Computer Science and Information Technologies

Vol. 4, No. 3, November 2023, pp. 226~239

ISSN: 2722-3221, DOI: 10.11591/csit.v4i3.pp226-239  226

Generalization of linear and non-linear support vector machine

in multiple fields: a review

Sundas Naqeeb Khan1, Samra Urooj Khan2, Hanane Aznaoui3, Canan Batur Şahin4,
Özlem Batur Dinler5
1
Department of Graphics, Computer Vision, and Digital Systems, Silesian University of Technology, Gliwice, Poland
2
Department of Electrical Engineering Technology, Punjab University of Technology, Rasul, Mandi Bahauddin, Punjab, Pakistan
3
Faculty of Computer Science, Cadi Ayyad University, Marrakesh, Morocco
4
Faculty of Computer Science, Turgut Özal University, Ankara, Turkey
5
Faculty of Computer Science, Siirt Üniversitesi, Siirt, Turkey

Article Info ABSTRACT

Article history: Support vector machines (SVMs) are a set of related supervised learning
methods used for classification and regression. They belong to a family of
Received Mar 22, 2023 generalized linear classifiers. In other terms, SVM is a classification and
Revised May 28, 2023 regression prediction tool that uses machine learning theory to maximize
Accepted Jun 29, 2023 predictive accuracy. In this article, the discussion about linear and non-linear
SVM classifiers with their functions and parameters is investigated. Due to
the equality type of constraints in the formulation, the solution follows from
Keywords: solving a set of linear equations. Besides this, if the under-consideration
problem is in the form of a non-linear case, then the problem must convert
Sentiment analysis into linear separable form with the help of kernel trick and solve it according
Generalization to the methods. Some important algorithms related to sentimental work are
Oversimplification also presented in this paper. Generalization of the formulation of linear and
Pre-processing non-linear SVMs is also open in this article. In the final section of this paper,
Support vector machines the different modified sections of SVM are discussed which are modified by
different research for different purposes.
This is an open access article under the CC BY-SA license.

Corresponding Author:
Sundas Naqeeb Khan
Department of Graphics, Computer vision and digital systems, Silesian University of Technology
Akademicka Street 2A, 44-100 Gliwice, Poland
Email: [email protected]

1. INTRODUCTION
Oversimplification performance for pattern recognition with any classifier can be attained while the
classification capability is achieved along with a better formulation function. This formulation function must
apply to the training set for the matching process in which the size is the most favorable factor. Instead of the
functions, classifiers keep several parameters for doing work position but these parameters change according
to the situation, so these parameters have moldability, due to this, known as amendable parameters. Based on
classification capability, these parameters be trained quickly about the training set devoid of any error but
display a slightly low simplification method [1]. On the contrary, a classifier with non-amendable parameters
or functions can’t maintain its capability for competent learning at all. Between them, the classifier's finest
capability for competence adjustment minimizes the estimated simplification error for the training set which
is provided as an original form. According to the empirical proof with theoretical investigation associated
with the simplification error for the training set with the help of a classifier, the classifier also resolves the
complexity issue in learning [2], [3]. Risk minimization error becomes the foundation of the unique classifier

Journal homepage: http://iaesprime.com/index.php/csit

Comput Sci Inf Technol ISSN: 2722-3221  227

that sustains the ability to solve this issue with very high performance for pattern recognition named support
vector machines (SVMs).
Nowadays this classifier solves a large number of problems in regression and classification sections
with high accuracy. The concerning point of SVMs is to explore a hyper-plane within n-dimensional space
which has particularly categorized the data according to its own selected data points called support vectors
[4]. SVM belongs to the category of supervised learning that is linked with learning algorithms in which
analysis of data provides accuracy for classification and regression problems. SVM is a representative of
training sets (data points) in a bounded region, separated into two classes of data with a reasonable distance
with the help of support vectors [5]. Thus, with the separation process of SVM, the bounded region is divided
into two marginal categories with suitable distance while the gap between two separable classes, and support
vectors should be as wide as possible. The main reason behind the wide range of distance between selective
support vectors is new prediction [6].
SVM performs two types of classification such as linear and non-linear. Linear classification is
active when data of classes are in labeled form. On the other hand, supervised learning cannot handle the
non-linear problem of classification. On behalf of this, researchers used a trick which is known as a kernel in
which the mapping process shifts their inputs into high dimensional feature space, to solve these types of
problems [7]. On the record, an SVM constructs a hyper-plane into high dimensional space in which
separated regions with decided boundaries become the reason for the largest distance between selected
support vectors. The gap between the selected support vectors of two classes is called functional margin. In
general, when the margin is low then the simplification error of the classifier is also low vice versa [8]. The
primary issue can be in a predetermined dimensional space in which the data sets are not present in the form
of a linear set, due to this reason, this space turns into high dimensional space. Reasonable, the mapping
process of SVM operates a dot product function in which the input data appears in pairs. As a subject, these
pair vectors can be calculated in terms of variables with their kernel function k(𝑥, 𝑦). With the help of a
conversion scheme, high dimensional space consists of data sets and the points of including these data sets
perform dot product along a vector such as a set of vectors is minimal. The vectors satisfy the pre-defined
hyper-planes with their linear parameters ∝𝑖 of classes of feature vector 𝑥𝑖 database. A point x in the feature
space which is going to be mapped on hyper-plane, describes the relationship of ∑𝑛𝑖 ∝𝑖 𝑘(𝑥𝑖 , 𝑥) =
𝑐𝑜𝑛𝑠𝑡𝑎𝑛𝑡,where 𝑘(𝑥, 𝑦) become small y extended as compared to x, every measurement of summation is
grown to be the degree of proximity of test point x to the equivalent database 𝑥𝑖 . Besides this, kernel
summation is used for the measurement of the comparative proximity of every test point while this function
construct or designs the optimal solution for the relative problem with some modifications [9]. The usage of
SVM can vary according to the domain of the problem and solve a variety of real-world problems such as
text categorization, image classification, recognition of handwritten characters, and bioinformatics [10].

2. RECENT LITERATURE
This section emphasizes the most related work for other researchers who used SVM for the
generalization of their research problems. Here we describe some significant research portions that are based
on the algorithms. The SVM algorithm is used for classifying the data according to the steps in Figure 1.

Input: I: Input data

Output: V: Set of support vectors
Begin
Step 1: Divide the given dataset into two set of data items having different class labels assigned to them
Step 2: Add them to support vector set V
Step 3: Loop the divided n data items
Step 4: If a data item is not assigned any of the class labels, then add it to set V
Step 5: Break if insufficient data items are found
Step 6: End loop
Step 7: Train using the derived SVM classifier model and test so as to validate over the unlabeled data items
End

Figure 1. Steps of SVM for sentiment analysis

According to Pavlidis et al. [11] research is based on the performance improvement in sentiment
analysis regarding classification. The proposed methodology presents the combination of SVM and Naïve
Bayes (NB) along with excellent results concerning accuracy metrics. They give two new algorithms for
sentiment analysis according to the word and sentence level and these algorithms [12] perform preprocessing
steps on selected datasets and translate unstructured forms of reviews into structured forms furthermore
structured forms translate into numerical values with the help of the lexicon scoring method. Therefore, the

Generalization of linear and non-linear support vector machine in multiple fields: … (Sundas Naqeeb Khan)
228  ISSN: 2722-3221

focused area of research in this research is feature selection and semantic analysis. For classification
purposes, SVM is used with its radial basis kernel function. Whereas, a dataset 𝐷 = {𝑋𝑖 , 𝑦𝑖 } as 𝑋𝑖 present the
set of records with class labels 𝑦𝑖 . A separating hyper-plane is used 𝑊 ∗ 𝑥 + 𝑏 = 0, where, 𝑊 =
{𝑤1 , 𝑤2 , … , 𝑤𝑛 } as 𝑤𝑛 is a weight vector with n features while b shows biases [13]. To achieve the goal, the
maximum margin hyper-plane with the help of lagrangian calculation in terms of formula for record testing
as: in SVM classifier perform operations for accuracy according to the 𝑓(𝑥) = ∑𝑛𝑖=1 ∝𝑖 𝑘(𝑋, 𝑋𝑖 ) + 𝑏 given
‖𝑋−𝑋́ ‖2
formula, where 𝑘(𝑋, 𝑋𝑖 ) is the radial basis kernel function along 𝑒𝑥𝑝 (− ) formulation. Another
2𝜎
research article presented text classification through cosine similarity with latent semantic indexing for the
Arabic language. In the reference article [14], the proposed algorithm is based on some useful steps. Table 1
illustrate the related literature about the usage of SVM with its properties, functions, datasets, algorithm
modifications, rules, and hybridization to solve different types of problem in the real world [15].

Table 1. Different research fields where SVM used for excellent results
Research areas Count frequency
Sentiment analysis [16]–[20]
Text categorization [21]–[23]
Image classification [24]–[26]
Bio-informatics [27]–[30]
Other fields [31]–[33]

3. BACKGROUND INFORMATION ABOUT SUPPORT VECTOR MACHINES

In the past two decades, machine learning progressed in the knowledge domain and performs
actions as a backbone. It evolves as a pivot point in our daily life. In the word world, data is growing day by
day then control of the access process to the data availability turns into a problem. The logical motivation to
consider is that elegant data analysis should be inescapable from the technical development. Machine
learning divided the outer factors into two major fields such as art and science. In the art field, it tries to
decrease some contrasting category issues with the help of quite contracted models while in the science field,
providing solutions to the issues with generalization performance [34], [35]. Intellectual learning is a field of
processes that describe complicated tasks specifically concerning understandable methods. According to the
standard definition of learning is “to increase knowledge with high indulgent or expertise through, learning,
training, and practice”. Therefore, learning about machine systems, mechanisms, infrastructure, approaches,
and working styles is collectively known as machine learning. Normally, the modifications of a system are
submitted to the work positions to operate several activities directly connected to artificial intelligence.
Several categories of activities engross in detection, analysis, arrangement, robot control systems, and
calculation. The modifications can be relevant to the enhancements or can be new [36].
The main conceptual idea about machine learning work can be comprehended in the light of four
broader perspectives. Firstly, its focal point is prediction while the prediction keeps some background
knowledge about things. Therefore, that background knowledge is useful in prediction such as based on the
past, and what they did. Secondly, it searches out the relationship between original data and prediction
practically. Thirdly, it can exploit a set of stimuli/inputs for prediction with statistical approaches in technical
form. Lastly, it tries to predict the value of a variable Y that is given an input of feature set X [37]. Machine
learning is divided into three main categories such as supervised learning, semi-supervised learning, and
unsupervised learning furthermore, these categories sub-divisions are shown in Figure 2. The study of the
support vector knowledge is beneficial from two major perspectives. Firstly, the theoretical part is strong
enough for satisfactory analysis in which the work foundation is pleasant with straightforward initiatives and
designs with a strong structure. Secondly, the guidance about any experimental application with high
accomplishment achieved. The intersection between the theoretical portion with experimental support vectors
becomes an intelligence of work for practical life [38]. Several categories of algorithms along arithmetical
tests might be classifying knowledge in a particular field and environmental factors support its structure.
However, the real world needs to use and learn the most multifaceted designs and algorithms just like neural
networks which are more complex than support vectors in the form of theoretical analysis [39].
The SVM predicts the supporting vectors for the separation of two classes with high margins.
Support vectors perform mathematical operations easily due to their special correspondence regarding a
linear scheme in a high-dimensional feature space. This feature space is non-linearly associated directly with
input space. Furthermore, a linear structure in a high dimensional space performs accurate operations in
experimental applications but the formulation of any mathematical equations cannot be computed in that
structural space. Therefore, kernels are a type of trick for solving this issue of computation [40]. Kernels

Comput Sci Inf Technol, Vol. 4, No. 3, November 2023: 226-239

Comput Sci Inf Technol ISSN: 2722-3221  229

achieve any type of formulation with evidence straight in that input structural space. A very nice solution
provided by a curl of support vectors is kernels.
Nowadays, researchers focus on non-linear trends for detection, deterioration problems, or mining
of significant features of useful applications. Support vectors become the root of some branches such as the
theoretical part of any knowledge, to get the most favorable results for hyper-plane algorithms, the
computation of kernel operations, and its functional evaluation [41]. Hyper-planes: according to the
mathematical term, a hyper-plane is divided into sub-spaces where the measurement belongs to its circulating
spaces. There are some specific learning rules for describing the relationship between the hyper-plane and its
spaces: if a space is represented in 3D it means its relation with the hyper-plane is in 2D planes while if the
space performing its operation within 2D then its associated hyper-plane is in 1D line. These rules are
implemented normally in generic spaces which belong to the idea about the structure of the sub-spaces.
Hyper-planes help to support vectors for their activities regarding pattern recognition or natural language.
Figure 3 illustrates many unique categories of spaces used in different types of hyper-planes. Every space has
some sub-category functions e.g., branch space has norm and completeness as sub-functions [42]. Therefore,
the presented result of this hyper-plane is going to be a solution of a single linear mathematical form such
as 𝑎1 𝑥1 + 𝑎2 𝑥2 +. . . +𝑎𝑛 𝑥𝑛 + 𝑏 = 0. Projective hyper-plane extended the concept of the plane. Sub-division
of the spaces is not possible in this form but it considers the two hyper-planes for division of the points and
then space. While it keeps a set of points along its property. For any two points from the set construct a
learning rule for examination of the rest of all points in the set e.g., a lone hyper-plane in which all the sides
are connecte [43], [44]. For the structure of the algorithm, a combination of functions is required for a class
in which capacity may be involved as a primary objective. Support vectors become the foundation of hyper-
planes equivalent towards the conclusion purpose (w. x) + b = 0 where w ϵ RN , b ϵ R. This is a simple
equation for getting optimal hyper-plane within space [40]. Generalization of SVM: machine learning is a
sub-field of artificial intelligence in which the main research is about the expansion phase of the approaches
with their suitable schemes whereas the computer learns and is used as a machine. Moreover, the expansion
phase included algorithms in which the machine learning process is considered its major task with their sub-
activities. In so many traditions, machine learning has common characteristics among statistical progress.
With time, various useful approaches with their structural design proposed for machine learning activities
[45].
The history of the SVM algorithm originated in 1963 by Vapnik and in 1992, the first time SVM
was introduced based on a set of correlated supervised learning methods, and these methods were used for
classification and regression problems as non-linear classifiers. According to the non-linear classifier, Vapnik
used kernel tricks for getting maximum margin hyper-planes [46], [47]. SVM is a specific type of
classification while the working layout depends on the conversion process where the training dataset is
transformed into a higher dimensional space in which the main purpose is to investigate how to divide
decision boundaries among classes. According to these boundaries, hyper-planes become useful boundaries
in which support vectors can be classified rather than other data points with their margin. These margins are
present in the form of parallel lines which describe through the shortest distance between a hyper-plane and
its support vectors. Therefore, SVM is capable of classification of both types of datasets such as linear and
non-linear [48], [49]. SVM roughly sketched for some significant issues [50] that is: class division:
researchers tried to obtain the optimum extrication solution for hyper-plane among the selected classes
through maximizing the distance. The distance between decision boundaries and support vectors is called
margin as shown in Figure 3 and in between these margins, researchers get their optimal hyper-plane.
Internal representation of classes: selected support vectors reside in the opposite direction of the prominent
distance effect on the margin and reduce its effect in terms of weight. Non-linear property of classes: there is
a big issue regarding if the linear separation cannot be found then selected support vectors can expected
towards higher dimensional space whereas these selected data points used kernel trick while efficiently
participating in linearly separable operation [51]. Weights of classes: this depends on the particular vector
which is known as the weight component such as A and B are two different classes with asymmetric class
sizes with weight vectors. Cross-validation for classification: for training data evaluation, k-fold cross-
validation is executed through different possible combinations of the parameters in which most of the time
default values are set for good accuracy.
𝟐
Why does the SVM margin is ‖𝐰‖: by using geometry, the margin is probably related to the
maximum distance between two parallel hyper-planes that can separate the two-point sets; let x0 be a point in
the hyper-plane of wx − b = −1, so this hyper-plane equation becomes wx0 − b = −1 [52], [53]. To
measure the distance between hyper-planes wx − b = −1, and wx − b = +1, there is only a need to
w
compute the perpendicular distance from x0 to plane wx − b = 1, denoted as r. Therefore, ‖w‖ is a unit
w w
normal vector of the hyper-plane wx − b = 1 ⇒ w (x0 + r ‖w‖) − b = 1, where (x0 + r ‖w‖) should be a

Generalization of linear and non-linear support vector machine in multiple fields: … (Sundas Naqeeb Khan)
230  ISSN: 2722-3221

point in hyper-plane, according to the definition of r, equation of hyper-plane becomes as [54]. General
example: an easy example selected from our daily life. Let’s suppose here a scenario-1 is given for the testing
approach. Scenario-1: “I have a business and I receive a lot of emails from customers every day. Some of
these emails are complaints and should be answered very quickly. I would like a way to identify them
quickly so that I answer these emails in priority”. According to this given scenario [55], we try to provide the
best optimum solution with the help of a supervised machine learning algorithm with some significant steps.
Now a supervised learning algorithm e.g., SVM is used for training sessions along the labeled dataset as a
linear model. So in simple words, the linear model is based on a line that separates the data hyper-plane.
Some points are described in Figure 4 and these play an important role in the process of separating the line in
hyper-plane [56], [57].

Figure 2. Sub-division of machine learning approaches

Figure 3. Types of abstract spaces of hyper-planes

Figure 4. Learning properties for a line with the separation process

Comput Sci Inf Technol, Vol. 4, No. 3, November 2023: 226-239

Comput Sci Inf Technol ISSN: 2722-3221  231

There are four major types of SVM used for classification tasks in any field of research. In terms of
scenario 1, SVM is divided into four categories of classification: i) the original one: the maximum margin
classifier; ii) the kernelized version using the kernel trick; iii) the soft margin version; and iv) the soft margin
kernelized version in which i), ii), and iii) are combined.
These four types merged into two types of SVM to linear and non-linear SVM. Figure 4 illustrates
the linear SVM in the best way. Formulation of SVM problem: In this type of SVM, the classifier basic
element is a separating hyper-plane with the line equation along [+1 -1] interval. The significant points that
belong to the training sets are considered support vectors which these points have the properties of the
separating process of hyper-plane. Mathematically, a linear SVM-focused equation is the separation of the
hyper-plane with its optimum line as (1) to (4) [58].

𝑊. 𝑋 + + 𝑏 = +1 (1)

𝑊. 𝑋 − + 𝑏 = −1 (2)

𝑊. (𝑋 + − 𝑋 − ) = 2 (3)

(𝑥 + −𝑥 − ).𝑤 2
𝑀= |𝑤|
= |𝑤| (4)

Where +1 belongs to the positive predicted class, -1 belongs to the negative predicted class, w is the weight
vector and M is the margin width.
Consequently, the main achievement through linear SVM can be obtained by the formulation
according to the formulas along their properties as (5) [59].

𝑤𝑥𝑖 + 𝑏 ≥ 1 𝑖𝑓 𝑦𝑖 = +1
({𝑤𝑥𝑖 + 𝑏 ≤ 1 𝑖𝑓 𝑦𝑖 = −1) (5)
𝑦𝑖 (𝑤𝑥𝑖 + 𝑏) ≥ 1 𝑖𝑓 ⩝𝑖

2 1
To maximize the margin |𝑤|
, and minimize 𝑤 𝑇 𝑤, researchers formulate a quadratic optimization problem
2
through the given equation with its subject constraint as (6).

{𝑚𝑖𝑛𝑖𝑚𝑖𝑧𝑒 ∅(𝑤) − 1/2 𝑤^𝑡 𝑤 𝑠𝑢𝑏𝑗𝑒𝑐𝑡 𝑡𝑜 𝑦_𝑖 (𝑤𝑥_𝑖 + 𝑏) ≥ 1 ∀_𝑖} (6)

For the proper solution, to solve the optimization problem, to find this statement:
1
{(𝑤 𝑎𝑛𝑑 𝑏)| min ∅(𝑤) = 𝑊 𝑇 𝑊 𝑎𝑛𝑑 ∀ {(𝑋𝑖 , 𝑌𝑖 )}: 𝑦𝑖 (𝑊 𝑇 𝑋𝑖 + 𝑏) ≥ 1} [60]. Therefore, for the optimization
2
of a quadratic function, linear constraints become a powerful subject. In mathematical programming
problems, quadratic optimization problems are a very famous category for optimal solutions. These solutions
include the structural design which is known as a dual problem in which a Lagrange multiplier named ∝𝑖 is
linked along each and every constraint within the primary problem [61]. For solving the optimization
problem, some properties combined in a formulation as (7):
1
𝑸(∝) = ∑ ∝𝑖 − ∑ ∑ ∝𝑖 ∝𝑗 𝑦𝑖 𝑦𝑗 𝑋𝑖𝑇 𝑋𝑗 𝑠𝑢𝑏𝑗𝑒𝑐𝑡 𝑡𝑜 ∑ ∝𝑖 𝑦𝑖
𝐹𝑖𝑛𝑑 (∝1 , … , ∝𝑁 )| max 2 (7)
= 0, ∝𝑖 ≥ 0 ∀∝𝑖

the formation of the solution depends on w and b as (8):

{(𝑤 = ∑ ∝𝑖 𝑦𝑖 𝑋𝑖 ) 𝑎𝑛𝑑 (𝑏 = 𝑦𝑘 − 𝑊 𝑇 𝑋𝑘 ) 𝑓𝑜𝑟 𝑎𝑛𝑦 𝑋𝑘 | ∝𝑘 ≠ 0} (8)

whereas each ∝𝑖 shows that it corresponding 𝑋𝑖 . This will be a support vector. Based on the category of
problem, the classifying function will have the form (9) [62].

𝑓(𝑋) = ∑ ∝𝑖 𝑦𝑖 𝑋𝑖𝑇 + 𝑏 (9)

This function depends on, an inner product between the testing point x and its corresponding sup
isport vector xi. Calculation of the inner products 𝑋𝑖𝑇 𝑋𝑗 between all pairs of points of the training set involved
in the solution of the optimization problem. As per instructions, if noise detects in the training set then slack
variables 𝜉𝑖 can be added in the function and allow misclassification of difficult data. After adding the slack
Generalization of linear and non-linear support vector machine in multiple fields: … (Sundas Naqeeb Khan)
232  ISSN: 2722-3221

variable in the quadratic optimization problem, the (10) will become next, and the representation is shown in
Figure 5.

1
{min ∅(𝑥) = 𝑊 𝑇 . 𝑊 + 𝐶 ∑𝑁 𝑇
𝑘=1 𝜉𝑘 ∀{(𝑋𝑖 , 𝑦𝑖 )}|𝑦𝑖 (𝑊 𝑋𝑖 + 𝑏) ≥ 1 − 𝜉𝑖 𝑎𝑛𝑑 𝜉𝑖 ≥ 0 ∀𝑖 } (10)
2

Where 𝐶 indicates the capacity parameter, 𝜉𝑖 represents parameters for handling the non-separable points,
and index i shows the labels of N training sets [63].
If the dataset is just too hard more shown in Figure 5 then convert this dataset into higher
dimensional space. The linear classifier relies on a dot product vector which is 𝐾(𝑋𝑖 , 𝑋𝑗 ). Therefore, every
single data point is mapped into higher dimensional space through a transformation process like 𝜙: 𝑋 →
𝜑(𝑋) where a kernel function corresponds to an inner product within the expanded feature space. If data is
not linearly separable, there is a function used for the transformation process to convert this data into higher
dimensional space [64]. So, the data goes from 1D to 2D for representation of the data. Based on the function
f(x), conversion of the dataset from 2D space to 2D feature dimensional space is easy. Now the only problem
with transformation into higher dimensional feature space is that it’s computationally expensive. Based on
expensive calculations, researchers use a kernel trick to reduce the computational process. A function that
takes as an input vector in the original space and returns the dot product of the vectors in the feature space is
called a kernel function also referred to as kernel trick [65]. Using a kernel function, researchers can apply
the dot product within the two vectors, so that every point is mapped to a higher dimensional space via some
transformation. Therefore, essentially various scholars use this kernel trick to transform a non-linear space
into a linear space. Some popular kernel tricks are used to transform the data into higher dimensional feature
space [66].
− Linear kernel function, 𝐾(𝑋𝑖 , 𝑋𝑗 ) = 𝑋𝑖𝑇 . 𝑋𝑗
𝑝
− Polynomial kernel function, 𝐾(𝑋𝑖 , 𝑋𝑗 ) = (1 + 𝑋𝑖𝑇 . 𝑋𝑗 )
2
‖𝑋𝑖 −𝑋𝑗 ‖
− Radial basis function (RBF), 𝐾(𝑋𝑖 , 𝑋𝑗 ) = 𝑒𝑥𝑝 (− )
2𝜎 2

− Sigmoid kernel function, 𝐾(𝑋𝑖 , 𝑋𝑗 ) = tanh(𝛽0 𝑋𝑖𝑇 . 𝑋𝑗 + 𝛽1 )

Figure 5. Linearly separable hyper-plane with slack variables

Unfortunately, choosing the correct kernel is a non-trivial task or maybe an unspecific task at hand,
no matter which kernel researchers choose according to their problem. There are some properties used during
the selection of kernel function e.g., the need to tune the kernel program to get good performance for the
classifier. A famous program the researchers need to tune includes k-fold cross-validation [57]. Mercer’s
theorem: according to machine learning [67], kernel function scheme is a most famous trick that is a much
near type of Mercer in which a variety of issues such as regression, classification, and inverse issues
regarding optimization can be resolved competently. Kernel functions are linked along feature mapping due
to its mapping procedure where the dataset is mapped from the original space to higher dimensional feature
space. A common assumption where an input space X is mapped via a feature mapping {Φ: X → H|(x, y) ∈
X}, where K(x, y) 〈∅(x), ∅(y)〉H. In Figure 6, this theorem performance steps described in detail with useful
equations and matrices [46].

Comput Sci Inf Technol, Vol. 4, No. 3, November 2023: 226-239

Comput Sci Inf Technol ISSN: 2722-3221  233

Figure 6. Stepwise Mercer's theorem

Where dual problem formulation for non-linear SVMs is described in (11) and (12) [68].

{? (𝛼𝑖 , … , 𝛼𝑁 )|𝑚𝑎𝑥(𝑄(𝛼) = ∑ 𝛼𝑖 − 1/2 ∑ ∑ 𝛼𝑖 𝛼𝑗 𝑦𝑖 𝑦𝑗 𝑘(𝑋𝑖 , 𝑋𝑗 )), ∑ 𝛼𝑖 𝑦𝑖 = 0 𝑎𝑛𝑑 𝛼𝑖 ≥ 0, ∀𝛼𝑖 } (11)

𝑓(𝑥) = ∑ 𝛼𝑖 𝑦𝑖 𝑘(𝑋𝑖 , 𝑋𝑗 ) + 𝑏 (12)

4. RESULT
In this section, we present the different modified sections that took place in SVM by different
research in different years. Table 2 (see in Appendix) presents the different categories of the result like the
year, function, improvement, and objective of many researchers’ modification in SVM for their research
purpose [69]–[79]. In this research, we collect all the information related to SVM. Consequently, Table 3
shows some properties of SVM related to the applications, pros, and cons, and mentions in which section
they are modified and for what purpose they are used all the data are mentioned in the given table where
different research can be used.

Table 3. SVMs pros, cons, and applications

Parameter Value
Pros: some advantages of − They are effective in high dimensional spaces; they are still effective in cases where ‘R’ is
SVMs are: the number of dimensions greater than the number of samples. According to the notations
representation is: ⇒ 𝑅 ^ 𝑁 > 𝑠𝑎𝑚𝑝𝑙𝑒𝑠.
− They used a subset of training points in the decision function or support vectors. So, it’s
also memory efficient.
− Support vectors are first it all. So different kernels can be specified for the decision
functions. Common kernels are provided but it is also possible to specify the custom
kernels. The addition of kernel functions together to achieve even more complex hyper-
planes as 𝐾1 + 𝐾2 = 𝑐𝑜𝑚𝑝𝑙𝑒𝑥 ℎ𝑦𝑝𝑒𝑟 − 𝑝𝑙𝑎𝑛𝑒𝑠, where K1 and K2 represents the first and
second kernel functions respectively [79].
Cons: the disadvantages of − SVM does not directly provide supervised probability estimates.
SVMs include: − These are calculated using an expensive five-fold cross-validation.
− If the number of features is greater than the number of samples then the method is likely to
give poor performance.
Application: it can be a quite − Medical imaging
popular alternative to − Regression model to study the air quality in the urban areas
artificial neural networks. − Image interpolation
Some useful applications − Medical diagnosis task
where SVMs used for good − Time series prediction as well as financial analysis
performance are: − Encoding theory with practice
− Pattern recognition
− Page ranking algorithm
− Text and object recognition

5. DISCUSSION
The optimization issues were resolved with the help of a support vector along with analytical
analysis. Some conditions were applied to the selected dataset for further processing. Especially for small
training datasets or the linear case, it is very critical to know which of the training datasets become support
vectors. This situation can happen when the issue is relevant to the symmetry case. Generally, the worst-case
Generalization of linear and non-linear support vector machine in multiple fields: … (Sundas Naqeeb Khan)
234  ISSN: 2722-3221

computational complexity can happen during analytical analysis. Therefore, linear and non-linear SVM
formulation provides the right path for the solution numerically and analytically. On the other hand, a range
of approaches are used for the larger problems. Here in this article, we just describe the general research
areas with the researcher’s efforts and the generalization of the SVMs formulations for linear and non-linear
problems. Some properties such as complexity, scalability, and parallelizability of SVMs play significant
roles in the processing. The dataset of training and testing functions depends on the kernel functions although
it corresponds to a dot product in higher dimensional space. There are some turning points for the SVMs
where machine learning goes deep knowledge and requires more research such as the choice of the best
kernel according to the dataset, processing speed, dataset size in terms of training and testing phases,
rescaling, and optimal design for multi-class problems. According to the RBF kernel function, classifiers will
automatically give values for the RBF weights, number of centers, center positions, and threshold.

6. CONCLUSION
This article provides a detailed description of the concept of linear and non-linear SVM for multiple
areas of research such as sentiment analysis, text classification or categorization, image classification, and
bio-informatics. It gives both hypothetical and mathematical verifications that SVMs show this is a very
appropriate option for multiple fields. The hypothetical analysis concludes that SVMs accept the specific
properties for completing the given tasks. The mathematical generalization shows the influence of SVMs on
consistently achieving good performance, and advancements in existing methods considerably and drastically
outperforming. In this paper, the authors also present the kernel trick idea of SVM in multiple fields with
their four main functions linear, polynomial, RBF, and sigmoid functions. All under-reviewed articles show
that the best kernel functions selection provides excellent results with high effects of accuracy. We analyze
the field areas of the existing linear and non-linear SVMs with its kernel trick along selection of the function
and parameters settings. We also analyze the concept that is related to the classical procedure of SVM for
training the weights, improved training, and testing error rates through soft margin. The improvement in
testing error or risk was exclusively the reason for the lower value of the training error or empirical risk. All
this makes SVMs a very promising and easy-to-use method for learning multiple field classifiers from the
given or selected examples.

APPENDIX

Table 2. Summary of result section with the help of improvements and objectives of the SVM functions
Ref. Year Function Improvement Objective
[69] 2000 RBF 𝐾(𝑥, 𝑦) = ‖𝑃(𝑥 − 𝑦)‖2 = (𝑥 − 𝑦)𝑇 𝑃. 𝑃(𝑥 − 𝑦)1 Semantic kernel function used
𝑒𝑥𝑝(−𝛾‖𝑥 − ‖𝑃(𝑥 − 𝑦)‖2 = (𝑥 − 𝑦)𝑇 𝑆(𝑥 − 𝑦) 2 for text categorization.
𝑦‖2 ) (4) 𝑓(𝑥) = 𝑠𝑔𝑛(∑𝑖=𝑙 𝑖=1 𝛼𝑖 𝑦𝑖 𝐾(𝑥, 𝑥𝑖 ) + 𝑏) 3
𝐾(𝑥, 𝑦) = 𝑒𝑥𝑝(−𝛾‖(𝑥 − 𝑦)𝑇 𝑆(𝑥 − 𝑦)‖2 ) (5)
[70] 2015 Mahalanobis 1 SVM was used in the training
𝜙(𝑤) = ‖𝑤 ⃗⃗ ‖2 𝑠𝑢𝑏𝑗𝑒𝑐𝑡 𝑡𝑜 𝑦𝑖 (𝑤𝑥𝑖 + 𝑏) ≥ 1, ∀(𝑥𝑖 , 𝑦𝑖 ) ∈
2
distance phase and 𝑀𝑑𝑖𝑠𝑡 was used in
𝐷 (1)
𝑀𝑑𝑖𝑠𝑡 = the testing phase for
𝑓(𝑥) = 𝑠𝑔𝑛(∑𝑁 𝑠
𝑖=1 𝛼𝑖 𝑦𝑖 𝐾(𝑥𝑖 , 𝑥 ) + 𝑏) 2
√(𝑥 − 𝑚)𝐶𝑥−1 (𝑥 − 𝑚)𝐾(𝑥𝑇 improving the classification
𝑖 , 𝑥𝑖 ) = 𝜙(𝑥𝑖 ). 𝜙(𝑥𝑖 ) (3) accuracy.
(4)
𝑀𝑑𝑖𝑠𝑡 = √(𝑥 − 𝑚)𝐼−1 (𝑥 − 𝑚)𝑇 = √(𝑥 − 𝑚)2 =
𝐸𝑑𝑖𝑠𝑡 (𝑥, 𝑚) = 𝐸𝐷𝐶 (5)
𝑑𝑖 = √∑𝑛𝑖=1(𝑥𝑖 − 𝑚𝑖 )2 (6)
[71] 2008 Reference in this 𝑤𝑥 + 𝑏 = 0 (4) To investigate the
paper 27: 𝛹(𝑥) = 𝑚𝑖𝑛 1 ‖𝑤‖2 + 𝐶 ∑𝑖 𝜉𝑖 (5) effectiveness of using multi-
2
∑𝑁𝑖=1 𝐶𝑖 𝜑𝑖 (𝑥) and words for text representation
With constraints
𝑘(𝑥, 𝑦) = 𝑦𝑖 (𝑥𝑖 𝑤 + 𝑏) ≥ 1 − 𝜉𝑖 , 𝜉𝑖 ≥ 0, ∀𝑖 (6)
on the performances of text
∑∞ 2
𝑖=1 𝜆𝑖 𝜑𝑖 (𝑥)𝜑𝑖 (𝑦)
classification
[72] 2016 RBF 〈𝑤, 𝑤〉 → 𝑚𝑖𝑛, 𝑦𝑖 . (〈𝑤, 𝑧𝑖 〉 + 𝑏) ≥ 1, 𝑖 = ̅̅̅̅̅
1, 𝑆 (1) SVM ensembles are used for
𝐾(𝑧𝑖 , 𝑧𝜏 ) = {−𝐿(𝜆) = − ∑𝑆𝑖=1 𝜆𝑖 + big data classification with the
𝑒𝑥𝑝(−〈𝑧𝑖 − 1
modified particle swarm
𝑧𝜏 , 𝑧𝑖 − 𝑧𝜏 〉/ . ∑𝑆𝑖=1 ∑𝑆𝜏=1 𝜆𝑖 . 𝜆𝜏 . 𝑦𝑖 . 𝑦𝜏 . 𝐾(𝑧𝑖 , 𝑧𝜏 ) → 𝑚𝑖𝑛𝜆 , ∑𝑆𝑖=1 𝜆𝑖 . 𝑦𝑖 = optimization.
2
(2. 𝜎 2 )) 0, 0 ≤ 𝜆𝑖 ≤ 𝐶, 𝑖 = 1, ̅̅̅̅̅
𝑆} (2)
𝑓(𝑧) = ∑𝑆𝑖=1 𝜆𝑖 . 𝑦𝑖 . 𝐾(𝑧𝑖 , 𝑧) + 𝑏 (3)
𝐹(𝑧) = 𝑠𝑔𝑛(𝑓(𝑧)) = 𝑠𝑖𝑔𝑛(∑𝑆𝑖=1 𝜆𝑖 . 𝑦𝑖 . 𝐾(𝑧𝑖 , 𝑧) + 𝑏) (4)
𝑚𝑖𝑛 1
[73] 2016
𝑤,𝑏,𝜉 2
𝑊 𝑇 𝑊 + 𝐶 ∑𝑙𝑖=1 𝜉𝑖 To examine the accuracy of
the SVM performance for the
subject to 𝑦𝑖 (𝑤 𝑇 ∅(𝑋𝑖 ) + 𝑏) ≥ 1 − 𝜉𝑖 , 𝜉𝑖 ≥ 0 (5)
classification of human
sentiments.

Comput Sci Inf Technol, Vol. 4, No. 3, November 2023: 226-239

Comput Sci Inf Technol ISSN: 2722-3221  235

Table 2. Summary of result section with the help of improvements and objectives of the SVM functions
Ref. Year Function Improvement Objective
𝑚𝑖𝑛 1
[74] 2015 RBF + 𝐶 ∑𝑁
𝑤,𝑏 2
‖𝑤‖2
𝑖=1 𝑖 , 𝑠. 𝑡. 𝑦𝑖 (〈𝑤, ∅(𝑥)〉 + 𝑏) ≥ 1 −
𝜉 Numerical and nominal
𝐾𝐺𝐴𝑈 (𝑥𝑖 , 𝑥𝑗 ) = 𝜉 , 𝜉 ≥ 0, ∀ (1)
attributes are used in practical
2 𝑖 𝑖 𝑖
‖𝑥 −𝑥 ‖ 𝑚𝑎𝑥 𝑁 tasks, and the proposed
𝑒𝑥𝑝 (− 𝑖 𝑗 ) , 𝜎 ∈ 𝛼 ∑𝑖=1 𝛼 − heterogeneous SVM improves
2𝜎2 1
𝑅+ (3) ∑𝑛𝑖=1 ∑𝑛𝑗=1 𝛼𝑖 𝛼𝑗 𝑦𝑖 𝑦𝑗 〈∅(𝑥𝑖 ), ∅(𝑥𝑗 )〉 , 𝑠. 𝑡. ∑𝑛𝑖=1 𝛼𝑖 𝑦𝑖 = 0, 0 ≤ classification performance for
2
𝛼𝑖 ≤ 𝐶, ∀𝑖 (2) both of them.
𝑚𝑎𝑥 𝑛
𝛽𝑖
∑𝑖=1 𝛽𝑖 𝐾(𝑥𝑖 , 𝑥𝑖 ) − ∑𝑛𝑖,𝑗=1 𝛽𝑖 𝛽𝑗 𝐾(𝑥𝑖 , 𝑥𝑗 ), 𝑠. 𝑡. ∑𝑛𝑖=1 𝛽𝑖 =
1, 𝛽𝑖 ≥ 0, 𝑖 = 1 … 𝑛 (10)
𝑅 2 = 𝛽 𝑇 𝑑𝑖𝑎𝑔(𝐾) − 𝛽 𝑇 𝐾𝛽 (11)
𝜕𝑇 𝜕‖𝑤‖2 𝜕𝑅2
= 𝑅2 ∗ + ∗ ‖𝑤‖2 (17)
𝜕𝛼𝑖𝑘 𝜕𝛼𝑖𝑘 𝜕𝛼𝑖𝑘
𝜕‖𝑤‖2 𝜕𝐾(𝑥𝑖 ,𝑥𝑗 ) 𝜕𝐾
= − ∑𝑛𝑖,𝑗=1 𝛼𝑖∗ 𝛼𝑗∗ 𝑦𝑖 𝑦𝑗 = −𝛼 𝑇 ( ) 𝛼 (19)
𝜕𝛼𝑖𝑘 𝜕𝛼𝑖𝑘 𝜕𝛼𝑖𝑘
𝜕𝑅2 𝜕𝐾(𝑥𝑖 ,𝑥𝑖 ) ∗ ∗ 𝜕𝐾(𝑥𝑖 ,𝑥𝑗 )
= ∑𝑛𝑖=1 𝛽𝑖∗ − 𝑛
∑𝑖,𝑗=1 𝛽𝑖 𝛽𝑗 =
𝜕𝛼𝑖𝑘 𝜕𝛼𝑘 𝑖 𝜕𝛼𝑘 𝑖
𝜕𝐾 𝜕𝐾
𝛽 𝑇 𝑑𝑖𝑎𝑔 ( 𝑇
𝑘) − 𝛽 ( 𝑘 ) 𝛽 (20)
𝜕𝛼𝑖 𝜕𝛼𝑖
𝜕𝑇 2 𝜕𝐾 𝜕𝐾
= −𝑅 (𝛼 𝑇 𝑘 𝛼) + ‖𝑤‖2 (𝛽 𝑇 𝑑𝑖𝑎𝑔 ( )−
𝜕𝛼𝑖𝑘 𝜕𝛼𝑖 𝜕𝛼𝑖𝑘
𝑇 𝜕𝐾
𝛽 ( ) 𝛽)(22)
𝜕𝛼𝑖𝑘
𝜕𝐾(𝑥,𝑥́ ) ‖𝑥−𝑥́ ‖2 1 𝜕(‖𝑥−𝑥́ ‖2 )
= 𝑒𝑥𝑝 (− ) (− × )=
𝜕𝛼𝑖𝑘 2𝜎2 2𝜎2 𝜕𝛼𝑖𝑘
+1 𝑖𝑓 𝑥 = 𝑘
𝛼𝑖𝑘
𝑥 𝑘 −𝑥́ 𝑘
𝐾(𝑥, 𝑥́ ) (− ) × {−1 𝑖𝑓 𝑥́ 𝑘 = (24) 𝛼𝑖𝑘
𝜎2
0 𝑜𝑡ℎ𝑒𝑟𝑤𝑖𝑠𝑒
[75] 2016 RBF 1 To evaluate the effectiveness
𝑀𝑖𝑛 𝑤 2 𝑠. 𝑡. 𝑦𝑖 𝑓(𝑥𝑖 ) ≥ 1 − 𝜃𝐷(𝑥𝑖 )2 (2.8)
2
𝑘(𝑥𝑖 , 𝑥𝑗 ) (𝑥𝑖 −𝜇)𝑡 𝑆 −1 (𝑥𝑖 −𝜇) of the proposed modified
2 2 𝐷(𝑥𝑖 )2 = (2.9) slack variables within the
= 𝑒 −𝑥𝑖−𝑥𝑗 /2𝜎 𝑚𝑎𝑥(𝐷(𝑥𝑖 )2 )

(2.6) 0 ≤ 𝐷(𝑥𝑖 )2 ≤ 1 (2.10) SVM to solve complex data

𝑦𝑖 𝑓(𝑥𝑖 ) = 1 − 𝜃𝐷(𝑥𝑖 )2 (2.11) problems including class
1
𝐿𝑝 = 𝑤 2 − ∑ 𝛼𝑖 (𝑦𝑖 𝑓(𝑥𝑖 ) − 1 + 𝜃𝐷(𝑥𝑖 )2 ) (2.12) imbalance and overlapping.
2
𝜕𝐿𝑝
= 𝑤 − ∑𝑛𝑖=1 𝛼𝑖 𝑦𝑖 𝑥𝑖 = 0 (2.13)
𝜕𝑤
𝜕𝐿𝑝
= − ∑𝑛𝑖=1 𝛼𝑖 𝑦𝑖 = 0 (2.14)
𝜕𝑏
𝑤 = ∑𝑛𝑖=1 𝛼𝑖 𝑦𝑖 𝑥𝑖 (2.15)
𝛼𝑖 {𝑦𝑖 𝑓(𝑥𝑖 ) − 1 + 𝜃𝐷(𝑥𝑖 )2 } = 0 (2.16)
𝑤(𝛼, 𝜃) = ∑𝑙𝑖=1 𝛼𝑖 (1 − 𝜃𝐷(𝑥𝑖 )2 ) −
1 𝑙
∑ 𝛼 𝛼 𝑦 𝑦 𝑘(𝑥𝑖 , 𝑥𝑗 ) (2.17)
2 𝑖,𝑗=1 𝑖 𝑗 𝑖 𝑗
𝑀𝑎𝑥 𝑤(𝛼, 𝜃) = ∑𝑙𝑖=1 𝛼𝑖 (1 − 𝜃𝐷(𝑥𝑖 )2 ) −
1 𝑙
∑𝑖,𝑗=1 𝛼𝑖 𝛼𝑗 𝑦𝑖 𝑦𝑗 𝑘(𝑥𝑖 , 𝑥𝑗 ) 𝑠. 𝑡. ∑𝑙𝑖=1 𝛼𝑖 𝑦𝑖 = 0, 𝛼𝑖 ≥ 0 (2.18)
2
𝜕𝑤(𝛼,𝜃) (𝑥𝑖 −𝜇𝑖 )𝑡 𝑆 −1 (𝑥𝑖 −𝜇𝑖 )
= − ∑𝑙𝑖=1 𝛼𝑖 (2.19)
𝜕𝜃 𝑚𝑎𝑥(𝐷(𝑥)2 )
(𝑥 −𝜇 ) 𝑆 𝑡 −1 (𝑥 −𝜇 )
𝜃̂𝑡+1 = 𝜃̂𝑡 + 𝜌 (∑𝑙𝑖=1 𝛼𝑖 𝑖 𝑖 𝑖 𝑖
) , 𝑡 ≥ 0 (2.20)
𝑚𝑎𝑥(𝐷(𝑥)2 )
𝜕𝑤(𝛼,𝜃) 1
= − ( ∑𝑙𝑖,𝑗=1 𝛼𝑖 𝛼𝑗 𝑦𝑖 𝑦𝑗 𝑥𝑖 − 𝑥𝑗2 𝑘(𝑥𝑖 , 𝑥𝑗 )) (2.21)
𝜕𝜎2 2
1
2
𝜎̂𝑡+1 = 𝜎̂𝑡2 + 𝜌 ( ∑𝑙𝑖,𝑗=1 𝛼𝑖 𝛼𝑗 𝑦𝑖 𝑦𝑗 𝑥𝑖 − 𝑥𝑗2 𝑘(𝑥𝑖 , 𝑥𝑗 )) , 𝑡 ≥ 0
2
(2.22)
[76] 2016 RBF ∅: (𝐷𝑠 , 𝐶𝑠 ) → {𝑃, 𝑁} (3) A robust classification
𝑘(𝑋𝑖 , 𝑋𝑗 ) = ∅: 𝑅 𝑁 → 𝑅 𝐹 (4) approach used for feature
‖𝑋𝑖 − 𝑋𝑗 ‖
2
ℒ(𝑤, 𝑏, 𝛼, 𝜉, 𝛾) =
‖𝑤‖2
+ 𝑐 ∑𝑛𝑖=1 𝜉𝑖 − ∑𝑛𝑖=1 𝛼𝑖 |𝑦𝑖 (𝑤𝑥𝑖 + review’s identification and
𝑒𝑥𝑝 { } (9) 2 semantic knowledge on the
2𝜎2 𝑛
𝑏) − 1 + 𝜉𝑖 | − ∑𝑖=1 𝛾𝑖 𝜉𝑖 (5) base of SVM and fuzzy
𝑓(𝑥) = 𝑠𝑖𝑔𝑛{∑𝑛𝑖=1 𝛼𝑖 𝑦𝑖 (𝑥𝑖 × 𝑥) + 𝑏} (6) domain ontology. The
1
max [∑𝑛𝑖=1 𝛼𝑖 − ∑𝑛𝑖=1 𝛼𝑖 𝛼𝑗 𝑦𝑖 𝑦𝑗 𝑘(𝑥𝑖 . 𝑥𝑗 )] (7) proposed approach increases.
2
𝑛
𝑓(𝑥) = 𝑠𝑖𝑔𝑛{∑𝑖=1 𝛼𝑖 𝑦𝑖 (𝑥𝑖 × 𝑥) + 𝑏} (10) where b is the The precision rate of review’s
solution of the equation 𝛼𝑖 [𝑦𝑖 ∑𝑛𝑖=1 𝛼𝑖 𝑦𝑖 𝑘(𝑥𝑖 × 𝑥) + 𝑏 − and opinion word’s extraction
1] = 0 𝑓𝑜𝑟 𝑛𝑜𝑛 − 𝑧𝑒𝑟𝑜 𝛼𝑖 and accuracy.
[77] 2013 Linear function 𝑅𝑡 = +1 𝑖𝑓 𝑥𝑡 ∗ 𝐶1 𝑎𝑛𝑑 Sentiment classification on
𝑅𝑡 = −1 𝑖𝑓 𝑥𝑡 ∗ 𝐶2 online movie reviews through
𝑤𝑡. 𝑥𝑡 + 𝑤0 ≥ +1 𝑖𝑓 𝑥𝑡 ∈ 𝐶1 three approaches and out of
𝑤𝑡. 𝑥𝑡 + 𝑤0 ≥ −1 𝑖𝑓 𝑥𝑡 ∈ 𝐶2 these, SVM performs best in
term of accuracy.
𝑚𝑖𝑛 1
[78] 2014 RBF
𝑤,𝑏,𝜉 2
‖𝑤‖2 + 𝐶 ∑𝑚 𝑇
𝑖=1 𝜉𝑖 𝑠. 𝑡. 𝑦𝑖 . (𝑤 . 𝑥𝑖 + 𝑏) ≥ 1 − 𝜉𝑖 , 𝑖 =
To address feature selection
𝑘(𝑋𝑖 , 𝑋𝑗 ) = 1 … . 𝑚, 𝜉𝑖 ≥ 0, 𝑖 = 1 … 𝑚 (2)
and class imbalance problems
2 and give simultaneous
𝑒𝑥𝑝 {
‖𝑋𝑖 − 𝑋𝑗 ‖
} (5) 𝑓(𝑥) = 𝑠𝑖𝑔𝑛(∑𝑚 ∗ ∗
𝑖=1 𝑦𝑖 𝛼𝑖 𝐾(𝑥, 𝑥𝑖 ) + 𝑏 ) (3)
2𝜎2 1
solutions for both problems.
𝑚𝑎𝑥 𝑚
∑𝑖=1 𝛼𝑖 − ∑𝑚 𝛼 𝛼 𝑦 𝑦 𝐾(𝑥𝑖 , 𝑥𝑠 ) 𝑠. 𝑡. ∑𝑚
𝑖=1 𝛼𝑖 𝑦𝑖 =
𝛼 2 𝑖,𝑠=1 𝑖 𝑠 𝑖 𝑠
0, 0 ≤ 𝛼𝑖 ≤ 𝐶, 𝑖 = 1 … . 𝑚 (4)

Generalization of linear and non-linear support vector machine in multiple fields: … (Sundas Naqeeb Khan)
236  ISSN: 2722-3221

Table 2. Summary of result section with the help of improvements and objectives of the SVM functions
Ref. Year Function Improvement Objective
𝑊 2 (𝛼) = ∑𝑚𝑖,𝑠=1 𝛼𝑖 𝛼𝑠 𝑦𝑖 𝑦𝑠 𝐾(𝑥𝑖 , 𝑥𝑠 ) (7)
[79] 2016 SVM structure 𝑦̂ = 𝑎𝑟𝑔𝑚𝑎𝑥
𝑦∈𝑌
(𝐹(𝑥, 𝑦)) Two hierarchical text
framework categorization approaches are
2
𝑚𝑖𝑛 ‖𝑤‖ used for text documents with
𝑤,𝜉 2
+ 𝐶𝜉 𝑠. 𝑡. ∀(𝑦̅1 , … , 𝑦̅𝑁 ) ∈
𝑁 1 1 byte n-gram-based document
𝑌 : 〈𝑤, ∑𝑁 ̅𝑖 )]〉 ≥ ∑𝑁
𝑖=1[𝛹(𝑥𝑖 , 𝑦𝑖 ) − 𝛹(𝑥𝑖 , 𝑦 ∆(𝑦𝑖 , 𝑦̅𝑖 ) −
𝑁 𝑁 𝑖=1 representation.
𝜉

REFERENCES
[1] T. Joachims, “Training linear SVMs in linear time,” in Proceedings of the 12th ACM SIGKDD international conference on
Knowledge discovery and data mining, Aug. 2006, pp. 217–226, doi: 10.1145/1150402.1150429.
[2] H. Q. Minh, P. Niyogi, and Y. Yao, “Mercer’s theorem, feature maps, and smoothing,” in Lecture Notes in Computer Science(),
Berlin: Springer, 2006, pp. 154–168, doi: 10.1007/11776420_14.
[3] K. Bennett and E. Bredensteiner, “Duality and geometry in SVM classifiers,” in ICML ’00: Proceedings of the Seventeenth
International Conference on Machine Learning, 2000, pp. 57–64.
[4] B. E. Boser, I. M. Guyon, and V. N. Vapnik, “A training algorithm for optimal margin classifiers,” in Proceedings of the fifth
annual workshop on Computational learning theory, Jul. 1992, pp. 144–152, doi: 10.1145/130385.130401.
[5] H. W. Guggenheimer, Applicable geometry: global and local convexity. Huntington: R.E. Krieger Pub. Co., 1977.
[6] J. Moody, “The effective number of parameters: an analysis of generalization and regularization in nonlinear learning systems,” in
Advances in Neural Information Processing Systems, 1991, vol. 4.
[7] C. Cortes and V. Vapnik, “Support-vector networks,” Machine Learning, vol. 20, no. 3, pp. 273–297, Sep. 1995, doi:
10.1007/BF00994018.
[8] C. J. Burges, “A tutorial on support vector machines for pattern recognition,” Data Mining and Knowledge Discovery, vol. 2, pp.
121–167, 1998, doi: 10.1023/A:1009715923555.
[9] A. Beutelspacher and U. Rosenbaum, Projective geometry: from foundations to applications. Cambridge University Press, 1998.
[10] D. Decoste and B. Schölkopf, “Training invariant support vector machines,” Machine Learning, vol. 46, no. 1–3, pp. 161–190,
2002, doi: 10.1023/A:1012454411458.
[11] P. Pavlidis, I. Wapinski, and W. S. Noble, “Support vector machine classification on the web,” Bioinformatics, vol. 20, no. 4, pp.
586–587, Mar. 2004, doi: 10.1093/bioinformatics/btg461.
[12] P. Mitra, B. U. Shankar, and S. K. Pal, “Segmentation of multispectral remote sensing images using active support vector
machines,” Pattern Recognition Letters, vol. 25, no. 9, pp. 1067–1074, Jul. 2004, doi: 10.1016/j.patrec.2004.03.004.
[13] L. Bruzzone, M. Chi, and M. Marconcini, “A novel transductive SVM for semisupervised classification of remote-sensing
images,” IEEE Transactions on Geoscience and Remote Sensing, vol. 44, no. 11, pp. 3363–3373, Nov. 2006, doi:
10.1109/TGRS.2006.877950.
[14] Y. Bazi and F. Melgani, “Semisupervised PSO-SVM regression for biophysical parameter estimation,” IEEE Transactions on
Geoscience and Remote Sensing, vol. 45, no. 6, pp. 1887–1895, Jun. 2007, doi: 10.1109/TGRS.2007.895845.
[15] B. Guo, S. R. Gunn, R. I. Damper, and J. D. B. Nelson, “Customizing kernel functions for SVM-based hyperspectral image
classification,” IEEE Transactions on Image Processing, vol. 17, no. 4, pp. 622–629, Apr. 2008, doi: 10.1109/TIP.2008.918955.
[16] A. Smola and S. Vishwanathan, Introduction to machine learning. Cambridge: Cambridge University Press, 2008.
[17] R. Zhang and J. Ma, “An improved SVM method P‐SVM for classification of remotely sensed data,” International Journal of
Remote Sensing, vol. 29, no. 20, pp. 6029–6036, Oct. 2008, doi: 10.1080/01431160802220151.
[18] F. Bovolo, L. Bruzzone, and M. Marconcini, “A novel approach to unsupervised change detection based on a semisupervised
SVM and a similarity measure,” IEEE Transactions on Geoscience and Remote Sensing, vol. 46, no. 7, pp. 2070–2082, Jul. 2008,
doi: 10.1109/TGRS.2008.916643.
[19] N. Ghoggali and F. Melgani, “Genetic SVM approach to semisupervised multitemporal classification,” IEEE Geoscience and
Remote Sensing Letters, vol. 5, no. 2, pp. 212–216, Apr. 2008, doi: 10.1109/LGRS.2008.915600.
[20] W. Zhang, T. Yoshida, and X. Tang, “Text classification based on multi-word with support vector machine,” Knowledge-Based
Systems, vol. 21, no. 8, pp. 879–886, Dec. 2008, doi: 10.1016/j.knosys.2008.03.044.
[21] A. Shmilovici, “Support vector machines,” in Data Mining and Knowledge Discovery Handbook, Boston, MA: Springer US,
2009, pp. 231–247.
[22] L. Bruzzone and C. Persello, “A novel context-sensitive semisupervised SVM classifier robust to mislabeled training samples,”
IEEE Transactions on Geoscience and Remote Sensing, vol. 47, no. 7, pp. 2142–2154, Jul. 2009, doi:
10.1109/TGRS.2008.2011983.
[23] C. A. C. Coello, G. B. Lamont, and D. A. V. Veldhuizen, Evolutionary algorithms for solving multi-objective problems. Boston,
MA: Springer US, 2007.
[24] U. Maulik and D. Chakraborty, “A self-trained ensemble with semisupervised SVM: An application to pixel classification of
remote sensing imagery,” Pattern Recognition, vol. 44, no. 3, pp. 615–623, Mar. 2011, doi: 10.1016/j.patcog.2010.09.021.
[25] Q. Liu, C. Chen, Y. Zhang, and Z. Hu, “Feature selection for support vector machines with RBF kernel,” Artificial Intelligence
Review, vol. 36, no. 2, pp. 99–115, Aug. 2011, doi: 10.1007/s10462-011-9205-2.
[26] S. Patra and L. Bruzzone, “A cluster-assumption based batch mode active learning technique,” Pattern Recognition Letters, vol.
33, no. 9, pp. 1042–1048, Jul. 2012, doi: 10.1016/j.patrec.2012.01.015.
[27] U. Maulik and D. Chakraborty, “A novel semisupervised SVM for pixel classification of remote sensing imagery,” International
Journal of Machine Learning and Cybernetics, vol. 3, no. 3, pp. 247–258, Sep. 2012, doi: 10.1007/s13042-011-0059-3.
[28] H. Zhang, W. Shi, and K. Liu, “Fuzzy-topology-integrated support vector machine for remotely sensed image classification,”
IEEE Transactions on Geoscience and Remote Sensing, vol. 50, no. 3, pp. 850–862, Mar. 2012, doi:
10.1109/TGRS.2011.2163518.
[29] N. Deng, Y. Tian, and C. Zhang, Support vector machines: optimization based theory, algorithms, and extensions. Chapman and
Hall/CRC, 2012.

Comput Sci Inf Technol, Vol. 4, No. 3, November 2023: 226-239

Comput Sci Inf Technol ISSN: 2722-3221  237

[30] B. Gaonkar and C. Davatzikos, “Analytic estimation of statistical significance maps for support vector machine based multi-
variate image analysis and classification,” NeuroImage, vol. 78, pp. 270–283, Sep. 2013, doi: 10.1016/j.neuroimage.2013.03.066.
[31] R. Parveen, N. Shrivastava, and P. Tripathi, “Sentiment classification of movie reviews by supervised machine learning
approaches using ensemble learning & voted algorithm,” in 2nd International Conference on Data, Engineering and Applications
(IDEA), Feb. 2020, pp. 1–6, doi: 10.1109/IDEA49133.2020.9170684.
[32] Y. Kodratoff, Introduction to machine learning, Elsevier, 1989.
[33] Z. Sun, C. Wang, D. Li, and J. Li, “Semisupervised classification for hyperspectral imagery with transductive multiple-kernel
learning,” IEEE Geoscience and Remote Sensing Letters, vol. 11, no. 11, pp. 1991–1995, Nov. 2014, doi:
10.1109/LGRS.2014.2316141.
[34] S. Maldonado, R. Weber, and F. Famili, “Feature selection for high-dimensional class-imbalanced data sets using support vector
machines,” Information Sciences, vol. 286, pp. 228–246, Dec. 2014, doi: 10.1016/j.ins.2014.07.015.
[35] T. Hastie, R. Tibshirani, and M. Wainwright, Statistical learning with sparsity, Chapman and Hall/CRC, 2015.
[36] L. Barghout, “Spatial-taxon information granules as used in iterative fuzzy-decision-making for image segmentation,” in
Granular Computing and Decision-Making. Studies in Big Data, 2015, pp. 285–318.
[37] C. D. A. Vanitha, D. Devaraj, and M. Venkatesulu, “Gene expression data classification using support vector machine and mutual
information-based gene selection,” Procedia Computer Science, vol. 47, pp. 13–21, 2015, doi: 10.1016/j.procs.2015.03.178.
[38] M. H. Bhavsar and D. A. Ganatra, “Support vector machine classification using mahalanobis distance function,” International
Journal of Scientific and Engineering Research, vol. 6, no. 1, pp. 618–626, Jan. 2015, doi: 10.14299/ijser.2015.01.015.
[39] S. Peng, Q. Hu, Y. Chen, and J. Dang, “Improved support vector machine algorithm for heterogeneous data,” Pattern
Recognition, vol. 48, no. 6, pp. 2072–2083, Jun. 2015, doi: 10.1016/j.patcog.2014.12.015.
[40] F. Ali, K.-S. Kwak, and Y.-G. Kim, “Opinion mining based on fuzzy domain ontology and support vector machine: a proposal to
automate online review classification,” Applied Soft Computing, vol. 47, pp. 235–250, Oct. 2016, doi:
10.1016/j.asoc.2016.06.003.
[41] Z. Yin and J. Hou, “Recent advances on SVM based fault diagnosis and process monitoring in complicated industrial processes,”
Neurocomputing, vol. 174, pp. 643–650, Jan. 2016, doi: 10.1016/j.neucom.2015.09.081.
[42] L. Demidova, E. Nikulchev, and Y. Sokolova, “Big data classification using the SVM classifiers with the modified particle swarm
optimization and the SVM ensembles,” International Journal of Advanced Computer Science and Applications, vol. 7, no. 5,
2016, doi: 10.14569/IJACSA.2016.070541.
[43] A. Tripathy, A. Agrawal, and S. K. Rath, “Classification of sentiment reviews using N-gram machine learning approach,” Expert
Systems with Applications, vol. 57, pp. 117–126, Sep. 2016, doi: 10.1016/j.eswa.2016.03.028.
[44] Y.-C. Chen and C.-T. Su, “Distance-based margin support vector machine for classification,” Applied Mathematics and
Computation, vol. 283, pp. 141–152, Jun. 2016, doi: 10.1016/j.amc.2016.02.024.
[45] J. Graovac, J. Kovacevic, and G. Pavlovic-Lazetic, “Hierarchical vs. flat N-gram-based text categorization: can we do better?,”
Computer Science and Information Systems, vol. 14, no. 1, pp. 103–121, 2017, doi: 10.2298/CSIS151017030G.
[46] T. Alam, R. Gupta, S. Qamar, and A. Ullah, “Recent applications of artificial intelligence for sustainable development in smart
cities,” in Recent Innovations in Artificial Intelligence and Smart Applications. Studies in Computational Intelligence, Cham:
Springer, 2022, pp. 135–154, doi: 10.1007/978-3-031-14748-7_8.
[47] K. Korovkinas and P. Danėnas, “SVM and Naïve Bayes classification ensemble method for sentiment analysis,” Baltic Journal of
Modern Computing, vol. 5, no. 4, Dec. 2017, doi: 10.22364/bjmc.2017.5.4.06.
[48] F. S. Al-Anzi and D. AbuZeina, “Toward an enhanced Arabic text classification using cosine similarity and latent semantic
indexing,” Journal of King Saud University - Computer and Information Sciences, vol. 29, no. 2, pp. 189–195, Apr. 2017, doi:
10.1016/j.jksuci.2016.04.001.
[49] U. Maulik and D. Chakraborty, “Remote sensing image classification: a survey of support-vector-machine-based advanced
techniques,” IEEE Geoscience and Remote Sensing Magazine, vol. 5, no. 1, pp. 33–52, Mar. 2017, doi:
10.1109/MGRS.2016.2641240.
[50] A. V. Phan, M. Le Nguyen, and L. T. Bui, “Feature weighting and SVM parameters optimization based on genetic algorithms for
classification problems,” Applied Intelligence, vol. 46, no. 2, pp. 455–469, Mar. 2017, doi: 10.1007/s10489-016-0843-6.
[51] A. H. Haghiabi, H. M. Azamathulla, and A. Parsaie, “Prediction of head loss on cascade weir using ANN and SVM,” ISH Journal
of Hydraulic Engineering, vol. 23, no. 1, pp. 102–110, Jan. 2017, doi: 10.1080/09715010.2016.1241724.
[52] M. A. Beer, “Predicting enhancer activity and variant impact using gkm‐SVM,” Human Mutation, vol. 38, no. 9, pp. 1251–1258,
Sep. 2017, doi: 10.1002/humu.23185.
[53] X. Niu, C. Yang, H. Wang, and Y. Wang, “Investigation of ANN and SVM based on limited samples for performance and
emissions prediction of a CRDI-assisted marine diesel engine,” Applied Thermal Engineering, vol. 111, pp. 1353–1364, Jan.
2017, doi: 10.1016/j.applthermaleng.2016.10.042.
[54] P. Kumar and A. Tiwari, Eds., Ubiquitous machine learning and its applications, IGI Global, 2017.
[55] Y. Al Amrani, M. Lazaar, and K. E. El Kadiri, “Random forest and support vector machine based hybrid approach to sentiment
analysis,” Procedia Computer Science, vol. 127, pp. 511–520, 2018, doi: 10.1016/j.procs.2018.01.150.
[56] S. Xie, Z. Li, and H. Hu, “Protein secondary structure prediction based on the fuzzy support vector machine with the hyperplane
optimization,” Gene, vol. 642, pp. 74–83, Feb. 2018, doi: 10.1016/j.gene.2017.11.005.
[57] D. Sebai and A. U. Shah, “Semantic-oriented learning-based image compression by only-train-once quantized autoencoders,”
Signal, Image and Video Processing, vol. 17, no. 1, pp. 285–293, Feb. 2023, doi: 10.1007/s11760-022-02231-1.
[58] A. Ullah, A. Salam, H. El Raoui, D. Sebai, and M. Rafie, “Towards more accurate iris recognition system by using hybrid
approach for feature extraction along with classifier,” International Journal of Reconfigurable and Embedded Systems (IJRES),
vol. 11, no. 1, pp. 59–70, Mar. 2022, doi: 10.11591/ijres.v11.i1.pp59-70.
[59] A. Ullah and A. Chakir, “Improvement for tasks allocation system in VM for cloud datacenter using modified bat algorithm,”
Multimedia Tools and Applications, vol. 81, no. 20, pp. 29443–29457, Aug. 2022, doi: 10.1007/s11042-022-12904-1.
[60] I. Guyon, V. Vapnik, B. Boser, L. Bottou, and S. A. Solla, “Structural risk minimization for character recognition,” in Advances
in Neural Information Processing Systems, 1991, vol. 4.
[61] D. Ciucci et al., Eds., Information Processing and Management of Uncertainty in Knowledge-Based Systems, vol. 1601. Cham:
Springer International Publishing, 2022, doi: 10.1007/978-3-031-08971-8.
[62] R. Cuingnet et al., “Spatial regularization of SVM for the detection of diffusion alterations associated with stroke outcome,”
Medical Image Analysis, vol. 15, no. 5, pp. 729–737, Oct. 2011, doi: 10.1016/j.media.2011.05.007.
[63] S. N. Khan et al., “Comparative analysis for heart disease prediction,” JOIV : International Journal on Informatics Visualization,
vol. 1, no. 4–2, p. 227, Nov. 2017, doi: 10.30630/joiv.1.4-2.66.
[64] M. A. Hearst, S. T. Dumais, E. Osuna, J. Platt, and B. Scholkopf, “Support vector machines,” IEEE Intelligent Systems and their
Generalization of linear and non-linear support vector machine in multiple fields: … (Sundas Naqeeb Khan)
238  ISSN: 2722-3221

Applications, vol. 13, no. 4, pp. 18–28, Jul. 1998, doi: 10.1109/5254.708428.
[65] E. Pasolli, F. Melgani, D. Tuia, F. Pacifici, and W. J. Emery, “SVM active learning approach for image classification using spatial
information,” IEEE Transactions on Geoscience and Remote Sensing, vol. 52, no. 4, pp. 2217–2233, Apr. 2014, doi:
10.1109/TGRS.2013.2258676.
[66] U. Ullah and A. Ullah, “An evolutionary algorithm for the solution of multi-objective optimization problem,” International
Journal of Advances in Applied Sciences, vol. 11, no. 4, pp. 287–295, Dec. 2022, doi: 10.11591/ijaas.v11.i4.pp287-295.
[67] S. N. Khan, N. M. Nawi, M. Imrona, A. Shahzad, A. Ullah, and A.- Rahman, “Opinion mining summarization and automation
process: a survey,” International Journal on Advanced Science, Engineering and Information Technology, vol. 8, no. 5, p. 1836,
Oct. 2018, doi: 10.18517/ijaseit.8.5.5002.
[68] A. Hanane, A. Ullah, and S. Raghay, “Enhanced GAF protocol based on graph theory to optimize energy efficiency and lifetime
in WSN technology,” International Journal of Intelligent Unmanned Systems, vol. 11, no. 2, pp. 214–225, Apr. 2023, doi:
10.1108/IJIUS-08-2021-0096.
[69] A. Ullah, I. Laassar, C. B. Şahin, O. B. Dinle, and H. Aznaoui, “Cloud and internet-of-things secure integration along with
security concerns,” International Journal of Informatics and Communication Technology (IJ-ICT), vol. 12, no. 1, pp. 62–71, Apr.
2023, doi: 10.11591/ijict.v12i1.pp62-71.
[70] B. Saeeda, T. Noor, A. Ullah, and H. Aznaoui, “A critical study of the teaching attitudes of teachers at primary school level in
Pakistan,” International Journal of Knowledge and Learning, vol. 14, no. 4, p. 385, 2021, doi: 10.1504/IJKL.2021.118556.
[71] A. Ullah, S. Baseer, and S. Umar, “Role of cooperation in energy minimization in visual sensor network,” in 2016 Sixth
International Conference on Innovative Computing Technology (INTECH), Aug. 2016, pp. 447–452, doi:
10.1109/INTECH.2016.7845026.
[72] A. Ullah, N. M. Nawi, A. Arifianto, I. Ahmed, M. Aamir, and S. N. Khan, “Real-time wheat classification system for selective
herbicides using broad wheat estimation in deep neural network,” International Journal on Advanced Science, Engineering and
Information Technology, vol. 9, no. 1, p. 153, Jan. 2019, doi: 10.18517/ijaseit.9.1.5031.
[73] N. Tenali and G. R. M. Babu, “A systematic literature review and future perspectives for handling big data analytics in COVID-
19 diagnosis,” New Generation Computing, vol. 41, no. 2, pp. 243–280, Jun. 2023, doi: 10.1007/s00354-023-00211-8.
[74] Q. I. Ahmed, H. Attar, A. Amer, M. A. Deif, and A. A. A. Solyman, “Development of a hybrid support vector machine with grey
wolf optimization algorithm for detection of the solar power plants anomalies,” Systems, vol. 11, no. 5, p. 237, May 2023, doi:
10.3390/systems11050237.
[75] T. Saida and M. Nishio, “Transfer learning Gaussian process regression surrogate model with explainability for structural
reliability analysis under variation in uncertainties,” Computers & Structures, vol. 281, p. 107014, Jun. 2023, doi:
10.1016/j.compstruc.2023.107014.
[76] J. Niyogisubizo et al., “Predicting traffic crash severity using hybrid of balanced bagging classification and light gradient boosting
machine,” Intelligent Data Analysis, vol. 27, no. 1, pp. 79–101, Jan. 2023, doi: 10.3233/IDA-216398.
[77] S. A. and S. R., “A systematic review of explainable artificial intelligence models and applications: recent developments and
future trends,” Decision Analytics Journal, vol. 7, p. 100230, Jun. 2023, doi: 10.1016/j.dajour.2023.100230.
[78] A. H. Elsheikh, “Applications of machine learning in friction stir welding: prediction of joint properties, real-time control and tool
failure diagnosis,” Engineering Applications of Artificial Intelligence, vol. 121, p. 105961, May 2023, doi:
10.1016/j.engappai.2023.105961.
[79] A. Ullah, S. N. Khan, and N. M. Nawi, “Review on sentiment analysis for text classification techniques from 2010 to 2021,”
Multimedia Tools and Applications, vol. 82, no. 6, pp. 8137–8193, Mar. 2023, doi: 10.1007/s11042-022-14112-3.

BIOGRAPHIES OF AUTHORS

Sundas Naqeeb Khan is a researcher and she has worked as a lecturer,

instructor, and adjunct professor with companies, academies, and universities. She has
reviewed six double-blind peer reviews. She has worked as an invited researcher with national
and international universities. Her broad research interests cover topics relating to electrical
and electronics, computer and software engineering, optimization, data science,
communication, and physics. She can be contacted at email: [email protected].

Samra Urooj Khan is working as a lecturer in Department of Electrical

Engineering Technology, Punjab University of Technology, Rasul, Mandi Bahauddin, Punjab,
Pakistan. Her academic qualification is M.S. in Electrical Engineering from UTHM, B.S.
from Pakistan. Her research area includes wireless communications, image processing, and
signal processing. She can be contacted at email: [email protected].

Comput Sci Inf Technol, Vol. 4, No. 3, November 2023: 226-239

Comput Sci Inf Technol ISSN: 2722-3221  239

Hanane Aznaoui works at Faculty of Computer Science, Cadi Ayyad

University, Morocco. Her main research interests focus on bio-inspired computing, artificial
intelligence, metaheuristic modeling and optimization, evolutionary computations,
optimization algorithms, information retrieval, feature selection, combinatorial problems, data
mining, and text mining. She can be contacted at email: [email protected].

Canan Batur Şahin works at as assistant professor at Faculty of Computer

Science, Turgut Özal University Turkey. Her research interests include software engineering,
artificial intelligence, and optimization. She can be contacted at email:
[email protected].

Özlem Batur Dinler works as assistant professor at Faculty of Computer

Science, Siirt Üniversitesi Turkey. Her research interests include artificial intelligent, machine
learning, and deep learning and software engineering. She can be contacted at email:
[email protected].

Generalization of linear and non-linear support vector machine in multiple fields: … (Sundas Naqeeb Khan)