检索结果-内蒙古大学图书馆

8th IEEE International Conference on Advanced robotics and Mechatronics, ICARM 2023

作者： Sun, Yubo Cheng, Yuanyuan Zhu, Zhizhong Liu, Jinrui Guo, Zhenhui Yu, Ningbo College of Artificial Intelligence Nankai University Tianjin300350 China Tianjin Huanhu Hospital Department of Rehabilitation Medicine Tianjin300350 China Nankai University Engineering Research Center of Trusted Behavior Intelligence Ministry of Education Tianjin300350 China Nankai University Tianjin Key Laboratory of Intelligent Robotics Tianjin300350 China Institute of Intelligence Technology and Robotic Systems Shenzhen Research Institute of Nankai University Shenzhen518083 China

ISBN: (纸本)9798350300178

Parkinson's disease (PD) is a progressive neurode-generative disorder that requires accurate severity assessment to facilitate proper medication and interventions. This study proposes a novel method for PD severity assessment by fusing bilateral surface electromyography (sEMG) signals and features using Fisher vector. The sEMG signals were measured from the tibialis anterior (TA) and lateral gastrocnemius (GL) muscles in 28 PD patients. Preprocessing was performed to remove industrial frequency noise and low-frequency trend, followed by feature extraction using a customized feature generator that included time-domain and frequency-domain features. The extracted features and preprocessed sEMG signals were then vectorized using the Fisher vector and fused as input to the classifier. Our results demonstrated that considering bilateral features is more favorable than unilateral features for the PD severity assessment. Moreover, the proposed method significantly enhanced the classification accuracy, with a remarkable classification accuracy of 96.00% achieved through the combination of our proposed method with a decision tree classifier. © 2023 IEEE.

关键词： Time domain analysis

来源：评论

学校读者我要写书评

暂无评论

Improving sharpness-aware minimization by lookahead 24

Improving sharpness-aware minimization by lookahead

引用

Proceedings of the 41st International Conference on Machine Learning

作者： Runsheng Yu Youzhi Zhang James T. Kwok Department of Computer Science and Engineering The Hong Kong University of Science and Technology Centre for Artificial Intelligence and Robotics Hong Kong Institute of Science & Innovation CAS

Sharpness-Aware Minimization (SAM), which performs gradient descent on adversarially perturbed weights, can improve generalization by identifying flatter minima. However, recent studies have shown that SAM may suffer from convergence instability and oscillate around saddle points, resulting in slow convergence and inferior performance. To address this problem, we propose the use of a lookahead mechanism to gather more information about the landscape by looking further ahead, and thus find a better trajectory to converge. By examining the nature of SAM, we simplify the extrapolation procedure, resulting in a more efficient algorithm. Theoretical results show that the proposed method converges to a stationary point and is less prone to saddle points. Experiments on standard benchmark datasets also verify that the proposed method outperforms the SOTAs, and converge more effectively to flat minima.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Identification of Predictive Subnetwork for Brain Network-Based Psychiatric Diagnosis: An Information-Theoretic Perspective

Identification of Predictive Subnetwork for Brain Network-Ba...

引用

Acoustics, Speech, and Signal Processing Workshops (ICASSPW), IEEE International Conference on

作者： Kaizhong Zheng Shujian Yu Badong Chen Institute of Artificial Intelligence and Robotics Xi’an Jiaotong University Xi’an Department of Computer Science Vrije Universiteit Amsterdam Amsterdam

Graph neural networks (GNNs) have recently been applied to develop useful diagnostic tools for psychiatric disorders. However, due to the lack of interpretability, clinicians are hard to identify quantifiable and personalizable biomarkers which provide biologically and clinically relevance. We introduce three recently proposed GNN-based psychiatric disorders diagnostic models, namely BrainIB, Graph-PRI and CI-GNN, from an information-theoretic perspective. These models are able to discriminate psychiatric patients from healthy controls and identify predictive subgraph, a.k.a. biomarkers, solely from observations. We demonstrate their improved classification accuracy and interpretability on ABIDE database. We also put forward three proposals for future research.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Head-Tail Cooperative Learning Network for Unbiased Scene Graph Generation

arXiv

引用

arXiv 2023年

作者： Wang, Lei Yuan, Zejian Lu, Yao Chen, Badong The Institute of Artificial Intelligence and Robotics Xi’an Jiaotong University Xi’an710049 China The Beijing Institute of Remote Sensing Beijing100011 China

Scene Graph Generation (SGG) as a critical task in image understanding, facing the challenge of head-biased prediction caused by the long-tail distribution of predicates. However, current unbiased SGG methods can easily prioritize improving the prediction of tail predicates while ignoring the substantial sacrifice in the prediction of head predicates, leading to a shift from head bias to tail bias. To address this issue, we propose a model-agnostic Head-Tail Collaborative Learning (HTCL) network that includes head-prefer and tail-prefer feature representation branches that collaborate to achieve accurate recognition of both head and tail predicates. We also propose a self-supervised learning approach to enhance the prediction ability of the tail-prefer feature representation branch by constraining tail-prefer predicate features. Specifically, self-supervised learning converges head predicate features to their class centers while dispersing tail predicate features as much as possible through contrast learning and head center loss. We demonstrate the effectiveness of our HTCL by applying it to various SGG models on VG150, Open Images V6 and GQA200 datasets. The results show that our method achieves higher mean Recall with a minimal sacrifice in Recall and achieves a new state-of-the-art overall performance. Our code is available at https://***/wanglei0618/HTCL. Copyright © 2023, The Authors. All rights reserved.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

EventAlign: LiDAR-Event Camera Calibration with Event Alignment Loss

EventAlign: LiDAR-Event Camera Calibration with Event Alignm...

引用

International Conference on Intelligent Transportation

作者： Pengfei Dong Renwei Hai Yanqing Shen Ziyu Zhu Shitao Chen Jingmin Xin Nanning Zheng National Key Laboratory of Human-Machine Hybrid Augmented Intelligence National Engineering Research Center for Visual Information and Applications Institute of Artificial Intelligence and Robotics Xi'an Jiaotong University Xi'an Shaanxi P.R. China Shunan Academy of Artificial Intelligence Ningbo Zhejiang China

ISBN: (数字)9798331505929

ISBN: (纸本)9798331505936

In recent years, event cameras, as a type of bio-inspired sensor, have become increasingly important in the fields of robotics and autonomous driving. Given that events inherently lack depth information, a multi-sensor solution is applied to combine events and LiDAR scans, and its performance highly depends on precise calibration between different sensors. However, due to the distinctive representation of event cameras, which only capture dynamic objects without texture structure, most previous calibration methods for event cameras have complex setups and controlled lighting conditions. In this paper, we propose a novel extrinsic calibration method by simulating events with LiDAR, which does not require any equipment beyond the sensors themselves. Specifically, we first extract LiDAR events from the continuous raw point clouds. Then a clustering algorithm is applied to refine this event data and identify motion centroids. Finally, a two-step optimization process is proposed: an initial rough calibration based on these centroids and a subsequent fine calibration achieved through nearest neighbor matching between LiDAR events and camera events. The experimental results validate that our algorithm achieves high accuracy and robustness in simulations and real-world experiments.

关键词： Point cloud compression Laser radar Accuracy Robot vision systems Clustering algorithms Cameras Robustness Sensor systems Calibration Testing

来源：评论

学校读者我要写书评

暂无评论

H3e: Learning Air Combat with a Three-Level Hierarchical Framework Embedding Expert Knowledge

SSRN

引用

SSRN 2023年

作者： Qian, Chenxu Zhang, Xuebo Li, Lun Zhao, Minghui Fang, Yongchun Institute of Robotics and Automatic Information System College of Artificial Intelligence Nankai University Tianjin China Tianjin Key Laboratory of Intelligent Robotics Nankai University China

Learning to perform air combat autonomously has been a long-standing challenge. The design of intelligent game strategies was difficult due to complex dynamic constraints and long decision-making process. Most exiting approaches depend heavily on simplified aircraft models or complex handcrafted rules. Different from previous works, this paper presents H3E, a novel and efficient Three-level Hierarchical decision framework embedding Expert knowledge, which gives birth to various strategies for high-fidelity one-on-one beyond-visual-range (BVR) air combat game. Inspired by the way pilots make decisions, we build a hierarchical framework to divide the air combat into several sub systems in which each level can perform its own task with much smaller exploration space. In addition, to make full use of the expert knowledge while minimizing its limitation, a novel "Rule-Imitation-Reinforcement" (RIR) training paradigm with an adjustable expert-guidance (AEG) loss function is established, which can increase the exploration efficiency as well as the game win rate. Finally, this work is evaluated in the Intelligent Air Game Simulator (IAGSim), a high-fidelity air combat simulation platform, through a series of games against the state-of-the-art (SOTA) methods. The learning process and game results verify the superior performance of our framework in terms of the exploration efficiency (higher rewards with the same training samples) and win rate (at least 72.9%) compared with the exiting SOTA approaches. © 2023, The Authors. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Tensor-Guided Interpolation For Off-Grid Power Spectrum Map Construction

Tensor-Guided Interpolation For Off-Grid Power Spectrum Map ...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Hao Sun Junting Chen Yuan Luo School of Science and Engineering The Chinese University of Hong Kong Shenzhen China Future Network of Intelligence Institute The Chinese University of Hong Kong Shenzhen China Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen China

This paper addresses the off-grid tensor-guided interpolation problem, aiming to reconstruct a 3D power spectrum map from sparse observations. A segmented polynomial model is employed to handle off-grid measurements, while a nuclear norm regularization is incorporated to account for the inherent low-rank characteristics of signals. An alternating regression and singular value thresholding algorithm is developed to solve the proposed method. The numerical results demonstrate the superiority of the proposed method, showcasing a remarkable improvement of over 10% in power spectrum map reconstruction accuracy when the sampling rate exceeds 6%, as compared to state-of-the-art approaches.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Depth Recognition of Hard Inclusions in Tissue Phantoms for Robotic Palpation

Depth Recognition of Hard Inclusions in Tissue Phantoms for ...

引用

2022 IEEE International Conference on Real-Time Computing and robotics, RCAR 2022

作者： Zhou, Zhenning Fang, Senlin Ye, Chaoxiang Mi, Tingting Huang, Binhua Li, Xiaoyu Yi, Zhengkun Wu, Xinyu Guangdong Provincial Key Laboratory of Robotics and Intelligent System Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen518055 China Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Guangdong Provincial Key Laboratory of Robotics and Intelligent System Shenzhen518055 China Shenzhen Institute of Artificial Intelligence and Robotics for Society SIAT Branch Shenzhen518055 China

ISBN: (数字)9781665469838

ISBN: (纸本)9781665469838

Medical palpation is an effective diagnosis method in which physicians use tactile sensation to diagnose a patient's pathology. Robotic palpation is a novel technique that leverages robots to assist medical diagnosis. The problem of tactile information loss in Robot-assisted Minimally Invasive Surgery (RMIS) has limited the development of the robot-assisted surgical system. Meanwhile, surgeons are difficult to acquire some key information about lesions only via visual feedback, such as tumor depth. To address the issue, we propose a tactile perception algorithm on the basis of the CNN-LSTM network, which achieves the depth recognition of hard inclusions in tissue phantoms. The method realizes the classification of twelve depths of hard inclusions. In addition, due to using hypergeometric distribution encoding, the proposed method can exploit the ordinal information of the labels to significantly improve the recognition accuracy rate. The experimental results on 720 real tactile data show that the average recognition rate is 96.45%. Compared with other state-of-the-art methods, the recognition accuracy rate of the proposed algorithm is the highest. © 2022 IEEE.

关键词： Tumors

来源：评论

学校读者我要写书评

暂无评论

Open-world Machine Learning: A Review and New Outlooks

arXiv

引用

arXiv 2024年

作者： Zhu, Fei Ma, Shijie Cheng, Zhen Zhang, Xu-Yao Zhang, Zhaoxiang Liu, Cheng-Lin Centre for Artificial Intelligence and Robotics Hong Kong Institute of Science and Innovation Chinese Academy of Sciences 999077 Hong Kong MAIS Institute of Automation Chinese Academy of Sciences Beijing100190 China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing100049 China

Machine learning has achieved remarkable success in many applications. However, existing studies are largely based on the closed-world assumption, which assumes that the environment is stationary, and the model is fixed once deployed. In many real-world applications, this fundamental and rather naive assumption may not hold because an open environment is complex, dynamic, and full of unknowns. In such cases, rejecting unknowns, discovering novelties, and then incrementally learning them, could enable models to be safe and evolve continually as biological systems do. This paper provides a holistic view of open-world machine learning by investigating unknown rejection, novel class discovery, and class-incremental learning in a unified paradigm. The challenges, principles, and limitations of current methodologies are discussed in detail. Finally, we discuss several potential directions for future research. This paper aims to provide a comprehensive introduction to the emerging open-world machine learning paradigm, to help researchers build more powerful AI systems in their respective fields, and to promote the development of artificial general intelligence. Copyright © 2024, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

A survey on the visual perception of humanoid robot

引用

Biomimetic intelligence & robotics 2025年第1期5卷 3-14页

作者： Teng Bin Hanming Yan Ning Wang Milutin N.Nikolić Jianming Yao Tianwei Zhang The Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen 518172China College of Intelligent Systems Science and Engineering Harbin Engineering UniversityHarbin 150001China College of Physics and Optoelectronic Engineering Shenzhen UniversityShenzhen 518060China College of Mechatronics Engineering Nanjing University of Aeronautics and AstronauticsNanjing 210016China Faculty of Technical Sciences University of Novi SadNovi Sad 21102Serbia Electronic science and technology Guangdong University of TechnologyGuangzhou 510006China

In recent years,humanoid robots have gained significant attention due to their potential to revolutionize various industries,from healthcare to manufacturing.A key factor driving this transformation is the advancement of visual perception systems,which are crucial for making humanoid robots more intelligent and *** the progress,the full potential of vision-based technologies in humanoid robots has yet to be fully *** review aims to provide a comprehensive overview of recent advancements in visual perception applied to humanoid robots,specifically focusing on applications in state estimation and environmental *** summarizing key developments and analyzing the challenges and opportunities in these areas,this paper seeks to inspire future research that can unlock new capabilities for humanoid robots,enabling them to better navigate complex environments,perform intricate tasks,and interact seamlessly with humans.

关键词： advanced technologies visual perception autonomous navigation human robot interaction environmental interaction state estimation humanoid robots advancement visual perception systemswhich

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：