检索结果-内蒙古大学图书馆

22nd IEEE Consumer Communications and Networking Conference, CCNC 2025

作者： Gervino, Francesco Eirale, Andrea Chiaberge, Marcello Sacco, Alessio Marchetto, Guido Casetti, Claudio Politecnico di Torino Department of Control and Computer Engineering Italy Politecnico di Torino Department of Electronics and Telecommunications Italy

ISBN: (纸本)9798331508050

Autonomous exploration of complex, unknown environments is a cutting-edge task not entirely solved by the scientific community. When an agent needs to explore a maze without any a priori information about the environment, the lack of proper destinations and explicit task objectives make traditional navigation policies inappropriate. While the literature presents some sporadic deterministic systems able to face the tasks, learning approaches still need an adequate investigation which could prove them to be more suitable and versatile for this purpose. In this paper, we present MARS, a path planner that exploits swarms of robots to optimize the exploration of complex unknown environments, such as mazes. To make the solution scalable, the proposed method exploits two cooperating modules: local and global planners. The local planner is modeled as a Markov Decision Process (MDP) and trained as a Reinforcement Learning (RL) multi-agent system. Each agent has access to image representations of a section of the global map, always centered in the robot reference frame, and decides the next navigation goal to complete the local exploration. The global planner is a deterministic system that recovers the navigation when a local solution is unavailable. The robots share the explored section with peers when they meet in a rendez-vous. We compared our approach to a single deterministic agent, a single RL agent and a close-to-optimal deterministic approach which deploys five greedy agents. The simulation results demonstrate MARS' efficiency, reaching near-optimal levels in significantly less time. © 2025 IEEE.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Mining Erasable Itemsets from a Product Database with Quantitative Components 24

Mining Erasable Itemsets from a Product Database with Quanti...

引用

11th Multidisciplinary International Social Networks Conference, MISNC 2024

作者： Hong, Tzung-Pei Chen, Da Huang, Wei-Ming Tsai, Yu-Chuan Department of Computer Science and Information Engineering National University of Kaohsiung Taiwan Department of Computer Science and Engineering National Sun Yat-Sen University Taiwan Department of Computer Science and Engineering Department of Electrical and Control China Steel Inc. China Library and Information Center National University of Kaohsiung Taiwan

ISBN: (纸本)9798400717550

Erasable itemset mining is one of the most well-known methods in data mining for optimizing limited materials. After mining erasable itemsets, the manager can rearrange the production plan effectively. However, in real applications, traditional mining methods neglect some critical factors, such as costs or quantities of components forming a product. This thesis thus considers mining erasable itemsets from a product database with quantitative components. An erasable profit-based itemset mining (EPIM) algorithm is proposed to mine erasable itemsets with low profits by analyzing the relationships between products and components. In experiments, a synthetic dataset was used to compare the performance in execution speed and memory usage under various threshold settings. It can also be easily generalized to find erasable itemsets satisfying the other criteria with a quantitative product database. © 2024 ACM.

关键词： Mine safety

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Segmentation of Smart Home Position Logs for Human Activity Analysis 19

Unsupervised Segmentation of Smart Home Position Logs for Hu...

引用

19th International Conference on Intelligent Environments, IE 2023

作者： Leotta, Francesco Mecella, Massimo Veneruso, Silvestro Sapienza Università di Roma Department of Computer Control and Management Engineering Rome Italy

ISBN: (纸本)9798350312225

Human activities represent a major source of information for smart home automation. While performing their daily activities, humans trigger sensors producing measurements that flow into a sensor log. Vast majority of techniques to recognize and exploit the occurrences of human activities are supervised, requiring the log to be manually labeled in correspondence of the onset and the end of each activity repetition. This task requires a considerable effort by the final user, resulting in imprecise labeling tampering the performance of algorithms. In this paper, we propose an unsupervised technique allowing to automatically segment smart home logs containing position sensor measurements. The proposed technique exploits information about the position of the human to automatically extract basic actions, which are then segmented on a temporal basis and clustered. The approach is evaluated against a state-of-the-art dataset. © 2023 IEEE.

关键词： Automation

来源：评论

学校读者我要写书评

暂无评论

Pneumonia Detection from X-ray Images Using Convolutional Neural Networks 24

Pneumonia Detection from X-ray Images Using Convolutional Ne...

引用

24th International Conference on control Systems and computer Science, CSCS 2023

作者： Dediu, Viorel Udrea, Andreea Faculty of Automatic Control and Computer Science Univesity Politehnica of Bucharest Department of Automatic Control and Systems Engineering Bucharest Romania

ISBN: (纸本)9798350313390

Pneumonia is one of the top causes of death in Romania and early detection of this disease improves the recovery chances and shortens the length of hospitalization. In this work, we develop a solution for automatic pneumonia detection based on convolutional neural networks. Four network models are investigated. They are trained on 4.163 images from a public dataset and tested on 530 images. The best results are obtained by one of the proposed models conducting to a sensitivity of 98.72%, an accuracy of 89.81%, and ROC 93.46%. Thus, this research proposes a lightweight screening tool that can help triaging the patients with pneumonia. © 2023 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Machine Learning for Fog Computing: Perceiving QoE for IoT Applications

Machine Learning for Fog Computing: Perceiving QoE for IoT A...

引用

作者： Ahmed, Eman Nashaat, Heba Rizk, Rawya Computer and Control Department Faculty of Engineering Port-Said University Port-Said Egypt

Since the Internet of Things (IoT) is a rapidly growing industry, so does the range of IoT applications;IoT transforms every aspect of our lives, from smart homes and cities to healthcare and agriculture. With the increasing popularity of IoT applications in many different areas, the round-trip delay of data processing in the cloud affects the user’s quality perception. A portable operating system distribution, high environmental consistency, and resource isolation are all features of the lightweight application virtualization technology known as containerization. Mainstream cloud service providers for automated application administration have widely incorporated container technologies into distributed system architectures. However, the distributed nature of cloud and edge computing environments and workloads significantly increases the complexity of orchestration systems. Therefore, the Quality of Experience (QoE) is required for Internet of Things (IoT) applications. Machine Learning (ML) algorithms are employed by container orchestration systems for modeling, predicting the multi-dimensional performance metrics, and improving the overall QoE. The main objective of this paper is to provide a comprehensive review of existing machine learning enablement of container orchestration. Moreover, we discuss and classify the ML implementation challenges in IoT applications and enlist the applications of machine learning algorithms with IoT. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Containers

来源：评论

学校读者我要写书评

暂无评论

CO2 Emission Mitigation in Container-Based Cloud Computing by the Power of Resource Management

CO2 Emission Mitigation in Container-Based Cloud Computing b...

引用

作者： Ashry, Nesma Attia, Radwa Nashaat, Heba Rizk, Rawya Computer and Control Department Faculty of Engineering Port-Said University Port-Said Egypt

The increasing amount of data processing through cloud systems leads to high energy costs and CO2 emissions challenges. Advanced monitoring tools are used to track resource utilization and identify possible optimization areas to mitigate CO2 emissions and reduce energy consumption. Thus, resource and power management in cloud environments is essential to ensure efficient performance and effective cost. Recently, container-based clouds become more widely used than hypervisor-based clouds. Scheduling the huge number of user-submitted tasks and optimizing both network and cloud resources are important aspects of cloud computing to decrease network overhead, reduce both Data Center (DC) energy consumption and Service-Level Agreement (SLA) violations and in turn, mitigate CO2 emissions. However, the state-of-the-art resource schedulers that consider power management and network transmissions are unfortunately not container-aware schedulers. The main objective of this paper is to introduce a solid analysis of the most significant techniques and tools in resource management to minimize power consumption and CO2 emissions with the advantage of being a container-aware scheduler;Applying the first stage of the proposed solution leads to mitigating the CO2 by an average of 2.12% against the Non-Clustered approach and 18.04% against the Clustered approach. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Containers

来源：评论

学校读者我要写书评

暂无评论

A dual adaptive unscented Kalman filter algorithm for SINS-based integrated navigation system

引用

Journal of Systems engineering and Electronics 2024年第3期35卷 732-740页

作者： LYU Xu MENG Ziyang LI Chunyu CAI Zhenyu HUANG Yi LI Xiaoyong YU Xingkai Department of Precision Instrument Tsinghua UniversityBeijing 100084China College of Mechanical and Power Engineering Three Gorges UniversityYichang 443002China Unit 91001 of the PLA Beijing 100161China School of Control and Computer Engineering North China Electric Power UniversityBeijing 100096China

In this study, the problem of measuring noise pollution distribution by the intertial-based integrated navigation system is effectively suppressed. Based on nonlinear inertial navigation error modeling, a nested dual Kalman filter framework structure is developed. It consists of unscented Kalman filter (UKF)master filter and Kalman filter slave filter. This method uses nonlinear UKF for integrated navigation state estimation. At the same time, the exact noise measurement covariance is estimated by the Kalman filter dependency filter. The algorithm based on dual adaptive UKF (Dual-AUKF) has high accuracy and robustness, especially in the case of measurement information interference. Finally, vehicle-mounted and ship-mounted integrated navigation tests are conducted. Compared with traditional UKF and the Sage-Husa adaptive UKF (SH-AUKF), this method has comparable filtering accuracy and better filtering stability. The effectiveness of the proposed algorithm is verified.

关键词： Kalman filter dual-adaptive integrated navigation unscented Kalman filter(UKF) robust

来源：评论

学校读者我要写书评

暂无评论

Semi-mind controlled robots based on Reinforcement Learning for Indoor Application 8

Semi-mind controlled robots based on Reinforcement Learning ...

引用

8th International Conference of Yearly Reports on Informatics, Mathematics, and engineering, ICYRIME 2023

作者： Naidji, Ilyes Tibermacine, Ahmed Guettala, Walid Tibermacine, Imad Eddine Department of Computer Science University Mohamed Khider of Biskra Algeria Department of Computer Control and Management Engineering Sapienza University of Rome Italy

This paper presents a solution to this challenge by introducing interactive feedback derived from brain signals to train robots using deep reinforcement learning, particularly in the context of indoor maze navigation. Our objective is to enhance the learning process in a human-robot interaction scenario by incorporating human emotion or attention feedback. To accomplish this, we empowered the robot to learn new tasks through a dynamic policy network based on human feedback, and we augmented this input with other sensor data, including LIDAR. Various experiments are conducted to compare the efficacy of manual feedback, brain signal feedback, and no brain signal feedback, employing diverse Reinforcement Learning models. Additionally, we explore different models for emotion classification, employing Graph Neural Network models and traditional deep learning models, and subsequently compare the outcomes. © 2023 Copyright for this paper by its authors.

关键词： Feedback

来源：评论

学校读者我要写书评

暂无评论

Robust and fault-tolerant spacecraft attitude control based on an extended-observer design

引用

control Theory and Technology 2022年第3期20卷 323-337页

作者： Alessandro Giuseppi Francesco Delli Priscoli Antonio Pietrabissa Department of Computer Control and Management EngineeringLa SapienzaUniversity of RomeVia Ariosto 25Rome00185Italy

The aim of this work is to develop a robust control strategy able to drive the attitude of a spacecraft to a reference value,despite the presence of unknown but bounded uncertainties in the system parameters and external *** to the use of an extended observer design,the proposed control law is robust against all the uncertainties that affect the high-frequency gain matrix,which is shown to capture a broad spectrum of modelling issues,some of which are often neglected by traditional *** proposed controller then provides robustness against parametric uncertainties,as moment of inertia estimation,payload deformations,actuator faults and external disturbances,while maintaining its asymptotic properties.

关键词： Extended observer Spacecraft control Attitude stabilization

来源：评论

学校读者我要写书评

暂无评论

A Dual-Stage Optimal controller Design for controlling AVR System 27

A Dual-Stage Optimal Controller Design for Controlling AVR S...

引用

27th International computer Science and engineering Conference, ICSEC 2023

作者： Abood, Layla H. Mohamed, Mohamed J. Abood, May H. University of Technology Department of Control and System Engineering Baghdad Iraq Al-Iraqia University Department of Computer Engineering Baghdad Iraq

ISBN: (纸本)9798350342109

In this study a cascade controller is proposed to maintain the Automatic Voltage Regulator (AVR) system, its comprises from two stage the first one is a conventional Proportional and Derivative (PD) controller and the second one is a Fractional Order PID (FOPID) controller is combined together for regulating the terminal voltage in AVR system, the gains of the proposed controller is tuned used a smart optimization algorithm called Squirrel Search algorithm (SSA) and adopt an Integral Time Absolute Error (ITAE) for monitoring for monitoring desired response to obtain a stable and robust response, the system response is tested using Matlab 2019 and the transient analysis is used to calculate overshoot, settling time, rise time, and peak time then compared these values selected classical controllers(PID,FOPID) to verify the robust response of the proposed controller. A robustness analysis verified the system response when there is an external disturbances, positive and negative disturbances signals are added, the controller try to face these signals, it takes 0.15 sec in negative disturbance and 0.1 sec in positive disturbance then in both states force the response to return to its desired response. © 2023 IEEE.

关键词： controllers

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：