IRAQI JOURNAL OF COMPUTERS, COMMUNICATIONS, CONTROL AND SYSTEMS ENGINEERING

Cryptographic approaches based on chaos theory provide several new and promising avenues for developing safe picture encryption solutions. This paper aims to complicate the process of decrypting images by adding encryption with keys. This was achieved by applying the principle of the 3D-chaotic system with the encryption algorithm. We present an image encryption algorithm called black mask by using an efficient Multidimensional Chaotic Map represented by the Lorenz system. For the confusion process, the suggested approach is based on a key stream generator. The process of confusion is initiated by 256-bit secret keys, which are produced by logistic maps. To make the cipher more dynamic in the face of any threat, the suggested digital image encryption technique, as well as its security analysis and implementation, are discussed in depth. The experimental results suggest that the proposed method for image encryption and transmission is both efficient and safe.

Researchers have extensively utilized optical orthogonal frequency division multiplexing (O-OFDM) in visible light communication (VLC) to achieve high data rate transmission for free spectrum bandwidth. The peak-to-average power ratio (PAPR) is the critical challenge for VLC systems-based O-OFDM that produces non-linearity and degrades performance. In this paper, a proposed model for PAPR reduction can be applied with different O-OFDM technologies. This model considered using μ-law companding with O-OFDM transmitter to compress high amplitude peaks and restore the signals using de-companding in the receiver. The obtained simulation results show an efficient achievement of about 75% PAPR reduction compared with the original O-OFDM for different techniques. Furthermore, The convolutional encoder with Viterbi decoder is used with our proposed model for improvement BER performance and tradeoff with PAPR. The BER performance for different coding schemes, O-OFDM technologies, and modulation orders has been graphed and compared. It can notice the convolutional encoder/Viterbi satisfies better BER than Hamming coding/decoding. However, the number of memory cells of the convolutional encoder plays an essential role in BER improvement.

Text summarization can be utilized for a variety of purposes, one of them being to summarize lecture files. Long documents require significant time and storage capacity and may contain duplicated or irrelevant details, making it time-consuming to access relevant information. Summarization provides the primary points of the whole document, saving user time, reducing storage, and increasing transfer speed. The proposed method uses a convolutional recurrent neural network (CRNN) deep model for abstractive text summarization of lecture files, aiding students in addressing lecture notes. The method involves an encoder-decoder deep model with convolutional and recurrent networks, incorporating attention mechanisms. Using the CNN/Daily Mail dataset, the model achieved 92.90% accuracy.

This article presents a decentralized controller/observer for nonlinear large-
scale interconnected systems with actuator fault. The proposal integrates a robust
proportional-integral-derivative (PID) controller with the unknown input observer (UIO)
to achieve closed-loop robustness against the interactions and the actuator faults. In this
scheme, the PID controller is tuned using the Bacterial foraging optimization algorithm
(BFO) algorithm. On the other hand, the unknown input observer can diagnose the
actuator faults from the controller input. A numerical example consisting of two
subsystems is adopted to clarify the effectiveness of the suggested method with a
guarantee that the state estimation error is asymptotically converged to zero. The
actuator faults have been added to the second subsystem, keeping the first subsystem free
of fault. The simulation results demonstrated the influence of the interactions between
subsystems, verifying that the unknown input observer can detect the actuator faults
despite the presence of these interactions between the subsystems.

Cryptography is a security strategy that prevents disclosure of the
information while it is transit, in storage, or both. There are a variety of
methods for maintaining data security, including utilizing light weight speed
algorithms for encryption and parameter validation. Many algorithms have
originated in the area of information protection, helping to assure the validity
of the information generated. These include the following algorithms: SHA-1,
SHA-2, SHA-3, AES, RC5, RSA, and more. In order to secure the legitimacy of
the information and monitoring data , the speed of encryption and
authentication must be critical. . Due to the necessity of fast and secure
algorithms, these features are required. In this work, modification of the SHA-3
algorithm by introducing a new function called (the keccak function), which has
an extremely quick execution time and a high level of security, also versatile
cryptographic function. This change is implemented via the 2D chaotic system,
which is geared towards generating random values for constants for the SHA3
algorithm. These constants values are generated by the SHA3 algorithm, and so
are random and unguessable by the intrude. Statistical tests conducted by the
National Institute of Standards and Technology (NIST) effectively outperformed
the randomness of a proposed approach .The proposed algorithm shows lower
execution time compared to previous studies, which is 0.041616sec for 1MB.

This Face detection is considering one of the important topics for
recognizing human, it is the first step before the face recognition process, it is
considered one of the biggest challenges in the field of vision computer. In
recent years Many algorithms for detection have appeared, which depend on
extracting the features of the human face, and works continue to develop them
to this day. This paper aims to make a comparison between two of the most
commonly face detection methods, Viola Jones (V_J) and YOLO v3. This
comparison is made to determine which of the two algorithms is being most
useful when used to detect faces in digital video. These algorithms are used in
many applications, including image classification, medical analysis of image,
and objects detection in real time (especially in surveillance cameras). Both
algorithms are applied to detect faces in the real time video. The experimental
results of a sample consists of 20 video frames show that V_J algorithm
consumes less time in comparison with YOLO v3 algorithm, but its results are
less accurate, unlike the YOLO v3 algorithm, which is slower in detect face with
high accurate rate.

Due to sophisticated cyber-attacks, and to produce false alarms on
suspicious or unusual behavior to monitor computer resources, Intrusion
Detection Systems (IDSs) are required. Hence, Many Machine Learning (ML)
and data mining techniques have been proposed to increase the effectiveness of
IDSs, whereas current IDS algorithms are still struggling to perform effectively
while many IDSs depend on a single classifier to detect intrusions. Single-
classifier IDSs cannot achieve high accuracy and low false alarm rates because
of zero-day attacks. In this paper, a hybrid ensemble method using AdaBoosting
and Bagging for IDS is proposed. This study aims to identify unknown (zero-day
attacks) and known (well-known) attacks. So, the proposed model comprises
three stages. The first stage is preprocessing. The second stage involves the
application of AdaBoosting and Bagging methods by four different classifiers
modifying (i.e., Naïve Bayesian (NB), Support Vector Machine (SVM), random
forest (RF), and K_Nearest Neighbor (KNN)). Such a modification is performed
for the AdaBoosting methods. The AdaBoosting classifier is then combined to
work in the Bagging method. For attack recognition, uses the voting technique
as the third stage. Experimental results reveal that using the UNSW BN15
dataset yields testing with 85.49% accuracy, 99.96% detection rate, and 0.006
false alarm rate. Therefore, the proposed Hybrid AdaBoosting and Bagging
Method (HABBM) can outperform other comparable and state-of-the-art
techniques across a variety of parameters.

Computer worms execute damaging functions in the network
systems, compromising system security. Although researchers use a variety of
methods to detect worms and prevent their spread. Detecting worms remains a
challenge for the following reasons: First, a huge volume of irrelevant data
affects classification accuracy. Second, frequently used individual classifiers in
systems are poor at detecting all types of worms, Third, many systems are built
on out-of-date information, rendering them useless for new worm species. As a
result, providing a network intrusion detection system is vital for ensuring
security and reducing the harm caused by worms on networks to information
systems. The goal of the study is to discover computer worms in the computer
networks and protect the systems from their damages. The proposed method
uses the UNSW NB15 dataset to train and test the ensemble Ada boosting and
Bagging algorithms with the Support Vector Nachine (SVM) as a contribution
rather than a decision tree. Due to Correlation Feature Selection (CFS)
identifying relationships between features and classes, and Chi-square (Chi2)
determining whether features and classes are independent or not, we combined
these two algorithms as a contribution in a method called CFS&Chi2fs to select
the relevant features and reduce the time. The system achieved accuracy
reaching 0.998 with Bagging(SVM), and 0.989 with Ada boost(SVM).

Recently, the Internet of Things (IoT) is begin used in many fields
such as smart homes, healthcare systems, industrial applications, etc.
Therefore, the use of the IoT led to a growth in the number of dangers
especially in the areas of privacy and security for applications running on low-
resource computers. Consequently, the demand for lightweight encryption
methods is growing. To safeguard sensing data, this study introduces a
Lightweight Advanced Encryption Standard (LAES) depending on dynamic
ShiftRows, initial permutation instead of MixColumns, and a dynamic number
of rounds. It was created with the goal of reducing encryption/decryption time.
The proposed approach was assessed by using various measurements such as
lengths of the key used was 2128 and it is quite enough for security, key
sensitivity values were 100%, Also, this study compared the
encryption/decryption time, NIST statistical test, and security strength of the
proposed architecture to those of XTEA, SIMON, Skinny, SPECK, and
PRESENT. The encryption/decryption time of the proposed approach was had
the shortest period (0.0169 S) while the SPECK algorithm was had the longest
period (4.1249 S) among the comparative algorithms. Whereas, NIST statistical
test values of the proposed approach were passed successfully and had higher
values than the comparative algorithms. Moreover, the proposed approach
utilized 1280, 1024, and 768 GE with 6, 8, or 10 rounds respectively. The
average number of GE was approximately 1000 GE. These numbers of GE are
considered highly efficient with the IoT environment.

The control technique for an exoskeleton system for lower limb
rehabilitation is complicated, and numerous internal and external elements
must be taken into account, in addition to the uncertainties in the system model.
In this paper, through the analysis of the lower extremity exoskeleton is utilized
to obtain the corresponding equation and its linearized form. The nonlinear
differential equations have been linearized by using Jacobean’s method in order
to facilitate the controller design. Considering the interior and external factors
of the connecting rod, the uncertain elements are introduced and therefore the
optimal control technique is applied to regulate the system. An optimal state
feedback control strategy of Linear Quadratic Regulator (LQR), and LQR-Servo
have been implemented in this work. Finally, the physical parameters of the
Knee-Ankle Orthosis (KAO) exoskeleton are used, and the simulation results
show the advantage and applicability of the proposed controller’s design of the
Knee-Ankle orthosis system.

Crowd detection has various applications nowadays. However,
detecting humans in crowded circumstances is difficult because the features of
different objects conflict, making cross-state detection impossible. Detectors in the
overlapping zone may therefore overreact. The proposal uses the YOLO v5 (You
Only Look Once) method to improve crowd recognition and counting. This
algorithm is entirely accurate and detects things in real-time. The idea relies on
edge enhancement and pre-processing to solve overlapping feature regions in the
image and improve performance. The CrowdHuman data set is used to train YOLO
v5. The system counts the number of humans in the image to detect a crowd. Before
training, this model enhanced the image with several filters. The YOLO v5
algorithm distinguishes a person inside a crowd by utilizing the surrounding box
on the head and overall body. Therefore, the number of head detection is x-
coordinated compared to the body. Assume the detected heads outnumber the
bodies. A square of the head will be extracted, but not a body square. Also,
cropping the image reduces interference between human beings and enhances the
edge features. Thus, YOLOv5 can detect it. The idea improves head and body
detection by 2.17 and 4.1 percent, respectively.

Ease of access to digital images and the many images editing
programs available, like photoshop. All this makes the Issue of protecting
images against modification becomes essential. Some images contain crucial
information that can risk a patient's life, such as medical images and e-
government images that relate to citizen information and state or ministry
security. The watermark was one of the essential methods for this type of
protection, especially the fragile watermark, which is very sensitive to any
attack. Because of its other characteristics, it was one of the techniques that
proved its efficiency in detecting tampering and the authenticity of images—
also, watermarking focuses on protecting the image itself, not about protecting
the secret message. A fragile watermark is a watermarking which inserts some
information to cover an image to secure it .fragile watermarking could use in
such a way and implement in spatial or frequency domain or in both so, making
it a hybrid watermarking scheme. The Paper presented set of fragile watermark
techniques used by the researchers with the performance metrics of an
algorithm used in spatial and frequency domains, also showing how to use
artificial intelligence with a watermarking technique to protect Document
images from manipulation and forgery.