检索结果-内蒙古大学图书馆

International Conference on computer Vision (ICCV)

作者： Xiao-Ming Wu Dian Zheng Zuhao Liu Wei-Shi Zheng School of Computer Science and Engineering Sun Yat-sen University China Pengcheng Lab China Guangdong Province Key Laboratory of Information Security Technology China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China

Binarization of neural networks is a dominant paradigm in neural networks compression. The pioneering work BinaryConnect uses Straight Through Estimator (STE) to mimic the gradients of the sign function, but it also causes the crucial inconsistency problem. Most of the previous methods design different estimators instead of STE to mitigate it. However, they ignore the fact that when reducing the estimating error, the gradient stability will decrease concomitantly. These highly divergent gradients will harm the model training and increase the risk of gradient vanishing and gradient exploding. To fully take the gradient stability into consideration, we present a new perspective to the BNNs training, regarding it as the equilibrium between the estimating error and the gradient stability. In this view, we firstly design two indicators to quantitatively demonstrate the equilibrium phenomenon. In addition, in order to balance the estimating error and the gradient stability well, we revise the original straight through estimator and propose a power function based estimator, Rectified Straight Through Estimator (ReSTE for short). Comparing to other estimators, ReSTE is rational and capable of flexibly balancing the estimating error with the gradient stability. Extensive experiments on CIFAR-10 and ImageNet datasets show that ReSTE has excellent performance and surpasses the state-of-the-art methods without any auxiliary modules or losses.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Blockchain-Based Transactive Energy Management Scheme for Nano-Grids using Power Flow Coloring

A Blockchain-Based Transactive Energy Management Scheme for ...

引用

IEEE International Conference on Consumer Electronics-Taiwan (ICCE-TW)

作者： Abdullah Bin Masood Saher Javaid Yasuo Tan Vasos Vassiliou Marios Lestas Department of Computer Science University of Cyprus Nicosia Cyprus CYENS - Centre of Excellence Nicosia Cyprus School of Information Science Japan Advanced Institute of Science and Technology Ishikawa Japan Department of Electrical Engineering Frederick University Nicosia Cyprus

The proliferation of distributed energy resources (DER) and the widespread adoption of the Internet of Things (IoT) in Prosumer Nano-Grids (P-NGs) pose severe challenges in existing energy management schemes, thus necessitating the need for the development of novel solutions which can guarantee system efficiency and security. To address such challenges, we propose a novel scheme leveraging the benefits of distributed power flow coloring, blockchain technology, and Transactive Energy Management (TEM). The proposed system model offers P-NGs a secure, transparent, trustworthy, and efficient energy management and transactions platform that can: maintain the overall voltage stability and specified power ratios against power fluctuations within the P-NG, offer an increase in energy security, provide real-time monitoring, and reduce energy waste.

关键词：

来源：评论

学校读者我要写书评

暂无评论

MLNet: Mutual Learning Network with Neighborhood Invariance for Universal Domain Adaptation

arXiv

引用

arXiv 2023年

作者： Lu, Yanzuo Shen, Meng Ma, Andy J. Xie, Xiaohua Lai, Jian-Huang School of Computer Science and Engineering Sun Yat-sen University Guangzhou China Guangdong Province Key Laboratory of Information Security Technology China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China Guangzhou China

Universal domain adaptation (UniDA) is a practical but challenging problem, in which information about the relation between the source and the target domains is not given for knowledge transfer. Existing UniDA methods may suffer from the problems of overlooking intra-domain variations in the target domain and difficulty in separating between the similar known and unknown class. To address these issues, we propose a novel Mutual Learning Network (MLNet) with neighborhood invariance for UniDA. In our method, confidence-guided invariant feature learning with self-adaptive neighbor selection is designed to reduce the intra-domain variations for more generalizable feature representation. By using the cross-domain mixup scheme for better unknown-class identification, the proposed method compensates for the misidentified known-class errors by mutual learning between the closed-set and open-set classifiers. Extensive experiments on three publicly available benchmarks demonstrate that our method achieves the best results compared to the state-of-the-arts in most cases and significantly outperforms the baseline across all the four settings in UniDA. Code is available at https://***/YanzuoLu/MLNet. Copyright © 2023, The Authors. All rights reserved.

关键词： Knowledge management

来源：评论

学校读者我要写书评

暂无评论

Benchmarking Deep Models on Salient Object Detection

SSRN

引用

SSRN 2023年

作者： Zhou, Huajun Lin, Yang Yang, Lingxiao Lai, Jianhuang Xie, Xiaohua School of Computer Science and Engineering Sun Yat-sen University Guangzhou China Guangdong Province Key Laboratory of Information Security Technology Guangzhou China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education Guangzhou China

Deep network-based methods have continuously refreshed state-of-the-art performance on the Salient Object Detection (SOD) task. However, the performance discrepancy caused by different implementation details may conceal the real progress. In this paper, we construct a SALient Object Detection (SALOD) benchmark to ensure a fair and comprehensive evaluation by unifying the implementation settings of SOD methods. We aim to reveal the reasons behind recent progress by conducting a comprehensive examination of the impact of the network structure, training strategy, and loss function on accuracy. Based on the experimental results, first, we find that U-shaped networks, both older and more recent, still achieve better performance than other recently proposed structures. Second, the ablation study on training strategy proves its significant impact on SOD performance. Third, we provide a comprehensive analysis on existing loss functions and propose a new Edge-Aware (EA) loss function in response. At last, an objectness shifting experiment stands on a new perspective to validate the generalizability of SOD methods. Code is available at https://***/moothes/SALOD. © 2023, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Visualizing nonlinear resonance in nanomechanical systems via single-electron tunneling

引用

Nano Research 2021年第4期14卷 1156-1161页

作者： Xinhe Wang Lin Cong Dong Zhu Zi Yuan Xiaoyang Lin Weisheng Zhao Zaiqiao Bai Wenjie Liang Ximing Sun Guang-Wei Deng Kaili Jiang Fert Beijing Research Institute School of Microelectronics&Beijing Advanced Innovation Centre for Big Data and Brain Computing(BDBC)Beihang UniversityBeijing 100191China State Key Laboratory of Low-Dimensional Quantum Physics Department of Physics and Tsinghua-Foxconn Nanotechnology Research CenterTsinghua UniversityBeijing 100084China Key Laboratory of Quantum Information CASUniversity of Science and Technology of ChinaHefei 230026China Department of Physics Beijing Normal UniversityBeijing 100875China Institute of Physics Chinese Academy of SciencesBeijing 100080China Institute of Nuclear and New Energy Technology Collaborative Innovation Center of Advanced Nuclear Energy TechnologyKey Laboratory of Advanced Reactor EngineeringTsinghua UniversityBeijing 100084China Institute of Fundamental and Frontier Sciences University of Electronic Science and Technology of ChinaChengdu 610054China

Numerous reports have elucidated the importance of mechanical resonators comprising quantum-dot-embedded carbon nanotubes(CNTs)for studying the effects of single-electron ***,there is a need to investigate the single-electron transport that drives a large amplitude into a nonlinear ***,a CNT hybrid device has been investigated,which comprises a gate-defined quantum dot that is embedded into a mechanical resonator under strong actuation *** Coulomb peak positions synchronously oscillate with the mechanical vibrations,enabling a single-electron Chopper*1 ***,the vibration amplitude of the CNT versus its frequency can be directly visualized via detecting the time-averaged single-electron tunneling *** understand this phenomenon,a general formula is derived for this time-averaged single-electron tunneling current,which agrees well with the experimental *** using this visualization method,a variety of nonlinear motions of a CNT mechanical oscillator have been directly recorded,such as Duffing nonlinearity,parametric resonance,and double-,fractional-,mixed-frequency *** approach opens up burgeoning opportunities for investigating and understanding the nonlinear motion of a nanomechanical system and its interactions with electron transport in quantum regimes.

关键词： carbon nanotube mechanical resonator quantum dot nonlinear coupling

来源：评论

学校读者我要写书评

暂无评论

AI-Based Load Forecasting for Demand Response

AI-Based Load Forecasting for Demand Response

引用

Frontier Technologies and Solutions (ICFTS), International Conference on

作者： Chintureena Thingom Mohan. S E. Afreen Banu E. Saranya M. Jasmin K. Anuradha Department of Computer Science & Engineering Alliance School of Advanced Computing Alliance University Bengaluru Karnataka India Department of Electrical And Electronics Engineering Sri Sairam Engineering College Chennai Tamil Nadu India Department of Computer Engineering Shah & Anchor Kutchhi Engineering College Mumbai Maharashtra India Department of Computer Science and Business Systems Sri Eshwar College of Engineering Coimbatore Tamil Nadu India Department of Electronics and Communication Engineering New Prince Shri Bhavani College of Engineering and Technology Chennai Tamil Nadu India Department of Electronics and Communication Engineering Mallareddy Engineering College (Autonomous) Hyderabad Telangana India

ISBN: (数字)9798331502768

ISBN: (纸本)9798331502775

Accurate load forecasting is essential for energy system demand response, energy distribution, and energy waste reduction. This work investigates artificial intelligence-based energy load estimation methods, focussing on Gradient Boosting Machines (GBM) to improve forecast accuracy. The study will focus on GBM use. The research project begins with extensive data preprocessing. This solution includes imputation for missing data and data inclusion to fix dataset imbalances. To improve model performance, autoencoder-based feature selection reduces data dimensionality while keeping crucial information. We also use a correlation matrix to find and remove duplicate characteristics. After that, the Gradient Boosting Machine classifier is used for regression jobs to manage nonlinear relationships and reduce prediction mistakes. This improves forecast accuracy. The studies show that the suggested strategy enhances load forecasting accuracy compared to standard models. This study shows that AI-driven methods can improve demand responsiveness. This can help smart grids and telecoms manage energy more efficiently and sustainably.

关键词： Accuracy Load forecasting Predictive models Feature extraction Boosting Demand response Data models Imputation Smart grids Load modeling

来源：评论

学校读者我要写书评

暂无评论

Machine Learning and Cloud computing: Synergies And Innovations for Data-Driven Insights

Machine Learning and Cloud Computing: Synergies And Innovati...

引用

International Conference on Contemporary computing and Informatics (IC3I)

作者： Dileep S. Sadhankar S. P. Santhoshkumar M. K. Sharma Pratha Saxena Ch. Srinivasa Reddy Amit Kumar Jain Department of Computer Science St. Francis De Sales College Nagpur Maharashtra Department of Computer Science and Engineering School of Computing Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Avadi Chennai Mathematics Chaudhary Charan Singh University Meerut Uttar Pradesh India Computer applications Invertis university Bareilly UP Department of Information Technology Vignan’s Institute of Information Technology (A) Duvvada Visakhapatnam Department of Electrical & Electronics Engineering Poornima University IS-2027-2031 Jaipur Rajasthan India

ISBN: (数字)9798350350067

ISBN: (纸本)9798350350074

This paper aims at discussing the interaction between cloud computing and machine learning in analyzing the data since they boost the analytical ability of insights through boosting the predictability and operational ability. The study employs Cybersecurity Attack data set from Kaggle together with Cloud data set and employs Random Forest and ARIMA algorithms together with cloud computationally intensive resources to analyze and interpret large and complicated datasets. It covers data preparation, building, and deploying of models that can analyze data in real-time with cloud support. Findings show that integrating machine learning with cloud computing has immensely improved threat detection, predictive analytics, and actions. This brings in to perspective the potential of such technologies in enhancing the performance of data processing and, forecast future research on the advanced machine learning algorithms and real-time data.

关键词： Cloud computing Machine learning algorithms Accuracy Machine learning Real-time systems Data models Threat assessment computer security Predictive analytics Random forests

来源：评论

学校读者我要写书评

暂无评论

Knowledge-based Multiple Adaptive Spaces Fusion for Recommendation

arXiv

引用

arXiv 2023年

作者： Yuan, Meng Zhuang, Fuzhen Zhang, Zhao Wang, Deqing Dong, Jin Institute of Artificial Intelligence Beihang University Beijing China Institute of Computing Technology Chinese Academy of Sciences Beijing China School of Computer Science and Engineering Beihang University Beijing China Beijing Academy of Blockchain and Edge Computing Beijing China Zhongguancun Laboratory Beijing China

Since Knowledge Graphs (KGs) contain rich semantic information, recently there has been an influx of KG-enhanced recommendation methods. Most of existing methods are entirely designed based on euclidean space without considering curvature. However, recent studies have revealed that a tremendous graph-structured data exhibits highly non-euclidean properties. Motivated by these observations, in this work, we propose a knowledge-based multiple adaptive spaces fusion method for recommendation, namely MCKG. Unlike existing methods that solely adopt a specific manifold, we introduce the unified space that is compatible with hyperbolic, euclidean and spherical spaces. Furthermore, we fuse the multiple unified spaces in an attention manner to obtain the high-quality embeddings for better knowledge propagation. In addition, we propose a geometry-aware optimization strategy which enables the pull and push processes benefited from both hyperbolic and spherical spaces. Specifically, in hyperbolic space, we set smaller margins in the area near to the origin, which is conducive to distinguishing between highly similar positive items and negative ones. At the same time, we set larger margins in the area far from the origin to ensure the model has sufficient error tolerance. The similar manner also applies to spherical spaces. Extensive experiments on three real-world datasets demonstrate that the MCKG has a significant improvement over state-of-the-art recommendation methods. Further ablation experiments verify the importance of multi-space fusion and geometry-aware optimization strategy, justifying the rationality and effectiveness of MCKG. © 2023, CC BY.

关键词： Spheres

来源：评论

学校读者我要写书评

暂无评论

RS-ModCubes: Self-reconfigurable, Scalable, Modular Cubic Robots for Underwater Multitasking

arXiv

引用

arXiv 2024年

作者： Zheng, Jiaxi Dai, Guangmin He, Botao Mu, Zhaoyang Meng, Zhaochen Zhang, Tianyi Zhi, Weiming Fan, Dixia Robotics Institute School of Computer Science Carnegie Mellon University PittsburghPA15213 United States Zhejiang University Zhejiang Hangzhou310027 China Key Laboratory of Coastal Environment and Resources of Zhejiang Province School of Engineering Westlake University Zhejiang Hangzhou310030 China Department of Computer Science University of Maryland College ParkMD20742 United States Institute of Advanced Technology Westlake Institute for Advanced Study Zhejiang Hangzhou310024 China

This paper introduces a reconfigurable underwater robot system, RS-ModCubes, which allows scalable multi-robot configuration. An RS-ModCubes system consists of multiple ModCube modules, that can travel underwater with 6 DoFs and assemble with each other into a larger structure with onboard electromagnets. This system is designed to support diverse underwater applications through modularity and reconfigurability, eliminating the need to customize mechanical designs for a specific task. We present a modeling framework tailored for such reconfigurable robot systems, with hydrodynamics integrated based on Monte Carlo approximation. A model-based feedforward Proportional Derivative (PD) controller serves as the baseline for control. Inspired by dexterous manipulation, we evaluated the robot’s maximum task wrench space and power efficiency, compared against four commercial underwater robots. RS-ModCubes is validated via both real-world experiments and simulations, including individual and multi-module trajectory tracking and hovering docking. We open-source the design and code to facilitate future research: https://***/***/. © 2024, CC BY.

关键词： Machine design

来源：评论

学校读者我要写书评

暂无评论

Classical to Quantum Transfer Learning Framework for Wireless Sensing Under Domain Shift

Classical to Quantum Transfer Learning Framework for Wireles...

引用

IEEE Conference on Global Communications (GLOBECOM)

作者： Yingxin Shan Peng Liao Xuyu Wang Lingling An Shiwen Mao Guangzhou Institute of Technology Xidian University Guangzhou China Knight Foundation School of Computing & Information Sciences Florida International University Miami FL USA School of Computer Science and Technology Xidian University Xi'an China Department of Electrical and Computer Engineering Auburn University Auburn AL USA

To implement ubiquitous wireless sensing, the domain shift problem (e.g., different environments, users, devices) for machine learning based approaches should be addressed. Some existing methods are proven to be effective, such as transfer learning and domain adaptation. Meanwhile, quantum machine learning, a combination of quantum computing and machine learning, has attracted much attention. More importantly, quantum transfer learning (QTL) has been successful for certain applications, e.g., image classification. In this paper, we explore a classical to quantum (C2Q) framework to address the domain shift problem in wireless sensing by exploiting the great potential of QTL. Specifically, we first analyze the data shift problem in various types of wireless datasets by calculating the Kullback-Leibler (KL) divergence of different domains. Then, a QTL framework is designed to introduce importance weighting and adversarial strategies. We finally evaluate the proposed framework using the representative human activity recognition task on three wireless sensing datasets. Experimental results demonstrate the feasibility of the framework and its great potential for solving the domain shift problem in wireless sensing.

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：