检索结果-内蒙古大学图书馆

Self-Supervised Continual Graph Learning in Adaptive Riemannian Spaces

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Sun, Li Ye, Junda Peng, Hao Wang, Feiyang Yu, Philip S. School of Control and Computer Engineering North China Electric Power University Beijing102206 China School of Computer Science Beijing University of Posts and Telecommunications Beijing100876 China Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing100191 China Department of Computer Science University of Illinois ChicagoIL United States

Continual graph learning routinely finds its role in a variety of real-world applications where the graph data with different tasks come sequentially. Despite the success of prior works, it still faces great challenges. On the one hand, existing methods work with the zero-curvature Euclidean space, and largely ignore the fact that curvature varies over the coming graph sequence. On the other hand, continual learners in the literature rely on abundant labels, but labeling graph in practice is particularly hard especially for the continuously emerging graphs on-the-fly. To address the aforementioned challenges, we propose to explore a challenging yet practical problem, the self-supervised continual graph learning in adaptive Riemannian spaces. In this paper, we propose a novel self-supervised Riemannian Graph Continual Learner (RieGrace). In RieGrace, we first design an Adaptive Riemannian GCN (AdaRGCN), a unified GCN coupled with a neural curvature adapter, so that Riemannian space is shaped by the learnt curvature adaptive to each graph. Then, we present a Label-free Lorentz Distillation approach, in which we create teacher-student AdaRGCN for the graph sequence. The student successively performs intra-distillation from itself and inter-distillation from the teacher so as to consolidate knowledge without catastrophic forgetting. In particular, we propose a theoretically grounded Generalized Lorentz Projection for the contrastive distillation in Riemannian space. Extensive experiments on the benchmark datasets show the superiority of RieGrace, and additionally, we investigate on how curvature changes over the graph sequence. © 2022, CC BY-NC-SA.

关键词： Distillation

Short-term Wind Power Predication Based on Feature engineering and SOA-SVM 5

学校读者我要写书评

暂无评论

Short-term Wind Power Predication Based on Feature Engineeri...

5th IEEE Conference on Energy Internet and Energy System Integration, EI2 2021

作者： Zhang, Wenfeng Yan, Renwu Yu, Ning Liu, Yunzhang Zhang, Yang College of Electronic Electrical and Physics FuJian University of Technology Fuzhou350118 China College of Electronic Electrical and Physics Fujian Provincial University Fuzhou350118 China Engineering Research Center for Smart Grid Simulation Analysis and Integrated Control FuJian University of Technology Fuzhou350118 China Department of Computing Sciences SUNY Brockport BrockportNY14420 United States College of Electronic EFuJian University of Tlectrical and Physics Echnology Fuzhou350118 China

ISBN: (纸本)9781665434256

Contraposing to the issues of strong randomness, large volatility, and high prediction error of wind power, this paper proposes a short-term wind power prediction method based on feature engineering and support vector machine optimized by the seagull optimization algorithm (ISOA-SVM). First, in feature engineering, the abnormal values are preprocessed and utilizing the Pearson correlation coefficient (PCC) method to analyze the correlation between wind power and every feature. On this basis, a set of new features are constructed. Then, in the construction of the combined model, the seagull optimization algorithm is utilized to optimize the parameters of the support vector machine, so as to realize the complementary advantages of the optimization characteristics of the seagull algorithm and the support vector machine in simplifying the high-dimensional space complexity problems. Finally, the short-term wind power prediction model is constructed based on the ISOA-SVM model. The emulation experiment is carried out with the relevant measurement data of a wind power field. The results show that, in relation to other models, the proposed ISOA-SVM model has more excellent precision and dependability of short-term wind power prediction, which provides a certain reference for power dispatching. © 2021 IEEE

关键词： Support vector machines

Model-free design of stochastic lqr controller from reinforcement learning and primal-dual optimization perspective

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Li, Man Qin, Jiahu Zheng, Wei Xing Wang, Yaonan Kang, Yu Department of Automation University of Science and Technology of China Hefei230027 China School of Computing Engineering and Mathematics Western Sydney University SydneyNSW2751 Australia College of Electrical and Information Engineering Hunan University Changsha410082 China National Engineering Laboratory for Robot Visual Perception and Control Technology Changsha410082 China

To further understand the underlying mechanism of various reinforcement learning (RL) algorithms and also to better use the optimization theory to make further progress in RL, many researchers begin to revisit the linear-quadratic regulator (LQR) problem, whose setting is simple and yet captures the characteristics of RL. Inspired by this, this work is concerned with the model-free design of stochastic LQR controller for linear systems subject to Gaussian noises, from the perspective of both RL and primal-dual optimization. From the RL perspective, we first develop a new model-free off-policy policy iteration (MF-OPPI) algorithm, in which the sampled data is repeatedly used for updating the policy to alleviate the data-hungry problem to some extent. We then provide a rigorous analysis for algorithm convergence by showing that the involved iterations are equivalent to the iterations in the classical policy iteration (PI) algorithm. From the perspective of optimization, we first reformulate the stochastic LQR problem at hand as a constrained non-convex optimization problem, which is shown to have strong duality. Then, to solve this non-convex optimization problem, we propose a model-based primal-dual (MBPD) algorithm based on the properties of the resulting Karush-Kuhn-Tucker (KKT) conditions. We also give a model-free implementation for the MB-PD algorithm by solving a transformed dual feasibility condition. More importantly, we show that the dual and primal update steps in the MB-PD algorithm can be interpreted as the policy evaluation and policy improvement steps in the PI algorithm, respectively. Finally, we provide one simulation example to show the performance of the proposed algorithms. Copyright © 2021, The Authors. All rights reserved.

关键词： Stochastic systems

GREEDY SEARCH OF OPTIMAL APPROXIMATE SOLUTIONS

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Lazar, Martin Zuazua, Enrique Department of Electrical Engineering and Computing University of Dubrovnik Ćira Carića 4 Dubrovnik20 000 Croatia Dynamics Control and Numerics - Alexander von Humboldt Professorship Department of Data Science Friedrich-Alexander Universität Erlangen-Nürnberg. Erlangen91058 Germany Computational Mathematics Deusto Foundation Av. de las Universidades 24 Basque Country Bilbao48007 Spain Department of Mathematics Autonomous University of Madrid Madrid28049 Spain

In this paper we develop a procedure to deal with a family of parameter-dependent ill-posed problems, for which the exact solution in general does not exist. The original problems are relaxed by considering corresponding approximate ones, whose optimal solutions are well defined, where the optimality is determined by the minimal norm requirement. The procedure is based upon greedy algorithms that preserve, at least asymptotically, Kolmogorov approximation rates. In order to provide a-priori estimates for the algorithm, a Tychonoff-type regularization is applied, which adds an additional parameter to the model. The theory is developed in an abstract theoretical framework that allows its application to different kinds of problems. We present a specific example that considers a family of ill-posed elliptic problems. The required general assumptions in this case translate to rather natural uniform lower and upper bounds on coefficients of the considered operators. Copyright © 2022, The Authors. All rights reserved.

关键词： Approximation algorithms

Chest area segmentation in depth images of sleeping patients

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Goldstein, Yoav Schätz, Martin Avigal, Mireille Department of Mathematics and Computer Science Open University of Israel Raanana Israel University of Chemistry and Technology in Prague Department of Computing and Control Engineering Czech Republic

Although the field of sleep study has greatly developed over the recent years, the most common and efficient way to detect sleep issues remains a sleep examination performed in a sleep laboratory, in a procedure called Polysomnography (PSG). This examination measures several vital signals during a full night’s sleep using multiple sensors connected to the patient’s body. Yet, despite being the golden standard, the connection of the sensors and the unfamiliar environment inevitably impact the quality of the patient’s sleep and the examination itself. Therefore, with the novel development of more accurate and affordable 3D sensing devices, new approaches for non-contact sleep study emerged. These methods utilize different techniques with the purpose to extract the same sleep parameters, but remotely, eliminating the need of any physical connections to the patient’s body. However, in order to enable reliable remote extraction, these methods require accurate identification of the basic Region of Interest (ROI) i.e. the chest area of the patient, a task that is currently holding back the development process, as it is performed manually for each patient. In this study, we propose an automatic chest area segmentation algorithm, that given an input set of 3D frames of a sleeping patient, outputs a segmentation image with the pixels that correspond to the chest area, and can then be used as an input to subsequent sleep analysis algorithms. Except for significantly speeding up the development process of the non-contact methods, accurate automatic segmentation can also enable a more precise feature extraction and it is shown it is already improving sensitivity of prior solutions on average 46.9% better compared to manual ROI selection. All mentioned will place the extraction algorithms of the non-contact methods as a leading candidate to replace the existing traditional methods used today. Copyright © 2020, The Authors. All rights reserved.

关键词： Sleep research

A New Method for Quantifying Workload of Drivers and Application in Analyzing Stabilization Time after Critical Events in Varying Automation Levels

学校读者我要写书评

暂无评论

SSRN

SSRN 2022年

作者： Zhai, Junda Lu, Guangquan Chen, Facheng Liu, Miaomiao School of Transportation Science and Engineering Beihang University Beijing Key Laboratory for Cooperative Vehicle Infrastructure Systems and Safety Control Beijing100191 China Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing100191 China Department of Traffic Management School People’s Public Security University of China Beijing100038 China Beijing100088 China

The workload of drivers increases rapidly after the critical events and the period of time for workload to stabilize is worthy to investigate due to the close relationship between the workload and driving performance of drivers. It is yet unclear if the stabilization time of drivers varies across the different automation levels. In previous studies, a number of measurements have been utilized in evaluating the workload of drivers while most of the existing methods have limitations in studying the stabilization time. Therefore, this study introduces a new method for quantifying the cognitive workload of drivers with a measurement frequency of 2 seconds based on the performance of drivers to a newly designed calculating NDRT. A driving simulator experiment containing three automated driving levels and two critical events was conducted for the verification and application of the quantification method. Data were collected from 52 participants. The workload before and after critical events was analyzed and the results of quantified workload, the measurement acquired through the quantification method, showed a high similarity with heart rate and pupil diameter, which supported that the measurement could well reflect the workload of drivers with and without critical events. Moreover, the quantification method was applied to analyzing stabilization time after the critical situations and it was observed that quantified workload was a more appropriate measurement in determining the stabilization time of workload compared to heart rate and pupil diameter. In addition, the analysis results based on the workload quantification method showed that the effect of automation levels on the stabilization time of drivers after the critical events occurred was not significant. © 2022, The Authors. All rights reserved.

关键词： Automobile drivers

Reinforcement Learning Algorithms for Online Single-Machine Scheduling

学校读者我要写书评

暂无评论

Reinforcement Learning Algorithms for Online Single-Machine ...

Federated Conference on Computer Science and Information Systems (FedCSIS)

作者： Yuanyuan Li Edoardo Fadda Daniele Manerba Roberto Tadei Olivier Terzo LINKS Foundation-Advanced Computing and Applications Torino Italy Department of Control and Computer Engineering Politecnico di Torino Torino Italy Department of Information Engineering University of Brescia Brescia Italy

ISBN: (数字)9788395541674

ISBN: (纸本)9781728141473

Online scheduling has been an attractive field of research for over three decades. Some recent developments suggest that Reinforcement Learning (RL) techniques have the potential to deal with online scheduling issues effectively. Driven by an industrial application, in this paper we apply four of the most important RL techniques, namely Q-learning, Sarsa, Watkins's Q(λ), and Sarsa(λ), to the online single-machine scheduling problem. Our main goal is to provide insights on how such techniques perform. The numerical results show that Watkins's Q(λ) performs best in minimizing the total tardiness of the scheduling process.

关键词： field surveys Learning learning (artificial intelligence) machine scheduling scheduling process

Optimal power flow solution using novel optimization technique: A case study

学校读者我要写书评

暂无评论

Expert Systems with Applications 2025年 287卷

作者： Gupta, Saket Bilal, Mohd Zuhaib, Mohd Srivastava, Laxmi Malik, Hasmat García Márquez, Fausto Pedro Afthanorhan, Asyraf Instrumnetation and Control Engineering Department Bharati Vidyapeeth's College of Engineering New Delhi110063 India SND College of Engineering and Research Center Yeola Pune India Department of Electrical Engineering GLA University Mathura India Department of Electrical Engineering MITS Gwalior India Johor Skudai81310 Malaysia Ingenium Research Group Department Universidad Castilla-La Mancha Ciudad Real13071 Spain Terengganu Kuala Nerus21300 Malaysia Dehradun248002 India Faculty of Computing and Information Technology Sohar University Oman

The Jaya algorithm is a novel and effective global optimization technique, yet it faces challenges such as slow convergence, limited exploitation capabilities, and suboptimal balance between exploration and exploitation. This research proposes a hybrid Jaya algorithm, designated HMJDE, that integrates a modified Jaya algorithm with Differential Evolution (DE) to address the Optimal Power Flow (OPF) problem. The modified Jaya algorithm facilitates global exploration of the search space, while DE enhances local search by refining solutions within the neighbourhoods identified by Jaya. The performance of HMJDE is first assessed using eight well-established benchmark functions. Subsequently, its effectiveness is validated through application to real-world OPF problems on the Algerian 59-bus and standard IEEE 57-bus systems. The HMJDE algorithm achieves minimum fuel costs of 1688.1210 $/h and 41656.0438 $/h, respectively, with standard deviations of 0.3295 and 0.2412, representing cost reductions of 13.1317% and 18.8753% compared to the base case. These translate to annual savings of approximately $2,235,922.55 and $84,903,463.50, respectively. Compared to other recent optimization techniques, HMJDE exhibits superior solution quality and computational efficiency for both benchmark functions and OPF applications. Statistical analysis, including best, worst, mean, and standard deviation metrics, further confirms that HMJDE is a robust and reliable optimization approach. © 2025 The Author(s)

关键词： Evolutionary algorithms

Mobile robot navigation for complete coverage of an environment

学校读者我要写书评

暂无评论

IFAC-PapersOnLine 2018年第22期51卷 512-517页

作者： Šelek, Ana Seder, Marija Petrovi, Ivan Department of Control and Computer Engineering Faculty of Electrical Engineering and Computing University of Zagreb Croatia

Inspired by the Spanning Tree Covering (STC) algorithm of Gabriely and Rimon, a novel algorithm of complete coverage for known environments is developed. Unlike the original STC algorithm, we detect dynamic elements of the environment and efficiently update the solution when changes are observed. The contribution is a path replanning algorithm that reduces overlapping when the part of the environment is changed. Experiments show that the proposed algorithm is capable of planning complete coverage robot paths with 70.27% coverage and without overlapping. © 2018

关键词： Mobile robots Collision avoidance Motion planning Robot programming Trees (mathematics) Complete coverages Dynamic elements Known environments Mobile Robot Navigation Novel algorithm Path re planning Robot path Spanning tree