检索结果-内蒙古大学图书馆

Smart World Congress (SWC), IEEE

作者： Yuzhen Liu Lei Huang Xiaoliang Wang Yuanyuan Ai Xiaolan Zhou School of Computer Science and Engineering Hunan University of Science and Technology Xiangtan China

ISBN: (数字)9798331520861

ISBN: (纸本)9798331520878

Accurate and swift prediction of surrounding vehicle trajectories is essential for autonomous driving. Currently, numerous methods have achieved excellent accuracy in trajectory prediction but they often overlook the prediction speed. Autonomous vehicles must quickly respond to various situations for safe driving. Therefore, we propose a lightweight model named STLL. We model the interactions among vehicles using a graph that fully considers the spatio-temporal information. Additionally, we represent all lanes by a sequence and employ an efficient method to encode lanes. These approaches effectively enable the model to extract and fuse features of vehicles and lanes, leading to accurate and swift trajectory predictions. We conduct our experiments on the widely recognized real-world trajectory prediction datasets: nuScenes and Argoverse. The results demonstrate that our method not only significantly reduces prediction time and the number of model parameters but also maintains high prediction accuracy.

关键词： Deep learning Accuracy Dynamics Predictive models Feature extraction Trajectory Vehicle dynamics Autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

High Quality Compression and Transmission of Remote Sensing Images Based on Semantic Communication

IEEE Transactions on Sustainable Computing

引用

IEEE Transactions on Sustainable Computing 2025年

作者： Jiang, Yan Xie, Kun Ouyang, Yudian Wen, Jigang Zhang, Guangxing Liang, Wei Feng, Quan Hunan University College of Computer Science and Electronics Engineering Changsha China Hunan University of Science and Technology School of Computer Science and Engineering Xiangtan China Chinese Academy of Sciences Institute of Computing Technology China Hunan Vanguard Group Corporation Limited Changsha China

Remote sensing imagery plays a crucial role in areas such as environmental monitoring and urban planning. However, due to fragile communication links, limited bandwidth and harsh wireless environments, transmitting data from remote locations to ground applications faces the dilemma of high biterror rates, which have a poor impact on downstream missions. Semantic communication is a feasible solution that transmits only the semantic features of the raw data extracted using neural networks. Although effective, existing semantic communication methods cannot cope with high compression rate requirements and complex communication environments. Therefore, in this paper, an effective image compression and transmission framework ASE-JSCC is proposed. To minimize the transmitted data, we design a semantic extraction module and an important feature selection module to efficiently extract, select, and compress critical semantic features required for downstream tasks. To improve the communication robustness of the model in complex environments affected by variable channels, we optimize the source-channel joint coding technique by randomly adding noise with different types and sizes. Finally, we deploy ASE-JSCC to the scene classification task of remote sensing images and conduct extensive experiments on four real datasets, achieving classification accuracy of 84.29% - 88.62% under 384 times compression ratio, verifying the excellent performance of the proposed framework. © 2016 IEEE.

关键词： Image compression

来源：评论

学校读者我要写书评

暂无评论

A study of the inhibitory effect and mechanism of airflow regarding mould on building surfaces

引用

Frontiers of Architectural Research 2024年第5期13卷 1067-1078页

作者： Hongling Zhang Hui Zhang Edward Arens Ling Jin Yingdong He Erxun Zhou Linxuan Zhou Jinhua Hu School of Water Conservancy and Civil Engineering South China Agricultural UniversityGuangzhou 510642China Center for Built Environment University of California BerkeleyCA 94720USA College of Civil Engineering Hunan UniversityChangsha 410082China College of Plant Protection South China Agricultural UniversityGuangzhou 510642China College of Civil Engineering Hunan University of Science and TechnologyXiangtan 411201China

Air movement dries surfaces by increasing evaporation and convection,which may prevent mould *** *** used as the test organism(dominant fungi in the envelope of rural houses in hot summer and warm winter areas),and the effect of fans on inhibiting mould growth on building materials is *** mould growth on materials was simulated and compared after rain leakage and surface condensation,and spore germination was studied in high humidity,with or without *** results are as follows:(1)Airflow has an evident inhibitory effect on mould growth on wet building *** observation was linked to the availability of moisture content in the building materials.(2)Airflow can slow the appearance of visual mould on the material *** did not appear on the gypsum surface due to the airflow,and mould growth on a wood surface was delayed for about two days.(3)Periodically,spore eluates were examined by electron microscopy to determine the stage of spore germination,and it was found that airflow delayed mould spore germination for about 2-3 days.

关键词： Building envelope Mould Airflow Spores Building material

来源：评论

学校读者我要写书评

暂无评论

Advancing Ultrasound Medical Continuous Learning with Task-Specific Generalization and Adaptability

Advancing Ultrasound Medical Continuous Learning with Task-S...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Zhu, Chunzheng Lin, Jianxin Tan, Guanghua Zhu, Ningbo Li, Kenli Wang, Chunlian Li, Shengli Hunan University College of Computer Science and Electronic Engineering Changsha China Hunan University Affiliated Hospital Ultrasound Diagnosis Department Xiangtan China Shenzhen Maternity and Child Healthcare Hospital Department of Ultrasound Shenzhen China

ISBN: (纸本)9798350386226

As artificial intelligence progresses in the field of medical ultrasound image analysis, mitigating catastrophic forgetting during continuous learning processes in disease diagnosis and fetal ultrasound assistance is crucial. Inspired by the significant performance improvements achieved in various downstream visual tasks through advanced visual representations, we introduce a novel approach called Masked Ultrasound Image Modeling (MUIM) to prevent forgetting of new disease diagnosis tasks. In this approach, MUIM initially pre-trains on ultrasound images specific to the current task. By utilizing a masked autoencoder to train on unlabeled ultrasound images, it learns highly abstract representations of task-relevant information. To ensure the model's adaptability to new tasks, we propose contrastive Historical-Current Learning strategy, which enhances the model's ability to retain and integrate knowledge from previous tasks while learning new ones. By incorporating knowledge distillation loss and the exponential moving average (EMA) technique for joint inference and continuously updating new knowledge into the historical expert model, our approach enables the model to adaptively learn new tasks while preventing forgetting of old ones. We conducted extensive experiments on three datasets: the Breast Ultrasound Image dataset (BUSI), the Algeria Thyroid Ultrasound Image dataset (AUITD), and our designed Obstetrics and Gynecology Ultrasound Dataset (USOGD). The results demonstrate that our method significantly reduces the forgetting of old task knowledge while outperforming state-of-the-art methods in classification accuracy. © 2024 IEEE.

关键词： Ultrasonic imaging

来源：评论

学校读者我要写书评

暂无评论

Evolution of defects and deformation mechanisms in different tensile directions of solidified lamellar Ti-Al alloy

引用

Chinese Physics B 2022年第4期31卷 518-524页

作者： Yutao Liu Tinghong Gao Yue Gao Lianxin Li Min Tan Quan Xie Qian Chen Zean Tian Yongchao Liang Bei Wang Institute of New Optoelectronic Materials and Technology College of Big Data and Information EngineeringGuizhou UniversityGuiyang 550025China College of Computer Science and Electronic Engineering Hunan UniversityChangsha 410082China

Two-phaseγ-TiAl/α_(2)-Ti_(3)Al lamellar intermetallics have attracted considerable attention because of their excellent strength and ***,the exact deformation mechanisms remain to be *** this paper,a solidified lamellar Ti-Al alloy with lamellar orientation at 0°,17°,and 73°with respect to the loading direction was stretched by utilizing molecular dynamics(MD)*** results show that the mechanical properties of the sample are considerably influenced by solidified defects and tensile *** structure deformation and fracture were primarily attributed to an intrinsic stacking fault(ISF)accompanied by the nucleated Shockley dislocation,and the adjacent extrinsic stacking fault(ESF)and ISF formed by solidification tend to form large HCP structures during the tensile process loading at 73°.Moreover,cleavage cracking easily occurs on theγ/α_(2)interface under tensile *** fracture loading mechanism at 17°is grain boundary slide whereas,at 73°and 0°,the dislocation piles up to form a dislocation junction.

关键词： molecular dynamics simulation solidified lamellar Ti-Al alloy tensile directions γ/α_(2)interface

来源：评论

学校读者我要写书评

暂无评论

Analysis and Research on BOX64's Core Technologies for Cross-Architecture Software Migration

Analysis and Research on BOX64's Core Technologies for Cross...

引用

2023 International Conference on Frontiers of Robotics and Software engineering, FRSE 2023

作者： Zhang, Jin Shan, Zehu Liu, Xiaodong Wang, Wenzhu Li, Zhuoheng Peng, Long Yu, Jie Hunan Normal University College of Computer and Communication Engineering Changsha University of Science and Technology College of Information Science and Engineering Changsha China Hunan Normal University College of Information Science and Engineering Changsha China National University of Defense Technology College of Computer Science Changsha China Haihe Lab of Itai Tianjin China Kylin Software Tianjin China

ISBN: (纸本)9798350301113

In the current context of increasingly diverse processor architectures and complex application requirements, how to seamlessly migrate software written for specific architectures (such as X86) to other architectures (such as ARM) has become a critical and urgent issue to resolve. This research primarily explores the key roles of WRAPPER and Dynarec technologies in this process. WRAPPER technology encapsulates the library function calls and system calls of X86_64 Linux programs, enabling them to run seamlessly and efficiently on the ARM64 Linux platform, thereby achieving cross-architecture software compatibility. Dynamic recompilation technology, on the other hand, can dynamically convert the binary code of the source architecture into the binary code of the target architecture during runtime, further enhancing program performance. Through in-depth theoretical analysis and empirical testing, the research team has found that there is still potential for optimization in these two technologies regarding library function calls and memory management. The team conducted a comprehensive theoretical analysis and evaluation of possible optimization strategies, expecting to further improve software performance on non-X86_64 architecture platforms through the implementation of these strategies. This has practical research value for the development and porting of software on non-X86_64 architecture platforms. © 2023 IEEE.

关键词： Binary codes

来源：评论

学校读者我要写书评

暂无评论

Unveiling the high ductility-strength mechanism induced by honeycomb dislocations and dispersed vacancies in 7A52- DCI4 aluminum alloy

引用

Journal of Materials science and technology 2025年 229卷 196-202页

作者： Liu, Wenhui Zhang, Lingji Ye, Fan Liu, Xiao Song, Yufeng Li, Weirong He, Donglei Yue, Xiaoming Wu, Jianzhao School of Marine Equipment and Mechanical Engineering Jimei University Xiamen361021 China College of Mechanical and Electrical Engineering Hunan University of Science and Technology Xiangtan411201 China Dongguan Eontec Co. Ltd Dongguan523662 China Department of Mechanical Engineering Tsinghua University Beijing100084 China

A novel deep cryogenic-interrupted aging treatment (DCI4) was developed to enhance mechanical properties, improve productivity, and reduce energy consumption. Compared to the T6I4PRE sample, the cryogenic treatment introduced unique honeycomb dislocations at the grain boundaries in DCT1h, which provided nucleation sites for precipitates and inhibited the formation of precipitation-free zones (PFZ) during subsequent aging. Additionally, the high dislocation density and dispersed vacancy induced by cryogenic treatment increased the number of nucleation sites and enhanced the driving force for precipitation. This resulted in denser/finer precipitates and a reduction in aging time for the DCI4 sample. As a result, the ultimate tensile strength (UTS) and elongation (EL) of the 7A52-DCI4 aluminum alloy were simultaneously improved, while the aging treatment time was reduced by 51 % compared to the T6I4 sample. This approach offers a promising strategy for the development of age-hardening aluminum alloys. © 2025

关键词： Copper alloys

来源：评论

学校读者我要写书评

暂无评论

SCENERY:a lightweight block cipher based on Feistel structure

引用

Frontiers of computer science 2022年第3期16卷 193-202页

作者： Jingya FENG Lang LI Hunan Provincial Key Laboratory of Intelligent Information Processing and Application Hengyang Normal UniversityHengyang 421002China College of Information Science and Engineering Hunan Normal UniversityChangsha 410081China College of Computer Science and Technology Hengyang Normal UniversityHengyang 421002China

In this paper,we propose a new lightweight block cipher called *** main purpose of SCENERY design applies to hardware and software *** is a 64-bit block cipher supporting 80-bit keys,and its data processing consists of 28 *** round function of SCENERY consists of 84×4 S-boxes in parallel and a 32× 32 binary matrix,and we can implement SCENERY with some basic logic *** hardware implementation of SCENERY only requires 1438 GE based on 0.18 um CMOS technology,and the software implementation of encrypting or decrypting a block takes approximately 1516 clock cycles 0118-bit microcontrollers and 364 clock cycles on 64-bit *** with other encryption algorithms,the performance of SCENERY is well balanced for both hardware and *** the security analyses,SCENERY can achieve enough security margin against known attacks,such as differential cryptanalysis,linear cryptanalysis,impossible differential cryptanalysis and related-key attacks.

关键词： lightweight block cipher feistel structure cryptanalysis internet of things

来源：评论

学校读者我要写书评

暂无评论

Side-channel analysis attacks based on deep learning network

引用

Frontiers of computer science 2022年第2期16卷 35-45页

作者： Yu OU Lang LI Hunan Provincial Key Laboratory of Intelligent Information Processing and Application Hengyang Normal UniversityHengyang 421002China College of Information Science and Engineering Hunan Normal UniversityChangsha 410081China College of Computer Science and Technology Hengyang Normal UniversityHengyang 421002China

There has been a growing interest in the sidechannel analysis(SCA)field based on deep learning(DL)*** DL network or model has been developed to improve the efficiency of ***,few studies have investigated the impact of the different models on attack results and the exact relationship between power consumption traces and intermediate *** on the convolutional neural network and the autoencoder,this paper proposes a Template Analysis Pre-trained DL Classification model named TAPDC which contains three *** TAPDC model detects the periodicity of power trace,relating power to the intermediate values and mining the deeper features by the multi-layer convolutional *** implement the TAPDC model and compare it with two classical models in a fair *** evaluative results show that the TAPDC model with autoencoder and deep convolution feature extraction structure in SCA can more effectively extract information from power consumption ***,Using the classifier layer,this model links power information to the probability of intermediate *** completes the conversion from power trace to intermediate values and greatly improves the efficiency of the power attack.

关键词： side-channel analysis template attack machine learning deep learning

来源：评论

学校读者我要写书评

暂无评论

Rucklidge-based memristive chaotic system:Dynamic analysis and image encryption

引用

Chinese Physics B 2023年第10期32卷 298-309页

作者：蹇璨岭田泽安梁波胡晨阳王桥陈靖翕 College of Big Data and Information Engineering Guizhou UniversityGuiyang 550025China College of Computer Science and Electronic Engineering Hunan UniversityChangsha 410082China College of Mathematics and Big Data Guizhou Education UniversityGuiyang 550018China College of Mechanical Engineering Guizhou UniversityGuiyang 550025China

A new four-dimensional(4D)memristive chaotic system is obtained by introducing a memristor into the Rucklidge chaotic system,and a detailed dynamic analysis of the system is *** sensitivity of the system to parameters allows it obtains 16 different attractors by changing only one *** various transient behaviors and excellent spectral entropy and C0 complexity values of the system can also reflect the high complexity of the system.A circuit is designed and verified the feasibility of the system from the physical ***,the system is applied to image encryption,and the security of the encryption system is analyzed from multiple aspects,providing a reference for the application of such memristive chaotic systems.

关键词： chaotic system memristor intermittent chaos multi-transient behavior image encryption

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：