检索结果-内蒙古大学图书馆

CMN: a co-designed neural architecture search for efficient computing-in-memory-based mixture-of-experts

science China(Information sciences) 2024年第10期67卷 100-114页

作者： Shihao HAN Sishuo LIU Shucheng DU Mingzi LI Zijian YE Xiaoxin XU Yi LI Zhongrui WANG Dashan SHANG Department of Electrical and Electronic Engineering The University of Hong Kong ACCESS-AI Chip Center for Emerging Smart Systems InnoHK Centers Key Lab of Fabrication Technologies for Integrated Circuits Chinese Academy of Sciences Laboratory of Microelectronics Devices and Integrated Technology Institute of MicroelectronicsChinese Academy of Sciences University of Chinese Academy of Sciences School of Microelectronics Southern University of Science and Technology

Artificial intelligence(AI) has experienced substantial advancements recently, notably with the advent of large-scale language models(LLMs) employing mixture-of-experts(MoE) techniques, exhibiting human-like cognitive skills. As a promising hardware solution for edge MoE implementations, the computing-in-memory(CIM) architecture collocates memory and computing within a single device, significantly reducing the data movement and the associated energy consumption. However, due to diverse edge application scenarios and constraints, determining the optimal network structures for MoE, such as the expert's location,quantity, and dimension on CIM systems remains elusive. To this end, we introduce a software-hardware co-designed neural architecture search(NAS) framework, CIM-based MoE NAS(CMN), focusing on identifying a high-performing MoE structure under specific hardware constraints. The results of the NYUD-v2 dataset segmentation on the RRAM(SRAM) CIM system reveal that CMN can discover optimized MoE configurations under energy, latency, and performance constraints, achieving 29.67×(43.10×) energy savings,175.44×(109.89×) speedup, and 12.24× smaller model size compared to the baseline MoE-enabled Visual Transformer, respectively. This co-design opens up an avenue toward high-performance MoE deployments in edge CIM systems.

关键词： mixture-of-experts computing-in-memory neural architecture search resistive random-access memory static random-access memory

来源：评论

学校读者我要写书评

暂无评论

Random suppression of ECG artifacts using a NLSRLMMN-based cascaded noise canceller 58

Random suppression of ECG artifacts using a NLSRLMMN-based c...

引用

58th Asilomar Conference on Signals, systems and Computers, ACSSC 2024

作者： Faiz, Mohammed Mujahid Ulla Zerguine, Azzedine Kale, Izzet Presidency University Department of Electrical and Computer Engineering Karnataka Bengaluru560064 India Interdisciplinary Research Center for Communication Systems and Sensing Kfupm Electrical Engineering Department Dhahran31261 Saudi Arabia Department of Computer Science and Engineering LondonW1W 6UW United Kingdom

ISBN: (纸本)9798350354058

Normally, the electrocardiogram (ECG) signal artifacts are removed in a particular sequence starting with baseline wander removal at the beginning. In this work, a methodology has been proposed using a novel algorithm called the Normalized Leaky Sign Regressor Least Mean Mixed Norm (NLSRLMMN) algorithm to remove multiple ECG artifacts such as baseline wander, motion artifacts, muscle artifacts, and power line interference randomly without following a particular sequence. Through rigorous simulations we have shown that if we remove multiple ECG artifacts randomly using our proposed approach then an improvement in signal to noise ratio and mean square error is observed as opposed to a conventional method that employs the Least Mean Square (LMS) algorithm in all the cascaded adaptive noise canceller stages. © 2024 IEEE.

关键词： Mean square error

来源：评论

学校读者我要写书评

暂无评论

Stunting Classification in Toddlers: Implementation and Evaluation of the Decision Tree Algorithm

Stunting Classification in Toddlers: Implementation and Eval...

引用

2024 International Conference on Information Technology and Computing, ICITCOM 2024

作者： Alita, Debby Ahmad, Imam Jafar Rumandan, Rhaishudin Erkamim, Moh Widyasmoro Universitas Teknokrat Indonesia Faculty of Engineering and Computer Science Bandarlampung Indonesia Institut Agama Islam Negeri Ambon Islamic Education Management Study Program Ambon Indonesia Universitas Tunas Pembangunan Smart City Information Systems Study Program Surakarta Indonesia Universitas Muhammadiyah Yogyakarta Faculty of Engineering Department of Electrical Engineering Yogyakarta Indonesia

ISBN: (纸本)9798350379839

Stunting in toddlers is a chronic nutritional issue that affects the physical and cognitive development of children, with serious long-term consequences such as reduced cognitive function and an increased risk of chronic diseases in adulthood. Therefore, early identification and prevention efforts for stunting are crucial. Classifying toddlers into categories of at-risk for stunting or not is essential to provide timely and appropriate interventions. This study employs data mining techniques using the decision tree algorithm to expedite the stunting detection process and improve the accuracy of nutritional status classification in children. The results indicate that the constructed decision tree model can classify children's nutritional status with an accuracy of 83.26%. The decision tree achieves high accuracy in classifying stunting in toddlers due to its ability to handle complex data and identify significant patterns within the data. © 2024 IEEE.

关键词： Classification Data Mining Decision Tree Stunting

来源：评论

学校读者我要写书评

暂无评论

Mechanistic modeling of copper corrosions in data center environments

引用

Building Simulation 2024年第3期17卷 483-492页

作者： Rui Zhang Jianshun Zhang Roger Schmidt Jeremy L.Gilbert Department of Mechanical and Aerospace Engineering College of Engineering and Computer ScienceSyracuse UniversitySyracuseNY13244USA Buildings and Transportation Science Division Oak Ridge National LaboratoryOak RidgeTN37830USA SyracuseCoE-New York Center of Excellence in Environmental and Energy Systems Syracuse University727 E.Washington StreetSyracuseNY13244USA Department of Bioengineering Clemson UniversityClemson-Medical University of South Carolina Bioengineering ProgramCharlestonSC29425USA

Air-side economizers are increasingly used to take advantage of“free-cooling”in data centers with the intent of reducing the carbon footprint of ***,they can introduce outdoor pollutants to indoor environment of data centers and cause corrosion damage to the information technology *** evaluate the reliability of information technology equipment under various thermal and air-pollution conditions,a mechanistic model based on multi-ion transport and chemical reactions was *** model was used to predict Cu corrosion caused by Cl_(2)-containing pollutant *** also accounted for the effects of temperature(25℃and 28℃),relative humidity(50%,75%,and 95%),and *** also identified higher air temperature as a corrosion barrier and higher relative humidity as a corrosion accelerator,which agreed well with the experimental *** average root mean square error of the prediction was 13.7Å.The model can be used to evaluate the thermal guideline for data centers design and operation when Cl_(2)is present based on pre-established acceptable risk of corrosion in data centers’environment.

关键词： chloride pollutant mixture copper corrosion model data center temperature relative humidity synergistic effect

来源：评论

学校读者我要写书评

暂无评论

User-Centric Security and Privacy Threats in Connected Vehicles: A Threat Modeling Analysis Using STRIDE and LINDDUN

User-Centric Security and Privacy Threats in Connected Vehic...

引用

2023 IEEE International Conference on Dependable, Autonomic and Secure Computing, 2023 International Conference on Pervasive Intelligence and Computing, 2023 International Conference on Cloud and Big Data Computing, 2023 International Conference on Cyber science and Technology Congress, DASC/PiCom/CBDCom/CyberSciTech 2023

作者： Stingelova, Beata Thrakl, Clemens Thaddaus Wronska, Laura Jedrej-Szymankiewicz, Sandra Khan, Sajjad Svetinovic, Davor Vienna University of Economics and Business Information Systems and Operations Management Vienna Austria Khalifa University Center for Cyber-Physical Systems Electrical Engineering and Computer Science Abu Dhabi United Arab Emirates

ISBN: (纸本)9798350304602

The increasing equipment of cars with smart systems and their networking with other devices is leading to a growing network of connected vehicles. Connected cars are Internet of Things (IoT) devices that communicate bidirectionally with other systems, enabling internet access and data exchange. Artificial Intelligence (AI) offers benefits such as autonomous driving, driver assistance programs, and monitoring. The increasing connectivity of cars also brings new risks to users' privacy. Our study focuses on privacy threats in connected cars from a user perspective. Our study provides a comprehensive threat model analysis based on a combination of STRIDE and LINDDUN. We analyze the various threats and vulnerabilities that arise from connecting cars to the internet and other devices, including Vehicle-to-Vehicle (V2V), Vehicle-to-Vloud (V2C), and Vehicle-to-Device (V2D). We conduct our study based on a theoretical model of a modern-day connected vehicle of another study. Our study shows that several types of threats can negatively impact the privacy of connected car users. This encapsulates the potential risks, such as the inadvertent disclosure of personal data due to the vehicle's interconnectedness with other devices, including smartphones, and the subsequent susceptibility to unauthorized access, while also highlighting the need for robust security measures indicated by our comprehensive threat modeling, to safeguard against a wide array of identified cybersecurity threats. © 2023 IEEE.

关键词： Electronic data interchange

来源：评论

学校读者我要写书评

暂无评论

Safeguarding Healthcare: A Comprehensive Threat Analysis of Clinical Decision Support systems

Safeguarding Healthcare: A Comprehensive Threat Analysis of ...

引用

作者： Hamel, Aleksandra Ursula Charlotte Zarcu, Bogdan-Cristian Csenteri, Andras-Gergely Pfliegler, Tamara Khan, Sajjad Svetinovic, Davor Vienna University of Economics and Business Information Systems and Operations Management Vienna Austria Khalifa University Center for Cyber-Physical Systems Electrical Engineering and Computer Science Abu Dhabi United Arab Emirates

ISBN: (纸本)9798350304602

Using digital data gathering and analytics in healthcare brings benefits and risks to patients and practitioners. Smart Health Information systems, such as Clinical Decision Support systems (CDSSs), consolidate data from various sources, utilizing artificial intelligence for decision support. However, machine learning models in CDSSs are vulnerable to various attacks, leading to incorrect predictions with severe consequences. This paper systematically investigates security and privacy threats related to CDSSs. First, we leverage the data flow and sequence diagrams to identify the critical use cases that might lead to security or privacy breaches. Second, we identify and classify threats imminent to the CDSSs using Security Cards and STRIDE. Lastly, the persona non-grata who pose a significant threat to the integrity of the CDSSs are identified. Implementing our method can assist teams in addressing security threats to CDSSs by considering their unique vulnerabilities. This research contributes to developing comprehensive security strategies for CDSSs. © 2023 IEEE.

关键词： Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Threat Modeling for ML-based Topology Prediction in Vehicular Edge Computing Architecture

Threat Modeling for ML-based Topology Prediction in Vehicula...

引用

作者： Doan, Hong Hanh Paul, Audri Adhyas Zeindlinger, Harald Zhang, Yiheng Khan, Sajjad Svetinovic, Davor Vienna University of Economics and Business Information Systems and Operations Management Vienna Austria Center for Cyber-Physical Systems Electrical Engineering and Computer Science Khalifa University Abu Dhabi United Arab Emirates

ISBN: (纸本)9798350304602

The Internet of Vehicles (IoV), a network that interlinks vehicles, infrastructure, and assorted entities, serves as a cornerstone for intelligent transportation systems and the emergence of smart cities. Within this context, edge computing has been identified as a critical solution for providing rapid and reliable data processing. Machine Learning (ML) techniques have become essential to IoV activities such as resource allocation and load balancing across mobile edge servers, typified by decentralized services that range from natural language processing to image recognition. The fusion of ML with edge computing within IoV architecture promises enhanced performance, efficiency, and safety. However, this amalgamation also creates challenges related to data privacy, cybersecurity, malfunctioning edge devices, inconsistent network connectivity, human errors, and malicious insiders. Consequently, this paper focuses on modeling security threats within an ML-based edge computing framework for the IoV. We analyze the system provided by the Linux Foundation Edge Akraino Project's Stable Topology Prediction blueprint by employing a hybrid threat modeling technique. Our strategy leverages STRIDE to elicit threats on distinct system elements like vehicle-to-vehicle communication networks, edge networks, and ML models. Subsequently, these threats are consolidated for a comprehensive view using an attack tree. © 2023 IEEE.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Blockchain CBDC Security Threats Using STRIDE 5

Blockchain CBDC Security Threats Using STRIDE

引用

5th International Conference on Blockchain Computing and Applications, BCCA 2023

作者： Hans, Jaqueline Khan, Sajjad Svetinovic, Davor Information Systems and Operations Management Vienna University of Economics and Business Vienna Austria Center for Cyber-Physical Systems Electrical Engineering and Computer Science Khalifa University Abu Dhabi United Arab Emirates

ISBN: (纸本)9798350339239

In strategic response to the increasing threats from crypto payment systems, cryptocurrencies, and stablecoins, central banks globally are contemplating the introduction of their digital currencies, termed Central Bank Digital Currencies (CBDCs). This trend, especially the emergence of CBDCs built on blockchain technology, instigates significant discourse on security and privacy concerns. This research paper delves into the potential security risks of blockchain-based CBDCs, distinguishing between permissionless and permissioned network architectures and token-based and account-based access mechanisms. We employed STRIDE, a threat modeling methodology, to elucidate these risks, on architectural constructs derived from CBDC proposals and use cases, identifying 39 distinct threats. Our study intends to enrich the ongoing dialogue on the evolution of blockchain-based CBDCs. The findings provide a robust foundation to guide and inform prudent design decisions by offering a detailed understanding of potential security and privacy risks, thereby contributing to developing more secure CBDCs. © 2023 IEEE.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Recent Developments in Event-Triggered Control of Nonlinear systems:An Overview

引用

无人系统（英文） 2023年第1期11卷 27-56页

作者： Pengpeng Zhang Tengfei Liu Jie Chen Zhong-Ping Jiang Department of Control Science & Engineering Frontiers Science Center for Intelligent Autonomous SystemsTongji UniversityShanghai 201804P.R.China State Key Laboratory of Synthetical Automation for Process Industries Northeastern UniversityShenyang 110819P.R.China Department of Electrical and Computer Engineering New York University370 Jay StreetBrooklynNY 11201USA

Event-triggered control is a most popular paradigm for transferring feedback information in an economical"as needed"*** study of event-triggered control can be traced back to the *** significant advances on the topic of control over networks and the topic of nonlinear control systems over the last two decades,event-triggered control has quickly emerged as a major theoretical subject in control *** of event-triggered control are wide-spread ranging from embedded control systems and industrial control processes to unmanned systems and cyber-physical transportation *** this paper,we first review developments in the synthesis of event-triggered sampling *** event triggering mechanisms,such as static event trigger,dynamic event trigger,time-regularized event trigger,and event trigger with positive threshold offsets,are systematically ***,we study how to design a stabilizing controller that is robust with respect to the sampling ***,we review some recent results in the directions of self-triggered control,event-triggered tracking control and cooperative control,and event-triggered control of stochastic systems and partial differential equation *** applications of event-triggered control are also discussed.

关键词： Event-triggered control event-triggered sampling mechanism event-triggered controller

来源：评论

学校读者我要写书评

暂无评论

Cyber Vulnerabilities in Blockchain Electronic Health Records: An In-Depth Threat Analysis

Cyber Vulnerabilities in Blockchain Electronic Health Record...

引用

作者： Brkic, Marija Dinu, Horia-Stefan Mirkovic, Alida Sabirovic, Alma Khan, Sajjad Svetinovic, Davor Vienna University of Economics and Business Information Systems and Operations Management Vienna Austria Center for Cyber-Physical Systems Electrical Engineering and Computer Science Khalifa University Abu Dhabi United Arab Emirates

ISBN: (纸本)9798350304602

The rapid evolution of information systems and the surge in data generation and dissemination have fostered the emergence of Electronic Health Records (EHRs). Specifically, blockchain-enabled EHRs are revolutionizing modern healthcare by centralizing patient data promoting transparency, accessibility, and interoperability. However, amidst increasing cyberattacks on healthcare institutions, the security of these EHRs is a critical concern. Existing research predominantly focuses on the advantages and disadvantages of incorporating blockchain technology into EHRs, leaving a noticeable gap in analyzing specific threats. Our study bridges this gap by leveraging a hybrid threat modeling methodology, integrating attack tree models with an exhaustive review of existing literature on threats to blockchain-based standardized EHRs. This approach has identified and organized 26 unique threats into an attack tree. Each threat is elaborated upon and discussed within the context of the Blockchain EHRs. © 2023 IEEE.

关键词： Blockchain

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：