检索结果-内蒙古大学图书馆

Design and Tool Flow of a Reconfigurable Asynchronous Neural Network Accelerator

Tsinghua science and technology 2021年第5期26卷 565-573页

作者： Jilin Zhang Hui Wu Weijia Chen Shaojun Wei Hong Chen the Institute of Microelectronics Tsinghua National Laboratory for Information Science and Technologyand Beijing Engineering Center of Technology and research on Wireless Medical and Health SystemTsinghua UniversityBeijing 100084China

Convolutional Neural Networks(CNNs)are widely used in computer vision,natural language processing,and so on,which generally require low power and high efficiency in real ***,energy efficiency has become a critical indicator of CNN *** that asynchronous circuits have the advantages of low power consumption,high speed,and no clock distribution problems,we design and implement an energy-efficient asynchronous CNN accelerator with a 65 nm Complementary Metal Oxide Semiconductor(CMOS)*** the absence of a commercial design tool flow for asynchronous circuits,we develop a novel design flow to implement Click-based asynchronous bundled data circuits efficiently to mask layout with conventional Electronic Design Automation(EDA)*** also introduce an adaptive delay matching method and perform accurate static timing analysis for the circuits to ensure correct *** accelerator for handwriting recognition network(LeNet-5 model)is *** test results show that the asynchronous accelerator has 30%less power in computing array than the synchronous one and that the energy efficiency of the asynchronous accelerator achieves 1.538 TOPS/W,which is 12%higher than that of the synchronous chip.

关键词： Convolutional Neural Network(CNN)accelerator asynchronous circuit energy efficiency adaptive delay matching asynchronous design flow

来源：评论

学校读者我要写书评

暂无评论

Review:Wearable Sweat Sensors for Diseases Prevention and Monitoring

引用

Journal of Harbin Institute of technology(New Series) 2023年第3期30卷 1-21页

作者： Yanan Ding Haiying Xiao Ping’an Hu School of Chemistry and Chemical Engineering Harbin Institute of TechnologyHarbin 150080China MOE Key Lab of Micro-System and Micro-Structures Manufacturing Harbin Institute of TechnologyHarbin 150080China State Key Laboratory of Robotics and System Harbin Institute of TechnologyHarbin 150080China School of Materials Science and Engineering Harbin Institute of TechnologyHarbin 150080China

Advanced in wireless technologies and flexible materials with great biocompatibility,wearable devices have been utilized in the field of healthcare,sports management,and diseases prevention,which have been widely applied in current electronic ***,as a common metabolite on the skin surface,contains a wealth of biomarkers for disease detection and ***,developing wearable sweat sensors can provide a non⁃invasive method for health data collecting,sports monitoring,and clinical diagnosis in a convenient *** research in sweat metabolomics has offered a lot of information for sweat analysis and the wearable sweat sensors with small size,various sensing,and transmission units,and good skin contact has exhibited dynamic multi⁃signal *** article introduces the biomarkers in sweat related to different diseases and the current development of sweat sensors for user􀆳s activation monitoring and diseases *** barriers and difficulties in the future are also discussed and perspectives in the next generation sweat sensors are proposed.

关键词： sweat sensor sweat metabolites disease monitoring wearable device

来源：评论

学校读者我要写书评

暂无评论

Object Relations Focused Siamese Network for Remote Sensing Image Change Detection 16th

Object Relations Focused Siamese Network for Remote Sensing ...

引用

16th International Conference on Bio-Inspired Computing: Theories and Applications, BIC-TA 2021

作者： Wang, Jie-pei Tang, Lei-yu Fan, Jian-cong Liu, Guo-qiang College of Computer Science and Engineering Shandong University of Science and Technology Qingdao China College of Mathematics and System Science Shandong University of Science and Technology Qingdao China Provincial Key Lab for Information Technology of Wisdom Mining of Shandong Province Shandong University of Science and Technology Qingdao China

ISBN: (纸本)9789811912528

In recent years, deep learning methods, especially convolutional neural networks (CNNs), have shown powerful discriminative ability in the field of remote sensing change detection. However, the multi-temporal remote sensing images often have a long time interval, which leads to the geographical objects with the same semantic may have different spectral representations in different spatial and temporal locations, thus affecting the performance of network detection. Exploring the latent connections between different objects helps promote the discrimination of feature maps, so as to suppress the generation of pseudo changes because the geographical objects are not isolated. In this paper, we propose a novel change detection network focused on the object relations (ORFNet), which can capture relevant context by exploring the relations between objects in dual spatio-temporal scenes, so as to enhance the discrimination of original image features. Experiments on CDD data sets show that our method only increases 0.4M parameters compared with the baseline, and improves F1 by 3.6%. © 2022, Springer Nature Singapore Pte Ltd.

关键词： Change detection

来源：评论

学校读者我要写书评

暂无评论

Track Slab Crack Detection Algorithm with Few Samples Based on Deep Learning 8

Track Slab Crack Detection Algorithm with Few Samples Based ...

引用

8th International Conference on Intelligent Informatics and Biomedical sciences, ICIIBMS 2023

作者： Liu, Zhongjie Li, Wenju Gao, Xiaosong Liu, Cui Shanghai Institute of Technology School of Computer Science and Information Engineering Shanghai China Shanghai Crrc Ro-Intelligent System. Co. Ltd. Shanghai China

ISBN: (纸本)9798350369564

In order to solve the problem of track slab crack detection under few samples' conditions, this paper proposes a track slab crack detection algorithm with few samples based on deep learning. Firstly, after extracting multi-scale query and support features through the Swin Transformer backbone, the similarity between query pixels and support pixels is computed according to the scaled dot-product attention of the Transformer architecture, and the query masks are aggregated;in order to filter a large amount of irrelevant background information in the crack image, multi-scale prototypes are computed by using prototypical learning, highlighting the class information of the cracks, and introducing a lightweight attention module to generate class-representative attention feature maps using support features at different scales, which guides the network to focus its attention on the target region;finally, the final prediction of cracks is realized by the feature fusion module. The experimental results show that the track slab crack IoU reaches 66.94% and the FB-IoU reaches 83.02% under the few samples' condition and exhibits strong generalization performance on the crack set of other scenarios as well. © 2023 IEEE.

关键词： Crack detection

来源：评论

学校读者我要写书评

暂无评论

Channel Capacity and Power Allocation of MIMO Visible Light Communication system

引用

China Communications 2023年第2期20卷 122-138页

作者： Shuai Ma Ruixin Yang Guanjie Zhang Hang Li Wen Cao Linqiong Jia Yanyu Zhang Shiyin Li Peng Cheng Laboratory Shenzhen 518055China School of Information and Control Engineering China University of Mining and TechnologyXuzhou 221116China Shenzhen Research Institute of Big Data Shenzhen 518172China School of Electronics and Control Engineering Chang’an UniversityXi’an 710064China School of Electronic and Optical Engineering Nanjing University of Science and TechnologyNanjing 210094China National Digital Switching System Engineering&Technological Research Center Zhengzhou 450000China

In this paper,the channel capacity of the multiple-input multiple-output(MIMO)visible light communication(VLC)system is investigated under the peak,average optical and electrical power *** the channel capacity of MIMO VLC is shown to be a mixed integer programming *** address this open problem,we propose an inexact gradient projection method to find the channel capacity-achieving discrete input distribution and the channel capacity of MIMO *** we derive both upper and lower bounds of the capacity of MIMO VLC with the closed-form ***,by considering practical discrete constellation inputs,we develop the optimal power allocation scheme to maximize transmission rate of MIMO VLC *** results show that more discrete points are needed to achieve the channel capacity as SNR *** the upper and lower bounds of channel capacity are tight at low SNR *** addition,comparing the equal power allocation,the proposed power allocation scheme can significantly increase the rate for the low-order modulation inputs.

关键词： visible light communication MIMO discrete constellation inputs power allocation

来源：评论

学校读者我要写书评

暂无评论

Adaptive Attribute-Based Honey Encryption: A Novel Solution for Cloud Data Security

引用

Computers, Materials & Continua 2025年第2期82卷 2637-2664页

作者： Reshma Siyal Muhammad Asim Long Jun Mohammed Elaffendi Sundas Iftikhar Rana Alnashwan Samia Allaoua Chelloug School of Computer Science and Engineering Central South UniversityChangsha410083China EIAS LAB College of Computer and Information Sciencesand Center of Excellence in Quantum and Intelligent ComputingPrince Sultan UniversityRiyadh11586Saudi Arabia Gianforte School of Computing Montana State UniversityBozemanMT 59717USA Department of Information Technology College of Computer and Information SciencesPrincess Nourah Bint Abdulrahman UniversityRiyadh11671Saudi Arabia

A basic procedure for transforming readable data into encoded forms is encryption, which ensures security when the right decryption keys are used. Hadoop is susceptible to possible cyber-attacks because it lacks built-in security measures, even though it can effectively handle and store enormous datasets using the Hadoop Distributed File system (HDFS). The increasing number of data breaches emphasizes how urgently creative encryption techniques are needed in cloud-based big data settings. This paper presents Adaptive Attribute-Based Honey Encryption (AABHE), a state-of-the-art technique that combines honey encryption with Ciphertext-Policy Attribute-Based Encryption (CP-ABE) to provide improved data security. Even if intercepted, AABHE makes sure that sensitive data cannot be accessed by unauthorized parties. With a focus on protecting huge files in HDFS, the suggested approach achieves 98% security robustness and 95% encryption efficiency, outperforming other encryption methods including Ciphertext-Policy Attribute-Based Encryption (CP-ABE), Key-Policy Attribute-Based Encryption (KB-ABE), and Advanced Encryption Standard combined with Attribute-Based Encryption (AES+ABE). By fixing Hadoop’s security flaws, AABHE fortifies its protections against data breaches and enhances Hadoop’s dependability as a platform for processing and storing massive amounts of data.

关键词： Cybersecurity data security cloud storage hadoop encryption and decryption privacy protection attribute-based honey encryption

来源：评论

学校读者我要写书评

暂无评论

Application of Artificial Intelligence in the Supply Chain: A systematic Literature Review 6th

Application of Artificial Intelligence in the Supply Chain: ...

引用

6th International Conference on Big Data Cloud and Internet of Things, BDIoT 2022

作者： Kriouich, Mohamed Sarir, Hicham Mahboub, Oussama Advanced Science and Technology Team ENSA Tetouan Abdelmalek Esaadi University Tetouan Morocco Information System and Software Engineering ENSA Tetouan Abdelmalek Esaadi University Tetouan Morocco

ISBN: (纸本)9783031283864

This research presents a systematic literature review of using artificial intelligence (AI) in the supply chain (SC). We examine the works done so far in relation to AI research, which still needs to be investigated in light of the potential benefits of implementing AI in supply chain management. Dynamic supply chain processes require artificial intelligence techniques capable of dealing with their increasing complexity. Artificial intelligence techniques such as machine learning, Deep learning, natural language processing, expert systems, knowledge representation, Fuzzy logic and models, social intelligence, Artificial neural networks, Support vector machines, Gaussian models, robotics, Ant colony, and computer vision can transform and optimize the supply chain. In order to classify the study material, we looked at 50 research papers from the Scopus database that were published between 2002 and 2022 and assigned each one a grade based on two fundamental structural factors are as follows: AI techniques and sector of application. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Mixing Dynamics and Synthesis Performance of Staggered Herringbone Micromixer for Limit Size Lipid Nanoparticles

引用

Journal of Beijing Institute of technology 2022年第3期31卷 293-301页

作者： Shuai Zhang Yunlong Fan Chenmu Xue Yuanzhan Yang Xiaoqiong Li Xiaodong Chen Yulin Deng School of Aerospace Engineering Beijing Institute of TechnologyBeijing 100081China Institute of Engineering Medicine Beijing Institute of TechnologyBeijing 100081China School of Life Science Beijing Institute of TechnologyBeijing 100081China Key Laboratory of Convergence Medical Engineering System and Healthcare Technology Ministry of Industry and Information TechnologyBeijing 100081China

Staggered herringbone micromixer has shown good efficiency of mixing and performance of synthesizing *** bring a detailed understanding of the mixing dynamics and syn-thesis performance of this kind of micromixer,this paper carries out a high-fidelity numerical simu-lation and a parametrial experimental study on a well-established design.A passive tracer is induced in the numerical simulation to analyze mixing dynamics induced by the staggered herring-bone *** effects are identified to reveal the underlying mechanisms,including folding,stretching,and *** the authors’knowledge,the splitting effect is identified for the first time by the isosurface of the passive tracer,to show the high efficiency of the staggered herring-bone *** micromixer is then used to synthesize lipid nanoparticles by mixing a mixture of lipid and poly(lactic-co-glycolic acid)(PLGA)solutions with deionized *** a wide mass ratio of lipid and PLGA solutions,nanoparticles with good monodispersity are synthesized to reflect the good compatibility of the micromixer and the *** addition,an optimized mass ratio is identified from the parametrical experiment.

关键词： mixing dynamics staggered herringbone micromixer folding stretching splitting

来源：评论

学校读者我要写书评

暂无评论

A fast simulated annealing heuristic for the multi-depot two-echelon vehicle routing problem with delivery options

引用

Transportation Letters 2024年第8期16卷 921-932页

作者： Yu, Vincent F. Lin, Shih-Wei Zhou, Lin Baldacci, Roberto Department of Industrial Management National Taiwan University of Science and Technology Taipei Taiwan Center for Cyber-Physical System Innovation National Taiwan University of Science and Technology Taipei Taiwan Department of Information Management Chang Gung University Taoyuan Taiwan Department of Industrial Engineering and Management Ming Chi University of Technology New Taipei Taiwan Department of Emergency Medicine Keelung Chang Gung Memorial Hospital Keelung Taiwan College of Management Chongqing University of Technology Chongqing China Division of Engineering Management and Decision Sciences College of Science and Engineering Hamad Bin Khalifa University Doha Qatar

We studied a variant of the vehicle routing problem (VRP) arising in last-mile distribution, called the multi-depot two-echelon vehicle routing problem with delivery options (MDTEVRP-DO). The MDTEVRP-DO involves two decision levels: (i) designing routes for a fleet of vehicles located in multiple depots to transport customer demands to a set of satellites and (ii) routing a fleet of vehicles from the satellites to serve the final customers. Nowadays, a relevant feature of the problem characterizing delivery services is that customers can collect their packages at pickup stations near their homes or workplaces. We designed an effectively simulated annealing (SA) heuristic for the problem. The new algorithm was extensively tested on benchmark instances from the literature, and its results were compared with those of start-of-the-art algorithms. The results show that the proposed SA obtains 30 out of the 36 best solutions for the MDTEVRP-DO benchmark instances. Moreover, its computation performance is superior to state-of-the-art algorithms for the MDTEVRP-DO. © 2023 Informa UK Limited, trading as Taylor & Francis Group.

关键词： Simulated annealing

来源：评论

学校读者我要写书评

暂无评论

Joint Beamforming Design for Multi-Functional RIS-Aided Over-the-Air Federated Learning

引用

IEEE Internet of Things Journal 2025年第12期12卷 21720-21739页

作者： Zhang, Xinran Tian, Hui Ni, Wanli Yang, Zhaohui Beijing University of Posts and Telecommunications State Key laboratory of Networking and Switching Technology Beijing100876 China Tsinghua University Department of Electronic Engineering Beijing100084 China Zhejiang Lab Hangzhou311121 China Zhejiang University College of Information Science and Electronic Engineering Hangzhou310027 China Hangzhou310007 China

Over-the-air computation has emerged as a high-spectrum efficient and low-latency solution for model aggregation in federated learning (FL) by leveraging the superposition property of wireless channels. However, traditional over-the-air FL (AirFL) faces challenges such as signal misalignment, imperfect channel state information (CSI), and noisy fading channels. To enable more efficient and reliable AirFL in Internet of Things, we employ a multi-functional reconfigurable intelligent surface (MF-RIS) to alleviate mean square error (MSE) of AirFL model aggregation. By deriving the convergence analysis of AirFL in both convex and non-convex settings, we unveil the impact of MSE on MF-RIS-aided AirFL under varying conditions. Based on the theoretical insights, we aim to minimize the MSE through a joint design of transceiver beamforming and MF-RIS coefficients, but it necessitates solving a mixed-integer nonlinear programming problem. To solve it efficiently, we propose an alternating optimization algorithm based on the semidefinite relaxation approach and difference-of-convex programming. The efficacy of our approach is corroborated by numerical results, which underscore the performance gains achieved by the proposed algorithm. Additionally, the MF-RIS demonstrates remarkable proficiency in suppressing MSE and bolstering AirFL performance, even under conditions of imperfect CSI. © 2025 IEEE.

关键词： Mean square error

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：