報告時間:2021年7月8日周四14:30-17:00
報告地點:9A103
報告題目一:Weighted Conditional Distribution Adaptation For Motor Imagery Classification(張瑞副教授)
報告人簡介:張瑞,博士,副教授。博士畢業(yè)于華南理工大學(xué),研究方向為模式識別、腦信號處理、腦機協(xié)同控制及其在運動康復(fù)中的應(yīng)用。
報告簡介:Individual differences of electroencephalogram (EEG) signals can increase calibration difficulty, which is a major challenge in the practical application of brain computer interface (BCI). Transfer learning is an available method to predict the target subject's EEG signals by learning an effective model from other subjects' signals. We propose a weight conditional distribution adaptation (WCDA) method, which can enhance feature transferability and discriminability by minimizing the conditional distribution of the same class between domains while maximizing the conditional distribution of different classes between domains. Moreover, a transferable source sample selection (TSSS) method is proposed to improve the transfer learning performance and reduce the computational cost. Experiments on two public motor imagery (MI) datasets demonstrated our approach outperforms the state of the art methods, thus providing an available way to reduce calibration effort for BCI applications.
報告題目二:柔性海洋立管系統(tǒng)振動控制研究(郭芳博士)
報告人簡介:郭芳,女,博士,研究方向主要包括柔性結(jié)構(gòu)系統(tǒng)、海洋控制論。
報告簡介:在科學(xué)技術(shù)迅猛發(fā)展的當代,社會生產(chǎn)對于系統(tǒng)結(jié)構(gòu)的要求越加苛刻,剛性結(jié)構(gòu)已逐漸被柔性結(jié)構(gòu)所取代。然而,柔性結(jié)構(gòu)自身阻尼較小、抗干擾能力弱,受到干擾后極易產(chǎn)生長時間振動等特點,也使其在實際工程中的應(yīng)用困難重重。因此,如何有效減小甚至消除柔性結(jié)構(gòu)在受到干擾時所產(chǎn)生的不利振動,對于工程實際應(yīng)用來說具有重大的指導(dǎo)價值。
本期報告主要以柔性海洋輸油立管系統(tǒng)為例,介紹柔性結(jié)構(gòu)大規(guī)模應(yīng)用所面臨的重大問題,以及對柔性結(jié)構(gòu)進行振動控制的研究意義、研究現(xiàn)狀及控制方法。
(一審:李艷霞;二審:任斌;三審:胡耀華)