检索结果-内蒙古大学图书馆

6th ieee international conference on Pattern Recognition and Artificial Intelligence, PRAI 2023

作者： Shi, Shuyu Cao, Xinyang Zhang, Qingmiao Chengdu Foreign Languages School International Department Chengdu China

ISBN: (纸本)9798350325485

The paper considers the privacy-preserving and communication constraints for multi-Agent systems. Firstly, a lightweight, decentralized, time-varying transformation method is introduced to prevent information leakage during information exchange between agents. This approach requires less computation and is compatible with systems with limited computing resources. Secondly, the paper proposes an event-Triggered mechanism that considers both privacy-preserving and communication constraints to avoid continuous updates of the privacy-preserving controller. By using intermittent communication mode, this approach effectively reduces computing and communication resources compared to traditional time-Triggered methods. Overall, these methods offer efficient solutions for privacy and communication challenges in multi-Agent systems. The finite-Time privacy-preserving control protocol is validated through numerical simulation examples to demonstrate its effectiveness. © 2023 ieee.

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

Cloud-Block: An Integrated Cloud and Blockchain using Secure Cloud computing 3

Cloud-Block: An Integrated Cloud and Blockchain using Secure...

引用

3rd international conference on Automation, computing and Renewable systems, ICACRS 2024

作者： Srinivas, B. Rao, K. Nageswara NRI Institute of Technology India DEPT of CSE NRI Institute of Technology India

ISBN: (纸本)9798331532420

Cloud computing is a domain that provides data storage services using a cloud server. Cloud also provides data processing, security, and integrity. Recently, cloud service providers (CSP) have required high-end security for the data stored by cloud users. Every cloud computing company provides various services, including advanced secure cloud applications. This paper developed a model that provides enhanced security to cloud applications. The integration of blockchain into cloud storage data becomes more complex when designing the model. The blockchain is a technology that combines cloud data, divides the data into blocks, and forms a chain. The data is encrypted by using the Advanced Encryption Standard (AES) algorithm in every block of data by creating a unique ID, which can be accessed by authorized users. In this context, a high-end security model addresses the key challenges in combining the blockchain in cloud applications to process the uploaded data. Experimental results show the quantitative performance of various algorithms, and the proposed approach shows high performance in terms of cloud-based parameters. © 2024 ieee.

关键词： Cloud security

来源：评论

学校读者我要写书评

暂无评论

Sleep Apnea Detection System Using Machine Learning on Resource-Constrained Devices 17

Sleep Apnea Detection System Using Machine Learning on Resou...

引用

17th Annual ieee international systems conference (SysCon)

作者： Mallick, Sayani Gawali, Shubhangi Onime, Clement Goveas, Neena BITS Pilani EEE Dept Goa Campus Sancoale Goa India BITS Pilani CSIS Dept Goa Campus Sancoale Goa India Abdus Salaam Int Ctr Theoret Phys Trieste Italy

ISBN: (纸本)9781665439947

Sleep Apnea is a condition in which a person has pauses in breathing or very low breathing episodes during sleep. It is a condition that could prove life-threatening if not monitored and treated. A medical diagnosis of Sleep Apnea involves overnight recording of body signals, monitoring by a medical professional, use of hospital based equipment and data analysis for detection of anomalies. During the past decade, the measurement and analysis of human body signals using machine learning techniques on embedded devices have started to transform healthcare applications. The use of cost effective micro-controllers can ensure that health monitoring is available and accessible to all. In this paper, we show that machine learning models deployed on microcontrollers can successfully analyze ECG signals in real-time for Sleep Apnea detection. We have created TinyML models using TensorFlow Lite which we have deployed on cost effective and resource constrained devices like the Raspberry Pi Pico and ESP32. Our setup has given results comparable to more advanced and expensive devices for the detection of Sleep Apnea using ECG signals.

关键词： ECG Embedded Device Signal Processing TinyML TensorFlow Lite Machine Learning Edge Impulse Sleep Apnea Artificial Neural Networks Edge computing

来源：评论

学校读者我要写书评

暂无评论

Predicting China's Marriage Rate using Machine Learning Models and Cross-Validation Evaluation 16

Predicting China's Marriage Rate using Machine Learning Mode...

引用

16th international conference on Cyber-Enabled distributed computing and Knowledge Discover, CyberC 2024

作者： Zhang, Deyu Theeramunkong, Thanaruk Khamsemanan, Nirattaya Yunnan College of Foreign Affairs and Foreign Language Kunming China Thammasat University Sirindhorn International Institute of Technology Thailand

ISBN: (纸本)9798331506896

After China's accession to the WTO, the country has experienced rapid development over the past 20 years, but the marriage rate has been declining. This study aims to analyze marriage data using machine learning, identify the factors influencing the marriage rate, and make predictions. The data covers seven variables including GDP, housing prices, fertility rate, and education level in 31 regions of China from 2003 to 2022. The study employed five machine learning algorithms with five models: Ridge, Lasso, Elastic Net, Polynomial, and Weighted Least Squares, along with three types of Cross-Validation techniques - Holdout, LOOCV, and K-Fold. By comparing the five regression models and evaluating the marriage rate models through Holdout, LOOCV, and K-Fold Cross-Validation, the results show that the Polynomial regression exhibits higher predictive accuracy, with MSE of 3.473 for Holdout, 3.001 for LOOCV, and 3.018 for K-Fold. Following closely is Ridge regression with MSE of 3.565 for Holdout, 3.326 for LOOCV, and 3.334 for K-Fold. These two models outperform the less performing Lasso and Elastic Net regressions. Weighted Least Squares show stable but slightly inferior performance. By comparing the predicted values for 2022 with the actual values, it is confirmed that Polynomial and Ridge regression closely align with the actual values, predicting the trend of changes in real and predicted values for each province, highlighting their effectiveness in predictive tasks involving complex data patterns. © 2024 ieee.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

distributed Training of Large Language Models 29

Distributed Training of Large Language Models

引用

29th ieee international conference on Parallel and distributed systems, ICPADS 2023

作者： Zeng, Fanlong Gan, Wensheng Wang, Yongheng Yu, Philip S. Jinan University Zhuhai519070 China Pazhou Lab Guangzhou510330 China University of Illinois Chicago Chicago United States

ISBN: (纸本)9798350330717

The advent of large language models (LLMs), like ChatGPT ushers in revolutionary opportunities that bring a vast variety of applications (such as healthcare, law, and education) across various disciplines. The research report pointed out that the model showcases excellent performance often closely related to the parameter scale of the model, so how to train an LLM? This is a question that everyone is more concerned about. At present, there are several commonly used distributed training frameworks including Megatron-LM, DeepSpeed, etc. In this paper, we first provide a brief introduction, which refers to the current development status of LLM. Second, we start from the status, introducing the current common parallel strategies of LLM distributed training. Next, we briefly introduce the underlying technologies and frameworks that LLM relies on nowadays, describing the current popular ones and types of large models. Then we introduce the optimization techniques used in the LLMs. Finally, we summarize the problems and challenges encountered in the current LLM training and describe the possible future development direction of LLM. © 2023 ieee.

关键词： Big data data parallelism distributed training large language models pipeline parallelism

来源：评论

学校读者我要写书评

暂无评论

Research on Double Layer Coordinated Optimization Planning of Distribution Network with distributed Generation 3

Research on Double Layer Coordinated Optimization Planning o...

引用

3rd international conference on Energy Engineering and Power systems, EEPS 2023

作者： Wang, Dan Ding, Hao State Grid Shiyan Power Supply Company Shiyan China State Grid Danjiangkou Power Supply Company Shiyan China

ISBN: (纸本)9798350313857

A network source coordination and expansion planning model considering cluster partitioning was established for the expansion planning of high penetration distributed energy distribution networks and the location and capacity determination of distributed power sources. The model is divided into two layers. The upper planning model aims to minimize the annual comprehensive cost, optimize the network structure, distributed power access location, and capacity. The lower level cluster partitioning model divides the upper level planning results into clusters based on comprehensive performance indicators that take into account electrical distance and active power balance. The optimization process is iterative and interactive, using an improved hybrid genetic algorithm for solution. Taking a 10 kV distribution system as an example, the effectiveness of the two-level optimization model for grid source coordination was verified. © 2023 ieee.

关键词： distributed power generation

来源：评论

学校读者我要写书评

暂无评论

Learning to Control Emulated Muscles in Real Robots: A Software Test Bed for Bio-Inspired Actuators in Hardware 10

Learning to Control Emulated Muscles in Real Robots: A Softw...

引用

10th ieee RAS/EMBS international conference for Biomedical Robotics and Biomechatronics (BioRob)

作者： Schumacher, Pierre Krausel, Lorenz Schneiders, Jan Btichler, Dieter Martius, Georg Haeufle, Daniel Max Planck Inst Intelligent Syst Tubingen Germany Univ Tubingen Hertie Inst Clin Brain Res Tubingen Germany Univ Tubingen Ctr Integrat Neurosci Tubingen Germany Univ Tubingen Distributed Intelligence Tubingen Germany Heidelberg Univ Inst Comp Engn ZITI Heidelberg Germany

ISBN: (纸本)9798350386523;9798350386530

Recent studies have demonstrated the immense potential of exploiting muscle actuator morphology for natural and robust movement - in simulation. A validation on real robotic hardware is yet missing. In this study, we emulate muscle actuator properties on hardware in real-time, taking advantage of modern and affordable electric motors. We demonstrate that our setup can emulate a simplified muscle model on a real robot while being controlled by a learned policy. We improve upon an existing muscle model by deriving a damping rule that ensures that the model is not only performant and stable but also tuneable for the real hardware. Our policies are trained by reinforcement learning entirely in simulation, where we show that previously reported benefits of muscles extend to the case of quadruped locomotion and hopping: the learned policies are more robust and exhibit more regular gaits. Finally, we confirm that the learned policies can be executed on real hardware and show that sim-to-real transfer with real-time emulated muscles on a quadruped robot is possible. These results show that artificial muscles can be highly beneficial actuators for future generations of robust legged robots. Videos: https://***/view/emulatedmuscles

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

distributed Power System Simulation and Monitoring Supported by Cloud Technology : A grid optimization scheduling method based on MADRL 4

Distributed Power System Simulation and Monitoring Supported...

引用

4th international conference on Energy, Power and Electrical Engineering, EPEE 2024

作者： Luo, Hui Zhang, Jie Hu, Yufeng Zhang, Jingyue Guo, Haiping Huang, Libin Csg Key Laboratory for Power System Simulation Electric Power Research Institute China Southern Power Grid Guangzhou China State Key Laboratory of Hvdc Electric Power Research Institute China Southern Power Grid Guangzhou China Guangdong Provincial Key Laboratory of Intelligent Operation and Control for New Energy Power System Guangzhou China National Energy Power Grid Technology R&d Centre Guangzhou China

ISBN: (纸本)9798331518066

This study explores the optimization of distributed Generation systems (DGS) within a Multi-Agent Deep Reinforcement Learning (MADRL) framework. The focus is on transforming the overall optimization goal of the system into a global reward function and designing local rewards adapted to heterogeneous agents. Using the ieee 33 node system as a case study, the impact of power aggregation and load management from photovoltaic systems, energy storage systems, electric vehicle charging facilities, and HVAC systems is analyzed. The results demonstrate that the proposed edge-cloud collaborative framework optimizes resource allocation and scheduling. The cloud platform is capable of integrating data from diverse sources and managing it in a unified manner, thereby coordinating the operations of multiple heterogeneous agents. The scalability and flexibility of cloud technology allow for the dynamic adjustment of computational resources according to demand, ensuring global optimization and the judicious allocation of resources. © 2024 ieee.

关键词： Cloud platforms

来源：评论

学校读者我要写书评

暂无评论

Voltage Containment and Reactive Power-Sharing in Microgrids: Centralized and distributed Approaches 5

Voltage Containment and Reactive Power-Sharing in Microgrids...

引用

5th international conference on Smart Energy systems and Technologies (SEST)

作者： Abdolmaleki, Babak Bergna-Diaz, Gilbert Norwegian Univ Sci & Technol Dept Elect Power Engn N-7491 Trondheim Norway

ISBN: (数字)9781665405577

ISBN: (纸本)9781665405577

In this article, a secondary voltage controller is proposed for ac microgrids, which ensures proportional reactive power-sharing among the distributed energy resources while their voltages stay within limits. The control objectives are formulated and analyzed as the steady-state control objectives, achieved by a nonlinear secondary controller for the energy resources. Both centralized and distributed forms of the proposed controller are presented, and the closed-loop system equilibrium and stability are discussed briefly. We show that the steady-state control objective is always achieved, if it is feasible. The effectiveness of the controller for different case studies is validated by adapting it to a microgrid system, based on the Conseil international des Grands Reseaux Electriques (CIGRE) benchmark MV distribution network.

关键词： distributed control droop control microgrid reactive power-sharing voltage control voltage stability

来源：评论

学校读者我要写书评

暂无评论

Application Level Synthesis: Creating Matrix-Matrix Multiplication Library: A Case Study

引用

ieee ACCESS 2024年 12卷 155885-155903页

作者： Pudi, Dhilleswararao Yang, Yu Stathis, Dimitrios Prajapati, Sunil Kumar Boppu, Srinivas Hemani, Ahmed Cenkeramaddi, Linga Reddy Indian Inst Technol Bhubaneswar Sch Elect Sci Bhubaneswar 752050 India KTH Royal Inst Technol Div Elect & Embedded Syst S-11428 Stockholm Sweden Indian Inst Technol Bhubaneswar Sch Basic Sci Bhubaneswar 752050 India Univ Agder Dept ICT N-4879 Grimstad Norway

Efficiently synthesizing an entire application that consists of multiple algorithms for hardware implementation is a very difficult and unsolved problem. One of the main challenges is the lack of good algorithmic libraries. A good algorithmic library should contain algorithmic implementations that can be physically composable, and their cost metrics can be accurately predictable. Physical composability and cost predictability can be achieved using a novel framework called SiLago. By physically abutting small hardware blocks together like Lego bricks, the SiLago framework can eliminate the time-consuming logic and physical synthesis and immediately give post-layout accurate cost estimation. In this paper, we build a library for matrix-matrix multiplication algorithm based on the SiLago framework as a case study because matrix-matrix multiplication is a fundamental operation in scientific computing that is frequently found in applications such as signal processing, image processing, pattern recognition, robotics, and so on. This paper demonstrates the methodology to construct such a library containing composable and predictable algorithms so that the application-level synthesis tools can utilize it to explore the design space for an entire application. Specifically, in this paper, we present an algorithm for matrix decomposition, several mapping strategies for selected kernel functions, an algorithm to construct the mapping of each matrix-matrix multiplication, and finally, the method to calculate the cost estimation of each solution.

关键词： Coarse grain reconfigurable architecture field programmable gate array (FPGA) dynamically reconfigurable resource array (DRRA) distributed memory architecture (DiMArch) matrix multiplication high-level synthesis hardware accelerators hardware-software co-design Coarse grain reconfigurable architecture field programmable gate array (FPGA) dynamically reconfigurable resource array (DRRA) distributed memory architecture (DiMArch) matrix multiplication high-level synthesis hardware accelerators hardware-software co-design

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：