Dijlah Journal of Engineering Sciences

Machine learning techniques play an increasingly prominent role in medical diagnosis. With the use of these techniques, patients’ data can be analyzed to find patterns or facts that are difficult to explain, making diagnoses more reliable and convenient. The purpose of this research was to compare the efficiency of diabetic classification models using four machine learning techniques: decision trees, random forests, support vector machines, and K-nearest neighbors. In addition, new diabetic classification models are proposed that incorporate hyper parameter tuning and the addition of some interaction terms into the models. These models were evaluated based on accuracy, precision, recall, and the F1-score. The results of this study show that the proposed models with interaction terms have better classification performance than those without interaction terms for all four machine learning techniques. Among the proposed models with interaction terms, random forest classifiers had the best performance, with 97.5% accuracy. The findings from this study can be further developed into a program that can effectively screen potential diabetes patients

This paper presents the face recognition techniques under c-sharp
language that used to simulate the proposed design to use several
applications in attendance management systems and security
systems. A time period is settled for taking the attendance and after
completion of time period attendance will directly stores into storage
device mechanically without any human intervention. A message
will send to absent student parent mobile using GSM technology.
For avoiding the sheet problem, we used face recognition techniques
technology. The input image goes through the recognition system for
facial identification. In some cases where the input image from the
web-cam does not exist in the database, the user will get some error.
However, in cases where the image exists in the database, that image
will be computed for similarity measurement using distance between
control point measures from the input image. The result of our
experiment indicates that the recognition process of number of
images in the database and some images from the web-cam provides
100% accuracy in terms of recognition. This system is most
effective, easy and less time taken for tracking attendance in
organizations with period wise without any human intervention.
Keywords- Attendance System, Face Recognition, GSM

Nowadays the implementation of a cryptographic system based on
traditional means is a late topic due to the development and
multiplicity of detection methods, intrusion and hacking. Therefore, it
is necessary to resort to more modern methods, such as the use of
programmed digital electronic circuits like Field Programmable Gate
Arrays (FPGAs). The objective of this paper is to design substitution
box (S-Box) for Data Encryption Standard (DES) using Very High
Speed Hardware Description Language (VHDL). As a result, S-box
VHDL code was designed and written then by using the capabilities of
the Xilinx Design Suite ISE the design was checked, analyzed,
simulated and then a file called bit stream will be generated. The
resulting file was downloaded to the FPGA circuit and the equivalent
physical digital circuit representing the S-box was obtained.

0rganic dye is a major industrial pollutant and needs innovative methods to
clear it. Zinc oxide (ZnO) is an attractive material for photo catalytic
degradation of organic dyes. In this paper, the photo catalytic activity of
ZnO nanoparticles (ZnO NPs) synthesized using chemical bath deposition
(CBD) and laser-assisted chemical bath deposition (LACBD) are studied.
Field Emission Scanning Electron Microscopy (FESEM) showed that ZnO
NPs synthesized using LACBD obtained a more packed structure,
resembling Nano sheets. This translates to a larger specific exposed area.
Energy Dispersive X-ray (EDX) study shows ZnO NPs synthesized using
the LACBD method exhibited a Zn:O ratio closer to 1:1, suggesting an
adequate concentration of oxygen vacancies, which are crucial for photo
catalytic degradation. For the photo catalyst degradation measurement, ZnO
NPs are utilized as catalysts in water degradation applications, where 0.01 g
of ZnO was added to 50 mL of 20 ppm methylene orange solution. The
concentration of methylene orange solution was studied using UV-Vis
measurements during photo catalyst degradation. ZnO NPs synthesized
using LACBD exhibited the highest photo catalytic degradation performance
under UV light, with the highest degradation rate constant, k, of 0.02521
min-1 and 71% photo degradation efficiency within 30 minutes.

Sidewalks are one of the structural components of urban space and
can be defined as paved strips meant to help people move from one
part of a city to another on foot· Sidewalks are a component of the
urban layout and fulfill the need for infrastructure combined with the
visual aspect of the urban area·
This work exposes the guidelines of integrated sidewalk design to
understand how or if they coordinate concerning surface aesthetics
and infrastructural requirements· It is also noteworthy that city
planning regulations also have a role in this design to provide
sidewalks not only for their functionality and stability, but also to
esthetically appeal to the city·
Attention to the design of the sidewalks in terms of the materials
used, the textures on the sidewalks and designing the sidewalks will
help in coming up with a better experience for the pedestrians and as
well blend the sidewalks with the rest of the urban fabric·
Besides that, it is necessary to define what structures such structures
as the necessary components for sidewalks’ function, safety, and
accessibility are the requirements exigent for the structure of the
pedestrian network·
Based on the works of various cities learning on the provision of
integrated sidewalk designs, this paper seeks to establish lessons that
policy makers and planners could learn and log from as they plan for
future projects of integrated sidewalk designs while trying to achieve
aesthetics and functionality·
Furthermore, future studies on trends involving conceptual
progresses of sidewalks design and futuristic embarked technologies,
plus activism of sustainability will be useful in extending knowledge
on probable requirements in the upcoming urban sidewalks design in
the progressive urban environment.

Data has become a consumer asset in the digital age, requiring innovative
solutions for storage, processing and analysis. Cloud computing has emerged
as a transformative technology that enables organizations to better manage
large amounts of data and improve business flexibility by reducing costs
This paper presents case studies of intelligent business applications (IBAs)
such as customers relationship management (CRM) and enterprise resource
management (ERP) systems -Examine how they improve data management
Studies show that cloud integration gives organizations real-time data
access, scalability, and advanced analytics capabilities, and enables them
enable faster and more accurate decision-making Despite the obvious
benefits, challenges remain such as data protection, privacy, and compliance
with regulations such as the GDPR and CCPA. This study identifies these
challenges and proposes solutions, including improved encryption, access
control, and hybrid cloud models. The findings suggest that future advances
in cloud technologies such as AI, blockchain, and edge computing will
further increase the efficiency, security, and scalability of cloud-based
enterprise data.

This paper presents the design of power stage voltage control model under
digital feedback compensator. The power high performance electronic
system has to maintain stable voltage supply even though rapid change in
power consumption in the load terminals. Hence, the efficient transfer
function parameters selection of digital control system in the power stage
converter is the most important in practices. To provide effective
suppression in the output voltage corresponding to fast load change, correct
feedback circuit with powerful transfer function has been suggested in this
work. Close to output tracking of reference sinusoidal voltage is achieved by
proposed techniques with fast rejection to sudden load variation.
Furthermore, the obtained control system is robust against to reservations in
the input DC voltage. The model is tested and evaluated under different
performance in both transient operation and steady state requirements.

This article aims to investigate the effects of heat transfer analysis, Ree
Eyring fluid concentration, magnetic field, porous media, and MHD on the
peristaltic transport of Ree-Eyring fluid in a rotating frame within a
symmetric channel that experiences triangular and square boundary in three
dimensions. The governing equations are written, which are continuity,
motion, heat, and concentration equations with help of conservation of mass,
Newton\'s second law, and conservation of energy, respectively. We then
simplified the equations using the long wave length hypothesis and the
Renold number approximation. This approximation led to the development
of nonlinear differential equations. The exact solution of the Ree-Eyring
particle concentration, temperature, velocity, and stream function are
calculated. Using the MATHMETICA program, we have graphically
clarified the flow quantities for different parameters. We have also
graphically explained the trapping phenomenon. In this analysis, we
observed that highlighting the concentration of fluid leads to a decrease in
axial velocity and secondary velocity. The increase in the magnetic field
resulted in an increase in axial velocity, but a decrease in secondary velocity.
We observed an increase in trapping phenomena as the concentration of
fluid increase and it decrease as the magnetic field increase.

The incorporation of technology into our everyday lives and
medium-sized corporations has become obvious, as most businesses
cannot operate without the use of technology. This has resulted in
weaknesses and shortcomings in security. The layered protocol
model of Open System Interconnection (OSI) divides networking
duties into layers and specifies a collection of offerings for each
component to be offered separately. The protocol\'s design allows
services to be realized for various levels; however, no direct
communication between nonadjacent layers is allowed because the
architecture prohibits such an action; communication is also
restricted to carrying out calls and replies between adjacent layers.
The smart grid\'s expansion of distributed energy resources is
increasing, causing solar distribution to extend network attack
surfaces. As a result, there is a mismatch between implementation
and adequate knowledge of security in communication needs.
Nowadays, the literature lacks protocol level susceptibility, solution
map, and assaults to all layers in the logic model, as in Open
Systems Interconnection (OSI) stacks inside vendors sporting
proprietary approaches to mitigate attack host. This paper examines
the primary vulnerability, viable remedy, and attack level of wind
and solar protocol. As a result, our study provides a starting point for
vendors, utilities, aggregators, and new manufacturing investors to
develop a basic understanding of the safety problem, which is a
prerequisite for understanding securities requirements.

Network traffic classification is crucial for network security and
management. Traditional methods often struggle with accuracy and
scalability. This paper proposes a deep learning-based approach to
classify various data types traversing a network. By leveraging the
powerful feature extraction capabilities of deep neural networks, we
aim to improve classification accuracy and adaptability to evolving
network traffic patterns. We explore the application of convolutional
neural networks (CNNs) to capture both spatial and temporal
dependencies within network packets. Experimental results
demonstrate the effectiveness of our proposed method in accurately
classifying different data types, surpassing traditional techniques in
terms of precision, recall, and overall accuracy.
Our CNN model is designed to capture the underlying patterns and
characteristics of network traffic. By processing raw traffic data as
images, the model can learn to identify distinctive features that
differentiate various traffic types.

Traffic classification is a fundamental task in network anomaly
detection and intrusion prevention systems. By accurately identifying
the types of traffic traversing a network, security professionals can
detect and mitigate various threats, such as malicious attacks,
unauthorized access, and network congestion. Traditional methods of
traffic classification often rely on handcrafted features, which can be
time-consuming and prone to errors.
In this research, we present a novel approach that leverages artificial
intelligence to streamline and improve the process of traffic
classification. Specifically, we propose a convolutional neural
network (CNN) model that directly processes raw traffic data as
images. This eliminates the need for manual feature extraction,
which can be a laborious and error-prone task.
Our CNN model is designed to capture the underlying patterns and
characteristics of network traffic. By processing raw traffic data as
images, the model can learn to identify distinctive features that
differentiate various traffic types.

The effect of treatments on leaf area, the Salcylic + Tricoderma treatment
gave the highest leaf area of 206.20 cm2, and the Bacllis subtulas treatment
gave the lowest leaf area of 147.07 cm2 compared to the contaminated
comparison, which gave a leaf area of 113.46 cm2 compared to the healthy
comparison, which gave a leaf area of 218.70 cm2. As for the effect of
treatments on plant length, the healthy comparison treatment gave the
highest plant length of 186.16 cm, followed by the Salcylic + Tricoderma
treatment, which gave a plant length of 178.00 cm compared to the
contaminated comparison treatment, which gave the lowest plant length of
115.50. As for the effect of treatments and fungi on the fresh green weight,
the healthy Control treatment gave the highest fresh green weight of 976 g,
followed by the Salcylic + Tricoderma treatment, which gave a fresh green
weight of 930 g compared to With the control treatment, the pollutant gave
the lowest fresh green weight of 576.33 g.