检索结果-内蒙古大学图书馆

Deep Reinforcement Learning-Based Security-Constrained Battery Scheduling in Home Energy System

IEEE TRANSACTIONS ON CONSUMER ELECTRONICS 2024年第1期70卷 3548-3561页

作者： Wang, Bo Zha, Zhongyi Zhang, Lijun Liu, Lei Fan, Huijin Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Key Lab Minist Educ Image Proc & Intelligent Control Wuhan 430074 Peoples R China

The home energy system today involves multiple renewable energy sources and battery energy storage systems, which can be considered as a microgrid. The battery energy storage system is a key component in the home energy system for the sake of filling the gap between the user demand and volatile energy supplies to maximize the techno and economic performances. However, the battery scheduling must suffer the stochastic nature of renewable energy resources and loads, which results in an intractable multi-period stochastic optimization problem with security constraints. An improved actor-critic-based reinforcement learning is proposed for this issue, where a distributional critic net is applied for faster and more accurate reward estimation under uncertainties, and a policy net incorporating protective secondary control is adopted to satisfy security constraints, preventing the unsafe state of batteries during the trial-and-error process. Numerical tests show that the proposed approach outperforms conventional reinforcement learning algorithms, as well as the rule-based battery scheduling approach while guaranteeing safe operation. The robustness and adaptability of the proposed method are also verified in case studies with different optimization tasks.

关键词： Batteries State of charge Security Degradation Trajectory Q-learning Monte Carlo methods Home energy system energy storage renewable energy resources security-constrained battery scheduling reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Observer-Based Consensus for Positive Multiagent Systems With Directed Topology and Nonlinear control Input

引用

IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS 2019年第7期49卷 1459-1469页

作者： Wu, Han Su, Housheng Huazhong Univ Sci & Technol Sch Automat Image Proc & Intelligent Control Key Lab Educ Minist China Wuhan 430074 Hubei Peoples R China

This paper studies the consensus problem for directed positive multiagent systems with nonlinear control input. The directed topology is supposed to be strongly connected. For the case of sector input nonlinearities, the non-negative global consensus conditions are presented by using a novel analysis method which directly considers the nonlinear input, and the feedback matrices are obtained with convex optimization method by solving the quadratic matrix inequalities subject to nonnegative constraints. For the case of saturation-type sector input nonlinearities, the global consensus and local consensus results are analyzed, respectively. With the properties of Metzler matrix, the non-negative consensus results are further extended to the strongly connected and balanced positive multiagent systems subject to (saturation-type) sector input nonlinearities and parameter uncertainties. The results are simplified, and the feedback matrices can be given by solving iterative linear matrix inequality with non-negative constraints. Two simulation examples and a practical electrical circuit model are finally carried out to verify the proposed control schemes.

关键词： Consensus convex optimization directed topology iterative linear matrix inequality nonlinear control input positive multiagent systems

来源：评论

学校读者我要写书评

暂无评论

Different Set Domain Adaptation for Brain-Computer Interfaces: A label Alignment Approach

引用

IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING 2020年第5期28卷 1091-1108页

作者： He, He Wu, Dongrui Huazhong Univ Sci & Technol Minist Educ Key Lab Image Proc & Intelligent Control Sch Artificial Intelligence & Automat Wuhan 430074 Peoples R China

A brain-computer interface (BCI) system usually needs a long calibration session for each new subject/task to adjust its parameters, which impedes its transition from the laboratory to real-world applications. Domain adaptation, which leverages labeled data from auxiliary subjects/tasks (source domains), has demonstrated its effectiveness in reducing such calibration effort. Currently, most domain adaptation approaches require the source domains to have the same feature space and label space as the target domain, which limits their applications, as the auxiliary data may have different feature spaces and/or different label spaces. This paper considers different set domain adaptation for BCIs, i.e., the source and target domains have different label spaces. We introduce a practical setting of different label sets for BCIs, and propose a novel label alignment (LA) approach to align the source label space with the target label space. It has three desirable properties: 1) LA only needs as few as one labeled sample from each class of the target subject;2) LA can be used as a preprocessing step before different feature extraction and classification algorithms;and, 3) LA can be integrated with other domain adaptation approaches to achieve even better performance. Experiments on two motor imagery datasets demonstrated the effectiveness of LA.

关键词： Covariance matrices Electroencephalography Manifolds Feature extraction Calibration Silicon Pipelines Brain-computerinterface EG label alignment Riemannian geometry domain adaptation transfer learning

来源：评论

学校读者我要写书评

暂无评论

Event-based H∞ filtering for networked system with communication delay

引用

SIGNAL processing 2012年第9期92卷 2029-2039页

作者： Hu, Songlin Yue, Dong Huazhong Univ Sci & Technol Key Lab Minist Educ Image Proc & Intelligent Cont Dept Control Sci & Engn Wuhan 430074 Peoples R China

This paper is concerned with the problem of event-based H-infinity filtering for networked systems with communication delay (or signal transmission delay). We first propose a novel event-triggering scheme upon which the sensor data is transmitted only when the specified event condition involving the sampled measurements of the plant is violated. By using delay system approach, a new model of filtering error system with state delay is formulated where the communication delay and event-triggering scheme are dealt with in a unified framework for networked systems. Then, by utilizing the Lyapunov-Krasovskii functional method plus free weighting matrix technique, sufficient conditions for ensuring the exponential stability as well as prescribed H-infinity performance for the filtering error system are derived in the form of linear matrix inequalities (LMIs). Based on these conditions, the explicit expression is given for the desired filter parameters. Finally, an illustrative example is presented to show the advantage of introducing the event-triggering scheme and the effectiveness of the proposed theoretical results. Crown Copyright (C) 2012 Published by Elsevier B.V. All rights reserved.

关键词： H-infinity filtering Communication delay Event-triggering scheme Networked systems

来源：评论

学校读者我要写书评

暂无评论

A novel fault diagnosis method in SVPWM voltage-source inverters for vector controlled induction motor drives

引用

INTERNATIONAL JOURNAL OF APPLIED ELECTROMAGNETICS AND MECHANICS 2016年第1期50卷 97-111页

作者： Huang, Chengguang Wu, Feng Zhao, Jin Zhou, Dehong Huazhong Univ Sci & Technol Sch Automat Minist Educ Key Lab Image Informat Proc & Intelligent Control Wuhan 430074 Hubei Peoples R China

This paper presents a novel single and multiple open circuit fault detection and identification method for three phase Voltage Source Inverter (VSI) fed vector controlled drives. In healthy condition, d-axis reference voltage is constant. When fault occurs, it is distorted, which is applied to detect the insulated-gate bipolar transistors (IGBTs) open circuit fault occurrence. The d-axis reference voltage distorted last for an interval time, the fault can be isolated by calculating the instant current vector rotating angles when the d-axis reference voltage gets distorted and recovered to constant, respectively, combined with space position of the current arc trajectory. The proposed method is fair robust to load torque changes and variable speed, and can be embedded into the existing drive software as a subroutine without excessive computational effort. The feasibility of the proposed fault diagnosis algorithm is evaluated by both simulation and experimental results.

关键词： PWM voltage-source-inverter induction motor drives inverter open-circuit fault diagnosis

来源：评论

学校读者我要写书评

暂无评论

Optimize TSK Fuzzy Systems for Classification Problems: Minibatch Gradient Descent With Uniform Regularization and Batch Normalization

引用

IEEE TRANSACTIONS ON FUZZY SYSTEMS 2020年第12期28卷 3065-3075页

作者： Cui, Yuqi Wu, Dongrui Huang, Jian Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Key Lab Minist Educ Image Proc & Intelligent Control Wuhan 430074 Peoples R China

Takagi-Sugeno-Kang (TSK) fuzzy systems are flexible and interpretable machine learning models;however, they may not be easily optimized when the data size is large, and/or the data dimensionality is high. This article proposes a minibatch gradient descent (MBGD) based algorithm to efficiently and effectively train TSK fuzzy classifiers. It integrates two novel techniques: First, uniform regularization (UR), which forces the rules to have similar average contributions to the output, and hence to increase the generalization performance of the TSK classifier;and, second, batch normalization (BN), which extends BN from deep neural networks to TSK fuzzy classifiers to expedite the convergence and improve the generalization performance. Experiments on 12 UCI datasets from various application domains, with varying size and dimensionality, demonstrated that UR and BN are effective individually, and integrating them can further improve the classification performance.

关键词： Training Fuzzy systems Neural networks Convergence Optimization Evolutionary computation Standards Batch normalization (BN) minibatch gradient descent Takagi– Sugeno– Kang (TSK) fuzzy classifier uniform regularization (UR)

来源：评论

学校读者我要写书评

暂无评论

Several Applications of Spiking Neural P Systems with Weights

引用

JOURNAL OF COMPUTATIONAL AND THEORETICAL NANOSCIENCE 2012年第6期9卷 769-777页

作者： Zhang, Xingyi Zeng, Xiangxiang Luo, Bin Xu, Jinbang Huazhong Univ Sci & Technol Dept Control Sci & Engn Key Lab Image Proc & Intelligent Control Wuhan 430074 Peoples R China Anhui Univ Sch Comp Sci & Technol Minist Educ Key Lab Intelligent Comp & Signal Proc Hefei 230039 Peoples R China

Spiking neural P systems with weights are a new variant of spiking neural P systems, where the applicability of rules is checked by a given potential threshold instead of the regular expression. There is a considerable computational power hidden into the implicit mechanism that spiking neural P systems use to decide whether a given rule can be applied or not. In this work, several applications of spiking neural P systems with weights regarding their capability to solve some classical computer science problems are investigated. Specifically, three spiking neural P systems with weights are constructed, which can provide basic models for simulating a well-known parallel computational device-Boolean circuits. A family of spiking neural P systems with weights is also presented, in which a system of size k can perform the sorting of arbitrary k natural numbers in linear time with respect to the maximally natural number to be sorted. These applications of spiking neural P systems with weights partially show the computational power hidden into the mechanism of using a given potential threshold to check the applicability of rules

关键词： Membrane Computing Spiking Neural P System Boolean Circuit Sorting

来源：评论

学校读者我要写书评

暂无评论

Spiking Neural P Systems with Weighted Synapses

引用

NEURAL processing LETTERS 2012年第1期35卷 13-27页

作者： Pan, Linqiang Zeng, Xiangxiang Zhang, Xingyi Jiang, Yun Huazhong Univ Sci & Technol Dept Control Sci & Engn Key Lab Image Proc & Intelligent Control Wuhan 430074 Hubei Peoples R China Anhui Univ Sch Comp Sci & Technol Key Lab Intelligent Comp & Signal Proc Hefei 230039 Anhui Peoples R China

Spiking neural P systems are a class of distributed parallel computing models inspired from the way neurons communicate with each other by means of electrical impulses, where there is a synapse between each pair of connected neurons. However, in a biological system, there can be several synapses for each pair of connected neurons. In this study, inspired by this biological observation, synapses in a spiking neural P system are endowed with integer weight denoting the number of synapses for each pair of connected neurons. With the price of weight on synapses, quite small universal spiking neural P systems can be constructed. Specifically, a universal spiking neural P system with standard rules and weight having 38 neurons is produced as device of computing functions;as generator of sets of numbers, we find a universal system with standard rules and weight having 36 neurons.

关键词： Membrane computing P system Spiking neural small universal device

来源：评论

学校读者我要写书评

暂无评论

Cross-Task Inconsistency Based Active Learning (CTIAL) for Emotion Recognition

引用

IEEE TRANSACTIONS ON AFFECTIVE COMPUTING 2024年第3期15卷 1659-1668页

作者： Xu, Yifan Jiang, Xue Wu, Dongrui Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Key Lab Minist Educ Image Proc & Intelligent Control Wuhan 430074 Peoples R China

Emotion recognition is a critical component of affective computing. Training accurate machine learning models for emotion recognition typically requires a large amount of labeled data. Due to the subtleness and complexity of emotions, multiple evaluators are usually needed for each affective sample to obtain its ground-truth label, which is expensive. To save the labeling cost, this paper proposes an inconsistency-based active learning approach for cross-task transfer between emotion classification and estimation. Affective norms are utilized as prior knowledge to connect the label spaces of categorical and dimensional emotions. Then, the prediction inconsistency on the two tasks for the unlabeled samples is used to guide sample selection in active learning for the target task. Experiments on within-corpus and cross-corpus transfers demonstrated that cross-task inconsistency could be a very valuable metric in active learning. To our knowledge, this is the first work that utilizes prior knowledge on affective norms and data in a different task to facilitate active learning for a new task, even the two tasks are from different datasets.

关键词： Task analysis Uncertainty Measurement uncertainty Estimation Entropy Emotion recognition Affective computing Active learning emotion classification emotion estimation transfer learning

来源：评论

学校读者我要写书评

暂无评论

Late better than early: A decision-level information fusion approach for RGB-Thermal crowd counting with illumination awareness

引用

NEUROCOMPUTING 2024年 594卷

作者： Cheng, Jian Feng, Chen Xiao, Yang Cao, Zhiguo Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Minist Educ Key Lab Image Proc & Intelligent Control Wuhan 430074 Peoples R China

In this paper, we make the first research effort to address the RGB-Thermal (RGB-T) crowd counting problem with the decision -level late fusion manner. Being different from the existing pixel -level or feature -level fusion methods, our proposition chooses to fuse the density maps yielded by RGB and thermal counterparts via spatially adaptive weighting with RGB illumination -aware attention. Our key intuition to conduct RGB-T density map fusion lies in 2 main folders. First, compared with the raw RGB-T images or convolutional feature maps, RGB-T density maps contain stronger counting -wise semantic meanings. Secondly, they are also of high spatial resolution for revealing fine local details. To fuse them adaptively, a spatial weighting map for each modality, together with an illumination -related RGB weight is generated. In this way, the issues of RGB illumination awareness and local counting pattern characterization ability are concerned jointly. To the best of our knowledge, we are the first to leverage RGB-T crowd counting concerning these 2 issues in a unified way. Meanwhile, cross -modality feature interaction is conducted between RGB and thermal modalities to facilitate spatial weighting map generation. The experiments on 2 well -established RGB-T crowd counting datasets ( i.e. , RGBT-CC and DroneRGBT) verify the superiority of our proposition.

关键词： Crowd counting RGB-T image Decision-level fusion

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：