检索结果-内蒙古大学图书馆

International Symposium on Computational Intelligence and Design, ISCID

作者： Jiaqi Liu Hongchuan Zhou Benchao Yang State Key Laboratory of Mathematical Engineering and advanced computing Information Engineering University Zhengzhou China

ISBN: (纸本)9781665438575

This paper mainly studies the change rule of center temperature of welding zone in backwelding furnace under different set temperature and transfer rate conditions, and searches for appropriate temperature and rate to obtain the optimal furnace temperature curve. Different infinite length plate models were established for the small temperature region and interval respectively, and the heat transfer of each part was considered according to Fourier heat law and Newton cooling law, and the equation about the temperature change with time was constructed based on the law of energy conservation.

关键词： Heating systems Semiconductor device modeling Temperature Cooling Furnaces Computational modeling Welding

来源：评论

学校读者我要写书评

暂无评论

ThicknessVAE: Learning a Lateral Prior for Clothed Human Body Reconstruction

ThicknessVAE: Learning a Lateral Prior for Clothed Human Bod...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Xiaotao Wu Zhaoxin Fan Huiguang He Dinggang Shen School of Biomedical Engineering & State Key Laboratory of Advanced Medical Materials and Devices ShanghaiTech University Shanghai China NeuBCI Group State Key Laboratory of Brain Cognition and Brain-Inspired Intelligence Technology Institute of Automation Chinese Academy of Sciences Beijing China Beijing Advanced Innovation Center for Future Blockchain and Privacy Computing Institute of Artificial Intelligence Beihang University Beijing China Beijing Academy of Blockchain and Edge Computing China Shanghai United Imaging Intelligence Co. Ltd. Shanghai China Shanghai Clinical Research and Trial Center Shanghai China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Sandwich-like structures have shown remarkable efficacy in clothed human reconstruction. However, these approaches often generate unrealistic side geometries due to inadequate handling of lateral regions. This paper addresses this limitation by incorporating the side geometry of clothed humans as a prior. We propose ThicknessVAE, a novel two-stage method that makes two key contributions: (1) We learn a prototype from point clouds for the lateral regions of clothed humans to extract common and detailed geometric features. (2) We utilize this prototype as a prior to transform geometric features into a thickness map associated with clothed human images, enabling refined normal integration for sandwich-like reconstruction methods. By seamlessly integrating our model into the sandwich-like reconstruction pipeline, we achieve highly realistic side views. Both qualitative and quantitative experiments demonstrate that our approach is comparable to state-of-the-art methods in terms of side-view realism.

关键词： Geometry Surface reconstruction Three-dimensional displays Pipelines Prototypes Transforms Feature extraction Speech processing Image reconstruction Surface treatment

来源：评论

学校读者我要写书评

暂无评论

Collision attack framework on RIPEMD-128 2

Collision attack framework on RIPEMD-128

引用

2nd International Conference on Artificial Intelligence and advanced Manufacture, AIAM 2020

作者： Li, Jingyu Zeng, Guang Yang, Yang State Key Laboratory of Mathematical Engineering and Advanced Computing PLA Strategic Force Information Engineering University Zhengzhou China State Key Laboratory of Mathematical Engineering and Advanced Computing PLA Information Engineering University Zhengzhou China Trusted Computing and Information Assurance Laboratory Institute of Software Chinese Academy of Sciences Beijing China

ISBN: (纸本)9781728199863

In the last few years, the hash functions are the very common and essential primitives implemented in lots of fields. RIPEMD-128, a member of MD-family hash function, has been found collisions on the full round. In this paper, we further analyze the property about the security against collision attack of RIPEMD-128. The collision attack framework for RIPEMD-128 is proposed in order to provide ideas for other hash functions. The framework consists of three parts namely choosing a message word difference insertion, constructing differential characteristics and collision search phase. Cryptographic techniques including message modification is also introduced to reduce the complexity. © 2020 IEEE.

关键词： Hash functions

来源：评论

学校读者我要写书评

暂无评论

Path planning of UAV base station based on deep reinforcement learning

引用

Procedia Computer Science 2022年 202卷 89-104页

作者： Siming Yang Zheng Shan Jiang Cao Yuan Gao Yang Guo Ping Wang Xiaonan Wang Jing Wang Tingting Zhang Jiayu Guo State Key Laboratory of Mathematical Engineering and Advanced Computing Zhengzhou Henan 450001 China Academy of Military Science of the PLA Beijing 100091 China Network Technology Research Center of the PLA Beijing 100090 China

UAV base station platform has become the current research hotspot of assisting ground base station for wireless *** present, the most important issue is how to make path planning to provide the stable communication guarantee for multiple mobile users. In this article, we model the air-to-ground channel to describe the path loss between the UAV platform and the user and build a simulation environment for training based on the OpenAI-GYM architecture. In addition, this paper proposes a reinforcement learning algorithm based on intrinsic rewards, which uses the mean square error of the state prediction results to quantify the novelty of the state. Algorithms enable agents to efficiently carry out strategy iterations. Experiments results showed that our algorithm has a higher score and takes less time.

关键词： UAV path planning Wireless communication coverage Deep learning Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

MAST-Pro: Dynamic Mixture-of-Experts for Adaptive Segmentation of Pan-Tumors with Knowledge-Driven Prompts

arXiv

引用

arXiv 2025年

作者： Meng, Runqi Song, Sifan Jin, Pengfei Oh, Yujin Teng, Lin Wang, Yulin Sun, Yiqun Chen, Ling Li, Xiang Li, Quanzheng Guo, Ning Shen, Dinggang School of Biomedical Engineering State Key Laboratory of Advanced Medical Materials and Devices ShanghaiTech University China Center of Advanced Medical Computing and Analysis Massachusetts General Hospital Harvard Medical School Harvard University United States Shanghai United Imaging Intelligence Co. Ltd China Shanghai Clinical Research and Trial Center China

Accurate tumor segmentation is crucial for cancer diagnosis and treatment. While foundation models have advanced general-purpose segmentation, existing methods still struggle with: (1) limited incorporation of medical priors, (2) imbalance between generic and tumor-specific features, and (3) high computational costs for clinical adaptation. To address these challenges, we propose MAST-Pro (Mixture-of-experts for Adaptive Segmentation of pan-Tumors with knowledge-driven Prompts), a novel framework that integrates dynamic Mixture-of-Experts (D-MoE) and knowledge-driven prompts for pan-tumor segmentation. Specifically, text and anatomical prompts provide domain-specific priors, guiding tumor representation learning, while D-MoE dynamically selects experts to balance generic and tumor-specific feature learning, improving segmentation accuracy across diverse tumor types. To enhance efficiency, we employ Parameter-Efficient Fine-Tuning (PEFT), optimizing MAST-Pro with significantly reduced computational overhead. Experiments on multi-anatomical tumor datasets demonstrate that MAST-Pro outperforms state-of-the-art approaches, achieving up to a 5.20% improvement in average DSC while reducing trainable parameters by 91.04%, without compromising accuracy. © 2025, CC BY-NC-ND.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

ODCP: Optimizing Data Caching and Placement in Distributed File System Using Erasure Coding 17th

ODCP: Optimizing Data Caching and Placement in Distributed F...

引用

17th IFIP WG 10.3 International Conference on Network and Parallel computing, NPC 2020

作者： Wu, Shuhan Li, Yunchun Yang, Hailong Luan, Zerong Li, Wei School of Computer Science and Engineering Beihang University Beijing100191 China College of Life Sciences and Bioengineering Beijing University of Technology Beijing100083 China State Key Laboratory of Mathematical Engineering and Advanced Computing Wuxi214125 China

ISBN: (纸本)9783030794774

Many current distributed file systems use erasure-coding based data redundancy techniques to improve the reliability of data storage. Such techniques can significantly improve the effective storage utilization. However, there are several drawbacks to the above techniques. Firstly, they introduce non-negligible computation overhead for decoding. Secondly, traditional data caching and placement strategies become less effective in such cases. To solve the above drawbacks, this paper proposes a new data cache allocation mechanism based on simulated annealing and a new data placement strategy based on convex optimization, which effectively reduces data block transmission delay and decoding delay. We have implemented the proposed data placement strategy in the real-world distributed file system Alluxio, and evaluated the performance of our strategy. Experiment results show that our strategy can significantly reduce the file read delay compared to traditional data placement strategies. © 2021, IFIP International Federation for Information Processing.

关键词： Convex optimization

来源：评论

学校读者我要写书评

暂无评论

PediaBench: A Comprehensive Chinese Pediatric Dataset for Benchmarking Large Language Models

arXiv

引用

arXiv 2024年

作者： Zhang, Qian Chen, Panfeng Li, Jiali Feng, Linkun Liu, Shuyu Zhao, Heng Chen, Mei Li, Hui Wang, Yanhao State Key Laboratory of Public Big Data College of Computer Science and Technology Guizhou University Guiyang China Guizhou Engineering Laboratory for Advanced Computing and Medical Information Services Guiyang China College of Big Data and Internet Shenzhen Technology University Shenzhen China School of Data Science and Engineering East China Normal University Shanghai China

The emergence of Large Language Models (LLMs) in the medical domain has stressed a compelling need for standard datasets to evaluate their question-answering (QA) performance. Although there have been several benchmark datasets for medical QA, they either cover common knowledge across different departments or are specific to another department rather than pediatrics. Moreover, some of them are limited to objective questions and do not measure the generation capacity of LLMs. Therefore, they cannot comprehensively assess the QA ability of LLMs in pediatrics. To fill this gap, we construct PediaBench, the first Chinese pediatric dataset for LLM evaluation. Specifically, it contains 4,117 objective questions and 1,632 subjective questions spanning 12 pediatric disease groups. It adopts an integrated scoring criterion based on different difficulty levels to thoroughly assess the proficiency of an LLM in instruction following, knowledge understanding, clinical case analysis, etc. Finally, we validate the effectiveness of PediaBench with extensive experiments on 20 open-source and commercial LLMs. Through an in-depth analysis of experimental results, we offer insights into the ability of LLMs to answer pediatric questions in the Chinese context, highlighting their limitations for further improvements. Our code and data are published anonymously at https://***/ACMISLab/PediaBench. © 2024, CC BY-SA.

关键词： Question answering

来源：评论

学校读者我要写书评

暂无评论

swRodinia: A Benchmark Suite for Exploiting Architecture Properties of Sunway Processor 3rd

swRodinia: A Benchmark Suite for Exploiting Architecture Pr...

引用

3rd BenchCouncil International Symposium on Benchmarking, Measuring, and Optimizing, Bench 2020

作者： Chen, Bangduo Li, Mingzhen Yang, Hailong Luan, Zhongzhi Gan, Lin Yang, Guangwen Qian, Depei School of Computer Science and Engineering Beihang University Beijing100191 China State Key Laboratory of Mathematical Engineering and Advanced Computing Wuxi Jiangsu214125 China Department of Computer Science and Technology Tsinghua University Beijing100084 China

ISBN: (纸本)9783030710576

The Sunway processor has been demonstrated with superior performance by various scientific applications, domain specific frameworks and numerical algorithms. However, the optimization techniques that can fully exploit the architecture features are usually buried deep in large code bases, which prevents average programmers to understand such optimization techniques. Thus, the existing complex software fails to provide guidance for more programs embracing the computation power of Sunway processor. In this paper, we build a benchmark suite swRodinia by porting and optimizing the well-known Rodinia benchmark on Sunway processor. Specifically, we demonstrate several optimization techniques by tailoring the benchmarks to better leverage the architecture features for higher performance. Moreover, based on the optimization experiences, we derive several useful insights from both software and hardware perspectives, that not only guide the better utilization of current Sunway processor, but also reveal the direction of hardware improvements for future Sunway processor. We open source the swRodinia benchmark suite and encourage the community to enhance the benchmark with us continuously. © 2021, Springer Nature Switzerland AG.

关键词： Open source software

来源：评论

学校读者我要写书评

暂无评论

An OFDM based interference reducing scheme with trajectory and resource optimization for UAV-powered IoT Networks 34

An OFDM based interference reducing scheme with trajectory a...

引用

34th General Assembly and Scientific Symposium of the International Union of Radio Science, URSI GASS 2021

作者： Gao, Yuan Cao, Jiang Guo, Yang Wang, Ping Yang, Siming Wang, Jing Lu, Weidang Si, Peiyuan Zhao, Ming Wu, Xiao Academy of Military Science of the PLA 100091 China College of Information Engineering Zhejiang University of Technology Hangzhou China Tsinghua University Beijing100084 China State Key Laboratory of Mathematical Engineering and Advanced Computing Zhengzhou450001 China

ISBN: (纸本)9789463968027

The massive and pervasive deployment of sensors for information collecting in IoT networks result to the scarcity of energy. Unmanned aerial vehicle (UAV) enabled wireless power transfer (WPT) is a feasible solution to provide energy for pervasively deployed sensors. In this paper, we propose an orthogonal frequency division multiplexing (OFDM) based interference reducing scheme with trajectory and resource optimization for UAV-powered IoT networks. The simulation results show that our proposed scheme outperforms two benchmark schemes in sum transmission rate. © 2021 URSI.

关键词： Orthogonal frequency division multiplexing

来源：评论

学校读者我要写书评

暂无评论

A Channel-Augmented Multi-Domain Graph Convolutional Network for Fatigue Driving Detection

A Channel-Augmented Multi-Domain Graph Convolutional Network...

引用

Industrial Automation, Robotics and Control engineering (IARCE), International Conference on

作者： Mingyi Sun Weigang Cui Yang Li Department of Automation Science and Electrical Engineering Beihang University Beijing China School of Engineering Medicine Beihang University Beijing China Department of Automation Science and Electrical Engineering State Key Laboratory of Virtual Reality Technology and Systems The Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing China

ISBN: (数字)9798350380323

ISBN: (纸本)9798350380330

Electroencephalography (EEG) has emerged as a crucial cornerstone within the realm of brain-computer interface (BCI) applications, with its significance notably pronounced in the field of fatigue detection. However, the inherent limitations of EEG acquisition equipment during real driving scenarios have contributed to the constrained robustness of existing models. Moreover, most of recent methods failed to extract robust multi-domain features, leading to a suboptimal performance. To address these challenges, we propose a novel channel-augmented multi-domain graph convolutional network (CA-MDGCNet). Specifically, the initial EEG signals are enriched by incorporating supplementary virtual EEG channels, distinguished as learnable parameters within the network architecture. Then, differential entropy features are extracted from the augmented EEG signals. Following this, a multi-domain graph convolutional network is designed to encode high-level EEG features by means of convolutions in diverse paths, which is beneficial to integrating the characteristics extracted from multiple domains. Finally, the classification block derives the detection outcome from the refined feature maps. To substantiate the potency of the proposed method, the validation was conducted on the publicly accessible SEED-VIG. The proposed CA-MDGCNet not only demonstrates more promising performance compared to state-of-the-art approaches but also underscores the potential viability of our method for the realm of fatigue driving detection.

关键词： Graph convolutional networks Convolution Service robots Neural activity Feature extraction Fatigue Brain modeling Electroencephalography Entropy Robustness

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：