检索结果-内蒙古大学图书馆

TSCompiler: efficient compilation framework for dynamic-shape models

science China(Information sciences) 2024年第10期67卷 67-84页

作者： Xiang LUO Chen ZHANG Chenbo GENG Yanzhi YI Jiahui HU Renwei ZHANG Zhen ZHANG Gianpietro CONSOLARO Fan YANG Tun LU Ning GU Li SHANG School of Computer Science Fudan University School of Electronic Information and Electrical Engineering Shanghai Jiao Tong University School of Computer Science and Technology Harbin Institute of Technology Huawei Technologies Co. Ltd. Huawei Paris Research Center School of Microelectronics Fudan University

Today's deep learning models face an increasing demand to handle dynamic shape tensors and computation whose shape information remains unknown at compile time and varies in a nearly infinite range at runtime. This shape dynamism brings tremendous challenges for existing compilation pipelines designed for static models which optimize tensor programs relying on exact shape values. This paper presents TSCompiler, an end-to-end compilation framework for dynamic shape models. TSCompiler first proposes a symbolic shape propagation algorithm to recover symbolic shape information at compile time to enable subsequent optimizations. TSCompiler then partitions the shape-annotated computation graph into multiple subgraphs and fine-tunes the backbone operators from the subgraph within a hardware-aligned search space to find a collection of high-performance schedules. TSCompiler can propagate the explored backbone schedule to other fusion groups within the same subgraph to generate a set of parameterized tensor programs for fused cases based on dependence analysis. At runtime, TSCompiler utilizes an occupancy-targeted cost model to select from pre-compiled tensor programs for varied tensor shapes. Extensive evaluations show that TSCompiler can achieve state-of-the-art speedups for dynamic shape models. For example, we can improve kernel efficiency by up to 3.97× on NVIDIA RTX3090, and 10.30× on NVIDIA A100 and achieve up to five orders of magnitude speedups on end-to-end latency.

关键词： machine learning tensor compilers dynamic shape operator fusion code generation auto-tuning

来源：评论

学校读者我要写书评

暂无评论

Secure Transmission Scheme for Blocks in Blockchain-Based Unmanned Aerial Vehicle Communication Systems

引用

computers, Materials & Continua 2024年第11期81卷 2195-2217页

作者： Ting Chen Shuna Jiang Xin Fan Jianchuan Xia Xiujuan Zhang Chuanwen Luo Yi Hong School of Computer Science and Engineering University of Electronic Science and Technology of ChinaChengdu611731China School of Computer Science Qufu Normal UniversityRizhao276826China School of Information Science and Technology Beijing Forestry UniversityBeijing100083China

In blockchain-based unmanned aerial vehicle(UAV)communication systems,the length of a block affects the performance of the *** transmission performance of blocks in the form of finite character segments is also affected by the block ***,it is crucial to balance the transmission performance and blockchain performance of blockchain communication systems,especially in wireless environments involving *** paper investigates a secure transmission scheme for blocks in blockchain-based UAV communication systems to prevent the information contained in blocks from being completely eavesdropped during *** our scheme,using a friendly jamming UAV to emit jamming signals diminishes the quality of the eavesdropping channel,thus enhancing the communication security performance of the source *** the constraints of maneuverability and transmission power of the UAV,the joint design of UAV trajectories,transmission power,and block length are proposed to maximize the average minimum secrecy rate(AMSR).Since the optimization problem is non-convex and difficult to solve directly,we first decompose the optimization problem into subproblems of trajectory optimization,transmission power optimization,and block length ***,based on firstorder approximation techniques,these subproblems are reformulated as convex optimization ***,we utilize an alternating iteration algorithm based on the successive convex approximation(SCA)technique to solve these subproblems *** simulation results demonstrate that our proposed scheme can achieve secure transmission for blocks while maintaining the performance of the blockchain.

关键词： Unmanned aerial vehicles blockchain finite blocklength block transmission alternating optimization

来源：评论

学校读者我要写书评

暂无评论

Augmented FCN: rethinking context modeling for semantic segmentation

引用

science China(Information sciences) 2023年第4期66卷 193-211页

作者： Dong ZHANG Liyan ZHANG Jinhui TANG School of Computer Science and Engineering Nanjing University of Science and Technology College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics

The effectiveness of modeling contextual information has been empirically shown in numerous computer vision tasks. In this paper, we propose a simple yet efficient augmented fully convolutional network(AugFCN) by aggregating content-and position-based object contexts for semantic ***, motivated because each deep feature map is a global, class-wise representation of the input,we first propose an augmented nonlocal interaction(AugNI) to aggregate the global content-based contexts through all feature map interactions. Compared to classical position-wise approaches, AugNI is more efficient. Moreover, to eliminate permutation equivariance and maintain translation equivariance, a learnable,relative position embedding branch is then supportably installed in AugNI to capture the global positionbased contexts. AugFCN is built on a fully convolutional network as the backbone by deploying AugNI before the segmentation head network. Experimental results on two challenging benchmarks verify that AugFCN can achieve a competitive 45.38% mIoU(standard mean intersection over union) and 81.9% mIoU on the ADE20K val set and Cityscapes test set, respectively, with little computational overhead. Additionally, the results of the joint implementation of AugNI and existing context modeling schemes show that AugFCN leads to continuous segmentation improvements in state-of-the-art context modeling. We finally achieve a top performance of 45.43% mIoU on the ADE20K val set and 83.0% mIoU on the Cityscapes test set.

关键词： semantic segmentation context modeling long-range dependencies attention mechanism

来源：评论

学校读者我要写书评

暂无评论

Progress on the Fault Diagnosis Approach for Lithium-ion Battery Systems:Advances,Challenges,and Prospects

引用

Protection and Control of Modern Power Systems 2024年第5期9卷 16-41页

作者： Hanxiao Liu Luan Zhang Liwei Li School of Control Science and Engineering Shandong UniversityJinan 250061China School of Computer Science and Technology Shandong UniversityQingdao 266237China

Because of their advantages of high energy and power density,low self-discharge rate,and long lifespan,lithium-ion batteries(LIBs)have been widely used in many applications such as electric vehicles,energy storage systems,smart grids,***,lithium-ion battery systems(LIBSs)frequently malfunction because of complex working conditions,harsh operating environment,battery inconsistency,and inherent defects in battery ***,safety of LIBSs has become a prominent problem and has attracted wide ***,efficient and accurate fault diagnosis for LIBs is very *** paper provides a comprehensive review of the latest research progress in fault diagnosis for ***,the types of battery faults are comprehensively introduced and the characteristics of each fault are ***,the fault diagnosis methods are systematically elaborated,including model-based,data processing-based,machine learning-based and knowledge-based *** latest research is discussed and existing issues and challenges are presented,while future developments are also *** aim is to promote further researches into efficient and advanced fault diagnosis methods for more reliable and safer LIBs.

关键词： Battery management system battery safety fault diagnosis lithiumion battery system

来源：评论

学校读者我要写书评

暂无评论

Inductive Lottery Ticket Learning for Graph Neural Networks

引用

Journal of computer science & Technology 2024年第6期39卷 1223-1237页

作者： Yong-Duo Sui Xiang Wang Tianlong Chen Meng Wang Xiang-Nan He Tat-Seng Chua School of Data Science University of Science and Technology of ChinaHefei 230027China Department of Electrical and Computer Engineering The University of Texas at AustinAustin 78712U.S.A School of Computer Science and Information Engineering Hefei University of TechnologyHefei 230009China School of Computing National University of SingaporeSingapore

Graph neural networks (GNNs) have gained increasing popularity, while usually suffering from unaffordable computations for real-world large-scale applications. Hence, pruning GNNs is of great need but largely unexplored. The recent work Unified GNN Sparsification (UGS) studies lottery ticket learning for GNNs, aiming to find a subset of model parameters and graph structures that can best maintain the GNN performance. However, it is tailed for the transductive setting, failing to generalize to unseen graphs, which are common in inductive tasks like graph classification. In this work, we propose a simple and effective learning paradigm, Inductive Co-Pruning of GNNs (ICPG), to endow graph lottery tickets with inductive pruning capacity. To prune the input graphs, we design a predictive model to generate importance scores for each edge based on the input. To prune the model parameters, it views the weight’s magnitude as their importance scores. Then we design an iterative co-pruning strategy to trim the graph edges and GNN weights based on their importance scores. Although it might be strikingly simple, ICPG surpasses the existing pruning method and can be universally applicable in both inductive and transductive learning settings. On 10 graph-classification and two node-classification benchmarks, ICPG achieves the same performance level with 14.26%–43.12% sparsity for graphs and 48.80%–91.41% sparsity for the GNN model.

关键词： lottery ticket hypothesis graph neural networks neural network pruning

来源：评论

学校读者我要写书评

暂无评论

A Transfer Function Design for Medical Volume Data Using a Knowledge Database Based on Deep Image and Primitive Intensity Profile Features Retrieval

引用

Journal of computer science & Technology 2024年第2期39卷 320-335页

作者： Younhyun Jung Jim Kong 盛斌 Jinman Kim School of Computing Gachon UniversitySeongnam 13120Korea School of Computer Science The University of SydneySydney 2006Australia Department of Computer Science and Engineering Shanghai Jiao Tong UniversityShanghai 200240China

Direct volume rendering(DVR)is a technique that emphasizes structures of interest(SOIs)within a volume visually,while simultaneously depicting adjacent regional information,e.g.,the spatial location of a structure concerning its *** DVR,transfer function(TF)plays a key role by enabling accurate identification of SOIs interactively as well as ensuring appropriate visibility of *** generation typically involves non-intuitive trial-and-error optimization of rendering parameters,which is time-consuming and *** at mitigating this manual process have led to approaches that make use of a knowledge database consisting of pre-designed TFs by domain *** these approaches,a user navigates the knowledge database to find the most suitable pre-designed TF for their input volume to visualize the *** these approaches potentially reduce the workload to generate the TFs,they,however,require manual TF navigation of the knowledge database,as well as the likely fine tuning of the selected TF to suit the *** this work,we propose a TF design approach,CBR-TF,where we introduce a new content-based retrieval(CBR)method to automatically navigate the knowledge *** of pre-designed TFs,our knowledge database contains volumes with SOI *** an input volume,our CBR-TF approach retrieves relevant volumes(with SOI labels)from the knowledge database;the retrieved labels are then used to generate and optimize TFs of the *** approach largely reduces manual TF navigation and fine *** our CBR-TF approach,we introduce a novel volumetric image feature which includes both a local primitive intensity profile along the SOIs and regional spatial semantics available from the co-planar images to the *** the regional spatial semantics,we adopt a convolutional neural network to obtain high-level image feature *** the intensity profile,we extend the dynamic time warping technique to address subtle alignment

关键词： data retrieval direct volume rendering ray analysis transfer function

来源：评论

学校读者我要写书评

暂无评论

Modified Bat Algorithm: a newly proposed approach for solving complex and real-world problems

引用

Soft Computing 2024年第13-14期28卷 7983-7998页

作者： Umar, Shahla U. Rashid, Tarik A. Ahmed, Aram M. Hassan, Bryar A. Baker, Mohammed Rashad Department of Software College of Computer Science and Information Technology University of Kirkuk Kirkuk Iraq Computer Science and Engineering Department School of Science and Engineering University of Kurdistan Hewler KRI Erbil Iraq Department of Computer Science College of Science Charmo University Sulaimani Chamchamal46023 Iraq

Bat Algorithm (BA) is a nature-inspired metaheuristic search algorithm designed to efficiently explore complex problem spaces and find near-optimal solutions. The algorithm is inspired by the echolocation behavior of bats, which acts as a signal system to estimate the distance and hunt prey. Although the BA has proven effective for various optimization problems, it exhibits limited exploration ability and susceptibility to local optima. The algorithm updates velocities and positions based on the current global best solution, causing all agents to converge toward a specific location, potentially leading to local optima issues in optimization problems. On this premise, this paper proposes the Modified Bat Algorithm (MBA) as an enhancement to address the local optima limitation observed in the original BA. MBA incorporates the frequency and velocity of the current best solution, enhancing convergence speed to the optimal solution and preventing local optima entrapment. While the original BA faces diversity issues, both the original BA and MBA are introduced. To assess MBA’s performance, three sets of test functions (classical benchmark functions, CEC2005, and CEC2019) are employed, with results compared to those of the original BA, Particle Swarm Optimization (PSO), Genetic Algorithm (GA), and Dragonfly Algorithm (DA). The outcomes demonstrate the MBA’s significant superiority over other algorithms. In addition, MBA successfully addresses a real-world assignment problem (call center problem), traditionally solved using linear programming methods, with satisfactory results. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2024.

关键词： Swarm intelligence

来源：评论

学校读者我要写书评

暂无评论

Heterologous Image Matching Based on Salience Region

IAENG International Journal of Computer Science

引用

IAENG International Journal of computer science 2025年第4期52卷 894-900页

作者： Zhai, Jinlong Xu, Yang Yan, Xiaohu Computer Science and Software Engineering University of Science and Technology LiaoNing Anshan114051 China School of Computer Science and Software Engineering University of Science and Technology LiaoNing Anshan114051 China Institute of Applied Artificial Intelligence of the Guangdong-Hong Kong-Macao Greater Bay Area Shenzhen Polytechnic University Shenzhen518055 China

To address the matching problem caused by the significant differences in spatial features, spectrum and contrast between heterologous images, a heterologous image matching method based on salience region is proposed in this paper. Firstly, texture features and corner features are detected. Secondly, the epanechnikov kernel function is used to calculate the point with the maximum kernel function value among all feature points, which is then defined as E-point. Thirdly, the salience region is defined and extracted according to the position of the E-point. Finally, six groups of heterologous images are used as data sources, and compared with HAPCG, HOWP, SIFT, and PSO_SIFT algorithms respectively. The results show that the comprehensive matching performance of the proposed method is better than the original algorithm without salience region processing. The root mean square error and the matching time are less than the original method while ensuring a similar number of matching points, which greatly improves the accuracy and speed of heterologous image matching. © (2025.0), (International Association of Engineers). All Rights Reserved.

关键词： Image matching

来源：评论

学校读者我要写书评

暂无评论

DIEONet:Domain-Invariant Information Extraction and Optimization Network for Visual Place Recognition

引用

computers, Materials & Continua 2025年第3期82卷 5019-5033页

作者： Shaoqi Hou Zebang Qin Chenyu Wu Guangqiang Yin Xinzhong Wang Zhiguo Wang School of Computer Science and Technology Xinjiang UniversityUrumqi830046China School of Information and Software Engineering University of Electronic Science and Technology ofChinaChengdu611731China Institute of Public Security Kash Institute of Electronics and Information IndustryKashi844000China

Visual Place Recognition(VPR)technology aims to use visual information to judge the location of agents,which plays an irreplaceable role in tasks such as loop closure detection and *** is well known that previous VPR algorithms emphasize the extraction and integration of general image features,while ignoring the mining of salient features that play a key role in the discrimination of VPR *** this end,this paper proposes a Domain-invariant Information Extraction and Optimization Network(DIEONet)for *** core of the algorithm is a newly designed Domain-invariant Information Mining Module(DIMM)and a Multi-sample Joint Triplet Loss(MJT Loss).Specifically,DIMM incorporates the interdependence between different spatial regions of the feature map in the cascaded convolutional unit group,which enhances the model’s attention to the domain-invariant static object *** Loss introduces the“joint processing of multiple samples”mechanism into the original triplet loss,and adds a new distance constraint term for“positive and negative”samples,so that the model can avoid falling into local optimum during *** demonstrate the effectiveness of our algorithm by conducting extensive experiments on several authoritative *** particular,the proposed method achieves the best performance on the TokyoTM dataset with a Recall@1 metric of 92.89%.

关键词： Visual place recognition domain-invariant information mining module multi-sample joint triplet loss

来源：评论

学校读者我要写书评

暂无评论

BA-GNN: Behavior-aware graph neural network for session-based recommendation

引用

Frontiers of computer science 2023年第6期17卷 135-144页

作者： Yongquan LIANG Qiuyu SONG Zhongying ZHAO Hui ZHOU Maoguo GONG School of Computer Science and Engineering Shandong University of Science and TechnologyQingdao 266590China School of Electronic Engineering Xidian UniversityXi’an 710071China

Session-based recommendation is a popular research topic that aims to predict users’next possible interactive item by exploiting anonymous *** existing studies mainly focus on making predictions by considering users’single interactive *** recent efforts have been made to exploit multiple interactive behaviors,but they generally ignore the influences of different interactive behaviors and the noise in interactive *** address these problems,we propose a behavior-aware graph neural network for session-based ***,different interactive sequences are modeled as directed ***,the item representations are learned via graph neural ***,a sparse self-attention module is designed to remove the noise in behavior ***,the representations of different behavior sequences are aggregated with the gating mechanism to obtain the session *** results on two public datasets show that our proposed method outperforms all competitive *** source code is available at the website of GitHub.

关键词： session-based recommendation multiple interactive behaviors graph neural networks

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：