Article Per Year (5 Year)
p-Index From 2021 - 2026
0.768
P-Index
This Author published in this journals
All Journal TELKOMNIKA (Telecommunication Computing Electronics and Control) Bulletin of Electrical Engineering and Informatics Buletin Ilmiah Sarjana Teknik Elektro
Hoger K. Omar
University of Kirkuk
Computer Science & IT Electrical & Electronics Engineering

Published : 3 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 3 Documents
Search

 1 
Comparative analysis of the essential CPU scheduling algorithms Hoger K. Omar; Kamal H. Jihad; Shalau F. Hussein
Bulletin of Electrical Engineering and Informatics Vol 10, No 5: October 2021
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/eei.v10i5.2812

Abstract

CPU scheduling algorithms have a significant function in multiprogramming operating systems. When the CPU scheduling is effective a high rate of computation could be done correctly and also the system will maintain in a stable state. As well as, CPU scheduling algorithms are the main service in the operating systems that fulfill the maximum utilization of the CPU. This paper aims to compare the characteristics of the CPU scheduling algorithms towards which one is the best algorithm for gaining a higher CPU utilization. The comparison has been done between ten scheduling algorithms with presenting different parameters, such as performance, algorithm’s complexity, algorithm’s problem, average waiting times, algorithm’s advantages-disadvantages, allocation way, etc. The main purpose of the article is to analyze the CPU scheduler in such a way that suits the scheduling goals. However, knowing the algorithm type which is most suitable for a particular situation by showing its full properties.
A Novel Slang and Formal Text Classification with Data Exploration and Optimized Deep Learning Models Hoger K. Omar
Buletin Ilmiah Sarjana Teknik Elektro Vol. 8 No. 3 (2026): June
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12928/biste.v8i3.14373

Abstract

Automated text classification involves applying artificial intelligence algorithms to classify text documents into predefined categories. Hence, developing a high-accuracy text categorization model is a significant task, especially in unstructured narratives such as research papers, medical documents, and news articles. This study examines the application of an artificial neural network (ANN) algorithm for categorizing formal and slang English language with the capabilities of popular deep learning frameworks such as TensorFlow and Keras. First of all, the dataset's features were examined through exploratory data analysis (EDA) methods to enhance understanding. Furthermore, the study emphasizes the use of several preprocessing techniques to address the challenge presented by the informal writing style. In addition, adding a list of common English abbreviations greatly improved the accuracy and effectiveness of classifying text. Lastly, the work involves using multiple hyperparameter optimization approaches for further enhancement. The proposed techniques effectively mitigated the impact of heterogeneous and noisy data in both formal and informal language by achieving an improvement of approximately 10% in overall classification accuracy. Additionally, the study contributes to an advancement in the field of text mining and offers practical guidance for optimizing deep learning models in the domain of English text categorization.
Big data cloud-based recommendation system using NLP techniques with machine and deep learning Hoger K. Omar; Mondher Frikha; Alaa Khalil Jumaa
TELKOMNIKA (Telecommunication Computing Electronics and Control) Vol 21, No 5: October 2023
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12928/telkomnika.v21i5.24889

Abstract

Recommendation systems (RS) are crucial for social networking sites. Without it, finding precise products is harder. However, existing systems lack adequate efficiency, especially with big data. This paper presents a prototype cloud-based recommendation system for processing big data. The proposed work is implemented by utilizing the matrix factorization method with three approaches. In the first approach, singular value decomposition (SVD) is used, which is an old and traditional recommendation technique. The second recommendation approach is fine-tuned using the alternating least squares (ALS) algorithm with Apache Spark. Finally, the deep neural network (DNN) algorithm is utilized with TensorFlow. This study solves the challenge of handling large-scale datasets in the collaborative filtering (CF) technique after tuning the algorithms by adjusting the parameters in the second approach, which uses machine learning, as well as in the third approach, which uses deep learning. Furthermore, the results of these two approaches outperformed conventional techniques and achieved an acceptable computational time. The dataset size is about 1.5 GB and it is collected from the Goodreads website API. Moreover, the Hadoop distributed file system (HDFS) is used as cloud storage instead of the computer’s local disk for handling larger dataset sizes in the future.
Co-Authors Alaa Khalil Jumaa Kamal H. Jihad Mondher Frikha Shalau F. Hussein