scispace - formally typeset
Search or ask a question
Institution

Shanghai Jiao Tong University

EducationShanghai, Shanghai, China
About: Shanghai Jiao Tong University is a education organization based out in Shanghai, Shanghai, China. It is known for research contribution in the topics: Population & Cancer. The organization has 157524 authors who have published 184620 publications receiving 3451038 citations. The organization is also known as: Shanghai Communications University & Shanghai Jiaotong University.


Papers
More filters
Proceedings Article
29 Apr 2018
TL;DR: Wasserstein distance guided representation learning (WDGRL) as mentioned in this paper utilizes a neural network, denoted by the domain critic, to estimate empirical Wasserstein distances between the source and target samples, and optimizes the feature extractor network to minimize the estimated distance in an adversarial manner.
Abstract: Domain adaptation aims at generalizing a high-performance learner on a target domain via utilizing the knowledge distilled from a source domain which has a different but related data distribution. One solution to domain adaptation is to learn domain invariant feature representations while the learned representations should also be discriminative in prediction. To learn such representations, domain adaptation frameworks usually include a domain invariant representation learning approach to measure and reduce the domain discrepancy, as well as a discriminator for classification. Inspired by Wasserstein GAN, in this paper we propose a novel approach to learn domain invariant feature representations, namely Wasserstein Distance Guided Representation Learning (WDGRL). WDGRL utilizes a neural network, denoted by the domain critic, to estimate empirical Wasserstein distance between the source and target samples and optimizes the feature extractor network to minimize the estimated Wasserstein distance in an adversarial manner. The theoretical advantages of Wasserstein distance for domain adaptation lie in its gradient property and promising generalization bound. Empirical studies on common sentiment and image classification adaptation datasets demonstrate that our proposed WDGRL outperforms the state-of-the-art domain invariant representation learning approaches.

379 citations

Journal ArticleDOI
16 Aug 2019-Science
TL;DR: The constructed heterostructure can selectively extract photogenerated charge carriers and impede the loss of decomposed components from soft perovskites, thereby reducing damage to the organic charge-transporting semiconductors.
Abstract: Here we report a solution-processing strategy to stabilize the perovskite-based heterostructure. Strong Pb–Cl and Pb–O bonds formed between a [CH(NH2)2]x[CH3NH3]1−xPb1+yI3 film with a Pb-rich surface and a chlorinated graphene oxide layer. The constructed heterostructure can selectively extract photogenerated charge carriers and impede the loss of decomposed components from soft perovskites, thereby reducing damage to the organic charge-transporting semiconductors. Perovskite solar cells with an aperture area of 1.02 square centimeters maintained 90% of their initial efficiency of 21% after operation at the maximum power point under AM1.5G solar light (100 milliwatts per square centimeter) at 60°C for 1000 hours. The stabilized output efficiency of the aged device was further certified by an accredited test center.

379 citations

Posted Content
TL;DR: Simulation results show that the proposed resource allocation schemes outperform other benchmark schemes and converge fast and have low computational complexity.
Abstract: Mobile edge computing (MEC) and wireless power transfer (WPT) are two promising techniques to enhance the computation capability and to prolong the operational time of low-power wireless devices that are ubiquitous in Internet of Things. However, the computation performance and the harvested energy are significantly impacted by the severe propagation loss. In order to address this issue, an unmanned aerial vehicle (UAV)-enabled MEC wireless powered system is studied in this paper. The computation rate maximization problems in a UAV-enabled MEC wireless powered system are investigated under both partial and binary computation offloading modes, subject to the energy harvesting causal constraint and the UAV's speed constraint. These problems are non-convex and challenging to solve. A two-stage algorithm and a three-stage alternative algorithm are respectively proposed for solving the formulated problems. The closed-form expressions for the optimal central processing unit frequencies, user offloading time, and user transmit power are derived. The optimal selection scheme on whether users choose to locally compute or offload computation tasks is proposed for the binary computation offloading mode. Simulation results show that our proposed resource allocation schemes outperforms other benchmark schemes. The results also demonstrate that the proposed schemes converge fast and have low computational complexity.

379 citations

Journal ArticleDOI
TL;DR: An end-to-end, atlas-free three-dimensional convolutional deep learning framework for fast and fully automated whole-volume HaN anatomy segmentation and demonstrates that the proposed model can improve segmentation accuracy and simplify the autosegmentation pipeline.
Abstract: Purpose Radiation therapy (RT) is a common treatment option for head and neck (HaN) cancer. An important step involved in RT planning is the delineation of organs-at-risks (OARs) based on HaN computed tomography (CT). However, manually delineating OARs is time-consuming as each slice of CT images needs to be individually examined and a typical CT consists of hundreds of slices. Automating OARs segmentation has the benefit of both reducing the time and improving the quality of RT planning. Existing anatomy autosegmentation algorithms use primarily atlas-based methods, which require sophisticated atlas creation and cannot adequately account for anatomy variations among patients. In this work, we propose an end-to-end, atlas-free three-dimensional (3D) convolutional deep learning framework for fast and fully automated whole-volume HaN anatomy segmentation. Methods Our deep learning model, called AnatomyNet, segments OARs from head and neck CT images in an end-to-end fashion, receiving whole-volume HaN CT images as input and generating masks of all OARs of interest in one shot. AnatomyNet is built upon the popular 3D U-net architecture, but extends it in three important ways: (a) a new encoding scheme to allow autosegmentation on whole-volume CT images instead of local patches or subsets of slices, (b) incorporating 3D squeeze-and-excitation residual blocks in encoding layers for better feature representation, and (c) a new loss function combining Dice scores and focal loss to facilitate the training of the neural model. These features are designed to address two main challenges in deep learning-based HaN segmentation: (a) segmenting small anatomies (i.e., optic chiasm and optic nerves) occupying only a few slices, and (b) training with inconsistent data annotations with missing ground truth for some anatomical structures. Results We collected 261 HaN CT images to train AnatomyNet and used MICCAI Head and Neck Auto Segmentation Challenge 2015 as a benchmark dataset to evaluate the performance of AnatomyNet. The objective is to segment nine anatomies: brain stem, chiasm, mandible, optic nerve left, optic nerve right, parotid gland left, parotid gland right, submandibular gland left, and submandibular gland right. Compared to previous state-of-the-art results from the MICCAI 2015 competition, AnatomyNet increases Dice similarity coefficient by 3.3% on average. AnatomyNet takes about 0.12 s to fully segment a head and neck CT image of dimension 178 × 302 × 225, significantly faster than previous methods. In addition, the model is able to process whole-volume CT images and delineate all OARs in one pass, requiring little pre- or postprocessing. Conclusion Deep learning models offer a feasible solution to the problem of delineating OARs from CT images. We demonstrate that our proposed model can improve segmentation accuracy and simplify the autosegmentation pipeline. With this method, it is possible to delineate OARs of a head and neck CT within a fraction of a second.

379 citations

Journal ArticleDOI
TL;DR: It is demonstrated that wild-type LRRK2 expression caused mitochondrial fragmentation along with increased mitochondrial dynamin-like protein (DLP1), a fission protein, which was further exacerbated by expression of PD-associated mutants (R1441C or G2019S) in both SH-SY5Y and differentiated primary cortical neurons.
Abstract: The leucine-rich repeat kinase 2 (LRRK2) mutations are the most common cause of autosomal-dominant Parkinson disease (PD). Mitochondrial dysfunction represents a critical event in the pathogenesis of PD. We demonstrated that wild-type (WT) LRRK2 expression caused mitochondrial fragmentation along with increased mitochondrial dynamin-like protein (DLP1, also known as DRP1), a fission protein, which was further exacerbated by expression of PD-associated mutants (R1441C or G2019S) in both SH-SY5Y and differentiated primary cortical neurons. We also found that LRRK2 interacted with DLP1, and LRRK2-DLP1 interaction was enhanced by PD-associated mutations that probably results in increased mitochondrial DLP1 levels. Co-expression of dominant-negative DLP1 K38A or WT Mfn2 blocked LRRK2-induced mitochondrial fragmentation, mitochondrial dysfunction and neuronal toxicity. Importantly, mitochondrial fragmentation and dysfunction were not observed in cells expressing either GTP-binding deficient mutant LRRK2 K1347A or kinase-dead mutant D1994A which has minimal interaction with DLP1 and did not increase the mitochondrial DLP1 level. We concluded that LRRK2 regulates mitochondrial dynamics by increasing mitochondrial DLP1 through its direct interaction with DLP1, and LRRK2 kinase activity plays a critical role in this process.

378 citations


Authors

Showing all 158621 results

NameH-indexPapersCitations
Meir J. Stampfer2771414283776
Richard A. Flavell2311328205119
Jie Zhang1784857221720
Yang Yang1712644153049
Lei Jiang1702244135205
Gang Chen1673372149819
Thomas S. Huang1461299101564
Barbara J. Sahakian14561269190
Jean-Laurent Casanova14484276173
Kuo-Chen Chou14348757711
Weihong Tan14089267151
Xin Wu1391865109083
David Y. Graham138104780886
Bin Liu138218187085
Jun Chen136185677368
Network Information
Related Institutions (5)
Zhejiang University
183.2K papers, 3.4M citations

97% related

Fudan University
117.9K papers, 2.6M citations

96% related

Peking University
181K papers, 4.1M citations

95% related

National University of Singapore
165.4K papers, 5.4M citations

93% related

Tsinghua University
200.5K papers, 4.5M citations

93% related

Performance
Metrics
No. of papers from the Institution in previous years
YearPapers
2023415
20222,315
202120,873
202019,462
201916,699
201814,250