检索结果-内蒙古大学图书馆

Deep Learning and Projection Neural Network With Finite-Time Convergence for Energy Management of Multi-Energy system

引用

IEEE Transactions on Smart Grid 2025年第3期16卷 2156-2168页

作者： Liu, Xueying He, Xing Li, Chaojie Huang, Tingwen Southwest University Chongqing Key Laboratory of Nonlinear Circuits and Intelligent Information Processing College of Electronic and Information Engineering Chongqing400715 China North China Electric Power University State Key Laboratory of Alternate Electrical Power System With Renewable Energy Sources Beijing102206 China Shenzhen University of Advanced Technology Faculty of Computer Science and Control Engineering Shenzhen518055 China

In this paper, an approach based on projection neural network (PNN), sliding mode control technique, and deep learning is proposed to solve the energy management problem of multi-energy systems (MES) containing dynamic parameters. First, the sliding mode technique is introduced in the PNN to design a finite-time PNN (FTPNN). The stability and finite-time convergence of the proposed FTPNN are proved by the Lyapunov method and the setting time bound is given. Then, the deep FTPNN (DFTPNN) is designed by combining deep learning with the proposed FTPNN. The dynamic parameters in the MES that change over time are used as input variables for the DFTPNN, allowing the trained DFTPNN to respond immediately to changes in the dynamic parameters and to predict the solutions of the FTPNN with different parameters directly. Simulation experiments show that FTPNN has faster convergence compared to PNN. DFTPNN significantly reduces the computation time compared to FTPNN. DFTPNN provides predicted solutions to FTPNN. Since DFTPNN can respond immediately to changes in dynamic parameters and directly provide energy management strategies under different parameters, it can adapt to changing environments and promote the economic and stable operation of MES. © 2010-2012 IEEE.

关键词： Cogeneration Heuristic algorithms Convergence Deep learning Prediction algorithms Optimization Heating systems Energy management Approximation algorithms Power system stability

来源：评论

学校读者我要写书评

暂无评论

Stochastic Trajectory Optimization for Robotic Skill Acquisition From a Suboptimal Demonstration

引用

IEEE Robotics and Automation Letters 2025年第6期10卷 6127-6134页

作者： Ming, Chenlin Wang, Zitong Zhang, Boxuan Cao, Zhanxiang Duan, Xiaoming He, Jianping Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education of China Department of Automation Shanghai China School of Computation Information and Technology Germany Shanghai Jiao Tong University Department of Computer Science and Engineering Shanghai China Shanghai Jiao Tong University State Key Laboratory of Submarine Geoscience the Department of Automation Shanghai200240 China

Learning from Demonstration (LfD) has emerged as a crucial method for robots to acquire new skills. However, when given suboptimal task trajectory demonstrations with shape characteristics reflecting human preferences but subpar dynamic attributes such as slow motion, robots not only need to mimic the behaviors but also optimize the dynamic performance. In this work, we leverage optimization-based methods to search for a superior-performing trajectory whose shape is similar to that of the demonstrated trajectory. Specifically, we use Dynamic Time Warping (DTW) to quantify the difference between two trajectories and combine it with additional performance metrics, such as collision cost, to construct the cost function. Moreover, we develop a multi-policy version of the Stochastic Trajectory Optimization for Motion Planning (STOMP), called MSTOMP, which is more stable and robust to parameter changes. To deal with the jitter in the demonstrated trajectory, we further utilize the gain-controlling method in the frequency domain to denoise the demonstration and propose a computationally more efficient metric, called Mean Square Error in the Spectrum (MSES), that measures the trajectories' differences in the frequency domain. We also theoretically highlight the connections between the time domain and the frequency domain methods. Finally, we verify our method in both simulation experiments and real-world experiments, showcasing its improved optimization performance and stability compared to existing methods. © 2016 IEEE.

关键词： Frequency domain analysis

来源：评论

学校读者我要写书评

暂无评论

Path Optimization Method Under UAV Charging Scheduling Network 24th

Path Optimization Method Under UAV Charging Scheduling Netwo...

引用

24th International Conference on Algorithms and architectures for Parallel Processing, ICA3PP 2024

作者： Yang, Tingting Wang, Yiqian Zhu, Jie Chang, Shuyu Huang, Haiping Nanjing University of Posts and Telecommunications Nanjing210003 China State Key Laboratory Chinese of Computer Architecture Institute of Computing Technology Academy of Sciences Beijing100864 China Jiangsu High Technology Research Key Laboratory for Wireless Sensor Networks Nanjing210003 China

ISBN: (纸本)9789819615278

Unmanned Aerial Vehicles (UAVs) have emerged as integral components in logistics systems, where their potential for efficient delivery services is being explored. However, the limited battery capacity of UAVs poses a significant challenge for long-distance delivery applications. In this paper, we investigate a hybrid problem involving UAV trajectory planning and charging scheduling for long-distance logistics systems with a charging network. In the problem under study, multiple UAVs are assigned long-distance delivery tasks. A UAV can stop at any charging station in the charging network to charge if it is in a low-energy state. An Ant Colony Optimization-based UAV Trajectory Planning and Charging Scheduling (ACO-TPCS) algorithm is proposed to minimize task completion time by optimizing UAV trajectory and charging plans. The main framework of the ACO-TPCS algorithm consists of several key components, including reachable graph construction, candidate flight path generation, pheromone matrix construction, ant generation, feasible solution generation, and pheromone update method. All these components are delicately designed. Through extensive experimentation and comparison with baseline algorithms, we demonstrate the effectiveness of the ACO-TPCS algorithm in addressing the problem under study. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Ant colony optimization

来源：评论

学校读者我要写书评

暂无评论

Air traffic complexity assessment based on multi-scale spatio-temporal data 4

Air traffic complexity assessment based on multi-scale spati...

引用

2024 4th International Conference on Intelligent Traffic systems and Smart City, ITSSC 2024

作者： Zhou, Zhihui Chen, Haiyan Fu, Yirui Yuan, Ligang State Key Laboratory of Air Traffic Management System Nanjing China College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics Nanjing China College of Civil Aviation Nanjing University of Aeronautics and Astronautics Nanjing China

ISBN: (纸本)9781510686304

Accurately assessing air traffic complexity is crucial for ensuring flight safety and efficiency. In this paper, we propose an air traffic complexity assessment method based on multi-scale spatio-temporal images. We first convert numerical air traffic data collected by surveillance radar into image data, and then interpolate the spatial and temporal scales of the images to generate multiple sets of images with different spatial and temporal scales. We found the best image set based on the Circle metric learning model by evaluating the performance of 20 image sets combined from different spatiotemporal scales. On this image set, we applied multiple deep metric learning methods to assess air traffic complexity. The results show that the new dataset performs better on several assessment metrics, confirming the validity of the approach to improve air traffic complexity assessment by adjusting the data scale. This demonstrates that the accuracy of air traffic complexity assessment can be effectively improved by adjusting the data scale. It also demonstrates the importance of choosing the right scale of dataset to improve the performance of machine learning algorithms. © 2025 SPIE.

关键词： Air transportation

来源：评论

学校读者我要写书评

暂无评论

A flight slots allocation method for single airport based on Q-Learning algorithm 4

A flight slots allocation method for single airport based on...

引用

2024 4th International Conference on Intelligent Traffic systems and Smart City, ITSSC 2024

作者： Fang, Xinyi Chen, Haiyan Qian, Yuhang Yang, Lei State Key Laboratory of Air Traffic Management System Nanjing China College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics Nanjing China College of Civil Aviation Nanjing University of Aeronautics and Astronautics Nanjing China

ISBN: (纸本)9781510686304

The air traffic demand surpasses the capacity of most of the busiest airports worldwide. The mismatch between airport capacity and air traffic demand leads to serious congestion and delay problems. Since airport capacity is difficult to expand in a short time, in order to reduce flight delays, we need to adjust and optimize flight slots for flight applications, and allocate flight time resources scientifically and efficiently under the premise of meeting airspace resource constraints such as airport capacity. In this paper, we proposed an airport flight slots allocation method based on the Q-Learning algorithm in reinforcement learning. Firstly, we preprocess the original data set. Data cleaning processes data with missing attribute values and removes irrelevant attributes. Through data transformation, the data of string attribute is transformed into discrete numbers, and the time attribute is processed. After that, we construct a mathematical model of single-airport flight time allocation, which is a combinatorial optimization problem and determines the optimization objectives and constraints. Then we apply the reinforcement learning algorithm Q-Learning to solve this optimization problem, and the algorithm updates the strategy through interaction with the environment to get a better solution. Finally, we take Guangzhou Baiyun International Airport as a study case to train and verify the proposed single-airport flight time allocation model. The experimental results show that, the optimized flight slots satisfy the airport capacity constraints while minimizing the adjustment of flight schedules as much as possible, and adjust the flights at some times to alleviate the congestion. © 2025 SPIE ·

关键词： Combinatorial optimization

来源：评论

学校读者我要写书评

暂无评论

Optimizing Self-training Sample Selection for Euphemism Detection in Special Scenarios 24th

Optimizing Self-training Sample Selection for Euphemism Dete...

引用

24th International Conference on Algorithms and architectures for Parallel Processing, ICA3PP 2024

作者： Zhang, Zhiwei Chang, Shuyu Huang, Haiping Wang, Rui Nanjing University of Posts and Telecommunications Nanjing210023 China Jiangsu High Technology Research Key Laboratory for Wireless Sensor Networks Nanjing210023 China Nanjing University of Posts and Telecommunications Nanjing210023 China State Key Laboratory Chinese of Computer Architecture Institute of Computing Technology Academy of Sciences Beijing100864 China

ISBN: (纸本)9789819615476

Euphemism, which is often used to disguise true intentions or soften the tone of speech, has garnered significant attention for its detection in recent years. Current approaches to euphemism detection struggle with uncommon data, where new and rare vocabularies frequently emerge in the test set, leading to decreased model performance. To address these challenges, we propose a novel framework that combines data augmentation, self-training, and a special sample selection method. We expand the original dataset using lexical and sentence-level data augmentation techniques, enhancing the representation of rare vocabulary and allowing the model to familiarize itself with their contexts and usage characteristics. Next, we employ self-training as a semi-supervised learning approach, utilizing the augmented datasets to iteratively generate and refine pseudo-labels. During each iteration, a KNN framework is used to generate pseudo-labels by searching for the nearest neighbor texts, thus enhancing the quality of these labels. Finally, to further increase the presence of rare vocabulary in the training data, we implement a sample selection strategy based on euphemism frequency and predictive uncertainty, integrating it with the earlier steps. Experimental results demonstrate that our framework outperforms previous research on most metrics and achieves a 10% increase over the baseline model. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Towards an effective method of ReDoS detection for non-backtracking engines 24

Towards an effective method of ReDoS detection for non-backt...

引用

Proceedings of the 33rd USENIX Conference on Security Symposium

作者： Weihao Su Hong Huang Rongchen Li Haiming Chen Tingjian Ge Key Laboratory of System Software (Chinese Academy of Sciences) and State Key Laboratory of Computer Science Institute of Software Chinese Academy of Sciences and University of Chinese Academy of Sciences Key Laboratory of System Software (Chinese Academy of Sciences) and State Key Laboratory of Computer Science Institute of Software Chinese Academy of Sciences Miner School of Computer & Information Sciences University of Massachusetts Lowell

ISBN: (纸本)9781939133441

Regular expressions (regexes) are a fundamental concept across the fields of computer science. However, they can also induce the Regular expression Denial of Service (Re-DoS) attacks, which are a class of denial of service attacks, caused by super-linear worst-case matching time. Due to the severity and prevalence of ReDoS attacks, the detection of ReDoS-vulnerable regexes in software is thus vital. Although various ReDoS detection approaches have been proposed, these methods have focused mainly on backtracking regex engines, leaving the problem of ReDoS vulnerability detection on non-backtracking regex engines largely *** address the above challenges, in this paper, we first systematically analyze the major causes that could contribute to ReDoS vulnerabilities on non-backtracking regex engines. We then propose a novel type of ReDoS attack strings that builds on the concept of simple strings. Next we propose EVILSTRGEN, a tool for generating attack strings for ReDoS-vulnerable regexes on non-backtracking engines. It is based on a novel incremental determinisation algorithm with heuristic strategies to lazily find the k-simple strings without explicit construction of finite automata. We evaluate EVILSTRGEN against six state-of-the-art approaches on a broad range of publicly available datasets containing 736,535 unique regexes. The results illustrate the significant efficacy of our tool. We also apply our tool to 85 intensively-tested projects, and have identified 34 unrevealed ReDoS vulnerabilities.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Towards Expanding Precise Timing for Collaborative Its with Deterministic Communications in 6G

Towards Expanding Precise Timing for Collaborative Its with ...

引用

IEEE Conference on Wireless Communications and Networking

作者： Hongxing Li Haotian Li Qianhan Gao Guochu Shou Yaqiong Liu Zhigang Guo Yihong Hu State Key Laboratory of Networking and Switching Technology School of Computer Science (National Pilot Software Engineering School) Beijing Key Laboratory of Network System Architecture and Convergence School of Information and Communication Engineering Beijing University of Posts and Telecommunications Beijing China

ISBN: (数字)9798350368369

ISBN: (纸本)9798350368376

The demand for precise timing continues to grow with the rapid development of smart cities, where intelligent transportation emerges as a critical application heavily dependent on accurate time distribution. Deterministic communication is anticipated to be a defining feature of nextgeneration mobile networks (6G), enabling end-to-end timecritical applications, and unlocking new possibilities for achieving end-to-end precise time synchronization as well. To cope with the challenge of delivering precise time synchronization across broader areas at a lower cost, this paper proposes a method to achieve end-to-end precise time synchronization by leveraging the deterministic characteristics of communication networks. Specially, the proposed approach adopts the Software-Defined Networking (SDN) paradigm to implement deterministic networking for the seamless integration of Time-Sensitive Networking (TSN) and cellular networks. Furthermore, to mitigate the impact of wireless channel uncertainties on synchronization accuracy, we propose a network delay measurement mechanism based on the principle of time redundancy, designed to reduce end-to-end network delay variation. Experimental results validate the effectiveness of the proposed method, demonstrating its capability to constrain the end-to-end relative time error of wired and wireless converged networks to the microsecond scale, without necessitating modifications to the existing network infrastructure.

关键词： 6G mobile communication Wireless communication Cellular networks Uncertainty Accuracy Measurement uncertainty Transportation Delays Synchronization Software defined networking

来源：评论

学校读者我要写书评

暂无评论

Online Credibility Assessment of Equipment Digital Twin for Discrete Manufacturing

引用

IEEE Transactions on Automation Science and Engineering 2025年 22卷 14763-14774页

作者： Lu, Han Zhang, Lin Deen, M. Jamal Wang, Kunyu Cheng, Hongbo Yang, Laurence T. Beihang University Hangzhou International Innovation Institute Zhejiang 311115 China Beihang University School of Automation Science and Electrical Engineering Beijing100191 China State Key Laboratory of Intelligent Manufacturing System Technology Beijing100854 China AI Atlas Inc Canada Zhengzhou University School of Computer and Artificial Intelligence School of Software Engineering Zhengzhou China St. Francis Xavier University Department of Computer Science Antigonish Canada

The equipment digital twins (EDTs) for discrete manufacturing should be calibrated quickly to avoid irreversible physical damage to the equipment caused by biased control commands. Therefore, an online credibility assessment method for EDTs is urgently needed. However, existing assessment approaches consume too much time, and thus could not reveal dynamic faults in time. In this paper, the dynamic relationship between online evolution and actual applications of EDTs is investigated. Then, two steps are proposed to accelerate the assessment process significantly. One involves pre-constructing a performance-deviation-agent (PDA), and the other involves dynamically fitting the application-time-window (ATW) probability distribution. The methodology is applicable to discrete manufacturing processes. The dynamic credibility of EDT evolution process can be updated after every iteration of the model evolution. Sorting manufacturing equipment was used as a case study to demonstrate the effectiveness of this method. The time consumption was reduced by 90% compared with traditional assessment methods in the case. © 2025 IEEE.

关键词： Fabrication

来源：评论

学校读者我要写书评

暂无评论

From an odd arity signature to a Holant dichotomy

arXiv

引用

arXiv 2025年

作者： Meng, Boning Wang, Juqiu Xia, Mingji Zheng, Jiayi Key Laboratory of System Software Chinese Academy of Sciences State Key Laboratory of Computer Science Institute of Software University of Chinese Academy of Sciences Beijing100080 China

Holant is an essential framework in the field of counting complexity. For over fifteen years, researchers have been clarifying the complexity classification for complex-valued Holant on the Boolean domain, a challenge that remains unresolved. In this article, we prove a complexity dichotomy for complex-valued Holant on Boolean domain when a non-trivial signature of odd arity exists. This dichotomy is based on the dichotomy for #EO, and consequently is an FPNP vs. #P dichotomy as well, stating that each problem is either in FPNP or #P-hard. Furthermore, we establish a generalized version of the decomposition lemma for complex-valued Holant on Boolean domain. It asserts that each signature can be derived from its tensor product with other signatures, or conversely, the problem itself is in FPNP. We believe that this result is a powerful method for building reductions in complex-valued Holant, as it is also employed as a pivotal technique in the proof of the aforementioned dichotomy in this article. Copyright © 2025, The Authors. All rights reserved.

关键词： Complex networks

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：