Latest News Archive

Please select Category, Year, and then Month to display items
Previous Archive
15 January 2024 | Story André Damons | Photo Supplied
CHPC students read more
The top finishing UFS team, Team 5, consisting of Nhlonipho Shezi, Kgoboketso Mphahlele, Albert van Eck (mentor), Itumeleng Khaka, and Bophelo Pharasi came third during the national round of the National Integrated Cyber Infrastructure Systems (NICIS) CHPC’s Student Cluster Competition.

Two students from the University of the Free State (UFS) who took part in the National Integrated Cyber Infrastructure Systems (NICIS) CHPC Student Cluster Competition were selected as part of the National Team to compete at the International Supercomputing Conference (ISC) Student Cluster Competition next year.

Itumeleng Khaka and Nhlonipho Shezi, both currently studying towards a Bachelor of Science degree in Information Technology majoring in Computer Science and Business Management, were part of one of the university’s teams (Team 5) that took third place during the national round of the competition.

Bophelo Pharasi (Bachelor of Science in Information Technology majoring in Computer Science and Business Management) and Kgoboketso Mphahlele (Bachelor of Computer Information Systems) were the other team members, and Albert van Eck, Head of the eResearch and High-Performance Computing Unit, was their mentor. The UFS entered three teams for the competition. 

Another student, Limpho Senatla (Bachelor of Science in Information Technology), was awarded the prize for the female student with the most potential during this competition. Some of the prizes awarded to her include an opportunity to work under the mentorship of sponsors such as Tsolo.io, Diplomics, Intel, and the South African Radio Astronomy Observatory (SARAO).

The other two teams that also participated were Team OptiCompute (mentor: Hendrik van Heerden), consisting of Senatla, Siphesihle Mvelase (Bachelor of Science in Information Technology majoring in Computer Science and Business Management), Ziphezinhle Malinga (Bachelor of Science in Information Technology majoring in Computer Science and Business Management), Ennosse Mkhutyukelwa (Bachelor of Science in Information Technology majoring in Computer Science and Chemistry); and Team KKRT (mentor: Zirke le Roux), consisting of Kananelo Nyakallo Mofokeng (Bachelor of Science in Information Technology majoring in Computer Science and Physics), Boitumelo Ramasike (Bachelor of Science in Information Technology majoring in Computer Science and Business Management), Kamohelo Kolanchu (Bachelor of Science in Information Technology majoring in Computer Science and Mathematics), and Thabang Maokeng (Bachelor of Computer Information Systems).

Highly stressful and demanding

“Since 2017, the UFS has competed in the CHPC Student Cluster Competition, with various successful outcomes. This year was no exception, with Team 5 winning third place at the national round. All teams endured a highly stressful and demanding round where external factors such as load shedding, late and incomplete hardware deliveries, extreme heat, and sleep deprivation played a role,” says Van Eck.

According to its website, the Centre for High-Performance Computing (CHPC), a division of the Council for Scientific and Industrial Research (CSIR), annually hosts a Human Capital Development (HCD) programme for undergraduate students currently enrolled in Science, Technology, Engineering and Mathematics (STEM) fields at South African universities. They undergo training that will take them from zero knowledge of HPC to being able to build mini clusters through various rounds.

The competition is held annually and consists of three rounds: a selection, national, and international round. A team composed of four undergraduate (second-year) students can enter the competition.

This year, twenty teams from eight universities participated in the selection round. Each year, this round is hosted at a different university in the country, with the UFS Bloemfontein Campus playing host this year from 10 to 15 July. During the first round, students were exposed to various technologies and concepts used in HPC and scientific computing. Students were then evaluated according to their technical skills acquired during the selection round, and had to design, present, and defend a cluster design with its network topology.

The national round, for which all three UFS teams qualified, was held at the Kruger National Park from 3 to 8 December.

Travel internationally

According to Van Eck, the students were given a limited budget to procure a small cluster for this round. Students then had to assemble the cluster and start configuring it during this round. After installing and configuring their clusters, students had to install and optimise scientific software. Installing and optimising scientific software is quite challenging. One must consider various technologies such as hardware components, networking, operating systems, compilers, intercommunication between processes, and the functionality of the software.

The winning team in the national round is combined with two members of either the second or third-place winners and two reserves selected from those teams. This team will travel to Austin, Texas, early next year to visit the Texas Advanced Computing Centre (TACC). Students will also undergo more training at Dell Labs in the USA.

The team will compete at the International Supercomputing Conference (ISC) Student Cluster Competition (SCC) against teams from across America, Europe, and Asia. This competition is held in Germany and sees the best international students competing in the final round. The South African teams have won this round on several occasions.

“The competition takes all students out of their comfort zones. The technologies and methodologies they are exposed to are state-of-the-art in theoretical and computational sciences. In the first round, students are trained by industry professionals on concepts they would otherwise never be exposed to. They come into contact with multiple disciplines within IT, engineering, and some scientific fields. The learning curve during this competition is immense, but students who rise to the challenge reap the benefits in the long run. With prizes such as laptops, prize money, and mentorship from the industry, multiple opportunities can be utilised,” says Van Eck.

Exposure to various technologies

Van Eck says even members from teams that do not make it into the top positions can benefit from exposure to various technologies and networking with other delegates. Leveraging knowledge attained during the competition also enhances one's ability to apply knowledge to other parts of one's career.

“To become an HPC specialist, one must master various field-specific domains, and each of these domains can become a career in itself should a student identify a specific field of more interest to them. This type of exposure is usually only experienced once one enters the workforce. It may be difficult and costly to enter a specific domain by that time. Earlier exposure during a competition like this can assist a student in identifying which fields of science, engineering, or IT they would like to focus on and perhaps later specialise in.”

News Archive

Mathematical methods used to detect and classify breast cancer masses
2016-08-10

Description: Breast lesions Tags: Breast lesions

Examples of Acho’s breast mass
segmentation identification

Breast cancer is the leading cause of female mortality in developing countries. According to the World Health Organization (WHO), the low survival rates in developing countries are mainly due to the lack of early detection and adequate diagnosis programs.

Seeing the picture more clearly

Susan Acho from the University of the Free State’s Department of Medical Physics, breast cancer research focuses on using mathematical methods to delineate and classify breast masses. Advancements in medical research have led to remarkable progress in breast cancer detection, however, according to Acho, the methods of diagnosis currently available commercially, lack a detailed finesse in accurately identifying the boundaries of breast mass lesions.

Inspiration drawn from pioneer

Drawing inspiration from the Mammography Computer Aided Diagnosis Development and Implementation (CAADI) project, which was the brainchild Prof William Rae, Head of the department of Medical Physics, Acho’s MMedSc thesis titled ‘Segmentation and Quantitative Characterisation of Breast Masses Imaged using Digital Mammography’ investigates classical segmentation algorithms, texture features and classification of breast masses in mammography. It is a rare research topic in South Africa.

 Characterisation of breast masses, involves delineating and analysing the breast mass region on a mammogram in order to determine its shape, margin and texture composition. Computer-aided diagnosis (CAD) program detects the outline of the mass lesion, and uses this information together with its texture features to determine the clinical traits of the mass. CAD programs mark suspicious areas for second look or areas on a mammogram that the radiologist might have overlooked. It can act as an independent double reader of a mammogram in institutions where there is a shortage of trained mammogram readers. 

Light at the end of the tunnel

Breast cancer is one of the most common malignancies among females in South Africa. “The challenge is being able to apply these mathematical methods in the medical field to help find solutions to specific medical problems, and that’s what I hope my research will do,” she says.

By using mathematics, physics and digital imaging to understand breast masses on mammograms, her research bridges the gap between these fields to provide algorithms which are applicable in medical image interpretation.

We use cookies to make interactions with our websites and services easy and meaningful. To better understand how they are used, read more about the UFS cookie policy. By continuing to use this site you are giving us your consent to do this.

Accept