The SciFest National Final celebrates the very best in STEM innovation in second-level education and offers the public a chance to engage with inspiring speakers and advocates of STEM.
At the SciFest National Final 2024 award-winning students from SciFest@College will compete for a number of prestigious awards.
St Josephs' Secondary School will be represented by Fifth Year Students Zuzanna Komon & Kamaya Gogna.
This year marks the 19th year of the SciFest programme which saw students participating in local and regional SciFest STEM fairs across the country. Since launching in 2006, more than 100,000 students have participated in the competition, which represents an average year-on-year increase of almost 20% in participation. Zuzanna & Kamaya were two of the almost 12,000 students who took part in the SciFest programme this year.
Click here to read a message from President Higgins to the competitors.
The 2024 National Final will take place on Thursday 28 November and Friday 29 November. See the full Programme of Events and Speakers here
The programme on Thursday will take place online from 7.00 p.m. For more information on the speakers and their talks please follow the Read more links. To view the talks please click on the icon in the View column. Talks will be available for viewing on Thursday 28 November.
On Friday, The SciFest National Final 2024 takes place in the Marino Conference Centre, Griffith Avenue, Dublin 9. The Awards Ceremony will be streamed live on this platform here and on YouTube.
The Awards Ceremony will Friday 29th November at 2:00pm and can be viewed on the SciFest National Final website here or directly on YouTube. Best of Luck to all the competitors.
Congratulations Kamaya and Zuzanna who both received STEM Excellance awards.
Zuzanna explains that ' The primary goal of this project was to investigate simultaneous increases and decreases in radiation levels detected by Geiger-Müller counters in close proximity, despite the random nature of radioactive decay.
The rise and fall in radiation seemed more like a pattern than random noise, suggesting the possibility of density fields. Having a better understanding of the type of random noise could be useful in calibrating radiation detectors such as X-Ray and Gamma Ray telescopes.
I measured with five Geiger counters (FS2011, QA060, XH-901, BELLA, RAD 100) at different intervals. At 35-second intervals close together, the correlation here was low at <0.6 so I performed a speed read using shorter intervals, hypothesising that radiation fields were changing in density faster than our detectors could register. With 5-second intervals, keeping the same close distance, significant correlation was found between the counters. Far apart, no correlation was detected, suggesting the presence of small, transient hotspots or cold spots, passing by us in mere seconds. '
Following the completion of the regional SciFest@College 2024 STEM fairs a panel of judges appointed by Boston Scientific and SciFest will assess the projects, based on the report books, and select the projects to go forward to compete at the National Final 2024.
The Boston Scientific award is presented to the project that best demonstrates:
- Understanding of a problem/unanswered question related to science or engineering in the field of medical devices
- Understanding of an area where you have experience or are aware of something to help / improve /change a person’s quality of life who may have a medical need - parent / sister / brother / grandparent / classmate
- A contribution to the medical device field through research/experimentation
The best of the winners of this award at the regional fairs compete at the National Final for the Boston Scientific Medical Devices Grand Award.
Kamaya explains her project with the following abstract ' Dental radiolucencies appear as darker regions in X-ray images, indicating reduced tissue density, which can suggest conditions ranging from benign lesions to serious pathology. Radiolucencies are broadly categorized into intraosseous (within the tooth structure) and periapical (in surrounding bone), each type exhibiting distinct morphological features. My project employs machine learning, specifically integrating active contour models and fuzzy logic, to streamline the classification and analysis of these radiolucent areas.
Active contour models assist in the segmentation of X-ray images by dynamically outlining regions of interest, a crucial step for isolating radiolucent areas accurately. Fuzzy logic, designed to handle imprecision in medical imaging, improves the algorithm’s ability to classify areas with overlapping or ambiguous boundaries, enhancing diagnostic accuracy.
Using reinforcement learning principles, I developed a neural network-based classification algorithm, which I rigorously coded and tested. Training involved supervised learning with labelled datasets, allowing the model to iteratively optimize for increased accuracy. Once validated, the algorithm was deployed through two website prototypes, enabling accessible, real-world application of the tool for healthcare professionals.
Machine learning-based classification not only expedites radiolucency analysis but also handles large datasets with a consistency and efficiency that would be challenging for manual assessment. This project applies advanced machine learning methodologies and holds potential as a diagnostic aid, allowing dental professionals to better identify and evaluate radiolucent regions, ultimately supporting more timely and precise patient care.'
St Joseph's would like to thank SciFest and it's sponsers for giving our students the opportunity to compete at such a high level. They believe that with continued effort anything is possible.