ArticlePDF Available

Abstract and Figures

Information security and confidentiality are the prime concern of any type of communication. The techniques that utilizing inconspicuous digital media such as text, audio, video and image for hiding confidential data in it are collectively called Steganography. The key challenge of steganographic system design is to maintain a fair trade-off between, security, robustness, higher bit embedding rate and imperceptibility. Thus, with the massive progress in digital technology, to transmit secret messages through the internet effective steganography algorithms are required. However, the object which has been used to hide secret messages within may be exposed by compression or any type of noise which leads to extract secret message incorrectly. Therefore, utilizing the non-traditional basics for information security is required, such as swarm intelligence algorithms which are focused as a new aspect to achieve better security. In this paper, a survey of recent swarm intelligence algorithms based on steganography is covered. The objective function for swarm intelligence algorithms is realized in a way that the quality and robustness of the object that has been used for hiding messages are acceptable. With a particular emphasis on the main purpose and the objective of the proposed method based on the particular swarm intelligence algorithm has been reviewed. To present a more secure, efficient steganography algorithm based on swarm intelligence algorithms for future work, this will be helpful.
Content may be subject to copyright.
May-June 2020
ISSN: 0193-4120 Page No. 2225722269
22257
Published by: The Mattingley Publishing Co., Inc.
Image Steganography Based on Swarm Intelligence
Algorithms: A Survey
Dilovan Asaad Zebari1, Diyar Qader Zeebaree2, Jwan Najeeb Saeed3,Nechirvan Asaad Zebari4,
Adel AL-Zebari5
1,2Research Center of Duhok Polytechnic University, Duhok, Kurdistan Region, Iraq
3IT Department, Duhok Technical Institute, Duhok Polytechnic University, Duhok, Kurdistan Region, Iraq
4Electrical & Electronic Engineering Duhok Polytechnic University, Duhok, Kurdistan
Department of Computer Engineering, Harran University, Sanliurfa, Turkey
5Dept. of Information Technology, Technical College of Informatics, Duhok Polytechnic University, Kurdistan
Region, Iraq.
Article Info
Volume 83
Page Number: 22257 22269
Publication Issue:
May-June 2020
Article History
Article Received: 11 May 2020
Revised: 19 May 2020
Accepted: 29 May 2020
Publication: 12 June 2020
Abstract
Information security and confidentiality are the prime concern of any type of
communication. The techniques that utilizing inconspicuous digital media such as
text, audio, video and image for hiding confidential data in it are collectively
called Steganography. The key challenge of steganographic system design is to
maintain a fair trade-off between, security, robustness, higher bit embedding rate
and imperceptibility. Thus, with the massive progress in digital technology, to
transmit secret messages through the internet effective steganography algorithms
are required. However, the object which has been used to hide secret messages
within may be exposed by compression or any type of noise which leads to extract
secret message incorrectly. Therefore, utilizing the non-traditional basics for
information security is required, such as swarm intelligence algorithms which are
focused as a new aspect to achieve better security. In this paper, a survey of recent
swarm intelligence algorithms based on steganography is covered. The objective
function for swarm intelligence algorithms is realized in a way that the quality and
robustness of the object that has been used for hiding messages are acceptable.
With a particular emphasis on the main purpose and the objective of the proposed
method based on the particular swarm intelligence algorithm has been reviewed.
To present a more secure, efficient steganography algorithm based on swarm
intelligence algorithms for future work, this will be helpful.
Keywords: Data security, Image Steganography, Swarm Intelligence Algorithms.
I. Introduction
Information security was among the most central
issues that attracted much consideration as it
played a significant role in every-day life. This
concern has grown considerably following the
advent of computers, particularly when the
computer was adopted in nearly all spheres of
modern life. Computer security is a broad label
for the array of methods, measures, and devices
proposed to shield, secure and safeguard computer
systems alongside their information and data from
hackers by discouraging them from attempting to
access such systems without authorization [1, 2].
Essentially, information security classified into
May-June 2020
ISSN: 0193-4120 Page No. 2225722269
22258
Published by: The Mattingley Publishing Co., Inc.
two main parts cryptography and information
hiding. Information hiding is considered a key
discipline of information security. Information
hiding is a science used for secret communication
among the source and the destination to protect
secret data from a third party [3, 2].
Essentially, cryptography and steganography
technologies are used to provide secret
communication. However, steganography and
cryptography differ considerably, Figure 1 showes
the classification of the information security
types. Both, of them technologies are utilized to
achieve the different target. Cryptography is made
up of two Greek words “kryptos” is meaning
(hidden) and “graphein” is meaning (to write) [4,
2].The main goal of cryptography is to protect the
secret message from unauthorized users by
changing the real meaning of it into the
unintelligible format without using any carrier
which is called cipher message. In cryptography,
the system will be break if the intruder can find
the real meaning of the secret message which is
called cryptanalysis. Therefore, the cryptosystem
makes doubt in the mind of attackers because the
cipher message is still known even after the
encryption process. In contrast, steganography has
been used to avoid the attacker's doubt [5, 6, 7,
8,9].
Fig 1: Classification of Information Security Types
The steganography notion is usually constructed
by a pair of algorithms which are hiding and
extracting secret message as shown in Figure 2.
Steganography is one of the main areas of
information hiding technologies. t is composed of
two Greek words “steganos” which is means
covered or secret, and “graphy” which is means
writing. The main goal of steganography is to
conceal the private or sensitive information within
different carries. In steganography, the secret
message must be converted into a binary system
to embed it. Therefore, the breaking
steganography system (steganalysis), will be done
if the intruder detects the hidden message. Aa a
result, steganography is considered as a higher
security level than cryptography in terms of the
braking system because the presence of secret
messages cannot be known by unauthorized
people [7, 8, 9].
Fig 2: General Process of Steganography [12]
Throughout history, steganography has been
utilized in ancient Greece and China in different
forms [13]. During 440 B.C., an ancient common
method of Greek had been demonstrated by
Histaeus for hiding message. He used the head of
trusted slaves to conceal the secret message. The
secret information has been tattooed on the slave's
scalp after shaving his hair. After growing slave's
hair again, he was sent with the secret message to
the destination place. The message cannot be
detecting until the hair shaved again. Also, around
480 B.C., Demerstus used a wooden wax tablet to
hide the message. In the process of his technique
the secret message was written on the wood after
taking off the wax and then covered the wood
again with fresh wax [11, 12]. The stomach of
Information
security
Steganography
Watermarking
Reversible
steganography
Pure steganography
Public key
steganography
May-June 2020
ISSN: 0193-4120 Page No. 2225722269
22259
Published by: The Mattingley Publishing Co., Inc.
rabbits is utilized for a hidden message, too [16].
Moreover, Jérôme Cardan invented another
method to conceal the information. In his method,
a masking paper that contains holes and blank
paper was used as it is shown in Figure 2.2, mask
located on the left side, cover located in the
middle, and message located on the left side. In
the process of hidden message, the mask was put
on the blank paper and the message was written
through the holes. After that, they were taking the
mask and filled the blanks to appear the secret
message [14, 15].
II. Steganography Types
In general, the steganography systems are divided
into three main categories based on the
steganography methods. The main goal of them is
to embed secret information within any carrier in
different ways. Using each type with any method
a stego carrier will be obtained but in the different
levels of security. As it is illustrated in Figure 1
there are three types of steganography are pure
steganography, secret key steganography, and
public key steganography.
A. Pure Steganography
Pure steganography is considered as one of the
steganography systems. After combining specific
carriers with a secret message by using any
steganography technique the stego carrier will be
obtained. Therefore, the process of this type does
not require any secret key during the embedding
process. Consequently, this type is considered as a
mush less secure method because no key is
involved. Thus, the security in this type is based
on the privacy of the algorithm[16, 17].
B. Secret Key Steganography
Secret key steganography is considered an
important type for protecting secret data from a
third party. Unlike the previous type, the system
of steganography in this type requiresa single
secret key, this same key is also called a private or
symmetric key. Therefore, the sender and receiver
use the same key during carried out of both hiding
and extraction. The main purpose of utilizing the
key is to make the system more secure because of
no one able to extract the secret message and read
it only the one who has the key[21]. One of the
great advantages of the private key is providing a
fast process in both procedures. On the other
hand, the drawback of this key is the system will
become in risk if the key discovered by
unauthorized users. Thus, this type of key should
be changed considerably to keep the system
securely [22]. The private key was the first type of
key used in encryption before developing the
public key in 1970 [23].
C. Public Key Steganography
Public key steganography is also known as an
asymmetric key. Unlike the previous type of
steganography, in this type pair of keys are used
one for embedding and another for extraction to
provide multiple levels of security during public
communication. The key which is utilized by the
transmitter to conceal the secret information
within the carrier is called the public key.
However, the other key utilized by the receiver
during extracting the secret message is labeled as
a private key. Both of keys are mathematically
related to each other because they are generated
together. The main advantage of this type of
steganography is providing more robust for the
system because even one key is known, it is hard
to find the other key by a third party [17, 21]. On
the other hand, the main problem of
theasymmetric key is slower than the private key
about 100-1000 times. Also, the public key
systems exposed to more efficient attacks due to
the publishing of the key [19, 22].
III. Steganography Applications
Several applications represent a container of
sensitive information. These applications are used
May-June 2020
ISSN: 0193-4120 Page No. 2225722269
22260
Published by: The Mattingley Publishing Co., Inc.
as cover objects or carriers in the steganography
systems as it is shown in Figure 3. Every carrier
has it is own characteristics to serve the
steganography technology. Also, steganography
technology needs a sufficient region in each
carrier to protect the secret data. Also, the amount
of secret information to conceal within each
carrier depends on the availability of the region of
the specific carrier. Therefore, carriers are
represented as an essential ingredient in
steganography technology because they are
determining the amount of data that can be
hidden. Furthermore, to conceal the secret data
within each carrier some parts of them will be
manipulated by using different algorithms.
However, maintain the accuracy and stay the
format intact of each carrier after the embedding
process or maybe modifying some parts of them
to stay imperceptible to unauthorized people in
public communication.
A. Text steganography
Historically, the text was an obvious carrier used
to protect secret data from unauthorized people.
Utilizing text as a carrier was the most important
steganography method. In this method, each bit of
secret data was concealed in every nth letter of
text carrier. After increasing the using of the
internet and discovering some other carriers, the
significance of using text as a carrier among
researchers is decreased because of a very small
amount of redundant data compared with other
carriers. However, stego text which obtaining
after embedding secret data is often more
imperceptible than other digital carriers [20, 26].
The main benefit of using text as a carrier in
steganography system is that, it does not require
much memory also it is easy to transfer [23, 24].
Several algorithms have been used to embed the
secret message within the text such as open space
methods [5], syntactic methods, semantic methods
[29], shift coding [30], and feature coding [27,
28].
B. Video steganography
Videos also as images are very common choice
were used to hide secret information as a carrier.
Steganography video is very effective and
successful due it is a high capacity more than
image capacity. Many different video file formats
can be used in the domain of steganography
videos such as Moving Picture Experts Group
(MPEG), MP4, and Audio Video Interleave (AVI)
[29, 30, 32]. Generally, steganography in the
video is classified into two main types which are
uncompressed and compressed video. Essentially,
hiding information in the video is similar to
hiding information in an image where the data
will be hidden within different frames of video
(Chandel, 2016). Consequently, techniques of
steganography in an image can also be applied on
video [29, 31, 32, 33]. Especially, Discrete Cosine
Transform (DCT) is the most common technique
has been used in video steganography to achieve
high security and high visual quality [39].
C. Audio steganography
In the field of information hiding, audio files have
been utilized as a carrier for embedding secret
data in digital sound. The process of
steganography in audio will be done by changing
the binary sequence of a sound file slightly.
Hiding data in audio is usually harder than
concealing data in other carriers. Different audio
files have been used for protecting secret
information such as WAV, AU, and even MP3
[16][10,26]. Several algorithms have been
presented to embed secret information within
audio files successfully. List Significant Bit (LSB)
coding, Parity coding, Phase coding, Spread
Spectrum, and Echo coding are the most common
methods were used to hide data in audio files [35,
36, 37, 38, 39].
D. Image steganography
Over the past few years, digital images became
popular carriers for hiding secret information to
May-June 2020
ISSN: 0193-4120 Page No. 2225722269
22261
Published by: The Mattingley Publishing Co., Inc.
prevent from unauthorized users. Since the 1990s,
we have seen a remarkable development in digital
image processing. Due to high capacity in images,
a low impact on the visibility, and the simplicity
of their manipulation have attracted many
researchers to work in the field of information
hiding for digital images. Many different image
formats can be used in the domain of image
steganography such as Graphics Interchange
Format (GIF), Windows Bitmap (BMP), Joint
Photographic Expert Group (JPEG), and so on
[29, 40]. Based on the spatial domain and
transform domain several steganography
techniques have been used for embedding secret
data within the digital images efficiently.
Recently, in the spatial domain immense schemes
based on LSB technique [41, 24], Optimal Pixel
Adjustment (OPA) technique [46,47], and Pixel
Value Differencing (PVD) [49] have been
proposed. Moreover, in the transform domain
several methods based on the Discrete Cosine
Transform (DCT) technique [50, 51] and Discrete
Wavelet Transform (DWT) technique [52] have
been presented. Furthermore, to increase the
security level some researchers proposed a hybrid
scheme by combining both spatial and transform
domains [46, 47, 52].
Fig 3: Bock Diagram of Steganography Application
Iv. Swarm Intelligence Algorithms in
Steganography
Swarm intelligence (SI) is a relatively novel line
of research Artificial Intelligence (AI)[48, 50,54].
Natural biological simulations motivated (SI)
through a set of locally naïve interrelated vehicles
that react with the surrounding setting [59]. In the
last period, a few SI algorithms, like PSO, FA,
and ABC made various significant applications to
the domain of steganography[51, 52], the
mechanism of hiding secret message based on
swarm intelligence algorithms has been illustrated
in Figure 4. To preserve the quality of the image
many techniques have been used with
steganography in image. After that, metaheuristic
algorithms named swarm intelligence algorithms
have been used with images to find the best
location where the secret message can be
embedded as well as payload capacity.
Fig4: Steganography Mechanism Using Swarm
Algorithms
A. Ant Colony Optimization (ACO)
Ant Colony Optimization (ACO) [62] algorithm
patterns the conduct of ants scrounging. It is
valuable for issues that need figuring out the most
express route as an objective. Practically, when
ants discover their surrounding area, it leaves the
pheromones to guide each other toward nutrients.
ACO likewise recreates this strategy and every ant
saves correspondingly its location to make more
ants pinpoint better arrangements in future cycles.
This pattern proceeds until the optimal route is
established. Ants to construct their trip, their
behavior is going via the vertices in the graph.
Assume that the nest will be left by ants to find
food. There are four various paths to four various
Secret data
Embedding
process
Cover text
Cover image
Cover audio
Cover video
Stego text
Stego image
Stego audio
Stego video
Steganography
key
Extracting
process
Secret data
Cover text
Cover image
Cover audio
Cover video
May-June 2020
ISSN: 0193-4120 Page No. 2225722269
22262
Published by: The Mattingley Publishing Co., Inc.
vertices v00v10v20 and v30, as shown in
Figure 5.
Fig 5: The Behavious of Ant Colony
B. Firefly Algorithm (FA)
Figure 6 illustrates Firefly Algorithm (FA) was
promoted by Xin-She Yang in 2008, which
depended on the glimmering examples and
conduct of tropical fireflies. FA is
straightforward, adaptable, and undemanding to
actualize [63]. It may be utilized for limited
optimization works. The glimmering conduct of
fireflies occurs as a result of the bioluminescence
process. Fireflies are capable of controlling their
glimmering conduct relying on an exterior
incentive. This process is utilized to draw in other
members of their species or prey. In a Firefly
algorithm, a population of fireflies is counted. The
power of light that they emanate determines the
attraction between fireflies. The flying insects
with the greatest glow may attract more fireflies.
The solution space is drawn on to these insects
and the nature of the arrangement of every firefly
is straightforwardly relative to its lighting level.
Hence, fireflies that have better arrangements pull
in its cohorts (paying little attention to their sex),
this means that exploring the hunt space will be
more well-organized[64].
Fig 6: The General Concept of Firefly Algorithm
C. Artificial Bee Colony (ABC)
The Artificial Bee Colony (ABC) algorithm is one
more population-dependent offered by [65]. This
algorithm emulates the smart conduct of
honeybees and harnesses triple stages to locate the
best arrangement: working honeybee, passerby
honeybee, and scout honeybee stages. Working
and passerby honeybees possess local seeking
everywhere in the area and pick nutrient-based on
the deterministic and probabilistic determination
in their stages correspondingly. They pick
nutrients in light of their knowledge and their
home mates and adjust their locations. In the
Scout stage, scout honeybees fly and pick the
nutrients arbitrarily without resorting to prior
experience. If the quantity of nectar in a new
source is greater than that of the past one that is
saved in their memory, they keep the new location
and disremember the earlier one. In this way,
May-June 2020
ISSN: 0193-4120 Page No. 2225722269
22263
Published by: The Mattingley Publishing Co., Inc.
ABC offsets exploration and exploitation process
with local and universal exploration techniques on
working, passerby, and scout's stages and gets the
best arrangement. Figure 7 ABC algorithm has an
asset in local and universal quests. Additionally, it
is actualized in a few optimization issues.
Fig 7: The Behaviors of Artificial Bee Colony
D. Particle Swarm Optimization (PSO)
Particle Swarm Optimization (PSO) is a fruitful
swarm intelligence strategy that relies on the
capacity of assemblies. It turned out to be
extremely famous nowadays as an effective
search and optimization method. This procedure
can be implemented where a question is raised,
and its answer can be acquired from multiple
means. PSO does not need any gradient
knowledge about the function that will undergo
optimization, and it utilizes just primitive
numerical operators and its conception is
extremely straightforward [57, 58, 59] PSO was
presented by Russell Eberhart, an electrician, and
James Kennedy, a social analyst, in 1995 [60,
61]. It is motivated by the smart, encounter
sharing, social-assembling conduct of birds, and it
was initially replicated on a PC by Craig
Reynolds, and further examined by Frank
Heppner [62, 63]. Figure 8 shows PSO has drawn
the consideration of a great deal of scholars
throughout the world coming which resulted the
introduction of countless fundamental versions of
the algorithm and also numerous parameter
computerization techniques [59,77, 65].
Fig 8: The process of PSO Algorithm
Table I briefly reviews the swarm
intelligence algorithms used with steganography
in the image. In this table, the purpose of using
existing algorithm as well as the objective of
applying swarm algorithm in this domain.To
preserve the quality of the image many techniques
have been used with steganography in image.
After that, metaheuristic algorithms named swarm
intelligence algorithms have been used with
images to find the best location where a secret
message can be embedded as well as payload
capacity. Table I briefly reviews the swarm
intelligence algorithms used with steganography
in the image. In this table, the purpose of using
existing algorithm as well as the objective of
applying swarm algorithm in this domain.
May-June 2020
ISSN: 0193-4120 Page No. 2225722269
22264
Published by: The Mattingley Publishing Co., Inc.
Table I: Swarm Intelligence Algorithms with Steganography in Image
feR
mhtiroglA
rof desU
evitcejbO
[74]
PSO
For converting secret data, the best substitution
matrix has been found
To ameliorate the quality of stego carrier
[75]
PSO
For any 8*8 block of the carrier the best
substitution matrix has been found rather than
only one matrix for the entire carrier then the
convert the secret data by these matrices
In order to increase the security, preserve
quality, and more embedding capacity
[76]
ACO
Helped to build the best LSB substitution
matrix to obtain the new secret message
In order to preserve the quality and to
obtain more effectiveness
[77]
PSO
Used in three schemes to obtain the best
conversion matrix T
First scheme to increase the security while
other schemes to ameliorate the quality of
stego
[20]
PSO
Producing the secret key also to select the best
pixel in cover image
Ameliorated the performance of LSB and
to reach the better quality.
[77]
PSO
The best pixel positions selected to embed the
pixels of secret image
To preserve the quality of stego image as
well as the robustness
[78]
PSO
To choose the global best location for
concealing data
In order to increase the hiding capacity
where more data can be hidden
[79]
PSO
andACO
To obtain the optimized edged cover and the
optimum pixels of image are selected for
embedding
In order to preserve the quality and better
security of stego image
[80]
PSO
To select the best LSBs of carrier to embed the
Most Significant Bit (MSB) of secret data as
well as to find a key
In order to enhance the performance of
concealing
[81]
Firefly
To select the optimum position
In order to preserve the quality of image
[82]
PSO
Used to conceal data within an image based on
DWT
In order to obtain the highest PSNR and
better payload capacity
[83]
PSO
Analyzing the hiding process to select the
position of pixels for embedding the data
In order to enhance the capacity and the
performance
[84]
ACO
The best set of pixel bits in carrier has been
found to substitute with the secret data bits
In order to present an efficient
steganography method and comparison
among Genetic Algorithm (GA) and ACO
[85]
ABC
The best solution has been calculated in order
to conceal the secret data within it
To increase hiding capacity and to
preserve the quality
[68]
PSO
Used to embed the message within Integer
Wavelet Transform (IWT) coefficients of the
carrier and to generate a key
To obtain more security, robustness, and
the quality of stego carrier
V. CONCLUSION
In steganography technologies, the bits of the secret
message should be encoded effectively, and the quality
of the image should be preserved efficiently. Many
researchers worked to hide secret messages in an
image based on different technologies. Several
approaches have been proposed and used to hide secret
messages in an image. Thus, a review of several image
steganography based on swarm intelligence algorithms
has been presented in this paper. The main purpose of
this paper is to show the importance of using swarm
intelligence algorithms in image steganography. The
swarm intelligence algorithm which has been used in
the proposed work has been indicated. More so, the
issue of the swarm intelligence algorithm used in
May-June 2020
ISSN: 0193-4120 Page No. 2225722269
22265
Published by: The Mattingley Publishing Co., Inc.
previous studies has been introduced. Finally, the main
objective of the previous studies has been cleared.
VI. References
[1] A. Al Wattar, “DYNAMIC key-depending
S-boxes inspired by biological DNA,” Int. J.
Electr. Comput. Sci. IJECS, vol. 15, no. 04,
pp. 4853, 2015.
[2] Zeebaree, D. Q., Haron, H., Abdulazeez, A.
M., & Zebari, D. A. (2019, April). Machine
learning and Region Growing for Breast
Cancer Segmentation. In 2019 International
Conference on Advanced Science and
Engineering (ICOASE) (pp. 88-93). IEEE.
[3] H. Singh and D. Singh, “Location based
information hiding,” presented at the 2016
International Conference on Advances in
Computing, Communication, & Automation
(ICACCA)(Spring), 2016, pp. 14.
[4] Zebari, D. A., Haron, H., Zeebaree, S. R., &
Zeebaree, D. Q. (2018, October). Multi-Level
of DNA Encryption Technique Based on
DNA Arithmetic and Biological Operations.
In 2018 International Conference on
Advanced Science and Engineering
(ICOASE) (pp. 312-317). IEEE.
[5] Shivani, V. Yadav, and S. Batham, “A Novel
Approach of Bulk Data Hiding using Text
Steganography,” in Procedia Computer
Science, 2015, vol. 57, pp. 14011410.
[6] A. Al-Zebari and A. Sengur, “Performance
Comparison of Machine Learning Techniques
on Diabetes Disease Detection,” presented at
the 2019 1st International Informatics and
Software Engineering Conference (UBMYK),
2019, pp. 14.
[7] Zeebaree, D. Q., Haron, H., & Abdulazeez, A.
M. (2018, October). Gene selection and
classification of microarray data using
convolutional neural network. In 2018
International Conference on Advanced
Science and Engineering (ICOASE) (pp. 145-
150). IEEE.
[8] O. Ahmed and A. Brifcani, “Gene Expression
Classification Based on Deep Learning,”
presented at the 2019 4th Scientific
International Conference Najaf (SICN), 2019,
pp. 145149.
[9] N. Najat and A. M. Abdulazeez, Gene
clustering with partition around mediods
algorithm based on weighted and normalized
Mahalanobis distance,” presented at the 2017
International Conference on Intelligent
Informatics and Biomedical Sciences
(ICIIBMS), 2017, pp. 140145.
[10] Sulaiman, D. M., Abdulazeez, A. M., Haron,
H., & Sadiq, S. S. (2019, April). Unsupervised
Learning Approach-Based New Optimization
K-Means Clustering for Finger Vein Image
Localization. In 2019 International
Conference on Advanced Science and
Engineering (ICOASE) (pp. 82-87). IEEE.
[11] A. Al-Mohammad, “Steganography-based
secret and reliable communications:
Improving steganographic capacity and
imperceptibility,” 2010.
[12]D. A. Zebari, H. Haron, D. Q. Zeebaree, and A.
M. Zain, „A Simultaneous Approach for
Compression and Encryption Techniques
Using Deoxyribonucleic Acid‟, presented at
the 2019 13th International Conference on
Software, Knowledge, Information
Management and Applications (SKIMA),
2019, pp. 16.
[13]Y. Wang and P. Moulin, “Optimized feature
extraction for learning-based image
steganalysis,” IEEE Trans. Inf. Forensics
Secur., vol. 2, no. 1, pp. 3145, 2007.
[14] Zebari, D. A., Haron, H., Zeebaree, S. R., &
Zeebaree, D. Q. (2019, April). Enhance the
Mammogram Images for Both Segmentation
and Feature Extraction Using Wavelet
Transform. In 2019 International Conference
on Advanced Science and Engineering
(ICOASE) (pp. 100-105). IEEE.
[15] V. Kumar, “A Study on Steganography &
Data Hiding,” Int. J. Innov. Res. Comput.
Commun. Eng., vol. 3, no. 10, pp. 95049513,
2015.
[16] S. K. Bandyopadhyay, D. Bhattacharyya, D.
Ganguly, S. Mukherjee, and P. Das, A
tutorial review on steganography,” presented
at the International conference on
May-June 2020
ISSN: 0193-4120 Page No. 2225722269
22266
Published by: The Mattingley Publishing Co., Inc.
contemporary computing, 2008, vol. 101, pp.
105114.
[17] A. Cheddad, “Steganoflage: a new image
steganography algorithm,” 2009.
[18] N. Adeen, M. Abdulazeez, and D. Zeebaree,
“Systematic Review of Unsupervised
Genomic Clustering Algorithms Techniques
for High Dimensional Datasets,” vol. 62, no.
3, 2020.
[19] J. Ashok, Y. Raju, S. Munishankaraiah, and
K. Srinivas, “Steganography: an overview,”
Int. J. Eng. Sci. Technol., vol. 2, no. 10, pp.
59855992, 2010.
[20] A. M. Nickfarjam and Z. Azimifar, “Image
steganography based on pixel ranking and
particle swarm optimization,” presented at the
The 16th CSI International Symposium on
Artificial Intelligence and Signal Processing
(AISP 2012), 2012, pp. 360363.
[21] Sheelu and B. Ahuja, “An Overview of
Steganography,” IOSR J. Comput. Eng. IOSR-
JCE, pp. 1519, 2013.
[22] A. Khalifa, “LSBase: A key encapsulation
scheme to improve hybrid crypto-systems
using DNA steganography,” presented at the
2013 8th International Conference on
Computer Engineering & Systems (ICCES),
2013, pp. 105110.
[23] S. William, Cryptography and Network
Security: for VTU. Pearson Education India,
2006.
[24] S. Jain and V. Bhatnagar, “Analogy of various
DNA based security algorithms using
cryptography and steganography,” presented
at the 2014 International Conference on Issues
and Challenges in Intelligent Computing
Techniques (ICICT), 2014, pp. 285291.
[25] M. R. N. Torkaman, N. S. Kazazi, and A.
Rouddini, “Innovative approach to improve
hybrid cryptography by using DNA
steganography,” Int. J. New Comput. Archit.
Their Appl., vol. 202, pp. 225236, 2012.
[26] S. I. Saleem, S. R. Zeebaree, D. Q. Zeebaree,
and A. M. Abdulazeez, “Building Smart Cities
Applications based on IoT Technologies: A
Review,Vol 62,03,2020.
[27] S. Bansod and G. Bhure, “Data encryption by
image steganography,” Int J Inf. Comput
Technol Int Res Publ House, vol. 4, pp. 453
458, 2014.
[28] D. M. Abdulqader, A. M. Abdulazeez, and D.
Q. Zeebaree, “Machine Learning Supervised
Algorithms of Gene Selection: A Review,”
Mach. Learn., vol. 62, no. 03, 2020.
[29] M. H. Shirali-Shahreza and M. Shirali-
Shahreza, “A new approach to Persian/Arabic
text steganography,” presented at the 5th
IEEE/ACIS International Conference on
Computer and Information Science and 1st
IEEE/ACIS International Workshop on
Component-Based Software Engineering,
Software Architecture and Reuse (ICIS-
COMSAR‟06), 2006, pp. 310–315.
[30] Y.-W. Kim, K.-A. Moon, and I.-S. Oh, “A
Text Watermarking Algorithm based on Word
Classification and Inter-word Space
Statistics.,” presented at the ICDAR, 2003, pp.
775779.
[31] K. F. Rafat, “Enhanced text steganography by
changing word‟s spelling,” presented at the
Proceedings of the 7th International
Conference on Frontiers of Information
Technology, 2009, pp. 14.
[32] D. Q. Zeebaree, H. Haron, A. M. Abdulazeez,
and D. A. Zebari, “Trainable Model Based on
New Uniform LBP Feature to Identify the
Risk of the Breast Cancer,” presented at the
2019 International Conference on Advanced
Science and Engineering (ICOASE), 2019, pp.
106111.
[33] K. U. Singh, “Video steganography: text
hiding in video by LSB substitution,” Int. J.
Eng. Res. Appl., vol. 4, no. 5, pp. 105108,
2014.
[34] A. M. A. Brifcani and J. N. Al-Bamerny,
“Image compression analysis using multistage
vector quantization based on discrete wavelet
transform,” presented at the 2010 International
Conference on Methods and Models in
Computer Science (ICM2CS-2010), 2010, pp.
4653.
[35] J. N. Saeed, “A SURVEY OF
ULTRASONOGRAPHY BREAST CANCER
May-June 2020
ISSN: 0193-4120 Page No. 2225722269
22267
Published by: The Mattingley Publishing Co., Inc.
IMAGE SEGMENTATION TECHNIQUES,”
Acad. J. Nawroz Univ., vol. 9, no. 1, pp. 114,
2020.
[36] V. M. Wajgade and D. S. Kumar, “Enhancing
data security using video steganography,” Int.
J. Emerg. Technol. Adv. Eng., vol. 3, no. 4,
pp. 549552, 2013.
[37] S. Khupse and N. N. Patil, “An adaptive
steganography technique for videos using
Steganoflage,” presented at the 2014
International Conference on Issues and
Challenges in Intelligent Computing
Techniques (ICICT), 2014, pp. 811815.
[38] R. Kaur and S. Kaur, “XOR-EDGE based
video steganography and testing against chi-
square steganalysis,” Int. J. Image Graph.
Signal Process., vol. 8, no. 9, p. 31, 2016.
[39] M. S. Kumar and G. M. Latha, “DCT based
secret image hiding in video sequence,” J.
Eng. Res. Appl. Www Ijera Com ISSN, pp.
22489622, 2014.
[40] R. M. Nugraha, “Implementation of direct
sequence spread spectrum steganography on
audio data,” presented at the Proceedings of
the 2011 International Conference on
Electrical Engineering and Informatics, 2011,
pp. 16.
[41] A. K. Mandal, M. Kaosar, M. O. Islam, and
M. D. Hossain, “An approach for enhancing
message security in audio steganography,”
presented at the 16th Int‟l Conf. Computer and
Information Technology, 2014, pp. 383388.
[42] S. Bhalshankar and A. K. Gulve, “Audio
steganography: LSB technique using a
pyramid structure and range of bytes,” ArXiv
Prepr. ArXiv150902630, 2015.
[43] R. Chowdhury, D. Bhattacharyya, S. K.
Bandyopadhyay, and T. Kim, “A view on
LSB based audio steganography,” Int. J.
Secur. Its Appl., vol. 10, no. 2, pp. 5162,
2016.
[44] S. R. Zeebaree, R. R. Zebari, K. Jacksi, and D.
A. Hasan, “Security Approaches For
Integrated Enterprise Systems Performance: A
Review.”
[45] Y. Yang, “Information analysis for
steganography and steganalysis in 3D
polygonal meshes,” 2013.
[46] G. Manjula and A. Danti, “A novel hash based
least significant bit (2-3-3) image
steganography in spatial domain,” ArXiv
Prepr. ArXiv150303674, 2015.
[47] P. K. Gupta, R. Roy, and S. Changder, “A
secure image steganography technique with
moderately higher significant bit embedding,”
presented at the 2014 International Conference
on Computer Communication and Informatics,
2014, pp. 16.
[48] N. N. Mohammed and A. M. Abdulazeez,
“Evaluation of partitioning around medoids
algorithm with various distances on
microarray data,” presented at the 2017 IEEE
International Conference on Internet of Things
(iThings) and IEEE Green Computing and
Communications (GreenCom) and IEEE
Cyber, Physical and Social Computing
(CPSCom) and IEEE Smart Data (SmartData),
2017, pp. 10111016.
[49] H. Al-Dmour, A. Al-Ani, and H. Nguyen, “An
efficient steganography method for hiding
patient confidential information,” presented at
the 2014 36th Annual International
Conference of the IEEE Engineering in
Medicine and Biology Society, 2014, pp. 222
225.
[50] A. Mondal and S. Pujari, “A novel approach
of imagebased steganography using
pseudorandom sequence generator function
and DCT coefficients,” Int. J. Comput. Netw.
Inf. Secur., vol. 7, no. 3, pp. 4249, 2015.
[51] S. S. Sadiq, A. M. Abdulazeez, and H. Haron,
“Solving multi-objective master production
schedule problem using memetic algorithm,”
Indones. J. Electr. Eng. Comput. Sci., vol. 18,
no. 2, pp. 938945, 2020.
[52] R. S. Naoum, “Image Steganography Based
on Discrete Wavelet Transform and
Enhancing Resilient Backpropogation Neural
Network,” 2015.
[53] K. S. Shete, M. Patil, and J. Chitode, “Least
significant bit and discrete wavelet transform
algorithm realization for image steganography
May-June 2020
ISSN: 0193-4120 Page No. 2225722269
22268
Published by: The Mattingley Publishing Co., Inc.
employing FPGA,” Int. J. Image Graph.
Signal Process., vol. 8, no. 6, p. 48, 2016.
[54] M. Mahdi Hashim, M. Rahim, and M. Shafry,
“IMAGE STEGANOGRAPHY BASED ON
ODD/EVEN PIXELS DISTRIBUTION
SCHEME AND TWO PARAMETERS
RANDOM FUNCTION.,” J. Theor. Appl. Inf.
Technol., vol. 95, no. 22, 2017.
[55] M. R. Mahmood, A. M. Abdulazeez, and Z.
Orman, “Dynamic Hand Gesture Recognition
System for Kurdish Sign Language Using
Two Lines of Features,” presented at the 2018
International Conference on Advanced
Science and Engineering (ICOASE), 2018, pp.
4247.
[56] J. Ghorpade-Aher and V. A. Metre,
“Clustering Multidimensional Data with PSO
based Algorithm,” ArXiv Prepr.
ArXiv14026428, 2014.
[57] I. M. Zeebaree, D. Q. Zeebaree, and Z. A.
Ayoub, “FACE RECOGNITION USING
STATISTICAL FEATURE EXTRACTION
AND NEURAL. Vol 62,03,2020.”
[58] A. S. Eesa, Z. Orman, and A. M. A. Brifcani,
“A novel feature-selection approach based on
the cuttlefish optimization algorithm for
intrusion detection systems,” Expert Syst.
Appl., vol. 42, no. 5, pp. 26702679, 2015.
[59] S. Roy, S. Biswas, and S. S. Chaudhuri,
“Nature-inspired swarm intelligence and its
applications,” Int. J. Mod. Educ. Comput. Sci.,
vol. 6, no. 12, p. 55, 2014.
[60] S. M. Thampi, “Information hiding
techniques: a tutorial review,” ArXiv Prepr.
ArXiv08023746, 2008.
[61] R. Zebari, A. Abdulazeez, D. Zeebaree, D.
Zebari, and J. Saeed, A Comprehensive
Review of Dimensionality Reduction
Techniques for Feature Selection and Feature
Extraction,” J. Appl. Sci. Technol. Trends, vol.
1, no. 2, pp. 5670, 2020.
[62] M. Dorigo, V. Maniezzo, and A. Colorni,
“Ant system: optimization by a colony of
cooperating agents,” IEEE Trans. Syst. Man
Cybern. Part B Cybern., vol. 26, no. 1, pp.
2941, 1996.
[63] X.-S. Yang, “Swarm intelligence based
algorithms: a critical analysis,” Evol. Intell.,
vol. 7, no. 1, pp. 1728, 2014.
[64] N. Kayarvizhy, S. Kanmani, and R.
Uthariaraj, “ANN models optimized using
swarm intelligence algorithms,” WSEAS
Trans. Comput., vol. 13, no. 45, pp. 501519,
2014.
[65] D. Karaboga, “An idea based on honey bee
swarm for numerical optimization,” Technical
report-tr06, Erciyes university, engineering
faculty, computer …, 2005.
[66] T. Yu, L. Wang, X. Han, Y. Liu, and L.
Zhang, “Swarm intelligence optimization
algorithms and their application,” WHICEB
2015 Proc, vol. 3, 2015.
[67] S. Das, A. Abraham, and A. Konar, Swarm
intelligence algorithms in bioinformatics,” in
Computational Intelligence in Bioinformatics,
Springer, 2008, pp. 113147.
[68] S. Thenmozhi and M. Chandrasekaran,
“Novel Technology for Secure Data
Transmission Based on Integer Wavelet
Transform and Particle Swarm Optimization,”
Res. J. Appl. Sci. Eng. Technol., vol. 12, no. 2,
pp. 188196, 2016.
[69] R. Eberhart and J. Kennedy, “A new optimizer
using particle swarm theory,” presented at the
MHS‟95. Proceedings of the Sixth
International Symposium on Micro Machine
and Human Science, 1995, pp. 3943.
[70] K. J, “abd Eberhart R,” in proceedings of the
IEEE, 1995.
[71] H. Ahmed and J. Glasgow, “Swarm
intelligence: concepts, models and
applications,” Sch. Comput. Queens Univ.
Tech. Rep., 2012.
[72] M. B. Abdulrazzaq and J. N. Saeed, “A
Comparison of Three Classification
Algorithms for Handwritten Digit
Recognition,” presented at the 2019
International Conference on Advanced
Science and Engineering (ICOASE), 2019, pp.
5863.
[73] O. M. S. Hassan, A. M. Abdulazeez, and V.
M. TİRYAKİ, “Gait-based human gender
classification using lifting 5/3 wavelet and
May-June 2020
ISSN: 0193-4120 Page No. 2225722269
22269
Published by: The Mattingley Publishing Co., Inc.
principal component analysis,” presented at
the 2018 International Conference on
Advanced Science and Engineering
(ICOASE), 2018, pp. 173178.
[74] X. Li and J. Wang, “A steganographic method
based upon JPEG and particle swarm
optimization algorithm,” Inf. Sci., vol. 177, no.
15, pp. 30993109, 2007.
[75] S. Fazli and M. Kiamini, “A
high_performance steganographic method
using JPEG and PSO algorithm,” presented at
the 2008 IEEE International Multitopic
Conference, 2008, pp. 100105.
[76] C.-S. Hsu and S.-F. Tu, “Finding optimal LSB
substitution using ant colony optimization
algorithm,” presented at the 2010 Second
International Conference on Communication
Software and Networks, 2010, pp. 293297.
[77] P. Bedi, R. Bansal, and P. Sehgal, “Using PSO
in a spatial domain based image hiding
scheme with distortion tolerance,” Comput.
Electr. Eng., vol. 39, no. 2, pp. 640654,
2013.
[78] K. Jaidka and A. Mavi, “PSO (Particle Swarm
Optimization) Based Reversible Data Hiding,”
Int. J. Sci. Res. IJSR, vol. 4, no. 6, pp. 2480
2483, 2015.
[79] N. Kaur and A. Garg, “Steganography Using
PSO Based Hybrid Algorithm,” Int. J. Adv.
Res. Comput. Sci. Softw. Eng., vol. 4, no. 1,
2014.
[80] A. Nickfarjam, H. Ebrahimpour-Komleh, and
A. P. Najafabadi, “Image hiding using
neighborhood similarity,” presented at the
2014 6th Conference on Information and
Knowledge Technology (IKT), 2014, pp. 79
82.
[81] A. Amsaveni and C. Arunkumar, “An efficient
data hiding scheme using firefly algorithm in
spatial domain,” presented at the 2015 2nd
International Conference on Electronics and
Communication Systems (ICECS), 2015, pp.
650655.
[82] E. Divya and P. Rajkumar, “Steganographic
Data Hiding using DWT and Particle Swarm
Optimization,” Int. J. Comput. Appl., vol. 117,
no. 14, 2015.
[83] D. E and R. P, “Image To Image Hiding Using
PSO,” Int. J. Innov. Res. Adv. Eng., vol. 2, no.
5, pp. 146151, 2015.
[84] W. S. Awad, “Information hiding using ant
colony optimization algorithm,” Int. J.
Technol. Diffus. IJTD, vol. 2, no. 1, pp. 1628,
2011.
[85] A. Kaur, R. Kaur, and N. Kumar, “Image
steganography using discrete wavelet
transformation and artificial bee colony
optimization,” presented at the 2015 1st
International Conference on Next Generation
Computing Technologies (NGCT), 2015, pp.
990994.
... Histogram reveals each pixel's precise occurrence in the picture. The remarkable resemblance between the histograms of the host and the stego shows the minimum distortion after the secret picture has been integrated into the host image [13]. ...
... Histogram reveals each pixel's precise occurrence in the picture. The remarkable resemblance between the histograms of the host and the stego shows the minimum distortion after the secret picture has been integrated into the host image [13]. ...
Article
Full-text available
Steganography includes hiding text, image, or any sentient information inside another image, video, or audio. It aims to increase individuals' use of social media, the internet and web networks to securely transmit information between sender and receiver and an attacker will not be able to detect its information. The current article deals with steganography that can be used as machine learning method, it suggests a new method to hide data by using unsupervised machine learning (clustering k-mean algorithm). This system uses hidden data into the cover image, it consists of three steps: the first step divides the cover image into three clusterings that more contrast by using k-means cluster, the selects a text or image to be converted to binary by using ASCII code, the third step hides a binary message or binary image in the cover image by using sequential LSB method. After that, the system is implemented. The objective of the suggested system is obtained, using Unsupervised Machine Learning (K-mean technique) to securely send sensitive information without worrying about man-in-the-middle attack was proposed. Such a method is characterized by high security and capacity. Through evaluation, the system uses PSNR, MSE, Entropy, and Histogram to hide the secret message and secret image in the spatial domain in the cover image.
... The optimization process goes through crossover, mutation and then the fittest gen will be selected [5]. Particle Swarm Optimization (PSO) technique that is depends on the swarm conduct of both fish as well as birds, the system which is described as system of multi-agent may include features of this intelligence of swarm group [6], Firefly Algorithm (FA) that is depends on the features of flashing ideal conduct of fireflies in the tropic regions [7] [8] whereas another algorithm depending on the echolocation conduct of micro bats called a Bat Algorithm (BA) [9]. Also, there are some recent nature inspired algorithms; for example, Harris Hawks Optimizer (HHO) is an optimization algorithm inspired by the conducts of cooperative as well as chasing patterns of predacious birds [10], Another algorithm which is simulates the conduct of slaps swarming during transportation when foraging in oceans called the Salp Swarm Algorithm (SSA) [11], also the technique of Beetle Antennae Search (BAS) which is inspired by the behavior of searching of long-horn bug [12], Finally, Black Widow Optimization (BWO) is an optimization technique that is inspired by the single conduct of black widow spiders mating [13]. ...
Article
Full-text available
Nature-inspired algorithms are often used by several diverse areas of engineering and science due to their easiness and versatility. Because metaheuristics operate by structurally changing and improving an established problem, they can often be extended to any optimization issues. The recent creation of meta-heuristic algorithms has rendered them effective tools for solving NP problems. This paper presents a hybrid meta-heuristic method based on the Differential Evolution and Bird Mating Optimizer techniques to solve problems of global optimization. Bird Mating Optimizer is a novel method and is inspired by mating behavior of birds. Bird Mating Optimizer has some drawbacks such as producing poor results, trapping into local optima and slow convergence speed. Therefore, to conquer these insufficient it is hybridized with Differential Evolution approach. Differential Evolution technique is utilized to retain a preferable balance between both searches local and global. The performance and effectiveness of new Differential Evolution and Bird Mating Optimizer algorithm is tested and evaluated on 15 different functions of benchmark. The results of the experiment have shown the proposed technique possesses excellent performance in convergence speed, stability, and robustness, as compared to the well-known algorithms. It is proved that the Differential Evolution and Bird Mating Optimizer algorithm is very effective and superior to solve problems of global optimization. Experimental results indicate that the proposed hybrid Differential Evolution and Bird Mating Optimizer method is superior to previous existing state-of-the-art metaheuristic algorithms.
... The optimization process goes through crossover, mutation and then the fittest gen will be selected [5]. Particle Swarm Optimization (PSO) technique that is depends on the swarm conduct of both fish as well as birds, the system which is described as system of multi-agent may include features of this intelligence of swarm group [6], Firefly Algorithm (FA) that is depends on the features of flashing ideal conduct of fireflies in the tropic regions [7] [8] whereas another algorithm depending on the echolocation conduct of micro bats called a Bat Algorithm (BA) [9]. Also, there are some recent nature inspired algorithms; for example, Harris Hawks Optimizer (HHO) is an optimization algorithm inspired by the conducts of cooperative as well as chasing patterns of predacious birds [10], Another algorithm which is simulates the conduct of slaps swarming during transportation when foraging in oceans called the Salp Swarm Algorithm (SSA) [11], also the technique of Beetle Antennae Search (BAS) which is inspired by the behavior of searching of long-horn bug [12], Finally, Black Widow Optimization (BWO) is an optimization technique that is inspired by the single conduct of black widow spiders mating [13]. ...
Article
Steganography has been used massively in numerous fields to maintain the privacy and integrity of messages transferred via the internet. The need to secure the information has augmented with the increase in e-governance usage. The wide adoption of e-governance services also opens the doors to cybercriminals for fraudulent activities in cyberspace. To deal with these cybercrimes we need optimized and advanced steganographic techniques. Various advanced optimization techniques can be applied to steganography to obtain better results for the security of information. Various optimization techniques like particle swarm optimization and genetic algorithms with cryptography can be used to protect information for e-governance services. In this study, a comprehensive review of steganographic algorithms using optimization techniques is presented. A new perspective on using this technique to protect the information for e-governance is also presented. Deep Learning might be the area that can be used to automate the steganography process in combination with other methods
Conference Paper
Full-text available
Digital watermarking is getting more research and industry attention. Digital multimedia data allows for robust and simple data editing and modification. However, the spread of digital media presents concerns for digital content owners. It is important to note that digital data can be copied without quality or content loss. This has a considerable impact on copyright holders' ability to safeguard their intellectual property rights. The method of transmitting information by imperceptibly embedding it into digital media is digital watermarking. There are various methods in literature, such as DWT and DCT, which take full energy, are seen and integrated. New strategies and procedures for optimization are required. The present study proposes a novel design and computation technique based on the discrete wavelet and discrete cosine transforms. Watermarking techniques have been progressing to shield media content such as text, audio, video, etc. From copyright. The proposed hybrid DWT-DCT Bacterial Foraging Optimization (BFO) technique improves the efficiency of watermarking digital images by 97%. Bacterial foraging optimization (BFO) is an innovative technique for intelligent optimization. It is a widely used optimization algorithm in a wide variety of applications. However, when compared to other optimizers, the BFO performs poorly in terms of convergence. This technique uses a high-frequency image region. A variety of techniques are compared with the (NCC) Normalized Cross Correlations, (PSNR) Peak Noise Signal Ratio and IF (Image Fidelity). The highest performance is seen in DWT-DCT-BFO watermarking.
Article
Full-text available
Whether you deal with a real-life issue or create a software product, optimization is constantly the ultimate goal. This goal, however, is achieved by utilizing one of the optimization algorithms. The progressively popular Gradient Descent (GD) optimization algorithms are frequently used as black box optimizers when solving unrestricted problems of optimization. Each iteration of a gradient-based algorithm attempts to approach the minimizer/maximizer cost function by using the gradient's objective function information.
Article
Full-text available
Diabetes may be predicted and prevented by exploring critical diabetes characteristics by computational data extraction methods. This study proposed a system biology approach to the pathogenic process to identify essential biomarkers as drug targets. The fact that disease recognition and investigation require many details, data mining plays a critical role in healthcare. This study aims to evaluate the efficiency of the methods used that are based on classification. Besides, the researchers have highlighted the most widely employed techniques and the strategies with the best precision. Many analyses include multiple Machine Learning algorithms for various disease assessments and predictions to improve overall issues. The detection and prediction of diseases is an aspect of classification and prediction. This paper estimates diabetes by its key features and also categorizes the relations between conflicting elements. The recursive random forest removal function provided a significant feature range. Random Forest Classifier investigated the diabetes estimate. RF offers 75,7813 greater precisions than Support Vector Machine (SVM).and may assist medical professionals in making care decisions.
Article
Full-text available
Transfer learning and deep learning approaches have been utilised in several real-world applications and hierarchical systems for pattern recognition and classification tasks. However, in few of the real-world machine learning situations, this presumption does not sustain since there are instances where training data is costly or tough to gather and there is continually a necessity to produce high-performance learners competent with more easily attained data from diverse fields. The objective of this review is to determine more abstract qualities at the greater levels of the representation, by utilising deep learning to detach the variables in the outcomes, formally outline transfer learning, provide information on present solutions, and appraise applications employed in diverse facets of transfer learning and deep learning. This can be attained by rigorous literature exploration and discussion on all presently accessible techniques and prospective research studies on transfer learning solutions of independent as well as big data scale. The conclusions of this study could be an effectual platform directed at prospective directions for devising new deep learning patterns for different applications and dealing with the challenges concerned. IJSB Literature Review
Article
Full-text available
Due to sharp increases in data dimensions, working on every data mining or machine learning (ML) task requires more efficient techniques to get the desired results. Therefore, in recent years, researchers have proposed and developed many methods and techniques to reduce the high dimensions of data and to attain the required accuracy. To ameliorate the accuracy of learning features as well as to decrease the training time dimensionality reduction is used as a pre-processing step, which can eliminate irrelevant data, noise, and redundant features. Dimensionality reduction (DR) has been performed based on two main methods, which are feature selection (FS) and feature extraction (FE). FS is considered an important method because data is generated continuously at an ever-increasing rate; some serious dimensionality problems can be reduced with this method, such as decreasing redundancy effectively, eliminating irrelevant data, and ameliorating result comprehensibility. Moreover, FE transacts with the problem of finding the most distinctive, informative, and decreased set of features to ameliorate the efficiency of both the processing and storage of data. This paper offers a comprehensive approach to FS and FE in the scope of DR. Moreover, the details of each paper, such as used algorithms/approaches, datasets, classifiers, and achieved results are comprehensively analyzed and summarized. Besides, a systematic discussion of all of the reviewed methods to highlight authors' trends, determining the method(s) has been done, which significantly reduced computational time, and selecting the most accurate classifiers. As a result, the different types of both methods have been discussed and analyzed the findings.
Article
Full-text available
High-dimensional data is interpreted with a considerable number of features, and new problems are presented in groups. The so-called "high dimension" is initially created to explain the common increase in time complexity of many computational problems, and therefore the performance of general aggregation algorithms is unsuccessful. Accordingly, many works focused on introducing new technologies and aggregation algorithms to process data with higher dimensions. Standard algorithms for all aggregate algorithms are the fact that they need a different essential evaluation of the similarity between data objects. However, current aggregation algorithms still have some open research problems. In this review work, they provide a summary of the results of the high-dimensional data space and its effects on different aggregation algorithms. It also provides a detailed overview of several grouping algorithms with several types: subspace methods, model-based grouping, density-based grouping methods, partition-based grouping methods, etc., including a more detailed description of the recent work of its advantages and disadvantages in Solve the problem of higher-dimensional data. The scope of future work is also discussed at the end of the work to expand existing compilation methods and algorithms.
Article
Full-text available
span>A master production schedule (MPS) need find a good, perhaps optimal, plan for maximize service levels while minimizing inventory and resource usage. However, these are conflicting objectives and a tradeoff to reach acceptable values must be made. Therefore, several techniques have been proposed to perform optimization on production planning problems based on, for instance, linear and non-linear programming, dynamic-lot sizing and meta-heuristics. In particular, several meta- heuristics have been successfully used to solve MPS problems such as genetic algorithms (GA) and simulated annealing (SA). This paper proposes a memetic algorithm to solve multi-objective master production schedule (MOMPS). The proposed memetic algorithm combines the evolutionary operations of MA (such as mutation and Crossover) with local search operators (swap operator and inverse movement operator) to improve the solutions of MA and increase the diversity of the population). This algorithm has proved its efficiency in solving MOMPS problems compared with the genetic algorithm and simulated annealing. The results clearly showed the ability of the algorithm to evaluate properly how much, when and where extra capacities (overtime) are permitted so that the inventory can be lowered without influencing the level of service. </span
Article
Full-text available
The most common cause of death among women globally is breast cancer. One of the key strategies to reduce mortality associated with breast cancer is to develop effective early detection techniques. The segmentation of breast ultrasound (BUS) image in Computer-Aided Diagnosis (CAD) systems is critical and challenging. Image segmentation aims to represent the image in a simplified and more meaningful way while retaining crucial features for easier analysis. However, in the field of image processing, image segmentation is a tough task particularly in ultrasound (US) images due to challenges associated with their nature. This paper presents a survey on several techniques of ultrasonography images segmentation including threshold based, region based, watershed, active contour and learning based techniques, their merits, and demerits. This can provide significant insights for CAD developers or researchers to advance this field.
Article
Full-text available
Advancement in Information and Communications Technology (ICT) has become the communication medium for virtually every small or large industry around the world. This technology changed the ways of doing business and has led to the invention of a new concept called Electronic Business (E-Business). E-Business involves various activities for any business such as ordering, transacting, customer servicing, delivering and paying. This new type of business consists of many advantages comparing with the traditional form of business, but on the other hand, it faces real challenges related to the approaches used to keep the data secure. The sharing of sensitive data for any enterprise system requires designing a security management framework in order to enable controlling access to sensitive information. In this paper, the last efforts of researchers proposed in the security field of the E-Business systematically reviewed. Furthermore, security approaches, techniques, and security frameworks have been discussed.
Conference Paper
Full-text available
In developing countries breast cancer has been found to be one of the diseases that threatens the lives of women, and that is why finding ways of detecting efficiently is of great importance. The detection of breast cancer at an early stage through self-examination is very difficult. In this study, we proposed a new descriptor that can help to identify the abnormality of the breast by enhancing the features of LBP texture and enhance the LPB descriptor by using a new threshold that can help to identify the important information for the detection of abnormal cases. In the next stage, the significant features are extracted from the breast tumours images that have been segmented. Such features could be found in frequency or spatial domain. The extracted features for diagnosing tumour automatically, are additional and different from those features which the radiologist extracts manually. The proposed method demonstrates the possibility of using the LBP based texture feature with the new proposed method for categorising ultrasound images, which registered a high accuracy of 96%, the sensitivity of 94%, specificity of 97%.