The first two days of the conference will comprise a range of workshops. 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.
Delegates are free to choose any combination of sessions to attend. The programme of workshops is shown below.
There is a lunch break from 13.00-14.00 each day and there are refreshment breaks scheduled during the morning and afternoon sessions.
Workshops organiser: Professor Adrian Hopgood, University of Portsmouth, UK
Please support PhD student Marie Oldfield, who is conducting surveys to determine perceptions of AI and how fairness is developed throughout the processes of building and using an AI system. Aimed at industry professionals or academics working with or researching AI systems, the survey will take 10-15 minutes.
Links to slideshow presentations (where available) are shown in the workshop headings, or you can go to the full set of presentations (opens in new tab).
Tuesday 8th Dec - morning (09.00-13.00, including a 30-minute refreshment break)
AI for Future Digital Health - Download slides (opens in new tab)
Prof Nirmalie Wiratunga, Robert Gordon University, Prof. Frans Coenen, University of Liverpool, and Dr Vitaly Kurlin, University of Liverpool
Following the success of this workshop in 2019, AI for Digital Health will again bring together AI practitioners representing health provider organisations, commercial enterprises with an interest in health care, and academic researchers. The workshop will encompass a number of strategic research themes including machine learning, medical diagnosis, analysis of health records and reasoning mechanisms to support decision making.
Artificial Intelligence (AI) offers the potential to revolutionise healthcare; the potential benefits have been well reported. The need for AI skills in healthcare has been identified by governments, and named as the principal driver for personalised healthcare and as providing a potential solution to the health funding gaps. Examples where AI can benefit healthcare and wellbeing include wearable devices for monitoring individuals, more effective diagnoses, better understanding of treatments, the minimisation of clinical risks, the closure of care gaps, drug discovery and innovative preventive healthcare solutions.
- 09:00 Welcome: Frans Coenen (Uni of Liverpool)
Session 1, Chair: Nirmalie Wiratunga (Aberdeen Robert Gordon University)
Kerstin Bach (Norwegian University of Science and Technology).
Invited speaker. AI-based recommendations to facilitate the self-management of low-back pain patients.
Nagesh Kalakonda (Clatterbridge Cancer Centre), Vitaliy Kurlin (Uni of Liverpool), Raji Muizdeen (Uni of Liverpool), Joseph Slupsky, (Uni of Liverpool).
Machine learning for mass cytometry data of chronic lymphocytic leukemia.
Iain Hennessey (Alder Hey Children's Hospital), Shan Luo (Uni of Liverpool), Farnaz Nickpour (Uni of Liverpool), Paolo Paolletti, (Uni of Liverpool), Peter Wright (Uni of Liverpool).
Future design of pediatric assistive mobility devices.
Tim Cross (Royal Liverpool and Broadgreen Hospital Trust), Mohamed Elhalwagy (Uni of Liverpool), Ahmed Elsheikh (Uni of Liverpool), Philip Johnson (Uni of Liverpool), Vinzent Rolny (Roche Diagnostics GmbH):
Biomarkers based detection of liver cancer.
Weiqiang Chen (Uni of Liverpool), Stephen Kaye (Royal Liverpool and Broadgreen Hospital Trust), Yaochun Shen Uni of Liverpool), Yalin Zheng Uni of Liverpool).
Segmentation of corneal images using a convolutional neural network.
Session 2, Chair: Vitaliy Kurlin (Uni of Liverpool)
Neil French (Uni of Liverpool), Roberto Vivancos (Public Health England), Dominik Wojtczak (Uni of Liverpool), Yanhua Xu (Uni of Liverpool):
Machine learning in influenza A classification.
Girvan Burnside (Uni of Liverpool), Paul Charnley (Wirral Teaching Hospital), Frans Coenen (Uni of Liverpool), Jing Qi (Uni of Liverpool):
Learning to prioritise pathology data in the absence of a ground truth.
Frans Coenen (Uni of Liverpool), Omar Elnaggar (Uni of Liverpool), Andrew Hopkinson (Hopkinson Research), Paolo Paolletti, (Uni of Liverpool).
Wearable sensing for non-invasive human pose recognition during sleep.
Dannie Arribas-Bel (Uni of Liverpool), Mark Green (Uni of Liverpool), Huw Jenkins (Liverpool City Region Combined Authority), Vitaliy Kurlin (Uni of Liverpool), Aidan Watmuff (Uni of Liverpool).
Using k-modes clustering to identify different types of cyclist in the Liverpool City Region.
Tuesday 8th Dec - afternoon (14.00-17.30, including a 30-minute refreshment break)
The Relationship of Artificial Intelligence and Operational Research - Download slides (opens in new tab)
Mathias Kern, BT Technology
The field of operational research (OR) studies the application of advanced analytical methods to problems in the management of complex systems to allow for better decision making. Typical examples include resource allocation problems, supply chain management, and scheduling. Operational research and artificial intelligence are two separate research disciplines, however there are also clear areas of overlap and shared interests. In this workshop, we introduce OR, look at a number of case studies, and discuss the relationship between AI and OR and how these two research disciplines can benefit from and enrich each other.
Session 1: 14:00-15:30
- Gavin Blackett, Secretary & General Manager at Operational Research Society: An Introduction to Operational Research and its professional body, The OR Society.
- Juergen Branke, Professor of Operational Research & Systems, University of Warwick: Learning to optimise and optimal learning - a look at the relationship between machine learning and optimisation.
- Mathias Kern, Senior Research Manager, Resource Management & Optimisation, BT: Driving operational transformation with AI.
Session 2: 16:00-17:30
- Richard Vidgen, Professor of Business Analytics, University of New South Wales, Australia: What can OR do for AI?
- Shakeel Khan, Artificial Intelligence Capability Building Lead, HMRC: Adopting Standards and Frameworks to Validate AI - An OR practitioner approach to build trust!
- Andrew Starkey, Principal Data Scientist - Explainable AI & ML at Temenos: Building Intelligent Systems: Insights from Industry.
Wednesday 9th Dec - morning (09.30-13.00, including a 30-minute refreshment break)
25th Case-Based Reasoning Workshop - Download slides (opens in new tab)
Dr Stelios Kapetanakis, University of Brighton, Dr Frederic Stahl, DFKI, and Nadia Abouayoub, SGAI
The symposium will be a relatively informal occasion where you can meet CBR colleagues and exchange news, views and opinions as well as learning about the work of other researchers and practitioners.
Please see the UKCBR webpage for further workshop information.
Session 1, Chair: Frederic Stahl (DFKI), Germany
Stelios Kapetanakis (University of Brighton):
Juan Recio Garcia (Complutense University, Spain):
Invited Talk: Experiences in knowledge engineering projects: Applying (or not) CBR to real problems.
Lukas Malburg, Maximilian Hoffmann, Simon Trumm and Ralph Bergmann (University of Trier):
Using Graphic Processing Units for Similarity-Based Retrieval in Case-Based Reasoning.
Francis Ekpenyong (University of Brighton):
A Stochastic Framework to Fuzzy Environments: CBR and the Inverse Problem Methodology on Financial Bubbles.
Session 2, Chair: Nadia Abouayoub (SGAI)
Jose Luis Jorro (Complutense University, Spain):
A knowledge-based platform for building recommender systems.
Marta Caro (Complutense University, Spain):
Recommender systems and explanations based on interaction graphs and link prediction techniques.
Kareem Amin (DFKI, Germany):
CBR in the era of Deep Learning and big data - DeepKAF: brief demonstration.
Kyle Martin (Robert Gordon University):
Towards Neural CBR: Using Deep Metric Learning to Bridge between Knowledge Containers.
Chairs and Participants
Discussion and Conclusion.
Wednesday 9th Dec - afternoon (14.00-17.30, including a 30-minute refreshment break)
Recent Advances in AI - Theory and Applications - Download slides (opens in new tab)
Dr Alexander Gegov, University of Portsmouth, Dr Raheleh Jafari, University of Leeds, and Dr Sina Razvarz, National Polytechnic Institute of Mexico
Part 1 - Theory 14.00-15.30
Theory 1: Dr Alexander Gegov, University of Portsmouth, UK (45 minutes, including Q&A)
The first presentation in part 1 will introduce recent developments, rational justification, current success, subject areas and wider popularity of AI. It will highlight Human Intelligence as a role model for AI and Computational Intelligence as a driving force behind AI. Computational Intelligence techniques such as Fuzzy Systems, Neural Networks and Evolutionary Algorithms will be discussed in the context of their ability to imitate different aspects of Human Intelligence in AI. Approaches such as Expert Systems and Machine Learning will also be discussed in the context of their ability to work in a complementary way with knowledge and data.
Theory 2: Dr Alexander Gegov, University of Portsmouth, UK (45 minutes, including Q&A)
The second presentation in part 1 will introduce Cybernetics and Complex Systems as research areas that are closely related and complementary to AI. It will underline the different aspects of system complexity and their impact on the performance of AI based models. Current hot topics in AI such as Big Data and Deep Learning will be discussed in the context of feature extraction and selection as well as structural and parametric identification. The session will end with a discussion on current limitations, future potential, main challenges, application areas, case studies and performance evaluation for AI.
Refreshment Break 15.30-16.00
Part 2 – Applications 16.00-17.30
Applications 1: Dr Raheleh Jafari, University of Leeds, UK (45 minutes, including Q&A)
The first presentation in part 2 will discuss the application of chatbots in healthcare and retail industry. Chatbots are an AI technique that is growing in its application and use. Chatbots are among the most visible applications of AI technology and have evolved into important tools for consumers, businesses and entire industries. A chatbot is a piece of software, usually powered by AI that can simulate a conversation with a user in natural language through messaging applications, website or mobile apps. Some top use cases for chatbots are healthcare chatbots and retail chatbots. Healthcare artificial intelligence chatbots can provide the user with health-related information. Retail chatbots help customers by providing in-store assistance.
Applications 2: Dr Sina Razvarz, National Polytechnic Institute, Mexico (45 minutes, including Q&A)
The second presentation in part 2 will discuss the application of neural networks and fuzzy systems techniques for fault detection in pipeline systems. Leakage and blockage in pipes that transport process fluids such as oil, industrial gas and water could result in crucial environmental, social, economic, health and safety problems. It is important for the industrial society that pipeline systems function appropriately by taking into consideration the growing requirement for effective interconnecting of fluid networks. Over the past few years, various techniques addressing uncertainties have been used for detecting flaws in pipelines. In particular, neural networks and fuzzy systems have emerged as important promising techniques for the development of leak detection systems.