Claim Missing Document
Check
Articles

Found 17 Documents
Search
Journal : The Indonesian Journal of Computer Science

Comprehensive Review of Advanced Machine Learning Strategies for Resource Allocation in Fog Computing Systems Abdulwahab, Sara; Ibrahim, Media; Askar, Shavan; Hussien, Diana
The Indonesian Journal of Computer Science Vol. 14 No. 1 (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.v14i1.4632

Abstract

This paper targets the development of advanced machine learning strategies for fog computing systems and is designed to further enhance current mechanisms related to resource allocation. Fog computing represents the extension of cloud facilities to network edges with increased data processing, allowing minimal latency for applications that need real-time processing. This is a review underlining deep learning as one of the basic tools through which neural networks predict the resource usage and optimization of resource allocation with its dynamic adaptation to modifications within the network conditions. The paper reviews techniques such as Convolutional Neural Networks, Recurrent Neural Networks, and Generative Adversarial Networks that are explored for their roles in enhancing efficiency, privacy, and responsiveness within the realm of distributed environments. These findings reveal that deep learning significantly enhances operational performance, reduces latency, and strengthens security in fog networks. By processing data locally and autonomously managing resources, these strategies ensure efficient handling of diverse and dynamic demands. It concludes that the integration of machine learning into fog computing forms a scalable and robust framework toward meeting modern challenges imposed by digital ecosystems, enabling smarter real-time decision-making systems at the edge.
The Role of Deep Learning in Network Intrusion Detection Systems: A Review Abdullah, Rebwar; ibrahim, Media; askar, Shavan; hussein, Diana
The Indonesian Journal of Computer Science Vol. 14 No. 1 (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.v14i1.4734

Abstract

This review synthesizes findings from several key studies focusing on the role of deep learning (DL) in network intrusion detection systems (NIDS). It highlights the growing importance of using DL techniques to enhance the detection of complex and evolving cyber threats. Traditional methods such as signature-based systems or anomalous systems often fail to meet the accuracy of modern attacks, prompting researchers to explore DLs to improve accuracy and adaptability. Several studies have demonstrated the effectiveness of convolutional neural networks (CNNs), recurrent neural networks (RNNs), and deep belief networks (DBNs) in classifying network traffic and identifying malicious activities. These deep learning models are particularly valuable because of their ability to automatically learn features from raw data, reducing the need for manual feature engineering. The review emphasizes the challenges in training DL models, including the need for large, labelled datasets and addressing issues associated with false positives and model interpretability. Despite these challenges, DL-based NIDS have shown significant improvements in real-time threat detection and mitigation rates. However, there is ongoing research to optimize these models for better performance, scalability, and generalizability across different network environments. Overall, the integration of deep learning into NIDS represents a promising frontier in combating increasingly sophisticated cyberattacks.
Machine Learning Techniques for Enhancing Internet of Things (IoT) Performance A Review Hussein, Diana; Abdullah, Rebwar; Askar, Shavan; Ibrahim, Media
The Indonesian Journal of Computer Science Vol. 14 No. 1 (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.v14i1.4735

Abstract

The Internet of Things (IoT) is basically billions of interconnected smart devices that can communicate with little interference from humans, thus making life easier. The IoT is a fast-moving area of research, and the challenges are growing, thus requiring continuous improvement. As IoT systems become more challenging to improve, machine learning (ML) is increasingly incorporated into IoT systems to develop better capabilities. This article review explores several machine learning techniques aimed at enhancing the performance of IoT systems. It highlights the growing importance of integrating machine learning with IoT to address challenges such as data management, security, and real-time processing. The techniques discussed include supervised learning, unsupervised learning, reinforcement learning, deep learning, ensemble methods, anomaly detection, and federated learning. Each method is evaluated for its effectiveness in optimizing IoT applications, such as predictive maintenance, energy efficiency, and smart city solutions. The review emphasizes the potential of these techniques to improve decision-making processes, automate operations, and enhance user experiences. Additionally, it addresses the limitations and challenges associated with implementing machine learning in IoT environments, including data privacy concerns and the need for robust algorithms capable of handling diverse datasets. Overall, the article underscores the transformative role of machine learning in advancing IoT capabilities and suggests future research directions to further leverage these technologies for improved system performance and reliability.
Comparative Analysis of XGBoost Performance for Text Classification with CPU Parallel and Non-Parallel Processing Ahmed Al-Zakhali, Omar; Zeebaree, Subhi; Askar, Shavan
The Indonesian Journal of Computer Science Vol. 13 No. 2 (2024): 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.v13i2.3798

Abstract

This paper shows the findings of a study that looks at how CPU parallel processing changes the way Extreme Gradient Boosting (XGBoost) classifies text. XGBoost models can sort news stories into set groups faster and more accurately, with or without CPU parallelism. This is the main goal of the study. The Keras dataset is used to prepare the text so that the TF-IDF (Term Frequency-Inverse Document Frequency) features can be found. These features will then be used to train the XGBoost model. This is used to check out two different kinds of the XGBoost classifier. There is parallelism between one of them and not it in the other. How well the model works can be observed by how accurate it is. This includes both how long it takes to learn and estimate and how well predictions work. The models take very different amounts of time to compute, but they are all pretty close in terms of how accurate they are. Parallel processing on the CPU has made tasks proceed more rapidly, and XGBoost is now better at making the most of that speed to do its task. The purpose of the study is to show that parallel processing can speed up XGBoost models without affecting their accuracy. This is helpful for putting text into categories.
Deep Learning Based Security Schemes for IoT Applications: A Review Othman, Mina; askar, shavan; Ali, Daban; Ibrahim, Media Ali; Abdullah, Nihad
The Indonesian Journal of Computer Science Vol. 13 No. 2 (2024): 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.v13i2.3839

Abstract

Due to its widespread perception as a crucial element of the Internet of the future, the Internet of Things (IoT) has garnered a lot of attention in recent years. The Internet of Things (IoT) is made up of billions of sentients, communicative "things" that expand the boundaries of the physical and virtual worlds. Every day, such widely used smart gadgets generate enormous amounts of data, creating an urgent need for rapid data analysis across a range of smart mobile devices. Thankfully, current developments in deep learning have made it possible for us to solve the issue tastefully. Deep models may be built to handle large amounts of sensor data and rapidly and effectively learn underlying properties for a variety of Internet of Things applications on smart devices. We review the research on applying deep learning to several Internet of Things applications in this post. Our goal is to provide insights into the many ways in which deep learning techniques may be used to support Internet of Things applications in four typical domains: smart industrial, smart home, smart healthcare, and smart transportation. One of the main goals is to seamlessly integrate deep learning and IoT, leading to a variety of novel ideas in IoT applications, including autonomous driving, manufacture inspection, intelligent control, indoor localization, health monitoring, disease analysis, and home robotics. We also go over a number of problems, difficulties, and potential avenues for future study that make use of deep learning (DL), which is turning out to be one of the most effective and appropriate methods for dealing with various IoT security concerns. The goal of recent research has been to enhance deep learning algorithms for better Internet of Things security. This study examines deep learning-based intrusion detection techniques, evaluates the effectiveness of several deep learning techniques, and determines the most effective approach for deploying intrusion detection in the Internet of Things. This study uses Deep Learning (DL) approaches to better expand intelligence and application skills by using the large quantity of data generated or acquired. The many IoT domains have drawn the attention of several academics, and both DL and IoT approaches have been explored. Because DL was designed to handle a variety of data in huge volumes and required processing in virtually real-time, it was indicated by several studies as a workable method for handling data generated by IoT.
Image Copyright Protection Based on Blockchain Technology Review Ali, Daban; Askar, Shavan; saleem, mohammed; Othman, Mina; Omer, Saman M.
The Indonesian Journal of Computer Science Vol. 13 No. 2 (2024): 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.v13i2.3840

Abstract

On a daily basis, a significant number of individuals distribute several photos and videos that have been marginally modified from the original material produced by copyright owners, such as photographers, graphic designers, and video producers. Individuals that infringe upon the rights of others, lacking the legal authority to access multimedia content, employ various digital image and picture manipulation techniques, it involves converting to gray scale, trimming, rotating, contracting the frame, and adjusting the background speed, to modify said content. Blockchain technology obviates the necessity of an intermediary, hence circumventing the possibility of a singular point of failure. Infractions to copyright poses a significant barrier to protecting commercial image and video information. The IPFS blockchain technology offers on-chain preservation for copyright information and off-chain storing for distinct multimedia files. The enhanced perceptual hashing algorithm significantly enhances the precision of identifying connections to identify digital image piracy. The photographers and designers that submit their photographs on websites are experiencing significant dissatisfaction due to a prevalent practice in which others attempt to claim credit and profit from the initial creator's effort.
The Industrial Internet of Things (IIoT) and its roles in the Fourth Industrial Revolution: A review Saleem, Mohammed; askar, shavan; Ibrahim, Media Ali; Othman, Mina; Abdullah, Nihad
The Indonesian Journal of Computer Science Vol. 13 No. 2 (2024): 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.v13i2.3841

Abstract

The Industrial Internet of Things and Industry 4.0 are now two highly sought-after areas of research and development, attracting significant interest from both academic and industrial sectors. The two ideas, Industry 4.0 and IIoT, share significant similarities, with Industry 4.0 being seen as the use of IIoT specifically in the automation and manufacturing sectors. Within the framework of the present Industry 4.0 paradigm, many growth pathways have emerged, collectively leading to notable enhancements in terms of efficiency, flexibility, communication, adaptability, customization, and modularity in the industrial sector. The Industry 4.0 is rapidly evolving within the framework of the Industrial Internet of Things (IIoT), and the authors are recognizing the necessity for a comprehensive and in-depth overview of the many research areas that are currently expanding. The area will remain intriguing in the foreseeable future due to its significant potential for enhancing the existing industrial technologies. An exhaustive evaluation of the current systems in the automotive sector, emergency response, and chain management on IIoT has been conducted, revealing that IIoT has been widely adopted across several technological domains. Industry 4.0 is the term used to describe the present automation and data sharing trend in businesses. Presently, there is a dearth of agreement about the assessment of an organization's readiness for Industry 4.0. Industry 4.0 encompasses a diverse array of digital technologies that profoundly influence industrial enterprises. The literature on Industry 4.0 has had significant exponential growth during the previous decade. The results of our research confirm the idea of Industry 4.0 as a concept that goes beyond the Smart Manufacturing sector, hence opening up possibilities for collaboration with other interconnected disciplines.
Deep Learning in Medical Image Analysis Article Review Ibrahim, Media Ali; askar, shavan; saleem, Mohammad; Ali, Daban; Abdullah, Nihad
The Indonesian Journal of Computer Science Vol. 13 No. 2 (2024): 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.v13i2.3842

Abstract

Transfer learning, in evaluation to common deep studying strategies which include convolutional neural networks (CNNs), stands proud due to its simplicity, efficiency, and coffee education value, efficaciously addressing the venture of restricted datasets. The importance of scientific picture analysis in both scientific research and medical prognosis can't be overstated, with image techniques like Computer Tomography (CT), Magnetic Resonance Image (MRI), Ultrasound (US), and X-Ray playing a crucial function. Despite their utility in non-invasive analysis, the scarcity of categorized medical images poses a completely unique challenge in comparison to datasets in other pc imaginative and prescient domains, like facial reputation. Given this shortage, switch getting to know has won reputation amongst researchers for medical photo processing. This complete evaluation draws on one hundred amazing papers from IEEE, Elsevier, Google Scholar, Web of Science, and diverse sources spanning 2000 to 2023 It covers vital components, which includes the (i) shape of CNNs, (ii) foundational know-how of switch learning, (iii) numerous techniques for enforcing transfer mastering, (iv) the utility of switch gaining knowledge of throughout numerous sub-fields of medical photo analysis, and (v) a dialogue at the future potentialities of transfer studying within the realm of medical image analysis. This evaluate no longer handiest equips beginners with a scientific understanding of transfer mastering applications in medical image analysis but additionally serves policymakers by means of summarizing the evolving trends in transfer learning within the scientific image domain. This insight might also encourage policymakers to formulate advantageous rules that support the continued development of Transfer learning knowledge of in medical image analysis.
Exploring the Landscape of Smart Cities: A Comprehensive Review of IoT and Cyber-Physical Systems Muheden, Karwan; askar, shavan; Mohammed, Mariwan; Bilal, Noura
The Indonesian Journal of Computer Science Vol. 13 No. 2 (2024): 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.v13i2.3843

Abstract

They focus on housing, well-being, equality, clean energy and fair conditions. The cyber-physical approach involves the development of IoT and Cyber-Things. Smart cities have a variety of use cases, including electricity and transportation. Automating is used for efficiency in industrial manufacturing. An integrated supply and demand side management system is required for the reliability, security and ability to manage the power grid. This paper introduces an integrated energy approach, enhances existing standards, and establishes a shared basis for multidisciplinary planning. It also introduces new semantic network ontologies to provide a comprehensive framework for solving resource-related challenges. This new approach aims to fill the gaps in current standards and create an integrated environment for multi-stakeholder collaboration, using a semantic web ontology for communication and improved decision making in energy systems Provides information integrated, including various forms of smart cities With flexibility for flexibility and inclusion in the energy industry, can accommodate the specific characteristics and needs of various smart city applications In this study, computing -physical system (CPS), software-defined network (SDN), internet (IoT). ), and analyze how smart cities are connected. CPS combines physical channels with electronic systems to provide increased network management efficiency and flexibility. SDN improves dynamic capacity and flexibility, while IoT is more connected for real-time data exchange and decision-making.
Enhancing Educational Paradigms: A Comprehensive Review of Virtual Desktop Infrastructure (VDI) Applications in Learning Environments Ahmed, Mariwan; Askar, Shavan; Muheden, Karwan; Bilal, Noura
The Indonesian Journal of Computer Science Vol. 13 No. 2 (2024): 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.v13i2.3844

Abstract

This article comprehensively evaluates Virtual Desktop Infrastructure (VDI) in academic environments. It explores the role of VDI in transforming and gaining knowledge via offering more advantageous accessibility and flexibility, addressing the digital divide, and adapting to various learning patterns. The paper examines case studies throughout one-of-a-kind educational settings, discusses the technical components, and evaluates VDI's effect on mastering and teaching. It additionally highlights the challenges and potential risks related to VDI implementation. Synthesizing the outcomes from various case studies and study papers lays a stable foundation for understanding the multifaceted nature of VDI's implementation and its effect on instructional paradigms. The technical limitations of reviewed cases play a significant function in determining the fulfillment of VDI implementations in instructional environments. Well-structured planning and evaluation of these elements are vital to ensure that the selected VDI efficiently meets the goals of instructional concerns and their participants. Future research instructions are cautioned to deal with diagnosed gaps, including their application in various educational contexts and lengthy-term impacts. The article is valuable for educators, policymakers, and era providers.