0% found this document useful (0 votes)
120 views11 pages

Machine Learning Techniques

This document summarizes a research article that discusses machine learning techniques, methods, and algorithms. It provides conceptual and practical insights into machine learning. The article defines machine learning and describes how it focuses on developing programs that can learn from data without being explicitly programmed. It also discusses the history of machine learning and how it has evolved from early work on neural networks to become its own field. The article aims to shed light on machine learning by covering topics like the different types of learning, models, and applications of machine learning techniques.

Uploaded by

nopal mahing
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
0% found this document useful (0 votes)
120 views11 pages

Machine Learning Techniques

This document summarizes a research article that discusses machine learning techniques, methods, and algorithms. It provides conceptual and practical insights into machine learning. The article defines machine learning and describes how it focuses on developing programs that can learn from data without being explicitly programmed. It also discusses the history of machine learning and how it has evolved from early work on neural networks to become its own field. The article aims to shed light on machine learning by covering topics like the different types of learning, models, and applications of machine learning techniques.

Uploaded by

nopal mahing
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/ 11

See discussions, stats, and author profiles for this publication at: https://www.researchgate.

net/publication/353887208

Machine Learning Techniques, methods and Algorithms: Conceptual and


Practical Insights

Article  in  International Journal of Engineering Research and Applications · August 2021


DOI: 10.9790/9622-1108025564

CITATIONS READS

2 751

3 authors:

Asongo Abraham Iorkaa Modu Barma


Modibbo Adama University of Technology, Adama Modibbo Adama University of Technology, Adama
19 PUBLICATIONS   35 CITATIONS    4 PUBLICATIONS   11 CITATIONS   

SEE PROFILE SEE PROFILE

Hamandikko GAYA Muazu


Modibbo Adama University of Technology, Adama
3 PUBLICATIONS   27 CITATIONS   

SEE PROFILE

All content following this page was uploaded by Asongo Abraham Iorkaa on 13 August 2021.

The user has requested enhancement of the downloaded file.


Asongo, A.I, et. al. International Journal of Engineering Research and Applications
www.ijera.com
ISSN: 2248-9622, Vol. 11, Issue 8, (Series-II) August 2021, pp. 55-64

RESEARCH ARTICLE OPEN ACCESS

Machine Learning Techniques, methods and Algorithms:


Conceptual and Practical Insights
Asongo, A.I*, Barma**, M, Muazu, H.G***
*
Department of Statistics and Operations Research, ModibboAdama University, Yola, Nigeria
**
Department of Statistics and Operations Research, ModibboAdama University, Yola, Nigeria
***
Department of Statistics and Operations Research, ModibboAdama University, Yola, Nigeria

ABSTRACT: Major companies have actively reoriented themselves around Artificial Intelligence and
machine learning. A lot of resources are being deployed and attention focused on the use of machine learning in
a bid to convincing the world that the machine intelligence revolution is arriving now. The technological
transformation resulting to powering new self-driving cars, virtual assistants, disease detection and therapy
planning and many more are just few out of numerous applications of machine learning. This paper, through a
review of the available literature seeks to offer conceptual and practical insights on the techniques, methods and
algorithms of machine Learning. This paper has shown that there are numerous research on applications of
machine learning in the management of banking risks such as credit risk, market risk, operational risk and
liquidity risk and other fields has been explored; however, it doesn’t appear commensurate with the needed
knowledge on the general models, application software and the applications in other sectors. This paper
therefore shed more light that could significantly add to the knowledge of the field by giving insight on the
history, types, models and other areas of applications of machine Learning.
Keywords: Algorithms, Applications, Machine Learning, Techniques, Training,
---------------------------------------------------------------------------------------------------------------------------------------
Date of Submission: 24-07-2021 Date of Acceptance: 09-08-2021
---------------------------------------------------------------------------------------------------------------------------------------

I. INTRODUCTION on the extensions of computer programs which is


According to [1] machine learning is an capable enough to modify when unprotected to new-
application of artificial intelligence (AI) that provides fangled data. The evolution of machine learning is
systems the ability to automatically learn and comparable to that of data mining. Both data mining
improve from experience without being explicitly and machine learning consider or explore from end to
programmed. Machine learning focuses on the end data to assume for patterns. On the other hand, in
development of computer programs that can access choice to extracting data for human knowledge as is
data and use it learn for themselves. The process of the case in data mining applications; machine
learning begins with observations or data, such as learning generate use of the data to identify patterns
examples, direct experience, or instruction, in order in data and fine-tune program actions.
to look for patterns in data and make better decisions Machine learning is closely related to and
in the future based on the examples that we provide. often overlaps with computational statistics and data
The primary aim is to allow the computers learn science [3]; a discipline that also specializes in
automatically without human intervention or prediction-making. It has strong ties to mathematical
assistance and adjust actions accordingly. In machine optimization, which deliver methods, theory and
learning, algorithms are used to distinguish between application domains to the field. Machine learning is
meaningful and irrelevant patterns in data. Examples employed in a range of computing tasks where
of machine learning applications include the designing and programming explicit algorithms is
provision of accurate medical diagnostics (e.g. breast infeasible. [4] put it that as the name suggests, the
cancer), real-time map-based monitoring of term machine learning can simply be explained to
environmental disasters (e.g. forest fires)and sensory mean empowering computer systems with the ability
monitoring in the industrial process (e.g. mechanical to learn. The intention of machine learning is to
failure). enable machines to learn by themselves using the
[2] describe Machine learning as a kind of provided data and make accurate predictions.
artificial intelligence (AI) which compose available Machine learning is therefore a subset of artificial
computers with the efficiency to be trained without intelligence; in fact, it’s simply a technique for
being veraciously programmed. ML learning interest realizing artificial intelligence. It is a method of

www.ijera.com DOI: 10.9790/9622-1108025564 55 | P a g e


Asongo, A.I, et. al. International Journal of Engineering Research and Applications
www.ijera.com
ISSN: 2248-9622, Vol. 11, Issue 8, (Series-II) August 2021, pp. 55-64

training algorithms such that they can learn how to networks; these were mostly perceptron and other
make decisions. Training in machine learning entails models that were later found to be reinventions of the
giving a lot of data to the algorithm and allowing it to generalized linear models of statistics. Probabilistic
learn more about the processed information. reasoning was also employed, especially in
To explain further how a machine learns automated medical diagnosis.
from data, let us look at this example. Supposing we Machine learning, reorganized as a separate
have a table comprising of different fruits to be field, started to flourish in the 1990s. The field
differentiated based on their weight and colour with changed its goal from achieving artificial intelligence
the last row showing only the weight and colour as to tackling solvable problems of a practical nature. It
shown in table 1 below: shifted focus away from the symbolic approaches it
had inherited from AI, and toward methods and
Table 1: Machine Learning algorithm explained models borrowed from statistics and probability
Weight Colour Type of theory[7].
(grams) Fruit Machine learning and data mining often
80 Green Apple employ the same methods and overlap significantly.
85 Green Apple The two areas overlap in many ways: data mining
95 Green Apple uses many machine learning methods, but often with
90 Yellow Orange a slightly different goal in mind. Machine learning
100 Yellow Orange also has intimate ties to optimization: many learning
103 Yellow ?? problems are formulated as minimization of some
loss function on a training set of examples. Loss
Here a machine learning algorithm can be functions express the discrepancy between the
developed to try to identify whether the fruit is an predictions of the model being trained and the actual
orange or an apple. After the algorithm is fed with the problem instances (for example, in classification, one
training data, it will learn the differing characteristics wants to assign a label to instances, and models are
between an orange and an apple. Therefore, if trained to correctly predict the pre-assigned labels of
provided with data of weight and colour, it can a set examples). The difference between the two
predict accurately the type of fruit with those fields arises from the goal of generalization: while
characteristics. optimization algorithms can minimize the loss on a
training set, machine learning is concerned with
minimizing the loss on unseen samples [8]
II. THE HISTORY OF MACHINE
LEARNING III. TYPES OF MACHINE LEARNING
The word Machine learning was first coined
[1] categorized machine learning algorithms
by Arthur Samuel in 1952 [5]. In 1957, Frank into supervised, unsupervised and reinforcement
Rosenblatt – at the Cornell Aeronautical Laboratory –
learning algorithms: Figure one present the
combined Donald Hebb's model of brain cell
classification in a pictorial form:
interaction with Arthur Samuel's Machine Learning
efforts and created the perceptron. In 1967, the
nearest neighbor algorithm was conceived, which
was the beginning of basic pattern recognition. This
algorithm was used for mapping routes and was one
of the earliest algorithms used in finding a solution to
the traveling salesperson’s problem of finding the
most efficient route. In the 1960s, the discovery and
use of multilayers opened a new path in neural
network research. It was discovered that providing
and using two or more layers in the perceptron
offered significantly more processing power than a
perceptron using one layer [5].
According to [6]machine learning grew out
Figure 1: Types of Machine Learning
of the quest for artificial intelligence. Already in the
early days of artificial intelligence as an academic
i. Supervised Learning
discipline, some researchers were interested in having
Supervised learning is a core area of
machines learn from data. They attempted to machine learning. In supervised learning the goal is
approach the problem with various symbolic
to learn a mapping from the input to the output. The
methods, as well as what were then termed neural
input is data that describes a collection of individual

www.ijera.com DOI: 10.9790/9622-1108025564 56 | P a g e


Asongo, A.I, et. al. International Journal of Engineering Research and Applications
www.ijera.com
ISSN: 2248-9622, Vol. 11, Issue 8, (Series-II) August 2021, pp. 55-64

objects of interest and are commonly referred to as association rule learning problem is where you want
instances or examples. The output is some outcome to discover rules that describe large portions of your
or result provided by a supervisor. Classification is a data, such as people that buy X also tend to buy Y.
form of supervised learning whereby a mapping (or Some popular examples of unsupervised learning
discriminant function) separates diff erent classes of algorithms are k-means for clustering problems and
the instances. The diff erent classes are specified by Apriori algorithm for association rule learning
the output which, in machine learning, is termed as problems.
the class label. The discriminant function is referred
to as a classifier or a model. A set of instances with iii. Reinforcement machine learning algorithms
their known class label is termed a training set. Reinforcement machine learning algorithms is a
During classification, a model is defined by a set of learning method that interacts with its environment
parameters that are optimized to generate a mapping by producing actions and discovers errors or rewards.
from training set instances to training set labels. The Trial and error search and delayed reward are the
trained model can be used to classify or label new, most relevant characteristics of reinforcement
unseen instances. learning. This method allows machines and software
The majority of practical machine learning agents to automatically determine the ideal behavior
uses supervised learning. Supervised learning is within a specific context in order to maximize its
where you have input variables (x) and an output performance. Simple reward feedback is required for
variable (Y) and you use an algorithm to learn the the agent to learn which action is best; this is known
mapping function from the input to the output. as the reinforcement signal. When it comes to
Y = f(X) (1) explaining machine learning to those not concerned
The goal is to approximate the mapping function so in the field, reinforcement learning is probably the
well that when you have new input data (x) that you easiest sub-field for this challenge. To make it more
can predict the output variables (Y) for that data. It is practical, it can be said Reinforcement Learning is
called supervised learning because the process of an like teaching your dog (or cat if you live your life in a
algorithm learning from the training dataset can be challenging way) to do tricks: you provide goodies as
thought of as a teacher supervising the learning a reward if your pet performs the trick you desire,
process. We know the correct answers, the algorithm otherwise, you punish him by not treating him, or by
iteratively makes predictions on the training data and providing lemons. Dogs really hate lemons. Beyond
is corrected by the teacher. Learning stops when the controversy, Reinforced learning is a more complex
algorithm achieves an acceptable level of and challenging method to be realized, but basically,
performance. it deals with learning via interaction and feedback, or
in other words learning to solve a task by trial and
ii. Unsupervised Learning error, or in other-other words acting in an
According to [9] this machine learning environment and receiving rewards for it. Essentially
algorithms are used when the information used to an agent (or several) is built that can perceive and
train is neither classified nor labeled. Unsupervised interpret the environment in which is placed,
learning studies how systems can infer a function to furthermore, it can take actions and as well as interact
describe a hidden structure from unlabeled data. The with the environment.
system doesn’t figure out the right output, but it
explores the data and can draw inferences from IV. MACHINE LEARNING MODELS
datasets to describe hidden structures from unlabeled This session discussed various machine Learning
data. Models. These includes:
Unsupervised learning is where you only
have input data (X) and no corresponding output i. Decision tree methodology
variables. The goal for unsupervised learning is to Decision trees is one of the machine
model the underlying structure or distribution in the learning models. According to [10], decision tree
data in order to learn more about the data. These are approach or the recursive partitioning algorithm
called unsupervised learning because unlike (RPA) is a non- parametric, complex and
supervised learning above there is no correct answers computerized intensive sorting algorithm. The basic
and there is no teacher. Algorithms are left to their idea is to split the sample responses into the new sub-
own devises to discover and present the interesting samples that are as homogeneous as possible and as
structure in the data.Unsupervised learning problems different from each other, and then to repeatedly split
can be further grouped into clustering and association the sub-sample into subgroups until it generates the
problems. A clustering problem is where you want to possibility for decision- making. The entire sample is
discover the inherent groupings in the data, such as the root node, while the sub-samples are called
grouping customers by purchasing behavior while an nodes. Figure 2 is a good example of decision tree

www.ijera.com DOI: 10.9790/9622-1108025564 57 | P a g e


Asongo, A.I, et. al. International Journal of Engineering Research and Applications
www.ijera.com
ISSN: 2248-9622, Vol. 11, Issue 8, (Series-II) August 2021, pp. 55-64

showing credit risk classification into bad credit and absolute errors or minimizing the maximum error
good credit. [12]. To solve the problem by linear programming, a
popular formulation is asfollows:

(4)

Where is the objective


function that includes the possible errors (all are
positive or zero), the weights that
minimize the sum of the absolute values of errors,

Figure 2: Diagram showing decision tree


iv. Integerprogramming
To grow the tree models, greedy algorithm Another known machine learning model is
is used such that at each node , evaluate a large set integer programming. Any decision problem (with an
of variable splits so as to find the best split, that is the objective to be maximized or minimized) in which
split that minimizesthe weighted decease in impurity: the (quantifiable) decision variables must assume
non-fractional or discrete values may be classified as
an integer optimization problem [17]. If only some of
unknown variables are required to be integers, then
Where and denote the proportion observations the problem is called mixed integer programming
associated with node that are sent to the left child which prevents a trivial solution. This method
node or right chid node respectively. overcomes the limitations of linear programming
resulting from minimization and maximization
ii. Nearest-neighboursmethodology ofdeviation.In this technique, at least some of the
The nearest-neighbours method (also called variables will have to be integer (0, 1, 2, etc.). [18]
pattern recognition) is a machine learning approach provided the following model:
for classifying and was first proposed by [11]. The
ideaofthismethodistoselectametriconthespaceofapplic
ation data to measure how far apart any two
applicants are [12]. [13] suggested a metric of the
form:
(3) (5)
Where and are points in the feature space, is Where L is the cost of misclassifying a good as a bad,
the identity matrix, D is a distance parameter, and w D the cost of misclassifying a bad as a good, M is a
is a particular direction in the measurement space. positive number, and is a variable that is 1 if a
customer in the sample is misclassifying a good and 0
iii. Goalprogramming otherwise.
Goal programming is another model in
machine learning. It is a branch of mathematical
programming that is concerned with the optimal
allocation of limited resources to achieve a desired
goal by maximizing and minimizing values as well as
an efficient part ofoperations research to solve many
practical problems [14]. [15] was the first to study
suggested goal programming in classifying problems
where there are two groups and there is a separating
hyperplane, which can separate the two groups
accurately. [16] proposed that goal programming can
be applied for discriminant problem when the two
groups are not necessarily separable by using
objectives such as minimization of the sum of

www.ijera.com DOI: 10.9790/9622-1108025564 58 | P a g e


Asongo, A.I, et. al. International Journal of Engineering Research and Applications
www.ijera.com
ISSN: 2248-9622, Vol. 11, Issue 8, (Series-II) August 2021, pp. 55-64

v. Geneticalgorithms Perceptron (MLP). A MLP is typically composed of


Genetic (or evolutionary) algorithms are one an input layer (consisting of neurons for all input
of the machine learning models used for modeling. variables), a hidden layer (consisting of any number
Genetic algorithms were pioneered by [19] who took of hidden neurons), and an output layer (in our case,
the same ideas of the general principles of one neuron). Each neuron processes its inputs and
evolutionary natural selection suggested by Charles transmits its output value to the neurons in the
Darwin and used them on unconstrained optimization subsequent layer. Each such connection between
problems. The idea of this method is to attempt to neurons is assigned a weight during training. The
simulate the survival of the fitness rule of genetic output of hidden neuron is computed by applying an
mutation to develop optimisation algorithms [20]. A activation function for example the logistic
basic genetic algorithm represents selecting a function to the weighted inputs and its bias term
population of candidate solutions (called individuals) :
to a problem. Solutions are represented as strings of
genes (called chromosomes). Genetic algorithms
basically assess the performance (called fitness) of
each possible solution in each generation and then
calculate the fitness of each string to achieve a given
Where W represents a weight matrix in denotes
objective. From the initial population of
chromosomes, a new population (children replaced the weight connecting input denotes the weight
their parents within the population) is generated using connecting input to hidden neuron .
three genetic operators: reproduction, crossover
andmutation. viii. Least Square Support Vector Machine (LS-
SVM)
vi. Linear probability model Support vector machines (SVMs) are a set
This is one of the machine learning models. of powerful supervised learning techniques used for
It is by far the most common empirical model form classification and regression. Their basic principle,
used is the linear regression model; mainly because it when applied as a classifier, is to construct a
is generally easy to use and understand. The linear maximum-margin separating hyperplane in some
probability model is an econometric model in which transformed feature space. Rather than requiring one
to specify the exact transformation though, they use
the dependent variable takes a value of zero or one. It
the principle of kernel substitution to turn them into a
assumes a linear relationship between the probability
of default and the independent variables and employs general (non-linear) model. The least square support
historical data as inputs to explain the repayment vector machine (LS-SVM) proposed by [22] is a
experience on past loans. Ordinary least squares or further adaptation of Vapnik's original SVM
formulation which leads to solving linear KKT
weighted least squares is employed to regress (the
(Karush-Kuhn-Tucker) systems (rather than a more
dependent variable) on (the independent variables)
complex quadratic programming problem). The
to find the parameter(s) which gives the estimated
optimisation problem for the LS-SVM is defined as:
importance of the th variable in explaining past
repayment experiences (Turvey, 1991).
The structural model takes the form:
Subject to the following constraints:
(9)
Where is the dependent variable or the probability Where the weight vector in primal space, is the
of default (Z =1) if the event is default; Z = 0 regularization parameter. In case of lending in
otherwise), are parameters to be estimated, are financial sector for example, it can be said that
independent variables of the value for th, the for borrowers who pay in time or for
observation and is the unobserved error defaulters.
term assumed to be a random variable.
vii. Neural Networks ix. . Memory Based Reasoning (k-NN)
Neural networks (NN) are mathematical The k-nearest neighbours algorithm (k-NN)
representations modelled on the functionality of the classifies a data point by taking a majority vote of its
human Brain [21]. The added benefit of neural k most similar data points [23]. The similarity
Network is its flexibility in modelling virtually any measure used in this thesis is the Euclidean distance
non-linear association between input variables and between the two points:
target variables. Although various architectures have
been proposed, this article focuses on Multilayer (10)

www.ijera.com DOI: 10.9790/9622-1108025564 59 | P a g e


Asongo, A.I, et. al. International Journal of Engineering Research and Applications
www.ijera.com
ISSN: 2248-9622, Vol. 11, Issue 8, (Series-II) August 2021, pp. 55-64

One of the major disadvantages of the k-nearest V. MACHINE LEARNING APPLICATION


neighbour classifier is the large requirement on SOFTWARE
computing power as for classifying an object, the Application software is a program or group of
distance between it and all the objects in the training programs designed for end users. Examples of
set has to be calculated. Furthermore, when many an application include a word processor, a
irrelevant attributes are present, the classification spreadsheet, an accounting application, a web
performance may degrade when observations have browser, an email client, a media player, a file
distant values for these attributes [24]. viewer, simulators, a console game or a photo editor.
there are numerous machine learning software
x. Random Forest developed by experts. The following list are some of
Random forests are defined as a group of the few notablesoftwares:
un-pruned classification or regression trees, trained i. Weka
on bootstrap samples of the training data using Weka stands for Waikato Environment for
random feature selection in the process of tree Knowledge Analysis (Weka). The software is a
generation. After a large number of trees have been collection of machine learning algorithms for data
generated, each tree votes for the most popular class. mining tasks. The algorithms can either be applied
These tree voting procedures are collectively defined directly to a dataset or called from your own Java
as random forests. A more detailed explanation of code. Weka contains tools for data pre-processing,
how to train a random forest can be found in [25]. classification, regression, clustering, association
For the Random Forests classification technique two rules, and visualization. WEKA was developed at the
parameters require tuning. These are the number of University of Waikato, New Zealand. It is free
trees and the number of attributes used to grow each software licensed under the GNU General Public
tree. License, and the companion software to the book
"Data Mining: Practical Machine Learning Tools and
The two meta-parameters that can be set for Techniques [27].
the Random Forests classification technique are: the
number of trees in the forest and the number of ii. Salford Predictive Modeler
attributes (features) used to grow each tree. In the The Salford Predictive Modeler softwareis
typical construction of a tree, the training set is an open source software suite that is highly accurate
randomly sampled, then a random number of and ultra-fast analytics and data mining platform for
attributes is chosen with the attribute with the most creating predictive, descriptive, and analytical models
informationgain comprising each node. The tree is from databases of any size, complexity, or
then grown until no more nodes can be created due to organization [28]
information loss.
iii. OpenCV
xi. Gradient Boosting OpenCV (Open Source Computer Vision
Gradient boosting [26] is an ensemble Library) is an open source computer vision and
algorithm that improves the accuracy of a predictive machine learning software library. OpenCV was built
function through incremental minimisation of the to provide a common infrastructure for computer
error term. After the initial base learner (most vision applications and to accelerate the use of
commonly a tree) is grown, each tree in the series machine perception in the commercial products.
isfit to the so-called “pseudo residuals” of the Being a BSD-licensed product, OpenCV makes it
prediction from the earlier trees with the purpose of easy for businesses to utilize and modify the code[29]
reducing the error. The estimated probabilities are
adjusted by weight estimates, and the weight iv. Torch
estimates are increased when the previous model Torch is an open-sourcemachine learning
misclassified a response. This leads to the library, a scientific computing framework, and a
followingmodel: script language based on the Lua programming
language. Its goal is to provide a flexible
environment to design and train learning machines.
Flexibility is obtained via Lua, an extremely light
Where equals the first value for the series, weight scripting language. High performance is
are the trees fitted to the pseudo residual, and are obtained via efficient Open MP/SSE and CUDA
coefficient for the respective tree nodes computed by implementations of low-level numeric routines.
the Gradient Boosting algorithm. Torch7 can easily be interfaced to third-party
software thanks to Lua’s light interface [30].

www.ijera.com DOI: 10.9790/9622-1108025564 60 | P a g e


Asongo, A.I, et. al. International Journal of Engineering Research and Applications
www.ijera.com
ISSN: 2248-9622, Vol. 11, Issue 8, (Series-II) August 2021, pp. 55-64

v. LIONsolver learning, and analytics. Databricks enables data


LIONsolver is an integrated software for exploration using interactive notebooks with support
data mining, business intelligence, analytics, and for multiple programming languages within the same
modeling Learning and Intelligent OptimizatioN and notebook, including R, Python, Scala, and SQL [35].
reactive business intelligence approach. A non-profit
version is available as LIONoso. LIONsolver can be x. H2O Software
used to build models, visualize them, and improve H2Ois a fully open source, distributed in-
business and engineering processes. It is a tool for memory machine learning platform with linear
decision making based on data and quantitative scalability. H2O supports the most widely used
models, it can be connected to most databases and statistical & machine learning algorithms including
external programs, it is fully integrated with the gradient boosted machines, generalized linear
Grapheur business intelligence software and intended models, deep learning and more [36].
for more advanced users, interested in designing
business logic and processes and not only in simple VI. THE APPLICATIONS OF
analytics and visualization tasks [31]. MACHINE LEARNING
According to [37], there is an increasing
vi. NeuroSolutions influence of machine learning applications in
NeuroSolutions is a neural network everyday life spanning from information technology,
development environment developed by Healthcare, sports, banking and a lot more with many
NeuroDimension. It combines a modular, icon-based solutions already implemented and many more being
(component-based) network design interface with an explored. This paper seeks to outline some key areas
implementation of advanced learning procedures, of machine learning applications as follows:
such as conjugate gradients, Levenberg-Marquardt
and backpropagation through time. The software is i. Virtual personal Assistant
used to design, train and deploy neural network According to [38], a virtual assistant, also
(supervised learning and unsupervised learning) called AI assistant or digital assistant, is
models to perform a wide variety of tasks such as an application program that understands natural
data mining, classification, function approximation, language voice commands and completes tasks for
multivariate regression and time-series[32]. the user. Such tasks, historically performed by a
personal assistant or secretary, include taking
vii. KXEN Modeler dictation, reading text or email messages aloud,
InfiniteInsightis a predictive modeling suite looking up phone numbers, scheduling, placing
developed by KXEN that assists analytic phone calls and reminding the end user about
professionals, and business executives to extract appointments. Popular virtual assistants currently
information from data. Among other functions, include Amazon Alexa, Apple's Siri, Google
InfiniteInsight is used for variable importance, Assistant and Microsoft's Cortana and the digital
classification, regression, segmentation, time series, assistant built into Windows Phone 8.1 and Windows
product recommendation, as described and expressed 10.
by the Java Data Mining interface, and for social The capabilities and usage of virtual
network analysis [33]. assistants are expanding rapidly, with new products
entering the market and a strong emphasis on both
viii. RapidMiner email and voice user interfaces. Apple and Google
RapidMiner is a data science software have large installed bases of users on smartphones.
platform developed by the company of the same Microsoft has a large installed base of Windows-
name that provides an integrated environment for based personal computers, smartphones and smart
data preparation, machine learning, deep learning, speakers. Amazon has a large install base for smart
text mining, and predictive analytics. It is used for speaker.
business and commercial applications as well as for
research, education, training, rapid prototyping, and ii. Video Surveillance
application development and supports all steps of the The video surveillance system nowadays are
machine learning process including data preparation, powered by Artificial Intelligence which is part of
results visualization, model validation and machine learning. This makes it possible to detect
optimization [34]. crime before they happen. They track unusual
behaviour of people like standing motionless for a
ix. Databricks long time, stumbling, or napping on benches etc. The
Databricks is an open and unified data system can thus give an alert to human attendants,
analytics platform for data engineering, machine which can ultimately help to avoid mishaps. And

www.ijera.com DOI: 10.9790/9622-1108025564 61 | P a g e


Asongo, A.I, et. al. International Journal of Engineering Research and Applications
www.ijera.com
ISSN: 2248-9622, Vol. 11, Issue 8, (Series-II) August 2021, pp. 55-64

when such activities are reported and counted to be operate a device, perform commands, or write
true, they help to improve the surveillance services. without having to use a keyboard, mouse, or press
This happens with machine learning doing its job at any buttons. All commercial purpose speech
the backend. A small video file contains more recognition system uses a machine learning approach
information compared to text documents and other to recognize the speech. This is because the speech
media files such as audio, images. For this reason, recognition system using machine learning approach
extracting useful information from video, i.e., the outperforms better than the speech recognition
automated video surveillance system has become a system using a traditional method.
hot research issue. With this regard, video
surveillance is one of the advanced application of a vi.Medical Services
machine learning approach. A system with the ability Machine learning methods, tools are used
to gather information about the presence of the same extensively in the area of the medical-related
person in a different frame of a video is highly problem. As an instance to detect a disease, therapy
demanding. There are several methods of machine planning, medical-related research, prediction of the
learning algorithm to track the movement of human disease situation.The value of machine learning in
and identifying them. healthcare is its ability to process huge datasets
beyond the scope of human capability, and then
iii. Email Spam and Malware Filtering reliably convert analysis of that data into clinical
There are a number of spam filtering insights that aid physicians in planning and providing
approaches that email clients use. To ascertain that care, ultimately leading to better outcomes, lower
these spam filters are continuously updated, they are costs of care, and increased. Some of the notable
powered by machine learning. When rule-based spam areas of applications in medical services include
filtering is done, it fails to track the latest tricks Identifying diseases and diagnosis, drug discovery
adopted by spammers. and manufacturing, medical imaging diagnosis,
To classify email and filter the spam in an personalized medicine, machine learning-based
automatic way machine learning algorithm is behavioral modification, smart health records,
employed. There are many techniques such as multi- clinical trial and research and crowdsourced data
layer perception, C4.5 decision tree induction etc. collection.
used to filter the spam. The rule-based spam filtering
has some drawbacks to filter the spam, whereas spam vii. Online Customer Support
filtering using the machine Learning approach is Online Customer Services are automated
more efficient. services that helps customers solve problems. Such a
service is usually connected to a business or brand
iv. Online Fraud Detection which sells products and offers support. There are
Machine learning is proving its potential to different types of online customer service, depending
make cyberspace a secure place and tracking on the type of industry involved. Recently almost all
monetary frauds online is one of its good websites allow the customer to chat with the website
applications. Online fraud detection is an advanced representative. However, not website has an
application of machine learning algorithm. This executive. Basically, they develop a chat-bot to chat
approach is practical to provide cybersecurity to the with the customer to know their opinion. This is
users efficiently. Recently, PayPal is using a machine possible only for the machine learning approach. It’s
learning and artificial intelligence algorithm for just a beauty of machine learning algorithm.
money laundering. This advanced machine learning
and artificial intelligence example helps to reduce the viii. Robot Control
loss and maximize the profit. Using machine learning Robotic control is the system that
in this application, the detection system becomes contributes to the movement of robots. This involves
robust than any other traditional rule-based system. the mechanical aspects and program systems that
makes possible to control robots. A machine learning
v. Speech Recognition algorithm is used in a variety of robot control system.
One of the applications of Machine Learning For instance, recently, several types of research have
is speech recognition. Speech recognition is the been working to gain control over stable helicopter
ability of a machine or program to identify words and flight and helicopter aerobatics. Another good
phrases in spoken language and convert them to a example of robotic control is the Darpa-sponsored
machine-readable format. Alternatively referred to as, competition- a robot driving for over one hundred
voice recognition is a computer software program or miles within the desert was won by a robot that used
hardware device with the ability to decode the human machine learning to refine its ability to notice distant
voice. Voice recognition is commonly used to objects (Mehedi, 2019).

www.ijera.com DOI: 10.9790/9622-1108025564 62 | P a g e


Asongo, A.I, et. al. International Journal of Engineering Research and Applications
www.ijera.com
ISSN: 2248-9622, Vol. 11, Issue 8, (Series-II) August 2021, pp. 55-64

ix. Image Recognition REFERENCES


Image Recognition is one of the most [1]. Liyuan, L., and Jennifer, P.L. (2018). A
significant Machine Learning and artificial Comparison of Machine Learning Algorithms
intelligence applications. It is the process of for Prediction of Past Due Service
identifying and detecting an object or a feature in a in Commercial Credit. Grey Literature from
digital image or video. This concept is used in many PhD thesis. Retrieved from
applications like systems for factory automation, toll https://digitalcommons.kennesaw.edu/dataphd
booth monitoring, and security surveillance. Typical greylit/8 on April 3, 2019.
image recognition algorithms include Optical [2]. Praveena, M. and Jaiganesh, V., ( 2017). A
character recognition, Object Recognition, Face Literature Review on Supervised Machine
Recognition, Scale-invariant Feature Transform, Learning Algorithms and Boosting Process.
Speeded Up Robust Features, Principal Component International Journal of Computer
Analysis and Linear Discriminant Analysis. This Applications (0975 – 8887) Volume 169 –
technique can be used for further analysis, such as No.8, July, 2017
pattern recognition, face detection, face recognition, [3]. Praveen M. (2020). Machine Learning in Web
optical character recognition, and many more. Analytics. Retrieved June 10, 2021 from
https://towardsdatascience.com/machine-
x. Social Media Services learning-in-web-analytics
One key area of application of machine [4]. Benard M. (2016). Benard Marr Blog on
Learning is in Social media. Social Media Services Machine Learning history. Available on
also known as social networking site or social media https://www.forbes.com/sites/bernardmarr/201
are online platforms which people use to build social 6/02/19/a-short-history-of-machine-learning
networks or social relationships with other people Accessed on December 27, 2020
who share similar personal or career interests, [5]. Keith B. (2019). History of Machine
activities, backgrounds or real-life connections. Learning. Keith D. Foote blog on March 26,
Common examples of social media services 2019. Available on
includesFacebook, Twitter, Pinterest, Instagram, https://www.dataversity.net/a-brief-history-of-
LinkedIn etc. Social media is using the machine machine-learning. Accessed on December 20,
learning approach to create attractive and splendid 2020
features, i.e. people you may know, suggestion, react [6]. Russell S., Norvig P. (2003). Artificial
options for their users. These features are just an Intelligence: A Modern Approach (2nd ed.).
outcome of the machine learning technique. Social Prentice Hall. ISBN 978-0137903955.
media is using the machine learning approach to [7]. Langley, P., Simon, H., Bradshaw, G.
create attractive and splendid features, i.e. people you &Zytkow, J. (1987), Scientific Discovery:
may know, suggestion and react options for their Computational Explorations of the
users. Creative Processes. MIT Press, Cambridge
[8]. Lee, H., & Choi, B. (2003). Knowledge
VII. CONCLUSION management enablers, processes, and
This paper provides practical insights on organizational performance: An
what machine learning is, the history, types, models, integrative view and empirical examination.
software and its application in real life. Machine Journal of Management Information
learning in this new era, is demonstrating the promise Systems, 20(1), 179– 228.
of producing and completing complex tasks with [9]. Nakhaeizadeh, G., & Taylor, C. (eds.) (1997).
effective and unimaginable results. Machine learning Machine Learning and Statistics: The
system effectively “learns” how to estimate from Interface. New York: Wiley- Interscience.
training set of completed projects. The paper outlined [10]. Mohamed A.H. (2009). Credit Risk Modeling
and expounded the application of machines learning in Developing Economy: The Case of Libya.
and its different fields and presents the most PhD Thesis. Griffith University.
commonly used machine learning applications [11]. Saitta, L. &Neri, F. (1998). Learning in the
software such as WEKA, Salford predictive modeler, real world. Machine Learning, 30, 133–163.
OpenCV, Torch, LIONSolver, NeuroSolution, 114
KXEN Modeler, RapidMiner, Databricks and H2O. [12]. Thomas, L. (2000). A survey of credit and
behavioural scoring: Forecasting financial risk
Acknowledgment of lending to consumers. International Journal
The authors sincerely thank all the reviewers for their of Forecasting,16(2), 149–172.
kind comments. Declaration of interest: none [13]. Henley, W., and Hand, D. (1996). k-nearest-
neighbour classifier for assessing consumer

www.ijera.com DOI: 10.9790/9622-1108025564 63 | P a g e


Asongo, A.I, et. al. International Journal of Engineering Research and Applications
www.ijera.com
ISSN: 2248-9622, Vol. 11, Issue 8, (Series-II) August 2021, pp. 55-64

credit risk. The Statistician, 45(1), 77– [30]. Battiti, Roberto; Mauro Brunato (2014). The
95. LION way. Machine Learning plus Intelligent
[14]. Feiring, B. R. (1986). Linear programming: Optimization.. Available online at
An Introduction. Beverly Hills: Sage https://www.academia.edu/28682987/ Viewed
Publications. on 29 May, 2021
[15]. Mangasarian O. (1965). Linear and nonlinear [31]. Neuro Networks (2020). Website information.
separation of patterns by linear programming, Accessed on April 3, 2021 from
Operations Research 13, pp. 444–452. www.neurosolutions.com/
[16]. Freed, N., and Glover, F. (1981). Simple but [32]. InfinityInsights (2021). Who we are: website
powerful goal programming models for Information accessed on July 6, 2021 from
discriminant problems. European Journal of www.infinityinsight.com/
Operational Research, 7, 44–60. [33]. Markus H., Ralf K. (2013). RapidMiner: Data
[17]. Ignizio, J. P. (1985). Introduction to Linear Mining Use Cases and Business Analytics
Goal Programming. Beverly Hills: Sage [34]. Applications (Chapman & Hall/CRC Data
Publications. Mining and Knowledge Discovery Series),”
[18]. Koehler, G., and Erenguc, S. (1990). CRC Press, October 25, 2013. Available on
Minimizing misclassifications in linear line at https://pdfs.semanticscholar.org/
discriminant analysis. Decision Downloaded on May 28, 2020
Sciences,21(1), 63–85. [35]. Delta Lake (2021). All your data, Analytics
[19]. Holland, J. (1975). Adaptation in Natural and and AI on one Lake Platform. website
Artificial Systems. Ann Arbor: University of information accessed from
Michigan Press. https://databricks.com/ on July 1, 2021.
[20]. Bishop C. M. (2006). Pattern Recognition and [36]. H2o Software. Open Source Machine Learning
Machine Learning. Springer. ISBN 0- 387- software. Website information accessed from
31073-8. www.h2o.ai/products/h2o/
[21]. Suykens, J. &Vandewalle, J. (1999). Least [37]. Mehedi H. (2020). Top 20 Best Examples and
squares support vector machines. Neural Applications of Artificial Intelligence and
processing letters, 9,293–300. 105 Machine Learning,Ubuntupit Blog.
[22]. Sprinthall, R. & Fisk, S. (1990). Basic https://www.ubuntupit.com/top-20-best-
statistical analysis. Prentice Hall, NJ, USA. 95 machine-learning-applications-in-real-world/
[23]. Baesens, B., Van Gestel, T., Stepanova, M., [38]. Hoy, Matthew B. (2018). "Alexa, Siri,
Suyken, J., and Vanthienen, J. (2003). Cortana, and More: An Introduction to Voice
Benchmarking state-of- the-art Assistants". Medical Reference
classification algorithms for credit scoring. Services Quarterly. 37 (1): 81–88.
Journal of the Operational Research Society, doi:10.1080/02763869.2018.1404391.
54(6),627– 635 PMID 29327988.
[24]. Breiman, L. (2001). Random forests. Machine
learning, 45, 5–32. 105
[25]. Breiman L. (2000). Randomizing outputs to
increase prediction accuracy. Machine
Learning, 40:229–242.
[26]. Witten, I., Frank. E., Hall M., Christopher J.
(2011). Data Mining: Practical machine
learning tools and techniques, 3rd Edition".
Morgan Kaufmann, San Francisco (CA).
Retrieved 2011-01-19
[27]. Salfold Systems (2020). Website information.
Accessed on June 10, 2021 from www.salford-
systems.com/
[28]. Adrian K. and Gary B. (2016). Learning
OpenCV 3: Computer Vision in C++ with the
OpenCV Library. O'Reilly Media.
pp. 26ff. ISBN 978-1-4919-3800-3.
[29]. Torch7 (2020): A Matlab-like Environment for
Machine Learning (PDF). Neural Information
Processing Systems. 2011. Online at
https://publications.idiap.ch/downloads/papers/

www.ijera.com DOI: 10.9790/9622-1108025564 64 | P a g e

View publication stats

You might also like