Muath Jarrah

Muath Jarrah

Auto-generated profile, based on publicly available information

Muath Jarrah

Skyline University College

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
4 February 2023 in ACM Transactions on Sensor Networks
Verified
Journal Article
Open access
AAAhmed Abu-Khadrah
Ahmed Abu-Khadrah
AAAli Mohd Ali
Ali Mohd Ali
MJMuath Jarrah
Muath Jarrah
Communications and Computer Engineering Department, Faculty of Engineering, Al-Ahliyya Amman University, Amman 19328, Jordan School of Information Technology, Skyline University, Sharjah, 1797, UAE Smart Sensors are used for monitoring, sensing, and actuating controls in small and large-scale agricultural plots. From soil features to crop health and climatic observations, the smart sensors integrate with sophisticated technologies such as the Internet of Things or cloud for decentralized processing and global actuation. Considering this integration, an Amendable Multi-Function Sensor Control (AMFSC) is introduced in this proposal. This proposed method focuses on sensor operations that aid agricultural production improvements. The agriculture hindering features from the soil, temperature, and crop infections are sensed and response is actuated based on controlled operations. The control operations are performed according to the sensor control validation and modified control acute sensor, which helps to maximize productivity. The sensor control and operations are determined using federated learning from the accumulated data in the previous sensing intervals. This learning validates the current sensor data with the optimal data stored for different crops and environmental factors in the past. Depending on the computed, sensed, and optimal (adaptable) data, the sensor operation for actuation is modified. This modification is recommended for crop and agriculture development to maximize agricultural productivity. In particular, the sensing and actuation operations of the smart sensors for different intervals are modified to maximize production and adaptability. The efficiency of the system was evaluated using different parameters and the system maximizes the analysis rate (12.52%), control rate (7%), adaptability (9.65%) and minimizes the analysis time (7.12%), and actuation lag (8.97%)

22 February 2020 in The Journal of Supercomputing
Verified
Journal Article
Closed access
PDF file
MJMuath Ibrahim Jarrah
Muath Ibrahim Jarrah
AJA. S. M. Jaya
A. S. M. Jaya
ZAZakaria N. Alqattan
Zakaria N. Alqattan
Mohd Asyadi AzamMohd Asyadi Azam
Mohd Asyadi Azam
RARosni Abdullah
Rosni Abdullah
AAAhmed Ismail Abu-Khadrah
Ahmed Ismail Abu-Khadrah

17 May 2019
Verified
Book Chapter
Closed access
PDF file
MJM. I. M. Jarrah
M. I. M. Jarrah
AJA. S. M. Jaya
A. S. M. Jaya
Mohd Asyadi AzamMohd Asyadi Azam
Mohd Asyadi Azam
ZAZakaria N. Alqattan
Zakaria N. Alqattan
MMMohd Razali Muhamad
Mohd Razali Muhamad
RARosni Abdullah
Rosni Abdullah

27 September 2018 in AIP Conference Proceedings
Verified
Conference Paper
Closed access
PDF file
MJM. I. Jarrah
M. I. Jarrah
AJA. S. M. Jaya
A. S. M. Jaya
Mohd Asyadi AzamMohd Asyadi Azam
Mohd Asyadi Azam
MMM. R. Muhamad
M. R. Muhamad
HAH. Akbar
H. Akbar
Optimization of coating parameters is important in the machining process, as an optimized coating layer enhances efficient machining result by providing high wear resistance, saving time and effort, reducing cost, increasing productivity and leading to extend tool life for better surface finish. In terms of tool wear resistance, tools with suitable film coating are forty times better than uncoated tools. Cutting tools are usually coated by Titanium Nitride (TiN), since it has properties such as resistance to wear and hardness resulting in increased cutting performance. Genetic algorithms (GAs) belong to the powerful artificial intelligence optimization family of evolutionary algorithm-based metaheuristic techniques. Since their inception, they have been successfully applied in numerous areas of industrial sectors as material design, tools coating and cutting, alloy design, and so on. In this research work, predicting thin film coating thickness of titanium nitride (TiN) on tungsten carbide (WC) inserts is presented. First, (WC) inserts were coated by TiN in different conditions using Physical Vapor Deposition (PVD), and the surface profilometer was used to measure thickness of the WC coated specimens. Second, Response Surface Methodology (RSM) was used to generate the objective function which represents the process parameters and coating thickness. Third, using a fitness function model, GAs were established to optimize the thickness value of TiN layer with respect to changes in three process parameters, namely Nitrogen gas pressure (N2), Argon gas pressure (Ar), and Turntable Speed (TT). Finally, for performance measurement, three real experimental tests were carried out in terms of Prediction Interval (PI) and Residual Error (e) to validate the RSM model. The actual coating thickness of validation data fell within the 95% (PI) and the (e) values percentage were very low. In terms of optimization, GAs is capable optimizing thickness better than the average experimental value, with a reduction ratio of 73.4%.

1 August 2025 in International Journal of Electrical and Computer Engineering (IJECE)
Verified
Journal Article
Open access
PDF file
AAAhmed Abu-Khadrah
Ahmed Abu-Khadrah
SASahar Al-Washmi
Sahar Al-Washmi
AAAli Mohd Ali
Ali Mohd Ali
MJMuath Jarrah
Muath Jarrah
Cybercrime covers a wide array of illegal online activities such as hacking and identity theft, while cyber fraud specifically involves deceptive practices like phishing and fraudulent financial transactions. The rise in technology and digital communication has exacerbated cyber fraud. Although prevention technologies are advancing, fraudsters continually adapt, making effective detection methods essential for identifying and addressing fraud when prevention fails. The proposed model aims to reduce online fraud through new detection algorithms. It utilizes statistical and machine learning techniques, including logistic regression, random forest, and naïve Bayes, to identify non-transactional fraud behaviors. By analyzing a meticulously collected and fine-tuned dataset, the study enhances detection capabilities beyond traditional transaction-focused approaches. The algorithms monitor user interactions and device characteristics to create profiles of normal behaviors and detect deviations indicative of fraud. The evaluation of proposed model showed 100% accuracy. A unified model incorporating all decision-making processes was used, leading to a voting phase and accuracy assessment. This approach consolidates multiple algorithms into a single framework, proving highly effective for comprehensive fraud detection. The research demonstrates the value of integrating machine learning techniques with real-world data to advance fraud detection and emphasizes the importance of continual adaptation to address evolving cyber threats.

1 August 2025 in Indonesian Journal of Electrical Engineering and Computer Science
Verified
Journal Article
Open access
PDF file
AAAhmed Abu-Khadrah
Ahmed Abu-Khadrah
SAShayma Alkhamis
Shayma Alkhamis
AAAli Mohd Ali
Ali Mohd Ali
MJMuath Jarrah
Muath Jarrah
Malicious URLs are web addresses purposely generated for a user’s detriment. Some examples include phishing scams in which the victim is fooled into logging into a fake site or portals for downloading malware where any click on a link invites a hostile program to the user’s device. The damage done to an individual’s finances, confidential information, and even reputation due to malicious URLs makes it crucial to devise means of countering these threats. This can be achieved by creating an intelligent model that identifies suspicious characteristics common to these websites. The objective of this research is to design a novel hybrid machine learning algorithm-based model for detecting malicious websites. A random forest, decision tree, and extreme gradient boosting (XGBoost) are the three hybrid classification algorithms proposed for the study. Accuracy in detection will help prevent and reduce the effects of such websites. The accuracy rate in this research is 98.7%, precision is at 98.9%, and recall at 98.5%. With these results, it follows that the hybrid model is more effective than training any individual algorithm with the given dataset.