检索结果-内蒙古大学图书馆

Latin American Test Workshop, LATW

作者： Robert Limas Sierra Giuseppe Esposito Juan-David Guerrero-Balaguera Josie E. Rodriguez Condia Matteo Sonza Reorda Politecnico di Torino - Department of Control and Computer Engineering (DAUIN)

ISBN: (数字)9781665477635

ISBN: (纸本)9781665477642

Convolutional Neural Networks (CNNs) have shown exceptional effectiveness in complex and data-intensive domains such as image and video processing, conversational systems, and healthcare. Moreover, sectors like High-Performance Computing and safety-critical applications, including automotive, aerospace, and autonomous robotics, impose stringent requirements on energy efficiency, performance, and robustness. However, modern semiconductor technologies are increasingly vulnerable to faults, which can degrade CNN performance and potentially result in catastrophic failures. This work explores the impact of regularization techniques (dropout layer) in enhancing the inference robustness of CNN models against soft errors. We analyzed soft error impacts on five widely adopted CNN architectures, each trained with ten different dropout rates. Our experimental results reveal that optimizing the dropout rate during training can improve the in-field robustness of CNN models by up to 12% compared to baseline configurations under soft error conditions. Additionally, fine-tuning this architectural parameter can lead to accurary improvements of up to 10%.

关键词： Training Accuracy Runtime computer architecture Medical services Robustness Hardware Convolutional neural networks Robots Optimization

来源：评论

学校读者我要写书评

暂无评论

About the Functional In-Field Self-Testing of AI Accelerators

About the Functional In-Field Self-Testing of AI Accelerator...

引用

Latin American Test Workshop, LATW

作者： Juan-David Guerrero-Balaguera Josie E. Rodriguez Condia Robert Limas Sierra Matteo Sonza Reorda Politecnico di Torino - Department of Control and Computer Engineering (DAUIN)

ISBN: (数字)9781665477635

ISBN: (纸本)9781665477642

1 1 Work supported by the National Resilience and Recovery Plan (PNRR) through the National Center for HPC, Big Data and Quantum *** Learning Accelerators (DLA) are pervasive hardware units in modern applications, including safety critical systems such as Automotive, Aerospace, Robotics, and health monitoring systems. Therefore, it is crucial to guarantee their reliability during the mission operation of any of these applications, as a failure can produce catastrophic results (e.g., loss of human lives). In fact, modern semiconductor technologies used to implement DLAs can be affected by faults due to several phenomena, such as aging, process variation, or manufacturing defects. Periodic testing and functional testing strategies have demonstrated their utility and effectiveness on DLA accelerators in spotting faults arising during the in-field operation of the system. Nonetheless, these approaches can have significant testing times and memory footprint overheads, making them hard to apply during the online operation of large-size accelerators. This work proposes an effective strategy for generating efficient functional test patterns for computational units in DLA accelerators by reducing the required testing time (43×) and memory footprints (3.3×) compared with literature solutions. Moreover, our strategy provides diagnostic capabilities for identifying defective units (e.g., multipliers).

关键词： Quantum computing Memory management AI accelerators Built-in self-test Hardware Manufacturing Reliability Robots Monitoring Resilience

来源：评论

学校读者我要写书评

暂无评论

Virtual Synchronous Generator Droop control for Renewable Energy Sources

Virtual Synchronous Generator Droop Control for Renewable En...

引用

2024 IEEE Global Energy Conference, GEC 2024

作者： Cakmak, Fevzi Aykat, Sukru Kazanbaş, Mehmet Cemil Akgul, Sabahattin Department of Electricity and Energy Mardin Atuklu University Mardin Turkey Department of Computer Engineering Mardin Atuklu University Mardin Turkey Department of Control and Automation Engineering Yildiz Technical University Istanbul Turkey Department of Handicrafts Mardin Atuklu University Mardin Turkey

ISBN: (纸本)9798331532611

The connection of large-scale RES (renewable energy source) to the grid and the increase in the efficiency of energy production also causes different power quality problems. It has become mandatory for these inverter-based systems to participate in load frequency control. For this purpose, the design and simulation of a virtual synchronous generator (VSG), which enables RES to operate like synchronous generators, has been carried out in Matlab/Simulink environment. It is observed that the VSG keeps the load frequency stable according to different load conditions. ©2024 IEEE.

关键词： Synchronous generators

来源：评论

学校读者我要写书评

暂无评论

Ontology-driven Data Management Design in Healthcare Domain: The ADCATER Experience

Ontology-driven Data Management Design in Healthcare Domain:...

引用

2024 Joint Ontology Workshops - Episode X: The Tukker Zomer of Ontology, and Satellite Events, JOWO 2024

作者： Cocco, Leonardo Fantozzi, Paolo Lembo, Domenico Nanni, Umberto Scafoglieri, Federico Maria Department of Computer Control and Management Engineering University of Rome la Sapienza Rome00185 Italy Department of Law Economics Politics and Modern Languages LUMSA University Rome00192 Italy

In this paper, we outline our experience in implementing the data management component of a data-intensive healthcare application within the ADCATER project (Advanced Digital Solutions for Professional Food and Nutrition Catering Service), where an ad hoc ontology, tailored to the project’s domain, plays a crucial role in driving the system design. We will discuss the creation process of this ontology, its underlying building principles, and how it aids the development of a reconciled database useful to integrate and consolidate heterogeneous sources of information, vital for the proper running of solution at hand. Here, the ontology is essential for harmonizing vocabularies and ensuring the establishment of a schema devoid of inconsistencies. Finally, we will explore how Business Intelligence services, operating on the foundation of the Data Warehouse built upon the reconciled database, are seamlessly aligned with the crafted ontology. © 2024 Copyright for this paper by its authors.

关键词： Data warehouses

来源：评论

学校读者我要写书评

暂无评论

MulDoor: A Multi-target Backdoor Attack Against Federated Learning System

MulDoor: A Multi-target Backdoor Attack Against Federated Le...

引用

2024 IEEE Global Communications Conference, GLOBECOM 2024

作者： Li, Xuan Wu, Longfei Guan, Zhitao Du, Xiaojiang Aitsaadi, Nadjib Guizani, Mohsen North China Electric Power University School of Control and Computer Engineering China Fayetteville State University Department of Mathematics and Computer Science Fayetteville United States Stevens Institute of Technology Department of Electrical and Computer Engineering HobokenNJ United States Université Paris-Saclay Uvsq David Versailles France Machine Learning Department United Arab Emirates

ISBN: (纸本)9798350351255

In recent years, with the development of wireless communication networks, federated learning (FL) has been widely deployed in distributed scenarios as a privacy-preserving machine learning paradigm. Due to its inherent features, FL shows vulnerability to backdoor attacks. In a backdoor attack, an adversary manipulates the global model's output by compromising the model of one or multiple participants. Existing backdoor attacks are constrained to outputting a single specified target label during the inference phase, limiting the adversary's flexibility to alter the model's output when different target labels are required. In this paper, we study the multi-target attack scenario within the federated learning context, where the adversary aims to manipulate the global model to output various specified labels by inserting different types of triggers. To effectively insert multiple backdoors simultaneously without reducing the attack's effectiveness, we propose MulDoor, a novel multi-target backdoor attack scheme. MulDoor incorporates the concept of supervised contrastive learning to learn the discrepancies among different types of triggers and mitigate interference between them. The experimental results demonstrate that MulDoor achieves better attack effectiveness compared to existing backdoor attacks in a multi-target backdoor attack setting. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Adaptive Active Fault-Tolerant Attitude control for Spacecraft with Adaptive Prescribed Performance 6

Adaptive Active Fault-Tolerant Attitude Control for Spacecra...

引用

6th International Symposium on Autonomous Systems, ISAS 2023

作者： Yang, Ze Yang, Baoqing Ji, Ruihang Ma, Jie Harbin Institute of Technology Control and Simulation Center Harbin China National University of Singapore Department of Electrical and Computer Engineering Singapore

ISBN: (纸本)9798350316155

For spacecraft attitude control affected by environmental disturbance, parameter uncertainty and actuator fault, a novel composite active fault-tolerant scheme, combining a strong tracking Cubature Kalman filter (STCKF) with adaptive prescribed performance control (APPC), is investigated in this paper. The proposed STCKF is capable of estimating lumped fault rapidly but accurately, and it is robust to model uncertainty. An adaptive finite-time prescribed performance function (APPF) whose boundaries can be flexibly adjusted in the case of actuator faults is proposed. Then an active fault tolerant controller is designed using nonsingular terminal sliding mode control (NTSMC) in conjunction with APPF. Simulation experiments and comparisons show that the proposed strategy exhibits better fault tolerance, lower conservatism and better steady-state performance. © 2023 IEEE.

关键词： Attitude control

来源：评论

学校读者我要写书评

暂无评论

Adaptive Neuro-Fuzzy Inference Systems for Cognitive Sensor Communication in Smart Cities

Adaptive Neuro-Fuzzy Inference Systems for Cognitive Sensor ...

引用

2024 IEEE International Conference on Intelligent Systems and Advanced Applications, ICISAA 2024

作者： Pradhan, Rahul Prathiba, Ch. Kholmukhamedov, Timur Patil, B.N. Mary, S. Suma Christal Raj, I Infant GLA University Department of Computer Engineering and Applications Mathura India Vignana Bharathi Institute of Technology Department of CSM Ghatkesar Hyderabad India Turin Polytechnic University Automatic Control and Computer Engineering Department Tashkent Uzbekistan Yeshwantrao Chavan College of Engineering Department of Applied Physics Nagpur India Panimalar Engineering College Department of Information Technology Poonamalle Chennai India K. Ramakrishnan College of Engineering Department of CSE Tamil Nadu Trichy India

ISBN: (纸本)9798331539948

Modern urban development depends on optimizing cognitive sensor communications in smart cities, which is the focus of this investigation. In the era of expanding sensor networks, efficient data transmission is paramount for the success of smart city initiatives. The current state of sensor communication faces challenges like suboptimal adaptability, inefficient energy usage, and limited fault detection. This study proposes a solution through the application of an Adaptive Neuro-Fuzzy Inference System (ANFIS), identifying these challenges as opportunities for improvement. The novelty lies in ANFIS's introduction as an intelligent and adaptive solution. Its ability to learn from sensor data, adapt to changing conditions, and optimize communication parameters sets it apart in enhancing cognitive sensor communication. The research methodology involves a systematic approach, encompassing data collection, pre-processing, and ANFIS model development. The model is rigorously trained, validated, and tested for real-world effectiveness. Integration into the smart city communication system is explored, emphasizing applications in context-aware communication, energy-efficient protocols, and fault detection. Performance is evaluated using metrics like accuracy, reliability, and efficiency, demonstrating the model's efficacy in addressing drawbacks and enhancing overall sensor communication in smart cities. The findings contribute to advancing intelligent systems for urban infrastructure and services. © 2024 IEEE.

关键词： Fuzzy neural networks

来源：评论

学校读者我要写书评

暂无评论

Renewable integration and energy reduction in multiple stage evaporator

引用

Materials Today: Proceedings 2023年 80卷 24-31页

作者： Pati, Smitarani Kumar Sharma, Tarun Kumar Goyal, Kapil Prakash Verma, Om Department of Instrumentation and Control Engineering Dr B R Ambedkar National Institute of Technology Jalandhar Punjab Jalandhar 144011 India Department of Computer Science and Engineering Shobhit University UP Saharanpur-247341 India Department of Industrial and Production Engineering Dr B R Ambedkar National Institute of Technology Jalandhar Punjab Jalandhar 144011 India

Multiple Effect Evaporator (MEE) is an imperative part of the paper industry. It is used to process the waste byproduct named Black Liquor to enhance its solid concentration that may be further utilized to produce biomass-based energy. This process accounts very high energy consumption which leads to the energy intensiveness of this unit. A substantial amount of energy-saving may be accumulated by integrating various Energy Reduction Schemes (ERSs) with the MEE. Steam splitting, feed splitting, feed liquor preheating, thermo-vapor compressor, etc. are the well-known ERSs that may be incorporated with the MEE to reduce energy utilization. Hence, this study investigates the hybrid ERSs incorporated with MEE to observe their energy efficiency in an optimal manner. The prime focus of this investigation is to achieve enhanced energy efficiency in teams of maximum steam efficiency which is computed by formulating the nonlinear mathematical models of the MEE. To achieve the maximized energy efficiency, an optimization function has been developed under a constraint environment and solved by using metaheuristic-based approach named Flow Direction Algorithm. Another ERSs named flash tanks can also be integrated with this system to encourage waste heat re-utilization and ensures an increase in energy efficiency with constant steam consumption. This work also deals with the incorporation of the Linear Fresnel Reflector with ERSs integrated MEE which is capable of reducing the conventional energy load. The overall integrated MEE model achieves an energy-efficient and renewably operated MEE unit that may enhance the self-sustainability of the industry. © 2022

关键词： Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

Microservice Deployment for Satellite Edge AI Inference via Deep Reinforcement Learning 35

Microservice Deployment for Satellite Edge AI Inference via ...

引用

35th IEEE International Symposium on Personal, Indoor and Mobile Radio Communications, PIMRC 2024

作者： Yu, Zhiyong Cheng, Hei Victor Yang, Zhanpeng Liu, Xin Jiang, Yuning Zhou, Yong Shi, Yuanming ShanghaiTech University School of Information Science and Technology Shanghai201210 China Aarhus University Department of Electrical and Computer Engineering Denmark Automatic Control Laboratory Switzerland

ISBN: (纸本)9798350362244

Artificial intelligence (AI) is critical in evolving 5G and developing 6G networks, running on edge devices, and solving resource management challenges. The burgeoning number of edge devices draws attention to the potential of low-earth orbit (LEO) satellite networks with their onboard computing capabilities for edge inference. This paper explores LEO scenarios where multiple remote sensing edge AI inference tasks concurrently process data from a single source. However, due to there being parts with the same functions between different AI applications, traditional monolithic edge AI architecture must be deployed repeatedly and falls short in efficiently harnessing the heterogeneous resources of LEO satellite networks. To solve this problem, we utilize the microservice architecture to decouple a single AI application into several independent microservices to reuse these same functions. However, due to the high latency caused by multiple microservices' communication, we need to design a deployment strategy to fully utilize resources to reduce the service latency. We present a microservice deployment model to minimize the total service latency across all AI applications and meet resource constraints with the constraints of hardware, energy, and memory limitations. This latency optimization problem is rewritten as a Markov decision process (MDP) to effectively deal with the challenge posed by the time-varying transmission rate caused by satellite mobility. To increase the training data utilization, we employ a Proximal Policy Optimization (PPO) based reinforcement learning algorithm to meet the dynamic environment challenge. Finally, we obtain a sub-optimal solution with minimal accuracy loss and an acceptable solution time. © 2024 IEEE.

关键词： Markov processes

来源：评论

学校读者我要写书评

暂无评论

Improving Security and Performance of Databases Through Single Cache System 4

Improving Security and Performance of Databases Through Sing...

引用

4th International Conference on Blockchain Technology and Information Security, ICBCTIS 2024

作者： Ul Haq, Ikram Khan, Salabat Khan, Mansoor Tamsal, Saher School of Computer Science and Technology Southwest University of Science and Technology Mianyang China School of Computer and Information Engineering Qilu Institute of Technology Jinan China School of Intelligent Manufacturing and Control Engineering Qilu Institute of Technology Jinan China University of Agriculture Department of Computer Science Faisalabad Pakistan

ISBN: (纸本)9798331528324

In today's world, connectivity and performance-driven technology are rapidly advancing each year, and new platforms and mechanisms are being utilized to enhance the security and performance of databases and cloud computing, which are trending in the global market. This examination focused on customer information security in cloud computing, i.e., information stockpiling security issues and how to control unapproved access to data by proposing access control;valuable measures were characterized subsequently, and an entrance control show was prescribed. Cloud computing can be described as an innovation that depends on the web and the sharing of resources. It has an adaptable foundation that customers can use with much of a stretch. With its wide event relationship, there are numerous obstacles to continuing with cloud computing because of security issues, mostly considering customer data security. The proposed study helped hesitant clients sensibly continue forward in the cloud while understanding the dangers of cloud computing. The research objective is to examine the security techniques employed in cloud technology to improve its performance by utilizing data mining within a unified cache system. We will apply the Apriori algorithm as a proposed solution to be used in a single cache while considering the security measures in the cloud. The study expects to apply this method to all cloud providers and vendors by entering data into a single cache mechanism that can be extended into different components and implemented using SPSS modelers to improve the security of the database. © 2024 IEEE.

关键词： Cloud security

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：