Article Per Year (5 Year)
p-Index From 2021 - 2026
0.659
P-Index
This Author published in this journals
All Journal International Journal of Electrical and Computer Engineering Bulletin of Electrical Engineering and Informatics Journal of Applied Engineering and Technological Science (JAETS)
Theo G. Swart
University of Johannesburg
Civil Engineering, Building, Construction & Architecture Computer Science & IT Decision Sciences, Operations Research & Management Electrical & Electronics Engineering Industrial & Manufacturing Engineering

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

Found 3 Documents
Search

 1 
Artificial neural network technique for improving prediction of credit card default: A stacked sparse autoencoder approach Sarah A. Ebiaredoh-Mienye; E. Esenogho; Theo G. Swart
International Journal of Electrical and Computer Engineering (IJECE) Vol 11, No 5: October 2021
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijece.v11i5.pp4392-4402

Abstract

Presently, the use of a credit card has become an integral part of contemporary banking and financial system. Predicting potential credit card defaulters or debtors is a crucial business opportunity for financial institutions. For now, some machine learning methods have been applied to achieve this task. However, with the dynamic and imbalanced nature of credit card default data, it is challenging for classical machine learning algorithms to proffer robust models with optimal performance. Research has shown that the performance of machine learning algorithms can be significantly improved when provided with optimal features. In this paper, we propose an unsupervised feature learning method to improve the performance of various classifiers using a stacked sparse autoencoder (SSAE). The SSAE was optimized to achieve improved performance. The proposed SSAE learned excellent feature representations that were used to train the classifiers. The performance of the proposed approach is compared with an instance where the classifiers were trained using the raw data. Also, a comparison is made with previous scholarly works, and the proposed approach showed superior performance over other methods.
Efficient topology discovery protocol using IT-SDN for software-defined wireless sensor network Joseph Kipongo; Ebenezer Esenegho; Theo G. Swart
Bulletin of Electrical Engineering and Informatics Vol 11, No 1: February 2022
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/eei.v11i1.3240

Abstract

The internet of things (IoT) and wireless sensor networks (WSNs) are two promising technologies for supporting new services and applications. However, because IoT and WSN entail interaction and transaction of device topology discovery protocols, WSN facing some challenges. Topology discovery (TD) is important for WSN in IoT since sensor nodes (SNs) are the main points of this network. Networking these SN (IoT-devices) has a few difficulties such as energy and bandwidth consumption, and data storage issues resulting from frequent interactions and transactions between devices. Because these challenges cannot be resolved by one solution, we focused on reducing the energy consumption associated with a WSN. We proposed software-defined networking (SDN) model to tackle energy-efficiency issue in a WSN setup by integrating SDN and WSN, which gave rise to a more robust system, software-defined wireless sensor network (SDWSN). In this direction, we proposed an improved fuzzy-logic-based strategy, fuzzy topology discovery protocol (FTDP). It used IT-SDN (an SDN-based WSN framework) to increase the network’s lifepan due to its low energy consumption. The link layer discovery protocol (LLDP) to build the SDN controller’s topology. The system’s performance was presented and compared, demonstrating that with an effective SDWSN discovery policy, energy efficiency is achievable.
Capacity Enhancement in D2D 5G Emerging Networks: A Survey Anthon Ejeh Itodo; Theo G. Swart
Journal of Applied Engineering and Technological Science (JAETS) Vol. 4 No. 2 (2023): Journal of Applied Engineering and Technological Science (JAETS)
Publisher : Yayasan Riset dan Pengembangan Intelektual (YRPI)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37385/jaets.v4i2.1394

Abstract

Several efforts are being made to improve the capacity of 5G networks using emerging technologies of interest. One of the indispensable technologies to fulfill the need is device-to-device (D2D) communication with its untapped associated benefits. Interference is introduced at the base station due to massive traffic congestion. The purpose of this research is to expand the knowledge of interference mitigation in D2D using stochastic geometrical tools which will result in capacity enhancement. This study uses a literature review method based on 5G and other already existing literature on D2D communication. More than one hundred and twenty papers on D2D communications in cellular networks exist but no precise survey paper on interference management to enhance capacity using stochastic geometrical tools exists. The contribution of this survey to theory is that apart from already existing capacity enhancement methods, interference mitigation using stochastic geometrical tools is another technique that can also be used for capacity enhancement in D2D communications.
Co-Authors Anthon Ejeh Itodo E. Esenogho Ebenezer Esenegho Joseph Kipongo Sarah A. Ebiaredoh-Mienye