检索结果-内蒙古大学图书馆

3rd International Conference on Internet of Everything, IoECon 2024

作者： Zhou, Kexing Chen, Juan College of Computer Science and Technology National University of Defense Technology Hunan410073 China

ISBN: (纸本)9783031844256

In today’s computing power era, AI model training, weather forecasting, aircraft design, and so on are inseparable from parallel computing. Parallel computing is everywhere. However, effectively tackling parallel computing tasks in real-world applications demands a deep connection of devices, people, processes, and data. This notion aligns with the core principle of the Internet of Everything (IoE), which posits that connections generate value. Moreover, the continuing flourish of IoE relies on the parallel computing. This paper aims to reveal the connection and interaction between the IoE and parallel computing. It provides an overview of their development and outlines the profound influence of IoE on parallel computing. The three primary communication channels of IoE—people-to-people (P2P), machine-to-machine (M2M), and people-to-machine (P2M)—are embodied in parallel computing. The potential is substantial to research and develop IoE and parallel computing in years to come, and combining them will navigate multi-domain requirements. © ICST Institute for computer sciences, Social Informatics and Telecommunications engineering 2025.

关键词： Weather forecasting

来源：评论

学校读者我要写书评

暂无评论

Using the Internet of Everything for Machine-Learning-Based computer System Design and Optimization 3rd

Using the Internet of Everything for Machine-Learning-Based ...

引用

3rd International Conference on Internet of Everything, IoECon 2024

作者： Feng, Shaojun Zhong, Jiaqing Chen, Juan College of Computer Science and Technology National University of Defense Technology Hunan410073 China

ISBN: (纸本)9783031844256

Machine learning (ML) has been widely used in computer system development and optimization levels, boosting computer design and optimization improvement. With the increase of computer system design complexity and the boost of the demand for software and application optimization, the difficulties of computer system problem solving are increasing, stimulating the development of ML methods. ML models represent computer system design and development approaches;combining these with the Internet of Everything (IoE) cannot be ignored. For ML models, all kinds of computer system sample data are the fundamental prerequisite for quantifying the computer system characteristics;the connection (internet) of all computer devices is critical for predicting computer system behaviors. The IoE enables more computer devices and ML models to be connected, extending how computer systems can be well developed. The IoE will affect the applications between computer system development and various ML models more deeply by connecting people, data, and machines. This work provides an overview of the history of the IoE and ML-based computer system development. It shows the interaction between ML models and computer system design and optimization. It also emphasizes the people-to-people (P2P), people-to-machine (P2M), and machine-to-machine (M2M) in the ML-based computer system design and optimization. It discusses the interpretability of ML-based computer system development. © ICST Institute for computer sciences, Social Informatics and Telecommunications engineering 2025.

关键词： Application programs

来源：评论

学校读者我要写书评

暂无评论

DATDM: Dynamic attention transformer diffusion model for underwater image enhancement

引用

Alexandria engineering Journal 2025年 126卷 591-604页

作者： Hu, Wang Chen, Shitu Luo, Tuyan Zhang, Lijun Zhang, Hongjin Liu, Zhixiang Zhang, Shiwen Xu, Jingxiang College of Engineering Science and Technology Shanghai Ocean University Shanghai201306 China Institute of Agricultural Quality Standards and Testing Technology Fujian Academy of Agricultural Sciences Fuzhou350003 China Shanghai Engineering Research Center of Marine Renewable Energy Shanghai201306 China College of Information Technology Shanghai Ocean University Shanghai201306 China School of Computer Science and Engineering Hunan University of Science and Technology Xiangtan411201 China

Underwater image degradation presents complex challenges, significantly impairing the efficiency of underwater tasks. The mainstream underwater image enhancement (UIE) methods are roughly divided into traditional physics-based and data-driven deep-learning methods. However, physical model-based methods have poor generalization capabilities. Data-driven methods require high-quality training data and suffer from limited model stability. We propose a novel UIE framework, DATDM, to address the above limitations and improve degraded underwater images. We first introduce a color correction module (CCM) to strengthen the model's image restoration capabilities. On the other hand, we propose a novel dynamic attention transformer (DAT) denoising network with excellent performance. The proposed DAT denoising network utilizes a dynamic attention transformer mechanism that adaptively extracts feature information based on the complexity of the feature map, effectively capturing rich features while optimizing computational efficiency. The proposed DATDM method significantly outperforms the existing state-of-the-art methods, with peak signal-to-noise ratios of 24.05 and 27.39 and structural similarity index measures of 0.9233 and 0.9504 on the UIEB and LSUI datasets, respectively. The final experiments demonstrate that our DATDM achieves better performance and visual effects on UIE tasks. © 2025 The Authors

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

In-Memory Computing Accelerator for Iterative Linear Algebra Solvers

IEEE Computer Architecture Letters

引用

IEEE computer Architecture Letters 2025年第1期24卷 161-164页

作者： Liu, Rui Li, Zerun Zhang, Xiaoyu Chen, Xiaoming Han, Yinhe Tang, Minghua Xiangtan University School of Materials Science and Engineering Hunan China Chinese Academy of Sciences Institute of Computing Technology Beijing China University of Chinese Academy of Sciences Beijing100190 China

Iterative linear solvers are a crucial kernel in many numerical analysis problems. The performance and energy efficiency of iterative solvers based on traditional architectures are severely constrained by the memory wall bottleneck. Computing-in-memory (CIM) has the potential to enhance solving efficiency. Existing CIM architectures are mostly customized for specific algorithms and primarily focus on handling fixed-point operations, which makes them difficult to meet the demands of diverse and high-precision applications. In this work, we propose a CIM architecture that natively supports various iterative linear solvers based on floating-point operations. We develop a new instruction set for the accelerator, which can be flexibly combined to implement various iterative solvers. The evaluation results show that, compared with the GPU implementation, our accelerator achieves more than 10.1× speedup and 6.8× energy savings when executing different iterative solvers. © 2002-2011 IEEE.

关键词： Fixed point arithmetic

来源：评论

学校读者我要写书评

暂无评论

VmPTP: Precise Time Protocol for Inter-VM Communication in Embedded Virtualized Systems

引用

IEEE Transactions on computer-Aided Design of Integrated Circuits and Systems 2025年第3期44卷 897-910页

作者： Zhao, Sirong Xie, Guoqi Ma, Wenhong Ren, Wei Li, Kenli Hunan University Key Laboratory for Embedded and Network Computing of Hunan Province College of Computer Science and Electronic Engineering Hunan Changsha410082 China Huawei Technology Co. Ltd. Central Software Institute Guangdong Shenzhen518129 China

System virtualization techniques are gradually applied to embedded systems with the performance improvement of embedded devices;however, there is a large time offset (i.e., deviation) of hundreds of ms between virtual machines (VMs) due to the drift of the virtualization abstraction layer and the jitter phenomenon. It is urgent to significantly reduce this offset by time synchronization techniques. Unfortunately, the current mainstream time synchronization software (e.g., Chrony and LinuxPTP) cannot be used in the embedded virtualized system connected by the fieldbus, such as controller area network (CAN);meanwhile, drift correction-based time synchronization techniques dedicated to CAN bus cannot be utilized for virtualized systems. In this study, we design a general vmPTP, which is a precise time protocol (PTP) for inter-VM communication in embedded virtualized systems based on Linux kernel-based VM (KVM). This is the first time synchronization work focused on embedded virtualized systems. We implement two vmPTP versions based on VirtIO and inter-VM shared memory (IVSHMEM) according to the four message (i.e., packet) exchanges of PTP. We propose an asymmetry compensation strategy to solve the problem of asymmetric rate of I/O operations in the message exchange process, which optimizes the offset computation. We further produce a convergence stopping approach which can continuously converge the offset until the offset is within the given bound and stop. We conduct experimental evaluations on both X86-64 and ARM64 architectures. For two versions of vmPTP, the experimental results show that: 1) the offsets are always within 1μ s on two architectures;2) the offsets are less than that of LinuxPTP and Chrony;and 3) the vmPTP's CPU and memory utilization on the X86-64 architecture are merely 0.3% and 0.1%, respectively, whereas those on the ARM64 architecture are 3.8% and 0.1%, respectively. We experiment with vmPTP in real-time application and the result demonstrates th

关键词： Linux

来源：评论

学校读者我要写书评

暂无评论

A lightweight deep learning model with knowledge distillation for pulmonary diseases detection in chest X-rays

引用

Multimedia Tools and Applications 2025年第15期84卷 14885-14913页

作者： Asham, Mohammed A. Al-Shargabi, Asma A. Al-Sabri, Raeed Meftah, Ibrahim School of Computer Science and Engineering Central South University Hunan Changsha410083 China Department of Information Technology Collage of Computer Qassim University Buraydah51452 Saudi Arabia College of Mechanical and Electrical Engineering Central South University Changsha410017 China

Accurate and timely diagnosis of pulmonary diseases is critical in the field of medical imaging. While deep learning models have shown promise in this regard, the current methods for developing such models often require extensive computing resources and complex procedures, rendering them impractical. This study focuses on the development of a lightweight deep-learning model for the detection of pulmonary diseases. Leveraging the benefits of knowledge distillation (KD) and the integration of the ConvMixer block, we propose a novel lightweight student model based on the MobileNet architecture. The methodology begins with training multiple teacher model candidates to identify the most suitable teacher model. Subsequently, KD is employed, utilizing the insights of this robust teacher model to enhance the performance of the student model. The objective is to reduce the student model's parameter size and computational complexity while preserving its diagnostic accuracy. We perform an in-depth analysis of our proposed model's performance compared to various well-established pre-trained student models, including MobileNetV2, ResNet50, InceptionV3, Xception, and NasNetMobile. Through extensive experimentation and evaluation across diverse datasets, including chest X-rays of different pulmonary diseases such as pneumonia, COVID-19, tuberculosis, and pneumothorax, we demonstrate the robustness and effectiveness of our proposed model in diagnosing various chest infections. Our model showcases superior performance, achieving an impressive classification accuracy of 97.92%. We emphasize the significant reduction in model complexity, with 0.63 million parameters, allowing for efficient inference and rapid prediction times, rendering it ideal for resource-constrained environments. Outperforming various pre-trained student models in terms of overall performance and computation cost, our findings underscore the effectiveness of the proposed KD strategy and the integration of the Conv

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

Combining intrinsic and sliding-induced polarizations for multistates in two-dimensional ferroelectrics

引用

Physical Review B 2025年第8期111卷 L081407-L081407页

作者： Chuhan Tang Zhiqiang Tian Tao Ouyang Anlian Pan Mingxing Chen Key Laboratory for Matter Microstructure and Function of Hunan Province Key Laboratory of Low-Dimensional Quantum Structures and Quantum Control of Ministry of Education School of Physics and Electronics Hunan Normal University Changsha 410081 China Hunan Key Laboratory for Micro-Nano Energy Materials and Device and School of Physics and Optoelectronics Xiangtan University Hunan Xiangtan 411105 China Key Laboratory for Micro-Nano Physics and Technology of Hunan Province College of Materials Science and Engineering Hunan University Changsha 410082 China State Key Laboratory of Powder Metallurgy Central South University Changsha 410083 China

Going beyond the bistability paradigm of the charge polarization in ferroelectrics is highly desired for ferroelectric (FE) memory devices toward ultrahigh-density information storage. Here, we propose to build multistates by combining the intrinsic and sliding-induced polarizations. The physics is that there is at least one order of magnitude difference in the energy barriers between these two types of polarizations, which leads to a significant difference in the electric fields for reversing the polarization. This difference, along with the symmetry breaking, allows for a unique flipping mechanism involving layer-by-layer sliding followed by layer-by-layer flipping during the transformation of the multistates. As a result, six and ten switchable states can be achieved for the 1T″ bilayers and trilayers, respectively. We further illustrate the concept in H-stacking bilayers and trilayers of 1T″ transition-metal dichalcogenides by first-principles calculations. Our study provides a route to design polarization multistates for developing next-generation memory devices.

关键词： Ferroelectricity

来源：评论

学校读者我要写书评

暂无评论

TransRain: A Hybrid Deep Learning and Image Registration Approach for Accurate Satellite Precipitation Estimation with Ground-Based Validation 4

TransRain: A Hybrid Deep Learning and Image Registration App...

引用

4th International Computational Imaging Conference, CITA 2024

作者： Guo, Yanan Cao, Xiaoqun Zhou, Mengge College of Computer Science National University of Defense Technology Hunan Changsha China College of Meteorology and Oceanography National University of Defense Technology Hunan Changsha China

ISBN: (纸本)9781510688834

To make full use of multi-source precipitation observation information and to solve the current problem of low accuracy of precipitation estimation using satellite images, a new satellite precipitation estimation method is proposed. In this study, we construct a new image registration algorithm based on Transformer and convolutional neural network to fuse rain gauge measurements with satellite image data to reduce errors in satellite data. The spatial correspondence between moving and fixed images are accurately mined by Transformer to enhance feature extraction of precipitation areas and effectively compensate for the lack of trace precipitation information. The convolution layer is also used to effectively capture local information, which results in a high-resolution feature map and enables the model to obtain richer features, thus improving the estimation of quantitative precipitation. Experimental results confirm the effectiveness of the method in satellite precipitation image registration. The quantitative analysis shows that the algorithm effectively improves the precipitation estimation accuracy and can achieve efficient and accurate precipitation estimation, which is of great value to the research of extreme precipitation estimation. © 2025 SPIE.

关键词： Satellite imagery

来源：评论

学校读者我要写书评

暂无评论

Understanding Deep Learning RF Wireless Side-Channel Attacks: Perspectives on Noisy Scenarios 25

Understanding Deep Learning RF Wireless Side-Channel Attacks...

引用

Proceedings of the 2025 4th International Conference on Cryptography, Network Security and Communication technology

作者： Bijia Cao Yuanyuan Chen Xiaoxia Wang Qixiang Ouyang Huanyu Wang Junnian Wang School of Physics and Electronics Hunan University of Science and Technology Xiangtan Hunan China School of Computer Science and Engineering Hunan University of Science and Technology Xiangtan Hunan China

ISBN: (纸本)9798400712623

Recently developed Radio Frequency Wireless Side-Channel Attacks (RF-WSCAs) have become a significant threat to the widespread deployment of IoT edge devices as they eliminate the need for physical proximity to the target. By analyzing side-channel emissions from mixed-signal chips (unintentionally coupled with radio transmission signals), attackers can compromise cryptographic implementations over long distances. Existing work demonstrates the feasibility of extracting AES keys from Bluetooth devices at a distance of 15-metres using CNN models trained on traces. However, they may overestimate the threat of RF WSCAs by ignoring the effects caused by ambient noise and interference. In this study, we conduct a detailed examination of the extent to which environmental noise and interference can affect the attack efficiency of RF-WSCAs. We first proposed a 20 input CNN architecture that achieved similar attack results to the SOTA model. Then, we conducted a comprehensive analysis of RF-WSCAs from the perspective of noisy scenarios.

关键词： AES

来源：评论

学校读者我要写书评

暂无评论

Privacy-Preserving Publishing Mechanism for Real-Time Vehicle Trajectory in Vehicle-to-Grid Networks

Privacy-Preserving Publishing Mechanism for Real-Time Vehicl...

引用

Power Electronics, computer Applications (ICPECA), IEEE International Conference on

作者： Yulong Wang Jianbo Xu Bo Gong School of Computer Science and Engineering Hunan University of Science and Technology Xiangtan China

ISBN: (数字)9798331533694

ISBN: (纸本)9798331533700

The Vehicle-to-Grid (V2G) network is a smart grid technology generated under the background of the rapid development of new energy technology, which allows mobile energy storage vehicles (MESVs) to realize bidirectional energy exchange with the grid system. As distributed energy storage units within the V2G network, MESVs help meet the grid's load-balancing demands. To accurately schedule grid loads, V2G networks rely on MESVs' real-time trajectory data. After collecting this data, the central authority (CA) publishes it to the grid enterprise (GM) for load-balancing decisions. However, before publication, the CA must process the data to protect the location privacy of MESVs and prevent GM from extracting sensitive information. To address this privacy protection challenge during data publication, we propose a differential privacy-based mechanism. Our mechanism uses the unscented Kalman filter to predict and correct the published data at the sampling point and intelligently adjusts the sampling interval. Additionally, we introduce a privacy budget allocation method based on regional access frequency and travel time, enhancing privacy protection of trajectory in high-access areas and peak hours. Through security analysis and experimental validation, our mechanism effectively preserves the privacy of real-time vehicle trajectory data while ensuring data validity.

关键词： Vehicle-to-grid Data privacy Privacy Publishing Real-time systems Trajectory Kalman filters Security Protection Radio spectrum management

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：