BEGIN:VCALENDAR VERSION:2.0 PRODID:-//CERN//INDICO//EN BEGIN:VEVENT SUMMARY:Investigating the Prospects of Blockchain Technology in an Elector al System DTSTART;VALUE=DATE-TIME:20240703T072500Z DTEND;VALUE=DATE-TIME:20240703T074500Z DTSTAMP;VALUE=DATE-TIME:20260307T152955Z UID:indico-contribution-134-2031@events.chpc.ac.za DESCRIPTION:Voting is part of our fundamental rights. It is crucial to hav e open and fair elections. As part of taking part in the election process\ , those voting need to have the utmost trust and confidence in the electio n processes and its outcome. When the underlying trust\, confidence\, and respect for the election is eroded by news of vote manipulation and disreg ard of processes by the officials overseeing the election\, the voters are less interested in voting as they believe the elections are rigged and se rves no purpose to participate in such an important exercise. The current voting systems which are often inundated by problems such as voter fraud\, ballot tampering\, and lack of transparency\, necessitate a robust\, secu re\, and transparent alternative. This research attempts to address some o f the issues relating to having an unsecured voting system. The focus of t he research is to investigate the prospects of implementing a blockchain b ased electoral system. Implementation of the blockchain technology\, a dec entralized ledger technology which is characterized by its immutability\, transparency\, and security\, might address some of the security challenge s with the current electoral systems. Furthermore\, the study examines the principles of blockchain technology and evaluates its application in vari ous stages of the electoral processes.\n\nhttps://events.chpc.ac.za/event/ 134/contributions/2031/ LOCATION:CSIR ICC ICC-G-Ruby - Ruby Auditorium URL:https://events.chpc.ac.za/event/134/contributions/2031/ END:VEVENT BEGIN:VEVENT SUMMARY:Welcome DTSTART;VALUE=DATE-TIME:20240703T060000Z DTEND;VALUE=DATE-TIME:20240703T060500Z DTSTAMP;VALUE=DATE-TIME:20260307T152955Z UID:indico-contribution-134-2267@events.chpc.ac.za DESCRIPTION:Welcome by Programme Director\, \nby\nMrs Ina Smith\nASSAf Pla nning Manager\n\nhttps://events.chpc.ac.za/event/134/contributions/2267/ LOCATION:CSIR ICC ICC-G-Ruby - Ruby Auditorium URL:https://events.chpc.ac.za/event/134/contributions/2267/ END:VEVENT BEGIN:VEVENT SUMMARY:Wrap Up Day 1 DTSTART;VALUE=DATE-TIME:20240702T141000Z DTEND;VALUE=DATE-TIME:20240702T141500Z DTSTAMP;VALUE=DATE-TIME:20260307T152955Z UID:indico-contribution-134-2266@events.chpc.ac.za DESCRIPTION:Speakers: Ina Smith (Academy of Science of South Africa (ASSAf ))\nWrap Up Day 1\nby\nMrs Ina Smith\nProgramme Director\;\n\nhttps://even ts.chpc.ac.za/event/134/contributions/2266/ LOCATION:CSIR ICC ICC-G-Ruby - Ruby Auditorium URL:https://events.chpc.ac.za/event/134/contributions/2266/ END:VEVENT BEGIN:VEVENT SUMMARY:Big Data Analytics for Intelligent Temperature Prediction in CNC M achining using PCA and AI DTSTART;VALUE=DATE-TIME:20240702T135000Z DTEND;VALUE=DATE-TIME:20240702T141000Z DTSTAMP;VALUE=DATE-TIME:20260307T152955Z UID:indico-contribution-134-2040@events.chpc.ac.za DESCRIPTION:Speakers: ZVIKOMBORERO HWEJU (Lecturer\, Chinhoyi University o f Technology\, Zimbabwe)\, Varaidzo Dandira-Chibaya (Lecturer\, Chinhoyi U niversity of Technology)\nAbstract. Temperature prediction is crucial in C NC machining to prevent overheating\, tool damage\, and surface finish qua lity. This study presents a big data analytics framework for intelligent t emperature prediction in CNC machining using Principal Component Analysis (PCA) and Artificial Intelligence (AI). The following methodology has been followed during the CNC machining of EN18 Steel: data collection from lab oratory CNC machining\, normalization of the collected data to ensure cons istency and comparability\, application of PCA to the preprocessed data to reduce dimensionality\, training of AI models (ANN\, ANFIS and Random For est) using PCA-extracted features and temperature data\, performance evalu ation of the AI models using mean absolute error and coefficient of determ ination\, utilization of the trained AI model to predict temperature value s for new\, unseen data\, comparison of the AI model results to those of t he traditional Linear Regression Model. The proposed approach predicts tem perature with high accuracy of above 95%. The results show improved predic tion performance compared to the traditional linear regression method\, de monstrating the effectiveness of intelligent big data analytics and AI in CNC machining. This research contributes to the development of Industry 4. 0 technologies\, enhancing manufacturing efficiency\, productivity\, and p roduct quality.\nKeywords: Big Data analytics\, Principal Component Analys is (PCA)\, Artificial Intelligence (AI)\, Temperature Prediction.\n\nhttps ://events.chpc.ac.za/event/134/contributions/2040/ LOCATION:CSIR ICC ICC-G-Ruby - Ruby Auditorium URL:https://events.chpc.ac.za/event/134/contributions/2040/ END:VEVENT BEGIN:VEVENT SUMMARY:Data mining\, management and modelling in advancing water and sani tation systems DTSTART;VALUE=DATE-TIME:20240702T133000Z DTEND;VALUE=DATE-TIME:20240702T135000Z DTSTAMP;VALUE=DATE-TIME:20260307T152955Z UID:indico-contribution-134-2044@events.chpc.ac.za DESCRIPTION:Speakers: Ridhwaan Suliman (CSIR)\nData mining and management play an important role in advancing water and sanitation systems\, ensurin g the sustainable delivery of essential services. The application of data mining encompasses the collection\, processing\, and analysis of vast data sets derived from various sources such as sensor networks\, satellite imag ery\, and public health records. These techniques facilitate the identific ation of patterns\, trends\, and anomalies\, which are important for infor med decision-making and strategic planning.\n \nBy leveraging predictive a nalytics\, water management authorities can anticipate demand fluctuations \, optimise resource allocation\, and enhance the efficiency of distributi on networks. Similarly\, in sanitation\, data mining assists in monitoring system performance\, detecting potential failures\, and mitigating health risks by providing early warnings of contamination events. Moreover\, the adoption of robust data management frameworks ensures the integration\, s torage\, and accessibility of diverse datasets\, supporting real-time moni toring and long-term strategic initiatives. Challenges such as data privac y\, accuracy\, and the need for interdisciplinary collaboration need to be addressed to ensure the reliability and efficacy of these systems. The co nvergence of data mining and management in water and sanitation sectors ho lds significant promise for enhancing operational efficiency\, ensuring re source sustainability\, and safeguarding public health. \n\nData integrati on poses a significant hurdle due to varying formats and structures across different sources. The main challenge is data quality and accuracy with i ssues like missing values and outliers. Water databases may contain divers e types of data\, including spatial\, temporal\, and multi-dimensional inf ormation. Integrating and reconciling these different types of data can be challenging\, especially when they come from various sources with distinc t formats and structures.\n\nMachine learning is a rapidly expanding field of computer science with diverse applications. Understanding seasonal rai nfall changes is crucial for both academic and societal objectives. Curren t data on surface and groundwater\, including water quality and quantity w as reviewed. Collecting real-time data\, using automated sensors\, and int egrating remote sensing technologies helped understand water quality dynam ics. Data from the Geographical Information System (GIS) was collected to better understand the spatial distribution of water quality and quantity f actors. Integrating GIS data enhances our understanding of water resources . \n\nAfter collection\, data was cleaned for accuracy and dependability. After analysing the water datasets\, it was found that the random forest ( RF) method outperforms all the water quality classification models tested in this project\, with a good combination of precision and recall across b oth classes. Although support vector machines are good at identifying nega tive classes\, they struggle with positive ones. Linear regression\, also known as logistic regression\, has limits when separating water quality gr oups. Although decision tree models have balanced performance\, there is s till potential for development. When estimating water volume\, both linear regression and RF models do moderately well\, but the latter struggles to capture the underlying patterns. A negative R2 score for the RF model imp lies a lack of substantial predictive potential\, necessitating additional research or evaluation of alternative models.\n\nhttps://events.chpc.ac.z a/event/134/contributions/2044/ LOCATION:CSIR ICC ICC-G-Ruby - Ruby Auditorium URL:https://events.chpc.ac.za/event/134/contributions/2044/ END:VEVENT BEGIN:VEVENT SUMMARY:The Future of Research Data: Open Science\, FAIR Principles\, and Effective Governance DTSTART;VALUE=DATE-TIME:20240702T125000Z DTEND;VALUE=DATE-TIME:20240702T131000Z DTSTAMP;VALUE=DATE-TIME:20260307T152955Z UID:indico-contribution-134-2038@events.chpc.ac.za DESCRIPTION:Speakers: Thapelo Maredi ()\nIn the realm of research\, effect ive data governance plays a pivotal role in ensuring the integrity\, acces sibility\, and usability of research data. We delve into the significance\ , methodologies\, and complexities involved in establishing robust data go vernance frameworks tailored specifically for research data.\nResearch dat a governance encompasses the policies\, processes\, and infrastructure whi ch facilitate data management\, sharing\, and reuse while adhering to ethi cal\, legal\, and regulatory requirements. This abstract elucidates key co mponents of research data governance\, including data management plans\, d ata stewardship\, metadata standards\, and data sharing protocols.\nMoreov er\, it addresses the unique challenges encountered in governing research data\, such as heterogeneous data formats\, disciplinary differences\, and evolving data management practices. Strategies for overcoming these chall enges\, such as community-driven standards development\, interoperable dat a repositories\, and data curation services\, are explored.\nFurthermore\, it discusses emerging trends and technologies shaping the landscape of re search data governance\, such as open science initiatives\, FAIR principle s (Findable\, Accessible\, Interoperable\, Reusable)\, and machine-readabl e data policies. It emphasises the need for collaborative efforts among re searchers\, institutions\, funding agencies\, and policymakers to foster a culture of responsible data stewardship and data sharing.\n\nhttps://even ts.chpc.ac.za/event/134/contributions/2038/ LOCATION:CSIR ICC ICC-G-Ruby - Ruby Auditorium URL:https://events.chpc.ac.za/event/134/contributions/2038/ END:VEVENT BEGIN:VEVENT SUMMARY:National Policy Data Observatory (NPDO) DTSTART;VALUE=DATE-TIME:20240702T121000Z DTEND;VALUE=DATE-TIME:20240702T123000Z DTSTAMP;VALUE=DATE-TIME:20260307T152955Z UID:indico-contribution-134-2264@events.chpc.ac.za DESCRIPTION:Speakers: Ross Holder (CSIR)\nThe National Policy Data Observa tory (NPDO) is a government-led initiative\, currently hosted at the CSIR\ , with the main objective to support data-driven decision making in govern ment on various socio-economic interventions. The NPDO was initiated at th e height of the Covid-19 pandemic by the DSI\, supported by the CSIR\, Sta tistics SA and South African Revenue Service. The NPDO leverages the CSIR ’s high-speed networking infrastructure (SANReN) and high-performance co mputing infrastructure (CHPC) under the National Integrated Cyber Infrastr ucture System.\n\nhttps://events.chpc.ac.za/event/134/contributions/2264/ LOCATION:CSIR ICC ICC-G-Ruby - Ruby Auditorium URL:https://events.chpc.ac.za/event/134/contributions/2264/ END:VEVENT BEGIN:VEVENT SUMMARY:Update on NICIS 100Gbps Data Transfer Services – 1TB in 3mins! DTSTART;VALUE=DATE-TIME:20240702T084000Z DTEND;VALUE=DATE-TIME:20240702T085500Z DTSTAMP;VALUE=DATE-TIME:20260307T152955Z UID:indico-contribution-134-2032@events.chpc.ac.za DESCRIPTION:Speakers: Kasandra Pillay (SANReN)\nMoving large amounts of da ta poses a significant challenge. In most cases\, networks optimised for b usiness operations are neither designed nor capable of meeting the data mo vement requirements of data-intensive research. When scientists attempt t o run data intensive applications over these so-called “general-purpose ” or enterprise networks\, the result is often poor performance. In many cases\, this poor performance significantly impacts the scientific missio n\, leading to challenges such as not receiving data on time or resorting to “desperate” measures\, such as physically shipping disks.\n\nThere has been a significant increase in available network capacity and a greate r need to be able to transfer large amounts of data efficiently. The CSIR through SANReN\, NICIS offers a Data Transfer Service as an effort to faci litate the movement of large datasets by South African researchers and sci entists.\n\nWith the implementation of the SANReN 100Gbps backbone network capacity\, 100Gbps Data Transfer Nodes have been implemented in Cape Town and Johannesburg with Globus (globus.org) data transfer software installe d. The best international data transfer results seen were between Johannes burg/Cape Town DTNs and Colorado (NCAR GLADE). Data transfer speeds reache d between 4.78GB/s-5.48GB/s\, which resulted in 1TB of data being moved in only 3 minutes!\n\nIf you have large data transfer requirements\, please contact pert@sanren.ac.za for assistance.\n\nhttps://events.chpc.ac.za/eve nt/134/contributions/2032/ LOCATION:CSIR ICC ICC-G-Ruby - Ruby Auditorium URL:https://events.chpc.ac.za/event/134/contributions/2032/ END:VEVENT BEGIN:VEVENT SUMMARY:The prediction of the South African elections’ outcome DTSTART;VALUE=DATE-TIME:20240702T072000Z DTEND;VALUE=DATE-TIME:20240702T081000Z DTSTAMP;VALUE=DATE-TIME:20260307T152955Z UID:indico-contribution-134-2042@events.chpc.ac.za DESCRIPTION:Speakers: Paul Mokilane ()\nAbstract\nThe CSIR used its highly acclaimed elections prediction model to predict the outcome of the 2024 e lections held on the 29 May 2024. This model was initially developed for S outh African elections and was first introduced during the 1999 general el ections. Since its inception\, the model has successfully forecasted the o utcomes for local government elections with just 5% to 10% of VDs declared . It has garnered international recognition for its accuracy across variou s electoral systems. The tool also plays an integral role in authenticatin g the final results of the elections.\nThe model relies on two main princi ples of understanding voting behaviour: past voting patterns and influence s from political\, socioeconomic and demographic factors. Using this data\ , CSIR statisticians and data scientists group voters into clusters\, anti cipating that changes in voting behaviour will be similar within each grou p. When the early results arrive\, the model uses this data to estimate ne w voting behaviour for similar groups of districts. These estimates are th en extended to the remaining districts yet to be counted. By combining kno wn results with predicted ones\, the model then generates a final predicti on. The model correctly predicted that the ANC would lose their majority\, even though they would remain the leading party in the country and predic ted that the MK party would overtake the EFF to be the 3rd largest party i n the country. The predictions for the MK party were surprisingly good\, c onsidering they were a new party\, and the model predicted their support t o be close to 14% of the votes at a time in the counting process when the scoreboard was only showing their support to be around 8%. Overall\, predi ctions for the top 6 parties performed well from around 10% of the VDs dec lared\, with the ANC prediction taking longer to stabilize than the other parties but remaining within the 2% error margin once predictions were rel eased.\n\nhttps://events.chpc.ac.za/event/134/contributions/2042/ LOCATION:CSIR ICC ICC-G-Ruby - Ruby Auditorium URL:https://events.chpc.ac.za/event/134/contributions/2042/ END:VEVENT BEGIN:VEVENT SUMMARY:DOCiD (Digital Object Container iD) by the Africa PID Alliance DTSTART;VALUE=DATE-TIME:20240702T065000Z DTEND;VALUE=DATE-TIME:20240702T072000Z DTSTAMP;VALUE=DATE-TIME:20260307T152955Z UID:indico-contribution-134-2018@events.chpc.ac.za DESCRIPTION:Speakers: Nabil Ksibi (Africa PID Alliance)\nThe Africa PID Alliance’s overall objective is to produce DOIs in Africa through i ts open infrastructure and the integration of different identifiers to disseminate indigenous knowledge \, cultural heritage and patent da ta.\n\n The DOI being produced by the Africa PID Alliance is called the Digital Object Container Identifier (DOCiD TM) which is multilinear i n nature and can accommodate different other identifier types and conn ect to the object being assigned.\n\n To achieve this goal The Africa PID Alliance intends to be a global open infrastructure provider\, where pa rtnership conversations have began with the DOI Foundation membership.\n \nIn this participation to the honourable DIRISA 2024 Annual National Rese arch Data workshop\, we intend to present the latest updates about our DOC iD and seek further collaboration and partnerships to build up on what we achieved so far.\n\nhttps://events.chpc.ac.za/event/134/contributions/2018 / LOCATION:CSIR ICC ICC-G-Ruby - Ruby Auditorium URL:https://events.chpc.ac.za/event/134/contributions/2018/ END:VEVENT BEGIN:VEVENT SUMMARY:Update on South African Cyberinfrastructure Initiatives DTSTART;VALUE=DATE-TIME:20240702T062000Z DTEND;VALUE=DATE-TIME:20240702T063500Z DTSTAMP;VALUE=DATE-TIME:20260307T152955Z UID:indico-contribution-134-2265@events.chpc.ac.za DESCRIPTION:Update on South African Cyberinfrastructure\nInitiatives\nby\n Dr Happy Sithole\nNICIS Centre Manager\n\nhttps://events.chpc.ac.za/event/ 134/contributions/2265/ LOCATION:CSIR ICC ICC-G-Ruby - Ruby Auditorium URL:https://events.chpc.ac.za/event/134/contributions/2265/ END:VEVENT BEGIN:VEVENT SUMMARY:Opening DTSTART;VALUE=DATE-TIME:20240702T060500Z DTEND;VALUE=DATE-TIME:20240702T062000Z DTSTAMP;VALUE=DATE-TIME:20260307T152955Z UID:indico-contribution-134-2036@events.chpc.ac.za DESCRIPTION:Speakers: Lulama Wakaba (NGEI Executive Manager)\nOpening\nby\ nNGEI Executive Manager\nDr Lulama Wakaba\n\nhttps://events.chpc.ac.za/eve nt/134/contributions/2036/ LOCATION:CSIR ICC ICC-G-Ruby - Ruby Auditorium URL:https://events.chpc.ac.za/event/134/contributions/2036/ END:VEVENT BEGIN:VEVENT SUMMARY:How do we measure the impact of big data in society? DTSTART;VALUE=DATE-TIME:20240702T063500Z DTEND;VALUE=DATE-TIME:20240702T065000Z DTSTAMP;VALUE=DATE-TIME:20260307T152955Z UID:indico-contribution-134-2037@events.chpc.ac.za DESCRIPTION:Speakers: Daniel Manama Mokhohlane (DSI)\nHow do we measure th e impact of big data in\nsociety?\nby\nDSI Deputy Director\, Cyber Infrast ructure\nMr Daniel Mokhohlane\n\nhttps://events.chpc.ac.za/event/134/contr ibutions/2037/ LOCATION:CSIR ICC ICC-G-Ruby - Ruby Auditorium URL:https://events.chpc.ac.za/event/134/contributions/2037/ END:VEVENT BEGIN:VEVENT SUMMARY:Spatial Modelling of Irrigation Water Quality: Assessing SAR in So uth Africa's Agricultural Landscapes DTSTART;VALUE=DATE-TIME:20240702T103000Z DTEND;VALUE=DATE-TIME:20240702T105000Z DTSTAMP;VALUE=DATE-TIME:20260307T152955Z UID:indico-contribution-134-2016@events.chpc.ac.za DESCRIPTION:Speakers: Danielle Roberts (University of KwaZulu-Natal)\, Xol ani Nocanda (CSIR Water Centre)\nThe Sodium Absorption Ratio (SAR) is a cr itical metric used to assess the suitability of water for agricultural irr igation\, reflecting the potential for sodium to accumulate in soil and ne gatively affect crop yield and the ecosystem. In South Africa\, agricultur e is a cornerstone of economic development\, contributing significantly to GDP and employment. Identifying geographical locations with poor SAR meas ures is essential for sustaining agricultural productivity and environment al health. In this study\, a generalized additive model (GAM) was employed to analyse the spatial distribution of the SAR across South Africa. The m odel incorporated a spatial effect based on the geographical coordinates o f the sample locations. This allowed for the investigation of how geograph ical factors influence the SAR in various regions across South Africa\, wh ile controlling for predictors\, such as other water quality parameters. T he study made use of data from inorganic water chemistry analysis of sampl es from rivers\, dams and lakes that were collected between the years 1970 to 2011 in South Africa. The significance of this research lies in its ca pacity to pinpoint locations with poor water quality\, thereby guiding int erventions aimed at soil and water management to avert potential degradati on of arable land. The findings of this study not only aid in optimizing r esource allocation for improving water quality but also contribute to the broader objectives of sustainable agricultural practices and economic stab ility in South Africa. \n\nAlongside this study\, an interactive dashboard in under development for the monitoring and evaluation of water quality d ata in South Africa. The dashboard incorporates visualizations and importa nt summary measures for SAR as well as other various water quality paramet ers. This tool democratizes access to vital information\, enabling stakeho lders to make informed decisions based on comprehensive water data analysi s and visualizations. This tool not only enhances transparency and account ability but also facilitates a more targeted and efficient allocation of r esources towards improving water quality initiatives in South Africa.\n\nh ttps://events.chpc.ac.za/event/134/contributions/2016/ LOCATION:CSIR ICC ICC-G-Ruby - Ruby Auditorium URL:https://events.chpc.ac.za/event/134/contributions/2016/ END:VEVENT BEGIN:VEVENT SUMMARY:The Significance of CoreTrustSeal Certification: A Case Study of S tellenbosch University DTSTART;VALUE=DATE-TIME:20240702T111000Z DTEND;VALUE=DATE-TIME:20240702T113000Z DTSTAMP;VALUE=DATE-TIME:20260307T152955Z UID:indico-contribution-134-2011@events.chpc.ac.za DESCRIPTION:Speakers: Xabiso Xesi (Stellenbosch University)\nAbstract:\nTh e Significance of CoreTrustSeal Certification: A Case Study of Stellenbosc h University\nStellenbosch University’s (SU) recent achievement of CoreT rustSeal (CTS) certification represents a significant milestone in the ins titution's commitment to excellence in research data management. This cert ification\, granted to its data repository\, SUNScholarData\, underscores the university's dedication to upholding international standards of data i ntegrity\, accessibility\, and sustainability.\nCTS is a globally recogniz ed certification awarded to data repositories that demonstrate adherence t o best practices in data management (Dillo and Leeuw\, 2018). For SU\, thi s certification signifies compliance with international standards\, includ ing the FAIR principles\, ensuring that research data is findable\, access ible\, interoperable\, and reusable. Moreover\, it highlights the universi ty's commitment to maintaining data integrity and quality\, thus enhancing the credibility of its research outputs.\nTo attain CTS certification\, S U had to meet a comprehensive set of requirements outlined by the CTS Boar d. These requirements encompassed data integrity and authenticity\, apprai sal criteria\, documented storage procedures\, preservation planning\, dat a quality assurance\, workflows\, data discovery and identification\, and data reuse capabilities.\nBeyond compliance\, CTS certification reinforces SU’s commitment to long-term data accessibility and preservation. By se curely storing and making research data accessible for future use\, the un iversity contributes to the longevity of scholarly contributions and facil itates collaboration across diverse research projects. Additionally\, the certification promotes interoperability\, enabling seamless data sharing a nd integration with other institutions.\nStellenbosch University's attainm ent of CTS certification enhances the trustworthiness and credibility of i ts data repository among researchers\, funders\, and the broader academic community. It positions the university as a trusted hub for valuable resea rch data and highlights its dedication to responsible data management prac tices. As Stellenbosch University continues to advance in research and inn ovation\, CTS certification serves as a guiding beacon towards a future wh ere data is managed\, preserved\, and shared responsibly for the benefit o f the global research community. \nThe aim of this presentation will be to share the experiences of SU Library and Information Service as it went th rough the rigorous process of applying for the CTS certification. Both pre senters have been intimately involved in the process from the Cape Peninsu la University of Technology (which is yet to receive a certification) and SU. It is hoped that the experiences shared may trigger more interest from other institutional repositories to follow the same process.\n\nReference s:\nDILLO\, I. & LEEUW\, L. D. 2018. CoreTrustSeal. Mitteilungen der Verei nigung Österreichischer Bibliothekarinnen & Bibliothekare\, 71\, 162-170. \n\nhttps://events.chpc.ac.za/event/134/contributions/2011/ LOCATION:CSIR ICC ICC-G-Ruby - Ruby Auditorium URL:https://events.chpc.ac.za/event/134/contributions/2011/ END:VEVENT BEGIN:VEVENT SUMMARY:Enhancing Climate Services in South Africa DTSTART;VALUE=DATE-TIME:20240703T113500Z DTEND;VALUE=DATE-TIME:20240703T115500Z DTSTAMP;VALUE=DATE-TIME:20260307T152955Z UID:indico-contribution-134-2029@events.chpc.ac.za DESCRIPTION:Speakers: DAWN MAHLOBO ()\nClimate Services plays a critical r ole in the country. It is a pertinent factor in the decision-making at var ious levels for almost all sectors and communities in South Africa. Unfort unately\, people who need it most cannot always obtain existing climate in formation or find it inaccessible when it does.\nChanges in climate\, both human-caused and natural\, have a major impact on society\, affecting are as such as the economy\, water and food security\, and overall health and well-being. South Africa has experienced noticeable changes\, including ri sing average temperatures\, increased frequency of extreme heat events\, p rolonged droughts\, and intensified floods\, all of which underscore the u rgency of addressing climate-related challenges. Collaborative efforts by different climate service providers through the National Framework for Cli mate Service (NFCS) will have to be strengthened to render climate service across all users. The NFCS aims to develop a practical model that acknowl edges the significance of emerging trends in producing climate service dat a that values consultation and involvement of climate users and the vital role users play in collaborating on climate service information. The ideas of collaborating in production and exploration are acknowledged as essent ial for the effective utilization of climate data in decision-making. This paper offers an overview of the current status of the NFCS implementation \nwithin South Africa.\n\nhttps://events.chpc.ac.za/event/134/contribution s/2029/ LOCATION:CSIR ICC ICC-G-Ruby - Ruby Auditorium URL:https://events.chpc.ac.za/event/134/contributions/2029/ END:VEVENT BEGIN:VEVENT SUMMARY:Big data and machine learning skills\, experience\, methods\, and big data usage. Empirical evidence from manufacturing firms in Zimbabwe. DTSTART;VALUE=DATE-TIME:20240703T111500Z DTEND;VALUE=DATE-TIME:20240703T113500Z DTSTAMP;VALUE=DATE-TIME:20260307T152955Z UID:indico-contribution-134-2033@events.chpc.ac.za DESCRIPTION:Speakers: Sostina Varaidzo Chibaya (Liaoning Technical Univers ity\, China)\, More Chinakidzwa (Higher Colleges of Technology\, UAE.)\nTh e use of big data and machine learning in decision making processes in man ufacturing industries is gaining momentum as manufacturers seek to enhance production performance and competitiveness. Big data technologies have tr ansformed manufacturing decision-making\, resulting in data-driven approac hes. To compete in today's dynamic market\, manufacturing organizations mu st adapt and evolve\, which necessitates the effective use of data for for ecasting future events and making decisions. Advanced analytics applied to large datasets allows firms to acquire deeper insights\, spot patterns\, forecast future trends\, and optimize processes. Limitations of convention al data processing methods create new opportunities for development and in novation. However\, in developing countries such as Zimbabwe the benefits of the use of big data are not fully realized in manufacturing industries. Three essential requirements are needed to effectively use big data. The se are big data skills\, experience using big data\, and effective data pr ocessing methods. The study focused on assessing how the three factors inf luence the utilization of big data in the manufacturing industry. Understa nding data skills\, experience and processing methods is essential in buil ding big data management skills and improving adoption in manufacturing fi rms. A preliminary survey was conducted on 36 manufacturing companies in Zimbabwe. The data was analyzed using SPSS version 27. The results showed that only 16.7% of the companies were effectively using big data. The effe ctiveness of data processing methods\, big data skills\, and experience us ing big data\, significantly affect the utilization of big data in manufac turing (p\n\nhttps://events.chpc.ac.za/event/134/contributions/2033/ LOCATION:CSIR ICC ICC-G-Ruby - Ruby Auditorium URL:https://events.chpc.ac.za/event/134/contributions/2033/ END:VEVENT BEGIN:VEVENT SUMMARY:Context-Based Question Answering using Large Language BERT Variant Models for Low Resourced Sotho sa Leboa Language. DTSTART;VALUE=DATE-TIME:20240703T103500Z DTEND;VALUE=DATE-TIME:20240703T105500Z DTSTAMP;VALUE=DATE-TIME:20260307T152955Z UID:indico-contribution-134-2026@events.chpc.ac.za DESCRIPTION:Speakers: Hlaudi Masethe (Tshwane University of Technology)\nS ince reading and responding to text needs both a grasp of natural language and awareness of the outside world\, it is challenging for machines to do (Akhila et al.\, 2023). The most difficult areas of information retrieval and natural language processing are question answering systems (QAS). The goal of the Question Answering System is to use the provided context or k nowledge base to provide replies in natural language to the user's questio ns. Both closed and open domains can produce the answers. A closed domain' s responses are limited to a specific situation\, whereas open-domain syst ems are able to provide answers in a human-readable language from a vast k nowledge base. Another issue is coming up with answers to the questions ba sed on certain situations\, as each question might have a variety of inter pretations and responses based on the context to which it relates (Kumari et al.\, 2022). In our comprehension\, this research work is the initial effort to extract answers from a context in low resourced Sesotho sa Leboa language. The Bidirectional\nEncoder Representation from Transformers (BE RT) variant model such as Albert\, and DistilBERT is used as the language model in this research study\n\nhttps://events.chpc.ac.za/event/134/contri butions/2026/ LOCATION:CSIR ICC ICC-G-Ruby - Ruby Auditorium URL:https://events.chpc.ac.za/event/134/contributions/2026/ END:VEVENT BEGIN:VEVENT SUMMARY:Machine Learning in HIV Testing: A Bibliometric Analysis of Publis hed Studies 2000-2024 DTSTART;VALUE=DATE-TIME:20240703T093500Z DTEND;VALUE=DATE-TIME:20240703T095500Z DTSTAMP;VALUE=DATE-TIME:20260307T152955Z UID:indico-contribution-134-2025@events.chpc.ac.za DESCRIPTION:Speakers: Musa Jaiteh (University of Johannesburg)\nBackground : The human deficiency virus (HIV) remains a devastating public health thr eat\, affecting 39 million people globally\, with approximately 60% of the se cases occurring in Sub-Saharan Africa. Early detection and diagnosis of HIV are crucial for preventing the further spread of the virus\, making H IV testing a pivotal tool for achieving the UNAIDS goal of ending AIDS by 2030. The World Health Organization and UNAIDS have emphasized the importa nce of adopting innovative testing strategies\, such as those involving ma chine learning. Machine learning can accurately predict high-risk individu als and facilitate more effective and efficient testing methods compared t o traditional approaches. Despite this advancement\, there exists a knowle dge gap regarding the extent to which machine learning techniques are inte grated into HIV testing strategies worldwide. To address this gap\, this s tudy aimed to analyze published studies that applied machine learning to H IV from 2000 to 2024.\nMethods: This study utilized a bibliometric approac h to analyze studies that were focused on the use of machine learning in H IV testing. Relevant studies were captured through the Web of Science dat abase using synonymous keywords. The bibliometrics package in R was used t o analyze the characteristics\, citation patterns\, and contents of 3962 a rticles\, while VOSviewer was used to conduct network violations. The anal ysis focused on the yearly growth rate\, citation analysis\, keywords\, in stitutions\, countries\, authorship\, and collaboration patterns. \nResult s: The analysis revealed a scientific annual growth rate of 8.8% with an i nternational co-authorship of 44.7% and an average citation of 23.16 per d ocument. The most relevant sources were from high-impact journals such as PLOS ONE\, Aids and Behavior\, Journal of Acquired Immune Deficiency Syndr ome\, Journal of International Aids Society\, AIDs\, and BMC Public Health . The USA\, The United Kingdom\, South Africa\, China\, and Canada produc e the highest number of contributions. The results show that the Universit y of California\, Johns Hopkins University\, Harvard University\, and the University of London have the highest collaboration networks.\nConclusion: This study identifies trends and hotspots of machine learning research re lated to HIV testing across various countries\, institutions\, journals\, and authors. These insights are crucial for future researchers to understa nd the dynamics of research outputs in this field.\n\nhttps://events.chpc. ac.za/event/134/contributions/2025/ LOCATION:CSIR ICC ICC-G-Ruby - Ruby Auditorium URL:https://events.chpc.ac.za/event/134/contributions/2025/ END:VEVENT BEGIN:VEVENT SUMMARY:Unpacking the role of information specialist at a 21st century aca demic library: Research Data Management at the University of Pretoria. DTSTART;VALUE=DATE-TIME:20240703T085500Z DTEND;VALUE=DATE-TIME:20240703T091500Z DTSTAMP;VALUE=DATE-TIME:20260307T152955Z UID:indico-contribution-134-2023@events.chpc.ac.za DESCRIPTION:Speakers: Tlou Mathiba (University of Pretoria)\nResearch data management (RDM) is rapidly becoming an essential service. This has force d higher education institutions (HEIs)\, research councils\, publishers an d funding agencies to embark on this journey. In February 2015\, in alignm ent with this global trend\, the South African National Research Foundatio n (NRF) released a statement on Open Access (OA) to Research Publications' funded by NRF. The statement states that research papers fully or partial ly funded by the NRF should be deposited to the administering institutiona l repository with an embargo period of not more than 12 months. Furthermor e\, the statement states that “the data supporting the publication shoul d be deposited in a trusted Open Access repository\, with the provision of a Digital Object Identifier (DOI) for future citation and referencing.” In support of the NRF statement\, the University of Pretoria (UP) as a re search-intensive institution and advocate for OA\, had an RDM policy (S441 7/17) approved in 2017. The university in its pursuit to implement RDM inf rastructure and services launched the research data repository\, Figshare in 2019. After the launch\, there was a change in information specialists ’ roles in order to support RDM services. The information didn’t know what their role in RDM would be and hence the researcher undertook this st udy. The research unpacks their role\, as information specialists in RDM. The University library\, as the custodian of the UP’s formal RDM drive\, must be setting the pace for all researchers. Information specialists emp loyed by this academic library are expected to be knowledgeable\, competen t and able to advise faculty staff and researchers within the institution. \n\nhttps://events.chpc.ac.za/event/134/contributions/2023/ LOCATION:CSIR ICC ICC-G-Ruby - Ruby Auditorium URL:https://events.chpc.ac.za/event/134/contributions/2023/ END:VEVENT BEGIN:VEVENT SUMMARY:Securing Identity using Biometrics and Zero Knowledge Proofs DTSTART;VALUE=DATE-TIME:20240703T083500Z DTEND;VALUE=DATE-TIME:20240703T085500Z DTSTAMP;VALUE=DATE-TIME:20260307T152955Z UID:indico-contribution-134-2028@events.chpc.ac.za DESCRIPTION:Speakers: Sthembile Ntshangase (Researcher)\, Siphelele Myaka (Cybersecurity Researcher)\nData protection and cybersecurity are distinc t concepts\, but they complement each other. Data protection ensures data integrity\, while cybersecurity protects the digital ecosystem from threat s like cyberattacks and malware. In an interconnected digital world\, iden tity is increasingly stored\, shared\, and processed as data\, including b iometrics and Personal Identifiable Information. To address these challeng es\, a method using Zero Knowledge Proofs (ZKPs) is proposed to protect bi ometrics information and secure identities. ZKPs allow one party to prove a statement is true without revealing additional information\, ensuring co nfidentiality and security without exposing the biometric information. Thi s approach not only enhances biometric data security but also addresses pr ivacy concerns associated with storing and transmitting sensitive informat ion.\n\nhttps://events.chpc.ac.za/event/134/contributions/2028/ LOCATION:CSIR ICC ICC-G-Ruby - Ruby Auditorium URL:https://events.chpc.ac.za/event/134/contributions/2028/ END:VEVENT BEGIN:VEVENT SUMMARY:Exploring Technical Challenges in Data Science Fundamentals with P ython for First-year Students at a Rural South African University DTSTART;VALUE=DATE-TIME:20240703T062500Z DTEND;VALUE=DATE-TIME:20240703T064500Z DTSTAMP;VALUE=DATE-TIME:20260307T152955Z UID:indico-contribution-134-2019@events.chpc.ac.za DESCRIPTION:Speakers: Sibukele Gumbo (Walter Sisulu University)\nAbstract. Most Eastern Cape rural schools operate in a disadvantaged context and ar e struggling to raise standards. In many rural areas\, access to quality e ducation and access to devices or other resources in information technolog y and computer science may be limited\, making such an initiative particul arly impactful. \nThe current state of high schools has a huge impact on s tudents going to universities. As an example. majority of first-year Infor mation Technology Diploma students in the selected University\, come from rural schools in the Eastern Cape (EC). Introducing data science with Pyth on to first-year students at the selected university presents an exception al opportunity to equip students with essential skills for the digital age while addressing the specific challenges of the local context. \nIn order to extract insights from data\, data science is an interdisciplinary fiel d that integrates statistical analysis\, machine learning\, and domain exp ertise. It is becoming more and more significant in a variety of global se ctors. The university can help first-year students develop the critical th inking and problem-solving abilities necessary for success in the twenty-f irst century\, as well as prepare them for future employment. Python\, a u seful and beginner-friendly programming language\, is complementary for in troducing data science concepts to beginner students. It an ideal choice f or introductory courses. Moreover\, Python's popularity in both industry a nd academia ensures that students will acquire skills relevant to their fu ture careers. Practical\, hands-on exercises can be incorporated into the course to address the unique requirements and challenges faced by rural st udents. To guarantee that every student has an equal chance to succeed\, t he institution can also offer support services like mentoring\, tutoring\, and access to computer labs and internet resources.\n\n\nIntroducing data science as supplementary content to these first-year students is a challe nge for disadvantaged students without this course background and access t o devices\, resulting in confusion\, anxiety and frustration.\nMany of the students entering the university lack basic computer and digital skills a nd have no access to devices\, in addition to the English language as a me dium of instruction used in programming. The paper focuses on some of the best approaches and support tools as well as resources for assisting disad vantaged students\, and we reflect on how they have worked out for any giv en computer programming problem-solving task.\n\nKeywords: Data Science\, Programming\, Digital Skills\, Information Technology\n\nhttps://events.ch pc.ac.za/event/134/contributions/2019/ LOCATION:CSIR ICC ICC-G-Ruby - Ruby Auditorium URL:https://events.chpc.ac.za/event/134/contributions/2019/ END:VEVENT BEGIN:VEVENT SUMMARY:Machine-learning algorithms for mapping LULC of the uMngeni catchm ent area\, KwaZulu-Natal DTSTART;VALUE=DATE-TIME:20240703T060500Z DTEND;VALUE=DATE-TIME:20240703T062500Z DTSTAMP;VALUE=DATE-TIME:20260307T152955Z UID:indico-contribution-134-2017@events.chpc.ac.za DESCRIPTION:Speakers: ORLANDO BHUNGENI (University of KwaZulu Natal)\nAbst ract: Analysis of land use/land cover (LULC) in the catchment areas is the first action toward safeguarding the freshwater resources. The LULC infor mation in the watershed has gained popularity in the natural science field as it helps water resource managers and environmental health specialists develop natural resource conservation strategies based on available quanti tative in-formation. Thus\, remote sensing is the cornerstone in addressin g environmental-related issues at the catchment level. In this study\, the performance of four machine learning algorithms (MLAs)\, such as Random F orests (RF)\, Support Vector Machine (SVM)\, Artificial Neural Networks (A NN)\, and Naïve Bayes (NB) was investigated to classify the catchment int o nine rele-vant classes of the undulating watershed landscape using Lands at 8 Operational Land Imager (L8-OLI) imagery. The assessment of the MLAs were based on the visual inspection of the analyst and the commonly used a ssessment metrics\, such as user’s accuracy (UA)\, producers’ accuracy (PA)\, overall accuracy (OA)\, and kappa coefficient. The MLAs produced g ood results\, where RF (OA= 97.02%\, Kappa= 0.96)\, SVM (OA= 89.74 %\, Kap pa= 0.88)\, ANN (OA= 87%\, Kappa= 0.86)\, and NB (OA= 68.64 Kappa= 0.58). The results show the outstanding performance of the RF model over SVM and ANN with a small margin. While NB yielded satisfactory results\, which cou ld be primarily influenced by its sensitivity to limited training samples. In contrast\, the robust per-formance of RF could be due to an ability to classify high-dimensional data with limited train-ing data.\nKeywords: uM ngeni River Catchment\; Machine learning\; LULC\; Landsat 8\; Remote sensi ng\n\nhttps://events.chpc.ac.za/event/134/contributions/2017/ LOCATION:CSIR ICC ICC-G-Ruby - Ruby Auditorium URL:https://events.chpc.ac.za/event/134/contributions/2017/ END:VEVENT BEGIN:VEVENT SUMMARY:A Robust Data Visualisation Technique for Data-Driven Decisions: I llustrations from Power Demand and Supply DTSTART;VALUE=DATE-TIME:20240702T115000Z DTEND;VALUE=DATE-TIME:20240702T121000Z DTSTAMP;VALUE=DATE-TIME:20260307T152955Z UID:indico-contribution-134-2014@events.chpc.ac.za DESCRIPTION:Speakers: Kassim Mwitondi (Sheffield Hallam University)\nOngoi ng technological advances in computing\, data acquisition and the complex interactions of Sustainable Development Goals (SDG) create a natural Big D ata environment for researchers and decision makers across fields and sect ors to tap into. Identifying the triggers of SDG targets under such condit ions is non-rivial\, not only because of the large data dimensionality and non-orthogonality nature of the SDGs\, but also due to the naturally aris ing data and information related gaps between data analysts and policy mak ers. We propose a cohesive data visualisation approach to bridging such ga ps. The approach’s main idea derives from a cohesion between technical a nd non-technical data generators and consumers. It is designed to provide a visual conduit between the two parties\, hence facilitating unified unde rstanding of the role and impact of the visualised data attributes. Visual isation of SDG-related data provides a natural interdisciplinary setting f or stakeholders to gain actionable insights into important patterns across the SDG spectrum. Identification of relevant data attributes and the natu re of their complex interactions are fundamental to creating robust data-d riven solutions. Thus\, given real-time access to the visual effects of a single or set of SDGs\, decision-makers can quickly grasp the significance of key attributes and make informed strategic choices before it is too la te. Most importantly\, the cohesive approach potentially leads to a unifie d understanding of the SDG project across the globe\, regions and within c ountries. Communicating information embedded into data attributes via inte ractive data visualisation is pivotal in optimising operational efficiency . It enables timely identification of bottlenecks\, tracking performance m etrics and making timely interventions. We illustrate the approach based o n a large time-series dataset obtained from the South African utility gian t\, ESKOM https://www.eskom.co.za/dataportal/\, covering the period 01 Apr il 2020 to 31 March 2024. The choice is motivated by ESKOM’s quest for s tabilisation of the national electricity grid by balancing supply with the demand for electricity which can realistically be validated through visua lisation and assessing demand forecasts. Visual patterns and forecasts sho w areas of attention\, potential associations with other aspects of SDGs a nd highlight paths to a unified understanding of the triggers of SDG indic ators\,between data technocrats and decision makers\, and open new paths t o interdisciplinary research.\n\nhttps://events.chpc.ac.za/event/134/contr ibutions/2014/ LOCATION:CSIR ICC ICC-G-Ruby - Ruby Auditorium URL:https://events.chpc.ac.za/event/134/contributions/2014/ END:VEVENT BEGIN:VEVENT SUMMARY:Data Management in National Assessments: A Look towards the Future DTSTART;VALUE=DATE-TIME:20240702T113000Z DTEND;VALUE=DATE-TIME:20240702T115000Z DTSTAMP;VALUE=DATE-TIME:20260307T152955Z UID:indico-contribution-134-2012@events.chpc.ac.za DESCRIPTION:Speakers: Lucy Tambudzai Chamba (Durban University of Technolo gy)\nNational assessments play a critical role in evaluating educational s ystems and informing policy decisions. However\, the effectiveness of thes e assessments hinges on robust data management practices. This article del ves into the evolving landscape of data management in national assessments \, exploring how research data repositories and services can contribute to a more secure\, accessible\, and sustainable future.\nThe paper highlight s key challenges in national assessment data management\, including data s ecurity\, long-term preservation\, and facilitating data sharing for resea rch and improvement. It will then showcase how research data repositories can address these challenges by providing secure storage\, standardized fo rmats\, and access controls. Additionally\, the article will explore how a dvancements in data services\, such as data cleaning\, harmonization\, and analysis tools\, can further empower researchers and policymakers to leve rage national assessment data effectively. By fostering collaboration betw een assessment developers\, researchers\, and data repositories\, the rese arch ensures that national assessment data becomes a valuable resource for generations to come. This article contributes to literature on data man agement by exploring how research data infrastructure plays a vital role i n propelling national assessments towards a data-driven future.\n\nhttps:/ /events.chpc.ac.za/event/134/contributions/2012/ LOCATION:CSIR ICC ICC-G-Ruby - Ruby Auditorium URL:https://events.chpc.ac.za/event/134/contributions/2012/ END:VEVENT BEGIN:VEVENT SUMMARY:AI model for securing Internet of Things communication systems in smart agriculture. DTSTART;VALUE=DATE-TIME:20240702T105000Z DTEND;VALUE=DATE-TIME:20240702T111000Z DTSTAMP;VALUE=DATE-TIME:20260307T152955Z UID:indico-contribution-134-2013@events.chpc.ac.za DESCRIPTION:Speakers: Issah Ngomane (University of Mpumalanga)\nThe rapid increase of Internet of Things (IoT) devices in smart agriculture has enab led a more connected and intelligent world. IoT devices are a collection o f interconnected systems that can communicate\, share data and information to achieve an automated environment. Smart agriculture presents a transfo rmative approach to farming that leverages technology and data-driven solu tions to address the challenges of modern agriculture\, including the need to sustain a growing global population while minimising environmental imp act and resource depletion. However\, the increase in the deployment of Io T systems has led to an increase in cyber-attacks and security challenges. Moreover\, security challenges such as man-in-the-middle\, denial and dis tributed denial of service\, botnets\, sinkhole and spoofing attacks compr omise the confidentiality\, integrity and availability (CIA) of smart agri culture. This study investigates measures deployed for anomaly detection a nd prevention in IoT smart agriculture communication systems. Furthermore\ , the study proposes a model that incorporates machine learning techniques to identify and predict anomalies in loT communication systems and adapt security measures dynamically. Python is used to develop the proposed mod el and tested on accuracy\, recall\, f1-score\, precision\, true positive rate\, false positive rate metrics. The IoT-based Datasets CIC-IDS2018\, T oN-IoT and Edge-IIoTset are used to evaluate the performance and efficienc y of the proposed model.\n\nhttps://events.chpc.ac.za/event/134/contributi ons/2013/ LOCATION:CSIR ICC ICC-G-Ruby - Ruby Auditorium URL:https://events.chpc.ac.za/event/134/contributions/2013/ END:VEVENT BEGIN:VEVENT SUMMARY:Welcome DTSTART;VALUE=DATE-TIME:20240702T060000Z DTEND;VALUE=DATE-TIME:20240702T060500Z DTSTAMP;VALUE=DATE-TIME:20260307T152955Z UID:indico-contribution-134-2035@events.chpc.ac.za DESCRIPTION:Speakers: Ina Smith (Academy of Science of South Africa (ASSAf ))\nWelcome\nby\nProgramme Director\,\nMrs Ina Smith\n\nhttps://events.chp c.ac.za/event/134/contributions/2035/ LOCATION:CSIR ICC ICC-G-Ruby - Ruby Auditorium URL:https://events.chpc.ac.za/event/134/contributions/2035/ END:VEVENT END:VCALENDAR