检索结果-内蒙古大学图书馆

IEEE Transactions on Artificial Intelligence 2024年第7期5卷 3607-3623页

作者： Mandal, Lakshmi Diddigi, Raghuram Bharadwaj Bhatnagar, Shalabh Indian Institute of Science Department of Computer Science and Automation Karnataka Bangalore560012 India International Institute of Information Technology Karnataka Bangalore560100 India

Reinforcement learning (RL) algorithms combined with deep learning architectures have achieved tremendous success in many practical applications. However, the policies obtained by many deep reinforcement learning (DRL) algorithms are seen to suffer from high variance making them less useful in safety-critical applications. In general, it is desirable to have algorithms that give a low iterate-variance while providing a high long-term reward. In this work, we consider the actor-critic (AC) paradigm, where the critic is responsible for evaluating the policy while the feedback from the critic is used by the actor for updating the policy. The updates of both the critic and the actor in the standard AC procedure are run concurrently until convergence. It has been previously observed that updating the actor once after every L>1 steps of the critic reduces the iterate variance. In this article, we address the question of what optimal L-value to use in the recursions and propose a data-driven L-update rule that runs concurrently with the AC algorithm with the objective being to minimize the variance of the infinite horizon discounted reward. This update is based on a random search (discrete) parameter optimization procedure that incorporates smoothed functional (SF) estimates. We prove the convergence of our proposed multitimescale scheme to the optimal L and optimal policy pair. Subsequently, through numerical evaluations on benchmark RL tasks, we demonstrate the advantages of our proposed algorithm over multiple state-of-the-art algorithms in the literature. © 2020 IEEE.

关键词： Optimization

来源：评论

学校读者我要写书评

暂无评论

Facial Expression Generation from Text with FaceCLIP

引用

Journal of computer Science & technology 2025年第2期40卷 359-377页

作者： Wen-Wen Fu Wen-Juan Gong Chen-Yang Yu Wei Wang Jordi Gonzàlez Qingdao Institute of Software College of Computer Science and TechnologyChina University of Petroleum(East China)Qingdao 266580China Institute of Automation Chinese Academy of SciencesBeijing 100190China Computer Vision Center Universitat Autònoma de BarcelonaBarcelona 08193Spain

Facial expression generation from pure textual descriptions is widely applied in human-computer interaction,computer-aided design,assisted education,***,this task is challenging due to the intricate facial structure and the complex mapping between texts and *** methods face limitations in generating high-resolution images or capturing diverse facial *** this study,we propose a novel generation approach,named FaceCLIP,to tackle these *** proposed method utilizes a CLIP-based multi-stage generative adversarial model to produce vivid facial expressions with high *** strong semantic priors from multi-modal textual and visual cues,the proposed method effectively disentangles facial attributes,enabling attribute editing and semantic *** facilitate text-toexpression generation,we build a new dataset called the FET dataset,which contains facial expression images and corresponding textual *** on the dataset demonstrate improved image quality and semantic consistency compared with state-of-the-art methods.

关键词： facial expression generation contrastive language-image pre-training(CLIP) multi-stage generative adversarial network(GAN)

来源：评论

学校读者我要写书评

暂无评论

Explanation and Speedup Comparison of Advanced Path-planning Algorithms Presented on Two-dimensional Grid

Mendel

引用

Mendel 2022年第2期28卷 97-107页

作者： Soustek, Petr Matousek, Radomil Dvorak, Jiri Manakova, Lenka Institute of Automation and Computer Science Brno University of Technology Czech Republic

Path planning or network route planning problems are an important issue in AI, robotics, or computer games. Appropriate implementation and knowledge of advanced and classical path-planning algorithms can be important for both autonomous navigation systems and computer games. In this paper, we compare advanced path planning algorithms implemented on a two-dimensional grid. Advanced path planning algorithms, including pseudocode, are introduced. The experiments were performed in the Python environment, thus with a significant performance margin over C++ or Rust implementations. The main focus is on the speedup of the algorithms compared to a baseline method, which was chosen to be the well-known Dijkstra’s algorithm. All experiments correspond to trajectories on a two-dimensional grid, with variously defined constraints. The motion from each node corresponds to a Moore neighborhood, i.e., it is possible in eight directions. In this paper, three well-known path planning algorithms are described and compared: the Dijkstra, A* and A* /w Bounding Box. And two advanced methods are included, namely Jump Point Search (JPS), incorporated with the Bounding Box variant (JPS+BB), and Simple Subgoal (SS). These advanced methods clearly show their advantage in the context of the speed up of solution time. © 2022, Brno University of technology. All rights reserved.

关键词： Motion planning

来源：评论

学校读者我要写书评

暂无评论

Knowledge As Not Only Justified True Beliefs in Vision

引用

IEEE/CAA Journal of Automatica Sinica 2025年第2期12卷 297-299页

作者： Wenbo Zheng Fei-Yue Wang IEEE School of Computer Science and Artificial Intelligence Wuhan University of Technology Sanya Science and Education Innovation Park of Wuhan University of Technology the State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences

COMPUTATIONAL knowledge vision [1] is emphasized as a novel perspective or field in this paper. It first proposes the visual hierarchy and its connection to knowledge, stating that knowledge is a justified true belief. To further the previous research, we concisely summarize our recent works and suggest a new direction that knowledge is also a thought framework in vision.

关键词： Computational modeling Visualization Artificial intelligence Data models Visual perception Visual databases Training data

来源：评论

学校读者我要写书评

暂无评论

Intelligent Sampling of Anterior Human Nasal Swabs using a Collaborative Robotic Arm

Mendel

引用

Mendel 2022年第1期28卷 32-40页

作者： Parak, Roman Juricek, Martin Institute of Automation and Computer Science Brno University of Technology Czech Republic

Advanced robotics does not always have to be associated with Industry 4.0, but can also be applied, for example, in the Smart Hospital concept. Developments in this field have been driven by the coronavirus disease (COVID-19), and any improvement in the work of medical staff is welcome. In this paper, an experimental robotic platform was designed and implemented whose main function is the swabbing samples from the nasal vestibule. The robotic platform represents a complete integration of software and hardware, where the operator has access to a web-based application and can control a number of functions. The increased safety and collaborative approach cannot be overlooked. The result of this work is a functional prototype of the robotic platform that can be further extended, for example, by using alternative technologies, extending patient safety, or clinical tests and studies. Code is available at https://***/ Steigner/ Robo_ Medicinae_ I. © 2022, Brno University of technology. All rights reserved.

关键词： Robot Operating System

来源：评论

学校读者我要写书评

暂无评论

Multispectral point cloud superpoint segmentation

引用

Science China(Technological Sciences) 2024年第4期67卷 1270-1281页

作者： WANG QingWang WANG MingYe ZHANG ZiFeng SONG Jian ZENG Kai SHEN Tao GU YanFeng Faculty of Information Engineering and Automation Kunming University of Science and TechnologyKunming 650500China Yunnan Key Laboratory of Computer Technologies Application Kunming 650500China School of Electronics and Information Engineering Harbin Institute of TechnologyHarbin 150001China

The multitude of airborne point clouds limits the point cloud processing *** are grouped based on similar points,which can effectively alleviate the demand for computing resources and improve processing ***,existing superpoint segmentation methods focus only on local geometric structures,resulting in inconsistent spectral features of points within a *** feature inconsistencies degrade the performance of subsequent ***,this study proposes a novel Superpoint Segmentation method that jointly utilizes spatial Geometric and Spectral Information for multispectral point cloud superpoint segmentation(GSI-SS).Specifically,a similarity metric that combines spatial geometry and spectral information is proposed to facilitate the consistency of geometric structures and object attributes within segmented *** the formation of the primary superpoints,an intersuperpoint pointexchange mechanism that maximizes feature consistency within the final superpoints is *** are conducted on two real multispectral point cloud datasets,and the proposed method achieved higher recall,precision,F score,and lower global consistency and feature classification *** experimental results demonstrate the superiority of the proposed GSI-SS over several state-of-the-art methods.

关键词： multispectral point cloud superpoint segmentation over-segmentation spatial-spectral joint metric

来源：评论

学校读者我要写书评

暂无评论

Integrating Ontology Design with the CRISP-DM in the Context of Cyber-Physical Systems Maintenance 29

Integrating Ontology Design with the CRISP-DM in the Context...

引用

29th IEEE International Conference on Emerging Technologies and Factory automation, ETFA 2024

作者： Gill, Milapji Singh Westermann, Tom Steindl, Gernot Gehlhoff, Felix Fay, Alexander Institute of Automation Technology Helmut Schmidt University Hamburg Germany Institute of Computer Engineering Tu Wien Austria Ruhr University Automation Bochum Germany

ISBN: (纸本)9798350361230

In the following contribution, a method is introduced that integrates domain expert-centric ontology design with the Cross-Industry Standard Process for Data Mining (CRISP-DM). This approach aims to efficiently build an application-specific ontology tailored to the corrective maintenance of Cyber- Physical Systems (CPS). The proposed method is divided into three phases. In phase one, ontology requirements are systematically specified, defining the relevant knowledge scope. Accordingly, CPS life cycle data is contextualized in phase two using domain-specific ontological artifacts. This formalized domain knowledge is then utilized in the CRISP-DM to efficiently extract new insights from the data. Finally, the newly developed data-driven model is employed to populate and expand the ontology. Thus, information extracted from this model is semantically annotated and aligned with the existing ontology in phase three. The applicability of this method has been evaluated in an anomaly detection case study for a modular process plant. © 2024 IEEE.

关键词： Cybersecurity

来源：评论

学校读者我要写书评

暂无评论

An Optimal Weighted Ensemble of 3D CNNs for Early Diagnosis of Alzheimer’s Disease

引用

SN computer Science 2024年第2期5卷 252页

作者： Dharwada, Sriram Tembhurne, Jitendra Diwan, Tausif Department of Computer Science and Automation Indian Institute of Science Bangalore India Department of Computer Science and Engineering Indian Institute of Information Technology Maharashtra Nagpur 441108 India

Alzheimer disease (AD) is a chronic neurological disorder in which the loss of brain cells causes dementia. Early and accurate diagnosis of AD will lead to better treatment of the disease before irreversible brain damage has been occurred. This paper proposes the classification of Alzheimer's disease using 3D structural Magnetic Resonance Imaging (sMRI) images through 3D convolutional neural networks (CNNs). Most existing methods utilizing 3D subject-level CNNs for Alzheimer's disease classification design a single model which relies on a very large training dataset for improved generalization. Herein, we address this issue through 3D transfer learning which makes use of knowledge gained from a pre-trained task. We train 3D versions of five classical 2D image classification architectures—ResNet, ResNeXt, SE-ResNet, SE-ResNeXt, and SE-Net—by initializing each model with pre-trained weights from their 2D counterparts, and combine their predictions through a weighted average method. The weights assigned to each model of the ensemble are optimized to achieve a performance better than any single 3D CNN model. With a relatively smaller training dataset, the proposed model obtains 97.27%, 82.33%, 90.41%, 84.22%, 84.26%, and 77.1% accuracies for the Alzheimer’s disease (AD) versus cognitively normal (CN), early mild cognitive impairment (EMCI) versus CN, late mild cognitive impairment (LMCI) versus CN, EMCI versus AD, LMCI versus AD, and EMCI versus LMCI classification tasks, outperforming current state-of-the-art methods, and indicating the effectiveness of our proposed model. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd 2024.

关键词： Alzheimer’s disease Convolutional neural networks Ensemble learning Transfer learning

来源：评论

学校读者我要写书评

暂无评论

Fixed-time-synchronized control: a system-dimension-categorized approach

引用

Science China(Information Sciences) 2023年第7期66卷 177-194页

作者： Wanyue JIANG Shuzhi Sam GE Dongyu LI Institute for Future & Shandong Key Laboratory of Industrial Control Technology School of Automation Qingdao University Department of Electrical and Computer Engineering National University of Singapore School of Cyber Science and Technology Beihang University Shanghai Institute of Satellite Engineering

This study addresses the fixed-time-synchronized control problem of perturbed multi-input multioutput(MIMO) systems. In the task of fixed-time-synchronized control, different dimensions of the output signal in MIMO systems are required to reach the desired value simultaneously within a fixed time *** MIMO system is categorized into two cases: the input-dimension-dominant and the state-dimensiondominant cases. The classification is defined according to the dimension of system signals and, more importantly, the capability of converging at the same time. For each kind of MIMO system, sufficient Lyapunov conditions for fixed-time-synchronized convergence are explored, and the corresponding robust sliding mode controllers are designed. Moreover, perturbations are compensated using the super-twisting technique. The brake control of the vertical takeoff and landing aircraft is considered to verify the proposed method for the input-dimension-dominant case, which shows the essential advantages of decreasing the energy consumption and the output trajectory length. Furthermore, comparative numerical simulations are performed to show the semi-time-synchronized property for the state-dimension-dominant case.

关键词： fixed-time-synchronized convergence sliding mode control perturbed MIMO systems

来源：评论

学校读者我要写书评

暂无评论

Dynamic Energy Management in Competing Microgrids using Reinforcement Learning

Dynamic Energy Management in Competing Microgrids using Rein...

引用

2024 IEEE Power and Energy Society Innovative Smart Grid Technologies Conference, ISGT 2024

作者： Vivek, V.P. Diddigi, Raghuram Bharadwaj Bhatnagar, Shalabh Computer Science and Automation Indian Institute of Science Bangalore India International Institute of Information Technology Bangalore India

ISBN: (纸本)9798350313604

Smart Grids are a concept for efficiently managing energy in power grids using both renewable and non-renewable power sources. Integrating renewable power sources into the traditional power supply has multi-fold advantages, like reducing carbon emissions and minimizing the peak demand at the main grid. An efficient way for this integration is by employing microgrids, which are autonomous intelligent decision-making networks that cater power to a small subset of customers. The microgrids are equipped with a renewable source like solar or wind to generate power and battery sources to store power. The microgrids would need to make optimal decisions like the amount of power to be stored in the battery, selling price, etc., at each decision time instant to maximize their long-Term goal of making a profit. At the same time, from the customers' perspective, fairness is paramount for easier and faster adoption. In this work, we address both problems in a unified framework by proposing a novel smart grid paradigm where two microgrids compete to distribute power to their customers. We formulate the competition in a two-player zero-sum stochastic game framework and propose an efficient Reinforcement Learning algorithm for solving this problem. Moreover, our formulation and solutions are designed for the finite horizon rather than the infinite horizon, thereby ensuring practical applicability. We demonstrate the performance of the algorithm through extensive experiments on simulated smart grid settings. © 2024 IEEE.

关键词： Reinforcement learning

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：