Honghan Wu | 吴鸿汉
Department of Biostatistics and Health Informatics
King’s College London
- (13 March 2017) Our book is officially published today: Exploiting Linked Data and Knowledge Graphs in Large Organisations, although the information has been out for quite a while.
- (08 March 2017) Our paper Automated PDF highlights to support faster curation of literature on Parkinson’s and Alzheimer’s disease has been accepted by Database: The Journal of Biological Databases and Curation.
- (02 March 2017) I am co-organising The 2nd International Workshop on Knowledge Discovery in Healthcare Data (KDH) – aligning with IJCAI 2017 (https://sites.google.com/site/kdhijcai2017/). Submissions are welcome!
- KG4Core – a knowledge graph infrastructure for supporting bioinformatics research, which integrates structured background knowledge (e.g., drug bank, uniprot, sider), electronic health records (e.g., CRIS data), and Linked Data(e.g., linked life data).
- EBEncoding – efficient bitwise encoding for temporal/longitudinal (medical) data analytics – particularly on Adverse Drug Event analytics on CRIS data.
- NapEasy – automated PDF highlighting tool to support faster curation of case studies and reviews on Parkinson’s and Alzheimer’s disease.
Research Interests Big (Semantic) Data, Semantic Web Data Management, Semantic Search, Web Data Mining, and applications of aforementioned techniques in various domains including healthcare, e-Commerce and etc.
Short Bio Dr Honghan Wu is a data scientist in Department of Biostatistics and Health Informatics of King’s College London. His current research focus is on annotating, analysing and searching large scale healthcare data by utilising Semantic Web and Knowledge Graph techniques. Before current post, Dr Wu got two Marie Curie Fellowships in two EU IAPP projects of K-Drive (in Aberdeen University, UK) and TEAM (in ELIKO, Estonia). He holds a PhD in computer science from the Southeast University. Dr Wu’s expertise is on dealing with huge volume and heterogeneous Semantic Web data, including combining information retrieval and data mining techniques with semantic technologies, including semantic search, summarisation and compression of RDF data, as well as query generation and query answering.