光电信息大讲堂第八十九讲:机器学习和大数据处理的自动化过程及其在湿地识别中的应用

时间:2018/06/19   来源:   点击数:

时间:  2018 年 5 月 15 日 10 : 00 - 12 : 00

地点:  南五楼 612 学术报告厅

报告人:  Sheng-Guo Wang (王胜国)教授,北卡罗莱纳大学夏洛特分校

邀请人:  刘德明   教授


报告摘要:

这次报告将介绍最近的研究工作:机器学习和大数据处理的自动化过程及其在基于数字高程模型(DEM)衍生变量的湿地识别中的应用。该工作不仅通过随机森林(RF)机器学习方法显著改善了基于DEM衍生变量的初始建模工作,而且还提供了针对湿地识别的一个的全自动化过程。研究工作表明,相比于Logistic回归方法,RF机器学习方法的误差减小了10倍左右。此外,作为创新的自动化过程使整个预测过程变得极其生动简单和快速。最后,本次报告还简要介绍了机器学习方法的广泛应用,包括智能制造,医疗诊断等。

This speech presents his recent research work: automation process of machine learning methods and big data treatment with its application to wetland identification based on DEM derivatives. The presented approach not only dramatically improves the initial modeling efforts based on DEM derivatives via random forest (RF) machine learning method, and but also provides a full automation process to wetland identification. The results show that the RF machine learning method significantly improves the prediction accuracy for wetlands by reducing error about 10 times comparing with the Logistic regression method, and the automation process as an innovation makes the whole prediction process vividly easy and impressive speed. Finally this speech briefs a discussion on the broad application areas of machine learning methods including intelligent manufacturing, medical diagnostics, etc.


报告人介绍:

王胜国教授是美国北卡罗莱纳大学夏洛特分校的终身教授。他在1967年和1981年分别获得中国科学技术大学电机工程系的学士和硕士学位,在1994年获得美国休斯顿大学获得电气和计算机工程专业博士学位,主攻系统和控制方向。王教授曾获得学术奖励多项,包括1978年中国科学大会奖(中国最高学术荣誉奖之一),1989-1990年度英国理事会学者奖,2016-2017年度美国富布赖特高级学者奖等。他近期的北卡罗莱纳州运输部研究项目“NCDOT湿地预测模型的改进”(2012〜2014),赢得了美国2015年“Sweet 16”高价值研究奖。自1974年以来,王教授一直是许多研究项目的首席研究员,发表论文100余篇。

Prof. Sheng-Guo Wang is a tenured Full Professor at the University of North Carolina at Charlotte, USA.  He received his B.S. and M.Sc. in Electrical Engineering from University of Science and Technology of China in 1967 and 1981 respectively, and Ph.D. in Electrical and Computer Engineering from University of Houston, USA in 1994, with a specialty in systems and control. Prof. Wang is a recipient of China National Science Conference Award 1978, one of the highest academic honors in China, British Council Scholar Award of 1989-1990, US Fulbright Senior Scholar Award of 2016-2017, and many other academic awards. His recent NCDOT research project, titled “Improvements to NCDOT’s Wetland Prediction Model” (2012 ~ 2014), has won a US national 2015 “Sweet 16” High Value Research.  He has been the Principal Investigators for numerous research projects since 1974,He has published more than 100 research papers, , and his research has been supported by the huge organizations, e.g., the Fulbright Program, NSF, NCDOT, HP, Tellabs, Agilent, etc. in US, the British Council in UK, and the China Railways in China.

Copyright © 2017华中科技大学光学与电子信息学院教育部敏感陶瓷工程技术中心
中国 武汉 洪山区珞喻路1037号 华中科技大学