检索结果-内蒙古大学图书馆

arXiv 2018年

作者： Zhan, Yufeng Xia, Yuanqing Zhang, Jiang Li, Ting Wang, Yu School of Automation Key Laboratory of Intelligent Control and Decision of Complex Systems Beijing Institute of Technology Beijing100081 China Lab Department of Computer Science University of North Carolina at Charlotte CharlotteNC28223 United States

Currently, explosive increase of smartphones with powerful built-in sensors such as GPS, accelerometers, gyroscopes and cameras has made the design of crowdsensing applications possible, which create a new interface between human beings and life environment. Until now, various mobile crowdsensing applications have been designed, where the crowdsourcers can employ mobile users (MUs) to complete the required sensing tasks. In this paper, emerging learning-based techniques are leveraged to address crowdsensing game with demand uncertainties and private information protection of MUs. Firstly, a novel economic model for mobile crowdsensing is designed, which takes MUs' resources constraints and demand uncertainties into consideration. Secondly, an incentive mechanism based on Stackelberg game is provided, where the sensing-platform (SP) is the leader and the MUs are the followers. Then, the existence and uniqueness of the Stackelberg Equilibrium (SE) is proven and the procedure for computing the SE is given. Furthermore, a dynamic incentive mechanism (DIM) based on deep reinforcement learning (DRL) approach is investigated without knowing the private information of the MUs. It enables the SP to learn the optimal pricing strategy directly from game experience without any prior knowledge about MUs' information. Finally, numerical simulations are implemented to evaluate the performance and theoretical properties of the proposed mechanism and approach. Copyright © 2018, The Authors. All rights reserved.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Understanding adversarial attacks on deep learning based medical image analysis systems

arXiv

引用

arXiv 2019年

作者： Ma, Xingjun Niu, Yuhao Gu, Lin Wang, Yisen Zhao, Yitian Bailey, James Lu, Feng State Key Laboratory of VR Technology and Systems School of CSE Beihang University Beijing China School of Computing and Information Systems The University of Melbourne ParkvilleVIC3010 Australia Beijing Advanced Innovation Center for Big Data-Based Precision Medicine Beihang University Beijing China National Institute of Informatics Tokyo101-8430 Japan Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai China Cixi Instuitue of Biomedical Engineering Ningbo Institute of Industrial Technology Chinese Academy of Sciences Ningbo China

Deep neural networks (DNNs) have become popular for medical image analysis tasks like cancer diagnosis and lesion detection. However, a recent study demonstrates that medical deep learning systems can be compromised by carefully-engineered adversarial examples/attacks with small imperceptible perturbations. This raises safety concerns about the deployment of these systems in clinical settings. In this paper, we provide a deeper understanding of adversarial examples in the context of medical images. We find that medical DNN models can be more vulnerable to adversarial attacks compared to models for natural images, according to two different viewpoints. Surprisingly, we also find that medical adversarial attacks can be easily detected, i.e., simple detectors can achieve over 98% detection AUC against state-of-the-art attacks, due to fundamental feature differences compared to normal examples. We believe these findings may be a useful basis to approach the design of more explainable and secure medical deep learning systems. Copyright © 2019, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Protein-coding genes combined with long noncoding RNA as a novel transcriptome molecular staging model to predict the survival of patients with esophageal squamous cell carcinoma

引用

Cancer Communications 2018年第1期38卷 50-62页

作者： Jin-Cheng Guo Yang Wu Yang Chen Feng Pan Zhi-Yong Wu Jia-Sheng Zhang Jian-Yi Wu Xiu-E Xu Jian-Mei Zhao En-Min Li Yi Zhao Li-Yan Xu Key Laboratory of Molecular Biology in High Cancer Incidence Coastal Chaoshan Area of Guangdong Higher Education Institutes Shantou University Medical CollegeShantouGuangdong 515041P.R.China Department of Biochemistry and Molecular Biology Shantou University Medical CollegeShantouGuangdong 515041P.R.China Departments of Oncology Surgery Shantou Central HospitalAffiliated Shantou Hospital of Sun Yat-Sen UniversityShantouGuangdong 515041P.R.China Institute of Oncologic Pathology Shantou University Medical CollegeShantouGuangdong 515041P.R.China Key Laboratory of Intelligent Information Processing Advanced Computer Research CenterState Key Laboratory of Computer ArchitectureInstitute of Computing TechnologyChinese Academy of SciencesBeijing 100190P.R.China

Background:Esophageal squamous cell carcinoma(ESCC)is the predominant subtype of esophageal carcinoma in *** study was to develop a staging model to predict outcomes of patients with ***:Using Cox regression analysis,principal component analysis(PCA),partitioning clustering,Kaplan-Meier analysis,receiver operating characteristic(ROC)curve analysis,and classification and regression tree(CART)analysis,we mined the Gene Expression Omnibus database to determine the expression profiles of genes in 179 patients with ESCC from GSE63624 and GSE63622 ***:Univariate cox regression analysis of the GSE63624 dataset revealed that 2404 protein-coding genes(PCGs)and 635 long non-coding RNAs(lncRNAs)were associated with the survival of patients with *** categorized these PCGs and lncRNAs into three principal components(PCs),which were used to cluster the patients into three *** analysis demonstrated that the predictive ability of PCG-lncRNA PCs when applied to new patients was better than that of the tumor-node-metastasis staging(area under ROC curve[AUC]:0.69 vs.0.65,P<0.05).Accord-ingly,we constructed a molecular disaggregated model comprising one lncRNA and two PCGs,which we desig-nated as the LSB staging model using CART analysis in the GSE63624 *** LSB staging model classified the GSE63622 dataset of patients into three different groups,and its effectiveness was validated by analysis of another cohort of 105 ***:The LSB staging model has clinical significance for the prognosis prediction of patients with ESCC and may serve as a three-gene staging microarray.

关键词： Long non-coding RNA Protein-coding gene Esophageal squamous cell carcinoma Overall survival Staging model Transcriptome

来源：评论

学校读者我要写书评

暂无评论

Topological-darkness-assisted phase regulation for atomically thin meta-optics

arXiv

引用

arXiv 2019年

作者： Wang, Yingwei Deng, Zi-Lan Hu, Dejiao Yuan, Jian Ou, Qingdong Qin, Fei Zhang, Yinan Ouyang, Xu Peng, Bo Cao, Yaoyu Guan, Bai-Ou Zhang, Yupeng He, Jun Qiu, Chengwei Bao, Qiaoliang Li, Xiangping Guangdong Provincial Key Laboratory of Optical Fiber Sensing and Communications Institute of Photonics Technology Jinan University Guangzhou510632 China Hunan Key Laboratory for Super-microstructure and Ultrafast Process School of Physics and Electronics Central South University 932 South Lushan Road Changsha Hunan410083 China College of Physics and Electronic Information Huaibei Normal University Huaibei235000 China Key Laboratory of Optoelectronic Devices and Systems of Ministry of Education and Guangdong Province College of Electronic Science and Technology Shenzhen University Shenzhen518060 China Monash University ClaytonVIC3800 Australia National Engineering Research Center of Electromagnetic Radiation Control Materials State Key Laboratory of Electronic Thin Films and Integrated Devices School of Microelectronics and Solid State Electronics University of Electronic Science and Technology of China Chengdu610054 China Department of Electrical and Computer Engineering National University of Singapore 4 Engineering Drive 3 117583 Singapore

Two-dimensional (2D) noble-metal dichalcogenides 1, 2 have emerged as a new platform for the realization of versatile flat optics with a considerable degree of miniaturization. However, light field manipulation at the atomic scale is widely considered unattainable since the vanishing thickness and intrinsic losses of 2D materials completely suppress both resonances and phase accumulation effects. Empowered by conventionally perceived adverse effects of intrinsic losses, we show that the structured PtSe2 films integrated with a uniform substrate can regulate nontrivial singular phase and realize atomic-thick meta-optics in the presence of topological darkness 3, 4. We experimentally demonstrate a series of atomic-thick binary meta-optics that allows angle-robust and high unit-thickness diffraction efficiency of 0.96%/nm in visible frequencies, given its thickness of merely 4.3 nm. Our results unlock the potential of a new class of 2D flat optics for light field manipulation at an atomic thickness. Copyright © 2019, The Authors. All rights reserved.

关键词： Platinum compounds

来源：评论

学校读者我要写书评

暂无评论

Multi-channel attenuation compensation based on compressive sensing 87

Multi-channel attenuation compensation based on compressive ...

引用

Society of Exploration Geophysicists International Exposition and 87th Annual Meeting, SEG 2017

作者： Wang, Benfeng Lu, Wenkai Gu, Chenglong Easysignal Group State Key Laboratory of Intelligent Technology and Systems Tsinghua National Laboratory for Information Science and Technology Department of Automation Tsinghua University China Exploration and Development Research Institute of Tarim Oilfield

The existing attenuation in the sub-surface medium can attenuate amplitude and distort phase of the observed seismic signal, which can decrease its vertical resolution, then affect performances of the following seismic data inversion and migration. Traditional inverse Q filtering and nonstationary deconvolution methods are common tools to improve the vertical resolution while they belong to single channel attenuation compensation methods which cannot guarantee horizontal continuity. Therefore, we propose a multi-channel attenuation compensation method based on compressive sensing strategy to improve the vertical resolution as well as enhance the horizontal continuity. We first extend the single channel compensation method into multi-channel cases, then a functional is established using sparse constraint, finally the iterative hard thresholding (IHT) method is used for the established functional to obtain the final compensated seismic data. Numerical examples on synthetic and real field data demonstrate the validity and effectiveness of the proposed multi-channel compensation method which can improve the vertical resolution as well as enhance the horizontal continuity. © 2017 SEG.

关键词： Compressed sensing

来源：评论

学校读者我要写书评

暂无评论

Model Checking Quantum systems-A Survey

arXiv

引用

arXiv 2018年

作者： Ying, Mingsheng Feng, Yuan Centre for Quantum Software and Information University of Technology Sydney Australia State Key Laboratory of Computer Science Institute of Software Chinese Academy of Sciences China Department of Computer Science and Technology Tsinghua University China

This article discusses the essential difficulties in developing model-checking techniques for quantum systems that are never present in model checking classical systems. It further reviews some early researches on checking quantum communication protocols as well as a new line of researches pursued by the authors and their collaborators on checking general quantum systems, applicable to both physical systems and quantum programs. Copyright © 2018, The Authors. All rights reserved.

关键词： Quantum optics

来源：评论

学校读者我要写书评

暂无评论

Double acceleration of the APGST for seismic data attenuation compensation 87

Double acceleration of the APGST for seismic data attenuatio...

引用

Society of Exploration Geophysicists International Exposition and 87th Annual Meeting, SEG 2017

The generalized S transform (GST), as a time frequency analysis tool, is very useful for anomalies identification, and reservoir characterization. Because it's self-adjustable according to local frequency components with the existing two adjustable parameters. But the amplitude preserving ability is a little poor near the boundary because the analytical windows cannot subject to a partition of unity (POU). In order to make the GST with the amplitude preserving ability, we first introduce a new analytical window, then propose an amplitude preserving GST (APGST), but with a large computational cost. To accelerate the APGST, we provide two strategies: the 3s criterion in probability theory is introduced to accelerate the analytical windows summation and a convolution operator is derived to accelerate the time integral or summation, which generates an efficient APGST (EAPGST). Finally, the proposed EAPGST is used for attenuation compensation to improve the vertical resolution. Detailed numerical examples are used to demonstrate the validity of the proposed EAPGST in amplitude preserving and high efficiency, and attenuation compensation performance of field data further proves its potential in compensation to improve the vertical resolution. © 2017 SEG.

关键词： Seismology

来源：评论

学校读者我要写书评

暂无评论

Cylindrical vector beam-excited frequency-tunable second harmonic generation in a plasmonic octamer

引用

Photonics Research 2018年第3期6卷 157-161页

作者： FAJUN XIAO WUYUN SHANG WEIREN ZHU LEI HAN MALIN PREMARATNE TING MEI JIANLIN ZHAO MOE Key Laboratory of Material Physics and Chemistry under Extraordinary Conditions and Shaanxi Key Laboratory of Optical Information TechnologySchool of ScienceNorthwestern Polytechnical UniversityXi'an 710129China Department of Electronic Engineering Shanghai Jiao Tong UniversityShanghai 200240China Advanced Computing and Simulation Laboratory(AχL) Department of Electrical and Computer Systems Monash UniversityClaytonVlC 3800Australia

We report a method to tune the second harmonic generation(SHG) frequency of a metallic octamer by employing cylindrical vector beams as the excitation. Our method exploits the ability to spatially match the polarization state of excitations with the fundamental target plasmonic modes, enabling flexible control of the SHG resonant *** is found that SHG of the octamer is enhanced over a broad band(400 nm) by changing the excitation from the linearly polarized Gaussian beam to radially and azimuthally polarized beams. More strikingly, when subjected to an azimuthally polarized beam, the SHG intensity of the octamer becomes 30 times stronger than that for the linearly polarized beam even in the presence of Fano resonance.

关键词： SHG Cylindrical vector beam-excited frequency-tunable second harmonic generation in a plasmonic octamer

来源：评论

学校读者我要写书评

暂无评论

Differential Evolution Based High-order Peak Filter Design with Application to Compensation of Contact-induced Vibration in HDD Servo systems

引用

International Journal of Automation and computing 2017年第1期14卷 45-56页

作者： Deqing Huang Jian-Xin Xu Xin Deng Venkatakrishnan Venkataramanan The Cat Tuong Huynh Institute of Systems Science and Technology School of Electrical Engineering Southwest Jiaotong University Department of Electrical and Computer Engineering National University of Singapore Chongqing Key Laboratory of Computational Intelligence Chongqing University of Posts and Telecommunications Data Storage Institute Agency for Science Technology and Research

Sensitivity loop shaping using add-on peak filters is a simple and effective method to reject narrow-band disturbances in hard disk drive （HDD） servo systems. The parallel peak filter is introduced to provide high-gain magnitude in the concerned frequency range of open-loop transfer function. Different from almost all the known peak filters that possess second-order structures, we explore in this paper bow high-order peak filters can be designed to improve the loop shaping performance. The main idea is to replace some of the constant coefficients of common second-order peak filter by frequency-related transfer functions, and then differential evolution （DE） algorithm is adopted to perform optimal design. We creatively introduce chromosome coding and fitness function design, which are original and the key steps that lead to the success of DE applications in control system design. In other words, DE is modified to achieve a novel design for hard disk drive control. Owing to the remarkable searching ability of DE, the expected shape of sensitivity function can be achieved by incorporating the resultant high-order peak filter in parallel with baseline feedback controller. As a result, a seventh-order peak filter is designed to compensate for contact-induced vibration in a high-density HDD servo system, where the benefits of high-order filter are clearly demonstrated.

关键词： Differential evolution （DE） contact-induced vibration peak filter optimization sensitivity loop shaping hard disk drive（HDD）.

来源：评论

学校读者我要写书评

暂无评论

Primitives Generation Policy Learning without Catastrophic Forgetting for Robotic Manipulation

Primitives Generation Policy Learning without Catastrophic F...

引用

IEEE International Conference on Data Mining Workshops (ICDM Workshops)

作者： Fangzhou Xiong Zhiyong Liu Kaizhu Huang Xu Yang Amir Hussain State Key Lab of Management and Control for Complex Systems Institute of Automation Chinese Academy of Science China School of Computer and Control University of Chinese Academy of Sciences (UCAS) China CAS Centre for Excellence in Brain Science and Intelligence Technology Chinese Academy of Sciences China Department of EEE Xi’an Jiaotong-Liverpool University China School of Computing Edinburgh Napier University U.K.

Catastrophic forgetting is a tough challenge when agent attempts to address different tasks sequentially without storing previous information, which gradually hinders the development of continual learning. Except for image classification tasks in continual learning, however, there are little reviews related to robotic manipulation. In this paper, we present a novel hierarchical architecture called Primitives Generation Policy Learning to enable continual learning. More specifically, a generative method by Variational Autoencoder is employed to generate state primitives from task space, then separate policy learning component is designed to learn torque control commands for different tasks sequentially. Furthermore, different task policies could be identified automatically by comparing reconstruction loss in the autoencoder. Experiment on robotic manipulation task shows that the proposed method exhibits substantially improved performance over some other continual learning methods.

关键词： Task analysis Robots Neural networks Learning systems Trajectory Decoding Aerospace electronics

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：