H
Hao Su
Researcher at University of California, San Diego
Publications - 364
Citations - 82843
Hao Su is an academic researcher from University of California, San Diego. The author has contributed to research in topics: Computer science & Point cloud. The author has an hindex of 57, co-authored 302 publications receiving 55902 citations. Previous affiliations of Hao Su include Philips & Jiangxi University of Science and Technology.
Papers
More filters
Proceedings ArticleDOI
A Fabry-Perot interferometry based MRI-compatible miniature uniaxial force sensor for percutaneous needle placement
TL;DR: A Fabry-Perot interference (FPI) based system of an MRI-compatible fiber optic sensor which has been integrated into a piezoelectrically actuated robot for prostate cancer biopsy and brachytherapy in 3T MRI scanner is presented.
Journal ArticleDOI
Adaptation, restoration and collapse of anammox process to La(III) stress: Performance, microbial community, metabolic function and network analysis
Hao Su,Dachao Zhang,Philip Antwi,Longwen Xiao,Zhidan Zhang,Deng Xiaoyu,Lai Cheng,Jiejun Zhao,Yukun Deng,Zuwen Liu,Miao Shi +10 more
TL;DR: In this article, the effects of La(III) on anammox process in performance, microbial community structure, metabolic function, and microbial co-occurrence network were investigated.
Proceedings ArticleDOI
Approaches to creating and controlling motion in MRI
TL;DR: This paper describes a newly developed piezoelectric actuator driver and control system designed to drive a variety of both harmonic and non-harmonic motors that has been demonstrated to be capable of operating both harmonicand non- Harmonic piezoeselectric actuators with less than 5% SNR loss under closed loop control.
Posted Content
BiPointNet: Binary Neural Network for Point Clouds
TL;DR: This work discovers that the immense performance drop of binarized models for point clouds is caused by two main challenges: aggregation-induced feature homogenization that leads to a degradation of information entropy, and scale distortion that hinders optimization and invalidates scale-sensitive structures.
Proceedings Article
Multi-task Batch Reinforcement Learning with Metric Learning
TL;DR: A novel application of the triplet loss is proposed to robustify task inference and relabel the transitions from the training tasks by approximating their reward functions, which leads to significantly faster convergence compared to randomly initialized policies.