检索结果-内蒙古大学图书馆

IEEE MTT-S International Conference on Microwaves for Intelligent Mobility (ICMIM)

作者： Xiangwei Dang Xingdong Liang Yanlei Li Zheng Rong National Key Laboratory of Microwave Imaging Technology Aerospace Information Research Institute Chinese Academy of Sciences School of Electronic Electrical and Communication Engineering University of Chinese Academy of Sciences Beijing China National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences Beijing China

ISBN: (数字)9781728167558

ISBN: (纸本)9781728167565

Robust and accurate localization and mapping are essential for autonomous driving. The traditional SLAM methods generally work under the assumption that the environment is static, while in dynamic environment the performance will be degenerate. In this paper, we propose an efficient and effective method to eliminate the influence of dynamic environment on SLAM by fusing LiDAR and mmW-radar, which significantly improves the robustness and accuracy of localization and mapping. The method fully utilizes the advantages of different measurement characteristics of two sensors, efficient moving object detection based on Doppler effect by radar and accurate object segmentation and localization by LiDAR, to remove the moving objects and uses the resulting filtered point cloud as the input of SLAM towards enhanced performance. The proposed approach is evaluated through experiments in various real world scenarios, and the results demonstrate the effectiveness of the method to improve the robustness and accuracy of SLAM in dynamic environments.

关键词： Simultaneous localization and mapping Laser radar Three-dimensional displays Radar measurements Radar detection Sensor phenomena and characterization Robustness

来源：评论

学校读者我要写书评

暂无评论

EEG-Based Brain-Computer Interfaces Are Vulnerable to Backdoor Attacks

Research Square

引用

research Square 2021年

作者： Meng, Lubin Huang, Jian Zeng, Zhigang Jiang, Xue Yu, Shan Jung, Tzyy-Ping Lin, Chin-Teng Chavarriaga, Ricardo Wu, Dongrui Ministry of Education Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China Brainnetome Center and National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences Beijing China La Jolla CA United States Center for Advanced Neurological Engineering Institute of Engineering in Medicine UCSD La Jolla CA United States Centre of Artificial Intelligence Faculty of Engineering and Information Technology University of Technology Sydney Australia ZHAW DataLab Zürich University of Applied Sciences Winterthur8401 Switzerland

research and development of electroencephalogram (EEG) based brain-computer interfaces (BCIs) have advanced rapidly, partly due to the wide adoption of sophisticated machine learning approaches for decoding the EEG signals. However, recent studies have shown that machine learning algorithms are vulnerable to adversarial attacks, e.g., the attacker can add tiny adversarial perturbations to a test sample to fool the model, or poison the training data to insert a secret backdoor. Previous research has shown that adversarial attacks are also possible for EEG-based BCIs. However, only adversarial perturbations have been considered, and the approaches are theoretically sound but very difficult to implement in practice. This article proposes to use narrow period pulse for poisoning attack of EEG-based BCIs, which is more feasible in practice and has never been considered before. One can create dangerous backdoors in the machine learning model by injecting poisoning samples into the training set. Test samples with the backdoor key will then be classified into the target class specified by the attacker. What most distinguishes our approach from previous ones is that the backdoor key does not need to be synchronized with the EEG trials, making it very easy to implement. The effectiveness and robustness of the backdoor attack approach is demonstrated, highlighting a critical security concern for EEG-based BCIs. © 2021, CC BY.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

AngularGrad: A New Optimization Technique for Angular Convergence of Convolutional Neural Networks

arXiv

引用

arXiv 2021年

作者： Roy, Swalpa Kumar Paoletti, Mercedes E. Haut, Juan M. Dubey, Shiv Ram Kar, Purbayan Plaza, Antonio Chaudhuri, Bidyut B. The Computer Science and Engineering Alipurduar Government Engineering and Management College 736206 India The Hyperspectral Computing Laboratory Department of Technology of Computers and Communications University of Extremadura Cáceres10003 Spain The Computer Vision and Biometrics Lab Indian Institute of Information Technology Prayagraj Uttar Pradesh Allahabad211015 India The Media Analysis Group Sony Research India Private Limited Karnataka Bangalore560103 India The Computer Vision and Pattern Recognition Unit Indian Statistical Institute Kolkata700108 India

Convolutional neural networks (CNNs) are trained using stochastic gradient descent (SGD)-based optimizers. Recently, the adaptive moment estimation (Adam) optimizer has become very popular due to its adaptive momentum, which tackles the dying gradient problem of SGD. Nevertheless, existing optimizers are still unable to exploit the optimization curvature information efficiently. This paper proposes a new AngularGrad optimizer that considers the behavior of the direction/angle of consecutive gradients. This is the first attempt in the literature to exploit the gradient angular information apart from its magnitude. The proposed AngularGrad generates a score to control the step size based on the gradient angular information of previous iterations. Thus, the optimization steps become smoother as a more accurate step size of immediate past gradients is captured through the angular information. Two variants of AngularGrad are developed based on the use of Tangent or Cosine functions for computing the gradient angular information. Theoretically, AngularGrad exhibits the same regret bound as Adam for convergence purposes. Nevertheless, extensive experiments conducted on benchmark data sets against state-of-the-art methods reveal a superior performance of AngularGrad. Source code: https://***/mhaut/AngularGrad. Copyright © 2021, The Authors. All rights reserved.

关键词： Optimization

来源：评论

学校读者我要写书评

暂无评论

Witnessing Entangled Two-Photon Absorption via Quantum Interferometry

arXiv

引用

arXiv 2022年

作者： Martínez-Tapia, Áulide Corona-Aquino, Samuel You, Chenglong Jin, Rui-Bo Magaña-Loaiza, Omar S. Dong, Shi-Hai U’Ren, Alfred B. León-Montiel, Roberto de J. Instituto de Ciencias Nucleares Universidad Nacional Autónoma de México Apartado Postal 70-543 Cd. Mx.04510 Mexico Quantum Photonics Laboratory Department of Physics & Astronomy Louisiana State University Baton RougeLA70803 United States Hubei Key Laboratory of Optical Information and Pattern Recognition Wuhan Institute of Technology Wuhan430205 China Research Center for Quantum Physics Huzhou University Huzhou313000 China Laboratorio de Ciencias de la Informacion Cuantica CIC Instituto Politecnico Nacional UPALM C.P CDMX07700 Mexico

Recent investigations suggest that the use of non-classical states of light, such as entangled photon pairs, may open new and exciting avenues in experimental two-photon absorption spectroscopy. Despite several experimental studies of entangled two-photon absorption (eTPA), there is still a heated debate on whether eTPA has truly been observed. This interesting debate has arisen, mainly because it has been recently argued that single-photon-loss mechanisms, such as scattering or hot-band absorption may mimic the expected entangled-photon linear absorption behavior. In this work, we focus on transmission measurements of eTPA, and explore three different two-photon quantum interferometers in the context of assessing eTPA. We demonstrate that the so-called N00N-state configuration is the only one amongst those considered insensitive to linear (single-photon) losses. Remarkably, our results show that N00N states may become a potentially powerful tool for quantum spectroscopy, and place them as a strong candidate for the certification of eTPA in an arbitrary sample. Copyright © 2022, The Authors. All rights reserved.

关键词： Particle beams

来源：评论

学校读者我要写书评

暂无评论

Erratum to “Luminance Learning for Remotely Sensed Image Enhancement Guided by Weighted Least Squares”

引用

IEEE Geoscience and Remote Sensing Letters 2022年 19卷

作者： Zhenghua Huang Zifan Zhu Qing An Zhicheng Wang Qin Zhou Tianxu Zhang Ali Saleh Alshomrani Hubei Key Laboratory of Optical Information and Pattern Recognition Wuhan Institute of Technology Wuhan China Artificial Intelligence School Wuchang University of Technology Wuhan China School of Electronics and Information Engineering Wuhan Donghu University Wuhan China Mathematical Modelling and Applied Computation Research Group (MMAC) King Abdulaziz University Jeddah Saudi Arabia

In the above article [1] , the model in (1) should be revised as \begin{equation*}\min _{\mathcal{I}^{\mathcal{B}}}\left\{\left(\mathcal{I}-\mathcal{I}^{\mathcal{B}}\right)^{2}+\lambda\left(a_{x}(\mathcal{I})\left(\frac{\partial \mathcal{I}^{\mathcal{B}}}{\partial x}\right)^{2}+a_{y}(\mathcal{I})\left(\frac{\partial \mathcal{I}^{\mathcal{B}}}{\partial y}\right)^{2}\right)\right\} \end{equation*} to be minimized for ${\mathcal {I}}^{\mathcal {B}}$ .

关键词： Remote sensing Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Learning data-adaptive non-parametric kernels

The Journal of Machine Learning Research

引用

The Journal of Machine Learning research 2020年第1期21卷 8590-8628页

作者： Fanghui Liu Xiaolin Huang Chen Gong Jie Yang Li Li Department of Electrical Engineering ESAT-STADIUS KU Leuven Belgium Institute of Image Processing and Pattern Recognition Institute of Medical Robotics Shanghai Jiao Tong University Shanghai China PCA Lab Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education School of Computer Science and Engineering Nanjing University of Science and Technology China and Department of Computing Hong Kong Polytechnic University Hong Kong SAR China Department of Automation BNRist Tsinghua University China

In this paper, we propose a data-adaptive non-parametric kernel learning framework in margin based kernel methods. In model formulation, given an initial kernel matrix, a data-adaptive matrix with two constraints is imposed in an entry-wise scheme. Learning this data-adaptive matrix in a formulation-free strategy enlarges the margin between classes and thus improves the model flexibility. The introduced two constraints are imposed either exactly (on small data sets) or approximately (on large data sets) in our model, which provides a controllable trade-off between model flexibility and complexity with theoretical demonstration. In algorithm optimization, the objective function of our learning framework is proven to be gradient-Lipschitz continuous. Thereby, kernel and classifier/regressor learning can be efficiently optimized in a unified framework via Nesterov's acceleration. For the scalability issue, we study a decomposition-based approach to our model in the large sample case. The effectiveness of this approximation is illustrated by both empirical studies and theoretical guarantees. Experimental results on various classification and regression benchmark data sets demonstrate that our non-parametric kernel learning framework achieves good performance when compared with other representative kernel learning based algorithms.

关键词： support vector machines non-parametric kernel learning gradient-Lipschitz continuous

来源：评论

学校读者我要写书评

暂无评论

Prediction of σ54 promoters in prokaryotes based on SVM–Adaboost

Prediction of σ54 promoters in prokaryotes based on SVM–Ad...

引用

Chinese Automation Congress (CAC)

作者： Yongxian Fan Qingqi Zhu Chengwei Lv Xianyong Pan School of Computer and Information Security Guilin University of Electronic Technology Guilin Guangxi Key Laboratory of System Control and Information Processing Ministry of Education of China Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Shanghai China

σ 54 promoters are responsible for transcriptional carbon and nitrogen in prokaryotes. However, it is costly and difficult by experimental identification of them, especially in the postgenomic era with avalanche of sequencing data. Thus, it is imperative to develop efficiently and rapidly computational algorithms to identify the σ 54 promoters. In this study, a novel predictor named SVM-Adaboost was developed to predict σ 54 promoters from sequences alone, it used the Adaboost algorithm as the core, and support vector machine (SVM) as weak base predictors. SVM-Adaboost integrated SVM predictors to construct a more powerful and robust ensemble predictor. In SVM-Adaboost, we used pseudo k-tuple nucleotide composition method to encode DNA sequences, and then a feature selection method was used to further select the discriminate features for subsequent classification. We strictly evaluate the SVM-Adaboost on a constructed gold-standard σ 54 promoter dataset using ten-fold cross validation 100 times, and achieved an average accuracy of 96.06%.

关键词： DNA Support vector machines Feature extraction Training Prediction algorithms Benchmark testing Computational modeling

来源：评论

学校读者我要写书评

暂无评论

Temperature sensor based on selective liquid-filled twin-core photonic crystal fiber 6

Temperature sensor based on selective liquid-filled twin-cor...

引用

Optical Sensing and Detection VI 2020

作者： Wang, Chenlu Shum, Perry Ping Hu, Dora Juan Juan Xu, Zhilin Liu, Shuhui Zhu, Yongwei Zheng, Yu Li, Baocheng Chen, Yang Tong, Weijun Meng, Yue Humbert, Georges Cintra CNRS/NTU/THALES Umi 3288 Singapore639798 Singapore School of Electrical and Electronic Engineering Nanyang Technological University Singapore639798 Singapore Institute for Infocomm Research Astar Singapore Singapore Moe Key Laboratory of Fundamental Physical Quantities Measurement Hubei Key Laboratory of Gravitation and Quantum Physics Pgmf School of Physics Huazhong University of Science and Technology Wuhan430074 China Hubei Key Laboratory of Optical Information and Pattern Recognition Wuhan Institute of Technology Wuhan430205 China Yangtze Optical Fibre and Cable Joint Stock Limited Company China Xlim Research Institute Umr Cnrs University of Limoges 123 av. A. Thomas Limoges87060 France

ISBN: (纸本)9781510634800

We experimentally demonstrated a temperature sensor by selectively infiltrating refractive index liquid (RIL) in the central air hole of a twin-core photonic crystal fiber (PCF). The selective liquid infiltration was realized by putting the PCF in the bulk liquid with its central air hole open for liquid infiltration using capillary effect. The rest of the air holes were covered by UV glue. The three-dimensional stage was used to translate the PCF, and a tapered SMF was used to transfer the UV glue to cover the air holes under the microscope. After UV glue was solidified by exposing the fiber end under the UV light, the PCF end was dipped into the RIL to fill the central air hole by capillary effect. Due to the large thermos-optic coefficient of the RIL, the RIL filled air channel would act as a liquid core whose core modes would be highly dependent on the ambient temperature. The core modes of the RIL filled core would be phase matched to the fundamental mode of the two solid cores. Therefore, the phase matching wavelengths for the mode coupling among the two solid cores of PCF and the liquid core were highly temperature sensitive. The resonant dips in the transmission spectrum were measured to estimate the temperature sensitivity. The experiment used a commercially available twin core PCF, and blocked all but the central airhole at one of the ends facets by UV glue (NOA81, Norland), the remaining open holes are infiltrated over a length of 10 cm by capillary force with fluid (Cargille Laboratories Inc. index-matching fluid, series A) that possesses a refractive index of 1.46 at 589.3nm, 25°C, and the thermal coefficient is - 0.000389 RIU/°C, which is around 10 times of that coefficient of silica. Any temperature induced changes will have an influence on the propagation properties because of the highly temperature response of the refractive index of the fluid. With a fiber cleaver, a 1.8 cm long PCF was then cut from the longer length of the partially liquid filled

关键词： Photonic crystal fibers

来源：评论

学校读者我要写书评

暂无评论

Object relational graph with teacher-recommended learning for video captioning

arXiv

引用

arXiv 2020年

作者： Zhang, Ziqi Shi, Yaya Yuan, Chunfeng Li, Bing Wang, Peijin Hu, Weiming Zha, Zhengjun National Laboratory of Pattern Recognition CASIA University of Science and Technology of China University of Chinese Academy of Sciences Center for Excellence in Brain Science and Intelligence Technology CAS Aerospace Information Research Institute CAS PeopleAI Inc. State Key Laboratory of Communication Content Cognition People's Daily Online

Taking full advantage of the information from both vision and language is critical for the video captioning task. Existing models lack adequate visual representation due to the neglect of interaction between object, and sufficient training for content-related words due to long-tailed problems. In this paper, we propose a complete video captioning system including both a novel model and an effective training strategy. Specifically, we propose an object relational graph (ORG) based encoder, which captures more detailed interaction features to enrich visual representation. Meanwhile, we design a teacher-recommended learning (TRL) method to make full use of the successful external language model (ELM) to integrate the abundant linguistic knowledge into the caption model. The ELM generates more semantically similar word proposals which extend the ground-truth words used for training to deal with the long-tailed problem. Experimental evaluations on three benchmarks: MSVD, MSR-VTT and VATEX show the proposed ORG-TRL system achieves state-of-the-art performance. Extensive ablation studies and visualizations illustrate the effectiveness of our system. Copyright © 2020, The Authors. All rights reserved.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Object Relational Graph With Teacher-Recommended Learning for Video Captioning

Object Relational Graph With Teacher-Recommended Learning fo...

引用

Conference on Computer Vision and pattern recognition (CVPR)

作者： Ziqi Zhang Yaya Shi Chunfeng Yuan Bing Li Peijin Wang Weiming Hu Zheng-Jun Zha National Laboratory of Pattern Recognition CASIA University of Chinese Academy of Sciences University of Science and Technology of China PeopleAI Inc. State Key Laboratory of Communication Content Cognition People's Daily Online Aerospace Information Research Institute CAS Center for Excellence in Brain Science and Intelligence Technology CAS

ISBN: (数字)9781728171685

ISBN: (纸本)9781728171692

Taking full advantage of the information from both vision and language is critical for the video captioning task. Existing models lack adequate visual representation due to the neglect of interaction between object, and sufficient training for content-related words due to long-tailed problems. In this paper, we propose a complete video captioning system including both a novel model and an effective training strategy. Specifically, we propose an object relational graph (ORG) based encoder, which captures more detailed interaction features to enrich visual representation. Meanwhile, we design a teacher-recommended learning (TRL) method to make full use of the successful external language model (ELM) to integrate the abundant linguistic knowledge into the caption model. The ELM generates more semantically similar word proposals which extend the groundtruth words used for training to deal with the long-tailed problem. Experimental evaluations on three benchmarks: MSVD, MSR-VTT and VATEX show the proposed ORG-TRL system achieves state-of-the-art performance. Extensive ablation studies and visualizations illustrate the effectiveness of our system.

关键词： Task analysis Visualization Feature extraction Cognition Linguistics Training Proposals

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：