Garuda - Garba Rujukan Digital

Bibliometric Analysis of Mixed Text Using Transformer-Based Architecture in Africa Sekwatlakwatla, Sello Prince; Malele, Vusumuzi; Ramalepe, Phetole Simon; Modipa, Thipe
Indonesian Journal of Data and Science Vol. 5 No. 2 (2024): Indonesian Journal of Data and Science
Publisher : yocto brain

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.56705/ijodas.v5i2.131

Deep learning techniques based on neural networks have been developed for text creation, a critical sub-task of natural language generation that aims to create human-readable content. Natural language processing (NLP) tasks are utilized to recognize speech in code-mixed comments on social media platforms like Facebook and Twitter, which enable users to interact and exchange ideas, views, status updates, pictures, and videos with people all over the world. Although NLP is widely investigated in the world and Africa is home to approximately 3,000 languages, many of which are derived from significant language families, in this regard, there are challenges that Africa faces in Natural Language Processing (NLP), especially mixed text using transformer-based architecture. The purpose of this study is to investigate the prevalence of mixed text using transformer-based architecture in Africa. Bibliometric analysis was used to assess natural language and mixed text in Africa, utilizing transformer-based architecture. show that sentiment analysis is the holistic tool that is used for mixed text using transformers, where social media, deep learning, codes, computational linguistics, and social networking are critical tools in generating human-like quality text. Therefore, this study proposes artificial intelligence, artificial neutral networks, and neural networks, as well as a prediction to estimate the technique or fluctuation as the method for mixed text using transformer-based architecture in Africa. This research sets the path for future studies that use mixed text using transformer-based architecture in Africa

A Literature Review to Investigate Data Analytics Tools for The Allocation of Resources in Cloud Computing Sekwatlakwatla, Sello Prince; Malele, Vusumuzi
Indonesian Journal of Data and Science Vol. 5 No. 2 (2024): Indonesian Journal of Data and Science
Publisher : yocto brain

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.56705/ijodas.v5i2.136

To ensure efficient operations and cost-effectiveness, resource management in cloud computing entails managing cloud resources to satisfy application needs, financial restrictions, and security. In this regard, utilizing data analytics tools for the allocation of resources in cloud computing to efficiently predict, track, allocate, and monitor resources enables businesses to make informed decisions based on real-time data, which plays a crucial role in resource allocation. Organizations adopting cloud computing services face increased network traffic, limiting traffic routing flexibility and causing excess traffic to reach unprepared physical nodes due to an inability to adjust to real-time traffic changes. This paper uses a systematic literature review to investigate the data analytics techniques used for resource allocation in cloud computing. It uses data from 2019 to 2024, sourced from different research databases. The results show that the majority of data analytics tools, including ARIMA and SVM, are employed for resource allocation in cloud computing. This study offers guidance to organizations regarding data analytics tools for the allocation of resources in cloud computing, and the recommendations can be utilized for the enhancement of the results in cloud computing, as well as to scholars by suggesting techniques to further investigate resource allocation to address the current gaps in cloud computing

Cybersecurity Cloud-Based Online Learning: A Literature Review Approach Malele, Vusumuzi
Journal of Information System and Informatics Vol 5 No 4 (2023): Journal of Information Systems and Informatics
Publisher : Universitas Bina Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51519/journalisi.v5i4.583

Cloud-based online learning is the electronic learning activity that supports teaching and learning (T&L) that could be done from anywhere and in the world. Some of its benefits are scalability and affordability that could in a decision-making support on the mechanisms of material selection. Cloud computing has been adopted by most universities around the world. In this regard, lecturers and students will use it to facilitate T&L; however, due to concerns of information technology or systems security, cloud-based online learning users are also not immune. In this regard, the users could be affected by different cybersecurity attacks. In this paper, a systematic literature review method was used to sift the different models and solutions used to address the cybersecurity concerns surrounding cloud-based online learning. A brief Likert-scale questionnaire was used to obtained data that could corroborate the systematic literature findings. In this regard, a group of 20 online learning designers were sampled as participants. It was found that the confidentiality, integrity, and availability issues are a concern. This led to issues of security awareness, authentication and blended attacks being issues. In this regard, a cloud-based online learning model is not immune from security issues. In this paper, a conceptual framework as the line-of-defense is proposed as a solution towards having a cybersecure cloud based online learning.

Data Analytics Techniques for Addressing Cloud Computing Resources Allocation Challenges: A Bibliometric Analysis Approach Sekwatlakwatla, Sello Prince; Malele, Vusumuzi
Journal of Information System and Informatics Vol 6 No 1 (2024): March
Publisher : Universitas Bina Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51519/journalisi.v6i1.640

The increase in the use of digital technology led to an increase in online activities. In this regard, many organizations adopted cloud computing systems to manage this online traffic. It is plan of every cloud computing resource provider to manage their system effectively and efficiently. This paper uses bibliometric analysis technique to look at the prevalence of utilization of data analytics techniques in addressing cloud computing resource allocation challenges. In this regard, the following research databases the Association for Computing Machinery, the Institute of Electrical and Electronics Engineering, Web of Science and Scopus databases, were consulted. The research articles published before the beginning of 2017 to 2023 were considered as part of the analysis. The results showed that the prevalent data analytics techniques used to address the cloud computing resources allocation challenge are Support Vector Machine, Spatio-temporal and edge-cloud collaborative scheme. Failure to effectively and efficiently provide cloud computing management resource allocation will lead to system bottlenecks especially during peak periods. In this regard, such a failure could lead to dissatisfied clients.

Model for Enhancing Cloud Computing Resource Allocation Management Using Data Analytics Sekwatlakwatla, Sello Prince; Malele, Vusumuzi
Journal of Information System and Informatics Vol 6 No 1 (2024): March
Publisher : Universitas Bina Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51519/journalisi.v6i1.679

The cloud computing environment requires an adequate and accurate traffic prediction tool to fulfill the needs of customers and support organizations effectively. In the absence of an effective tool for forecasting cloud computing traffic, many organizations might fail. It is difficult to predict the network resources that are suitable to meet the needs of all network clients at a given time in a cloud computing environment because of the inconsistent network traffic flow. There is still room for improving the predictive accuracy of the model in cloud computing. The higher the accuracy of the traffic flow, the better the allocation of resources. Therefore, this study proposes an ensemble method called SGLA (Stepwise Gaussian Linear Autoregressive) by combining linear regression, support vector machines, Gaussian process regression, and the autoregressive integrated moving average technique. SGLA performed better than all methods with a minimum MAPE of 1.03% of the ensemble approach by using the averaging strategy, SGLA shows a clear advantage in handling resource allocation better despite traffic fluctuations, with 91.7% traffic prediction accuracy. Overall experimental results indicate that this method performed better than single models in terms of prediction accuracy. The main contribution of this study is to propose a data analytics model for enhancing cloud computing resource management.

Bibliometric Analysis of Data Analytics Techniques in Cloud Computing Resources Allocation Sekwatlakwatla, Sello Prince; Malele, Vusumuzi
Journal of Information System and Informatics Vol 6 No 3 (2024): September
Publisher : Universitas Bina Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51519/journalisi.v6i3.782

Cloud computing provides on-demand computing services over the Internet, allowing for quicker innovation, more flexible resources, and economies of scale while reducing the need for physical data centers and servers. With this benefit, most organizations are adopting this technology, and some organizations are also operating fully on cloud computing. This causes traffic to increase, and most of these organizations are struggling with resource allocation, resulting in complaints from users regarding inactive system performance, timeouts in applications, and higher bandwidth use during peak hours. In this regard, this study investigates data analytics techniques and tools for the allocation of resources in cloud computing. The study indexed journal articles from the Scopus Database and Web of Science (WOS) between 2010 and 2024. This article brings new insights into the analysis of data analytics techniques in Africa and collaborations with other developing countries. The findings present tools and approaches that may be used to allocate cloud computing resources and give recommendations.

Probabilistic Graphical Models for Predicting Properties of New Materials Based on Their Composition and Structure Malele, Vusumuzi; Phala, Ashley
Indonesian Journal of Data and Science Vol. 5 No. 3 (2024): Indonesian Journal of Data and Science
Publisher : yocto brain

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.56705/ijodas.v5i3.177

Probabilistic graphical model (PGMs) offer a powerful framework for modeling complex relationships between different components. By integrating information on the element composition and structural features, these models enable the inference of materials properties with a probabilistic perspective. This approach holds promising efforts towards accelerating materials discovery design, as it facilitates the predication of diverse materials characteristics, ranging from electronic and mechanical properties to thermal and optical behavior. The use of PGMs in materials science represents a sophisticated methodology for harnessing data-driven insights to guide the exploration of innovative materials with tailored functionalities. The purpose of this paper is to investigate literature for the exploitation of the data science concepts, big data and machine learning that yields computational intelligence. A literature review approach to understand the exploitation and use of computational intelligence in the leading-edge research and innovation of materials science. The findings illustrate that machine learning can be used to intricate chemical problems that otherwise would not be tractable. Leveraging PGMs presents a promising avenue for predicting the properties of new materials based on their composition and structure.

Evaluations of Large Language Models a Bibliometric analysis sekwatlakwatla, Sello Prince; Malele, Vusumuzi
The Indonesian Journal of Computer Science Vol. 13 No. 1 (2024): The Indonesian Journal of Computer Science (IJCS)
Publisher : AI Society & STMIK Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33022/ijcs.v13i1.3767

The development of artificial intelligence (AI) and the increased curiosity about how large language models (LLMs) may maximize an organization's opportunities and the ethical implications of LLMs, such as the ability to generate human-like text, give rise to concerns regarding disinformation and fake news. As a result, it is crucial to develop evaluation benchmarks that take into account the social and ethical implications involved. The great challenges of LLMs lack awareness of their own limitations, yet they persist in producing responses to the best of their capabilities. This often results in seemingly plausible but ultimately incorrect answers, posing challenges to the implementation of reliable generative AI in industry. This paper aims to delve into the evaluation metrics of machine-learning models' performance, specifically focusing on LLM. Therefore, bibliometric analysis utilized to explore and analyze various techniques and methods used in evaluating large language models. Additionally, it sheds light on the specific areas of focus when evaluating these models. The results show that natural language processing systems, classification of information, and computational linguistics are some of the techniques used to evaluate large language models. This work paves the way for future investigations employing extensive language models.

Data science for energy applications: A Bibliometric Analysis Sekwatlakwatla, Sello Prince; Malele, Vusumuzi
The Indonesian Journal of Computer Science Vol. 13 No. 2 (2024): The Indonesian Journal of Computer Science (IJCS)
Publisher : AI Society & STMIK Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33022/ijcs.v13i2.3781

Global digitalization is altering the energy sector, demanding the adoption of data science applications to improve efficiency and innovation, despite the industry's existing data analytics. Data science is revolutionizing the energy and utilities industries, enabling efficient, sustainable, and innovative decision-making through data analysis and smart grid optimization. In the energy industry, organizations are turning to data science to reduce waste, optimize energy usage, and provide alternative energy sources. With the different parts of Africa facing energy crises, different applications are needed to provide a solution. Data science has the potential to provide good information and knowledge that could be used to contribute to energy solutions. To address these concerns, data science models enable utilities to accurately forecast energy demand, enabling efficient generation, distribution, waste reduction, and informed investment decisions by leveraging historical consumption data, weather patterns, and economic indicators. This article aims to explore data science for energy applications. The findings show tools and techniques that can be utilized to provide energy efficiency and energy sustainability through data science applications.

Evolution of the optical add/drop multiplexer in dense wavelength division multiplexing optical networks Mkhwanazi, Mnotho P.; Mpofu, Khumbulani; Malele, Vusumuzi
Indonesian Journal of Electrical Engineering and Computer Science Vol 39, No 1: July 2025
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v39.i1.pp247-257

Mobile network operators are facing ever-increasing traffic demands because of the numerous data-hungry applications used by subscribers nowadays. As a result, technologies that support high bandwidth and network availability have become essential. One such technology is dense wavelength division multiplexing (DWDM). This study investigated the evolution of an optical add/drop multiplexer (OADM), which is one of the key components of DWDM technology. The goal of this research was to investigate how the evolution of an OADM has contributed to network survivability and bandwidth enhancement in DWDM optical networks. A thorough search of the literature on an OADM was undertaken using data sources like Google Scholar, Elsevier, ResearchGate, ScienceDirect, Springer, and DWDM vendor manuals. The study found that in order to address present and future DWDM optical network demands, a reconfigurable optical add/drop multiplexer (ROADM) deployed over flexgrid spectrum is essential. The most advanced iteration of a ROADM supports colorless, directionless, contentionless, and flex-grid functionalities, resulting in the most robust, flexible, and future-proof DWDM optical network. The study further found that flex-grid technology supports uplinks with high line rates and has superior spectral efficiency.

Title

Found 16 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 16 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 16 Documents
Search