Kenneth (Kezhi) Li is a lecturer (Assistant Professor) at Institute of Health Informatics, University College London (UCL). He obtained the PhD degree at Imperial College London, and B.Eng. degree in Electronic Engineering from and University of Science and Technology of China (USTC), Hefei, China, respectively.

His research interests are quite broad in several inter-discipline areas, such as biomedical signal processing/time series analysis in glucose management, patient flow optimization, critical care condition prediction, using machine learning, data mining and computer vision; structured signal processing and their applications in imaging system, quantum tomography and information theory. Prior to joining UCL, he used to be a senior research associate at Imperial College London, research scientist at Medical Research Council (MRC), a research associate at University of Cambridge, a research fellow at Royal Institute of Technology (KTH) in Stockholm and a research assistant at Microsoft Research Asia (MSRA) and USTC.

---------------------

News:
16/07/2018: Paper "Dilated Recurrent Neural Network for Short-Time Prediction of Glucose Concentration'' won the 1st Prize in the challenge of Blood Glucose Level Prediction, the 27th International Joint Conference on Artificial Intelligence (IJCAI-ECAI 2018), in WKDH, at Stockholm, July, 2018.
09/07/2018: Paper "An open source platform for analyzing and sharing worm behavior data" has been accepted in principle in Nature Methods, to appear. Great news!
15/12/2017: Paper "Recurrent Neural Networks with Interpretable Cells Predict and Classify Worm Behaviour'' won the best paper award in workshop of WNIP, Annual Conference and Workshop on Neural Information Processing Systems, (NIPS 2017), Los Angeles, Dec. 2017.

__________

李克之,英国伦敦大学学院讲师(助理教授)。在信号处理理论,机器学习大数据和人工智能在医疗健康,量子方向有超过十年的研究经验。他发表超过50篇英文论文,包括IEEE Trans, Physical Rev., Nature Methods等杂志以及NIPS, IJCAI, ICASSP, IFAC等顶级大会上,影响因子总和超过100。他曾工作于剑桥大学,瑞典皇家理工学院,微软亚洲研究院和英国普拓资本公司。帝国理工博士,中科大本科。

www.hitwebcounter.com
This Website Visits