Profile

Susan Craw H&S
Title: Professor
First Name: Susan
Surname: Craw
Position: Research Professor
Telephone: +44 (0) 1224 262711
Email:
ORCID: ORCID Icon http://orcid.org/0000-0003-1870-0323


Duties and Responsibilities

  • Researcher Case-Based Reasoning, Data/Text Mining, Knowledge Discovery, Recommender Systems, Intelligent Information Systems
  • Research Student Supervisor
  • Member of Smart Information Systems research group 

Academic Background

  • PhD in Computing Science, University of Aberdeen, “Automating the Refinement of Knowledge Based Systems” (1991).
  • MSc by Research in Mathematics, University of Aberdeen, “Homotopy in Banach Algebras”  (1979)

Research Interests

Susan’s research in Artificial Intelligence develops innovative data/text/web mining technologies to discover knowledge to embed in case-based reasoning systems, recommender systems, and other intelligent information systems. Her research extracts knowledge from sources of ‘big data’, including databases, documents, music and image collections, and social media, and focuses on discovery and refinement for CBR’s knowledge containers including case bases and retrieval, reuse and adaptation knowledge.

Her work is highly relevant to industry; e.g. assisted living in technology-enabled homes, oil & gas ‘lessons learned’, satellite incident management, medical decision support, and pharmaceutical product design.  Recommender system research allows intelligent interaction and engagement with e-learning materials, on-line music, textile archives, and tourist locations. A new sensor data project develops a fall prediction system by learning from data captured by sensors in the home – “your house keeping you safe @ home”.

Susan's research papers are available at Google Scholar, SCOPUS, ResearchGate and RGU’s OpenAir open-access repository.

Current Research

Current/Recent Research Projects Include

  • FITsense: Fall prediction in technology-enabled ‘FIT Homes’. FITsense analyses data captured by a variety of static sensors, identifies patterns of activity, and changes in these patterns, that are linked to increased risk of falling. These underpin evidence- based alerts that enable interventions with preventative measures before incidents occur.
  • e-Learning Recommendation: The Web is an excellent source of e-learning materials but learners can have difficulty finding the right learning materials because of the difficulty in assembling effective search keywords. This recommender exploits learning concepts extracted from e-books as a knowledge-rich representation that takes advantage of tutors' expertise.
  • Music Recommenders: Users of on-line music services are looking for good recommendations, but also want to discover music that they do not already know. This recommender uses audio and social tagging to find tracks that balance novelty with quality.
  • Decisions from Data: a methodology allowing knowledge to be extracted from numeric or textual data, so that it can be effectively retrieved and reused to support decision-making on new problems.
  • Living History: A mobile app solution for tourists improves the interaction with objects at remote historic sites. NFC tags for tap-and-go services provide relevant visitor information about specific objects/places on historic sites to the visitor’s mobile without 3G/Web connectivity.
  • Smart Beacons: This mobile app uses proximity-aware Neate Beacon sensors to trigger the delivery of content relevant to a nearby item. Museums are interested to exploit this to enhance visitor experiences through engagement with exhibits.
  • STAR Smart Textile Archive: This prototype provides more flexible, interactive and collaborative engagements for designers and practitioners with textile assets. The project assesses the feasibility and potential impact of such an archive to the textile industry.

Funding

  • The Data Lab, FITsense: Fall Prediction in Technology-Enabled ‘FIT Homes’, Craw, Massie & Fraser (Albyn Housing), 2017-18
  • AHRC Digital Transformations, Accessing implicit knowledge of textiles and design - a smart, living archive for a heritage industry'' (AH/J013218/1), Williams, Craw, Wiratunga, Martin (Heriot-Watt) & Burnett, 2012
  • SFC Horizon, Smart Tourism, Oberlander (Edinburgh), Chalmers (Glasgow), Craw, Edwards (Aberdeen) & Quigley (St Andrews), 2011-2014, 

External / Professional Roles

  • Member of EPSRC Peer College
  • Member of SFC Research and Knowledge Exchange Committee
  • Member of Opportunity North East ONE Digital Board
  • International expert for SFI EXPOSED Aquaculture Centre for Research-Based Innovation, Trondheim
  • Member of Senior PC IJCAI 2015-17
  • Member of Advisory Committee ICCBR 2017-18
  • Senior Member of AAAI (Association for the Advancement of Artificial Intelligence) in recognition of contribution to AI
  • Member ACM, IEEE

Publications

Susan's research papers are available at Google Scholar, SCOPUS, ResearchGate and RGU’s OpenAir open-access repository.

  • Susan Craw. Case-based reasoning (2017). In Claude Sammut and Geoffrey Webb, editors, Encyclopedia of Machine Learning and Data Maining, pages 180–188. Springer, US. http://dx.doi.org/10.1007/978-1-4899-7687-1_34 Invited Chapter.
  • Blessing Mbipom, Susan Craw and Stewart Massie (2016).  Harnessing Background Knowledge for E-learning Recommendation. In Proceedings of the 36th SGAI International Conference on Innovative Techniques and Applications of Artificial Intelligence, pages 3–17, Springer. doi:10.1007/978-3-319-47175-4_1  PDF
  • Eduardo Lupiani, Stewart Massie, Susan Craw, Jose M Juarez and Jose T Palma (2016). Case-base maintenance with multi-objective evolutionary algorithms. Journal of Intelligent Information Systems, 46(2):259–284, Springer. doi:10.1007/s10844-015-0378-zPDF
  • Susan Craw, Ben Horsburgh and Stewart Massie (2015). Music recommendation: Audio Neighbourhoods to Discover Music in the Long Tail. In Proceedings of the 23rd International Conference on Case-Based Reasoning, pages 73–87, Frankfurt, Germany. Springer LNAI 9343. Best Paper Award. doi:10.1007/978-3-319-24586-7_6 PDF
  • Susan Craw, Ben Horsburgh and Stewart Massie (2015). Music Recommenders: User evaluation without real users? In Proceedings of the 24th International Joint Conference on Artificial Intelligence (IJCAI), pages = 1749–1755, Buenos Aires, Argentina. AAAI Press. http://ijcai.org/papers15/Papers/IJCAI15-249.pdf PDF
  • Ben Horsburgh, Susan Craw and Stewart Massie (2015). Learning pseudo-tags to augment sparse tagging in hybrid music recommender systems, Artificial Intelligence 219:25–39. In Elsevier’s Top25 Hottest Articles for the Artificial Intelligence Journal (13th) Jan-Mar 2015. doi:10.1016/j.artint.2014.11.004PDF
  • Ben Horsburgh, Susan Craw, Dorothy Williams, Simon Burnett, Katie Morrison and Suzanne Martin (2013). User perceptions of relevance and its effect on retrieval in a smart textile archive. In Proceedings of the 21st International Conference on Case-Based Reasoning, pages 149–163, Saratoga Springs, NY. Springer. doi:10.1007/978-3-642-39056-2_11PDF
  • Eduardo Lupiani, Susan Craw, Stewart Massie, Jose M Juarez and Jose T Palma (2013). A multi-objective evolutionary algorithm fitness function for case-base maintenance. In Proceedings of the 21st International Conference on Case-Based Reasoning, pages 218–232, Saratoga Springs, NY. Springer. doi:10.1007/978-3-642-39056-2_16 PDF
  • Ben Horsburgh, Susan Craw and Stewart Massie (2012). Music-inspired texture representation. In Proceedings of the 26th AAAI  Conference on Artificial Intelligence, pages 52–58, Toronto, Canada. AAAI Press. http://www.aaai.org/ocs/index.php/AAAI/AAAI12/paper/view/5041PDF
  • Susan Craw (2011). Introspective learning to build case-based reasoning. In Norbert M. Seel, editor, Encyclopedia of the Sciences of Learning. Springer, Heidelberg. doi:10.1007/978-1-4419-1428-6. Invited Chapter.
  • Ben Horsburgh, Susan Craw, and Stewart Massie (2011). Finding the hidden gems: Recommending untagged music. In Proceedings of the 22nd International Joint Conference in Artificial Intelligence (IJCAI), pages 2256–2261, Barcelona, Spain, AAAI Press. doi:10.5591/978-1-57735-516-8/IJCAI11-376PDF
  • Richard Thomson, Susan Craw, Stewart Massie, Hatem Ahriz, and Ian Mills (2011). Plan recommendation for well engineering. In Proceedings of the 24th International Conference on Industrial, Engineering and Other Applications of Applied Intelligent Systems, pages 436–445, Syracuse, NY. Springer. doi:10.1007/978-3-642-21827-9_45PDF
  • Martijn van den Branden, Nirmalie Wiratunga, Dean Burton, and Susan Craw (2011). Integrating case-based reasoning with an electronic patient record system. Artificial Intelligence in Medicine, 51(2):117– 123. doi:10.1016/j.artmed.2010.12.004
  • Susan Craw (2009). We’re wiser together. In Proceedings of the 8th International Conference on Case-Based Reasoning, pages 1–5, Seattle, WA. Springer. doi:10.1007/978-3-642-02998-1_1
  • Susan Craw, David W. Aha, Sarabjot Singh Anand, and Barry Smyth, editors (2009). Proceedings of the IJCAI Workshop on Grand Challenges for Reasoning from Experiences, Pasadena, CA.
  • Susan Craw (2009). Agile case-based reasoning: A grand challenge towards opportunistic reasoning from experiences. In Proceedings of the IJCAI-09 Workshop on Grand Challenges in Reasoning from Experiences, pages 33–39, Pasadena, CA, 2009.
  • Stella Asiimwe, Susan Craw, Nirmalie Wiratunga, and Bruce Taylor (2007). Automatically acquiring structured case representations: The SMART way. In Proceedings of the 27th BCS SGAI International Conference on Innovative Techniques and Applications of Artificial Intelligence, pages 45-58, Cambridge, UK. Springer. doi:10.1007/978-1-84800-086-5_4PDF.
  • Susan Craw, Nirmalie Wiratunga and Ray C. Rowe (2006). Learning adaptation knowledge to improve case-based reasoning. Artificial Intelligence, 170(16-17):1175–1192. doi:10.1016/j.artint.2006.09.001.
  • K.B. Matthews, K. Buchan, A.R. Sibbald, and S. Craw (2006). Combining deliberative and computer-based methods for multi-objective land-use planning.  Agricultural Systems, 87(1):18–37. doi:10.1016/j.agsy.2004.11.002
  • Ramon López de Mántaras, David McSherry, Derek Bridge, David Leake, Barry Smyth, Susan Craw, Boi Faltings, Mary Lou Maher, Michael T. Cox, Kenneth Forbus, Mark Keane, Agnar Aamodt, and Ian Watson (2005). Retrieval, reuse, revision, and retention in case-based reasoning. Knowledge Engineering Review, 20(3):215–240. doi:10.1017/S0269888906000646PDF.
  • Ashok K. Goel and Susan Craw (2005). Design, innovation and case-based reasoning. Knowledge Engineering Review, 20(3):271–276. doi:10.1017/S0269888906000609
  • Jacek Jarmulak, Susan Craw and Ray Rowe (2001). Using case-base data to learn adaptation knowledge for design. In Proceedings of the 17th International Joint Conference in Artificial Intelligence (IJCAI), pages 1011–1016, Seattle, WA. Morgan Kaufmann. http://ijcai.org/Past%20Proceedings/IJCAI-2001/PDF/IJCAI-2001-l.pdf/IJCAI-2001-l.pdf
  • Jacek Jarmulak, Susan Craw and Ray Rowe (2000). Self-optimising CBR retrieval. In Proceedings of the 12th IEEE International Conference on Tools with AI, pages 376–383. IEEE Press. doi.org/10.1109/TAI.2000.88989PDF.
  • Keith B. Matthews, Alan R. Sibbald and Susan Craw (1999). Implementation of a spatial decision support system for rural land use planning: integrating geographic information system and environmental models with search and optimisation algorithms. Computers and Electronics in Agriculture 23(1):9–26. doi:10.1016/S0168-1699(99)00005-8
  • Susan Craw and Robin Boswell (1999). Representing Problem-Solving for Knowledge Refinement. In Proceedings of the 16th AAAI  Conference on Artificial Intelligence, pages 227–234, Orlando, FL. AAAI Press/MIT Press. PDF.
  • Susan Craw, Nirmalie Wiratunga and Ray Rowe (1998). Case-based design for tablet formulation. In Proceedings of the 4th European Workshop on Case-Based Reasoning, pages 358–369, Dublin, Ireland. Springer LNCS 1488. doi:10.1007/BFb0056347.

Additional Information/Media Coverage

  • Invited Talk “Explainable and Robust AI from Case-Based Systems”, ScotSoft Conference, Edinburgh, UK, October 2017
  • Exhibit “Artificial Intelligence for Healthy Living”, Scotland’s Futures Forum: The Future of Housing and Health, Scottish Parliament, September 2017
  • Donald Michie Award for the Best Technical Paper Award for “Harnessing Background Knowledge for E-learning Recommendation”, 36th BCS SGAI International Conference on Innovative Techniques and Applications of Artificial Intelligence, Cambridge, UK, December 2016 PDF
  • Invited Keynote “Robust Intelligence from Case-Based Systems”, BCS Real AI Day, London, UK, October 2016
  • Meet the Expert Talk “Artificial Intelligence & Big Data”, Aberdeen Science Centre, Aberdeen, UK, August 2016
  • Invited Keynote “Recommender Systems: Taking Advantage of Noisy Neighbours”, UK CBR Workshop, Cambridge, UK, December 2015
  • Invited Seminar “Discovering Knowledge for Smarter Case-Based Systems”, Fraunhofer Institute for Intelligent Analysis and Information Systems, Sankt Augustin, Germany, September 2015
  • ICCBR 2015 Best Paper Award for “Music recommendation: Audio Neighbourhoods to Discover Music in the Long Tail”, 23rd International Conference on Case-Based Reasoning, Frankfurt, Germany, September 2015 PDF
  • Invited Presentation “Smart Information Systems for Exposed Aquaculture Operations”, SINTEF, Trondheim, Norway, August 2015
  • Invited Keynote “The Future Influence of Digital Technology on Tourism”, Aberdeen City Shire Tourism Conference, Aberdeen, UK, March 2014
  • Invited Keynote “Smart Data Technologies: From Data to Improved Decision Making”, Oil Gas ICT Leader Conference, Aberdeen, UK, March 2014
  • Invited Talk ”You Are Here: The Right Information at the Right Time”, SICSA DemoFest, Aberdeen, UK, February 2014
  • Application Keynote “Corporate Memory and Innovation: Closing the Loop”, “Real AI Day”, 30th BCS-SGAI International Conference on Artificial Intelligence, Cambridge, UK, December 2010
  • Invited Keynote “We’re Wiser Together”, 8th International Conference on Case-Based Reasoning, Seattle, WA, July 2009