检索结果-内蒙古大学图书馆

Annual Conference of Industrial Electronics Society

作者： Yongchao Wang Hengrui Li Cong Li Fangzhou Liu School of Aerospace Science and Technology Xidian University Xi’an China Algorithm Engineer Research and Development Department Agile Robots Beijing China College of Intelligence Science and Technology National University of Defense Technology Changsha China Research Institute of Intelligent Control and Systems Harbin Institute of Technology Harbin China

ISBN: (数字)9781665464543

ISBN: (纸本)9781665464550

In this article, an incremental model predictive controller is proposed for the velocity-controlled robot manipulator. First, the time-delay estimation (TDE) technique is used to approximate the unknown discrepancy between the command and the real joint velocity due to velocity dynamics, and the equation of motion in the incremental form is obtained. Then, on the basis of the resulting equation of motion and taking into account joint position and velocity constraints, the incremental model predictive controller is developed by formulating a constrained optimal control problem (OCP). The constrained OCP is cast to a quadratic programming (QP) problem, making it possible to employ computationally efficient QP solvers to solve the constrained OCP. As a result, real-time control is guaranteed. Finally, experiments on a robot manipulator are implemented to verify the effectiveness of the developed incremental model predictive controller.

关键词： Service robots Computational modeling Optimal control Estimation Predictive models Mathematical models Robustness Computational efficiency Quadratic programming Predictive control

来源：评论

学校读者我要写书评

暂无评论

RaftGP: Random Fast Graph Partitioning

RaftGP: Random Fast Graph Partitioning

引用

IEEE Conference on High Performance Extreme Computing (HPEC)

作者： Yu Gao Meng Qin Yibin Ding Li Zeng Chaorui Zhang Weixi Zhang Wei Han Rongqian Zhao Bo Bai Theory Lab 2012 Labs Central Research Institute Huawei Technologies Co. Ltd. Department of Computer Science & Engineering Hong Kong University of Science & Technology Algorithm & Technology Development Department Global Technical Service Department Huawei Technologies Co. Ltd.

Graph partitioning (GP), a.k.a. community detection, is a classic problem that divides the node set of a graph into densely-connected blocks. Following prior work on the IEEE HPEC Graph Challenge benchmark and recent advances in graph machine learning, we propose a novel RAndom FasT Graph Partitioning (RaftGP) method based on an efficient graph embedding scheme. It uses the Gaussian random projection to extract community-preserving features from classic GP objectives. These features are fed into a graph neural network (GNN) to derive low-dimensional node embeddings. Surprisingly, our experiments demonstrate that a randomly initialized GNN even without training is enough for RaftGP to derive informative community-preserving embeddings and support high-quality GP. To enable the derived embeddings to tackle GP, we introduce a hierarchical model selection algorithm that simultaneously determines the number of blocks and the corresponding GP result. We evaluate RaftGP on the Graph Challenge benchmark and compare the performance with five baselines, where our method can achieve a better trade-off between quality and efficiency. In particular, compared to the baseline algorithm [1] of the IEEE HPEC Graph Challenge, our method is 6.68x - 23.9x faster on graphs with 1E3 - 5E4 nodes and at least 64.5x faster on larger (IE5 node) graphs on which the baseline takes more than 1E4 seconds. Our method achieves better accuracy on all test cases. We also develop a new graph generator to address some limitations of the original generator in the benchmark.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Advanced function approach

引用

Procedia Engineering 2011年 9卷 92-102页

作者： Simon Litvin Naum Feygenson Oleg Feygenson Vice President and Chief Scientific Officer GEN3 Partners Inc. Ten Post square Boston02109 MAUSA TRIZ expert Saint Petersburg Russian Federation Head of Training Support Department Technology Research Center Algorithm Ltd.Saint Petersburg Russian Federation

Function Approach is widely used for analyzing Engineering Systems and formulating and solving inventive problems: Function Analysis is an inalienable part of the analytical stage of any innovation project, while Function-Oriented Search is used effectively at the problem-solving stage. The goal of the current research is to develop the Advanced Function Approach which would significantly increase the effectiveness of existing methodological tools. The main parts of the study presented here are: 1. research of the application history and the evolution of Function Analysis, which indicates that the next logical step for enhancing the Function Approach is the introduction of two parameters: “time of performing a function” and “place of performing a function”. 2. Logical deductive substantiation of the need to apply spatio-temporal parameters for formulating functions. 3. Examples of the application of this Advanced Function Approach. It should be mentioned that the recommendations formulated here are practical and may be used by researchers and TRIZ practitioners who have basic knowledge of the function approach.

关键词： Function Parameter Function approach Function analysis Functional disadvantages

来源：评论

学校读者我要写书评

暂无评论

Automated detection of proximal right coronary artery occlusion in ST-elevation myocardial infarction

引用

Journal of Electrocardiology 2011年第6期44卷 744-745页

作者： Richard E. Gregg Miquel Fiol Kjell C. Nikus Andrés Carrillo Simon Cheng-hao Chien James M. Lindauer Victoria Barbara Sophia H. Zhou Advanced Algorithm Research Center Philips Healthcare Thousand Oaks CA Hospital Son Dureta Palma de Mallorca Spain Department of Cardiology Heart Center Tampere University Hospital Tampere Finland Heart Institute Long Beach Memorial Medical Center Long Beach CA

来源：评论

学校读者我要写书评

暂无评论

Electrocardiographic identifying proximal occlusion within left anterior descending coronary artery

引用

Journal of Electrocardiology 2010年第6期43卷 641-642页

作者： Richard E. Gregg Kjell Nikus Leonard S. Gettes Ronald H. Startt/Selvester Victoria Barbara Sophia H. Zhou Advanced Algorithm Research Center Philips Healthcare Thousand Oaks CA Cardiology Department Tampere University Hospital Tampere Finland Cardiology Division University of North Carolina School of Medicine Chapel Hill NC Heart Institute Long Beach Memorial Medical Center Long Beach CA

来源：评论

学校读者我要写书评

暂无评论

Robust AI-Generated Text Detection by Restricted Embeddings

arXiv

引用

arXiv 2024年

作者： Kuznetsov, Kristian Tulchinskii, Eduard Kushnareva, Laida Magai, German Barannikov, Serguei Nikolenko, Sergey Piontkovskaya, Irina AI Foundation and Algorithm Lab Russia HSE University Russia Noeon Research Japan Skolkovo Institute of Science and Technology Russia CNRS Université Paris Cité France ISP RAS Research Center for Trusted Artificial Intelligence Moscow Russia St. Petersburg Department of the Steklov Institute of Mathematics Russia

Growing amount and quality of AI-generated texts makes detecting such content more difficult. In most real-world scenarios, the domain (style and topic) of generated data and the generator model are not known in advance. In this work, we focus on the robustness of classifier-based detectors of AI-generated text, namely their ability to transfer to unseen generators or semantic domains. We investigate the geometry of the embedding space of Transformer-based text encoders and show that clearing out harmful linear subspaces helps to train a robust classifier, ignoring domain-specific spurious features. We investigate several subspace decomposition and feature selection strategies and achieve significant improvements over state of the art methods in cross-domain and cross-generator transfer. Our best approaches for head-wise and coordinate-based subspace removal increase the mean out-of-distribution (OOD) classification score by up to 9% and 14% in particular setups for RoBERTa and BERT embeddings respectively. We release our code and data. © 2024, CC BY.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

An Enhanced Coarse-to-Fine Framework for the Segmentation of Clinical Target Volume 23rd

An Enhanced Coarse-to-Fine Framework for the Segmentation of...

引用

Anatomical Brain Barriers to Cancer Spread: Segmentation from CT and MR Images Challenge, ABCs 2020, Learn2Reg Challenge, L2R 2020 and Thyroid Nodule Segmentation and Classification in Ultrasound Images Challenge, TN-SCUI 2020 held in conjunction with 23rd International Conference on Medical Image Computing and Computer-Assisted Intervention, MICCAI 2020

作者： Chen, Huai Qian, Dahong Liu, Weiping Li, Hui Wang, Lisheng Institute of Image Processing and Pattern Recognition Department of Automation Shanghai Jiao Tong University Shanghai200240 China School of Biomedical Engineering Shanghai Jiao Tong University Shanghai200240 China Department of Algorithm and Research Shanghai Aitrox Technology Co. Ltd. Shanghai China National Key Laboratory of Science and Technology on Nano/Micro Fabrication Key Laboratory for Thin Film and Micro Fabrication of the Ministry of Education Institute of Micro-Nano Science and Technology Shanghai Jiao Tong University Shanghai200240 China

ISBN: (纸本)9783030718268

In radiation therapy, obtaining accurate boundary of the clinical target volume (CTV) is the vital step to decrease the risk of treatment failures. However, it is a time-consuming and laborious task to obtain the delineation by hand. Therefore, an automatic algorithm is urgently needed to realize accurate segmentation. In this paper, we propose an enhanced coarse-to-fine frameworkto automatically fuse the information of CT, T1 and T2 images to get the target region. This framework includes a coarse-segmentation stage to identify the region of interest (ROI) of targets and a fine-segmentation stage to iteratively refine the segmentation. In the coarse-segmentation stage, the F-loss is proposed to keep the high recall rate of the ROI. In the fine segmentation, the ROI of target will be first cropped according to the ROI obtained by coarse-segmentation and be fed into a 3D-Unet to get the initial results. Then, the prediction and medium features will be set as additional information for the next one network to refine the results. When evaluated on the validation dataset of challenge of Anatomical Brain Barriers to Cancer Spread (ABCs), our method won the 3th place in the public leaderboard. © 2021, Springer Nature Switzerland AG.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

RaftGP: Random Fast Graph Partitioning

arXiv

引用

arXiv 2023年

作者： Gao, Yu Qin, Meng Ding, Yibin Zeng, Li Zhang, Chaorui Zhang, Weixi Han, Wei Zhao, Rongqian Bai, Bo Theory Lab Central Research Institute 2012 Labs Huawei Technologies Co. Ltd China Algorithm & Technology Development Department Global Technical Service Department Huawei Technologies Co. Ltd. China Department of Computer Science & Engineering Hong Kong University of Science & Technology Hong Kong

Graph partitioning (GP), a.k.a. community detection, is a classic problem that divides the node set of a graph into densely-connected blocks. Following prior work on the IEEE HPEC Graph Challenge benchmark and recent advances in graph machine learning, we propose a novel RAndom FasT Graph Partitioning (RaftGP) method based on an efficient graph embedding scheme. It uses the Gaussian random projection to extract community-preserving features from classic GP objectives. These features are fed into a graph neural network (GNN) to derive low-dimensional node embeddings. Surprisingly, our experiments demonstrate that a randomly initialized GNN even without training is enough for RaftGP to derive informative community-preserving embeddings and support high-quality GP. To enable the derived embeddings to tackle GP, we introduce a hierarchical model selection algorithm that simultaneously determines the number of blocks and the corresponding GP result. We evaluate RaftGP on the Graph Challenge benchmark and compare the performance with five baselines, where our method can achieve a better trade-off between quality and efficiency. In particular, compared to the baseline algorithm [1] of the IEEE HPEC Graph Challenge, our method is 6.68x – 23.9x faster on graphs with 1E3 – 5E4 nodes and at least 64.5x faster on larger (1E5 node) graphs on which the baseline takes more than 1E4 seconds. Our method achieves better accuracy on all test cases. We also develop a new graph generator to address some limitations of the original generator in the benchmark. Copyright © 2023, The Authors. All rights reserved.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

An automated algorithm to improve ECG detection of posterior STEMI associated with left circumflex coronary artery occlusion

An automated algorithm to improve ECG detection of posterior...

引用

Computers in Cardiology (CinC)

作者： S. H. Zhou R. H. Startt/Selvester X. Liu E. W. Hancock E. Tragardh O. Pahlm B. M. Horacek R. E. Gregg E. D. Helfenbein J. M. Lindauer FACC Advanced Algorithm Research Center Thousand Oaks CA Philips Medical Systems Advanced Algorithm Research Center Thousand Oaks CA USA Division of Cardiology Long Beach Memorial Medical Center Long Beach CA USA Division of Cardiology Rui-Jin Hospital Shanghai Jiao-Tong University Shanghai China Division of Cardiology University of Stanford Palo Alto USA Division of Cardiology Stanford University Palo Alto USA Department of Clinical Physiology Lund University Hospital Lund Sweden Department of Physiology and Biophysics Dalhousie University Halifax Canada

ISBN: (纸本)9781424425327

The under-recognition, underestimate of area at risk, and under-treatment of ST elevation posterior myocardial infarct in patients with acute coronary syndrome are often due to the insensitive standard 12-lead electrocardiographic diagnosis and bias toward "anterior subendocardial ischemia". We designed a new computer algorithm to improve ECG detection of isolated and combined posterior myocardial infarct using extended posterior leads V7, V8 and V9. ECG criteria for PMI include "age" (acute, recent, age indeterminate or old) and "probability" (consider, probable or definite) infarct. Combining the subjects with posterior myocardial infarct (n=182), we obtained an increase of 26 percentage points in sensitivity of posterior myocardial infarction detection from 14% using standard 12-leads to 40% including posterior leads with a small drop in specificity from 98% to 96.4%. The highest increase was seen in a subset of subjects having undergone for PTC A procedure from 21% to 86% (65 percentage points). We conclude the automated posterior myocardial infarct detection algorithm provides another valuable tool for diagnosis of ST elevation posterior myocardial infarct. Posterior leads V7, V8 and V9 can capture ECG changes due to isolated ST elevation PMI or acute myocardial infarct with posterior wall involvement and provide improved sensitivity in posterior myocardial infarct detection.

关键词： Electrocardiography Arterial occlusion Myocardium Hospitals Cardiology Ischemic pain Medical diagnostic imaging Physiology Automatic testing Biophysics

来源：评论

学校读者我要写书评

暂无评论

AI-generated text boundary detection with RoFT

arXiv

引用

arXiv 2023年

作者： Kushnareva, Laida Gaintseva, Tatiana Magai, German Barannikov, Serguei Abulkhanov, Dmitry Kuznetsov, Kristian Tulchinskii, Eduard Piontkovskaya, Irina Nikolenko, Sergey AI Foundation and Algorithm Lab Russia Digital Environment Research Institute Queen Mary University of London United Kingdom HSE University Russia Noeon Research Japan Skolkovo Institute of Science and Technology Russia CNRS Université Paris Cité France St. Petersburg Department The Steklov Institute of Mathematics Russia

Due to the rapid development of large language models, people increasingly often encounter texts that may start as written by a human but continue as machine-generated. Detecting the boundary between human-written and machine-generated parts of such texts is a challenging problem that has not received much attention in literature. We attempt to bridge this gap and examine several ways to adapt state of the art artificial text detection classifiers to the boundary detection setting. We push all detectors to their limits, using the Real or Fake text benchmark that contains short texts on several topics and includes generations of various language models. We use this diversity to deeply examine the robustness of all detectors in cross-domain and cross-model settings to provide baselines and insights for future research. In particular, we find that perplexity-based approaches to boundary detection tend to be more robust to peculiarities of domain-specific data than supervised fine-tuning of the RoBERTa model;we also find which features of the text confuse boundary detection algorithms and negatively influence their performance in cross-domain settings. © 2023, CC BY.

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：