检索结果-内蒙古大学图书馆

GenSafe: A Generalizable Safety Enhancer for Safe Reinforcement Learning Algorithms Based on Reduced Order Markov Decision Process Model

引用

IEEE Transactions on Neural Networks and Learning Systems 2024年第6期36卷 10678-10692页

作者： Zhehua Zhou Xuan Xie Jiayang Song Zhan Shu Lei Ma Department of Electrical and Computer Engineering University of Alberta Edmonton AB Canada Department of Computer Science The University of Tokyo Tokyo Japan

Safe reinforcement learning (SRL) aims to realize a safe learning process for deep reinforcement learning (DRL) algorithms by incorporating safety constraints. However, the efficacy of SRL approaches often relies on accurate function approximations, which are notably challenging to achieve in the early learning stages due to data insufficiency. To address this issue, we introduce, in this work, a novel generalizable safety enhancer (GenSafe) that can overcome the challenge of data insufficiency and enhance the performance of SRL approaches. Leveraging model order reduction techniques, we first propose an innovative method to construct a reduced order Markov decision process (ROMDP) as a low-dimensional approximator of the original safety constraints. Then, by solving the reformulated ROMDP-based constraints, GenSafe refines the actions of the agent to increase the possibility of constraint satisfaction. Essentially, GenSafe acts as an additional safety layer for SRL algorithms. We evaluate GenSafe on multiple SRL approaches and benchmark problems. The results demonstrate its capability to improve safety performance, especially in the early learning phases, while maintaining satisfactory task performance. Our proposed GenSafe not only offers a novel measure to augment existing SRL methods but also shows broad compatibility with various SRL algorithms, making it applicable to a wide range of systems and SRL problems.

关键词： Safety Costs Data models Computational modeling Accuracy Optimization Markov decision processes Lyapunov methods Function approximation Prediction algorithms

来源：评论

学校读者我要写书评

暂无评论

Optimization of SVM Based on IPSO Algorithm for Tool Life Prediction 6

Optimization of SVM Based on IPSO Algorithm for Tool Life Pr...

引用

6th International Conference on computer Network, Electronic and Automation, ICCNEA 2023

作者： Gao, Xianghong Cao, Yan Xi'an Technological University School of Mechanical and Electrical Engineering Xi'an China Xi'an Technological University School of Computer Science and Engineering Xi'an China

ISBN: (纸本)9798350305388

As the basic parts of workshop processing, the life of the tool will affect the processing efficiency and processing quality, and the life of the tool will be affected by a variety of uncertain factors in the processing process, which makes it difficult to accurately predict. In order to improve the prediction accuracy, an improved IPSO algorithm was proposed to optimize the penalty factor c and kernel parameter g of SVM based on particle swarm optimization (PSO). Firstly, the influencing parameters of tool life are analyzed and the experimental data are extracted, and then the data is brought into the IPSO-SVM model to obtain the predicted data. IPSO algorithm can realize the adaptive change of inertia weight and introduce asynchronous learning formula to dynamically adjust the learning factor, which can effectively improve the prediction accuracy of tool life. Compared with the traditional PSO-SVM prediction model, the average relative error and average absolute error of IPSO-SVM are reduced by 5.275% and 5.006% respectively, which indicates that the SVM model optimized by IPSO algorithm has higher prediction accuracy. © 2023 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Smart Roads: Lighting the Way to Safety and Efficiency 26

Smart Roads: Lighting the Way to Safety and Efficiency

引用

26th International Conference on computer and Information Technology, ICCIT 2023

作者： Hasan, Shakibul Raxit, Srabone Jahan, Israt Hossain, Md Sajid Ramisa Samiha, Kazi Zayad, Ahnaf Abdullah Hossain, Rifat American International University-Bangladesh Computer Science and Engineering Dhaka Bangladesh American International University-Bangladesh Electrical and Electronic Engineering Dhaka Bangladesh

ISBN: (纸本)9798350359015

The "Smart Roads: Lighting the Way to Safety and Efficiency"project introduces an innovative solution to improve the efficiency and sustainability of outdoor lighting systems. This research focuses on developing automated streetlights and introduces the indication concept for over-speeding drivers. The primary objectives of this design are to conserve energy, improve road traffic safety, and lower casualties from road traffic collisions. By harnessing LDR, Ultrasonic sensor, and Arduino board, the proposed streetlights can automatically detect ambient lighting conditions and respond accordingly. These smart streetlights are programmed to activate during nighttime (or overcast days) and remain off during daylight hours, thereby optimizing energy usage. An Ultrasonic sensor is introduced that detects any vehicle from a distance and activates the Streetlights as the vehicle approaches. Even so, using the data from the Ultrasonic sensor, the speed of vehicles is measured, and drivers are warned using additional lights at the mid-bottom of the lamp post. The significance of this project lies in its potential to revolutionize urban lighting infrastructure. The technology's accessibility and affordability can lead to a widespread adaptation, contributing to broader societal benefits. © 2023 IEEE.

关键词： Arduino LDR Speed Streetlights Ultrasonic

来源：评论

学校读者我要写书评

暂无评论

A Framework for Optimizing Multilevel AC Battery Energy Storage Systems 24

A Framework for Optimizing Multilevel AC Battery Energy Stor...

引用

24th IEEE Workshop on Control and Modeling for Power Electronics, COMPEL 2023

作者： Ramyar, Alireza Siegel, Jason B. Avestruz, Al-Thaddeus University of Michigan Electrical Engineering and Computer Science Ann Arbor United States University of Michigan Mechanical Engineering Ann Arbor United States

ISBN: (纸本)9798350316186

Battery energy storage systems (BESS) play an essential role in modern grids by supporting renewable power systems, improving grid power quality through voltage and frequency regulation, and supporting electric vehicle (EV) charging stations. At the same time, and with the rapid growth of EVs, an enormous number of EV batteries will be retired soon. These second-use EV batteries still have approximately 80% capacity and can be utilized in stationary applications like grid-connected BESSs to reduce the emissions from producing new batteries for energy storage systems. Directly producing multilevel AC from batteries reduces cost by eliminating the need for an explicit conventional inverter. In this paper, a framework is presented for optimizing the multilevel integration of power processing in BESSs, which is particularly applicable to BESSs with heterogeneous second-use batteries. © 2023 IEEE.

关键词： Power quality

来源：评论

学校读者我要写书评

暂无评论

Near-end Intelligibility Improvement Through Voice Transformation in Transfer Learning Framework 31

Near-end Intelligibility Improvement Through Voice Transform...

引用

31st European Signal Processing Conference, EUSIPCO 2023

作者： Biswas, Ritujoy Nathwani, Karan Abrol, Vinayak Dept. of Electrical Engineering IIT Jammu India Infosys Centre for AI Dept. of Computer Science and Engineering IIIT Delhi India

ISBN: (纸本)9789464593600

In recent works, using voice transformation functions (VTF) in optimal shifting of formants has improved near-end speech intelligibility. Though these VTFs are promising, they are computationally expensive to optimize and generate unwanted artifacts during voice modification. Additionally, they were specific to the environmental condition they were optimized for. For the applicability of this approach to different languages without re-optimization, transfer learning (TL) was used to shape the parameters of VTF to accommodate the target language [1]. However, TL across noises and TL across languages and noises (simultaneously) was not viable due to the dependency on pitch information of source and target noises. Hence in this work, a statistical Gaussian Transformation Function (GTF) is developed with parameters optimized for specific environmental conditions. Defined by just three parameters, the optimization time came down, and the intelligibility surpassed the previously used VTF. Additionally, GTF allows TL across both noises and languages simultaneously, with fewer artifacts while shifting the formants. © 2023 European Signal Processing Conference, EUSIPCO. All rights reserved.

关键词： Speech intelligibility

来源：评论

学校读者我要写书评

暂无评论

Advanced Frequency Control for Renewable and Electric Vehicle Integrated Systems

Advanced Frequency Control for Renewable and Electric Vehicl...

引用

2023 IEEE IAS Global Conference on Emerging Technologies, GlobConET 2023

作者： Pandit, Deepak Saket, Ram K. Cai, Niannian Nguyen, Nga University of Wyoming Electrical Engineering and Computer Science LaramieWY United States Department of Electrical Engineering Uttar Pradesh Varanasi India Google AustinTX United States

ISBN: (纸本)9798350331790

Modern power systems are experiencing a rapid movement from fossil-based generations to renewable energy resources (RERs) due to concerns about the environment and the dependence on fossil fuel sources. However, the replacement of conventional generation with intermittent and low inertia RERs in the power grid can negatively affect system regulation capability. Also, the increasing integration of electric vehicles (EVs) presents concerns over power system stability and reliability. To maintain the frequency of the system within stable limits, load frequency control (LFC) regulates the power output of the generating units in response to the changes in load demand. Therefore, appropriate control strategies and optimization algorithms are required for effective LFC while RER/EV penetration increases. In this paper, an advanced LFC model of a multi-area interconnected system with EV and RER integration is developed which considers the change in system inertia that arises from generator outages or the replacement of conventional units with RERs. A non-sequential Monte Carlo simulation (MCS) is implemented to calculate the system inertia and regulation capacity of each area considering the generator failure rates and load changes. The contribution of inertial response and primary frequency regulation from EVs to the system is assessed using a simulation-based approach. A particle swarm optimization (PSO) algorithm is used to tune the parameters of the PID controllers. The efficacy of the developed algorithm is demonstrated on a two-area model of the IEEE RTS-96 system with varying RER penetration levels. © 2023 IEEE.

关键词： Renewable energy resources

来源：评论

学校读者我要写书评

暂无评论

Characterization of All Optimal Finite-length Codes of Size Four for Binary Symmetric Channels

Characterization of All Optimal Finite-length Codes of Size ...

引用

2023 IEEE International Symposium on Information Theory, ISIT 2023

作者： Dong, Yanyan Yang, Shenghao National University of Singapore Department of Electrical and Computer Engineering Singapore The Chinese University of Hong Kong Shenzhen School of Science and Engineering Shenzhen China

ISBN: (纸本)9781665475549

The search for optimal finite-length binary block codes is a long-standing open problem for memoryless binary symmetric channels (BSCs) with the maximum likelihood decoding. A recent work studied the optimal codes among all binary codes of size four, including both linear codes and nonlinear codes, and showed the existence of optimal codes in the set composed of linear codes and Class-I codes for any given blocklength. Furthermore, for blocklength up to 300, it has been shown that there exists a linear code that is optimal among all the codes of size four. However, it is unknown whether there are optimal codes outside the set of linear codes and Class-I codes for a general blocklength. In this paper, we derive a subset of nonlinear codes called Class-II codes and justify that the set composed of linear, Class-I and Class-II codes and their equivalent codes includes all the optimal codes of size four when the blocklength is not equal to 3. For blocklength 3, we verify that there are nonlinear codes (not equivalent to linear, Class-I or Class-II codes) that are optimal. For the blocklength from 2 to 300 and not equal 3, our computer evaluations show that no nonlinear code is optimal except for the ones that are equivalent to linear codes. Moreover, we characterize all the best codes among all linear codes of size four for any given blocklength. © 2023 IEEE.

关键词： Optimal systems

来源：评论

学校读者我要写书评

暂无评论

Multiscale aggregation and illumination-aware attention network for infrared and visible image fusion

Multiscale aggregation and illumination-aware attention netw...

引用

作者： Song, Wenhao Zhai, Wenzhe Gao, Mingliang Li, Qilei Chehri, Abdellah Jeon, Gwanggil School of Electrical and Electronic Engineering Shandong University of Technology Zibo China School of Electronic Engineering and Computer Science Queen Mary University of London London United Kingdom Department of Mathematics and Computer Science Royal Military College of Canada Kingston Canada Department of Embedded Systems Engineering Incheon National University Incheon Korea Republic of

Image fusion plays a significant role in computer vision since numerous applications benefit from the fusion results. The existing image fusion methods are incapable of perceiving the most discriminative regions under varying illumination circumstances and thus fail to emphasize the salient targets and ignore the abundant texture details of the infrared and visible images. To address this problem, a multiscale aggregation and illumination-aware attention network (MAIANet) is proposed for infrared and visible image fusion. Specifically, the MAIANet consists of four modules, namely multiscale feature extraction module, lightweight channel attention module, image reconstruction module, and illumination-aware module. The multiscale feature extraction module attempts to extract multiscale features in the images. The role of the lightweight channel attention module is to assign different weights to each channel so as to focus on the essential regions in the infrared and visible images. An illumination-aware module is employed to assess the probability distribution regarding the illumination factor. Meanwhile, an illumination perception loss is formulated by the illumination probabilities to enable the proposed MAIANet to better adjust to the changes in illumination. Experimental results on three datasets, that is, MSRS, TNO, and RoadSence, verify the effectiveness of the MAIANet in both qualitative and quantitative evaluations. © 2023 John Wiley & Sons, Ltd.

关键词： Image fusion

来源：评论

学校读者我要写书评

暂无评论

An Innovative Next Activity Prediction Approach Using Process Entropy and DAW-Transformer

arXiv

引用

arXiv 2025年

作者： Zare, Hadi Abbasi, Mostafa Ahang, Maryam Najjaran, Homayoun Department of Electrical and Computer Engineering Faculty of Engineering and Computer Science University of Victoria Victoria Canada Department of Mechanical Engineering Faculty of Engineering and Computer Science University of Victoria Victoria Canada

Purpose - In Business Process Management (BPM), accurate prediction of the next activities is vital for operational efficiency and decision-making. Current Artificial Intelligence (AI)/Machine Learning (ML) models struggle with the complexity and evolving nature of business process event logs, balancing accuracy and interpretability. This paper proposes an entropy-driven model selection approach and DAW-Transformer, which stands for Dynamic Attribute-Aware Transformer, to integrate all attributes with a dynamic window for better accuracy. Design/methodology/approach - This paper introduces a novel next-activity prediction approach that uses process entropy to assess the complexity of event logs and dynamically select the most suitable ML model. A new transformer-based architecture with multi-head attention and dynamic windowing mechanism, DAW-Transformer, is proposed to capture long-range dependencies and utilize all relevant event log attributes. Experiments were conducted on six public datasets, and the performance was evaluated with process entropy. Finding - The results demonstrate the effectiveness of the approach across these publicly available datasets. DAW-Transformer achieved superior performance, especially on high-entropy datasets such as Sepsis exceeding Limited window Multi-Transformers by 4.69% and a benchmark CNN-LSTM-SAtt model by 3.07%. For low-entropy datasets like Road Traffic Fine, simpler, more interpretable algorithms like Random Forest performed nearly as well as the more complex DAW-Transformer and offered better handling of imbalanced data and improved explainability. Originality/ value - This work’s novelty lies in the proposed DAW-Transformer, with a dynamic window and considering all relevant attributes. Also, entropy-driven selection methods offer a robust, accurate, and interpretable solution for next-activity prediction. © 2025, CC BY-NC-SA.

关键词： Administrative data processing

来源：评论

学校读者我要写书评

暂无评论

Embedded Coded Relay System for Molecular Communications

引用

computers, Materials & Continua 2022年第8期72卷 2729-2748页

作者： Eman S.Attia Ashraf A.M.Khalaf Fathi E.Abd El-Samie Saied M.Abd El-atty Konstantinos A.Lizos Osama Alfarraj Farid Shawki Imran Khan Ki-Il Kim Department of Electrical Engineering Faculty of EngineeringMinia UniversityMiniaEgypt Department of Electronics and Electrical Communications Faculty of Electronic EngineeringMenoufia UniversityMenoufiaEgypt Department of Informatics Faculty of Mathematics and Natural SciencesUniversity of Oslo(UiO)Norway Computer Science Department Community CollegeKing Saud UniversityRiyadh11437Saudi Arabia Department of Electrical Engineering University of Engineering&TechnologyPeshawar814Pakistan Department of Computer Science and Engineering Chungnam National UniversityDaejeon34134Korea

With the emergence of the COVID-19 pandemic,the World Health Organization(WHO)has urged scientists and industrialists to exploremodern information and communication technology(ICT)as a means to reduce or even eliminate *** World Health Organization recently reported that the virus may infect the organism through any organ in the living body,such as the respiratory,the immunity,the nervous,the digestive,or the cardiovascular *** the abovementioned goal,we envision an implanted nanosystem embedded in the intra living-body *** main function of the nanosystem is either to perform diagnosis and mitigation of infectious diseases or to implement a targeted drug delivery system(i.e.,delivery of the therapeutic drug to the diseased tissue or targeted cell).The communication among the nanomachines is accomplished via communication-based molecular *** control/interconnection of the nanosystem is accomplished through the utilization of Internet of bio-nano things(IoBNT).The proposed nanosystem is designed to employ a coded relay nanomachine disciplined by the decode and forward(DF)principle to ensure reliable drug delivery to the targeted ***,both the sensitivity of the drug dose and the phenomenon of drug molecules loss before delivery to the target cell site in long-distance due to the molecules diffusion process are taken into *** this paper,a coded relay NM with conventional coding techniques such as RS and Turbo codes is selected to achieve minimum bit error rate(BER)performance and high signal-to-noise ratio(SNR),while the detection process is based on maximum likelihood(ML)probability and minimum error probability(MEP).The performance analysis of the proposed scheme is evaluated in terms of channel capacity and bit error rate by varying system parameters such as relay position,number of released molecules,relay and receiver *** results are validated through simulation and demonstrate that the proposed scheme can

关键词： Molecular communication nanonetwork internet of bio-nano things coded relay scheme coding

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：