International Journal of Research in Engineering and Science (IJRES)

ISSN (Online): 2320-9364, ISSN (Print): 2320-9356

www.ijres.org Volume 10 Issue 10 ǁ October 2022 ǁ PP. 274-279

A review on Machine Learning: Application and

Algorithms
1
Diksha, 2Monika, 3Palvi, 4Pankaj Verma
1
Diksha Department of CSA, Arni University, Kathgarh Indora H.P, India
2
Monika Department of CSA, Arni University, Kathgarh Indora H.P, India
3
Palvi Department of CSA, Arni University, Kathgarh Indora H.P, India
4
Pankaj Verma Department of CSA, Arni University, Kathgarh Indora H.P, India
Corresponding Author: Pankaj Verma

Abstract: The field of machine learning is introduced at a conceptual level. The main goal of machine learning
is how computers automatically learn without any human invention or assistance so that they can adjust their
action accordingly. We are discussing mainly three types of algorithms in machine learning and also discussed
ML’s features and applications in detail. Supervised ML, In this typeof algorithm, the machine applies what it
has learned in its past to new data, in which they use labeled examples, so that they predict future events.
Unsupervised ML studies how systems can infer a function, so that they can describe a hidden structure from
unlabeled data. Reinforcement ML, is a type of learning method, which interacts with its environment, produces
action, as well as discovers errors and rewards.
Keywords: Machine Learning, Applications, Algorithms, Features.
----------------------------------------------------------------------------------------------------------------------------- ----------
Date of Submission: 26-09-2022 Date of acceptance: 11-10-2022
----------------------------------------------------------------------------------------------------------------------------- ----------

I. Introduction
Artificial intelligence is providing the field of machine learning. Machine learning was released by
Arthur Samuel in the year of 1959. Machine learning is a type of learning, in which the machines Learns over
selves. It is a machine that has the ability to think and make decisions. Machine learning is a type of application
that provides systems with the ability to learn automatically and improve over selves if needed. We can generate
a program that has been made to integrate the input and output of the same program. The main goal of machine
learning is how computers automatically learn without any human invention or assistance so that they can adjust
their action accordingly. According to need for machine learning is increasing to day by day. In the main reason
is that are too complex for person to implement directly. A concise review of what ML includes can be found in.
De Mantras’ and Armengol (1998) also presented a historical survey of logic and 25 instances-based learning
classifiers.[1]

Figure 1 Machine Learning

To implement machine learning, we can also discuss some algorithms in it... Like:-
 Supervised machine learning algorithm
 Unsupervised machine learning algorithm
 Reinforcement machine learning algorithm

www.ijres.org 274 | Page

 A review on Machine Learning: Application and Algorithms

1.1 Supervised Machine Learning Algorithm:-In this type of algorithm, the machine applies what it has
learned in its past to new data , in which they use labeled examples, so that they predict future events. To
analyzing a known training dataset, this learning algorithm produces a kind of inferred function which can easily
make predictions regarding the output values [2]. This system can provide them targets for new inputs to give
them sufficient training, and it compares the resulting output with the correct, intended output and finds errors,
so that they can modify the model accordingly...

1.1.1 Types of Supervised Machine Learning Algorithm:-

Supervised machine learning algorithms are divided into two groups “Regression and Classification”. The main
goal of both these method is that the relationship in structure determine correct output data and both have the
goal of finding the value of dependent variable from the attribute variable[3].
Regression: - It is a technique use to find out the relationship between independent and dependent. Also
regression is used as a method of predictive modeling in machine learning. If there is a relationship between the
input or output variables, then regression algorithm is used in it. Further regression is divided into sub parts:-
 Linear regression:-Linear regression is the supervised Machine Learning model in which the model
finds the best fit linear line between the independent and dependent variable.

 Non -Linear regression:- Non -Linear regression is a statistical technique that help describes nonlinear
relationship in experimental data
 Polynomial regression:- This regression algorithm that model the relationship between a dependent and
independent variable as nth degree polynomial. [4]

 Regression trees:- this regressing tree is basically a decision tree that is used for the task of regression
which can be used to predicate continuous valued outputs instead of discrete outputs.
Classification:-when inputs are divided into two or more classes and the learner produces a model that assigns
unseen Inputs to one or more classes. It is usually set about in a supervised way.
In classification, some mathematical techniques are used:-
 Decision Tree: provided an overview of work in decision trees and a sample of their usefulness to
newcomers as well as practitioners in the field of machine learning. Decision trees are Rees that classify
instances by sorting them based on feature values.[5]In decision tree there is two nodes parent node and child
node it is also known asdecision node and leaf node. The parent node has branches and child nodes are the result
of the parent nodes.

 Linear programming: -Decision trees can be translated into a set of rules by creating a separate rule
for each path from the root to a leaf in the tree . However, rules can also be directly induced from training data
using a variety of rule-based algorithms. A large number of learned rules is usually a sign that the learning
algorithm is attempting to “remember” the training set, instead ofdiscovering the assumptions that govern it.[6]

 Neural Networks: - Perceptions can only classify linearly separable sets of instances. If a straight line
or plane can be drawn to separate the input instances into their correct categories, input instances are linearly
separable and the preceptor will find the solution. Provided an overview of existing work in Artificial Neural
Networks (ANNs)

1.1.2 Applications of Supervised Machine Learning

There are many applications of supervised machine learning, these applications are as follows:-
1. Online machine learning.
2. Speech recognition
3. Spam detection
4. Object-recognition for vision

1.1.3 Features of supervised machine learning:-

Supervised learning used a training set to each models to yield the desired outputs. This training dataset includes
inputs and correct output, which allow the model to learn over time.

1.2 Unsupervised Machine Learning:-Unsupervised machine learning algorithm are used when the
information is to be trained and not classified alone or labeled. Machine cannot identify the difference between
features of humans and animals. But it can identify the similarities, structure and differences. This system does
not describe any right output, but it explores the data.[7]

www.ijres.org 275 | Page

 A review on Machine Learning: Application and Algorithms

1.2.1Types of unsupervised machine learning

Clustering is a task of unsupervised machine learning. It involves automatically discovering natural grouping in
data with two or more variable quantities. Group cannot be known in advance, expect for its classification,
which make it’s a typically unsupervised task. Always remember machine learning come into picture only when
problem cannot be solving with typical approaches.
 Partitioning clustering: -Partitioning clustering are clustering methods used to classify observations, within a
dataset, into multiple groups based on their similarity.

 Density-based clustering:- density based clustering refer to unsupervised learning methods that identify
distinctive groups /clusters in the data, based on the idea that a cluster in a data space is a contiguous region of
high point density, separated from other such cluster by contiguous regions of low point density.

 Distribution model-based clustering: - Model based clustering is a statistical approach to data clustering.
The observed data is considered to have been created from a finite combination of component models.

 Hierarchical clustering: -Hierarchical clustering is another unsupervised machine learning algorithm, which
is used to group the unlabeled datasets into a cluster and it is also known as hierarchical cluster analysis. The
Hierarchical clustering technique has two approaches: - Bottom- up approach, top-down approach.

 Fuzzy clustering: - this algorithm works by assigning membership to each data point corresponding to each
cluster center on the basic of distance between the cluster center and the data point.[8]
Association: -Association is a technique that describes how objects are associated with each other. Association
is a very well know method of finding relationship between variables in large databases.[9]

1.2.2 Applications of Unsupervised Machine Learning:-

1. Products segmentation
2. Customer segmentation
3. Similarity detection
4. Recommendation system
5. Labeling unlabelled datasets

1.2.3 Features of Unsupervised machine learning:-

There are following features of Unsupervised Machine learning i.e.
 Knowledge Discovery
 Wrapping
 Filtering
 Course of dimensionality
1.3Reinforcement Machine Learning Algorithm:-It is a type of learning method, which interacts with its
environment, produces action, as well as discovers errors and rewards. This method allows machines and
software agents to automatically determine any ideal behavior, which is within a specific context and so that it
can maximize their performance.
1.3.1Types of reinforcement machine learning
 Decision Making:-It is a process that helps us for make decisions and provides a way to solve our
problems step by step. It is process of identifying a decision, gathering information and assigning alternative
decision. Reinforcement ML is a providing further some steps of decision making.[10]

 Q- Learning:-Q-Learning is a model-free reinforcement learning algorithm to learn the value of an

action in particular states. It does not require a model of the environment, and it can handle problems with
transitions.
 Q- Table:- Q-table is a value based learning algorithm in reinforcement learning.
1.3.2Applications of Reinforcement Machine Learning:-
1. Business strategy planning
2. Machine learning and data processing
3. Robotic for industrial automation
4. Motion planning
5. Dynamic path
6. Controller optimization
7. Provide custom instruction and materials according to the requirement
8. Aircraft control

www.ijres.org 276 | Page

 A review on Machine Learning: Application and Algorithms

9. Healthcare
1.3.3Features of Reinforcement Machine Learning:-
This technique is used to achieve such results which are very difficult to achieve.
It provides accurate results.

2. Features of Machine Learning:-

 In fact, it has made the life of man a lot easier.
 Today machine learning is constantly being used to improve tasks in every field.
 For this, machines are being made more the effective and efficient.
 The use of machine learning is not limited to any one field, but today this technology of AI is being
benefited in almost every field.
 Finance: - AI and machine learning are also being used in the finance sector, to provide a better and
faster service to the customer, such as enhancing the security of transaction and preventing fraud activity, etc...
 Health: -Machine learning is making a big change in health sector, such as machine learning and
diagnosis of patients, improving radiotherapy facilities, as well as promoting health facilities at a much lower
cost.[11]

3. Applications of machine learning:-

3.1 Image Recognition:-Image recognition is one of the most common applications of machine learning. Image
recognition is a technology that is used to identifier places, people, building, objects and other variables in
digital images.
3.2 Email Spam and Malware Filtering:-Whenever we receive a new email, it is automatically filters whether
it is important email, normal, and spam. We always receive an important mail in our inbox and spam emails in
our spam box, and the technology behind this is Machine learning. Some following filters in gmail:-
 Content Filter
 Header filter
 General blacklists
 filter Rules-based filters
 Permission filters.
3.3 Speech Recognition: -This is such technology in which you do not need a keypad or keyboard because this
technology recognizes your voice and responds to you accordingly. It is also known as “speech to text”. At
present the speech recognition are widely used in machine learning algorithm. [12]
3.4 Traffic Prediction: -Machine learning allows you to create predictive models that consider large masses
from different sources. Traffic prediction is the task of forecasting real time traffic information, such as traffic
flow average traffic speed.[13]
3.5 Medical Diagnosis: - This medical diagnosis is used for diseases diagnosis. AI techniques extend from
machine learning to deep learning are used in healthcare for risk identification, medical imaging & medicine
diagnosis.[14]
3.6 Automatic Language Translation: - Machine translation is a challenging task to convert one language into
another language translation. The Neural Machine Learning feature provides by GNMT (Google Neural
Machine Translation) that helps to translate the text into our friendly language and it's known as automatic
translation.
3.7 Self Driving Car: -An autonomous car is a vehicle that uses a combination of sensors, cameras, radar and
artificial intelligence to travel between destinations without a human operator[15]
3.8 Online Fraud Detection: - Machine learning is making our transaction safe and secure by detection fraud
transaction. Through machine learning fraud detection allows you to run automated transaction processing on an
example dataset or your own dataset.[16]

www.ijres.org 277 | Page

 A review on Machine Learning: Application and Algorithms

Automatic
language
Image translation
recognition Medical
diagnosis

Speech Applications
recognition Online fraud
Of detection
Machine learning

Traffic Email spam

prediction and
Self driving malwarefilter
cars ing

Figure 2 Application of Machine Learning

4. PRESENT SCOPE OF MACHINE LEARNING

 Healthcare
 Education
 Finance
 Agriculture
 Covid-19
4.1 Healthcare: Machine learning helps the development of hospitalization by expanding patient crisis and
improving health results. In healthcare machine learning helps in finding diseases and diagnosing.[17]
4.2 Education: Machine learning is a transfer education and essentially changeable training, study, and
research. Educationists are using Machine learning to help to struggle with scholars previous and take the deal
to better success and detention. Researchers are growing research with Machine learning to free new
analysis.[18]
4.3 Finance: In finance, machine learning is used to catch blackmail, automatize commerce enterprises, and
arrange financial helping convocation to shareholders. Machine learning is evaluating lots of document sets
within a little time to better the results without clear programmed.[19]
4.4 Agriculture: - The scopes of Machine Learning are students can take career paths in this field, such as a job
as an agriculture engineer at agro-based industries, farm shop managers, agriculture researcher, food
supervisors, and agriculture inspectors. In fact, the development in technology, research, and innovation has
multiplied the scope of agriculture in a big way.[20]
4.5 Covid-19: Machine learning is used to disease based on x-ray copies. For instance, chest copies of patients
can be used to find whether a patient is altered with covid-19.

5. FUTURE SCOPE OF MACHINE LEARNING

Machine learning is a type of application that provides system with the ability to learn automatically and
improve over serves if needed.Lavanyatekumalla the founder of aifonilabs and spring board mentor is says that
"Machine learning is the process of automatically getting insights from data that can drive business value “Let
us look and discuss about some of the top use cases evolving today, which will come to extend the future scope
of machine learning: -
1. Safer Healthcare.
2. Optimizing operations.
3. Fraud Prevention.
4. Mass Personalization.

Conclusion:
Machine learning is both supervised and unsupervised. If you have fewer data points with clearly
identified training data, choose supervised learning. Unsupervised learning would normally perform and get
better results for large data sets. If you have a huge data collection that is readily available, you might want to

www.ijres.org 278 | Page

 A review on Machine Learning: Application and Algorithms

think about applying deep learning techniques. You also learned about reinforcement learning and deep
reinforcement learning. Now that you are more knowledgeable about neural networks, their applications, and
their shortcomings. This study surveys a wide range of machine learning algorithms. Nowadays, everyone
employs machine learning, whether consciously or unconsciously. From changing pictures on social networking
sites to getting product suggestions when shopping online virtually all of the well-known.

References:
[1]. Mitchell, T., Buchanan, B., DeJong, G., Dietterich, T., Rosenbloom, P., & Waibel, A. (1990). Machine learning. Annual review of
computer science, 4(1), 417-433.
[2]. Singh, A., Thakur, N., & Sharma, A. (2016, March). A review of supervised machine learning algorithms. In 2016 3rd International
Conference on Computing for Sustainable Global Development (INDIACom) (pp. 1310-1315). Ieee.
[3]. Ayodele, T. O. (2010). Types of machine learning algorithms. New advances in machine learning, 3, 19-48.
[4]. Maulud, D., & Abdulazeez, A. M. (2020). A review on linear regression comprehensive in machine learning. Journal of Applied
Science and Technology Trends, 1(4), 140-147.
[5]. Somvanshi, M., Chavan, P., Tambade, S., & Shinde, S. V. (2016, August). A review of machine learning techniques using decision
tree and support vector machine. In 2016 international conference on computing communication control and automation
(ICCUBEA) (pp. 1-7). IEEE.
[6]. Poos, A. M., Maicher, A., Dieckmann, A. K., Oswald, M., Eils, R., Kupiec, M., ... & König, R. (2016). Mixed Integer Linear
Programming based machine learning approach identifies regulators of telomerase in yeast. Nucleic acids research, 44(10), e93-e93.
[7]. Gentleman, R., & Carey, V. J. (2008). Unsupervised machine learning. In Bioconductor case studies (pp. 137-157). Springer, New
York, NY.
[8]. Kassambara, A. (2017). Practical guide to cluster analysis in R: Unsupervised machine learning (Vol. 1). Sthda.
[9]. Chen, Y., Zhu, X., & Gong, S. (2018). Deep association learning for unsupervised video person re-identification. arXiv preprint
arXiv:1808.07301.
[10]. Qiang, W., & Zhongli, Z. (2011, August). Reinforcement learning model, algorithms and its application. In 2011 International
Conference on Mechatronic Science, Electric Engineering and Computer (MEC) (pp. 1143-1146). IEEE.
[11]. Blum, A. L., & Langley, P. (1997). Selection of relevant features and examples in machine learning. Artificial intelligence, 97(1-2),
245-271.
[12]. Worden, K., & Manson, G. (2007). The application of machine learning to structural health monitoring. Philosophical Transactions
of the Royal Society A: Mathematical, Physical and Engineering Sciences, 365(1851), 515-537.
[13]. Rzeszótko, J., & Nguyen, S. H. (2012). Machine learning for traffic prediction. Fundamenta Informaticae, 119(3-4), 407-420.
[14]. Kononenko, I. (2001). Machine learning for medical diagnosis: history, state of the art and perspective. Artificial Intelligence in
medicine, 23(1), 89-109.
[15]. Stilgoe, J. (2018). Machine learning, social learning and the governance of self-driving cars. Social studies of science, 48(1), 25-56.
[16]. Minastireanu, E. A., & Mesnita, G. (2019). Light gbm machine learning algorithm to online click fraud detection. J. Inform. Assur.
Cybersecur, 2019.
[17]. Ngiam, K. Y., & Khor, W. (2019). Big data and machine learning algorithms for health-care delivery. The Lancet Oncology, 20(5),
e262-e273.
[18]. Halde, R. R. (2016, September). Application of Machine Learning algorithms for betterment in education system. In 2016
International Conference on Automatic Control and Dynamic Optimization Techniques (ICACDOT) (pp. 1110-1114). IEEE.
[19]. Ghoddusi, H., Creamer, G. G., & Rafizadeh, N. (2019). Machine learning in energy economics and finance: A review. Energy
Economics, 81, 709-727.
[20]. Liakos, K. G., Busato, P., Moshou, D., Pearson, S., & Bochtis, D. (2018). Machine learning in agriculture: A
review. Sensors, 18(8), 2674.
[21]. Verma, P., Khanday, A. M. U. D., Rabani, S. T., Mir, M. H., & Jamwal, S. (2019). Twitter sentiment analysis on Indian government
project using R. Int J Recent Technol Eng, 8(3), 8338-41.

www.ijres.org 279 | Page