检索结果-内蒙古大学图书馆

arXiv 2020年

作者： Qi, Chang Chen, Junyang Xu, Guizhi Xu, Zhenghua Lukasiewicz, Thomas Liu, Yang State Key Laboratory of Reliability and Intelligence of Electrical Equipment Hebei University of Technology China Tianjin Key Laboratory of Bioelectromagnetic Technology and Intelligent Health Hebei University of Technology China Department of Computer Science University of Macau China Department of Computer Science University of Oxford United Kingdom College of Computer Science and Technology Harbin Institute of Technology China

Recently deep learning methods, in particular, convolutional neural networks (CNNs), have led a massive breakthrough in the range of computer vision. Also, the large-scale annotated dataset is the essential key to a successful training procedure. However, it is a huge challenge getting such datasets in the medical domain. Towards this, we present a data augmentation method for generating synthetic medical images using cycle-consistency Generative Adversarial Networks (GANs). We add semi-supervised attention modules to generate images with convincing details. We treat tumor images and normal images as two domains. The proposed GANs-based model can generate a tumor image from a normal image, and in turn, it can also generate a normal image from a tumor image. Furthermore, we show that generated medical images can be used for improving the performance of ResNet18 for medical image classification. Our model is applied to three limited datasets of tumor MRI images. We first generate MRI images on limited datasets, then we trained three popular classification models to get the best model for tumor classification. Finally, we train the classification model using real images with classic data augmentation methods and classification models using synthetic images. The classification results between those trained models showed that the proposed SAG-GAN data augmentation method can boost Accuracy and AUC compare with classic data augmentation methods. We believe the proposed data augmentation method can apply to other medical image domains, and improve the accuracy of computer-assisted diagnosis. Copyright © 2020, The Authors. All rights reserved.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Artificial intelligence-based methods for renewable power system operation

Nature Reviews Electrical Engineering

引用

Nature Reviews Electrical Engineering 2024年第3期1卷 163-179页

作者： Yuanzheng Li Fei Hu Juntao Duan Yong Zhao Zhigang Zeng Yizhou Ding Shangyang He Guanghui Wen Hua Geng Zhengguang Wu Hoay Beng Gooi Chenghui Zhang Shengwei Mei Key Laboratory of lmage Information Processing and Intelligent Control of Ministry of Education of China School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China National Key Laboratory of Multispectral Information Intelligent Processing Technology Huazhong University of Science and Technology Wuhan China China-EU Institute for Clean and Renewable Energy Huazhong University of Science and Technology Wuhan China Department of Systems Science School of Mathematics Southeast University Nanjing China Department of Automation Tsinghua University Beijing China State Key Laboratory of Industrial Control Technology Institute of Cyber-Systems and Control Zhejiang University Hangzhou China School of Electrical and Electronics Engineering Nanyang Technological University Singapore Singapore School of Control Science and Engineering Shandong University Jinan China Department of Electrical Engineering Tsinghua University Beijing China

Carbon neutrality goals are driving the increased use of renewable energy (RE). Large-scale use of RE requires accurate energy generation forecasts; optimized power dispatch, which minimizes costs while satisfying operational constraints; effective system control to ensure a stable power supply; and electricity markets that support bidding and trading decisions associated with RE. However, the uncertainties in RE generation make renewable power systems challenging to operate. For example, the intermittent nature of wind power can make it difficult to balance the supply and demand of electricity in real time; therefore, traditional power sources could be needed to meet the demand, which can increase electricity prices. This Review outlines the potential of artificial intelligence-based methods for supporting renewable power system operation. We discuss the ability of machine learning, deep learning and reinforcement learning methods to facilitate power system forecasts, dispatch, control and markets to support the use of RE. We also emphasize the applicability of these techniques to different operational problems. Finally, we discuss potential trends in renewable power system development and approaches to address the associated operational challenges such as the increasingly distributed nature of RE installations, diversification of energy storage systems and growing market complexity.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Deep Forest with Hashing Screening and Window Screening

arXiv

引用

arXiv 2022年

作者： Ma, Pengfei Wu, Youxi Li, Yan Guo, Lei Jiang, He Zhu, Xingquan Wu, Xindong School of Artificial Intelligence Hebei University of Technology Tianjing300401 China Hebei Key Laboratory of Big Data Computing Tianjing300401 China School of Economics and Management Hebei University of Technology Tianjing300401 China State Key Laboratory of Reliability and Intelligence of Electrical Equipment Hebei University of Technology Tianjing300401 China School of Software Dalian University of Technology Dalian116023 China Department of Computer & Electrical Engineering and Computer Science Florida Atlantic University FL33431 United States Hefei University of Technology Hefei230009 China Mininglamp Academy of Sciences Mininglamp Technology Beijing100084 China

As a novel deep learning model, gcForest has been widely used in various applications. However, the current multi-grained scanning of gcForest produces many redundant feature vectors, and this increases the time cost of the model. To screen out redundant feature vectors, we introduce a hashing screening mechanism for multi-grained scanning and propose a model called HW-Forest which adopts two strategies, hashing screening and window screening. HW-Forest employs perceptual hashing algorithm to calculate the similarity between feature vectors in hashing screening strategy, which is used to remove the redundant feature vectors produced by multi-grained scanning and can significantly decrease the time cost and memory consumption. Furthermore, we adopt a self-adaptive instance screening strategy to improve the performance of our approach, called window screening, which can achieve higher accuracy without hyperparameter tuning on different datasets. Our experimental results show that HW-Forest has higher accuracy than other models, and the time cost is also reduced. Copyright © 2022, The Authors. All rights reserved.

关键词： Scanning

来源：评论

学校读者我要写书评

暂无评论

Discovering new intents with deep aligned clustering

arXiv

引用

arXiv 2020年

作者： Zhang, Hanlei Xu, Hua Lin, Ting-En Lyu, Rui State Key Laboratory of Intelligent Technology and Systems Department of Computer Science and Technology Tsinghua University Beijing100084 China Beijing100084 China Beijing University of Posts Telecommunications University Beijing100876 China

Discovering new intents is a crucial task in dialogue systems. Most existing methods are limited in transferring the prior knowledge from known intents to new intents. They also have difficulties in providing high-quality supervised signals to learn clustering-friendly features for grouping unlabeled intents. In this work, we propose an effective method, Deep Aligned Clustering, to discover new intents with the aid of the limited known intent data. Firstly, we leverage a few labeled known intent samples as prior knowledge to pre-train the model. Then, we perform k-means to produce cluster assignments as pseudo-labels. Moreover, we propose an alignment strategy to tackle the label inconsistency problem during clustering assignments. Finally, we learn the intent representations under the supervision of the aligned pseudo-labels. With an unknown number of new intents, we predict the number of intent categories by eliminating low-confidence intent-wise clusters. Extensive experiments on two benchmark datasets show that our method is more robust and achieves substantial improvements over the state-of-the-art methods. The codes are released at https://***/thuiar/DeepAligned-Clustering. Copyright © 2020, 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

Mechanical Structure and Control Methods for Lower-Limb Rehabilitation Robots

Mechanical Structure and Control Methods for Lower-Limb Reha...

引用

第40届中国控制会议

作者： Wangyang Ge Ruoyu Jiang Juan Zhao Zhentao Liu Zhaohui Yang Jinhua She School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education Department of Rehabilitation Union HospitalTongji Medical CollegeHuazhong Univ.Science & Technology School of Engineering Tokyo University of Technology

As a rehabilitation aid,lower-limb rehabilitation robots help patients recover their walking *** paper presets a review of such a rehabilitation ***,we classify commercially available common types of lower-limb rehabilitation ***,we briefly describe the structure and characteristics of those robots,Then,we present the control methods used in those ***,we explain future research directions.

关键词： rehabilitation robots mechanical structure control method biological signal

来源：评论

学校读者我要写书评

暂无评论

Non-destructive Degradation Pattern Decoupling for Ultra-early Battery Prototype Verification Using Physics-informed Machine Learning

arXiv

引用

arXiv 2024年

作者： Tao, Shengyu Zhang, Mengtian Zhao, Zixi Li, Haoyang Ma, Ruifei Che, Yunhong Sun, Xin Su, Lin Chen, Xiangyu Zhou, Zihao Chang, Heng Cao, Tingwei Xiao, Xiao Liu, Yaojun Yu, Wenjun Xu, Zhongling Li, Yang Hao, Han Zhang, Xuan Hu, Xiaosong Zhou, Guangmin Tsinghua-Berkeley Shenzhen Institute Tsinghua Shenzhen International Graduate School Tsinghua University Shenzhen China State Key Laboratory of Intelligent Green Vehicle and Mobility Tsinghua University Beijing China Department of Energy Aalborg University Aalborg Denmark University of Groningen Groningen Netherlands Department of Engineering Science University of Oxford OxfordOX1 3PJ United Kingdom Sunwoda Mobility Energy Technology Co. Ltd. Shenzhen China College of Mechanical and Vehicle Engineering Chongqing University Chongqing China

Manufacturing complexities and uncertainties have impeded the transition from material prototypes to commercial batteries, making prototype verification critical to quality assessment. A fundamental challenge involves deciphering intertwined chemical processes to characterize degradation patterns and their quantitative relationship with battery performance. Here we show that a physics-informed machine learning approach can quantify and visualize temporally resolved losses concerning thermodynamics and kinetics only using electric signals. Our method enables non-destructive degradation pattern characterization, expediting temperature-adaptable predictions of entire lifetime trajectories, rather than end-of-life points. The verification speed is 25 times faster yet maintaining 95.1% accuracy across temperatures. Such advances facilitate more sustainable management of defective prototypes before massive production, establishing a 19.76 billion USD scrap material recycling market by 2060 in China. By incorporating stepwise charge acceptance as a measure of the initial manufacturing variability of normally identical batteries, we can immediately identify long-term degradation variations. We attribute the predictive power to interpreting machine learning insights using material-agnostic featurization taxonomy for degradation pattern decoupling. Our findings offer new possibilities for dynamic system analysis, such as battery prototype degradation, demonstrating that complex pattern evolutions can be accurately predicted in a non-destructive and data-driven fashion by integrating physics-informed machine learning. Copyright © 2024, The Authors. All rights reserved.

关键词： Electric losses

来源：评论

学校读者我要写书评

暂无评论

Synergistic integration of metaheuristics and machine learning: latest advances and emerging trends

引用

Artificial Intelligence Review 2025年第9期58卷

作者： Zhang, Ruining Wang, Jian Liu, Chanjuan Su, Kaile Ishibuchi, Hisao Jin, Yaochu School of Computer Science and Technology Dalian University of Technology Dalian116024 China Qingdao266580 China School of Information and Communication Technology Griffith University Brisbane4111 Australia Guangdong Provincial Key Laboratory of Brain-Inspired Intelligent Computation Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen518055 China School of Engineering Westlake University Hangzhou310024 China

Metaheuristic algorithms (MH) and machine learning (ML) are important components of artificial intelligence (AI). The synergy between MH’s optimization search capabilities and ML’s data analysis strengths has proven to be highly effective, providing a powerful combination for delivering high-quality solutions across diverse fields. Particularly in real-world applications such as autonomous driving and healthcare, the integration of MH and ML can significantly enhance the intelligence level and decision-making efficiency of systems, addressing the urgent societal and industrial demands for high-efficiency and high-precision solutions. This paper clarifies the logic behind the surge in research on MH-ML hybrid algorithms and addresses the gaps in current reviews regarding their timeliness and breadth of perspective. We begin by elucidating the fundamental concepts underpinning MH and ML, followed by a comprehensive classification framework that categorizes and synthesizes the latest research findings systematically. The paper concludes with an exploration of the challenges inherent in MH-ML hybrid algorithms and proposes future research directions. The analysis of the collected literature demonstrates that the integration of MH and ML generally enhances the performance of algorithms in specific problems. Despite progress from simple combinations to deeper integrations, challenges such as theoretical lag and interpretability remain. Future research will focus on solving these challenges by exploring further integration, using open-source tools, and adapting across diverse domains to expand the use of MH-ML hybrid algorithms. © The Author(s) 2025.

关键词： Supervised learning

来源：评论

学校读者我要写书评

暂无评论

TR-BERT: Dynamic token reduction for accelerating BERT inference

arXiv

引用

arXiv 2021年

作者： Ye, Deming Lin, Yankai Huang, Yufei Sun, Maosong Department of Computer Science and Technology Tsinghua University Beijing China Institute for Artificial Intelligence Tsinghua University Beijing China Beijing National Research Center for Information Science and Technology China State Key Lab on Intelligent Technology and Systems Tsinghua University Beijing China Beijing Academy of Artificial Intelligence China Pattern Recognition Center WeChat AI Tencent Inc

Existing pre-trained language models (PLMs) are often computationally expensive in inference, making them impractical in various resource-limited real-world applications. To address this issue, we propose a dynamic token reduction approach to accelerate PLMs' inference, named TR-BERT, which could flexibly adapt the layer number of each token in inference to avoid redundant calculation. Specially, TR-BERT formulates the token reduction process as a multi-step token selection problem and automatically learns the selection strategy via reinforcement learning. The experimental results on several downstream NLP tasks show that TR-BERT is able to speed up BERT by 2-5 times to satisfy various performance demands. Moreover, TR-BERT can also achieve better performance with less computation in a suite of long-text tasks since its token-level layer number adaption greatly accelerates the self-attention operation in PLMs. The source code and experiment details of this paper can be obtained from https://***/thunlp/TR-BERT. Copyright © 2021, 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

Synthesis of Abiotic Supramolecular Polymers Inside Living Cells via Organocatalysis-Mediated Self-Assembly

引用

Angewandte Chemie 2025年

作者： Hucheng Wang Ya-Ting Zheng Jiahao Zhang Yuliang Gao Jingjing Chen Peiwen Cai Junyou Wang Jan H. van Esch Xuhong Guo Hui Li Yiming Wang State Key Laboratory of Chemical Engineering School of Chemical Engineering East China University of Science and Technology Shanghai 200237 P.R. China School of Systems Science and Institute of Nonequilibrium Systems Beijing Normal University Beijing 100875 P.R. China Department of Chemical Engineering Delft University of Technology Delft 2629 HZ The Netherlands Key Laboratory of Cell Proliferation and Regulation Biology Ministry of Education Beijing Normal University Beijing 100875 P.R. China Shanghai Key Laboratory for Intelligent Sensing and Detection Technology East China University of Science and Technology Shanghai 200237 P.R. China

Cells execute mesmerizing functions using supramolecular polymers (SPs) formed through the self-assembly of biological precursors. Integration of the vast array of synthetic SPs with living cells would offer a powerful way to remold cellular functions and bridge the gap between synthetic materials and the biological realm, yet remains a challenge because of the lack of robust abiotic SP systems that can be triggered to self-assemble inside cells. Here, we report how fully abiotic SPs can be synthesized inside living cells via an organocatalysis-responsive self-assembly strategy, and how the in situ-generated SPs are capable of interfering and can interfere with cellular functions. The incorporation of a nucleophilic organocatalyst ( CAT ) into living cells accelerates the intracellular conversion of hydrazide ( H ) and aldehyde-derived precursors ( A ) to hydrazone-based monomers ( HA 3 ) that locally self-assemble into SPs. Interestingly, the in situ-generated SPs possess ignorable effects on cell viability and proliferation but remarkably hinder cell migration. Furthermore, the presence of SPs is found to retard intracellular diffusion and alter the organization of the actin cytoskeleton, both of which are suggested to be responsible for the hindered cellular migration. In considering the vastly wide range of synthetic SPs, tremendous non-natural cellular functionalities can be obtained by in situ-synthesizing SPs.

关键词： Gelation Intracellular self-assembly Local catalysis Supramolecular polymers

来源：评论

学校读者我要写书评

暂无评论

Learning with Group Noise

arXiv

引用

arXiv 2021年

作者： Wang, Qizhou Yao, Jiangchao Gong, Chen Liu, Tongliang Gong, Mingming Yang, Hongxia Han, Bo Department of Computer Science Hong Kong Baptist University Hong Kong Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information of MoE School of Computer Science and Engineering Nanjing University of Science and Technology China Data Analytics and Intelligence Lab Alibaba Group China Department of Computing Hong Kong Polytechnic University Hong Kong Trustworthy Machine Learning Lab School of Computer Science University of Sydney Australia School of Mathematics and Statistics University of Melbourne Australia

Machine learning in the context of noise is a challenging but practical setting to plenty of real-world applications. Most of the previous approaches in this area focus on the pairwise relation (casual or correlational relationship) with noise, such as learning with noisy labels. However, the group noise, which is parasitic on the coarse-grained accurate relation with the fine-grained uncertainty, is also universal and has not been well investigated. The challenge under this setting is how to discover true pairwise connections concealed by the group relation with its fine-grained noise. To overcome this issue, we propose a novel Max-Matching method for learning with group noise. Specifically, it utilizes a matching mechanism to evaluate the relation confidence of each object (cf. Figure 1) w.r.t. the target, meanwhile considering the Non-IID characteristics among objects in the group. Only the most confident object is considered to learn the model, so that the fine-grained noise is mostly dropped. The performance on a range of real-world datasets in the area of several learning paradigms demonstrates the effectiveness of Max-Matching. Copyright © 2021, 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

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：