報(bào)告題目：Temporal Order-based First-Take-All Hashing for Fast Attention-Deficit-Hyperactive-Disorder Detection
報(bào)告人：齊國君 博士
報(bào)告單位：美國中佛羅里達(dá)大學(xué)
報(bào)告時(shí)間：2016年12月13日 (星期二) 上午10:45-11:30
報(bào)告地點(diǎn)：學(xué)術(shù)活動(dòng)中心二樓小報(bào)告廳
報(bào)告摘要：Attention De?cit Hyperactive Disorder (ADHD) is one of the most common childhood disorders and can continue through adolescence and adulthood. Although the root cause of the problem still remains unknown, recent advancements in brain imaging technology reveal there exists di?erences between neural activities of Typically Developing Children (TDC) and ADHD subjects. Inspired by this, we propose a novel First-Take-All (FTA) hashing framework to investigate the problem of fast ADHD subjects detection through the fMRI time-series of neuron activities. By hashing time courses from regions of interests (ROIs) in the brain into ?xed-size hash codes, FTA can compactly encode the temporal order di?erences between the neural activity patterns that are key to distinguish TDC and ADHD subjects. Such patterns can be directly learned via minimizing the training loss incurred by the generated FTA codes. By conducting similarity search on the resultant FTA codes, data-driven ADHD detection can be achieved in an e?cient fashion. The experiments’ results on real-world ADHD detection bench-marks demonstrate the FTA can outperform the state-of-the-art baselines using only neural activity time series with-out any phenotypic information.
報(bào)告人簡介：齊國君博士是美國中佛羅里達(dá)大學(xué)助理教授，他的研究方向包括大數(shù)據(jù)分析與知識發(fā)現(xiàn)、智能決策系統(tǒng)等。齊國君博士在Proceedings of IEEE、TPAMI、TKDE、TIP、SIGKDD、ICML、ACM MM、CVPR、ICDM、ICDE等頂尖國際期刊與會(huì)議發(fā)表論文超過六十篇，并獲得ICDM2014最佳學(xué)生論文、ICDE2013最佳論文、ACM MM2007最佳論文。齊國君博士曾獲得微軟學(xué)者獎(jiǎng)一次，IBM學(xué)者獎(jiǎng)兩次。齊國君博士是Multimedia Modeling(MMM)2016的大會(huì)共同主席，SIGKDD、CIKM、ACM MM的領(lǐng)域主席(Area Chair)，CVPR、ICCV、SIGKDD、IJCAI、ICMR等國際會(huì)議程序委員會(huì)委員，亦是《IEEE大數(shù)據(jù)匯刊》、《IEEE多媒體匯刊》等國際頂尖期刊的客座編輯。
太陽集團(tuán)tyc5997
TOP
