Student Stories: Cohort 1 student, Emmanouil Pitsikalis, shares details of his recent papers re scalable maritime analytics

Published on

 impact-on-studies-pod

Cohort 1 student, Emmanouil Pitsikalis, shares details of his recent papers submitted for two summer conferences relating to scalable maritime analytics


My Journey

I received my Bachelor of Science in Computer Science from the Department of Informatics and Telecommunications of the National Kapodistrian University of Athens in 2018. During my BSc thesis I worked on maritime monitoring related research at the National Centre for Scientific Research "Demokritos" in Greece. In 2019, I applied for a PhD studentship at the Distributed Algorithms CDT.

My Project

Nowadays, shipping is one of the most important industries that undeniably requires increased security and safety. Both security and safety can be improved through maritime analytics applied on the massive amount of currently available heterogeneous maritime data.  Using data from multiple sources, such as CCTV, AIS and RADAR, tasks such as vessel type classification, vessel behavioural analysis, and anomaly detection can effectively be addressed. In my project, in a collaboration between the University of Liverpool and Denbridge Marine, we focus on ship type classification using novel methods and scalable maritime analytics over AIS and RADAR streams.

Recent Publications

My publication entitled "Logic Rules Meet Deep Learning: A Novel Approach for Ship Type Classification" has been accepted at the RuleML+RR 2021 conference. The paper shows that our work combines logic rules with deep learning in order to use data of different format, i.e., vessel images and AIS static transmitted data for ship type classification. Our evaluation results showed that our model can increase prediction scores by up to 15.4% when compared with the next best model we considered, while also maintaining a level of explainability as opposed to common black box approaches.

Manolis received the newly introduced “Harold Boley Award for Most Promising Paper” which is given to the paper that seems to be the most promising and based on its reviews.  The award was introduced at this year's conference, in memory of Harold Boley, and will now be awarded each year during the RuleML+RR conferences.

In another paper entitled "Representation and Processing of Instantaneous and Durative Temporal Phenomena", which was presented in the 31st International Symposium on Logic-based Program Synthesis and Transformation (LOPSTR 2021), we propose a new logic based temporal phenomena definition language, specifically tailored for Complex Event Processing, that allows the representation and processing of both instantaneous and durative phenomena and the temporal relations between them. Moreover, we introduce `Phenesthe' (https://github.com/manospits/Phenesthe), an open source Complex Event Processing system utilising our new phenomena definition language.

Distributed Algorithms CDT 

The Distributed Algorithms CDT is an Innovative Data Science, AI and Machine Learning Research Centre, aligning PhD students, academics and industrialists to work together to generate novel solutions to tough data science challenges. If you would like to find out more about our programme and would like to talk about becoming an active member of our CDT community, please visit our website or email kelli.cassidy@liverpool.ac.uk