BEGIN:VCALENDAR VERSION:2.0 PRODID:researchseminars.org CALSCALE:GREGORIAN X-WR-CALNAME:researchseminars.org BEGIN:VEVENT SUMMARY:I-Ping Tu/杜憶萍 (The Institute of Statistical Science\,Academi a Sinica\,Taiwan) DTSTART:20201229T070000Z DTEND:20201229T081500Z DTSTAMP:20260423T023932Z UID:iccm2020/75 DESCRIPTION:Title: 2SDR for noisy high-dimensional images and application to Cryogenic Elec tron Microscopy\nby I-Ping Tu/杜憶萍 (The Institute of Statistical Science\,Academia Sinica\,Taiwan) as part of ICCM 2020\n\n\nAbstract\nPrin cipal component analysis (PCA) is arguably the most widely used dimension- reduction method for vector-type data. When applied to a sample of images\ , PCA requires vectorization of the image data\, which in turn entails sol ving an eigenvalue problem for the sample covariance matrix. We propose he rein a two-stage dimension reduction (2SDR) method for image reconstructio n from high-dimensional noisy image data. The first stage treats the image as a matrix\, which is a tensor of order 2\, and uses multilinear princip al component analysis (MPCA) for matrix rank reduction and image denoising . The second stage vectorizes the reduced-rank matrix and achieves further dimension and noise reduction. Simulation studies demonstrate excellent p erformance of 2SDR\, for which we also develop an asymptotic theory that e stablishes consistency of its rank selection. Applications to cryo-EM (cry ogenic electronic microscopy)\, which has revolutionized structural biolog y\, organic and medical chemistry\, cellular and molecular physiology in t he past decade\, are also provided and illustrated with benchmark cryo-EM datasets. Connections to other contemporaneous developments in image recon struction and high-dimensional statistical inference are also discussed. \nThis is a joint work with Szu-Chi Chung\, Po-Yao Niu\, Su-Yun Huang and Wei-Hau Cha ng.\n LOCATION:https://researchseminars.org/talk/iccm2020/75/ END:VEVENT END:VCALENDAR