检索结果-内蒙古大学图书馆

Improved Evolutionary Multitasking Optimization Algorithm With Similarity Evaluation of Search Behavior

IEEE Transactions on Evolutionary Computation 2024年第3期29卷 1-1页

作者： Wu, Xiaolong Wang, Wei Zhang, Tengfei Han, Honggui Qiao, Junfei Beijing Key Laboratory of Computational Intelligence and Intelligent System Engineering Research Center of Digital Community Ministry of Education Beijing Artificial Intelligence Institute and Beijing Laboratory for Intelligent Environmental Protection Faculty of Information Technology Beijing University of Technology Beijing China

Task similarity is a major requisite to trigger knowledge sharing in evolutionary multitasking optimization (EMTO). Unfortunately, most of the existing EMTO algorithms only focus on the similarity between population distributions of tasks, but ignore the search behavior of populations, which may degrade the performance of cross-task knowledge sharing. Motivated by this, an improved EMTO algorithm with similarity evaluation of search behavior (SESB-IEMTO), employing the particle swarm optimization (PSO) algorithm as a task solver for each task, is proposed. It comprises three key elements: 1) a dynamic similarity-based evaluation strategy, 2) a cross-task knowledge adaptation method, and 3) a search direction sharing mechanism. Primarily, the source tasks with similar search behavior are discriminated with the dynamic similarity-based evaluation strategy, where individuals can be fully exploited for cross-task evolution. Then, the knowledge derived from these source tasks is regulated by the cross-task knowledge adaption method for alleviating the risk of negative transfer caused by the heterogeneity between tasks. Moreover, to further promote knowledge sharing between tasks, the search direction sharing mechanism is developed to navigate tasks efficiently searching for promising regions. Finally, the convergence of SESB-IEMTO is analyzed, and the effectiveness and superiority are also verified with the experiments on several benchmark tests and a real-world application study. IEEE

关键词： Multitasking

来源：评论

学校读者我要写书评

暂无评论

Motor Imagery Classification Based on Plain Convolutional Neural Network and Linear Interpolation

引用

Journal of Shanghai Jiaotong university(Science) 2024年第6期29卷 958-966页

作者： LI Mingai WEI Lina Faculty of Information Technology Beijing University of TechnologyBeijing 100124China Beijing Key Laboratory of Computational Intelligence and Intelligent System Beijing 100124China

Deep learning has been applied for motor imagery electroencephalogram(MI-EEG)classification in brain-computer system to help people who suffer from serious neuromotor *** inefficiency network and data shortage are the primary issues that the researchers face and need to solve.A novel MI-EEG classification method is proposed in this paper.A plain convolutional neural network(pCNN),which contains two convolution layers,is designed to extract the temporal-spatial information of MI-EEG,and a linear interpolation-based data augmentation(LIDA)method is introduced,by which any two unrepeated trials are randomly selected to generate a new *** on two publicly available brain-computer interface competition datasets,the experiments are conducted to confirm the structure of pCNN and optimize the parameters of pCNN and LIDA as *** average classification accuracy values achieve 90.27%and 98.23%,and the average Kappa values are 0.805 and 0.965 *** experiment results show the advantage of the proposed classification method in both accuracy and statistical consistency,compared with the existing methods.

关键词： motor imagery classification convolutional neural network data augmentation deep learning braincomputer interface

来源：评论

学校读者我要写书评

暂无评论

RaSTFormer: region-aware spatiotemporal transformer for visual homogenization recognition in short videos

引用

Neural computing and Applications 2024年第18期36卷 10713-10732页

作者： Zhang, Shuying Zhang, Jing Zhang, Hui Zhuo, Li Faculty of Information Technology Beijing University of Technology Beijing China Beijing Key Laboratory of Computational Intelligence and Intelligent System Beijing University of Technology Beijing China

With the surge in network traffic, the homogenization of short video content is becoming increasingly prominent, resulting in low-quality entertainment due to proliferation and infringement. Therefore, recognizing visual homogeneity in short videos is of great significance. Considering the extremely similar dynamic evolution in specific regions from intra and inter-frames, introducing region-aware attention is attractive to achieve homogenization recognition. Therefore, we propose a region-aware spatiotemporal Transformer (RaSTFormer) for visual homogenization recognition, including: (1) a region-aware Transformer encoder is designed to extract multi-region frame-level features from short videos;(2) a multi-layer spatiotemporal Transformer decoder is used to aggregate multi-region frame-level features, generating shot-level spatiotemporal features;and (3) measuring symmetric shot-level chamfer similarity to recognize visual homogeneous content. Specially, we established a real-world video homogenization dataset, BJUT-HCD, and conducted extensive experiments. The proposed RaSTFormer achieved the highest mean average precision (mAP) of 98.13% and a top-1 accuracy of 99.37%, outperforming SOTA methods. The results show that our method achieves competitive performance in visual homogenization recognition in short videos. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Homogenization method

来源：评论

学校读者我要写书评

暂无评论

Event-triggered fuzzy neural multivariable control for a municipal solid waste incineration process

引用

Science China(Technological Sciences) 2023年第11期66卷 3115-3128页

作者： DING HaiXu QIAO JunFei HUANG WeiMin YU Tao Faculty of Information Technology Beijing University of TechnologyBeijing 100124China Beijing Laboratory of Smart Environmental Protection Beijing 100124China Beijing Key Laboratory of Computational Intelligence and Intelligent System Beijing 100124China

Because of coupling,nonlinearity,and uncertainty in a municipal solid waste incineration(MSWI)process,a suitable multivariable controller is difficult to establish under strong ***,the problems of reducing mechanical wear and energy consumption in the control process should also be *** solve these problems,an event-triggered fuzzy neural multivariable controller is proposed in this ***,the MSWI object model based on the multiinput multioutput TakagiSugeno fuzzy neural network is established using a data-driven ***,a fuzzy neural multivariable controller is designed to control the furnace temperature and flue gas oxygen content synchronously under external ***,an event-triggered mechanism is constructed to update the control rate online while ensuring control ***,the stability of the proposed control strategy is proven through the LyapunovⅡtheorem to guide its practical ***,the effectiveness of the controller is verified using the real industrial data of an MSWI factory in beijing,*** experimental results show that the proposed control strategy greatly improves the control efficiency,reduces energy consumption by 66.23%,and improves the multivariable tracking control accuracy.

关键词： municipal solid waste incineration multivariable control event-triggered multiinput multioutput fuzzy neural network

来源：评论

学校读者我要写书评

暂无评论

GRAMO:geometric resampling augmentation for monocular 3D object detection

引用

Frontiers of Computer Science 2024年第5期18卷 161-169页

作者： He GUAN Chunfeng SONG Zhaoxiang ZHANG School of Artificial Intelligence University of Chinese Academy of SciencesBeijing 100049China Center for Research on Intelligent Perception and Computing State Key Laboratory of Multimodal Artificial Intelligence SystemsInstitute of Automation Chinese Academy of SciencesBeijing 100190China

Data augmentation is widely recognized as an effective means of bolstering model ***,when applied to monocular 3D object detection,non-geometric image augmentation neglects the critical link between the image and physical space,resulting in the semantic collapse of the extended *** address this issue,we propose two geometric-level data augmentation operators named Geometric-Copy-Paste(Geo-CP)and Geometric-Crop-Shrink(Geo-CS).Both operators introduce geometric consistency based on the principle of perspective projection,complementing the options available for data augmentation in monocular ***,Geo-CP replicates local patches by reordering object depths to mitigate perspective occlusion conflicts,and Geo-CS re-crops local patches for simultaneous scaling of distance and scale to unify appearance and *** operations ameliorate the problem of class imbalance in the monocular paradigm by increasing the quantity and distribution of geometrically consistent *** demonstrate that our geometric-level augmentation operators effectively improve robustness and performance in the KITTI and Waymo monocular 3D detection benchmarks.

关键词： 3D detection monocular augmentation geometry

来源：评论

学校读者我要写书评

暂无评论

A Hippocampus Spatial Cognition Model based on Predictive Coding 43

A Hippocampus Spatial Cognition Model based on Predictive Co...

引用

43rd Chinese Control Conference, CCC 2024

作者： Yu, Naigong Lv, Zexuan Yan, Jinhan Beijing University of Technology Faculty of information Technology Beijing100021 China Beijing Key Laboratory of Computing Intelligence and Intelligent System Beijing100021 China

ISBN: (纸本)9789887581581

In current computation neuroscience, it is widely accepted that the mammalian entorhinal-hippocampus complex provides representations of spatial environment, exhibiting specific responses to particular locations and directions. Various computation models of spatial cell firing have been proposed to unravel the mysteries of spatial cognition representation in the brain. However, an increasing body of experimental evidence suggests that the brain operates more akin to a predictive system. Actively acquiring and utilizing limited environmental information, the brain constructs internal models during interaction with the external world, generating predictive representations of internal states following environmental changes. Building upon this premise, we propose a predictive coding theory-based entorhinal-hippocampus spatial cognition model. This model incorporates vestibular proprioceptive cues and border vector cells discharge responses to initially derive unimodal place cell discharge fields, followed by hippocampal place cells projecting to the entorhinal cortex via excitatory-inhibitory synaptic connections, ultimately generating periodic hexagonal grid cell discharge fields. Experimental results demonstrate that the neuronal discharge patterns obtained by this model align with physiological research findings, thereby providing new insights for further investigations into brain cognitive mechanisms. © 2024 Technical Committee on Control Theory, Chinese Association of Automation.

关键词： Mammals

来源：评论

学校读者我要写书评

暂无评论

Safe Q-Learning for Data-Driven Nonlinear Optimal Control With Asymmetric State Constraints

引用

IEEE/CAA Journal of Automatica Sinica 2024年第12期11卷 2408-2422页

作者： Mingming Zhao Ding Wang Shijie Song Junfei Qiao the School of Information Science and Technology the Beijing Key Laboratory of Computational Intelligence and Intelligent Systemthe Beijing Laboratory of Smart Environmental Protectionand the Beijing Institute of Artificial IntelligenceBeijing University of Technology.Beijing 100124China IEEE the School of Mechanical and Electrical Engineering University of Electronic Science and Technology of ChinaChengdu 611731China

This article develops a novel data-driven safe Q-learning method to design the safe optimal controller which can guarantee constrained states of nonlinear systems always stay in the safe region while providing an optimal ***,we design an augmented utility function consisting of an adjustable positive definite control obstacle function and a quadratic form of the next state to ensure the safety and ***,by exploiting a pre-designed admissible policy for initialization,an off-policy stabilizing value iteration Q-learning(SVIQL)algorithm is presented to seek the safe optimal policy by using offline data within the safe region rather than the mathematical ***,the monotonicity,safety,and optimality of the SVIQL algorithm are theoretically *** obtain the initial admissible policy for SVIQL,an offline VIQL algorithm with zero initialization is constructed and a new admissibility criterion is established for immature iterative ***,the critic and action networks with precise approximation ability are established to promote the operation of VIQL and SVIQL ***,three simulation experiments are conducted to demonstrate the virtue and superiority of the developed safe Q-learning method.

关键词： Adaptive critic control adaptive dynamic programming(ADP) control barrier functions(CBF) stabilizing value iteration Q-learning(SVIQL) state constraints

来源：评论

学校读者我要写书评

暂无评论

Identity-Preserving Adversarial Training for Robust Network Embedding

引用

Journal of Computer Science & Technology 2024年第1期39卷 177-191页

作者：岑科廷沈华伟曹婍徐冰冰程学旗 Data Intelligence System Research Center Institute of Computing TechnologyChinese Academy of SciencesBeijing 100190China University of Chinese Academy of Sciences Beijing 101480China Beijing Academy of Artificial Intelligence Beijing 100000China Chinese Academy of Sciences Key Laboratory of Network Data Science and Technology Institute of Computing Technology Chinese Academy of SciencesBeijing 100190China

Network embedding,as an approach to learning low-dimensional representations of nodes,has been proved extremely useful in many applications,e.g.,node classification and link ***,existing network embed-ding models are vulnerable to random or adversarial perturbations,which may degrade the performance of network em-bedding when being applied to downstream *** achieve robust network embedding,researchers introduce adversari-al training to regularize the embedding learning process by training on a mixture of adversarial examples and original ***,existing methods generate adversarial examples heuristically,failing to guarantee the imperceptibility of generated adversarial examples,and thus limit the power of adversarial *** this paper,we propose a novel method Identity-Preserving Adversarial Training(IPAT)for network embedding,which generates imperceptible adversarial exam-ples with explicit identity-preserving *** formalize such identity-preserving regularization as a multi-class classification problem where each node represents a class,and we encourage each adversarial example to be discriminated as the class of its original *** experimental results on real-world datasets demonstrate that our proposed IPAT method significantly improves the robustness of network embedding models and the generalization of the learned node representations on various downstream tasks.

关键词： network embedding identity-preserving adversarial training adversarial the example

来源：评论

学校读者我要写书评

暂无评论

Improving Multi-task GNNs for Molecular Property Prediction via Missing Label Imputation

引用

Machine intelligence Research 2025年第1期22卷 131-144页

作者： Fenyu Hu Dingshuo Chen Qiang Liu Shu Wu University of Chinese Academy of Sciences Beijing100190China Center for Research on Intelligent Perception and Computing State Key Laboratory of Multimodal Artificial Intelligence SystemsInstitute of AutomationChinese Academy of SciencesBeijing100190China

The prediction of molecular properties is a fundamental task in the field of drug ***,graph neural networks(GNNs)have been gaining prominence in this *** a molecule tends to have multiple correlated properties,there is a great need to develop the multi-task learning ability of ***,limited by expensive and time-consuming human annotations,collecting complete labels for each task is *** a result,most existing benchmarks involve many missing labels in training data,and the performance of GNNs is impaired due to the lack of sufficient supervision *** overcome this obstacle,we propose to improve multi-task molecular property prediction by missing label ***,a bipartite graph is first introduced to model the molecule-task co-occurrence ***,the imputation of missing labels is transformed into predicting missing edges on this bipartite *** predict the missing edges,a graph neural network is devised,which can learn the complex molecule-task co-occurrence *** that,we select reliable pseudo labels according to the uncertainty of the prediction *** with enough and reliable supervision information,our approach achieves state-of-the-art performance on a variety of real-world datasets.

关键词： Graph classification imbalance learning prediction bias mixture of experts multiview representations

来源：评论

学校读者我要写书评

暂无评论

Prediction of NO_(x)concentration using modular long short-term memory neural network for municipal solid waste incineration

引用

Chinese Journal of Chemical Engineering 2023年第4期56卷 46-57页

作者： Haoshan Duan Xi Meng Jian Tang Junfei Qiao Faculty of Information Technology Beijing University of TechnologyBeijing 100124China Beijing Laboratory of Smart Environmental Protection Beijing 100124China Beijing Key Laboratory of Computational Intelligence and Intelligent System Beijing 100124China Engineering Research Center of Intelligence Perception and Autonomous Control Ministry of Education Beijing 100124China

Air pollution control poses a major problem in the implementation of municipal solid waste incineration(MSWI).Accurate prediction of nitrogen oxides(NO_(x))concentration plays an important role in efficient NO_(x)emission *** this study,a modular long short-term memory(M-LSTM)network is developed to design an efficient prediction model for NO_(x)***,the fuzzy C means(FCM)algorithm is utilized to divide the task into several sub-tasks,aiming to realize the divide-and-conquer ability for complex ***,long short-term memory(LSTM)neural networks are applied to tackle corresponding sub-tasks,which can improve the prediction accuracy of the ***,a cooperative decision strategy is designed to guarantee the generalization performance during the testing or application ***,after being evaluated by a benchmark simulation,the proposed method is applied to a real MSWI *** the experimental results demonstrate the considerable prediction ability of the M-LSTM network.

关键词： Municipal solid waste incineration NO_(x)concentration prediction Modular neural network Model

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：