Imperial College London

Mr Liuqing Chen (Kevin Chen)

Faculty of EngineeringDyson School of Design Engineering

Research Postgraduate
 
 
 
//

Contact

 

l.chen15

 
 
//

Location

 

Dyson BuildingSouth Kensington Campus

//

Summary

 

Summary

Liuqing Chen (Kevin Chen) is a PhD student at Imperial College London, starting from September 2015. He is supervised by Peter Childs. His general research interests include: the application of artificial intelligence in design and manufacturing; data-driven design; AI design; design creativity; computational creativity; creativity tool design; data mining and data visualization; machine learning and deep learning; Natural Language Processing (NLP).

The research projects he has completed or has been doing include:
- A data-driven creativity engine
- An artificial intelligence based combinational creativity
- Creative design interpretation with artificial intelligence
- Human-in-the-loop design with machine learning

He got his bachelor degree at Ocean University of China in 2012, and then went to Shandong University as a postgraduate, which was suspended one year later. He got the full scholarship (Erasmus Mundus program) from EU and obtained a master degree at Politecnico di Torino in Italy from 2013 to 2015. 

Research Projects

A data-driven creativity engine design B-Link: Developed a data-driven tool for information retrieval and creative knowledge discovery. The tool aquatically collected over 3 million keywords from digital academic publications by NLP, and built a massive network graph for mining knowledge associations and new insights by means of proposed far-association algorithms.

Artificial intelligence for combinational design: Proposed a new Generative Adversarial Networks (GAN) model for generating synthesised images, and programmed the model using Tensorflow in a case study in which qualitative data was transformed into quantitative data for evaluation and model validation.

Interpreting innovative design with artificial intelligence:To capture the composition of a combinatorial design solution, an integrated deep learning model was proposed. In the model, convolutional neural networks (CNN) was used for image recognition and long-short term memory (LSTM) was applied for named entity extraction and relation classification.

Contact


Linkedin

Google Scholar


Publications

Journals

Chen L, Wang P, Dong H, et al., 2019, An artificial intelligence based data-driven approach for design ideation, Journal of Visual Communication and Image Representation, Vol:61, ISSN:1047-3203, Pages:10-22

Garvey B, Chen L, Shi F, et al., 2019, New directions in computational, combinational and structural creativity, Proceedings of the Institution of Mechanical Engineers, Part C: Journal of Mechanical Engineering Science, Vol:233, ISSN:0954-4062, Pages:425-431

Han J, Park D, Shi F, et al., 2019, Three driven approaches to combinational creativity: Problem-, similarity- and inspiration-driven, Proceedings of the Institution of Mechanical Engineers, Part C: Journal of Mechanical Engineering Science, Vol:233, ISSN:0954-4062, Pages:373-384

Han J, Shi F, Chen L, et al., 2018, A computational tool for creative idea generation based on analogical reasoning and ontology, Ai Edam, Vol:32, ISSN:0890-0604, Pages:462-477

Han J, Shi F, Chen L, et al., 2018, The Combinator – a computer-based tool for creative idea generation based on a simulation approach, Design Science, Vol:4, ISSN:2053-4701

More Publications