Iraqi Journal for Computer Science and Mathematics

This work presents a novel approach to enhancing the rate of occurrence of non-homogeneous
Poisson processes (NHPP) by utilizing the Gompertz distribution as the rate of occurrence. The primary objective
of this study is to determine the parameters of the new process using both traditional methods and intelligent
technology, specifically particle swarm optimization (PSO). Additionally, the study aims to estimate the reliability
function of the process. The suggested model is simulated to achieve these goals, and the results are compared
among various estimation techniques to identify the most accurate estimator. The study demonstrates that when
predicting the time rate of occurrence of the proposed Gompertz process and its reliability function, the PSO
algorithm outperforms other approaches. Furthermore, this research showcases a practical application utilizing real
data from the Mosul power facility. Specifically, the data pertains to the stoppage times of two consecutive units of
the Mosul Dam power stations from January 1st, 2021 to January 1st, 2022. Overall, this study introduces a novel
process based on the Gompertz distribution to improve the rate of occurrence of NHPP. It employs particle swarm
optimization to calculate the process parameters and estimate the reliability function. The superiority of the PSO
algorithm is demonstrated through comprehensive comparisons. The practical application using data from the
Mosul power facility further validates the effectiveness of the proposed approach.

Bug bounty schemes make use of outside ethical hackers to find and fix a variety of security flaws, guaranteeing
quicker and more affordable problem solving. Better confidence in and image of the company in the cybersecurity
space, faster solving issues, and increased community collaboration are some of its results. Computer vision relies on
face detection, which has several uses. This article uses convolutional neural networks (CNNs) and an error reward
algorithm in the facial recognition simulation library to enhance face detection. Trainers trained CNNs to detect faces
from other visual components and extract human facial traits, making them powerful facial identification tools. These
networks classify and extract face characteristics automatically, obtaining approaching 100% identification rates.
CNNs have greater identification rates and easier face-image extraction than earlier methods. Network architecture
determines its performance, transcending machine learning methodologies. This article suggests a bug reward scheme
to discover and resolve bugs in the face recognition library. The program has helped Google find flaws in its
intelligent systems, including model manipulation and adversarial assaults. These activities enhance AI safety and
security studies, highlight possible concerns, and promote AI safety. CNN-based facial recognition models enhance
accuracy and offer advantages over previous approaches. The CNN-based method and Bug Bounty software
improved the facial recognition library.

The crucial role of information technology (IT) in operating and managing industrial systems is widely recognized, and Iraq's IT capabilities hold great promise for its industrial and other economic sectors. The demand for IT services has risen considerably, particularly for oil and gas companies, which face the challenge of boosting capital asset returns while ensuring safety and sustainability. They need to manage rising demands as well as competition for access to oil reserves while driving improved asset reliability, productivity, and performance.

This application show how information technology is used in the petroleum industry. It specifically examines information technology applications in the upstream, midstream, and downstream important segments of the petroleum industry during the drilling process. The increased price volatility's noteworthy effect on the profitability of the energy industry is just one of the current supply chain management challenges. Better supply chain management aids in lowering operational costs, a challenge that many businesses are under demand to address right away. The study's theoretical and practical value is in exposing the characteristics and issues with the infrastructure supporting the Iraqi oil industry and in creating a control algorithm for the evolution of its Regular visual inspections of pipelines, offshore oil rigs, and other infrastructure may be carried out swiftly and safely thanks to technology. Light devices that enable temperature checks using infrared scanning are available in modern applications. Hazards like poisonous substances can be identified by other sensors from a safe distance. Enhancing oil and gas safety with artificial intelligence technologies protects the environment and ensures worker safety

Wireless Body Area Networks (WBANs) have risen as a promising innovation for checking human
physiological parameters in real time. Be that as it may, the unwavering quality and precision of WBANs depend
on the right working of sensor hubs. The distinguishing proof of defective sensor hubs is vital for guaranteeing the
quality of information collected by WBANs. In this paper, we propose a novel approach to recognizing faulty
sensor hubs in WBAN employing a hereditarily linked artificial neural organize (GLANN). The GLANN is
prepared to employ a crossbreed fuzzy-genetic calculation to optimize its execution in distinguishing defective
sensor hubs. The proposed approach is assessed employing a dataset collected from a real-world WBAN. The
comes about appears that the GLANN-based approach beats existing strategies in terms of exactness and
proficiency. The proposed approach has potential applications within the field of healthcare, where exact and solid
observing of human physiological parameters is basic for conclusion and treatment. By and large, this ponder
presents a promising approach to progressing the unwavering quality and exactness of WBANs by identifying
flawed sensor hubs utilizing GLANN .

The present article focuses on the analytical approach using fractional orders and its application
in the dynamics of physical processes. Fractional order models align better with experimental data compared to
non-fractional ones. This study primarily focuses on employing the new approximate analytical method to solve
shallow water models with fractional orders. Numerical examples within the Caputo fractional derivative showcase
the method’s application. Results for both integer and fractional orders are graphically depicted, demonstrating the
fractional solutions’ closeness to actual data. Analysis of 3D and 2D fractional order graphs reveals convergence
toward integer order graphs as fractional derivatives approach non-fractional ones. This method shows promise for
direct application in solving targeted problems and can be easily adapted for other fractional nature problems.

The rapid growth of social media platforms has led to an increase in hate speech. This has prompted
the development of effective detection mechanisms that aim to mitigate the potential hazards and threats it poses to
society. BERT (Bidirectional Encoder Representations from Transformers) has produced cutting-edge results in
this field. This review paper aims to identify and analyze the whole process of using the BERT model to tackle the
challenges associated with the hate speech detection problem. This academic discussion will begin by addressing
the training datasets and the preprocessing methods involved. Subsequently, the use of the BERT model will be
explored, followed by an examination of the contributions made to address the issues encountered. Finally, we will
discuss the evaluation phase. The use of BERT included the application of two primary approaches. In the featurebased approach, BERT accepts textual input and generates its corresponding representation as output. The resulting
output is then used as input for any classification model. The second approach involves the process of fine-tuning
BERT using labeled datasets and then employing it directly for classification purposes. The controversial issues
and open challenges that appeared at each stage were discussed. The results indicate that in both approaches,
BERT has shown its efficacy relative to other models under contention. However, there is a need for greater
attention and advancement to effectively solve the existing issues and constraints in the future.

In this article, a projection type two step inertial iterative scheme for investigating set-valued quasi
variational inequality in real Banach spaces is designed. We manifest the existence result and verified by an illustrative
example. Also, we estimate the approximate solution of a set-valued quasi variational inequality by analyzing the
convergence of the proposed inertial iterative algorithm. Further, an extended Weiner-Hopf equation is considered
and substantiated that it is analogous to the extended set-valued quasi variational inequality. Finally, we investigate
the extended Weiner-Hopf equation by analyzing the convergence of the composed iterative scheme.

Consider a left J-module I. The present study introduces the conception of rad-Quasi- Prime submodule, that serves as a dual popularization of both Quasi-Prime submodules and primary submodules. An apposite submodule A of an J-module named as rad- Quasi Prime if for all and with implies that either or . Numerous facts and characterizations that concerning are acquired.

Lie detection has gained importance and is now extremely significant in a variety of fields. It plays
an important role in several domains, including law enforcement, criminal investigations, national security,
workplace ethics, and personal relationships. As advances in lie detection continue to develop, real-time
approaches such as voice stress technology have emerged as a feasible alternative to traditional methods such as
polygraph testing. Polygraph testing, a historical and generally established approach, may be enhanced or replaced
by these revolutionary real-time techniques. Traditional lie detection procedures, such as polygraph testing, have
been challenged for their lack of reliability and validity. Newer techniques, such as brain imaging and machine
learning, might offer better outcomes, although they are still in their early phases and require additional testing.
This project intends to explore a deception-detection module based on sophisticated speech-stress analysis
techniques that might be applied in a real-time deception system. The purpose is to study stress and other
articulation cues in voice patterns, to establish their precision and reliability in detecting deceit, by building upon
previous knowledge and applying state-of-the-art architecture. The performance and accuracy of the system and its
audio aspects will be thoroughly analyzed. The ultimate purpose is to contribute to the advancement of more
accurate and reliable lie-detection systems, by addressing the limitations of old techniques and proposing practical
solutions for varied applications. This paper proposes an efficient feature-selection strategy, which uses random
forest (RF) to select only the significant features for training when a real-life trial dataset consisting of audio files
is employed. Next, utilizing the RF as a classifier, an accuracy of 88% is reached through comprehensive
evaluation, thereby confirming its reliability and precision for lie-detection in real-time scenarios.

The Internet of Things (IoT) has cultivated a promising environment, pivotal across diverse sectors
via MANET protocols within the w.w.w. This technology significantly contributes to advanced services for mobile
devices in the MANET-IoT domain. However, MANET encounters security challenges, notably malicious attacks
as a prime concern. To counter these threats, preventive measures like subjective-context evaluation and node
protection are employed, ensuring data packet integrity before delivery. This study aims to enhance the
performance of a novel reactive protocol, integrated with a fuzzy system within the MANET-IoT environment. The
methodology is implemented in two directions: 1) Establishing a secure network founded on trust parameters and
shortest path selection. 2) Incorporating an integrated fuzzy system into an improved reactive routing protocol
within the MANET environment. Subjective context ensures a secure milieu, evaluating nodes before packet
delivery based on trust and shortest path. The fuzzy system\'s rules determine the network\'s probability distribution,
contingent upon trust and the number of hop counts. The proposed routing protocol is evaluated both pre- and postattacks during packet transmission. Results demonstrate its superiority in packet transmission over the original
protocol. Three scenarios evaluate packet delivery fraction (PDF), end-to-end delay (E2E), and normalized routing
load (NRL). FS-AODV\'s percentages were 0.9873% against AODV\'s 1.9871% without drop) and 0.8419% with a
drop for PDF. FS-AODV\'s percentages stood at 0.0006% against AODV\'s 0.0007% without a drop and 0.0005%
with a drop for E2E. In contrast, FS-AODV\'s percentage was 0.058%, AODV at 0.0127% without a drop, and
0.066% with a drop for NRL.

Optimization algorithms exist to find solutions to various problems and then find out the optimal solutions. These algorithms are designed to reach desired goals with high accuracy and low error, as well as improve performance in various fields, including machine learning, operations research, physics, chemistry, and engineering. As technology continues to advance, optimization algorithms are increasingly needed to address complex real-world challenges and drive innovation across all disciplines. Quantitative leaps have been achieved in improving the efficiency of optimization algorithms through the diversity of sources of information feeding these algorithms according to the type of optimization problem, based on scientific and organized foundations. The objectives of this paper are to discuss the most important optimization algorithms, classify the scientific fields involved in their application, and optimize problems involved in this regard, in addition to providing a brief overview for comparison among these algorithms.

The novelty of this article is estimating the parameters of Weibull inverted exponential (WIE)
distribution with a constant stress partially accelerated life test (PALT) under adaptive type-II progressively
censored samples. Moreover, the maximum likelihood estimators (MLEs), their asymptotic variances confidence
intervals, and Bayes estimators (BEs) of the model parameters and the acceleration factor are obtained.
Furthermore, the approximate bootstrap and credible confidence intervals of the estimators are acquired. The
accuracy of the MLEs and BEs for the model parameters and the acceleration factor is investigated through the
simulation studies.