2021 IEEE AFRICONPub Date : 2021-09-13DOI: 10.1109/africon51333.2021.9571005
Poovendren Govender, K. Ogudo, Chabalala S. Chabalala
{"title":"Quality of Service Enabled Network Slicing Model in 5G and the Next Generation Virtualized Networks","authors":"Poovendren Govender, K. Ogudo, Chabalala S. Chabalala","doi":"10.1109/africon51333.2021.9571005","DOIUrl":"https://doi.org/10.1109/africon51333.2021.9571005","url":null,"abstract":"The demand for high-speed connectivity has increased globally. The covid-19 pandemic, which forced global lockdown and directly led to most of the global workforce to telecommute, dramatically exacerbated the need for quality mobile connectivity and high data rates. The 5th generation of mobile communication technology (5G), with its ultra-low latency and high bandwidth capacity, becomes a natural fit to overhaul communication infrastructure to meet the connectivity demands. Key to 5G’s performance is network slicing, which allows for the 5G network to be segmented into virtual networks that can be used to serve specific industry verticals. To assure Quality of Service (QoS), our paper proposes a model that creates network slices with respect to QoS requirements for various industry verticals. The proposed model is designed and evaluated using a software simulation technique, and the results obtained show that QoS-enabled network slicing guarantees improved performance in terms of throughput and loss in highly varying network conditions.","PeriodicalId":170342,"journal":{"name":"2021 IEEE AFRICON","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127478930","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
2021 IEEE AFRICONPub Date : 2021-09-13DOI: 10.1109/africon51333.2021.9570945
Ezra Misaki
{"title":"Assessment of the Used Mobile Applications by Small-Scale Farmers at Miono and User Requirements in the Present and Future Mobile Apps","authors":"Ezra Misaki","doi":"10.1109/africon51333.2021.9570945","DOIUrl":"https://doi.org/10.1109/africon51333.2021.9570945","url":null,"abstract":"The revolution of smartphone usage in agriculture by small-scale farmers has improved productivity by establishing a reliable agricultural knowledge information system. Despite the development achieved by the smartphone in agriculture, information on how the applications improve the farming value chain is still very scanty. Consequently, this study set out to assess the currently used application technologies by small-scale farmers at Miono to upgrade the user requirements for present and future applications. The study applied qualitative interview and observation approach in collecting data and thematic analysis to analyze the data. Results show that farmers at Miono used messaging applications, call applications, calculator apps and clock applications the most. On the other hand, the farmers rarely used WhatsApp, Facebook, email applications, and photo apps. Thus, for real present and future development, farmers need upgraded apps that disseminate information on local pests, pesticides, weather forecasts, and market information.","PeriodicalId":170342,"journal":{"name":"2021 IEEE AFRICON","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121023924","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
2021 IEEE AFRICONPub Date : 2021-09-13DOI: 10.1109/africon51333.2021.9570983
Tawanda Matereke, Clement N. Nyirenda, Mehrdad Ghaziasgar
{"title":"A Performance Evaluation of 3D Deep Learning Algorithms for Crime Classification","authors":"Tawanda Matereke, Clement N. Nyirenda, Mehrdad Ghaziasgar","doi":"10.1109/africon51333.2021.9570983","DOIUrl":"https://doi.org/10.1109/africon51333.2021.9570983","url":null,"abstract":"This paper presents a study on crime classification using two 3D deep learning algorithms, i.e., 3D Convolutional Neural Network and the 3D Residual Network. The Chicago crime dataset, which has 7.29 million records, collected from 2001 to 2020, is used for training the models. The models are evaluated by using F1 score, Area Under Receiver Operator Curve (AUROC), and Area Under Curve - Precision Recall (AUCPR). Furthermore, the effectiveness of spatial grid resolutions on the performance of the models is also evaluated. Results show that the 3D ResNet-18 achieved the best performance with an F1 score of 0.9985, whereas the 3D CNN achieved an F1 score of 0.9979, during training with a spatial resolution of 16 pixels. Furthermore, the 3D ResNet-18 achieved an accuracy of 0.92 and the 3D CNN achieved an accuracy of 0.87 during model testing. In terms of future work, we intend to test these algorithms on multi-label classification and regression crime problems, improve the performance of the 3D CNN by adding RNN layers, and evaluate the implementation of 3D ResNeXt for crime prediction and classification.","PeriodicalId":170342,"journal":{"name":"2021 IEEE AFRICON","volume":"410 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116527073","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
2021 IEEE AFRICONPub Date : 2021-09-13DOI: 10.1109/africon51333.2021.9570882
Jacob J. Greeff, A. Nel, Reolyn Heymann, Johnson Carroll
{"title":"Academic challenges as part of capstone project resilience training","authors":"Jacob J. Greeff, A. Nel, Reolyn Heymann, Johnson Carroll","doi":"10.1109/africon51333.2021.9570882","DOIUrl":"https://doi.org/10.1109/africon51333.2021.9570882","url":null,"abstract":"Capstone projects are the projects students undertake during undergraduate studies where they serve as the final gatekeeping process in engineering degrees to ensure students have the ability to leverage all of the knowledge they have gained in the solving of an open ended problem. As part of a larger project to improve the experience of students in a capstone project module, a challenge-based system has been implemented with inspiration taken from the Superbetter approach. This paper introduces the wider project context, presents the three design cycles the challenge system went through and presents results. In this paper it is shown that the implementation of the artefact was ultimately not a success, and the reasons for this are explored and recommendations for the implementation of similar systems in the future in other contexts are presented.","PeriodicalId":170342,"journal":{"name":"2021 IEEE AFRICON","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132349733","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
2021 IEEE AFRICONPub Date : 2021-09-13DOI: 10.1109/africon51333.2021.9571008
Jacobus Kampman, Judas Masela, T. Joubert
{"title":"Wireless sensor network for water pipe corrosion monitoring","authors":"Jacobus Kampman, Judas Masela, T. Joubert","doi":"10.1109/africon51333.2021.9571008","DOIUrl":"https://doi.org/10.1109/africon51333.2021.9571008","url":null,"abstract":"The development of accurate corrosion models from corrosion data is a key requirement for well informed, preemptive actions towards extending the life of water infrastructure systems and reducing maintenance costs. This work presents the development of a custom proof-of-concept system implementation performing water corrosion monitoring using custom integrated corrosion sensing technologies powered by energy harvested through an in-line turbine generator. Implementing a star topology network of wireless corrosion sensor nodes distributed through water infrastructure systems offers an innovative solution for real-time and on-line monitoring of corrosion in water infrastructure systems. The wireless sensor network includes a wireless access point that provides an interface for retrieval of the corrosion data and a nexus for communications. A low-power bidirectional data transfer communications protocol using a form of time-division multiplex access is designed and implemented towards the optimisation of energy efficiency in the network. In an emulated pipeline field setup, the energy harvested and stored provides 125.80 mWh at 4.89 V for an in-pipe flow rate of 13.25 l/min, a typical value for municipal potable water supply in South Africa. The local node ER sensor can of measure changes in resistance values to an accuracy of 1% and will be usable in-system for a year. The access point implements EIS and LPR sensing. The extracted LPR value predicts a corrosion rate is 63.0 um/year in potable water.","PeriodicalId":170342,"journal":{"name":"2021 IEEE AFRICON","volume":"249 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114333283","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
2021 IEEE AFRICONPub Date : 2021-09-13DOI: 10.1109/africon51333.2021.9570971
D. Modungwa, F. Mekuria, Mzuziwezulu Kekana
{"title":"Conceptual Development of an Autonomous Underwater Robot Design for Monitoring and Harvesting Invasive Weeds","authors":"D. Modungwa, F. Mekuria, Mzuziwezulu Kekana","doi":"10.1109/africon51333.2021.9570971","DOIUrl":"https://doi.org/10.1109/africon51333.2021.9570971","url":null,"abstract":"The design of a biomimicry autonomous underwater robot for monitoring and harvesting invasive weeds in lakes is presented in this paper. The systematic design of the robot focuses on integrating 5G-AI-IoT as effective technological tools to autonomously monitor and harvest invasive weeds in order to replace traditional weed control approaches. The robustness and versatility of the robotic platform to structural topology and autonomous navigation that uses convolutional neural network methods and unsupervised learning techniques will be demonstrated. The robotic concept design will investigate real time sensing, mapping and visualization of the invasive weeds. The system based on real-time mapping information obtained from the swarm of drones will also manage the control of the underwater robots equipped with smart networked sensors using State of the Art IoT technologies. The mechanical dislodging machine will be guided to the mapped areas and accurately controlled and guided through smart sensors via the 5G Ultra-reliable Low-Latency Communication Control (URLLC) and tactile control system to dislodge the invasive weed with no impact on other organisms and the biodiversity of the lake.","PeriodicalId":170342,"journal":{"name":"2021 IEEE AFRICON","volume":"203 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116179515","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
2021 IEEE AFRICONPub Date : 2021-09-13DOI: 10.1109/africon51333.2021.9570845
Naveenbalaji Gowthaman, V. Srivastava
{"title":"Arbitrary Alloy Semiconductor Material Based DG MOSFET for High-Frequency Industrial and Hybrid Consumer Applications","authors":"Naveenbalaji Gowthaman, V. Srivastava","doi":"10.1109/africon51333.2021.9570845","DOIUrl":"https://doi.org/10.1109/africon51333.2021.9570845","url":null,"abstract":"The performance of the transistors is a measure for the system to perform desired output. The research in the development of transistors is continuously growing and defines an efficient system and device modeling. This work shows a comparative analysis of the various materials in the double-gate (DG) MOSFET. Here, the DG MOSFETs have been constructed using high-ƙ dielectrics to reduce the short channel effects and improve the performance of the transistors, which is the unit cell of the industrial and consumer electronics devices. This MOSFET can further be optimized by enhancing the analog characteristics in the nanometer regime. This work focuses on the performance of the DG MOSFETs by considering channels like Indium Arsenide (InAs) and Indium Phosphide (InP) in the Aluminium Gallium Arsenide (AlxGa1-xAs) and Gallium Arsenide Antimonide (GaAs1-xSbx) substrates. From the simulation and tabulations, it is evident that the properties of the DG MOSFETs with these novel materials change drastically, thereby inferring the optimum materials in MOSFETs for the high speed and long haul RF applications. In this work, three different models have been proposed, namely AlxGa1-xAs/HfO2, AlxGa1-xAs/La2O3, and GaAs1-xSbx/La2O3; which shows improvement in threshold voltage with 1.16%, 1.20%, and 1.64% respectively when compared to the conventional Silicon-based DG MOSFETs.","PeriodicalId":170342,"journal":{"name":"2021 IEEE AFRICON","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115466898","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
2021 IEEE AFRICONPub Date : 2021-09-13DOI: 10.1109/africon51333.2021.9570989
L. Butgereit
{"title":"Focusing Benford’s Law on the Daily Covid-19 Cases Numbers and Daily Covid-19 Deaths Numbers","authors":"L. Butgereit","doi":"10.1109/africon51333.2021.9570989","DOIUrl":"https://doi.org/10.1109/africon51333.2021.9570989","url":null,"abstract":"Benford’s Law has been used to attempt to determine if a list of numbers has been artificially manipulated in any way. Benford’s Law is applicable to many types of lists of numbers and is often used in the accounting domain to flag possible fraud. This paper provides a history of Benford’s Law and presents a number of examples where Benford’s Law applies in the domain of geography, transportation, and economics. The goal of this research, however, is to focus Benford’s Law on the list of numbers representing daily Covid-19 cases and daily Covid-19 deaths. The lists of numbers were analysed with respect to Benford’s Law and graphs were produced comparing the Covid-19 numbers against what was predicted by Benford’s Law. The conclusion of this paper is that at a country level or at a specific date level, the datasets do not have the proper characteristics and Benford’s Law can not be used on those datasets. At a continent level, however, the datasets are much larger and wide ranging. Benford’s Law can be applied to continental datasets.","PeriodicalId":170342,"journal":{"name":"2021 IEEE AFRICON","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124769836","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
2021 IEEE AFRICONPub Date : 2021-09-13DOI: 10.1109/africon51333.2021.9570921
Reeshen Reddy
{"title":"Strategic Considerations of Industry 4.0 on Electronic Warfare using Technology Roadmaps","authors":"Reeshen Reddy","doi":"10.1109/africon51333.2021.9570921","DOIUrl":"https://doi.org/10.1109/africon51333.2021.9570921","url":null,"abstract":"The Fourth Industrial Revolution or Industry 4.0 is an ongoing industrial revolution brought about by several emerging technologies expected to disrupt most business sectors. The effect of Industry 4.0 on the Electronic Warfare (EW) sector is strategically analyzed using Technology Road Mapping (TRM). An enhanced TRM is proposed based on the fast-start TRM method that incorporates an additional military capability layer to assess the linkage between market trends and products. The enhanced TRM is applied to analyze trends, capability, product, technology, research, and resources.The TRM-based strategic analysis reveals that Industry 4.0 will create both market pull and technology push driving the required characteristics of future EW Products. The market pull effects will drive future EW products to operate in a battlespace supporting Multi-Domain Operations (MDO) and Decision Centric Warfare (DCW). Industry 4.0 will drive commercial demand for spectrum resulting in contested, congested, and shared spectrum. Advances in smart industries will facilitate prototype warfare and the Internet of Military Things (IoMT), increasing ad-hoc bespoke non-traditional threats. Traditional threats will support DCW supported by several unmanned platform concepts.Technology push effects will advance key technologies that will shape future EW products such as Artificial Intelligence (A.I), Cyber-Physical Systems (CPS), Internet of Things (IoT), and Heterogeneous Processing. Finally, we conclude that the emergent properties of future EW products will be cognitive, distributed, networked, coordinated, multi-spectral, reduced size, weight, and power (SWAP), and modular using open architectures.","PeriodicalId":170342,"journal":{"name":"2021 IEEE AFRICON","volume":"80 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121793367","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}