检索结果-内蒙古大学图书馆

15th IEEE International Conference on ASIC, ASICON 2023

作者： Zhang, Xiaojun Zhu, Chenshi Han, Qin Wang, Zhengrong Zhang, Dexue Shandong University of Science and Technology College of Electronic and Information Engineering China State Key Laboratory of High-end Server and Storage Technology Qingdao China

ISBN: (纸本)9798350312980

In the training of Convolutional Neural Networks (CNN), the conventional max unpooling architecture introduces significant sparsity for zero-filling during upsampling, leading to additional resource costs in adjacent deconvolution layers. In order to leverage the high sparsity of the recovery matrix, this paper proposes a low-complexity hardware architecture. This architecture solely stores the input matrix in the max unpooling layer, eliminating the need for the upsampling recovery process, while mapping the stored relative indices from the forward inference to deconvolution. Moreover, the deconvolution process exclusively involves non-zero elements, reducing computational and storage requirements. This paper derives the distribution of the maximum number of non-zero values corresponding to the deconvolution window for different layers, demonstrating its compatibility with networks of various sizes. Synthesizing the proposed architecture on Arria 10 AX115N2F45E1SG, for the VGG16, it can save 60.7% of ALMs and 68.8% of storage resources, Moreover, the proposed architecture enhances the frequency by 8.0%. © 2023 IEEE.

关键词： Convolution neural network FPGA Hardware acceleration Max unpooling

来源：评论

学校读者我要写书评

暂无评论

Communication-Efficient Decision-Making of Digital Twin Assisted Internet of Vehicles: A Hierarchical Multi-Agent Reinforcement Learning Approach

引用

China Communications 2023年第3期20卷 55-68页

作者： Xiaoyuan Fu Quan Yuan Shifan Liu Baozhu Li Qi Qi Jingyu Wang State Key Laboratory of Networking and Switching Technology Beijing University of Posts and TelecommunicationsBeijing 100876China State Key Laboratory of Integrated Services Networks Xidian UniversityXi’an 710071China Internet of Things&Smart City Innovation Platform Zhuhai Fudan Innovation InstituteZhuhai 519000China State Key Laboratory of High-End Server and Storage Technology Jinan 250101China

The connected autonomous vehicle is considered an effective way to improve transport safety and *** overcome the limited sensing and computing capabilities of individual vehicles,we design a digital twin assisted decision-making framework for Internet of Vehicles,by leveraging the integration of communication,sensing and *** this framework,the digital twin entities residing on edge can effectively communicate and cooperate with each other to plan sub-targets for their respective vehicles,while the vehicles only need to achieve the sub-targets by generating a sequence of atomic ***,we propose a hierarchical multiagent reinforcement learning approach to implement the framework,which can be trained in an end-to-end *** the proposed approach,the communication interval of digital twin entities could adapt to timevarying *** experiments on driving decision-making have been performed in traffic junction scenarios of different *** experimental results show that the proposed approach can largely improve collaboration efficiency while reducing communication overhead.

关键词： digital twin Internet of Vehicles hierar-chical reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Toward Big-Data Sharing: A Unified Trusted Remote Attestation Scheme based on Blockchain

引用

IEEE Internet of Things Journal 2025年第13期12卷 24656-24671页

作者： Wang, Ran Ma, Fuqiang Duan, Shihong Su, Zhiyuan Zhang, Xiaotong Xu, Cheng University of Science and Technology Beijing School of Computer and Communication Engineering Shunde Innovation School China Inspur Data Technology Co. Ltd. Shandong Jinan China State Key Laboratory of High-end Server & Storage Technology Beijing China Inspur Electronic Information Industry Co. Ltd Shandong Jinan China

The rapid expansion of the Internet of Things (IoT) has brought forth new challenges and opportunities in securely managing and sharing vast amounts of data generated by connected devices. Blockchain technology, with its decentralization, tamper-resistance, and traceability, offers a promising framework for IoT data sharing but struggles to safeguard smart contracts and sensitive data. Integrating Trusted Execution Environments (TEEs) with blockchain addresses these concerns, enabling secure execution and communication via remote attestation. However, existing remote attestation methods face challenges, including incompatibility across heterogeneous TEEs, inefficiency under frequent authentication, and vulnerability to DoS attacks. To tackle these, we propose a blockchain-based unified remote attestation scheme for IoT. Our three-tier blockchain architecture–comprising a Certificate Authority (CA) channel, an authoritative channel, and a business channel–separates authentication, attestation, and operations while ensuring auditability. An abstraction layer supports heterogeneous TEEs, and an authoritative blockchain stores authentication reports, enabling secure, frequent attestations. Additionally, a distributed CA system enhances resilience to DoS attacks. Experimental results validate our scheme’s efficiency and security, offering a robust solution for IoT data sharing. © 2014 IEEE.

关键词： Blockchains Security Hardware Software Scalability Internet of Things Privacy Authentication Data privacy Cloud computing

来源：评论

学校读者我要写书评

暂无评论

Layer-wise based Adabelief Optimization Algorithm for Deep Learning 4

Layer-wise based Adabelief Optimization Algorithm for Deep L...

引用

4th International Conference on Advanced Information Science and System, AISS 2022

作者： Qiu, Zhiyong Guo, Zhenhua Wang, Li Zhao, Yaqian Li, Rengang State Key Laboratory of High-end Server and Storage Technology Shandong Massive Information Technology Research Institute China State Key Laboratory of High-end Server and Storage Technology Inspur Electronic Information Industry Co. Ltd. China

ISBN: (纸本)9781450397933

For the optimization problem of deep learning, it is important to formulate a optimization method that can improve the convergence rate without sacrificing generalization ability. This paper proposes a layer-wise based Adabelief optimization algorithm to solve the deep learning optimization problems more efficiently. In the proposed algorithm, each layer of the deep neural network is set different learning rate appropriately in order to achieve a faster convergence rate. We also give the theorems that can guarantee the convergence property of Layer-wised AdaBelief method. Finally, we evaluate the effectiveness and efficiency of the proposed algorithm on experimental examples. Experimental results show that the converges speed of the layer-wised AdaBelief algorithm is the fastest compared with the mainstream algorithms. Besides, the new algorithm also maintaining an excellent convergence result in all numerical examples. © 2022 ACM.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Bilateral Anomaly Detection Based on Edge Computing: Baseboard Management Controller 16

Bilateral Anomaly Detection Based on Edge Computing: Baseboa...

引用

16th International Symposium on Computational Intelligence and Design, ISCID 2023

作者： Zou, Deqiang Man, Hongtao Li, Tuo State Key Laboratory of High-End Server & Storage Technology Beijing China 1nspur Electronic Information Industry Co. Beijing China

ISBN: (纸本)9798350317459

Anomaly detection on servers is a crucial technique with the increment of computing patterns in this period. To accommodate current demands, we propose a version of a bilateral detection scheme based on the baseboard management controller with machine learning to conduct compound anomaly detection and boost the upper bound. On the local part, the naive logic trees are deployed on the calculating module to make initial detection and carry out prompt actions maintaining the applicable working environment. Once the local anomaly alerts, the remote part is triggered to judge with the Gaussian Mixture Model, which ensures the anomaly type and proceeds with advanced steps. The bilateral detection system resorts to edge computing priority and scientifically allocates computing power to improve the level of anomaly detection on servers. The anomaly detection system's effect herein is excellent in real-time demand and stability. ©2023 IEEE.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Optimization of UAV base station placement for D2D content delivery network

引用

Soft Computing 2024年第13-14期28卷 7823-7839页

作者： Li, Jialiuyuan Lu, Dianjie Hu, Chunyu Ai, Xinwei Liu, Pingshan Zhang, Guijuan Liu, Hong School of Information Science and Engineering Shandong Normal University Jinan250358 China State Key Laboratory of High-End Server and Storage Technology Jinan250358 China Jinan250353 China Qingdao Hisense Network Technology Co. Ltd Qingdao266104 China Business School Guilin University of Electronic Technology Guilin541004 China

In a device-to-device content delivery network (D2D-CDN), user equipment (UE) covered by a base station can forward content received from the base station to other uncovered UEs in a multi-hop manner to increase network coverage. However, infrastructures, such as local base stations, are destroyed and D2D-CDN cannot operate normally due to the lack of base stations as a content source in disaster scenarios. Unmanned aerial vehicle (UAV) can temporarily serve as a content source with its flexibility to deliver content to terrestrial UEs, which we call it UAV base station (UAV-BS). However, the placement of UAV-BS will be affected by many factors, such as UE distribution and communication interference. Therefore, how to place UAV-BS in a reasonable way to maximize the network throughput and the number of covered UEs while ensuring the communication quality of service (QoS) is still a challenging problem. To solve this problem, first, we propose a UAV-BS placement optimization model (U-POM) and formulate an optimization problem. Secondly, we prove that our maximization problem is NP-hard and propose an improved artificial bee colony algorithm (ABC), called the global optimal artificial bee colony (GOABC) algorithm. Finally, we construct an analysis and testing platform to analyze the accuracy and the stability of the GOABC algorithm. The results highlight the effectiveness of the proposed GOABC algorithm in maximizing network throughput and the number of covered UEs while ensuring the communication QoS. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2024.

关键词： Base stations

来源：评论

学校读者我要写书评

暂无评论

Adjustable MMI for dynamic on-chip monitoring based on nano-optoelectro-mechanical interaction 3

Adjustable MMI for dynamic on-chip monitoring based on nano-...

引用

3rd International Conference on Laser, Optics, and Optoelectronic technology, LOPET 2023

作者： Zhang, Feng Zhu, Kejian Sun, Pengfei Li, Tuo Zou, Xiaofeng Liu, Kai Man, Hongtao Song, Qi Zhou, Lang Li, Chen Inspur Electronic Information Industry Co. Ltd. Beijing100085 China State Key Laboratory of High-end Server&Storage Technology Jinan250013 China State Key Laboratory of Advanced Optical Communications Systems and Networks School of Electronics Peking University Beijing100871 China

ISBN: (纸本)9781510667624

Energy efficiency and integration scale are two of the major challenges of current optical computing chips. To solve these problems, we propose for the first time a special multimode interference(MMI) and dynamic monitoring idea. The research of the device is based on finite element analysis. There is a nano-opto-electro-mechanical(NOEM) ratio controller in the upper left of the multimode waveguide. Most of the time, the device is in static mode with power-splitting-ratio(PSR) close to 0:100. The research shows that once the controller is started, the device enters dynamic mode with a PSR bigger than 5:95. The PSR is less than 0.36:99.64 in a selected static mode and up to 8.35:91.65 in dynamic mode. The change of PSR in dynamic mode is realized by adjusting distance between NOEM module and multimode waveguide. The footprint of the multimode waveguide is only 1.54×3.63μm2. Its minimum insertion loss(IL) is less than 0.2dB and has good process tolerance characteristics. The energy consumption of discontinuous monitoring based on the MMI is significantly lower than that of continuous monitoring. It is estimated that when duty cycle of the periodic monitoring module is 0.1 and 0.01, its monitoring energy consumption can be reduced by 70% and 97%, respectively. The MMI is expected to greatly promote the development of optical computing chips. © 2023 SPIE.

关键词： Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

Multimodal Emotion Recognition Using CNN-SVM with Data Augmentation

Multimodal Emotion Recognition Using CNN-SVM with Data Augme...

引用

2022 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2022

作者： Guo, Gengyuan Gao, Pengzhi Zheng, Xiangwei Ji, Cun Shandong Normal University State Key Laboratory of High-end Server & Storage Technology School of Information Science and Engineering Jinan China

ISBN: (纸本)9781665468190

With the development of human-computer interaction and mobile sensors, emotion recognition based on physiological signals has aroused a lively discussion among scholars. The main difficulty faced is the small amount of data which leads to poor training results. In this paper, we proposed a multimodal emotion recognition using CNN-SVM and data augmentation (CSDAMER). Electrocardiography (ECG), galvanic skin response (GSR) and respiration (RSP) are utilized as input data, which are less requiring on the collection environment and can be collected by mobile sensors. To improve the training effect of model, data augmentation is performed by transformations, such as inversion, recombination and noise injection. Moreover, the convolutional layer of the convolutional neural network (CNN) is leveraged to extract the high-level features of the physiological signals, and then the features are input into the support vector machine (SVM) classifier to obtain the recognition results. The experimental results show that CSDAMER achieves 80.7% and 79.92% accuracy in arousal and valance, respectively. Compared with CNN alone, the accuracy of arousal and valance is increased by 12.87% and 9.95%. Meanwhile, the addition of the data augmentation improves the accuracy in arousal and valance by 21.94% and 25.73%. © 2022 IEEE.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

A SoC Booting Acceleration Strategy Based on Self-Migration technology 2

A SoC Booting Acceleration Strategy Based on Self-Migration ...

引用

2nd International Conference on Networking, Communications and Information technology, NetCIT 2022

作者： Man, Hongtao Zhou, Lang Wang, Shuo Electronic Information Industry Co. Ltd. China State Key Laboratory of High-end Server & Storage Technology China

ISBN: (纸本)9781665492737

The SoC booting is performed as the first step after system power-on and its rate is significantly affected by the boot medium interface rate. This paper reported an acceleration strategy based on self-migration technology. By redirecting boot image itself from a low-speed NOR flash device to a high-speed RAM device, a higher booting speed was achieved. The modified data format of the boot image was designed and two kinds of boot processes of the bare metal and bootloader were proposed. A SoC verification platform based on a dual-core ARM CPU and various interface modules was set up. By compiling different interface functions, the boot time was all decreased significantly in different boot image size. This result proved the code self-migration was a promising candidate in the SoC booting. © 2022 IEEE.

关键词： System-on-chip

来源：评论

学校读者我要写书评

暂无评论

Research on the Application of Blockchain in the Safe and Trusted Sharing of Government Data 2

Research on the Application of Blockchain in the Safe and Tr...

引用

2nd International Conference on Artificial Intelligence and Blockchain technology, AIBT 2023

作者： Zhang, Heng Liu, Wenguo Zibo Housing Provident Fund Management Center Zibo China Inspur Group Co. Ltd Jinan China State Key Laboratory of High-end Server Storage Technology Jinan China

ISBN: (纸本)9781665475839

To avoid the security vulnerabilities and privacy leakage risks in the process of government data sharing, a data sharing scheme for government data based on blockchain is proposed in this paper. As one of the basic protocols for the next generation of global credit authentication and value Internet, blockchain technology has been paid more and more attention. The blockchain is used to realize data tamper-proof, distributed storage, privacy protection, traceability, and access control. Data sharing and exchange agreements between government public services have adopted blockchain technology, providing identity authentication and message permission management. Using the blockchain to record the sharing behavior and provide traceability, the smart contract is used to share and manage the data and ensure the data's consistency on-chain and off-chain. Due to shortcomings of government data sharing, the paper designs a data-sharing scheme and technical framework based on blockchain technology. From its perspective, it takes housing provident fund data sharing, for example, to establish a provident fund chain in the industry. This blockchain application scenario has been applied to the housing provident fund industry, forming a new model of industry data sharing. © 2023 IEEE.

关键词： Smart contract

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：