检索结果-内蒙古大学图书馆

SSRN 2024年

作者： Zhao, Xinwei Liu, Yonggui Xiao, Bin Key Laboratory of Autonomous Systems and Network Control Ministry of Education School of Automation Science and Engineering South China University of Technology Guangzhou510641 China School of Computer Science and Technology Guangdong University of Technology Guangzhou510006 China Information Engineering School Guangzhou Vocational College of Technology & Business Guangzhou511442 China

Lithium-ion batteries are valuable as the primary power source for electric vehicles (EVs). However, their capacity degradation and reliability directly affect driving of on-service EVs, accurately forecasting battery capacity is still a tricky challenge due to complex battery systems and limitations of computing power. To overcome such barriers, a concise battery capacity prediction method is proposed based on charging data and decomposition framework in this paper. First, charging hot-spot intervals are counted to provide a reliable foundation for screening high-quality and low-quantity data. Then, the seasonal-trend decomposition method with independent analysis is designed and applied to extract significant correlation features associated with capacity degradation. Subsequently, a temporal convolution network with the decomposed mode is developed to forecast battery capacity, in conjunction with the use of decoupling mechanism to rectify the analytical interference and misinformation caused by data mixing. Finally, experiment results demonstrate that the proposed method can accurately predict capacity of on-service EVs. Furthermore, this approach alleviates the computational burden without compromising prediction accuracy. © 2024, The Authors. All rights reserved.

关键词： Lithium-ion batteries

来源：评论

学校读者我要写书评

暂无评论

Unified Grid-Forming control of PMSG Wind Turbines for Fast Frequency Response and MPPT

arXiv

引用

arXiv 2022年

作者： Lyu, Xue Groß, Dominic Subotić, Irina Department of Electrical and Computer Engineering University of Wisconsin Madison Madison United States Automatic Control Laboratory ETH Zürich Zürich Switzerland

In this work we present a novel dual-port grid-forming control strategy, for permanent magnet synchronous generator wind turbines with back-to-back voltage source converters, that unifies the entire range of functions from maximum power point tracking (MPPT) to providing inertia and fast frequency response without explicit mode switching between grid-following and grid-forming control. The controls impose a well-defined AC voltage at the grid-side converter (GSC) and the machine-side converter (MSC) AC terminals and explicitly stabilize the DC-link capacitor voltage through both GSC and MSC. The wind turbine's kinetic energy storage and curtailment are adjusted through a combination of implicit rotor speed control and pitch angle control and directly determine the operating mode and level of grid support. Moreover, we provide analytical small-signal stability conditions for a simplified system and explicitly characterize the relationship between control gains, curtailment, and the wind turbines steady-state response. Finally, a detailed simulation study is used to validate the results and compared the proposed control with state-of-the-art MPPT control. Copyright © 2022, The Authors. All rights reserved.

关键词： Wind turbines

来源：评论

学校读者我要写书评

暂无评论

An intelligent recommendation model for small batch gradient descent method

An intelligent recommendation model for small batch gradient...

引用

Cloud Computing, Big Data Applications and Software engineering (CBASE), International Conference on

作者： Xiaoying Ye Rong Tang Xiaoyan Ye School of Computer Guangdong Neusoft Institute Foshan Guangdong China Chongqing Center for Disease Control and Prevention China Software Engineering Institute of Guangzhou China

In order to solve the problems of objective function oscillation and lack of accuracy caused by random gradient descent in intelligent recommendation system, a personalized recommendation model based on small batch gradient descent method is proposed. By establishing a personalized recommendation model based on small batch gradient descent method, the model can reduce the randomness of the optimal solution of the objective function, improve the accuracy and reduce the running time, so as to improve the quality of personalized recommendation. The model is verified with the public movielens data set. The results show that the root mean square error (RMSE) and mean absolute error (MAE) of the model are better than the existing algorithms. It is verified that the personalized recommendation model based on small batch gradient descent method can get better recommendation effect.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Fast Load control of Supercritical Unit Through ADRC Optimized by Cross Quantum Pigeon

Fast Load Control of Supercritical Unit Through ADRC Optimiz...

引用

Chinese Intelligent Systems Conference, CISC 2020

作者： Hou, Guolian Huang, Ting Su, Huilin Gong, Linjuan Huang, Congzhi Hu, Bo Wang, Bing School of Control and Computer Engineering North China Electric Power University Beijing102206 China State Grid Liaoning Electric Power Supply Co. Ltd. Shenyang110004 China

ISBN: (纸本)9789811584572

In order to absorb the random fluctuations caused by the large scale integration of new energy into the power grid, it is essential to improve the flexible operation ability of cool-fired especially supercritical units. In this paper, a fast load control strategy based on the active disturbance rejection control (ADRC) theory is proposed for the coordinated control system in supercritical units. Then, a novel cross quantum pigeon optimization algorithm is used to optimize the ADRC controller parameters automatically for coordinated control system. Finally, extensive simulation results demonstrate the feasibility and effectiveness of the optimal control strategy in fast load control. © 2021, The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Disturbance rejection

来源：评论

学校读者我要写书评

暂无评论

Adaptation Via Proxy: Building Instance-Aware Proxy for Unsupervised Domain Adaptive 3d Object Detection

SSRN

引用

SSRN 2023年

作者： Li, Ziyu Yao, Yuncong Quan, Zhibin Qi, Lei Feng, Zhenhua Yang, Wankou School of Automation Southeast University Nanjing210096 China Key Lab of Measurement and Control of Complex Systems of Engineering Ministry of Education Southeast University Nanjing210096 China School of Computer Science and Engineering Southeast University Nanjing210096 China Department of Computer Science University of Surrey GuildfordGU2 7XH United Kingdom

LiDAR-based 3D detectors perform well on particular autonomous driving benchmarks, but may poorly generalize to other domains. Existing 3D domain adaptive detection methods usually require annotation-related statistics or continuous refinement of pseudo-labels. The former is not always feasible for practical applications, while the latter lacks sufficient accurate supervision. In this work, we propose a novel unsupervised domain adaptive framework, namely Adaptation Via Proxy (AVP), that explicitly leverages cross-domain relationships to generate adequate high-quality samples without any target statistics, thus mitigating domain shifts for existing LiDAR-based 3D detectors. Specifically, we first train the detector on the source domain with curriculum example mining to enhance its generalization capability. Then, we fine-tune the pre-trained detector on the instance-aware proxy that is a data collection with stronger supervision. The instance-aware proxy utilizes the profitable instances from the source domain to provide more robust supervision for optimizing the detector to overcome domain gaps. Note that AVP is architecture-agnostic thus it can be easily injected with any LiDAR-based 3D detectors. Extensive experiments on Waymo, nuScenes, KITTI and Lyft demonstrate the superiority of the proposed method over the state-of-the-art approaches for different adaptation scenarios. © 2023, The Authors. All rights reserved.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Effect of lead time prediction accuracy in trust-based resource sharing

引用

IFAC-PapersOnLine 2021年第1期54卷 1126-1131页

作者： Ádám Szaller Botond Kádár Centre of Excellence in Production Informatics and Control Institute for Computer Science and Control Budapest Hungary Department of Manufacturing Science and Engineering Budapest University of Technology and Economics Budapest Hungary

Nowadays, challenges are changing production facilities: decentralized production networks are replacing centralized organizations to remain competitive. This paper investigates a resource sharing approach where matching resource offers and requests are made by an intermediate platform. One of the main pillars of collaboration is to keep promises, especially about deadlines: in the presented model, facilities could rate each other based on trustfulness and choose from offers based on this setting. Lead time prediction accuracy has a direct effect on the real processing intervals: if the prediction was accurate, the deadline could be met, which results in good ratings and a higher possibility to win more jobs. In the paper, effect of lead time prediction accuracy is investigated in trust-based resource sharing, and the performance of facilities is compared with agent-based simulation.

关键词： Co-operative control/manufacturing Multi-agent simulation Manufacturing System engineering

来源：评论

学校读者我要写书评

暂无评论

Predicting of Uncertainty Facial Expressions in Children with Autism Spectrum Disorder Based on an Improved Fuzzy Convolutional Neural Network Model

SSRN

引用

SSRN 2024年

作者： Abd-Alhalem, Samia M. Ali, Hesham A. El-Shafai, Walid Algarni, Abeer D. Soliman, Naglaa F. El-Samie, Fathi E. Faculty of Artificial Intelligence Delta University for Science and Technology Gamasa35712 Egypt Computers and Control Systems Engineering Department Faculty of Engineering Mansoura University Mansoura35516 Egypt Security Engineering Lab Computer Science Department Prince Sultan University Riyadh11586 Saudi Arabia Department Electronics and Electrical Communications Engineering Faculty of Electronic Engineering Menoufia University Menouf32952 Egypt Department of Information Technology College of Computer and Information Sciences Princess Nourah Bint Abdulrahman University P.O. Box 84428 Riyadh11671 Saudi Arabia Zagazig University Egypt Menoufia University Egypt

Facial expression recognition plays a pivotal role in comprehending emotions and social interactions, particularly in individuals grappling with autism spectrum disorder (ASD), who often encounter challenges in non-verbal communication. For some with ASD, even subtle shifts in their facial expressions can prove elusive, rendering it arduous to categorize their emotional states accurately. Consequently, the analysis and processing of facial expression data hold the potential to facilitate early autism diagnosis, thereby enabling timely therapeutic interventions and alleviating the economic and psychological burdens experienced by patients. In this study, we introduce an enhanced approach that leverages a fuzzy convolutional neural network (CNN) and an Improved Binary Genetic Algorithm (IBGA) for autism diagnosis based on facial expression data. Our model confronts the intricate task of recognizing facial images by selecting salient features employing the IBGA method. Moreover, it employs fuzzy weights to ascertain the probability of similarity within the classifier layer. Our proposed model has yielded impressive outcomes, boasting an average accuracy of 0.9405 for ASD detection and 0.9365 for the recognition of six distinct facial expressions. These results hold profound implications for the enhancement of emotion recognition systems and the refinement of interventions aimed at bolstering social interactions for individuals grappling with ASD. © 2024, The Authors. All rights reserved.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

Phase chimera states on nonlocal hyperrings

引用

Physical Review E 2024年第2期109卷 L022201-L022201页

作者： Riccardo Muolo Thierry Njougouo Lucia Valentina Gambuzza Timoteo Carletti Mattia Frasca Department of Systems and Control Engineering Tokyo Institute of Technology Tokyo 152-8552 Japan Department of Mathematics University of Namur B5000 Namur Belgium naXys Namur Institute for Complex Systems University of Namur B5000 Namur Belgium Faculty of Computer Science University of Namur B5000 Namur Belgium Department of Electrical and Electronic Engineering University of Buea P.O. Box 63 Buea Cameroon Department of Electrical Electronics and Computer Science Engineering University of Catania 95125 Catania Italy Istituto di Analisi dei Sistemi ed Informatica “A. Ruberti” IASI-CNR 00185 Roma Italy

Chimera states are dynamical states where regions of synchronous trajectories coexist with incoherent ones. A significant amount of research has been devoted to studying chimera states in systems of identical oscillators, nonlocally coupled through pairwise interactions. Nevertheless, there is increasing evidence, also supported by available data, that complex systems are composed of multiple units experiencing many-body interactions that can be modeled by using higher-order structures beyond the paradigm of classic pairwise networks. In this work we investigate whether phase chimera states appear in this framework, by focusing on a topology solely involving many-body, nonlocal, and nonregular interactions, hereby named nonlocal d-hyperring, (d+1) being the order of the interactions. We present the theory by using the paradigmatic Stuart-Landau oscillators as node dynamics, and we show that phase chimera states emerge in a variety of structures and with different coupling functions. For comparison, we show that, when higher-order interactions are “flattened” to pairwise ones, the chimera behavior is weaker and more elusive.

关键词： Chimera states Collective behavior in networks Dynamics of networks Pattern formation Synchronization Synchronization transition

来源：评论

学校读者我要写书评

暂无评论

A deep learning-based unsupervised learning method for spatially resolved transcriptomic data analysis

A deep learning-based unsupervised learning method for spati...

引用

2022 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2022

作者： Peng, Lihong He, Xianzhi Zhang, Li Peng, Xinhuai Lu, Yuankang Li, Zejun Chen, Xing Hunan University of Technology School of Computer Science Zhuzhou China China University of Mining and Technology School of Information and Control Engineering Xuzhou221116 China Artificial Intelligence Research Institute Hunan Institute of Technology Hengyang China Artificial Intelligence Research Institute China University of Mining and Technology Xuzhou China

ISBN: (纸本)9781665468190

Spatially resolved transcriptomic data provide a large quantity of high-throughput gene expression and spatial structure information of tissues. Spatial clusters obtained by spatial transcriptome helps us to identify co-expressed regions and gene modules corresponding to cell types. In this study, we developed a Deep learning-based spatial clustering algorithm (RkDeep) by combining Ratio-cut and k-means. We first preprocessed spatial transcriptome data using graph neural network, and conducted dimensional reduction on the preprocessed data with denoising autoencoder. Finally, we clustered spatial transcriptome data by combining ratio cut and k-means. We compared our proposed RkDeep method with the other two spatial clustering methods, Seurat and Panoview. The results show that RkDeep computed the smallest Davide-Bouldin index and the largest Caliniski Harabaz index, adjusted rand index and normalized mutual information. Moreover, RkDeep was applied to analyze spatial transcriptome data of adult mouse brain, adult mouse kidney, and breast cancer. The results show that RkDeep can more accurately identify cell types from spatial transcriptome data. © 2022 IEEE.

关键词： Gene expression

来源：评论

学校读者我要写书评

暂无评论

Molecular communication networks: drug target scalability based on artificial intelligence prediction techniques

引用

Journal of Nanoparticle Research 2021年第3期23卷 1-23页

作者： A. R. Junejo Xiang Li Hina Madiha Soha Mohamed School of Control Science and Control Engineering Harbin Institute of Technology Harbin China School of Computer Science &Technology Shaanxi Normal University Xian China School of Computer Science & Technology Harbin Institute of Technology Harbin China

With the continuous improvement of computer performance and related technology, the combination of molecular communication networks (MCN) and artificial intelligence (AI) can find the prediction to analyze target methods that are molecular diagnosis (MD) and more efficient. To overcome this issue, researchers have suggested the novel paradigm of the MD that combines nanoparticles-medicine (NPs-M) with tools from synthetic biology to provide re-engineering of biological computing devices. Here, in this work, the prediction model of the target is established by combining the drug calculation model of MCN and deep neural network (DNN) including classification performance for prediction. We developed a numerical analysis model to refer to drug target scalability (DTS), on a genome-wide scale based on protein to protein interaction (PPI) such as in-term of cardiac-disease. Finally, the prediction of the strength and direction of binding affinity between drugs and targets is achieved. Furthermore, to expand the application of the model, with a combination of genetic databases, the micro-processes related to genes are displayed. Then, to combine medicine, a multi-layer network is established based on the effect on/off mechanism. We establish a systematic MCN evaluation model that reveals the basis of MD of medicine and serves for screening, reorientation, drug development, and other fields of medical healthcare industries (MHI). The engineering finding demonstrates that the integration of phenotypic, chemical index in the NPs-M and PPI cannot only achieve scalability but also finds new applications for an existing drug.

关键词：

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：