| |||||||
Workshops
The first day of the conference comprises a range of workshops, to be held on Tuesday 13th December. Delegates will find these events to be especially valuable where there is a current need to consider the introduction of new AI technologies into their own organisations. There will be four half-day workshops, including the Twenty-first UK CBR Workshop. Delegates are free to choose any combination of morning and afternoon sessions to attend. The programme of workshops is shown below. Note that the morning session starts at 11 a.m. to reduce the need for delegates to stay in Cambridge on the previous night. There is a lunch break from 12.30-13.15 and there are refreshment breaks from 14.45-15.15 and from 16.45-17.00. Workshops organiser: Professor Adrian Hopgood, University of Liege, Belgium
Stream 1 - Morning (11.00-12.30 and 13.15-14.45 Nightingale Room)Data stream mining Chair: Dr Frederic Stahl, University of Reading, UK The four main dimensions of Big Data are known as Volume, referring to the size of the data, Velocity, referring to the data that is generated rapidly, Veracity, referring to uncertainty in data and Variety, referring to data from different kinds of sources such as text, structure and video data. This workshop's focus is on the Velocity dimension of Big Data. The analytics of high velocity data has many applications, such as topic detection in Twitter, traffic control, network intrusion detection, etc. The difference compared with data that is stored on a disk is that real-time data may change its characteristics over time. However, decision support applications rely on the recency of their supporting data, hence, data generated at a high velocity needs to be processed ‘on the fly’. On the other hand, there are applications that are more interested in the actual change of the data, i.e. intrusion detection and network fault detection. Hence there is a need for computationally efficient real-time techniques that take changes of the data into consideration. The workshop’s aim is to bring together researchers in this field to present their latest work, discuss challenges and future directions of research in Data Stream Mining. A selection of papers from the workshop are available at the workshop web page. Programme 11am-12:30pm
1:15pm-2:45pm
Stream 1 - Afternoon (15.15-16.45 and 17.00-18.30 Nightingale Room)Deep learning meets the semantic web Chair: Dr Mercedes Arguello Casteleiro, University of Manchester, UK
The workshop will use material from the following contributors:
1 School of Computer Science, University of Manchester, UK Ontologies are the backbone of the Semantic Web and the W3C vision of the Web of linked data. Within the biomedical field, ontologies such as the Gene Ontology (GO) are used to represent the meaning of data. The bioinformatics field is rich in textual sources, both structured and unstructured, where data comes from a variety of resources, such as ‘omics (e.g. genomics, transcriptomics, proteomics and metabolomics) experiments, the biomedical literature, and healthcare systems. Over the years, ontologies such as GO and controlled vocabularies like the Medical Subject Headings (MeSH) emerged as methods to represent the semantic meaning of terms in a way that can support computational tasks such as information extraction, information retrieval and data analysis. A current challenge is how to maintain and keep updated resources such as GO and MeSH considering the continuously growth of biomedical textual repositories, especially with ‘big data’ being continuously produced in the areas of health research and health care. This workshop examines both traditional methods from knowledge engineering to capture and represent information extracted from texts, and the latest trends from machine learning to automatically derive semantic similarity from large unannotated free text. Recent advances in artificial neural networks make feasible the derivation of words from corpora of billions of words: hence the growing interest in Deep Learning. We demonstrate tasks for which Deep Learning technology can be utilised to support the development and enrichment of ontologies, with a particular focus on biomedical and clinical data. Please see the group's webpage http://pole-dl.cs.manchester.ac.uk for further information and post-workshop follow-up.
Stream 2 - Morning (11.00-12.30 and 13.15-14.45 Peterhouse Lecture Theatre)Twenty-first UK Case-Based Reasoning Workshop Organiser: Professor Miltos Petridis, University of Brighton Session 1: 11.00-12.30 Lecture Theatre Chair: Professor Miltos Petridis Please see the UKCBR webpage for further information and post-workshop follow-up. Welcome, introductions and housekeeping
Invited talk: Dr Stelios Kapetanakis (University of Brighton)
Accepted paper: Vani Aul and Thomas Roth-Berghofer Session 2: 13.15-14.45 Lecture Theatre Chair: Dr Stelios Kapetanakis
Invited research project talk: Dr Sadiq Sani (Robert Gordon University)
Accepted paper: Maria Leikola, Lotta Rintala, Christian Severin Sauer, Thomas Roth-Berghofer and Mari Lundström
Stream 2 - Afternoon (15.15-16.45 Peterhouse Lecture Theatre)Twenty-first UK Case-Based Reasoning Workshop Organiser: Professor Miltos Petridis, University of Brighton Session 3: 15.15-16.45 Chair: Professor Nirmalie Wiratunga
Invited PhD Thesis work Presentation: Jose Luis Jorro-Aragoneses (Universidad Complutense de Madrid)
Accepted paper: Tariq Saad Al Murayziq, Stelios Kapetanakis and Miltos Petridis Community discussion (15 mins)
|