 CONTACT DETAILS

No 62, 4th Cross, Manjunatha Layout C N Halli, R T Nagar Pb32 BANGALORE
Bangalore 560032

9743396604 / 9738802359

Dept of CSE , RRIT 2023-24 2

Innovation (Projects on Python, Machine Learning & AI)

CHAPTER 2
DEPARTMENT PROFILE
Organization structures the organization structure is having three different departments such as
design department, software department and sales and marketing.

AAPL

SALES &
DESIGN SOFTWARE MARKETING

2.1 Service 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 equipments for colleges.

2.2 Ongoing projects

Automation related projects
CNC Machines
Open-source Custom Robots
Garment Industry slider project

Dept of CSE , RRIT 2023-24 3

Innovation (Projects on Python, Machine Learning & AI)

CHAPTER 3

BASIC OF PYTHON
3.1 INTRODUCTION
 Python is a general-purpose high-level programming language.
 Python was developed by Guido Van Rossam in 1989 while working at National Research
 Institute at Netherlands.
 But officially Python was made available to public in 1993. The official Date of Birth for
 Python is: Feb 20th 1993.
 Python is recommended as the first programming language for beginners.

Ex: In C:
#include<stdio.h>
void main()
{
print("Hello world");
}
Output: Hello world

In Python:
Print(“Hello world”);
Output: Hello world

3.2 USE OF PYTHON

We can use it everywhere. The most common important application areas are:
 For developing Desktop Applications
 For developing web Applications
 For developing database Applications
 For Network Programming
 For developing games
 For Data Analysis Applications
 For Machine Learning and IOT
 For developing Artificial Intelligence Applications etc.……,

Dept of CSE , RRIT 2023-24 4

Innovation (Projects on Python, Machine Learning & AI)

3.3 Features of Python

Simple and easy to learn.

 Python is a simple programming language. When we read Python program, we can feel
like reading English statements.
 The syntaxes are very simple and only 30+ keywords are available.
 When compared with other languages, we can write programs with very less number of
lines.

Freeware and Open Source

 We can use Python software without any license, and it is freeware.

 Its source code is open, so that we can customize based on our requirement.
 Eg: Python is customized version of Python to work with Java Applications.

High Level Programming language

 Python is high level programming language and hence it is a programmer friendly

language.
 Being a programmer, we are not required to concentrate on low level activities like memory
management and security etc.
Platform Independent

o Once we write a Python program, it can run on any platform without rewriting once
again.
 Internally PVM is responsible for converting into machine understandable form.

Portability

 Python programs are portable. i.e. we can migrate from one platform to another platform
very easily. Python programs will provide same results on any platform.

3.4 Limitations of Python

 Performance wise not up to the mark because it is interpreted language.

 Not using for mobile Applications

Dept of CSE , RRIT 2023-24 5

Innovation (Projects on Python, Machine Learning & AI)

CHAPTER 4
MACHINE LEARNING
Machine Learning is a system that can learn from example through self-improvement and without
being explicitly coded by programmer. The breakthrough comes with the idea that a machine can
singularly learn from the data (i.e., example) to produce accurate results.

4.1 WHAT IS MACHINE LEARNING?

Machine learning combines data with statistical tools to predict an output. This output is
then used by corporate to make actionable insights. Machine learning is closely related to data
mining and Bayesian predictive modeling. The machine receives data as input, use an algorithm
to formulate answers.
A typical machine learning task is to provide a recommendation. For those who have a
Netflix account, all recommendations of movies or series are based on the user's historical data.
Tech companies are using unsupervised learning to improve the user experience with personalizing
recommendations. Machine learning is also used for a variety of task like fraud detection,
predictive maintenance, portfolio optimization, automatize task and so on.
4.2 HOW DOES MACHINE LEARNING WORK?
Machine learning is the brain where all the learning takes place. The way the machine
learns is similar to the human being. Humans learn from experience. The more we know, the more
easily we can predict. By analogy, when we face an unknown situation, the likelihood of success
is lower than the known situation.
Machines are trained the same. To make an accurate prediction, the machine sees an
example. When we give the machine a similar example, it can figure out the outcome. However,
like a human, if it feed a previously unseen example, the machine has difficulties to predict.
4.3 WHY MACHINE LEARNING?
The world today is evolving and so are the needs and requirements of people. Furthermore,
we are witnessing a fourth industrial revolution of data. In order to derive meaningful insights
from this data and learn from the way in which people and the system interface with the data, we
need computational algorithms that can churn the data and provide us with results that would
benefit us in various ways.

Dept of CSE , RRIT 2023-24 6

Innovation (Projects on Python, Machine Learning & AI)

Machine Learning has revolutionized industries like medicine, healthcare, manufacturing,

banking, and several other industries. Therefore, Machine Learning has become an essential part
of modern industry.
Furthermore, machine learning has facilitated the automation of redundant tasks that have taken
away the need for manual labor. All of this is possible due to the massive amount of data that you
generate daily. Machine Learning facilitates several methodologies to make sense of this data and
provide you with steadfast and accurate results. Different Types of Machine Learning
1. Supervised Machine Learning
2. Unsupervised Machine Learning
3. Reinforcement Machine Learning
4. Semi Supervised Machine Learning

Dept of CSE , RRIT 2023-24 7

Innovation (Projects on Python, Machine Learning & AI)

CHAPTER 5
ALGORITHMS
5.1 LINEAR REGRESSION
Definition
Linear Regression establishes a relationship between dependent variable (Y) and one or
more independent variables (X) using a best fit straight line (also known as regression line).

It is represented by an equation Y = a + b * X + e, where a is intercept, b is slope of the

line and e is error term. This equation can be used to predict the value of target variable based on
given predictor variable(s).

Figure 2 Regression analysis How to obtain best fit line

It calculates the best-fit line for the observed data by minimizing the sum of the squares of
the vertical deviations from each data point to the line. Because the deviations are first squared,
then added, there is no cancelling out between positive and negative values.

Advantages
Linear regression is an extremely simple method. It is very easy and intuitive to use and
understand. A person with only the knowledge of high school mathematics can understand and use
it. In addition, it works in most of the cases. Even when it doesn’t fit the data exactly, we can use
it to find the nature of the relationship between the two variables.

Dept of CSE , RRIT 2023-24 8

Innovation (Projects on Python, Machine Learning & AI)

Disadvantage

 By its definition, linear regression only models‟ relationships between dependent and
independent variables that are linear. It assumes there is a straight-line relationship between
them which is incorrect sometimes.
 Take for example most of your data lies in the range 0-10. If due to any reason only one of
the data items comes out of the range, say for example 15, this significantly influences the
regression coefficients.

 Another disadvantage is that if we have a number of parameters than the number of samples
available then the model starts to model the noise rather than the relationship between the
variables.
5.2 MULTIPLE LINEAR REGRESSION
Multiple linear regression (MLR), also known simply as multiple regression, is a statistical
technique that uses several explanatory variables to predict the outcome of a response variable.
The goal of multiple linear regression (MLR) is to model the linear relationship between the
explanatory (independent) variables and response (dependent) variable.
A simple linear regression is a function that allows an analyst or statistician to make
predictions about one variable based on the information that is known about another variable.
Linear regression can only be used when one has two continuous variables an independent variable
and a dependent variable. The independent variable is the parameter that is used to calculate the
dependent variable or outcome.
Definition
In many cases, there may be possibilities of dealing with more than one predictor variable for
finding out the value of the response variable. Therefore, the simple linear models cannot be
utilized as there is a need for undertaking Multiple Linear Regression for analyzing the predictor
variables. Using the two explanatory variables, we can delineate the equation of Multiple Linear
Regression as follows:
yi = β0 + β1x1i + β2x1i + εi
The two explanatory variables x1i and x1i, determine yi, for the ith data point. Furthermore, the
predictor variables are also determined by the three parameters β0, β1, and β2 of the model, and
by the

Dept of CSE , RRIT 2023-24 9

Innovation (Projects on Python, Machine Learning & AI)

residual ε1 of the point i from the fitted surface.

General Multiple regression models can be represented as:
yi = Σβ1x1i + εi
Advantages of multiple regression
 Any disadvantage of using a multiple regression model usually comes down to the data
being used. Two examples of this are using incomplete data and falsely concluding that a
correlation is causation.
 When reviewing the price of homes, for example, suppose the real estate agent looked at
only 10 homes, seven of which were purchased by young parents. In this case, the
relationship between the proximity of schools may lead her to believe that this had an effect
on the sale price for all homes being sold in the community.
Disadvantages of multiple regression
 Multiple regression model usually comes down to the data being used. Two examples of
this are using incomplete data and falsely concluding that a correlation is causation. When
reviewing the price of homes, for example, suppose the real estate agent looked at only 10
homes, seven of which were purchased by young parents.
 In this case, the relationship between the proximity of schools may lead her to believe that
this influenced the sale price for all homes being sold in the community.
 This illustrates the pitfalls of incomplete data. Had she used a larger sample, she could have
found that, out of 100 homes sold, only ten percent of the home values were related to a
school's proximity.
5.3 LOGISTIC REGRESSION
 Logistic regression is one of the most popular Machine Learning algorithms, which comes
under the Supervised Learning technique. It is used for predicting the categorical dependent
variable using a given set of independent variables.
 Logistic regression predicts the output of a categorical dependent variable. Therefore, the
outcome must be a categorical or discrete value. It can be either Yes or No, 0 or 1, true or
False, etc. but instead of giving the exact value as 0 and 1, it gives the probabilistic values
which lie between 0 and 1.

Dept of CSE , RRIT 2023-24 10

Innovation (Projects on Python, Machine Learning & AI)

 Logistic Regression is much similar to the Linear Regression except that how they are used.
Linear Regression is used for solving Regression problems, whereas Logistic regression is
used for solving the classification problems.
 In Logistic regression, instead of fitting a regression line, we fit an "S" shaped logistic
function, which predicts two maximum values (0 or 1).
 The curve from the logistic function indicates the likelihood of something such as whether
the cells are cancerous or not, a mouse is obese or not based on its weight, etc.
 Logistic Regression is a significant machine learning algorithm because it has the ability
provide probabilities and classify new data using continuous and discrete datasets.
 Logistic Regression can be used to classify the observations using different types of data
and can easily determine the most effective variables used for the classification. The below
image is showing the logistic function:

Fig 3 Logistic Regression Graph

5.4 KNN Algorithm

What is KNN Algorithm?
K nearest neighbor or KNN Algorithm is a simple algorithm which uses the entire dataset
in its training phase. Whenever a prediction is required for an unseen data instance, it searches

Dept of CSE , RRIT 2023-24 11

Innovation (Projects on Python, Machine Learning & AI)

through the entire training dataset for k-most similar instances and the data with the most similar
instance is finally returned as the prediction.

KNN is often used in search applications where you are looking for similar items, like find items
like this one.
Advantage of KNN algorithm
 The algorithm is simple and easy to implement.
 There’s no need to build a model, tune several parameters, or make additional assumptions.
 The algorithm is versatile. It can be used for classification, regression, and search.
 The training phase of K-nearest neighbor classification is much faster compared to other
classification algorithms. There is no need to train a model for generalization that is why
KNN is known as the simple and instance-based learning algorithm.
 KNN can be useful in case of nonlinear data. It can be used with the regression problem.
Output value for the object is computed by the average of k closest neighbours‟ value.
Disadvantage of KNN

 The algorithm gets significantly slower as the number of examples and/or

predictors/independent variables increase.
 The testing phase of K-nearest neighbour classification is slower and costlier in terms
of time and memory. It requires large memory for storing the entire training data set
for prediction.
 KNN requires scaling of data because KNN uses the Euclidean distance between two
data points to find nearest neighbours. Euclidean distance is sensitive to magnitudes.
The features with high magnitudes will weigh more than features with low magnitudes.
 KNN also not suitable for large dimensional data.

5.5 SUPPORT VECTOR MACHINES (SVM)

Generally, Support Vector Machines is considered to be a classification approach, it but

can be employed in both types of classification and regression problems. It can easily handle
multiple continuous and categorical variables. SVM constructs a hyperplane in
multidimensional space to separate different classes. SVM generates optimal hyperplane in an

Dept of CSE , RRIT 2023-24 12

Innovation (Projects on Python, Machine Learning & AI)

iterative manner, which is used to minimize an error. The core idea of SVM is to find a
maximum marginal hyperplane (MMH) that best divides the dataset into classes.

Fig 4 Support Vectors

Support vectors are the data points, which are closest to the hyperplane. These points will define
the separating line better by calculating margins. These points are more relevant to the construction
of the classifier.

5.6 DECISION TREE ALGORITHM

 Decision Tree is a Supervised learning technique that can be used for both classification
and Regression problems, but mostly it is preferred for solving Classification problems. It
is a tree-structured classifier, where internal nodes represent the features of a dataset,
branches represent the decision rules, and each leaf node represents the outcome.
 In a Decision tree, there are two nodes, which are the Decision Node and Leaf Node.
Decision nodes are used to make any decision and have multiple branches, whereas Leaf
nodes are the output of those decisions and do not contain any further branches.
 The decisions or the test are performed on the basis of features of the given dataset.
 It is a graphical representation for getting all the possible solutions to a problem/decision
based on given conditions.
 It is called a decision tree because, similar to a tree, it starts with the root node, which
expands on further branches and constructs a tree-like structure.

Dept of CSE , RRIT 2023-24 13

Innovation (Projects on Python, Machine Learning & AI)

 To build a tree, we use the CART algorithm, which stands for Classification and
Regression Tree algorithm.
 A decision tree simply asks a question and based on the answer (Yes/No), it further split
the tree into subtrees.
 Below diagram explains the general structure of a decision tree:4

Fig 5 Decision Tree

How does the Decision Tree algorithm Work?

In a decision tree, for predicting the class of the given dataset, the algorithm starts from the
root node of the tree. This algorithm compares the values of root attribute with the record (real
dataset) attribute and, based on the comparison, follows the branch and jumps to the next node.

For the next node, the algorithm again compares the attribute value with the other sub-
nodes and move further. It continues the process until it reaches the leaf node of the tree. The
complete process can be better understood using the below algorithm:

Step-1: Begin the tree with the root node, says S, which contains the complete dataset.

Step-2: Find the best attribute in the dataset using Attribute Selection Measure (ASM).

Step-3: Divide the S into subsets that contains possible values for the best attributes.

Step-4: Generate the decision tree node, which contains the best attribute.

Step-5: Recursively make new decision trees using the subsets of the dataset created in step -3.

Dept of CSE , RRIT 2023-24 14

Innovation (Projects on Python, Machine Learning & AI)

Continue this process until a stage is reached where you cannot further classify the nodes and

called the final node as a leaf node.

Advantages of the Decision Tree

 It is simple to understand as it follows the same process which a human follow while
making any decision in real-life.
 It can be very useful for solving decision-related problems.
 It helps to think about all the possible outcomes for a problem.
 There is less requirement of data cleaning compared to other algorithms.

Disadvantages of the Decision Tree

 The decision tree contains lots of layers, which makes it complex.

 It may have an overfitting issue, which can be resolved using the Random Forest algorithm.
 For more class labels, the computational complexity of the decision tree may increase.

Dept of CSE , RRIT 2023-24 15

Innovation (Projects on Python, Machine Learning & AI)

CHAPTER 6
TASKS ASSIGNED
6.1 INTRODUCTION
The Introduction section sets the stage for the entire project, providing readers with essential context
and a clear understanding of the project's objectives. It serves as a critical bridge between the cover
page and the core content of the report.

In the context of our project, "Predictive Institute Results Analysis for Academic Planning," the
introduction begins by outlining the project's overarching goal: to develop a machine learning-based
system that predicts institute Result Analysis. This system aims to address a pressing need for
accurate Result.

Significance of Institute Result Prediction

In today's dynamic educational landscape, institutions are continually seeking ways to enhance their
academic planning processes. One powerful tool that has gained prominence is predictive analysis.
Predictive analysis harnesses the power of data and statistical modeling to provide valuable insights
that can inform decision-making in various sectors, including academia.

Machine learning in institute Result Prediction

Machine learning is transforming institute result prediction by analyzing student data to forecast
academic outcomes. Using historical records and various data sources, machine learning models can
identify at-risk students, enabling timely interventions and personalized learning. While offering
significant benefits, ethical considerations, including data privacy and fairness, must be addressed for
responsible implementation in educational institutions.

6.2 PROJECT DESCRIPTION

Its primary aim is to predict the future results of all the branches of the institute by referring the
previous year dataset. So that if the management are not satisfied by the results, they can change the
teaching style or any other changes in the institute to get a better result.

Dept of CSE , RRIT 2023-24 16

Innovation (Projects on Python, Machine Learning & AI)
6.3 OBJECTIVES
Predictive Model Creation: Our primary goal was to design and implement a predictive model
capable of institute results with accuracy.
Accuracy Assessment: We sought to rigorously evaluate the predictive model’s precision
and reliability by employing appropriate evaluation metrics.
Practical Application: We aimed to demonstrate how accurate the result of institutions
prediction can offer valuable insight of the management of the institution for provide a better
education.

6.4 PROBLEM STATEMENT

Academic institutions require an accurate and ethical means of predicting institute results and
academic outcomes to improve academic planning and student success. This project seeks to
develop a machine learning-based system that can effectively predict institute result analysis
while addressing data privacy and fairness concerns, ultimately empowering educational
institutions to make informed decisions and support their students effectively.

6.5 SOURCE CODE

1.Data Collection:
You can use a dataset that includes information about video game sales. A popular dataset is available
on Kaggle: Video Game Sales with Ratings.

2. Data Preprocessing:
Clean and preprocess the dataset, handling missing values, encoding categorical variables, and scaling
numerical features.

CODE:-
from mpl_toolkits.mplot3d import Axes3D
from sklearn.preprocessing import StandardScaler
import matplotlib.pyplot as
import numpy as np
import os
import pandas as pd
for dirname, _, filenames in os.walk('/kaggle/input'):

Dept of CSE , RRIT 2023-24 17

Innovation (Projects on Python, Machine Learning & AI)
for filename in filenames:
print(os.path.join(dirname, filename))
def plotPerColumnDistribution(df, nGraphShown, nGraphPerRow):
nunique = df.nunique()
df = df[[col for col in df if nunique[col] > 1 and nunique[col] < 50]]
nRow, nCol = df.shape
columnNames = list(df)
nGraphRow = (nCol + nGraphPerRow - 1) / nGraphPerRow
plt.figure(num = None, figsize = (6 * nGraphPerRow, 8 * nGraphRow), dpi = 80, facecolor = 'w',
edgecolor = 'k')
for i in range(min(nCol, nGraphShown)):
plt.subplot(nGraphRow, nGraphPerRow, i + 1)
columnDf = df.iloc[:, i]
if (not np.issubdtype(type(columnDf.iloc[0]), np.number)):
valueCounts = columnDf.value_counts()
valueCounts.plot.bar()
else:
columnDf.hist()
plt.ylabel('counts')
plt.xticks(rotation = 90)
plt.title(f'{columnNames[i]} (column {i})')
plt.tight_layout(pad = 1.0, w_pad = 1.0, h_pad = 1.0)
plt.show()
def plotCorrelationMatrix(df, graphWidth):
filename = df.dataframeName
df = df.dropna('columns') # drop columns with NaN
df = df[[col for col in df if df[col].nunique() > 1]] # keep columns where there are more than 1
unique values
if df.shape[1] < 2:
print(f'No correlation plots shown: The number of non-NaN or constant columns ({df.shape[1]}) is
less than 2')
return

Dept of CSE , RRIT 2023-24 18

Innovation (Projects on Python, Machine Learning & AI)
corr = df.corr()
plt.figure(num=None, figsize=(graphWidth, graphWidth), dpi=80, facecolor='w', edgecolor='k')
corrMat = plt.matshow(corr, fignum = 1)
plt.xticks(range(len(corr.columns)), corr.columns, rotation=90)
plt.yticks(range(len(corr.columns)), corr.columns)
plt.gca().xaxis.tick_bottom()
plt.colorbar(corrMat)
plt.title(f'Correlation Matrix for {filename}', fontsize=15)
plt.show()
def plotScatterMatrix(df, plotSize, textSize):
df = df.select_dtypes(include =[np.number]) # keep only numerical columns
# Remove rows and columns that would lead to df being singular
df = df.dropna('columns')
df = df[[col for col in df if df[col].nunique() > 1]]
columnNames = list(df)
if len(columnNames) > 10:
columnNames = columnNames[:10]
df = df[columnNames]
ax = pd.plotting.scatter_matrix(df, alpha=0.75, figsize=[plotSize, plotSize], diagonal='kde')
corrs = df.corr().values
for i, j in zip(*plt.np.triu_indices_from(ax, k = 1)):
ax[i, j].annotate('Corr. coef = %.3f' % corrs[i, j], (0.8, 0.2), xycoords='axes fraction', ha='center',
va='center', size=textSize)
plt.suptitle('Scatter and Density Plot')
plt.show()
df1 = pd.read_csv('/kaggle/input/Video_Games_Sales_as_at_22_Dec_2016.csv', delimiter=',', nrows =
nRowsRead)
df1.dataframeName = 'Video_Games_Sales_as_at_22_Dec_2016.csv'
nRow, nCol = df1.shape
print(f'There are {nRow} rows and {nCol} columns')
df1.head(5)
plotPerColumnDistribution(df1, 10, 5)

Dept of CSE , RRIT 2023-24 19

Innovation (Projects on Python, Machine Learning & AI)

CHAPTER 7
RESULTS
7.1 OUTPUTS

df1.head(5) :-

Distribution graphs (histogram/bar graph) of sampled columns

plotPerColumnDistribution(df1, 10, 5)

Fig 6 Distribution Graph of Sampled Columns

Dept of CSE , RRIT 2023-24 20

Innovation (Projects on Python, Machine Learning & AI)

Corelation Matrix
plotCorrelationMatrix(df1, 8)

Fig 7 Corelation Matrix

Dept of CSE , RRIT 2023-24 21

Innovation (Projects on Python, Machine Learning & AI)

CHAPTER 8
ARTIFICIAL INTELLIGENCE

Fig 8 Artificial intelligence

Artificial intelligence (AI) is the intelligence of machines or software, as opposed to the intelligence of
humans or animals. It is the subject of an eponymous field of study in computer science, which
develops and studies intelligent machines. The term AI may also refer to the intelligent machines
themselves.

8.1 History of Artificial Intelligence:

Artificial Intelligence was first proposed by John McCarthy in 1956 in his first academic conference
on the subject. The idea of machines operating like human beings began to be the center of scientist’s
mind and whether if it is possible to make machines have the same ability to think and learn by itself
was introduced by the mathematician Alan Turing. Alan Turing was able to put his hypotheses and
questions into actions by testing whether “machines can think”? After series of testing (later was
called as Turing Test) it turns out that it is possible to enable machines to think and learn just like
humans. Turing Test uses the pragmatic approach to be able to identify if machines can respond as
humans. (“Smith”, (n.d.))

Dept of CSE , RRIT 2023-24 22

Innovation (Projects on Python, Machine Learning & AI)
8.2 AI Algorithms and Models
AI is mainly based on algorithms and models as a technique which is designed based on scientific
findings such as math, statists, and biology (Li& Jiang, (n.d.)). AI works based on several models
such as: Ant Colon Algorithm, Immune Algorithm, Fuzzy Algorithm, Decision Tree, Genetic
Algorithm, Particle Swarm Algorithm, Neural Network, Deep Learning and in this report, I will
discuss some of the most known models which are: Support Vector Machine, and the Artificial
Neural Network.
• Support Vector Machine (SVM) where it is used to build a classification model by finding an
optimal hyperplane based on a set of training examples as shown in (figure A-1). It is also have been
used for pattern classification and trend prediction lots of applications for instance: power
transformer fault diagnosis, disease diagnosis and treatment optimization. (Li& Jiang, (n.d.)).

Figure 9 Describes how SVM algorithm being represented in AI

8.3 Some Applications on Artificial Intelligence:

AI can be designed using lots of algorithms. These algorithms help the system to determine the
expected response which will basically tell the computer what to expect and work accordingly. Here
are some of the greatest AI applications that we are probably using in our daily life without knowing:
o Voice recognition
o Virtual agents:
o Machine learning platform
o Ai optimized hardware
o Decision management

Dept of CSE , RRIT 2023-24 23

Innovation (Projects on Python, Machine Learning & AI)
o Deep learning platform
o Biomatters
o Robotic process automation
o Text analytics and NLP
o Adaptive Manufacturing: Machines that are “able to learn a multitude of tasks from
demonstrations, just like their human counterparts can.” (“Yoa”,2017))

8.4 AI Design Models

AI application are a lot around us and in this paper, I will discuss some of the most common
application of AI that we always use nowadays which is Virtual Assistants such as Siri, Cortana...etc.
Over the past few years smart assistants are becoming a very common technology in most of the
smart devices and most importantly, that these assistants are getting smarter than ever. In addition to
the awesome help they provide us with, is that every one of these apps has unique features. Artificial
Intelligence works according to the following phases: getting the data, clean/manipulate/ prepare the
data, train model, test data, and improve the data as mentioned in (figure A-3). Before accessing the
data, a business must verify the quality of the data to ensure that it meets the requirement.

Figure 10 Describes Phases of Developing Artificial

Siri Virtual Assistant:

Siri is the well-known virtual assistant which uses voice recognitions and typed command in order to
perform a certain task within a device. Siri is considered one of AI most used applications. The
application simply takes the input from the user such as (e.g. Call dad) and try to find the most
related keywords used in this command. Siri tries to eliminate inconsistent result through using the
language pattern recognizer and from there to active ontology by searching through the contacts, then
it tries to relate the contact named “Dad” and perform the task which is in this case is “Calling” and
finally the output of this action will be “calling dad” .

Dept of CSE , RRIT 2023-24 24

Innovation (Projects on Python, Machine Learning & AI)

Figure 11 Describes one Example of configuration for Siri

In another scenario the architecture of the virtual assistant is shown in (figure A – 5) as we can see
the flow of the system starts by taking the input from the user, after that the system decide the
conversation strategy module to be used which is a respond from the dialog management module,
meanwhile a classification module response to an NLP module. Finally, using the conversation
history database is used to analyze the knowledge base construction module which will response
back to the domain knowledge based as explained in detail in (figure A- 5)

Figure 12 Describes Proposed conversational agent architecture

Dept of CSE , RRIT 2023-24 25

Innovation (Projects on Python, Machine Learning & AI)

CHAPTER 9
CONCLUSION

The Conclusion section marks the culmination of our project, "Predictive Institute Results Analysis for
Academic Planning." In this section, we summarize the key achievements and outcomes of our
endeavor, reflecting on its broader significance.
Our project embarked with the overarching goal of developing a predictive Institute Result analysis
system to aid agricultural planning. Through meticulous data analysis, model development, and
evaluation, we have achieved substantial progress in this regard.
One of the standout achievements of our project is the development of a data-driven Institute Results
prediction model. This model, based on Linear Regression, exhibits promising accuracy in forecasting
institute result patterns. It holds the potential to revolutionize institute result prediction for academic’s
purposes.
Enhanced academic planning, driven by data-driven insights and advanced predictive modeling,
optimizes resource allocation, supports personalized learning, and identifies at-risk students for timely
interventions. This approach empowers educational institutions to make informed decisions and improve
overall student success.
In the comparison between our project and existing institute result prediction systems, it becomes
evident that our approach offers significant benefits. The enhanced accuracy, timeliness, and
adaptability of our predictive model make it a promising solution for the future.

Dept of CSE , RRIT 2023-24 26

Innovation (Projects on Python, Machine Learning & AI)

REFERENCES
file:///C:/Users/puneeth/OneDrive/Desktop/ArtificialIntellegence.pdf :- Artificial intelligence PDF

https://en.wikipedia.org/wiki/Artificial_intelligence :- Artificial intelligence Wikipedia

Artificial Intelligence Technology and Engineering Applications. (2017). ACES JOURNAL, 32, 5th ser.,
381-386. Retrieved November 23, 2017, from file:///C:/Users/lenovo/Desktop/ContentServer%20(1).pdf

Apple introduces us to Siri, the Killer Patent. (2012, January 19). Retrieved November 25, 2017, from
http://www.patentlyapple.com/patently-apple/2012/01/apple-introduces-us-to-siri-the- killer-patent.html

Sophia The A.I Robot [Video File]. Retrieved from https://www.youtube.com/watch?v=wimUaNqEJyw

Galeon, D., & Gphd, C. (2017, October 20). Dubai just appointed a "State Minister for Artificial
Intelligence". Retrieved November 22, 2017, from https://futurism.com/

Hong, K. (n.d.). Machine Learning with scikit-learn. Retrieved November 22, 2017, from
http://www.bogotobogo.com/python/scikit

Dept of CSE , RRIT 2023-24 27

Innovation (Projects on Python, Machine Learning & AI)

Dept of CSE , RRIT 2023-24 28