Article Per Year (5 Year)
p-Index From 2021 - 2026
3.847
P-Index
This Author published in this journals
All Journal Jurnal Teknoinfo JISA (Jurnal Informatika dan Sains) International Journal of Informatics, Information System and Computer Engineering (INJIISCOM) International Journal of Research and Applied Technology (INJURATECH) The Indonesian Journal of Computer Science
Abdulazeez, Adnan Mohsin
Unknown Affiliation
Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Electrical & Electronics Engineering Engineering Industrial & Manufacturing Engineering Mechanical Engineering

Published : 31 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 31 Documents
Search

 1   2   3   4 
Detection of Hate-Speech Tweets Based on Deep Learning: A Review Miran, Ara Zozan; Abdulazeez, Adnan Mohsin
JISA(Jurnal Informatika dan Sains) Vol 6, No 2 (2023): JISA(Jurnal Informatika dan Sains)
Publisher : Universitas Trilogi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31326/jisa.v6i2.1813

Abstract

Cybercrime, cyberbullying, and hate speech have all increased in conjunction with the use of the internet and social media. The scope of hate speech knows no bounds or organizational or individual boundaries. This disorder affects many people in diverse ways. It can be harsh, offensive, or discriminating depending on the target's gender, race, political opinions, religious intolerance, nationality, human color, disability, ethnicity, sexual orientation, or status as an immigrant. Authorities and academics are investigating new methods for identifying hate speech on social media platforms like Facebook and Twitter. This study adds to the ongoing discussion about creating safer digital spaces while balancing limiting hate speech and protecting freedom of speech.   Partnerships between researchers, platform developers, and communities are crucial in creating efficient and ethical content moderation systems on Twitter and other social media sites. For this reason, multiple methodologies, models, and algorithms are employed. This study presents a thorough analysis of hate speech in numerous research publications. Each article has been thoroughly examined, including evaluating the algorithms or methodologies used, databases, classification techniques, and the findings achieved.   In addition, comprehensive discussions were held on all the examined papers, explicitly focusing on consuming deep learning techniques to detect hate speech.
Network Intrusion Detection Based on Machine Learning Classification Algorithms: A Review Younis, Aqeel Hanash; Abdulazeez, Adnan Mohsin
JISA(Jurnal Informatika dan Sains) Vol 7, No 1 (2024): JISA(Jurnal Informatika dan Sains)
Publisher : Universitas Trilogi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31326/jisa.v7i1.2056

Abstract

The worldwide internet continues to spread, presenting numerous escalating hazards with significant potential. Existing static detection systems necessitate frequent updates to signature-based databases and solely detect known malicious threats. Efforts are currently being made to develop network intrusion detection systems that can utilize machine learning techniques to accurately detect and classify hazardous content. This would result in a decrease in the overall workload required. Network Intrusion Detection Systems are created with a diverse range of machine learning algorithms. The objective of the review is to provide a comprehensive overview of the existing machine learning-based intrusion detection systems, with the aim of assisting those involved in the development of network intrusion detection systems.
Empowering Diagnosis: A Review On Deep Learning Applications for COVID-19 and Pneumonia in X-Ray Images Yaqoub, Karin Younis; Abdulazeez, Adnan Mohsin
JISA(Jurnal Informatika dan Sains) Vol 7, No 1 (2024): JISA(Jurnal Informatika dan Sains)
Publisher : Universitas Trilogi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31326/jisa.v7i1.2024

Abstract

The emergence of COVID-19, a highly contagious virus capable of infecting both the upper and lower respiratory tracts, has led to one of the deadliest pandemics in modern history, claiming millions of lives worldwide. Early and accurate detection of this rapidly spreading disease is crucial for effective containment and saving lives. Chest X-ray (CXR) stands out as a promising diagnostic tool due to its accessibility, affordability, and long-term sample preservation. However, distinguishing COVID-19 pneumonia from other respiratory ailments poses a significant challenge. This article delves into various approaches utilized for COVID-19 detection and the hurdles encountered in this endeavor. The imperative for developing automated detection systems to mitigate virus transmission via contact is underscored. Notably, deep learning architectures such as ResNet, Inception and Googlenet have been deployed for COVID-19 detection, albeit with a focus on identifying pneumonia cases. Discriminating between COVID-19-induced pneumonia and pneumonia caused by other pathogens remains a formidable task, demanding innovative solutions for accurate and timely diagnosis.
Face Emotion Recognition Based on Machine Learning: A Review Abdulazeez, Adnan Mohsin; Ageed, Zainab Salih
International Journal of Informatics, Information System and Computer Engineering (INJIISCOM) Vol. 5 No. 1 (2024): INJIISCOM: VOLUME 5, ISSUE 1, JUNE 2024
Publisher : Universitas Komputer Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34010/injiiscom.v5i1.12145

Abstract

Computers can now detect, understand, and evaluate emotions thanks to recent developments in machine learning and information fusion. Researchers across various sectors are increasingly intrigued by emotion identification, utilizing facial expressions, words, body language, and posture as means of discerning an individual's emotions. Nevertheless, the effectiveness of the first three methods may be limited, as individuals can consciously or unconsciously suppress their true feelings. This article explores various feature extraction techniques, encompassing the development of machine learning classifiers like k-nearest neighbour, naive Bayesian, support vector machine, and random forest, in accordance with the established standard for emotion recognition. The paper has three primary objectives: firstly, to offer a comprehensive overview of effective computing by outlining essential theoretical concepts; secondly, to describe in detail the state-of-the-art in emotion recognition at the moment; and thirdly, to highlight important findings and conclusions from the literature, with an emphasis on important obstacles and possible future paths, especially in the creation of state-of-the-art machine learning algorithms for the identification of emotions.
Classification of Heart Diseases Based on Machine Learning: A Review Abdulazeez, Adnan Mohsin; Hasan, Shereen Sadiq
International Journal of Informatics, Information System and Computer Engineering (INJIISCOM) Vol. 6 No. 1 (2025): INJIISCOM: VOLUME 6, ISSUE 1, JUNE 2025
Publisher : Universitas Komputer Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34010/injiiscom.v6i1.13600

Abstract

The article emphasizes the critical need for early and accurate diagnosis of cardiovascular disease (CVD), a leading cause of global mortality. Recent advancements in machine learning (ML) have shown promising results in classifying cardiac disorders, aiming to enhance healthcare practices. It discusses both the benefits and limitations of current ML algorithms used in this field, highlighting their role in improving the management of cardiac diseases through accurate diagnosis. The study evaluates various supervised learning techniques like support vector machines, decision trees, and neural networks, illustrating their effectiveness in handling diverse datasets and identifying significant patterns. Furthermore, it explores unsupervised learning methods such as clustering algorithms, which uncover hidden patterns in cardiac data. The research also investigates the potential of ensemble approaches and deep learning to further enhance classification accuracy. In conclusion, the study provides an overview of the current state of ML-based heart disease classification research, aiming to inform policymakers, physicians, and researchers about the transformative potential of ML in advancing heart disease diagnosis and treatment, ultimately aiming for improved patient outcomes and reduced healthcare costs.
LUNG CANCER DETECTION AND CLASSIFICATION BASED ON DEEP LEARNING: A REVIEW Ismaeel, Hivi Kamal; Abdulazeez, Adnan Mohsin
Jurnal Teknoinfo Vol 18, No 2 (2024): Juli 2024
Publisher : Universitas Teknokrat Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33365/jti.v18i2.4309

Abstract

AbstractLung cancer is a significant health problem worldwide because it is difficult to treat and often caused by factors such as smoking and lifestyle choices. Early detection and accurate classification are crucial for assisting patients. Lung cancer remains a major global health challenge due to its late detection and the complexity of its treatment options. Advancements in deep learning, a form of artificial intelligence that mimics the way humans learn, are offering new hopes for earlier detection and more accurate classification of this disease through the analysis of medical images. This review paper explores recent progress in the use of deep learning techniques, specifically focusing on how these methods are applied to improve lung cancer diagnostics. Our study delves into several types of neural networks such as Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), and Graph Neural Networks (GNNs), which have been adapted to analyze complex medical imaging data effectively. These networks help in identifying and classifying cancerous tissues from lung scans with a higher degree of accuracy than traditional methods, which rely heavily on human interpretation. We review a variety of models and approaches that demonstrate significant improvements in detecting lung cancer features from imaging studies like CT scans. These models not only enhance the accuracy but also reduce the time needed for diagnosis, which is crucial in improving patient outcomes. The paper discusses the specific roles of these models in automating the detection processes, their efficiency, and how they overcome some of the common challenges in lung cancer diagnosis, such as dealing with ambiguous or incomplete images. Furthermore, we address the challenges still facing deep learning applications in this field, including the need for large, annotated datasets and the computational demands of training complex models. Despite these challenges, the future looks promising due to the continuous improvements in computational power and the increasing availability of medical data.
Classification of Medical Images Based on Unsupervised Algorithms: A Review Zeebaree, Imad Majed; Abdulazeez, Adnan Mohsin
International Journal of Research and Applied Technology (INJURATECH) Vol. 4 No. 2 (2024): Vol 4 No 2 (2024)
Publisher : Universitas Komputer Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Artificial intelligence models are becoming increasingly essential in biomedical research and healthcare services. Various healthcare organizations utilize information-based machine learning and image-processing methods for the diagnosis of diseases. This review delves explicitly into elucidating the challenges and considerations of developing unsupervised learning for clinical decision support systems in real-world contexts. In recent years, supervised and unsupervised deep learning have demonstrated promising medical imaging and image analysis outcomes. Unsupervised learning gathers data, draws insights from it, and makes data-driven judgments without bias, unlike supervised learning, which requires manual class labeling. A systematic review of unsupervised medical image analysis methods is presented here. This extensive review introduces diverse methodologies rooted in unsupervised classification for detecting diseases and analyzing images. Moreover, we offer insights into publicly available image benchmarks, datasets, and performance measurement details. Each method's strengths and weaknesses are thoroughly discussed, complemented by tabular summaries illuminating each category's outcomes. Additionally, the article furnishes detailed descriptions of the frameworks employed by each approach and the image datasets utilized.
Classification of Ultra Sound Images Breast Cancer Based on Deep Learning: A review Abdulazeez, Adnan Mohsin; Alnabi, Nisreen Luqman Abd
International Journal of Research and Applied Technology (INJURATECH) Vol. 4 No. 2 (2024): Vol 4 No 2 (2024)
Publisher : Universitas Komputer Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Breast cancer is the second most common cause of mortality for women, after lung cancer. Women's death rates can be decreased if breast cancer is identified early. The artificial intelligence model has the ability to predict breast cancer with the same level of accuracy as an experienced radiology technician. For early cancer detection, an automated approach is necessary because manual breast cancer diagnosis is time-consuming. Deep learning is a type of artificial intelligence that enables software applications to predict more accurate results without being explicitly programmed. The main objective of this paper is to evaluate the performance of a general deep learning algorithm (DLS) with human readers with varying degrees of breast imaging experience in order to train it to identify cancer of the breast on ultrasound pictures. Moreover, this study will examine five deep learning methods that have aided in breast cancer prediction, these are Convolutional Neural Network (CNN), Genetic Algorithm GA-CNN, Deep Belief Network (DBN), Computer Aided Diagnosis (CAD), and Generative Adversarial Networks (GAN). Our main goal is to identify the most appropriate and accurate algorithm for the prediction of breast cancer.
Feature Selection Methods of Gene Expression Based on Machine Learning: A Review Merceedi, Karwan Jameel; Abdulazeez, Adnan Mohsin
International Journal of Research and Applied Technology (INJURATECH) Vol. 5 No. 1 (2025): Vol 5 No 1 (2025)
Publisher : Universitas Komputer Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

This article offers a thorough analysis of feature selection strategies that use machine learning to analyze gene expression data. In order to extract significant biological insights, the explosion of high-dimensional genomic data has required the invention and use of sophisticated analysis techniques. In this situation, feature selection is essential because it finds the most pertinent genes that have a major impact on the prediction ability of machine learning models. The paper examines a range of feature selection techniques, classifying them into filter, wrapper, and embedding approaches, each having special advantages and disadvantages. The importance of gene expression data in comprehending the molecular mechanisms underlying complicated diseases and biological processes. The difficulties presented by high-dimensional datasets are next explored, with a focus on feature selection as a means of enhancing model interpretability, lowering computational cost, and raising prediction accuracy. In order to shed light on the fundamental ideas and practical uses of well-known feature selection algorithms, the writers thoroughly examine a number of them, including Mutual Information, Relief, and Recursive Feature Elimination (RFE). Additionally, the study assesses these methods' performance critically across a range of datasets and experimental situations, emphasizing important factors like interpretability, scalability, and resilience. The paper also discusses new developments in feature selection, such as the incorporation of deep learning techniques, ensemble methods, and domain expertise. In order to fully realize the promise of gene expression data for biomedical research and clinical applications, the study ends with a discussion of the present issues and prospective future directions in the field. This discussion emphasizes the significance of creating reliable and understandable feature selection techniques. This thorough study will be an invaluable tool for practitioners, researchers, and bioinformaticians in the field of genomics as they navigate the challenging terrain of feature selection techniques in the context of machine learning-based gene expression analysis.
Multiclass Regression for Facial Beauty Prediction Based on Deep Learning Using SCUT-B 5500 Haji, Vaman; Abdulazeez, Adnan Mohsin
The Indonesian Journal of Computer Science Vol. 14 No. 6 (2025): The Indonesian Journal of Computer Science
Publisher : AI Society & STMIK Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33022/ijcs.v14i6.5008

Abstract

FBP, that is, facial beauty prediction, is a fundamental procedure of how beautiful a face person perceives, just like human beings. The challenge focuses on systems that can assess facial features and provide ratings that align with human perceptions of attractiveness. In this paper, we investigate the usage of deep learning techniques using ResNet18 models for predicting beauty of a face using SCUT-B 5500 dataset and share our findings. In the last ten years machine recognition and scoring of attractiveness has developed into a new field through the use of artificial intelligence. We present our exploratory research on constructing a robust model based on a dataset containing 5500 annotated frontal images ranked according to perceived beauty. Multi-task transfer learning was employed to improve the model performance and address the issue of limited data. Our ResNet18 model had an impressive accuracy of over 91% on predicting beauty ratings. Furthermore, this study not only contributes to the field of facial beauty prediction, but it also has the potential to be implemented in multiple fields such as social networks, dating applications, personalized ads.
Co-Authors Abdi, Abdo Abdulazeez, Ali Hussein Ageed, Zainab Salih Alhamzo, Jelan Salih Jasim Ali, Ali Hamad Almufti, Saman M. Alnabi, Nisreen Luqman Abd Ashqi Saeed, Vaman Fadhil, Jawaher Ferzo, Barwar Haji, Vaman Hamid, Ari Ibrahim Hasan, Dathar Hasan, Mayaf Hasan, Shereen Sadiq Hassan, Shivan Hussein Hussein, Nashwan Ibrahem, Ali Hikmat Ismaeel, Hivi Kamal Jalal, Dimen Jameel, Dilan Kamil, Zheen Merceedi, Karwan Jameel Miran, Ara Zozan Musa, Jihan Rasheed, Hakar Hasan Salih, Sardar Sulaiman , Sulaiman Muhammed Yaqoub, Karin Younis Younis, Aqeel Hanash Zeebaree, Imad Majed