检索结果-内蒙古大学图书馆

2024 IEEE International Conference on Robotics and Biomimetics, ROBIO 2024

作者： Li, Pengcheng Guo, Shuxiang Li, Chunying Southern University of Technology and Science Department of Electronic and Electrical Engineering Shenzhen China Aerospace Center Hospital School of Life Science Key Laboratory of Convergence Medical Engineering System and Healthcare Technology Ministry of Industry and Information Technology Beijing Institute of Technology Beijing China

ISBN: (纸本)9781665481090

Bilateral training is a widely adopted approach in upper limb rehabilitation due to its effectiveness and ease of implementation. Variable stiffness actuators enhance this approach by facilitating compliant human-machine interaction, ensuring both comfort and safety. However, optimizing stiffness levels for individual subjects to maximize training effectiveness remains a significant challenge. The difficulty of different task phases varies across subjects, necessitating customized robotic assistance. This paper proposes an adaptive stiffness modulation strategy that leverages the cyclic nature of rehabilitation tasks. An adaptive frequency oscillator is employed for real-time phase detection, while a tuning rule, based on motion tracking error and muscular activation, dynamically adjusts stiffness levels. Experimental validation with two participants demonstrated that the proposed strategy effectively promotes affected arm motion and tailors assistance to the user's specific needs. © 2024 IEEE.

关键词： Human robot interaction

来源：评论

学校读者我要写书评

暂无评论

Combination of a reaction cell and an ultra-high vacuum system for the in situ preparation and characterization of a model catalyst

引用

Nuclear science and Techniques 2023年第5期34卷 13-21页

作者： Yi-Jing Zang Shu-Cheng Shi Yong Han Hui Zhang Wei-Jia Wang Peng Liu Mao Ye Zhi Liu State Key Laboratory of Functional Materials for Informatics Shanghai Institute of Microsystem and Information TechnologyChinese Academy of SciencesShanghai 200050China School of Physical Science and Technology ShanghaiTech UniversityShanghai 201210China Center for Transformative Science ShanghaiTech UniversityShanghai 201210China University of Chinese Academy of Sciences Beijing 100049China

An in-depth understanding of the structure-activity relationship between the surface structure,chemical composition,adsorption and desorption of molecules,and their reaction activity and selectivity is necessary for the rational design of high-performance ***,we present a method for studying catalytic mechanisms using a combination of in situ reaction cells and surface science *** proposed system consists of four parts:preparation chamber,temperatureprogrammed desorption(TPD)chamber,quick load-lock chamber,and in situ reaction *** preparation chamber was equipped with setups based on the surface science techniques used for standard sample preparation and characterization,including an Ar+sputter gun,Auger electron spectrometer,and a low-energy electron *** a well-defined model catalyst was prepared,the sample was transferred to a TPD chamber to investigate the adsorption and desorption of the probe molecule,or to the reaction cell,to measure the catalytic activity.A thermal desorption experiment for methanol on a clean Cu(111)surface was conducted to demonstrate the functionality of the preparation and TPD ***,the repeatability of the in situ reaction cell experiment was verified by CO_(2) hydrogenation on the Ni(110)*** a reaction pressure of 800 Torr at 673 K,turnover frequencies for the methanation reaction and reverse water-gas shift reaction were 0.15 and 7.55 Ni atom^(-1) s^(-1),respectively.

关键词： Surface science Model catalysts Ultra-high vacuum Temperature-programmed desorption In situ reaction cell

来源：评论

学校读者我要写书评

暂无评论

Combined Representation Learning for Uncertain Knowledge Graphs 2

Combined Representation Learning for Uncertain Knowledge Gra...

引用

2nd International Conference on Mechatronics, IoT and Industrial Informatics, ICMIII 2024

作者： Qiao, Rui Zhong, Xiaolei Fu, Yang Wuhan University of Science and Technology School of Computer Science and Technology Wuhan China Wuhan University of Science and Technology Hubei Province Key Laboratory of Intelligent Information Processing and Real-Time Industrial System Wuhan China Dianchi College Kunming China Huazhong University of Science and Technology Wuhan China

ISBN: (纸本)9798350386639

Uncertain knowledge graphs store the relations between entities in the real world in the form of weighted triples, where the weights indicate the confidence scores of the triples to be true. However, there is limited research on the inference of uncertain knowledge graphs, especially in the integration of symbolic and numerical methods. Rules are explicit knowledge. Encoding the rules directly can provide more knowledge graph semantic information and can make full use of the interpretability and accuracy of logical rules. Unfortunately, none of the existing methods directly encode rules for uncertain knowledge graphs, but only use rules to calculate the confidence of unseen triples in training data. In this paper, we propose a new reasoning model CRLUKG for uncertain knowledge graphs, that combines the advantages of symbolic and numerical reasoning. We directly encode rules mined from the knowledge graph as one of the inputs of the CRLUKG model. Compositional representation learning with triple and rule embedding is implemented for optimizing objective function for triples and relations pairs. Experimental results demonstrate that our proposed method enhances the accuracy of reasoning, and furthermore, CRLUKG exhibits superior performance in comparison to baseline models when handling multi-task scenarios. © 2024 IEEE.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Identification of international trade patterns of agricultural products:the evolution of communities and their core countries

引用

地球空间信息科学学报（英文版） 2024年第1期27卷 49-63页

作者： Jiaxin Dong Siwei Li Lina Huang Jing He Wenping Jiang Fu Ren Yujing Wang Jiang Sun Hao Zhang School of Remote Sensing and Information Engineering Wuhan UniversityWuhanChina School of Remote Sensing and Information Engineering Wuhan UniversityWuhanChina State Key Laboratory of Information Engineering in Surveying Mapping and Remote SensingWuhan UniversityWuhanChina School of Resource and Environmental Sciences Wuhan UniversityWuhanChina School of Resource and Environmental Sciences Wuhan UniversityWuhanChina Key Laboratory of Geographic Information Systems Ministry of EducationWuhan UniversityWuhanChina Department of Aerospace System and Application The 54 Research Institute of China Electronics Technology Group CorporationShijiazhuangChina Institute of Natural Resources Survey Hydrogeology and Engineering Geology Institute of Hubei Geological BureauJingzhouChina Management Department 32034 TroopsChengduChina

As a special branch of global trade,the trade of agricultural products has an important impact on food security and the *** this paper,we studied international trade network of agricultural products from 2000 to 2016 as a whole and in *** explored the overall characteristics of the network,analyzed the evolution of communities and identified core countries of the *** results show that the structure of the trade network became increasingly complex and the trade relations became closer over *** were four major communities in the network,whose primary core countries were Germany,the United states,Brazil,and *** 2007,the community represented by China has disappeared,and the community pattern of the network has been in a three-pillar state and basically *** discuss the actual roles of certain trading countries,the formation of communities and the impact of economic events on agricultural products *** paper reveals the underlying patterns of the agricultural products trade and provides a way to track its evolution over time.

关键词： Complex network communities core countries international trade of agricultural products spatial pattern

来源：评论

学校读者我要写书评

暂无评论

Adaptive SOM neural network algorithm 3

Adaptive SOM neural network algorithm

引用

3rd International Conference on Artificial Intelligence, Automation, and High-Performance Computing, AIAHPC 2023

作者： Wang, Xin Yan, Taishan School of Information Science and Engineering Hunan Institute of Science and Technology Hunan Yueyang China Hunan Institute of Science and Technology School of Information Science and Engineering China Key Laboratory of Hunan Province on Intelligent Control and Optimization of Complex Industrial Logistics System Hunan Yueyang China

ISBN: (数字)9781510666580

ISBN: (纸本)9781510666573

In order to improve the performance of traditional SOM model, an adaptive SOM neural network algorithm is proposed. By introducing the error square sum solution formula, the clustering error of the model sub-data set is calculated by using the method of cutting the data set, and the change trend of the clustering error is quickly obtained. Then the learning rate of the SOM network is adaptively adjusted according to this, and the convergence speed is accelerated on the basis of ensuring that the network is fully trained, thereby improving the performance of the SOM network. © 2023 SPIE.

关键词： Errors

来源：评论

学校读者我要写书评

暂无评论

FIRE: A Dataset for Feedback Integration and Refinement Evaluation of Multimodal Models 38

FIRE: A Dataset for Feedback Integration and Refinement Eval...

引用

38th Conference on Neural information Processing systems, NeurIPS 2024

作者： Li, Pengxiang Gao, Zhi Zhang, Bofei Yuan, Tao Wu, Yuwei Harandi, Mehrtash Jia, Yunde Zhu, Song-Chun Li, Qing Beijing Key Laboratory of Intelligent Information Technology School of Computer Science & Technology Beijing Institute of Technology China State Key Laboratory of General Artificial Intelligence BIGAI China State Key Laboratory of General Artificial Intelligence Peking University China Department of Electrical and Computer System Engineering Monash University Australia Guangdong Laboratory of Machine Perception and Intelligent Computing Shenzhen MSU-BIT University China Department of Automation Tsinghua University China

Vision language models (VLMs) have achieved impressive progress in diverse applications, becoming a prevalent research direction. In this paper, we build FIRE, a feedback-refinement dataset, consisting of 1.1M multi-turn conversations that are derived from 27 source datasets, empowering VLMs to spontaneously refine their responses based on user feedback across diverse tasks. To scale up the data collection, FIRE is collected in two components: FIRE-100K and FIRE-1M, where FIRE-100K is generated by GPT-4V, and FIRE-1M is freely generated via models trained on FIRE-100K. Then, we build FIRE-Bench, a benchmark to comprehensively evaluate the feedback-refining capability of VLMs, which contains 11K feedback-refinement conversations as the test data, two evaluation settings, and a model to provide feedback for VLMs. We develop the FIRE-LLaVA model by fine-tuning LLaVA on FIRE-100K and FIRE-1M, which shows remarkable feedback-refining capability on FIRE-Bench and outperforms untrained VLMs by 50%, making more efficient user-agent interactions and underscoring the significance of the FIRE dataset. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Optimization of optical convolution kernel of optoelectronic hybrid convolution neural network

引用

Optoelectronics Letters 2022年第3期18卷 181-186页

作者： XU Xiaofeng ZHU Lianqing ZHUANG Wei ZHANG Dongliang LU Lidan YUAN Pei School of Electro-Optical Engineering Changchun University of Science and TechnologyJilin 130022China Key Laboratory of the Ministry of Education for Optoelectronic Measurement Technology and Instrument Beijing Information Science and Technology UniversityBeijing 100192China Beijing Laboratory of Optical Fiber Sensing and System Beijing Information Science and Technology UniversityBeijing 100016China

To enhance the optical computation’s utilization efficiency, we develop an optimization method for optical convolution kernel in the optoelectronic hybrid convolution neural network(OHCNN). To comply with the actual calculation process, the convolution kernel is expanded from single-channel to two-channel, containing positive and negative weights. The Fashion-MNIST dataset is used to test the network architecture’s accuracy, and the accuracy is improved by 7.5% with the optimized optical convolution kernel. The energy efficiency ratio(EER) of two-channel network is 46.7% higher than that of the single-channel network, and it is 2.53 times of that of traditional electronic products.

关键词： convolution kernel weights

来源：评论

学校读者我要写书评

暂无评论

Automated Design of Complex Analog Circuits with Multiagent based Reinforcement Learning

Automated Design of Complex Analog Circuits with Multiagent ...

引用

Design Automation Conference

作者： Jinxin Zhang Jiarui Bao Zhangcheng Huang Xuan Zeng Ye Lu State Key Lab. of ASIC & System School of Information Science and Technology Frontier Institute of Chip and System State Key Lab. of ASIC & System Microelectronics Department Fudan University Shanghai China

Despite the effort of analog circuit design automation, currently complex analog circuit design still requires extensive manual iterations, making it labor intensive and time-consuming. Recently, reinforcement learning (RL) algorithms have been demonstrated successfully for the analog circuit design optimization. However, a robust and highly efficient RL method to design analog circuits with complex design space has not been fully explored yet. In this work, inspired by multiagent planning theory as well as human expert design practice, we propose a multiagent based RL (MA-RL) framework to tackle this issue. Particularly, we (i) partition the complex analog circuits into several sub-blocks based on topology information and effectively reduce the complexity of design search space; (ii) leverage MA-RL for the circuit optimization, where each agent corresponds to a single sub-block, and the interactions between agents delicately mimic the best design tradeoffs between circuit sub-blocks by human experts; (iii) introduce the multiagent twin-delayed techniques to further boost training stability and accomplish higher performances. Experiments on two different analog circuit topologies and knowledge transfers between two technology nodes are demonstrated. It’s shown that MA-RL framework can achieve the best FoM for complex analog circuits design. This work shines the light for future large scale analog circuit system design automation.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Memristor-based in-situ convolutional strategy for accurate braille recognition

引用

science China Materials 2024年第12期67卷 3986-3993页

作者： Xianghong Zhang Congyao Qin Wenhong Peng Ningpu Qin Enping Cheng Jianxin Wu Yuyang Fan Qian Yang Huipeng Chen Institute of Optoelectronic Display National&Local United Engineering Lab of Flat Panel Display TechnologyFuzhou UniversityFuzhou 350002China Zhicheng College Fuzhou UniversityFuzhou 350002China Fujian Science&Technology Innovation Laboratory for Optoelectronic Information of China Fuzhou 350100China State Key Laboratory of ASIC and System School of MicroelectronicsFudan UniversityShanghai 200433China

Signal processing has entered the era of big data,and improving processing efficiency becomes *** computing architectures face computational efficiency limitations due to the separation of storage and *** circuits based on multi-conductor devices enable full hardware convolutional neural networks(CNNs),which hold great potential to improve computational ***,when processing large-scale convolutional computations,there is still a significant amount of device redundancy,resulting in low computational power consumption and high computational ***,we innovatively propose a memristor-based in-situ convolutional strategy,which uses the dynamic changes in the conductive wire,doping area,and polarization area of memristors as the process of convolutional operations,and uses the time required for conductance switching of a single device as the computation result,embodying convolutional computation through the unique spiked digital signal of the *** strategy reasonably encodes complex analog signals into simple digital signals through a memristor,completing the convolutional computation at the device level,which is essential for complex signal processing and computational efficiency *** on the implementation of device-level convolutional computing,we have achieved feature recognition and noise filtering for braille *** believe that our successful implementation of convolutional computing at the device level will promote the construction of complex CNNs with large-scale convolutional computing capabilities,bringing innovation and development to the field of neuromorphic computing.

关键词： convolutional computing multi-conductor memristor conductive filaments

来源：评论

学校读者我要写书评

暂无评论

AISLE: Self-supervised Representation Learning for the Investigation of Advanced Persistent Threat 7

AISLE: Self-supervised Representation Learning for the Inves...

引用

7th IEEE International Conference on Data science in Cyberspace, DSC 2022

作者： Jia, Zian Wang, Xiaosu Xiong, Yun Zhang, Yao Zhao, JinJing Shanghai Key Laboratory of Data Science School of Computer Science Fudan University China National Key Laboratory of Science and Technology on Information System Security China

ISBN: (数字)9781665474801

ISBN: (纸本)9781665474801

Advanced Persistent Threats (APT) are difficult to detect and defend due to their high variability and concealment. Current APT detection and investigation approaches suffer from two major problems. First, most recent models heavily rely on heuristic rules derived from a large amount of expensive prior knowledge, which in turn prevents the models from generalizing to new types of APT attacks. Second, the development of existing fully supervised models is limited by the scarcity of APT attack data. In this paper, we first construct the provenance graph by introducing logical entities to reduce the dependency on prior knowledge. Then we propose a novel self-supervised representation-learning based model, AISLE, for the investigation of the APT attack, which consists of a graph structure encoder (GSE) and an entity interaction pattern encoder (IPE). The GSE employs a graph attention auto-encoder to effectively compress the structural information of the graph;and the IPE employs a LSTM auto-encoder to extract the interaction patterns of entities from their interaction history. The two entity embeddings calculated respectively by the two auto-encoders are concatenated to form the final representation of the entity, which is evaluated by the attack investigation module to identify attack entities. Our model is evaluated on ten real-world APT attacks in a realistic virtual environment. The results show that our model can achieve superior generalization ability and consistently outperform the latest state-of-the-art APT attack investigation approaches. © 2022 IEEE.

关键词： Graph neural networks

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：