Scribd
Upload
47 views4 pages

Theories, Detection Methods, and Opportunities of Fake News Detection

This document summarizes research on pattern recognition and fake news detection. It discusses common techniques for pattern recognition like convolutional neural networks and support vector machines. It also outlines the structure of a research paper, describing sections like the introduction, related work, problem formulation, methodology, experiments, results and discussion, conclusions, and references. The goal of the research was to develop a machine learning model to identify images using a CNN and achieve 80% accuracy on a dataset of pizza images.

Uploaded by

aditya
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
47 views4 pages

Theories, Detection Methods, and Opportunities of Fake News Detection

This document summarizes research on pattern recognition and fake news detection. It discusses common techniques for pattern recognition like convolutional neural networks and support vector machines. It also outlines the structure of a research paper, describing sections like the introduction, related work, problem formulation, methodology, experiments, results and discussion, conclusions, and references. The goal of the research was to develop a machine learning model to identify images using a CNN and achieve 80% accuracy on a dataset of pizza images.

Uploaded by

aditya
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 4

Springer Nature 2021 LATEX template

Theories, Detection Methods, and


Opportunities of Fake News detection
Aditya Khangar, Omprakash Choudhary, Govinda Kumar
and Mohit Kumar
Department of Computer Science and Engineering, Indian
Institute of Information Technology Kota, Jaipur, India. 302017.

Abstract
Abstract- The way we see world is changing a lot as we see reg-
ularly. Pattern recognition is not a new field of research, actually,
theories and techniques about it has developed for a long time. While
with the fast advancement of computer architecture, machine learn-
ing, and computer vision, computational complexity is possible to be
dealt with and more and more new ways of thinking are brought into
the research of pattern recognition. In this report, I‘d like to intro-
duce the basic concept, compact explanation, widely-used methods of
pattern recognition, and some outstanding applications are included.

Keywords: Convulational Neural Network, Support Vector Machine,


Computer Vision

1 Introduction
Pattern recognition is a process that taking in raw data and making an action
based on the category of the pattern. There are some interesting explanations
about the term pattern‘. Norbert Wiener said that —A pattern is essentially
an arrangement. It is characterized by the order of the elements of which it
is made, rather than by the intrinsic nature of these elements, and Watanabe
said that —A pattern is the opposite of a chaos; it is an entity vaguely defined,
that could be given a name. After analyzing the raw data based on a certain
purpose and method, we can do actions such as classification or clustering
on those raw data. Classification is to classify a data into known categories,

1
Springer Nature 2021 LATEX template

2 Article Title

while clustering is to create new categories from a set of data. In the sense of
training, classification is also called —supervised classification and clustering
as —unsupervised classification.
Human beings can easily recognize things or objects based on past learning
experiences. For example, when we look at a picture with cars, roads, people,
and building inside, we can tell which part is a person or a car, its shape,
and even the brand of a car or the gender of a specific person. But what do
computers do for recognition? Could they learn as what we did? Could they
directly tell what inside a digital picture? If not, what could we do to give
computers the ability as we have? This may be the motivation and purpose of
the research of pattern recognition.

2 Related Work
Pattern recognition and image recognition follow same path all together. There
are many works done before this and would be done after this too. We have read
about image detection and identification paper in which they have used CNN
as their main model and they use template matching as accuracy enhancer.

3 Problem
3.1 Problem Statement
To make a machine learning model for recognition of image.

3.2 Problem Definition


Practically we are going to train a model to identify an image accordingly and
name it. For example, we have used pizza images as our dataset soo whenever
a pizza photo will come in our model it may identify it easily.

4 Problem Formulation
4.1 Feature extraction
Feature extraction is a part of the dimensionality reduction process, in which,
an initial set of the raw data is divided and reduced to more manageable
groups. So when you want to process it will be easier. The most important
characteristic of these large data sets is that they have a large number of
variables. The technique of extracting the features is useful when you have
a large data set and need to reduce the number of resources without losing
any important or relevant information. Feature extraction helps to reduce the
amount of redundant data from the data set.
Springer Nature 2021 LATEX template

Article Title 3

4.2 Neural Network


A neural network consists of several simple processing elements called neurons.
Neural networks provide a simple computing paradigm to perform complex
recognition tasks in real time. The chapter categorizes neural networks into
three types: single-layer networks, multi-layer feed-forward networks, and feed-
back networks. Similar to the way that human beings learn from mistakes,
neural networks also could learn from their mistakes by giving feedback to the
input patterns. This kind of feedback would be used to reconstruct the input
patterns and make them free from error; thus increasing the performance of
the neural networks.

4.3 Artificial Neural Network


Artificial Neural Network has the ability to learn by examples. ANN is an
information processing model inspired by the biological neuron system. It
is composed of a large number of highly interconnected processing elements
known as the neuron to solve problems. Computational model consisting of sev-
eral processing elements recieves input and deliver output based on predefined
functions.
To much computation for neural network Sensitive to location of an object
.if the image pixels location change then it can not able to recogmise the image
Not able to find out accurate features for image classification

4.4 Convolutional Neural Network


A Convolutional neural network (CNN) is a neural network that has one
or more convolutional layers and are used mainly for image processing,
classification, segmentation and also for other auto correlated data.
CNN are used for image classification and recognition because of its high
accuracy. The CNN follows a hierarchical model which works on building a
network, like a funnel, and finally gives out a fully-connected layer where all
the neurons are connected to each other and the output is processed.

5 Problem Formulation
6 Methodology
The way we have progressed toward the implementation is quite simple. To
train our model we acquired data set from an open platform. Then Using
Tensor flow( Tensor Flow is a free and open-source software library for machine
learning and artificial intelligence. It can be used across a range of tasks but has
a particular focus on training and inference of deep neural networks), Feature
Extraction and Eventually training with CNN, We were able to process the
data and get the result with almost 80 percent accuracy.
Springer Nature 2021 LATEX template

4 Article Title

7 Experiments
The data set that we got from an open platform helped us in the experimen-
tation process. After training with almost 100 data, we were able to achieve
accuracy of just 34 percent. But as we increased the number of data for train-
ing our model, we achieved an accuracy of 81.2 percent. Now we are trying
to experiment with different data sets and data sets with a few noises, which
would in start decrease the accuracy but eventually would train the model
better.

8 Results and Discussions


Image AI provides many more features useful for customization and production
capable deployments for object detection tasks. Some of the features supported
are: - Adjusting Minimum Probability: By default, objects detected with a
probability percentage of less than 50 will not be shown or reported. You can
increase this value for high certainty cases. An example of pattern recogni-
tion is discussion, which attempts to assign each input value to one of a given
set of classes and get arround 80 percent. This is opposed to pattern match-
ing algorithms, which look for exact matches in the input with pre-existing
patterns.

9 Conclusions
We have just completed our work as team and then we got the processing of
images is faster and more cost-effective. One needs less time for processing, as
wel as less film and other photographing equipment. It is more ecological to
process images. No processing or fixing chemicals are needed to take and pro-
cess digital images. However, printing inks are essential when printing digital
images. When shooting a digital image, one can immediately see if the image
is good or not. Copying a digital image is easy, and the quality of the image
stays good unless it is compressed. However, it has some disadvantages too.
A digital file of a certain size cannot be enlarged with a good quality any-
more. For instance, a good poster cannot be made of an image file of 500 kb.
However, it is easy to make an image smaller

10 References
[1] T. O. Binford, ”Visual perception by computer,” in IEEE Conference on
Systems and Control, 1971. [2] Mukkamalla Rohith Sri Sai, ”Object Detection
and Identification”, in Research Gate

You might also like