检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Zhou, Ziqi Qi, Lei Shi, Yinghuan State Key Laboratory for Novel Software Technology Nanjing University China National Institute of Healthcare Data Science Nanjing University China School of Computer Science and Engineering Southeast University China

For medical image analysis, segmentation models trained on one or several domains lack generalization ability to unseen domains due to discrepancies between different data acquisition policies. We argue that the degeneration in segmentation performance is mainly attributed to overfitting to source domains and domain shift. To this end, we present a novel generalizable medical image segmentation method. To be specific, we design our approach as a multi-task paradigm by combining the segmentation model with a self-supervision domain-specific image restoration (DSIR) module for model regularization. We also design a random amplitude mixup (RAM) module, which incorporates low-level frequency information of different domain images to synthesize new images. To guide our model be resistant to domain shift, we introduce a semantic consistency loss. We demonstrate the performance of our method on two public generalizable segmentation benchmarks in medical images, which validates our method could achieve the state-of-the-art performance. ‡ Copyright © 2022, The Authors. All rights reserved.

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Microstructure and mechanical properties of a recycled aluminum alloy fabricated by consolidation of small pieces

引用

Heat Treatment and Surface engineering 2024年第1期6卷

作者： Liu, Feifei Zhang, Deliang School of Materials Science and Engineering Northeastern University Shenyang China National Frontiers Science Center for Industrial Intelligence and Systems Optimization Northeastern University Shenyang China Key Laboratory of Data Analytics and Optimization for Smart Industry (Ministry of Education) Northeastern University Shenyang China

The microstructure and mechanical properties of recycled AA6063 aluminum alloy rods fabricated by hot extrusion of forging compacts formed by upsetting compacts of small AA6063 aluminum alloy pieces with different Fe contents before and after T6 heat treatment were studied. In the as-extruded state and with the higher extrusion ratio of 25:1, the microstructure consists of fully recrystallized grains, but the high iron content regions exhibit clearly finer equiaxed grains due to the stronger grain boundary pinning and nucleation effects of a higher number density of Fe-rich phase particles. Increasing the extrusion ratio increases both the strength and ductility of the as-extruded material. The reason is that increasing extrusion ratio enhances the bonding strength of the prior boundaries between the strips formed by deformation of the small pieces. In the T6 heat-treated state, increasing the extrusion ratio from 9:1 to 25:1 clearly increases the fraction of fine and equiaxed grains. The enhancement of the bonding strength and the refinement of the microstructure with the increase of extrusion ratio cause the yield strength and ultimate tensile strength to increase from 174 and 221 MPa to 213 and 237 MPa, respectively, and the elongation to fracture to decrease from 22.1 to 15.4%. Solid-state recycled samples all exhibit a ductile fracture behavior despite formation of microcracks at the prior boundaries. © 2024 The Author(s). Published by Informa UK Limited, trading as Taylor & Francis Group.

关键词： Aluminum alloy hot extrusion mechanical properties microstructure solid state recycling

来源：评论

学校读者我要写书评

暂无评论

Blockchain-Based Homomorphic Transaction Framework for Enhanced Consumer Security and Business Scalability

引用

IEEE Transactions on Consumer Electronics 2024年

作者： Guo, Tao Shang, Fengjun Dai, Xiangguang Liu, Qilie Chongqing University of Posts and Telecommunications School of Computer Science and Technology Chongqing400065 China Key Laboratory of Big Data Intelligent Computing Chongqing400065 China Chongqing Three Gorges University Key Lab. of Intelligent Info. Proc. and Contr. of Chongqing Munic. Institutions of Higher Education Chongqing Engineering Research Center of Internet of Things and Intelligent Control Technology School of Three Gorges Artificial Intelligence Chongqing400044 China Chongqing University of Posts and Telecommunications School of Communications and Information Engineering Chongqing400065 China

Energy trading in distributed microgrids represents an effective means of enhancing the utilization of renewable energy. However, the aggregation of large-scale consumption data may encounter business scalability issues and potential privacy exposure concerns, necessitating the development of novel secure and scalable frameworks for integrating consumption demands between prosumer and microgrid entities. we research focuses on providing a user-friendly transaction model for consumers and microgrid operators. Firstly, a privacy aggregation scheme for user resource requests is designed to ensure the security and decentralization of user data. In addition, the model employs a bidirectional heterogeneous resource allocation mechanism to support the optimal allocation of multiple resources, such as renewable energy, power assets, energy storage devices, and carbon credits, among different microgrids. Finally, a microgrid transaction prototype has been constructed on the Truffle development framework. In this context, smart contracts has been designed to ensure that the transactions are carried out automatically. Experimental results indicate that the scheme provides enhanced security for multi-resource trading in a cluster context relative to existing methodologies. The number of transactions increases linearly with the resource overhead, resulting in more efficient utilization of energy trading. Furthermore, the framework's scalability has been demonstrated through both temporal and spatial considerations. © 1975-2011 IEEE.

关键词： Decentralized finance

来源：评论

学校读者我要写书评

暂无评论

Neural Network Panning: Screening the Optimal Sparse Network Before Training

arXiv

引用

arXiv 2022年

作者： Kang, Xiatao Li, Ping Yao, Jiayi Li, Chengxi School of Computer and Communication Engineering Changsha University of Science and Technology China School of Computer Xidian University China Hunan Provincial Key Laboratory of Intelligent Processing of Big Data on Transp China

Pruning on neural networks before training not only compresses the original models, but also accelerates the network training phase, which has substantial application value. The current work focuses on fine-grained pruning, which uses metrics to calculate weight scores for weight screening, and extends from the initial single-order pruning to iterative pruning. Through these works, we argue that network pruning can be summarized as an expressive force transfer process of weights, where the reserved weights will take on the expressive force from the removed ones for the purpose of maintaining the performance of original networks. In order to achieve optimal expressive force scheduling, we propose a pruning scheme before training called Neural Network Panning which guides expressive force transfer through multi-index and multi-process steps, and designs a kind of panning agent based on reinforcement learning to automate processes. Experimental results show that Panning performs better than various available pruning before training methods. Our code is made public at: https://***/kangxiatao/RLPanning. Copyright © 2022, 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

Environmental Impact on Connected and Automated Vehicle in Heterogeneous State Considering Different Penetration Rates

Environmental Impact on Connected and Automated Vehicle in H...

引用

2022世界交通运输大会(WTC2022)

作者： Yixin Zhang Xumei Chen Xiaoyue Liu Yu Zhang Key Laboratory of Transport Industry of Big Data Application Technologies for Comprehensive Transport Beijing Jiaotong University School of Traffic and Transportation Xuchang University Department of Civil & Environmental Engineering University of Utah

With the rapid development of Connected and Automated Vehicle(CAV) technology,vehiclesequipped with such technology have gradually entered the commercialization *** a long time to come,road traffic will be *** this environment,whether different mixes of human-driven vehicles(HVs) and CAVs can achieve the expected benefits and whether the overall benefits on the road will improve are important *** main goal of this paper is to quantify the impact of CAV technology on traffic efficiency and traffic environment in complex ***,the driving behavior of HV and CAV is characterized based on the Wiedemann ***,the measurement model of energy consumption and emission is established based on the kinetic ***,a simulation platform is developed based on VISSIM for a case *** traffic efficiency and environmental benefit characteristics of vehicles on an expressway in Beijing are measured at different CAV penetration *** results show that with the increase of CAV penetration,the average operating time,average energy consumption,and average vehicle emissions are significantly *** study will effectively support the formulation of relevant road traffic management policies.

关键词： Wiedemann model Connected and automated vehicle Energy consumption emission Vissim

来源：评论

学校读者我要写书评

暂无评论

Heptagonal core anti-resonant hollow-core fiber for laser beam mode shapers

引用

Chinese Optics Letters 2025年第4期 54-60页

作者：王洋张小贝陈伟张琦杨勇李茂春颜苗王廷云 Key Laboratory of Specialty Fiber Optics and Optical Access Networks' Joint International Research Laboratory of Specialty Fiber Optics and Advanced Communication' Shanghai Institute for Advanced Communication and Data Science School of Communication and Information EngineeringShanghai University Laboratory of Science and Technology on Marine Navigation and Control' China State Shipbuilding Corporation

We report a novel anti-resonant hollow-core fiber（ARF） with a heptagonal core surrounded by connected cladding tubes,which is employed as a laser beam mode shaper. Cladding nodes are formed between each pair of adjacent cladding tubes,which efficiently enhances the mode coupling, thus significantly suppressing higher-order modes（HOMs） within a short fiber length. Numerical investigation and simulation for variations in the curvature of each node are conducted, through which an optimized structure of cladding nodes is obtained. Experimental results demonstrate that for a 1-m-long ARFbased mode shaper, the output beam quality M2is enabled, and the near-diffraction-limit beam quality is 1.03. The ARF presents a maximum average transmission power of 600 mW, achieving a total coupling efficiency of approximately85%. Moreover, it is maintained for one hour without inducing any damage while maintaining beam quality. These results highlight the great potential of the mode shaper in applications such as laser surgery, precision welding, and laser writing.

关键词：

来源：评论

学校读者我要写书评

暂无评论

POViT: Vision Transformer for Multi-objective Design and Characterization of Nanophotonic Devices

arXiv

引用

arXiv 2022年

作者： Chen, Xinyu Li, Renjie Yu, Yueyao Shen, Yuanwen Li, Wenye Zhang, Zhaoyu Zhang, Yin School of Science and Engineering The Chinese University of Hong Kong Shenzhen China Shenzhen Key Laboratory of Semiconductor Lasers China School of Data Science The Chinese University of Hong Kong Shenzhen China

We solve a fundamental challenge in semiconductor IC design: the fast and accurate characterization of nanoscale photonic devices. Much like the fusion between AI and EDA, many efforts have been made to apply DNNs such as convolutional neural networks (CNN) to prototype and characterize next-gen optoelectronic devices commonly found in photonic integrated circuits (PICs). These prior works generally strive to predict the quality factor (Q) and modal volume (V) of for instance, photonic crystals, with ultra-high accuracy and speed. However, state-of-the-art models are still far from being directly applicable in the real-world: e.g. the correlation coefficient of V (Vcoeff) is only about 80%, which is much lower than what it takes to generate reliable and reproducible nanophotonic designs. Recently, attention-based transformer models have attracted extensive interests and been widely used in CV and NLP. In this work, we propose the first-ever Transformer model (POViT) to efficiently design and simulate semiconductor photonic devices with multiple objectives. Unlike the standard Vision Transformer (ViT), we supplied photonic crystals as data input and changed the activation layer from GELU [1] to an absolute-value function (ABS). Our experiments show that POViT exceeds results reported by previous models significantly. The correlation coefficient Vcoeffincreases by over 12% (i.e., to 92:0%) and the prediction errors of Q is reduced by an order of magnitude, among several other key metric improvements. Our work has the potential to drive the expansion of EDA to fully automated photonic design. The complete dataset and code will be released to aid researchers endeavoring in the interdisciplinary field of physics and computer science. © 2022, CC BY-NC-SA.

关键词： Photonic devices

来源：评论

学校读者我要写书评

暂无评论

Rethinking the Video Sampling and Reasoning Strategies for Temporal Sentence Grounding

Rethinking the Video Sampling and Reasoning Strategies for T...

引用

2022 Findings of the Association for Computational Linguistics: EMNLP 2022

作者： Zhu, Jiahao Liu, Daizong Zhou, Pan Di, Xing Cheng, Yu Yang, Song Xu, Wenzheng Xu, Zichuan Wan, Yao Sun, Lichao Xiong, Zeyu Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering Huazhong University of Science and Technology China ProtagoLabs Inc Microsoft Research Wangxuan Institute of Computer Technology Peking University China Beijing Institute of Technology China School of Sichuan University China Dalian University of Technology China Lehigh University United States School of Computer Sci. & Tech. Huazhong University of Science and Technology China

Temporal sentence grounding (TSG) aims to identify the temporal boundary of a specific segment from an untrimmed video by a sentence query. All existing works first utilize a sparse sampling strategy to extract a fixed number of video frames and then conduct multimodal interactions with query sentence for reasoning. However, we argue that these methods have overlooked two indispensable issues: 1) Boundary-bias: The annotated target segment generally refers to two specific frames as corresponding start and end timestamps. The video downsampling process may lose these two frames and take the adjacent irrelevant frames as new boundaries. 2) Reasoning-bias: Such incorrect new boundary frames also lead to the reasoning bias during frame-query interaction, reducing the generalization ability of model. To alleviate above limitations, in this paper, we propose a novel Siamese Sampling and Reasoning Network (SSRN) for TSG, which introduces a siamese sampling mechanism to generate additional contextual frames to enrich and refine the new boundaries. Specifically, a reasoning strategy is developed to learn the inter-relationship among these frames and generate soft labels on boundaries for more accurate frame-query reasoning. Such mechanism is also able to supplement the absent consecutive visual semantics to the sampled sparse frames for fine-grained activity understanding. Extensive experiments demonstrate the effectiveness of SSRN on three challenging datasets. © 2022 Association for Computational Linguistics.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Downstream-agnostic Adversarial Examples

arXiv

引用

arXiv 2023年

作者： Zhou, Ziqi Hu, Shengshan Zhao, Ruizhi Wang, Qian Zhang, Leo Yu Hou, Junhui Jin, Hai School of Cyber Science and Engineering Huazhong University of Science and Technology China School of Computer Science and Technology Huazhong University of Science and Technology China School of Cyber Science and Engineering Wuhan University China School of Information and Communication Technology Griffith University Australia Department of Computer Science City University of Hong Kong Hong Kong National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Hubei Key Laboratory of Distributed System Security China Hubei Engineering Research Center on Big Data Security China Cluster and Grid Computing Lab

Self-supervised learning usually uses a large amount of unlabeled data to pre-train an encoder which can be used as a general-purpose feature extractor, such that downstream users only need to perform fine-tuning operations to enjoy the benefit of "large model". Despite this promising prospect, the security of pre-trained encoder has not been thoroughly investigated yet, especially when the pre-trained encoder is publicly available for commercial use. In this paper, we propose AdvEncoder, the first framework for generating downstream-agnostic universal adversarial examples based on the pre-trained encoder. AdvEncoder aims to construct a universal adversarial perturbation or patch for a set of natural images that can fool all the downstream tasks inheriting the victim pre-trained encoder. Unlike traditional adversarial example works, the pre-trained encoder only outputs feature vectors rather than classification labels. Therefore, we first exploit the high frequency component information of the image to guide the generation of adversarial examples. Then we design a generative attack framework to construct adversarial perturbations/patches by learning the distribution of the attack surrogate dataset to improve their attack success rates and transferability. Our results show that an attacker can successfully attack downstream tasks without knowing either the pre-training dataset or the downstream dataset. We also tailor four defenses for pre-trained encoders, the results of which further prove the attack ability of AdvEncoder. Our codes are available at: https://github. com/CGCL-codes/AdvEncoder. Copyright © 2023, 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

Once Read is Enough: Domain-specific Pretraining-free Language Models with Cluster-guided Sparse Experts for Long-tail Domain knowledge 38

Once Read is Enough: Domain-specific Pretraining-free Langua...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Dong, Fang Chen, Mengyi Zhou, Jixian Shi, Yubin Chen, Yixuan Dong, Mingzhi Wang, Yujiang Li, Dongsheng Yang, Xiaochen Zhu, Rui Dick, Robert Lv, Qin Yang, Fan Lu, Tun Gu, Ning Shang, Li China and Shanghai Key Laboratory of Data Science School of Computer Science Fudan University China Oxford Suzhou Centre for Advanced Research Suzhou China University of Bath United Kingdom Microsoft Research Asia Shanghai China School of Mathematics & Statistics University of Glasgow United Kingdom Bayes Business School City St George's University of London United Kingdom Department of Electrical Engineering and Computer Science University of Michigan United States Department of Computer Science University of Colorado Boulder United States School of Microelectronics Fudan University China

Language models (LMs) only pretrained on a general and massive corpus usually cannot attain satisfying performance on domain-specific downstream tasks, and hence, applying domain-specific pretraining to LMs is a common and indispensable practice. However, domain-specific pretraining can be costly and time-consuming, hindering LMs' deployment in real-world applications. In this work, we consider the incapability to memorize domain-specific knowledge embedded in the general corpus with rare occurrences and "long-tail" distributions as the leading cause for pretrained LMs' inferior downstream performance. Analysis of Neural Tangent Kernels (NTKs) reveals that those long-tail data are commonly overlooked in the model's gradient updates and, consequently, are not effectively memorized, leading to poor domain-specific downstream performance. Based on the intuition that data with similar semantic meaning are closer in the embedding space, we devise a Cluster-guided Sparse Expert (CSE) layer to actively learn long-tail domain knowledge typically neglected in previous pretrained LMs. During pretraining, a CSE layer efficiently clusters domain knowledge together and assigns long-tail knowledge to designate extra experts. CSE is also a lightweight structure that only needs to be incorporated in several deep layers. With our training strategy, we found that during pretraining, data of long-tail knowledge gradually formulate isolated, "outlier" clusters in an LM's representation spaces, especially in deeper layers. Our experimental results show that only pretraining CSE-based LMs is enough to achieve superior performance than regularly pretrained-finetuned LMs on various downstream tasks, implying the prospects of domain-specific-pretraining-free language models. © 2024 Neural information processing systems foundation. All rights reserved.

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：