检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Tao, Jiale Wang, Biao Xu, Borun Ge, Tiezheng Jiang, Yuning Li, Wen Duan, Lixin School of Computer Science and Engineering Shenzhen Institute for Advanced Study University of Electronic Science and Technology of China China Alibaba Group China

Given a source image and a driving video depicting the same object type, the motion transfer task aims to generate a video by learning the motion from the driving video while preserving the appearance from the source image. In this paper, we propose a novel structure-aware motion modeling approach, the deformable anchor model (DAM), which can automatically discover the motion structure of arbitrary objects without leveraging their prior structure information. Specifically, inspired by the known deformable part model (DPM), our DAM introduces two types of anchors or keypoints: i) a number of motion anchors that capture both appearance and motion information from the source image and driving video;ii) a latent root anchor, which is linked to the motion anchors to facilitate better learning of the representations of the object structure information. Moreover, DAM can be further extended to a hierarchical version through the introduction of additional latent anchors to model more complicated structures. By regularizing motion anchors with latent anchor(s), DAM enforces the correspondences between them to ensure the structural information is well captured and preserved. Moreover, DAM can be learned effectively in an unsupervised manner. We validate our proposed DAM for motion transfer on different benchmark datasets. Extensive experiments clearly demonstrate that DAM achieves superior performance relative to existing state-of-the-art methods. Copyright © 2022, The Authors. All rights reserved.

关键词： Anchors

来源：评论

学校读者我要写书评

暂无评论

Sub-femtonewton force sensing in solution by super-resolved photonic force microscopy (Jun, 10.1038/s41566-024-01462-7, 2024)

引用

NATURE PHOTONICS 2024年第9期18卷 998-998页

作者： Shan, Xuchen Ding, Lei Wang, Dajing Wen, Shihui Shi, Jinlong Chen, Chaohao Wang, Yang Zhu, Hongyan Huang, Zhaocun Wang, Shen S. J. Zhong, Xiaolan Liu, Baolei Reece, Peter John Ren, Wei Hao, Weichang Lu, Xunyu Lu, Jie Su, Qian Peter Chang, Lingqian Sun, Lingdong Jin, Dayong Jiang, Lei Wang, Fan Beihang University School of Physics Beijing People’s Republic of China (GRID:grid.64939.31) (ISNI:0000 0000 9999 1211) University of Technology Sydney School of Biomedical Engineering Faculty of Engineering and Information Technology Sydney Australia (GRID:grid.117476.2) (ISNI:0000 0004 1936 7611) RMIT University Centre for Atomaterials and Nanomanufacturing School of Science Melbourne Australia (GRID:grid.1017.7) (ISNI:0000 0001 2163 3550) University of Technology Sydney Institute for Biomedical Materials and Devices (IBMD) School of Mathematical and Physical Sciences Faculty of Science Sydney Australia (GRID:grid.117476.2) (ISNI:0000 0004 1936 7611) The Australian National University Australian Research Council Centre of Excellence for Transformative Meta-Optical Systems Department of Electronic Materials Engineering Research School of Physics Canberra Australia (GRID:grid.1001.0) (ISNI:0000 0001 2180 7477) Beihang University Key Laboratory of Biomechanics and Mechanobiology (Ministry of Education) Beijing Advanced Innovation Center for Biomedical Engineering School of Biological Science and Medical Engineering Beijing People’s Republic of China (GRID:grid.64939.31) (ISNI:0000 0000 9999 1211) University of Melbourne Computing and Information Systems Department Melbourne School of Engineering Melbourne Australia (GRID:grid.1008.9) (ISNI:0000 0001 2179 088X) The University of New South Wales School of Physics Sydney Australia (GRID:grid.1005.4) (ISNI:0000 0004 4902 0432) Shaanxi Normal University School of Chemistry & Chemical Engineering Xi’an People’s Republic of China (GRID:grid.412498.2) (ISNI:0000 0004 1759 8395) The University of New South Wales Particles and Catalysis Research Laboratory School of Chemical Engineering Sydney Australia (GRID:grid.1005.4) (ISNI:0000 0004 4902 0432) University of Technology Sydney Australian Artificial Intelligence Institute Faculty of Engineering and IT Sydney Australia (GRID:grid.117476.2) (ISNI:0000 0004 1936 7611) University of

Precise force measurement is critical to probe biological events and physics processes, spanning from molecular motor’s motion to the Casimir effect, as well as the detection of gravitational waves. Yet, despite extensive technological developments, the three-dimensional nanoscale measurement of weak forces in aqueous solutions still faces major challenges. Techniques that rely on optically trapped nanoprobes are of significant potential but are beset with limitations, including probe heating induced by high trapping power, undetectable scattering signals and localization errors. Here we report the measurement of the long-distance interaction force in aqueous solutions with a minimum detected force value of 108.2 ± 510.0 attonewton. To achieve this, we develop a super-resolved photonic force microscope based on optically trapped lanthanide-doped nanoparticles coupled with nanoscale three-dimensional tracking-based force sensing. The tracking method leverages neural-network-empowered super-resolution localization, where the position of the force probe is extracted from the optical-astigmatism-modified point spread function. We achieve a force sensitivity down to 1.8 fN Hz–1/2, which approaches the nanoscale thermal limit. We experimentally measure electrophoresis forces acting on single nanoparticles as well as the surface-induced interaction force on a single nanoparticle. This work opens the avenue of nanoscale thermally limited force sensing and offers new opportunities for detecting sub-femtonewton forces over long distances and biomechanical forces at the single-molecule ***-resolved photonic force microscopy employs the fluorescence of lanthanide-doped nanoparticles as a force probe, enabling the measurement of sub-femtonewton forces with a sensitivity of 1.8 fN Hz–1/2, approaching the thermal limit.

关键词： Electrophoresis

来源：评论

学校读者我要写书评

暂无评论

A Digital Twin Empowered Lightweight Model Sharing Scheme for Multi-Robot Systems

arXiv

引用

arXiv 2023年

作者： Xiong, Kai Wang, Zhihong Leng, Supeng He, Jianhua School of Information and Communication Engineering University of Electronic Science and Technology of China Chengdu611731 China Shenzhen Institute for Advanced Study University of Electronic Science and Technology of China Shenzhen518110 China The School of Computer Science and Electronic Engineering ColchesterCO4 3SQ United Kingdom

Multi-robot system for manufacturing is an Industry Internet of Things (IIoT) paradigm with significant operational cost savings and productivity improvement, where Unmanned Aerial Vehicles (UAVs) are employed to control and implement collaborative productions without human intervention. This mission-critical system relies on 3-Dimension (3-D) scene recognition to improve operation accuracy in the production line and autonomous piloting. However, implementing 3-D point cloud learning, such as Pointnet, is challenging due to limited sensing and computing resources equipped with UAVs. Therefore, we propose a Digital Twin (DT) empowered Knowledge Distillation (KD) method to generate several lightweight learning models and select the optimal model to deploy on UAVs. With a digital replica of the UAVs preserved at the edge server, the DT system controls the model sharing network topology and learning model structure to improve recognition accuracy further. Moreover, we employ network calculus to formulate and solve the model sharing configuration problem toward minimal resource consumption, as well as convergence. Simulation experiments are conducted over a popular point cloud dataset to evaluate the proposed scheme. Experiment results show that the proposed model sharing scheme outperforms the individual model in terms of computing resource consumption and recognition accuracy. Copyright © 2023, The Authors. All rights reserved.

关键词： Multipurpose robots

来源：评论

学校读者我要写书评

暂无评论

Gedss: A Generic Framework to Enhance Model Robustness for Intrusion Detection on Noisy Data

Gedss: A Generic Framework to Enhance Model Robustness for I...

引用

International Conference on computer Supported Cooperative Work in Design

作者： Lingfeng Yao Anran Hou Weina Niu Qingjun Yuan Junpeng He Yanfeng Zhang School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu China Shenzhen Institute for Advanced Study University of Electronic Science and Technology of China Shenzhen China Henan Key Laboratory of Network Cryptography Technology Zhengzhou China Intelligent Policing Key Laboratory of Sichuan Province Sichuan Police College Luzhou China

ISBN: (数字)9798350349184

ISBN: (纸本)9798350349191

Training a deep neural network-based intrusion detection system requires a large amount of clean labeled data, yet malicious traffic datasets are usually collected from the open-source web community or simulated attack environments, which inevitably contain a large portion of unreliably labeled traffic data. The state-of-the-art methods dealing with label noise combine sample separation and semi-supervised learning (SSL), however, they are hardly usable in the traffic field because traffic data lacks a reasonable data augmentation like image data. To this end, we propose a generic label-noise-resistant framework for malicious traffic detection called Gedss. Unlike previous approaches focusing on data augmentation, our approach improves model performance by enhancing the quality of sample selection and model decision boundaries. The framework contains two parts: sample selection and semi-supervised learning. The sample selection method is presented to divide the original traffic instances into clean ones (labeled set) and noisy ones (unlabeled set). We fit a Jensen-Shannon divergence-based sample prediction loss to a mixture model as the criterion, and the threshold is automatically and dynamically adjusted, which makes our selection mechanism adaptive to various malicious traffic datasets. Besides, a semi-supervised learning method is designed, which uses two networks to jointly predict the pseudo label of the unlabeled set. Considering the class imbalance of divided labeled data, the idea of fine-tuning the models with all data is presented to improve the performance of SSL. Extensive experimental results under different label noise scenarios demonstrate that our approach outperforms state-of-the-art methods.

关键词： Training Adaptation models Noise Intrusion detection Mixture models Semisupervised learning Data augmentation

来源：评论

学校读者我要写书评

暂无评论

Interpretive Clinical Measurements Prediction and Diagnosis in ICU with Multi-Task Attention-Guided Sequential Feature Learning

Interpretive Clinical Measurements Prediction and Diagnosis ...

引用

Artificial Intelligence technology (ACAIT), Asian Conference on

作者： Peng Zhao Yan Xiao Yuqing Lei Yazhou Ren Zenglin Xu School of Basic Medical Sciences Chongqing Medical University Chongqing China School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu China Shenzhen Institute for Advanced Study University of Electronic Science and Technology of China Shenzhen China School of Computer Science and Technology Harbin Institute of Technology Shenzhen Shenzhen China Center of Artificial Intelligence Peng Cheng National Lab Shenzhen China

ISBN: (数字)9798350359145

ISBN: (纸本)9798350359152

During the outbreak of COVID-19, it is particularly important to improve clinical decision making for critically ill patients in intensive care units (ICU). Machine learning has become increasingly important in healthcare analysis with the wide adoption of Electronic Health Records (EHR). Many deep learning algorithms, such as Recurrent Neural Networks (RNNs), have been developed to deal with clinical time series data to predict the health status of patients, such as mortality, ventilation, and phenotype, etc. Despite RNN being successful in medical tasks, the special traits of data, such as long temporality, high dimensionality, existence of missing values, and multi-labels, have brought challenges to either shallow or deep learning algorithms. Motivated by the fact that the progress of diseases may vary over time, to address these challenges, we proposed a multi-task attention-guided recurrent neural network for learning sequential features (MASFL) model, which employs recurrent units and an attention mechanism. The recurrent units can memorize the past progressive information of patients after entering ICU, while the attention mechanism can selectively utilize this information for different prediction tasks. Meanwhile, the attention also helps to interpret the relationship between the clinical time series data and the prediction result. Furthermore, in order to solve undesirable local solutions for the patient’s length-of-stay task, we develop an ordinal regression loss to address the issue. According to the experiments on MIMIC-III, we demonstrate that the proposed model can improve the prediction performance over state-of-the-art prediction approaches.

关键词： Representation learning Deep learning Recurrent neural networks Time series analysis MIMICs Predictive models Prediction algorithms

来源：评论

学校读者我要写书评

暂无评论

A Joint DOA and Range Estimation Technique for Underwater Transportation System based on Compressive Sensing

A Joint DOA and Range Estimation Technique for Underwater Tr...

引用

IEEE International Conference on Consumer Electronics-Taiwan (ICCE-TW)

作者： Hai-Yan Song Chang-Yi Yang Yu-Jie Zhang Jia-Xin Tang Jia- Qi Gao School of Electrical and Information Engineering Heilongjiang Institute of Technology Harbin China Department of Computer Science and Information Engineering National Penghu University of Science and Technology Magong Taiwan R.O.C. Petro China Tarim Oil Field Company Korla China

Obstacle detection can help human to reduce risk on underwater transportation activities. In our work, we use compressive sensing technique to estimate the Direction of Arrival (DOA) and range for spatial targets especially in underwater transportation system. According to underwater acoustic propagation ray theory, the signal model for horizontal L-Shaped array is first constructed. Then, the joint DOA and range estimation is converted into an optimizing procedure, which can be finally solved by an efficient toolbox for Disciplined Convex Programming (CVX). The performance of our proposed method is discussed in the computer simulation results.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Obstacle Detection Technique for Marine Intelligent Transportation System based on Maximum likelihood Method

An Obstacle Detection Technique for Marine Intelligent Trans...

引用

IEEE International Conference on Consumer Electronics-Taiwan (ICCE-TW)

作者： Xin-Ming Ma Hai-Yan Song Chang-Yi Yang Xiao-Jun Song Dong-Xu Gao School of Electrical and Information Engineering Heilongjiang Institute of Technology Harbin China Department of Computer Science and Information Engineering National Penghu University of Science and Technology Magong Taiwan R.O.C Petro China Tarim Oil Field Company Korla China

Obstacle detection is a key technology for marine intelligent transportation system. In this paper, an obstacle detection technique for marine intelligent transportation system based on Maximum Likelihood (ML) processor is proposed. Different from most of the former source localization algorithms, our proposed algorithm explicitly makes use of both the horizontal L-Shaped array and the underwater acoustic propagation model to achieve a relatively high spatial resolution. Numerical simulations are presented to demonstrate the superior performance of our proposed algorithm.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Models for Colloidal Nanocrystal Synthesis

arXiv

引用

arXiv 2024年

作者： Gu, Kai Liang, Yingping Su, Jiaming Sun, Peihan Peng, Jia Miao, Naihua Sun, Zhimei Fu, Ying Zhong, Haizheng Zhang, Jun MIIT Key Laboratory for Low-Dimensional Quantum Structure and Devices School of Materials Sciences & Engineering Beijing Institute of Technology Beijing100081 China School of Computer Science and Technology Beijing Institute of Technology Beijing100081 China School of Materials Science and Engineering Beihang University Beijing100191 China State Key Laboratory of CNS/ATM MIIT Key Laboratory of Complex-field Intelligent Sensing Beijing Institute of Technology Beijing100081 China

Colloidal synthesis of nanocrystals usually includes complex chemical reactions and multi-step crystallization processes. Despite the great success in the past 30 years, it remains challenging to clarify the correlations between synthetic parameters of chemical reaction and physical properties of nanocrystals. Here, we developed a deep learning-based nanocrystal synthesis model that correlates synthetic parameters with the final size and shape of target nanocrystals, using a dataset of 3500 recipes covering 348 distinct nanocrystal compositions. The size and shape labels were obtained from transmission electron microscope images using a segmentation model trained with a semi-supervised algorithm on a dataset comprising 1.2 million nanocrystals. By applying the reaction intermediate-based data augmentation method and elaborated descriptors, the synthesis model was able to predict nanocrystal's size with a mean absolute error of 1.39 nm, while reaching an 89% average accuracy for shape classification. The synthesis model shows knowledge transfer capabilities across different nanocrystals with inputs of new recipes. With that, the influence of chemicals on the final size of nanocrystals was further evaluated, revealing the importance order of nanocrystal composition, precursor or ligand, and solvent. Overall, the deep learning-based nanocrystal synthesis model offers a powerful tool to expedite the development of high-quality nanocrystals. © 2024, CC BY.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Resource Optimization-Oriented Method for Generating Cooperative Interference Strategies

Resource Optimization-Oriented Method for Generating Coopera...

引用

Intelligent Communication and computer engineering (ICICCE), International Conference on

作者： Yue Zeng Qiao Liu Tingting Dai Yanwen Huang Rui Hou Yanglei Gan Junjie Lang School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu China Shenzhen Institute for Advanced Study University of Electronic Science and Technology of China Chengdu China The 54th Research Institute of China Electronics Technology Group Corporation Shijiazhuang China

The generation of effective jamming strategies stands as a critical imperative in the realm of communication countermeasures. A comparative analysis of extant jamming strategy generation methods reveals a scarcity of research that simultaneously addresses the optimization of cooperative jamming effectiveness and the judicious allocation of resources, with a focus on resource minimization. In light of these observations, this study employs a multifaceted approach, harnessing machine learning and allied methodologies, to discern potential behavioral patterns within communication stations. Specifically, we construct a scenario of communication confrontation, featuring multiple jammers and multiple communication stations. Subsequently, we establish a model for the generation of cooperative jamming strategies, leveraging a double deep Q-network. Moreover, we introduce a dual-dynamic penalty function that synergizes with the double deep Q-network. This combined approach aids the model in searching for optimal solutions under specific constraints throughout the interference process's various stages. In doing so, the model strives to optimize the utilization of interference resources while ensuring effective cooperative interference. Simulation results substantiate the efficacy of the proposed approach. The double deep Q-network algorithm, when integrated with the dual dynamic penalty function, significantly enhances interference effectiveness. Furthermore, it achieves a noteworthy 25% reduction in interference resource consumption compared to an unconstrained algorithm.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Novel Platform to Control Biofouling in Pearl Oysters Cultivation

A Novel Platform to Control Biofouling in Pearl Oysters Cult...

引用

IEEE International Conference on Robotics and Automation (ICRA)

作者： Van-Nhan Tran Quan-Dung Pham Tan-Sang Ha Yue Him Wong Sai-Kit Yeung Division of Integrative Systems and Design School of Engineering Hong Kong University of Science and Technology Clear Water Bay Hong Kong SAR Department of Computer Science and Engineering School of Engineering Hong Kong University of Science and Technology Clear Water Bay Hong Kong SAR Institute for Advanced Study Shenzhen University Shenzhen Guangdong China

This paper presents a simple yet effective design of a platform to automate the task of shellfish aquaculture, specifically pearl oysters. Compared to traditional methods, our platform can eliminate the tedious task of cleaning the pearl oysters due to fouling. Inspired by the low and high tide characteristics of the intertidal zone, our platform employs an air-water displacement mechanism to periodically float pearl oysters above the water's surface, exposing fouling organisms to air and sunlight. While pearl oysters have developed the ability to stay alive during low tide, these fouling organisms cannot survive after prolonged exposure, thus preventing them from developing. Additionally, the platform provides an alternative approach to grow not only pearl oysters but also various types of shellfish, consequently benefiting the aquaculture industry. We introduce the design of the platform and provide a comprehensive analysis. We also demonstrate the practical deployment of the platform for cultivating pearl oysters.

关键词：

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：