检索结果-内蒙古大学图书馆

IET International Radar Conference (IRC 2023)

作者： Xinyu Wang Jin Zhao Xianliang Wu Key Lab of Intelligent Computing & Signal Processing Ministry of Education Anhui University Hefei People's Republic of China

ISBN: (数字)9781837240982

Aiming at the traditional blind source separation for the received single-channel mixed radar signal makes it difficult to accurately recover the source signal, a single-channel radar signal comprehensive separation method based on the combination of the FastICA algorithm and the variational modal decomposition (VMD) algorithm is proposed. The method utilizes VMD to first perform modal separation of single-channel mixed Linear Frequency Modulation (LFM) signal, then selects the modal component signal with the largest correlation coefficient with the mixed signal and expands it with single-channel mixed LFM signal into a virtual multi-channel mixed signal, and finally inputs it into FastICA algorithm to obtain the source signal. The simulation experiment results show that the comprehensive separation algorithm can accurately separate the LFM signal, overcoming the limitation that the FastICA algorithm cannot directly separate the single-channel mixed radar signal.

关键词：

来源：评论

学校读者我要写书评

暂无评论

What matters in graph class incremental learning? an information preservation perspective 24

What matters in graph class incremental learning? an informa...

引用

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

作者： Jialu Li Yu Wang Pengfei Zhu Wanyu Lin Qinghua Hu College of Intelligence and Computing Tianjin University Tianjin China and Engineering Research Center of City Intelligence and Digital Governance Ministry of Education of the People's Republic of China Tianjin China and Haihe Lab of ITAI Tianjin China Department of Computing The Hong Kong Polytechnic University Hong Kong China

ISBN: (纸本)9798331314385

Graph class incremental learning (GCIL) requires the model to classify emerging nodes of new classes while remembering old classes. Existing methods are designed to preserve effective information of old models or graph data to alleviate forgetting, but there is no clear theoretical understanding of what matters in information preservation. In this paper, we consider that present practice suffers from high semantic and structural shifts assessed by two devised shift metrics. We provide insights into information preservation in GCIL and find that maintaining graph information can preserve information of old models in theory to calibrate node semantic and graph structure shifts. We correspond graph information into low-frequency local-global information and high-frequency information in spatial domain. Based on the analysis, we propose a framework, Graph Spatial Information Preservation (GSIP). Specifically, for low-frequency information preservation, the old node representations obtained by inputting replayed nodes into the old model are aligned with the outputs of the node and its neighbors in the new model, and then old and new outputs are globally matched after pooling. For high-frequency information preservation, the new node representations are encouraged to imitate the near-neighbor pair similarity of old node representations. GSIP achieves a 10% increase in terms of the forgetting metric compared to prior methods on large-scale datasets. Our framework can also seamlessly integrate existing replay designs. The code is available through https://***/Jillian555/GSIP.

关键词：

来源：评论

学校读者我要写书评

暂无评论

All Muscle Activity Test and Evaluation (AMATE): An analytical tool to assess lower limb muscle activation for stroke patients

All Muscle Activity Test and Evaluation (AMATE): An analytic...

引用

Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)

作者： Xiyan Xiong Nan Gao Qing Zhang Xiao Ma Pavel Smirnov Duchun Zeng Junxiao Xue Chun Yang Feng Lin Research Center for Frontier Fundamental Studies Zhejiang Lab Hangzhou China School of Aerospace Engineering Tsinghua University Beijing China Research Center for Astronomical Computing Zhejiang Lab Hangzhou China Department of Physical Medicine and Rehabilitation Zhejiang Provincial People’s Hospital Hangzhou China Research Center for Space Computing System Zhejiang Lab Hangzhou China

ISBN: (数字)9798350371499

ISBN: (纸本)9798350371505

Assessing muscle activation and monitoring stroke recovery progress are vital aspects of evaluating motor impairment. Surface electromyography, a common tool for measuring muscle activity, has practical limitations for clinical implementation and fails to capture deep muscle activities, leading to challenges in accurately identifying muscle activation patterns in stroke patients. To address these limitations, we introduce an All Muscle Activity Test and Evaluation (AMATE) system, combining wearable sensor technology with a musculoskeletal model. AMATE computes activation levels of all lower limb muscles during various activities without requiring surface electrodes. It also generates an Activation Dissimilarity Index (ADI) to illustrate muscle activation patterns among individuals. We evaluated AMATE’s effectiveness through a pilot study involving 22 walking trials with healthy subjects and stroke patients. The results highlight AMATE’s capability in aiding clinicians to analyze and understand diverse lower limb muscle activation patterns in stroke patients, particularly identifying muscles with abnormal activation for targeted rehabilitative training.

关键词： Training Legged locomotion Muscles Stroke (medical condition) Motors Electromyography Indexes Engineering in medicine and biology Wearable sensors Monitoring

来源：评论

学校读者我要写书评

暂无评论

CR-GIS: Improving Conversational Recommendation via Goal-aware Interest Sequence Modeling 29

CR-GIS: Improving Conversational Recommendation via Goal-awa...

引用

29th International Conference on Computational Linguistics, COLING 2022

作者： Zhou, Jinfeng Wang, Bo Yang, Zhitong Zhao, Dongming Huang, Kun He, Ruifang Hou, Yuexian College of Intelligence and Computing Tianjin University Tianjin China State Key Laboratory of Communication Content Cognition China People’s Daily Online Beijing China AI Lab China Mobile Communication Group Tianjin Co. Ltd. China

Conversational recommendation systems (CRS) aim to determine a goal item by sequentially tracking users’ interests through multi-turn conversation. In CRS, implicit patterns of user interest sequence guide the smooth transition of dialog utterances to the goal item. However, with the convenient explicit knowledge of knowledge graph (KG), existing KG-based CRS methods over-rely on the explicit separate KG links to model the user interests but ignore the rich goal-aware implicit interest sequence patterns in a dialog. In addition, interest sequence is also not fully used to generate smooth transited utterances. We propose CR-GIS with a parallel star framework. First, an interest-level star graph is designed to model the goal-aware implicit user interest sequence. Second, a hierarchical Star Transformer is designed to guide the multi-turn utterances generation with the interest-level star graph. Extensive experiments verify the effectiveness of CR-GIS in achieving more accurate recommended items with more fluent and coherent dialog utterances. © 2022 Proceedings - International Conference on Computational Linguistics, COLING. All rights reserved.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Socialized learning: making each other better through multi-agent collaboration 24

Socialized learning: making each other better through multi-...

引用

Proceedings of the 41st International Conference on Machine Learning

作者： Xinjie Yao Yu Wang Pengfei Zhu Wanyu Lin Jialu Li Weihao Li Qinghua Hu College of Intelligence and Computing Tianjin University Tianjin China and Engineering Research Center of City Intelligence and Digital Governance Ministry of Education of the People's Republic of China Tianjin China and Haihe Lab of ITAI Tianjin China Department of Computing The Hong Kong Polytechnic University Hong Kong China Department of Computer Science Boston University Boston

Learning new knowledge frequently occurs in our dynamically changing world, e.g., humans culturally evolve by continuously acquiring new abilities to sustain their survival, leveraging collective intelligence rather than a large number of individual attempts. The effective learning paradigm during cultural evolution is termed socialized learning (SL). Consequently, a straightforward question arises: Can multi-agent systems acquire more new abilities like humans? In contrast to most existing methods that address continual learning and multi-agent collaboration, our emphasis lies in a more challenging problem: We prioritize the knowledge in the original expert classes, and as we adeptly learn new ones, the accuracy in the original expert classes stays superior among all in a directional manner. Inspired by population genetics and cognitive science, leading to unique and complete development, we propose Multi-Agent Socialized Collaboration (MASC), which achieves SL through interactions among multiple agents. Specifically, we introduce collective collaboration and reciprocal altruism modules, organizing collaborative behaviors, promoting information sharing, and facilitating learning and knowledge interaction among individuals. We demonstrate the effectiveness of multi-agent collaboration in an extensive empirical study. Our code will be publicly available at https://***/yxjdarren/SL.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Novel Lesion Segmentation Algorithm based on U-Net Network for Tuberculosis CT Image 10

A Novel Lesion Segmentation Algorithm based on U-Net Network...

引用

10th International Conference on Control, Automation and Information Sciences, ICCAIS 2021

作者： Wen, Shaoyue Liu, Jing Xu, Wenge Xi'an Jiaotong-Liverpool University Department of Computing Suzhou China The Fifth People's Hospital of Suzhou Department of Radiology Suzhou China Birmingham City University DMT Lab Birmingham United Kingdom

ISBN: (纸本)9781665440295

Lung CT images provide several essential information for lung disease diagnosis and lung surgery. However, the traditional detection method through manual segmentation is laborious and time-consuming. This paper presents automatic tuberculosis (TB) lesion segmentation method based on U-Net neural network for detecting TB. In addition, we combined an edge detection algorithm called canny edge detector with this network to get a more accurate TB lesion boundary. This method is trained on two split databases with 3576 lung CT images obtained by data enhancement on 447 discontinuous lung CT images. The results show that the proposed approach is validated for complex TB lesions with a high dice coefficient (91.2%). © 2021 IEEE.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

TopKG: Target-oriented Dialog via Global Planning on Knowledge Graph 29

TopKG: Target-oriented Dialog via Global Planning on Knowled...

引用

29th International Conference on Computational Linguistics, COLING 2022

作者： Yang, Zhitong Wang, Bo Zhou, Jinfeng Tan, Yue Zhao, Dongming Huang, Kun He, Ruifang Hou, Yuexian State Key Laboratory of Communication Content Cognition People’s Daily Online Beijing China College of Intelligence and Computing Tianjin University Tianjin China School of New Media and Communication Tianjin University Tianjin China AI Lab China Mobile Communication Group Tianjin Co. Ltd. China

Target-oriented dialog aims to reach a global target through multi-turn conversation. The key to the task is the global planning towards the target, which flexibly guides the dialog concerning the context. However, existing target-oriented dialog works take a local and greedy strategy for response generation, where global planning is absent. In this work, we propose global planning for target-oriented dialog on a commonsense knowledge graph (KG). We design a global reinforcement learning with the planned paths to flexibly adjust the local response generation model towards the global target. We also propose a KG-based method to collect target-oriented samples automatically from the chit-chat corpus for model training. Experiments show that our method can reach the target with a higher success rate, fewer turns, and more coherent responses. © 2022 Proceedings - International Conference on Computational Linguistics, COLING. All rights reserved.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Cluster-Induced Mask Transformers for Effective Opportunistic Gastric Cancer Screening on Non-contrast CT Scans

arXiv

引用

arXiv 2023年

作者： Yuan, Mingze Xia, Yingda Chen, Xin Yao, Jiawen Wang, Junli Qiu, Mingyan Dong, Hexin Zhou, Jingren Dong, Bin Lu, Le Zhang, Li Liu, Zaiyi Zhang, Ling DAMO Academy Alibaba Group China Peking University China Hupan Lab Hangzhou310023 China Guangdong Province People’s Hospital China The First Affiliated Hospital of Zhejiang University China Peking University Changsha Institute for Computing and Digital Economy China

Gastric cancer is the third leading cause of cancer-related mortality worldwide, but no guideline-recommended screening test exists. Existing methods can be invasive, expensive, and lack sensitivity to identify early-stage gastric cancer. In this study, we explore the feasibility of using a deep learning approach on non-contrast CT scans for gastric cancer detection. We propose a novel cluster-induced Mask Transformer that jointly segments the tumor and classifies abnormality in a multitask manner. Our model incorporates learnable clusters that encode the texture and shape prototypes of gastric cancer, utilizing self- and cross-attention to interact with convolutional features. In our experiments, the proposed method achieves a sensitivity of 85.0% and specificity of 92.6% for detecting gastric tumors on a hold-out test set consisting of 100 patients with cancer and 148 normal. In comparison, two radiologists have an average sensitivity of 73.5% and specificity of 84.3%. We also obtain a specificity of 97.7% on an external test set with 903 normal cases. Our approach performs comparably to established state-of-the-art gastric cancer screening tools like blood testing and endoscopy, while also being more sensitive in detecting early-stage cancer. This demonstrates the potential of our approach as a novel, non-invasive, low-cost, and accurate method for opportunistic gastric cancer screening. Copyright © 2023, The Authors. All rights reserved.

关键词： Computerized tomography

来源：评论

学校读者我要写书评

暂无评论

Aligning Recommendation and Conversation via Dual Imitation

Aligning Recommendation and Conversation via Dual Imitation

引用

2022 Conference on Empirical Methods in Natural Language Processing, EMNLP 2022

作者： Zhou, Jinfeng Wang, Bo Huang, Minlie Zhao, Dongming Huang, Kun He, Ruifang Hou, Yuexian College of Intelligence and Computing Tianjin University Tianjin China State Key Laboratory of Communication Content Cognition People's Daily Online Beijing China The CoAI Group DCST Institute for Artificial Intelligence State Key Lab of Intelligent Technology and Systems China Beijing National Research Center for Information Science and Technology Tsinghua University Beijing100084 China AI Lab China Mobile Communication Group Tianjin Co. Ltd. China

Human conversations of recommendation naturally involve the shift of interests which can align the recommendation actions and conversation process to make accurate recommendations with rich explanations. However, existing conversational recommendation systems (CRS) ignore the advantage of user interest shift in connecting recommendation and conversation, which leads to an ineffective loose coupling structure of CRS. To address this issue, by modeling the recommendation actions as recommendation paths in a knowledge graph (KG), we propose DICR (Dual Imitation for Conversational Recommendation), which designs a dual imitation to explicitly align the recommendation paths and user interest shift paths in a recommendation module and a conversation module, respectively. By exchanging alignment signals, DICR achieves bidirectional promotion between recommendation and conversation modules and generates high-quality responses with accurate recommendations and coherent explanations. Experiments demonstrate that DICR outperforms the state-of-the-art models on recommendation and conversation performance with automatic, human, and novel explainability metrics. © 2022 Association for Computational Linguistics.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Establishing Rigorous and Cost-effective Clinical Trials for Artificial Intelligence Models

arXiv

引用

arXiv 2024年

作者： Gao, Wanling Huang, Yunyou Cui, Dandan Yu, Zhuoming Liu, Wenjing Liang, Xiaoshuang Zhao, Jiahui Xie, Jiyue Li, Hao Ma, Li Ye, Ning Kang, Yumiao Luo, Dingfeng Pan, Peng Huang, Wei Liu, Zhongmou Hu, Jizhong Zhao, Gangyuan Jiang, Chongrong Huang, Fan Wei, Tianyi Tang, Suqin Xia, Bingjie Zhang, Zhifei Zhan, Jianfeng Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China Guangxi Key Lab of Multi-Source Information Mining and Security Guangxi Normal University Guilin541004 China International Open Benchmark Council China University of Chinese Academy of Sciences Beijing100086 China Guilin Medical University Guilin541100 China Affiliated Hospital of Guilin Medical University Guilin541000 China XuanJi Technology Co. Ltd. Guilin541000 China Xing An County People’s Hospital Guilin541300 China Meng Shan County People’s Hospital Wuzhou543000 China Guilin People’s Hospital Guilin541000 China Yong Fu County People’s Hospital Guilin541000 China Ling Chuan County People’s Hospital Guilin541000 China Quan Zhou County People’s Hospital Guilin541000 China Guan Yang County People’s Hospital Guilin541000 China The Second Affiliated Hospital of Guilin Medical University Guilin541000 China International College Guangxi University Nanning530004 China Capital Medical University Beijing100069 China Key Lab of Education Blockchain and Intelligent Technology Ministry of Education Guangxi Normal University Guilin541004 China

A profound gap persists between artificial intelligence (AI) and clinical practice in medicine, primarily due to the lack of rigorous and cost-effective evaluation methodologies. State-of-the-art and state-of-the-practice AI model evaluations are limited to laboratory studies on medical datasets or direct clinical trials with no or solely patient-centered controls. Moreover, the crucial role of clinicians in collaborating with AI, pivotal for determining its impact on clinical practice, is often overlooked. For the first time, we emphasize the critical necessity for rigorous and cost-effective evaluation methodologies for AI models in clinical practice, featuring patient/clinician-centered (dual-centered) AI randomized controlled trials (DC-AI RCTs) and virtual clinician-based in-silico trials (VC-MedAI) as an effective proxy for DC-AI RCTs. Leveraging 7500 diagnosis records from two-phase inaugural DC-AI RCTs across 14 medical centers with 125 clinicians, our results demonstrate the necessity of DC-AI RCTs and the effectiveness of VC-MedAI. Notably, VC-MedAI performs comparably to human clinicians, replicating insights and conclusions from prospective DC-AI RCTs. We envision DC-AI RCTs and VC-MedAI as pivotal advancements, presenting innovative and transformative evaluation methodologies for AI models in clinical practice, offering a preclinical-like setting mirroring conventional medicine, and reshaping development paradigms in a cost-effective and fast-iterative manner. Chinese Clinical Trial Registration: ChiCTR2400086816. © 2024, CC BY-NC-ND.

关键词： Artificial intelligence

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：