Category: research

MCAST @ DaSET 2023

Very pleased that our MCAST IICT undergraduate research, authored by Ms Clair Abela and myself, has been accepted and presented at the 2nd International Conference on Data Science and Emerging Technologies 2023 (DaSET 2023). Our study titled “Wound Stage Recognition using YOLOv5” focuses on the use of YOLOv5 to detect and classify pressure injuries. Clair has demonstrated great dedication and rigor in her research undertaking and excelled not just at an institute level but also at an international level, representing MCAST and Malta.

Abstract: Pressure injuries or pressure sores are lesions that develop over the bony prominences of the body. It is noted from professional nurses and from first-hand experience, that such wounds are often wrongly classified, making the healing process difficult and painful for the patient, when it does not need to be the case. This study aims to research the use of modern computer vision and artificial intelligence techniques to aid in the classification of pressure ulcers to a degree superior to that achieved by humans. The YOLOv5 algorithm was trained in various combinations of three data sets. Single-phase and multi-phase architecture models were developed and trained for the different data set configurations to identify the ideal scenario of classification for the different stages of pressure ulcers. A single-phase architecture model trained using the public data sets and enhanced with the novel data set improves on the current state of the art. While the single-phase architecture was deemed the better option for the wound stage classification throughout this study, both architectures had their own strong points. The multi-phase architecture was found to be better suited for smaller data sets, while the single-phase architecture was better suited for larger ones. It was also found that throughout both architectures, the combination of 3 data sets is varied enough, however, less is not. This study is further strengthened through the input of different viewpoints that complement the lead researcher’s work.

MCAST @ B2C 2022

It was a great pleasure to have the opportunity to present our research at the B2C 2022 Conference in Barcelona, Spain. Mr Jake Carabott has presented our research titled “A Last Mile Blockchain Based Proof of Delivery System” in which we explore the use of blockchain technology as a solution for the last mile delivery service.

In this research, Jake has custom-built a locker fitted with a smart lock that interacts with a custom-built mobile application. This application allows the owner to manage access to the locker with a courier being allowed to deposit parcels when a human is not available to gather. Access is logged on the blockchain for transparency and auditing purposes. This proof of concept prototype has been lab-tested and validated. To further complement the research an interview with a manager in a logistics company was held to get the business point of view, as well as a survey with 100 respondents to gather the end-user point of view.

The conference was packed with various other Blockchain research by other students and various keynote speakers. Thanks to MCAST IICT for the support. Special thanks to Profs. Sergey Yurish for the organization of this conference.

MCAST Research & Innovation EXPO 2021

It was a real pleasure and honour to participate and present current research undertaken at MCAST Research & Innovation Expo 2021. Great advancements and achievements from cross-institute and industry collaboration.

Mr Juan Jose Bonello, Mr Daren Scerri and I presented our work under the Continuous Assessment of Pollution and Environment Events via Satellites (CAPES), namely the Land-Use and Land-Cover project with the Malta Resource Authority, the research in remote NO2 sensing with Ms Abigail Vella, and the RemSen event.

With Ms Kimberly Terribile, Mr Juan Jose Bonello and Mr Daren Scerri we presented our research in the Recognition of Underutilized Maltese Marine Species (RUMMS).

MCAST @ ICCE-Berlin 2021

At the 11th IEEE International Conference on Consumer Technology, six undergraduate research have been published. Mr Justin Duncan, Mr Sigmond Gatt, Ms Yanika Mifsud and Mr Owen Xuereb were mentored by myself, whilst Ms Zvetlana Bajada and Mr Silvan Vella were mentored by Mr Daren Scerri.

Mr Justin Duncan has undertaken research in “Social Distancing Crowd Segmentation, Estimation and Visualisation”. Mr Sigmond Gatt researched “Use of Blockchain Technology in Automation of Ad-Hoc Leasing Agreements”. Ms Yanika Mifsud has researched “Dance Style Classification by LSTM RNN”. Mr Owen Xuereb researched “A Grad-CAM and YOLO based approach to extracting a human passageway ROI”. Ms Zvetlana Bajada focused her research in “A Cloud-based Edtech Framework for Augmenting 3D Objects to Assist Vocational Learning”. Mr Silvan Vella has researched “Vision-based Health Protocol Observance System for Small Rooms”.

It was also an honour and privilege to have served on the Technical Programme Committee where I had the opportunity and pleasure of reviewing other research. Thank you to the team.

Well done to all students for your hard work and dedication.

MCAST @ BNAIC/BENELEARN 2021

On the 10th November 2021, MCAST IICT was represented by Ms Abigail Vella who presented our research in “Remote NO2 emissions assessment during COVID-19 lockdowns” at the BNAIC/BENELEARN 2021 conference. This work was also assisted by Mr Daren Scerri. We made use of the European Space Agency Copernicus Sentinel-5 satellites and observed the emissions for the months of March-May of 2019 and 2020. Our observations were strongly correlated with official reports by the Environment & Resource Authority, to whom we presented our findings. A really well done to Ms Abigail Vella for her hard work and dedication, really proud of our work.

A really well done to the organising committee of the conference and to the University of Luxembourg for such a wonderful and inspiring event. Strongly recommend the event and venue.

RemSen 21

This year, Mr Daren Scerri and I have set up and organized the first Remote Sensing hackathon for MCAST, named RemSen 21. This event started in February till June of this year, during which we trained our IICT degree students in the use of the European Space Agency Copernicus Sentinel-2 satellite data. For the competition, the participants were requested to research topics of local relevance and of environmental importance. Supporting this event was the Ministry for the Environment & Climate Change Planning, Environment & Resource Authority, EIC-Climate KIC Malta and eSkills Foundation Malta. On the 11th of June, we had a half-day seminar during which our participants presented their work. We wish to congratulate all participants: Abigail Vella, Dylan Luke Abela, Eman Paul Abela, Gabriel Gauci, Ismael Scicluna, Kurt Agius, Leonard Bruno, Luke Zammit, Mandy Cortis, Marc Finger, Massimo Darmanin and Robert Meli. Special congratulations go to Ms Mandy Cortis for being recognised with the best overall project for her research in the progress done in Wied Fulija; to Mr Leonard Bruno for being recognised with the best technical development with his research in Maltese coastline erosion; finally to Mr Massimo Darmanin for being recognised with the best impact project for his research in various uses of Remote Sensing in Malta. Our intention is to focus on the Sentinel-2 and Sentinel-5 satellites for RemSen 22. Thank you and well done to all.

COVID-19 a powerful time-series visualisation

Under these difficult times due to the COVID-19 pandemic we have all learnt to appreciate the importance and value of data and visualisations. For that reason at Lobeslab Ltd. we have taken the John Hopkins University dataset and empowered it with additional information, giving a focus on time-series visualisations and projections. Check the full article here.

Theme: Overlay by Kaira