检索结果-内蒙古大学图书馆

Design, Automation and Test in Europe Conference and Exhibition

作者： Ruide Cao Jiao Ye Jin Zhang Qian You Chao Tang Yan Liu Yi Wang Institute of Future Networks DET of Heyuan School of Architecture and Urban Planning SZU Department of Computer Science and Engineering Peng Cheng Laboratory School of Design SUSTech

ISBN: (数字)9783981926385

ISBN: (纸本)9798350348606

Benefiting from high flexibility and probability of line-of-sight, deploying unmanned aerial vehicles (UAV s) as aerial access points has emerged as a promising solution for ensuring reliable wireless connectivity in crowded events. This paper introduces a UAV scheduling process adaptive to dynamic mobile network demand, including three phases. In the sensing phase, the user distribution is sensed, and user number thresholds are set to determine whether UAV assistance is needed. The planning phase presents an enhanced mean shift algorithm to find suitable locations to deploy UAVs with a dynamic bandwidth derived from the user distribution, the UAV's maximum capacity, and the UAV's maximum throughput. The deploying phase dispatches and recalls UAV s based on planning results. Comprehensive simulation experiments are conducted on OMNeT ++ using real-world data. Results show that the proposed process shows great adaptivity, with an efficiency increase of 18.7% and a fairness increase of 28.9 % compared to the existing related works on average.

关键词： Adaptive scheduling Adaptive systems Heuristic algorithms Bandwidth Autonomous aerial vehicles Dynamic scheduling Throughput

来源：评论

学校读者我要写书评

暂无评论

TransferTOD: A Generalizable Chinese Multi-Domain Task-Oriented Dialogue System with Transfer Capabilities

arXiv

引用

arXiv 2024年

作者： Zhang, Ming Huang, Caishuang Wu, Yilong Liu, Shichun Zheng, Huiyuan Dong, Yurui Shen, Yujiong Dou, Shihan Zhao, Jun Ye, Junjie Zhang, Qi Gui, Tao Huang, Xuanjing School of Computer Science Fudan University China Shanghai Key Laboratory of Intelligent Information Processing Fudan University China Institute of Modern Languages and Linguistics Fudan University China

Task-oriented dialogue (TOD) systems aim to efficiently handle task-oriented conversations, including information collection. How to utilize TOD accurately, efficiently and effectively for information collection has always been a critical and challenging task. Recent studies have demonstrated that Large Language Models (LLMs) excel in dialogue, instruction generation, and reasoning, and can significantly enhance the performance of TOD through fine-tuning. However, current datasets primarily cater to user-led systems and are limited to predefined specific scenarios and slots, thereby necessitating improvements in the proactiveness, diversity, and capabilities of TOD. In this study, we present a detailed multi-domain task-oriented data construction process for conversations, and a Chinese dialogue dataset generated based on this process, TransferTOD, which authentically simulates human-computer dialogues in 30 popular life service scenarios. Leveraging this dataset, we trained a model using full-parameter fine-tuning called TransferTOD-7B, showcasing notable abilities in slot filling and questioning. Our work has demonstrated its strong generalization capabilities in various downstream scenarios, significantly enhancing both data utilization efficiency and system performance. The data is released in https://***/KongLongGeFDU/TransferTOD. Copyright © 2024, The Authors. All rights reserved.

关键词： Human computer interaction

来源：评论

学校读者我要写书评

暂无评论

RoTBench: A Multi-Level Benchmark for Evaluating the Robustness of Large Language Models in Tool Learning

arXiv

引用

arXiv 2024年

作者： Ye, Junjie Wu, Yilong Gao, Songyang Huang, Caishuang Li, Sixian Li, Guanyu Fan, Xiaoran Zhang, Qi Gui, Tao Huang, Xuanjing School of Computer Science Fudan University China Institute of Modern Languages and Linguistics Fudan University China Shanghai Key Laboratory of Intelligent Information Processing Fudan University China

Tool learning has generated widespread interest as a vital means of interaction between Large Language Models (LLMs) and the physical world. Current research predominantly emphasizes LLMs' capacity to utilize tools in well-structured environments while overlooking their stability when confronted with the inevitable noise of the real world. To bridge this gap, we introduce RoTBench, a multi-level benchmark for evaluating the robustness of LLMs in tool learning. Specifically, we establish five external environments, each featuring varying levels of noise (i.e., Clean, Slight, Medium, Heavy, and Union), providing an in-depth analysis of the model's resilience across three critical phases: tool selection, parameter identification, and content filling. Experiments involving six widely-used models underscore the urgent necessity for enhancing the robustness of LLMs in tool learning. For instance, the performance of GPT-4 even drops significantly from 80.00 to 58.10 when there is no substantial change in manual accuracy. More surprisingly, the noise correction capability inherent in the GPT family paradoxically impedes its adaptability in the face of mild noise. In light of these findings, we propose RoTTuning, a strategy that enriches the diversity of training environments to bolster the robustness of LLMs in tool learning. The code and data are available at https://***/Junjie-Ye/RoTBench. Copyright © 2024, The Authors. All rights reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

The differential fault analysis on block cipher FeW

引用

Cybersecurity 2023年第2期6卷 62-74页

作者： Haiyan Xiao Lifang Wang Jinyong Chang School of Computer Science Northwestern Polytechnical UniversityXiAn 710055People's Republic of China Engineering University of PAP XiAn 710055People's Republic of China School of Information and Control Engineering XiAn University of Architecture and TechnologyXi'An 710055People's Republic of China State Key Laboratory of Information Security(SKLOIS) Institute of Information EngineeringChinese Academy of SciencesBeijing 100089People's Republic of China

Feather weight(FeW)cipher is a lightweight block cipher proposed by Kumar et *** 2019,which takes 64 bits plaintext as input and produces 64 bits *** Kumar et ***,FeW is a software oriented design with the aim of achieving high efficiency in software based *** seems that FeW is immune to many cryptographic attacks,like linear,impossible differential,differential and zero correlation ***,in recent work,Xie et *** the security of *** precisely,they proved that under the differential fault analysis(DFA)on the encryption states,an attacker can completely recover the master secret *** this paper,we revisit the block cipher FeW and consider the DFA on its key schedule algorithm,which is rather popular cryptanalysis for kinds of block *** particular,by respectively injected faults into the 30th and 29th round subkeys,one can recover about 55/80~69%bits of master *** the brute force searching remaining bits,one can obtain the full master secret *** simulations and experiment results show that our analysis is practical.

关键词： Differential fault analysis Block cipher FeW Side channel attack

来源：评论

学校读者我要写书评

暂无评论

An Dual-Branch Network Based on Wavelet Decomposition for Image Inpainting 43

An Dual-Branch Network Based on Wavelet Decomposition for Im...

引用

43rd Chinese Control Conference, CCC 2024

作者： Shi, Yuqing Li, Jiacheng Zhang, Yang Du, Shiqiang Northwest Minzu University College of Electronic Engineering Gansu Lanzhou730030 China Chinese National Information Technology Research Institute Northwest Minzu University Key Laboratory of China's Ethnic Languages and Information Technology of Ministry of Education Gansu Lanzhou730030 China Northwest Minzu University College of Mathematics and Computer Science Gansu Lanzhou730030 China

ISBN: (纸本)9789887581581

In this paper, we propose the Wavelet-Guided Dual-Branch Network (WGDN), an innovative deep learning framework designed for image inpainting. WGDN uniquely leverages wavelet decomposition to address the challenge of reconstructing large missing regions by analyzing both low-frequency and high-frequency subbands of the image. The structure branch focuses on the low-frequency subband to restore overall structure, while the texture branch reconstructs intricate details using three high-frequency subbands. Key enhancements include the integration of an Efficient Transformer Block (ETB) in the structure branch for global information capture and a Residual in Residual Dense Block (RRDB) in the texture branch for detailed texture recovery. Additionally, we employ the CIEDE2000 color difference formula to ensure color consistency in the restored images. Our extensive testing demonstrates that WGDN outperforms existing methods in both qualitative and quantitative measures, establishing new benchmarks for the field of image inpainting. © 2024 Technical Committee on Control Theory, Chinese Association of Automation.

关键词： Wavelet decomposition

来源：评论

学校读者我要写书评

暂无评论

I/O lower bounds for auto-tuning of convolutions in CNNs 21

I/O lower bounds for auto-tuning of convolutions in CNNs

引用

26th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming, PPoPP 2021

作者： Zhang, Xiaoyang Xiao, Junmin Tan, Guangming State Key Laboratory of Computer Architecture Institute of Computing Technology Chinese Academy of Sciences University of Chinese Academy of Science China

ISBN: (纸本)9781450382946

Convolution is the most time-consuming part in the computation of convolutional neural networks (CNNs), which have achieved great successes in numerous practical applications. Due to the complex data dependency and the increase in the amount of model samples, the convolution suffers from high overhead on data movement (i.e., memory access). This work provides comprehensive analysis and methodologies to minimize the communication for the convolution in CNNs. With an in-depth analysis of the recent I/O complexity theory under the red-blue game model, we develop a general I/O lower bound theory for a composite algorithm which consists of several different sub-computations. Based on the proposed theory, we establish the data movement lower bound results for two main convolution algorithms in CNNs, namely the direct convolution and Winograd algorithm, which represents the direct and indirect implementations of a convolution respectively. Next, derived from I/O lower bound results, we design the near I/O-optimal dataflow strategies for the two main convolution algorithms by fully exploiting the data reuse. Furthermore, in order to push the envelope of performance of the near I/O-optimal dataflow strategies further, an aggressive design of auto-tuning based on I/O lower bounds, is proposed to search an optimal parameter configuration for the direct convolution and Winograd algorithm on GPU, such as the number of threads and the size of shared memory used in each thread block. Finally, experiment evaluation results on the direct convolution and Winograd algorithm show that our dataflow strategies with the auto-tuning approach can achieve about 3.32× performance speedup on average over cuDNN. In addition, compared with TVM, which represents the state-of-the-art technique for auto-tuning, not only our auto-tuning method based on I/O lower bounds can find the optimal parameter configuration faster, but also our solution has higher performance than the optimal solution provided

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Statistical static timing analysis for circuit aging prediction

引用

The Journal of China Universities of Posts and Telecommunications 2021年第2期28卷 14-23页

作者： Duan Shengyu Zhai Dongyao Lu Yue Shanghai Engineering Research Center of Intelligent Computing System Shanghai UniversityShanghai 200444China State Key Laboratory of Computer Architecture Institute of Computing TechnologyChinese Academy of SciencesBeijing 100190China School of Electronics and Computer Science University of SouthamptonSouthamptonUK

Complementary metal oxide semiconductor(CMOS)aging mechanisms including bias temperature instability(BTI)pose growing concerns about circuit *** results in threshold voltage increases on CMOS transistors,causing delay shifts and timing violations on logic *** amount of degradation is dependent on the circuit workload,which increases the challenge for accurate BTI aging prediction at the design *** this paper,a BTI prediction method for logic circuits based on statistical static timing analysis(SSTA)is proposed,especially considering the correlation between circuit workload and BTI *** consists of a training phase,to discover the relationship between circuit scale and the required workload samples,and a prediction phase,to present the degradations under different workloads in Gaussian probability *** method can predict the distribution of degradations with negligible errors,and identify 50%more BTI-critical paths in an affordable time,compared with conventional methods.

关键词： bias temperature instability(BTI) reliability prediction statistical static timing analysis(SSTA)

来源：评论

学校读者我要写书评

暂无评论

Multi-View Subspace Clustering Based on Affinity Matrix and Low-rank Tensor Decomposition 7

Multi-View Subspace Clustering Based on Affinity Matrix and ...

引用

7th International Conference on Intelligent Computing and Signal Processing, ICSP 2022

作者： Yu, Yao Du, Shiqiang Zhang, Kaiwu Song, Jinmei Northwest Minzu University College of Mathematics and Computer Science Lanzhou China Northwest Minzu University Key Laboratory of Chinas Ethnic Languages and Information Technology Ministry of Education Chinese National Information Technology Research Institute Lanzhou China

ISBN: (纸本)9781665478571

Subspace clustering is one of the important methods to solve the problem of high-dimensional data clustering, and the performance of traditional methods based on spectral clustering largely depends on the affinity matrix learned directly from the original data or their computational representation. In this paper, we propose multi-view subspace clustering based on affinity matrix and low-rank tensor decomposition (ATMSC) algorithm, which not only constructs a more meaningful affinity matrix but also makes full use of multi-view complementary information and explores high-order correlation. The Alternating Direction Multiplier Method (ADMM) can efficiently find the optimal solution to the problem. Extensive experiments on real datasets show that our method outperforms other state-of-the-art methods. © 2022 IEEE.

关键词： Tensors

来源：评论

学校读者我要写书评

暂无评论

Incomplete Multi-View Clustering Based on Weighted Adaptive Graph Learning 7

Incomplete Multi-View Clustering Based on Weighted Adaptive ...

引用

7th International Conference on Intelligent Computing and Signal Processing, ICSP 2022

作者： Zhang, Kaiwu Song, Jinmei Yu, Yao Du, Shiqiang Chinese National Information Technology Research Institute Key Laboratory of Chinas Ethnic Languages and Information Technology Northwest Minzu University Ministry of Education Lanzhou China Northwest Minzu University College of Mathematics and Computer Science Lanzhou China

ISBN: (纸本)9781665478571

Multi-view clustering methods utilize complementary and consistent information among different views to classify samples into correct clusters. However, traditional multi-view clustering methods are proposed based on complete datasets. In practical applications, complete data samples rarely exist, and incomplete data are more common. This paper proposes an incomplete multi-view clustering algorithm based on weighted adaptive graph learning. Specifically, we first introduce a distance regularization term and integrate it into the framework of low-rank representations to learn graphs with both local and global structure of the data. Then, we use spectral clustering to achieve a low dimensional matrix for each graph. Finally, we use a weighted fusion mechanism to learn a consensus representation, and utilize the K-means algorithm to get the final clustering results. Experimental results on different incomplete datasets demonstrate the effectiveness of the algorithms. © 2022 IEEE.

关键词： Cluster analysis

来源：评论

学校读者我要写书评

暂无评论

Spatial-Temporal Constrained Aircraft Sequencing and Path Planning for Airport Ground Movement Problem 19th

Spatial-Temporal Constrained Aircraft Sequencing and Path P...

引用

19th CCF Conference on computer Supported Cooperative Work and Social Computing, ChineseCSCW 2024

作者： Liu, Fengmei Sun, Jingzhe Zhu, Jie Zhao, Zheng Huang, Huimin School of Computer Science Nanjing University of Posts and Telecommunications Nanjing210023 China The State Key Laboratory Chinese of Computer Architecture Institute of Computing Technology Chinese Academy of Sciences Beijing100864 China Nanjing University of Aeronautics and Astronautics Nanjing210016 China

ISBN: (纸本)9789819623754

In order to effectively alleviate the congestion and delay of aircraft during peak hours in a large hub airport, the paper studies the cooperative scheduling and path planning for arrival and departure aircrafts. A cooperative aircraft scheduling and path planning model for the airport ground movement problem is established with multiple spatial and temporal constraints, such as the queue constraint, time difference constraint, corner constraint. It aims to minimize the average taxiing time for all aircrafts. A genetic algorithm with elite selection strategy (ESGA) is proposed for the problem under study. Experimental results show that the proposed algorithm can effectively obtain the aircraft sequencing and path planning solutions, and significantly reduce the average taxiing time of the aircraft. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Motion planning

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：