检索结果-内蒙古大学图书馆

International Conference on Advanced Robotics and Mechatronics (ICARM)

作者： Min Zeng Jason Gu Ying Feng AHU-IAI AI Joint Laboratory Anhui University Institute of Artificial Intelligence Hefei Comprehensive National Science Center Hefei China Department of Electrical and Computer Engineering Dalhousie University Halifax NS Canada College of Automation Science and Engineering South China University of Technology Guangzhou China

While lower limb exoskeleton robots can realize assisted walking by extracting the user's motion intention, it is difficult to effectively obtain the motion intention of the human body and convert it into information for the robot. In this paper, a novel model based on sEMG-Transformer is proposed for continuous motion prediction of multiple joint angles of lower limbs and applied to the developed lower limb exoskeleton robot. The sEMG-Transformer model can be used to extract the time series features from the sEMG sequences and establish the mapping between input data and multi-joint angle. Then, the predicted multi-joint angles are inputted into the developed lower limb exoskeleton robot. Experimental studies are performed with able-bodied human wearers and compared to existing methods, such as convolutional neural network (CNN), back propagation (BP), and long short-term memory (LSTM) networks. The motion intention estimation based on the sEMG-Transformer network has better estimation performance, which can effectively enable users to walk synchronously with the lower limb exoskeleton robot.

关键词：

来源：评论

学校读者我要写书评

暂无评论

LU2Net: A Lightweight Network for Real-time Underwater Image Enhancement

arXiv

引用

arXiv 2024年

作者： Yang, Haodong Xu, Jisheng Lin, Zhiliang He, Jianping The Department of Computer Science Shanghai Jiao Tong University China The Department of Automation Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai Engineering Research Center of Intelligent Control and Management Shanghai200240 China The School of Ocean and Civil Engineering Shanghai Jiao Tong University State Key Laboratory of Ocean Engineering Shanghai200240 China

computer vision techniques have empowered underwater robots to effectively undertake a multitude of tasks, including object tracking and path planning. However, underwater optical factors like light refraction and absorption present challenges to underwater vision, which cause degradation of underwater images. A variety of underwater image enhancement methods have been proposed to improve the effectiveness of underwater vision perception. Nevertheless, for real-time vision tasks on underwater robots, it is necessary to overcome the challenges associated with algorithmic efficiency and real-time capabilities. In this paper, we introduce Lightweight Underwater Unet (LU2Net), a novel U-shape network designed specifically for real-time enhancement of underwater images. The proposed model incorporates axial depthwise convolution and the channel attention module, enabling it to significantly reduce computational demands and model parameters, thereby improving processing speed. The extensive experiments conducted on the dataset and real-world underwater robots demonstrate the exceptional performance and speed of proposed model. It is capable of providing well-enhanced underwater images at a speed 8 times faster than the current state-of-the-art underwater image enhancement method. Moreover, LU2Net is able to handle real-time underwater video enhancement. Copyright © 2024, The Authors. All rights reserved.

关键词： Motion planning

来源：评论

学校读者我要写书评

暂无评论

Modeling Inter-Intra Heterogeneity for Graph Federated Learning 39

Modeling Inter-Intra Heterogeneity for Graph Federated Learn...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Yu, Wentao Chen, Shuo Tong, Yongxin Gu, Tianlong Gong, Chen School of Computer Science and Engineering Nanjing University of Science and Technology China Center for Advanced Intelligence Project RIKEN Japan State Key Laboratory of Complex & Critical Software Environment Beihang University China Engineering Research Center of Trustworthy AI Ministry of Education Jinan University China Department of Automation Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University China

ISBN: (纸本)157735897X

Heterogeneity is a fundamental and challenging issue in federated learning, especially for the graph data due to the complex relationships among the graph nodes. To deal with the heterogeneity, lots of existing methods perform the weighted federation based on their calculated similarities between pairwise clients (i.e., subgraphs). However, their inter-subgraph similarities estimated with the outputs of local models are less reliable, because the final outputs of local models may not comprehensively represent the real distribution of subgraph data. In addition, they ignore the critical intra-heterogeneity which usually exists within each subgraph itself. To address these issues, we propose a novel Federated learning method by integrally modeling the Inter-Intra Heterogeneity (FedIIH). For the inter-subgraph relationship, we propose a novel hierarchical variational model to infer the whole distribution of subgraph data in a multi-level form, so that we can accurately characterize the inter-subgraph similarities with the global perspective. For the intra-heterogeneity, we disentangle the subgraph into multiple latent factors and partition the model parameters into multiple parts, where each part corresponds to a single latent factor. Our FedIIH not only properly computes the distribution similarities between subgraphs, but also learns disentangled representations that are robust to irrelevant factors within subgraphs, so that it successfully considers the inter- and intra- heterogeneity simultaneously. Extensive experiments on six homophilic and five heterophilic graph datasets in both non-overlapping and overlapping settings demonstrate the effectiveness of our method when compared with nine state-of-the-art methods. Specifically, FedIIH averagely outperforms the second-best method by a large margin of 5.79% on all heterophilic datasets. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Federated learning

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 24

FIRE: a dataset for feedback integration and refinement eval...

引用

Proceedings of the 38th International Conference on Neural Information Processing Systems

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

ISBN: (纸本)9798331314385

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.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Sustainable Self-evolution Adversarial Training

arXiv

引用

arXiv 2024年

作者： Wang, Wenxuan Wang, Chenglei Qi, Huihui Ye, Menghao Qian, Xuelin Wang, Peng Zhang, Yanning School of Computer Science Northwestern Polytechnical University National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology Shaanxi Xi’an China School of Automation Northwestern Polytechnical University The BRain and Artificial INtelligence Lab Shaanxi Xi’an China

With the wide application of deep neural network models in various computer vision tasks, there has been a proliferation of adversarial example generation strategies aimed at deeply exploring model security. However, existing adversarial training defense models, which rely on single or limited types of attacks under a one-time learning process, struggle to adapt to the dynamic and evolving nature of attack methods. Therefore, to achieve defense performance improvements for models in long-term applications, we propose a novel Sustainable Self-Evolution Adversarial Training (SSEAT) framework. Specifically, we introduce a continual adversarial defense pipeline to realize learning from various kinds of adversarial examples across multiple stages. Additionally, to address the issue of model catastrophic forgetting caused by continual learning from ongoing novel attacks, we propose an adversarial data replay module to better select more diverse and key relearning data. Furthermore, we design a consistency regularization strategy to encourage current defense models to learn more from previously trained ones, guiding them to retain more past knowledge and maintain accuracy on clean samples. Extensive experiments have been conducted to verify the efficacy of the proposed SSEAT defense method, which demonstrates superior defense performance and classification accuracy compared to competitors. Copyright © 2024, The Authors. All rights reserved.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Towards Open-Set Text Recognition via Label-to-Prototype Learning

arXiv

引用

arXiv 2022年

作者： Liu, Chang Yang, Chun Qin, Hai-Bo Zhu, Xiaobin Liu, Cheng-Lin Yin, Xu-Cheng Department of Computer Science and Technology School of Computer and Communication Engineering University of Science and Technology Beijing Beijing100083 China National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences Beijing100190 China

Scene text recognition is a popular topic and extensively used in the industry. Although many methods have achieved satisfactory performance for the close-set text recognition challenges, these methods lose feasibility in open-set scenarios, where collecting data or retraining models for novel characters could yield a high cost. For example, annotating samples for foreign languages can be expensive, whereas retraining the model each time when a "novel" character is discovered from historical documents costs both time and resources. In this paper, we introduce and formulate a new open-set text recognition task which demands the capability to spot and recognize novel characters without retraining. A label-to-prototype learning framework is also proposed as a baseline for the proposed task. Specifically, the framework introduces a generalizable label-to-prototype mapping function to build prototypes (class centers) for both seen and unseen classes. An open-set predictor is then utilized to recognize or reject samples according to the prototypes. The implementation of rejection capability over out-of-set characters allows automatic spotting of unknown characters in the incoming data stream. Extensive experiments show that our method achieves promising performance on a variety of zero-shot, close-set, and open-set text recognition datasets. Copyright © 2022, The Authors. All rights reserved.

关键词： Character recognition

来源：评论

学校读者我要写书评

暂无评论

A New Visual & Inertial Based Satellite Quality Evaluation Method 5

A New Visual & Inertial Based Satellite Quality Evaluation M...

引用

5th International Conference on Artificial Intelligence and Pattern Recognition, AIPR 2022

作者： Qiao, Pingan Wu, Ruichen Sun, Lei Yang, Dongfang Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing Xi'an710121 China School of Computer Science Xi'an University of Posts and Telecommunications Xi'an710121 China School of Automation Xi'an University of Posts and Telecommunications Xi'an710121 China The Rocket Force University of Engineering Graduate School Xi'an710025 China

ISBN: (纸本)9781450396899

Visual and inertial navigation have obvious complementarity in navigation accuracy, and the combined navigation of the two has excellent anti-interference ability. In this paper, a visual-inertial-based satellite quality evaluation method is proposed. This method can judge whether the GPS (Global Positioning System) is interfered by comparing the visual-inertial navigation information with the GPS data information in the geographic coordinate system. This method enables the UAV to quickly switch the navigation mode under the condition of being disturbed, which ensures that the navigation function is accurate and free from interference, and provides a more solid foundation for the navigation of the UAV and other platforms. © 2022 ACM.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

Binary Banyan Tree Growth Optimization for High-Dimensional Feature Selection

SSRN

引用

SSRN 2023年

作者： Wu, Xian Fei, Minrui Zhou, Wenju Du, Songlin Fei, Zixiang Zhou, Huiyu Shanghai Key Laboratory of Power Station Automation Technology School of Mechatronics Engineering and Automation Shanghai University Shanghai200444 China School of Computer Engineering and Science Shanghai University Shanghai200444 China School of Computing and Mathematical Sciences University of Leicester LeicesterLE1 7RH United Kingdom

In Scientific and Technical Service resources (STSR) classification, the existence of high-dimensional feature space results in increased computational cost and deteriorated accuracy. Therefore, identifying the optimal feature combination from raw text vectors is a crucial step towards effective data classification. This paper proposes a novel metaheuristic named Binary Banyan Tree Growth Optimization (BBTGO) for high-dimensional feature selection. Inspired by the unique growth characteristics of the Banyan tree, BBTGO leverages several search techniques with Boolean vectors, including rooting operator, multi-trunk operator, adjustment operator, and perturbation phase. These operators enhance the search for promising regions and reduce features by utilizing the optimal solutions clustered within subgroups. Furthermore, BBTGO incorporates a dynamic adjustment mechanism that periodically activates different growth operators to meet the search demands in high-dimensional space. The exploration and exploitation capabilities of BBTGO are examined through the statistical analysis of various metrics. The proposed method demonstrates excellent results on 12 high-dimensional benchmark datasets and is successfully applied to feature selection in STSR text. The experimental results show that BBTGO outperforms other methods in terms of selected features, classification accuracy, fitness, and processing time. © 2023, The Authors. All rights reserved.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Point Gated Attention

Point Gated Attention

引用

2022 Chinese automation Congress, CAC 2022

作者： Wang, Haibin Wang, Tian Zhang, Mengyi Zhang, Baochang Shi, Peng Snoussi, Hichem Beihang University School of Automation Science and Electrical Engineering Beijing China Nanjing University of Science and Technology Jiangsu Key Laboratory of Image and Video Understandingof Scoial Safety Nanjing China Institute of Artificial Intellgence Beihang University Beijing China Nanjing Tech University College of Electrical Engineering and Control Science Nanjing China Fujian Normal University School of Mathematics and Computer Science Fujian China University of Technology of Troyes Institute Charles Delaunay-LM2S Troyes France

ISBN: (纸本)9781665465335

Self-attention networks have achieved great success in traditional language processing, and have also made great progress in image classification and object detection. When analyzing the previous work, it is found that some point cloud information is lost in their feature extraction work, so we design a network to reduce the loss when extracting features. And through the feature extraction network - Gated Attention Unit instead of Transformer, to make the extraction of point cloud features more efficient. Based on Point Transformer, a new network structure named Point Gated Attention is used to classify point clouds. The overallacc on the dataset ModelNet40 can reach 91.4%, and the average accuracy can reach 93.9%. © 2022 IEEE.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Pathways for Efficient Transition into Net Zero Energy Buildings (Nzeb) in Sub-Saharan Africa. Case Study: Cameroon, Senegal, and Côte D’Ivoire

SSRN

引用

SSRN 2023年

作者： Umaru Mohammed, Bongwirnso Wiysahnyuy, Yufenyuy Severine Ashraf, Noman Mempouo, Blaise Mengata, Ghislain Mengounou Department of Building Engineering College of Architecture and Planning Imam Abdulrahman Bin Faisal University Dammam31451 Saudi Arabia Laboratory of Computer Science Engineering and Automation University of Douala Cameroon Smart Green Shift Ltd Rotherham United Kingdom Laboratory of Technology and Applied Sciences University of Douala Cameroon

The combustion of fossil fuels to generate electricity to meet up with high energy demands of buildings, increases pollution;deteriorating the environment and accelerating climate change. The idea of net zero energy buildings (nZEB) was developed to reduce building energy use and pollution. However, there are still many obstacles to implementing the nZEB idea, notably in sub-Saharan Africa, where energy consumption and pollutant emissions from buildings are particularly high. This article focuses on Cameroon, Senegal, and Côte d'Ivoire and proposes guidelines for making a smooth transition to nZEB in sub-Saharan Africa, as are examples of strategies that might be used to minimize energy consumption in buildings and pollution. The path has been shown to consist of the following steps: conducting a baseline assessment;creating building energy codes and standards;conducting a stakeholder analysis;carrying out capacity building and awareness-raising;setting up financing mechanisms and incentives;creating a strong supply chain;setting up a monitoring and evaluation framework;piloting nZEB projects;disseminating best practices;and scaling up adoption. With this plan in place, sub-Saharan Africa can make the most of its resources while preserving the environment as it makes the move to nZEB © 2023, The Authors. All rights reserved.

关键词： Energy utilization

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：