检索结果-内蒙古大学图书馆

On the Cognitive Interface of Intelligent Systems Implementing the JSM Method of Automated research Support

Automatic Documentation and Mathematical Linguistics 2025年第1期59卷 50-56页

作者： Shesternikova, O. P. Finn, V. K. Federal Research Center “Computer Science and Control ” Russian Academy of Sciences Moscow Russia

This article presents comments on the cognitive interface of an intelligent system (IS) implementing the JSM method of automated research support (JSM method ARS). The IS consists of an information environment, a Solver, and a cognitive interface. One component of the cognitive interface is a metatheoretical study (metatheoretical analysis) applied to the results generated by the Solver of IS. New procedures are proposed that expand the existing set of procedures in metatheoretical research: determining the type of the cause context (determining the influence of other causes in a situation of multiple causes) and recognizing the ternary of the cause (satisfaction with the ternary relation “object-set of obstacles (brakes)-effect”) for empirical preregularities (EPRs) and, accordingly, empirical regularities (ERs), a superposition of EPRs. An example from a study of type 3c diabetes is given.

关键词： Automation

来源：评论

学校读者我要写书评

暂无评论

Scalable Multi-Agent Reinforcement Learning for Residential Load Scheduling Under Data Governance

IEEE Transactions on Industrial Cyber-Physical Systems

引用

IEEE Transactions on Industrial Cyber-Physical Systems 2025年 3卷 351-361页

作者： Qin, Zhaoming Dong, Nanqing Liu, Di Wang, Zhefan Cao, Junwei EPFL Automatic Control Laboratory Lausanne1015 Switzerland Shanghai Artificial Intelligence Laboratory Shanghai200232 China Tsinghua University Department of Electrical Engineering Beijing100084 China Tsinghua University Beijing National Research Center for Information Science and Technology Beijing100084 China

As a data-driven approach, multi-agent reinforcement learning (MARL) has made remarkable advances in solving cooperative residential load scheduling problems. However, centralized training, the most common paradigm for MARL, limits large-scale deployment in communication-constrained cloud-edge environments. As a remedy, distributed training shows unparalleled advantages in real-world applications but still faces challenge with system scalability, e.g., the high cost of communication overhead during coordinating individual agents, and needs to comply with data governance in terms of privacy. In this work, we propose a novel MARL solution to address these two practical issues. Our proposed approach is based on actor-critic methods, where the global critic is a learned function of individual critics computed solely based on local observations of households. This scheme preserves household privacy completely and significantly reduces communication cost. Simulation experiments demonstrate that the proposed framework achieves comparable performance to the state-of-the-art actor-critic framework without data governance and communication constraints. © 2023 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Diversity-enhanced adaptive golden jackal optimization based on multi-strategy and its engineering applications

引用

Cluster Computing 2025年第5期28卷 1-27页

作者： Wang, Wenjie Zhang, Boqin Liu, Zhao Zhu, Ping School of Mechanical Engineering Shanghai Jiao Tong University Shanghai200240 China National Engineering Research Center of Automotive Power and Intelligent Control Shanghai Jiao Tong University Shanghai200240 China School of Design Shanghai Jiao Tong University Shanghai200240 China

Nowadays, many real-world optimization problems are becoming increasingly complex, leading to a growing popularity of metaheuristics. Among various metaheuristics, the recently developed Golden Jackal Optimization (GJO) has attracted significant attention due to its flexibility and effectiveness in engineering. However, GJO suffers from poor diversity and limited exploration. To address these drawbacks, this paper proposes a multi-strategy improved algorithm called Diversity-enhanced Adaptive Golden Jackal Optimization (DAGJO). Jackals in DAGJO are assigned two novel roles with five enhanced search modes to increase solution diversity. Particularly, the elite diverse utilization strategy is introduced to fully leverage individuals with better fitness. Then, the multiple candidate mechanism and perturbation mechanism are employed to avoid premature convergence. Additionally, the alternating compound adaptive mechanism is designed to balance exploration and exploitation capabilities. To verify the effectiveness, 25 benchmark test functions and 12 CEC2022 functions are solved by DAGJO, along with 12 excellent algorithms including the latest GJO variants. Furthermore, to assess the performance of DAGJO in real-world scenarios, four constrained engineering design problems and a data-driven automotive crash safety optimization design case are also employed for experiments. The results indicate that DAGJO generally exhibits superior performance in both global optimization and engineering design problems. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2025.

关键词： Machine design

来源：评论

学校读者我要写书评

暂无评论

DADAN: Dynamic-Augmented and Density-Aware Network for Accurate 3-D Object Detection With 4-D Radar

引用

IEEE Sensors Journal 2025年第6期25卷 10272-10286页

作者： Wang, Xingzheng Li, Jiahui Wu, Jianbin Wu, Shaoyong Li, Lihua Shenzhen University College of Mechatronics and Control Engineering Shenzhen518060 China Shenzhen Technology University Guangdong-Hongkong-Macao Critical Optical Components Precision Manufacturing Research Center Sino-German College of Intelligent Manufacturing Shenzhen518118 China

The cost-effective automotive 4-D radar is emerging as a feasible solution for 3-D object detection in autonomous driving scenarios. However, point clouds generated by 4-D radar are typically sparse. Current methods encounter challenges in resolving the foreground-background confusion in sparse point clouds due to: 1) the underutilization of the unique dynamic information (velocity and intensity) of 4-D radar points;and 2) the density variations of point clouds where they are near-dense-far-sparse, exacerbating the confusion. Therefore, we propose a dynamic-augmented and density-aware network (DADAN) to address these challenges by: 1) assigning high weights to foreground points based on dynamic information and enhancing their feature encoding to reduce confusion effectively;and 2) utilizing attention mechanisms along with density information to adaptively address exacerbated confusion caused by density variations. The DADAN comprises a dynamic-augmented encoding network, a density-aware backbone, and a detection head. The encoding network incorporates a dynamic-augmented encoding module (DAEM) that assigns high weights to foreground points based on velocity and intensity data to improve their feature encoding. Notably, foreground points typically exhibit distinct dynamic information compared to background points, distinguishing them from the background. The backbone network incorporates an attention mechanism along with density information to generate density-aware features. The detection head is responsible for 3-D bounding boxes and object categories. The experimental results on various public datasets demonstrate the superior performance of the proposed method compared to existing approaches. These results illustrate that the DADAN effectively addresses the issue of confusion, accurately detecting objects in complex scenes. © 2001-2012 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Terahertz time-of-flight tomography algorithm for different curvature samples

引用

Optics Express 2025年第7期33卷 15095-15109页

作者： Zhou, Yu Li, Quanyong Cui, Zongyu Zhang, Jiyang Ren, Jiaojiao Zhang, Dandan Gu, Jian Li, Haoxiang Lin, Zihao Key Laboratory of Optoelectronic Measurement and Control and Optical Information Transmission Technology Ministry of Education Changchun University of Science and Technology Changchun130022 China School of Optoelectronic Engineering Changchun University of Science and Technology Changchun130022 China Zhongshan Research Institute Changchun University of Science and Technology Zhongshan528403 China

Traditional guide rail-based terahertz reflection tomography works well with planar samples and complements transmission tomography. Most imaging methods perform effectively with plane-like or simple curvature samples. However, these methods are ineffective for complex shapes due to the challenges of dealing with internal corrections and stitching errors. To address the above issues, terahertz time-of-flight tomography is applied to the prepared samples with abnormal curvature using a rotating scanning array and "point cloud splicing" method. This approach enables comprehensive sample information collection and resolves the inner layer point cloud position correction challenge. A radial distance point cloud down-sampling method is proposed to reduce the impact of overlapping point clouds on reconstruction accuracy. After down-sampling, the outer layer reconstruction error reduces to 0.22%. Poisson surface reconstruction further enhances the intuitiveness of imaging results, and the reconstruction accuracy is 0.01 mm. This study broadens the application of terahertz time-of-flight tomography and offers a different approach for reflection tomography. © 2025 Optica Publishing Group under the terms of the Optica Open Access Publishing Agreement.

关键词： Surface reconstruction

来源：评论

学校读者我要写书评

暂无评论

HPO-BiLSTM Based on Causal Analysis of Upstream and Downstream Industries Load Forecasting Method 19th

HPO-BiLSTM Based on Causal Analysis of Upstream and Downstre...

引用

19th Annual Conference of China Electrotechnical Society, ACCES 2024

作者： Liu, Yaoxian Su, Jiahao Qiu, Min Chen, Jingwen School of Electrical and Control Engineering Shaanxi University of Science and Technology Xi’an710021 China China Electric Power Research Institute Limited BeiJing100192 China

ISBN: (纸本)9789819646746

Due to the lack of causality between upstream and downstream industries in the existing load forecasting research, the accuracy of load forecasting between industries is poor. Therefore, this paper proposes an HPO-BiLSTM industry load forecasting method based on causal analysis. Firstly, convergence cross-mapping algorithm is used to identify the causal relationship between ferroalloy industry and related industries, and typical industries with strong causality are selected. Secondly, the original load data is decomposed by an improved adaptive noise complete empirical mode decomposition method. Finally, the hunter and prey algorithm is used to optimize the bidirectional long and short term network, and the decomposed load data is predicted. Finally, the accuracy of the proposed method is compared with that of XGBoost and LSTM prediction models. Experiments show that the proposed method can effectively extract the relevant features of different industries in the load prediction of ferroalloy industry. The prediction accuracy is significantly improved, which provides important support for rational planning and stable operation of urban power grid. © Beijing Paike Culture Commu. Co., Ltd. 2025.

关键词： Causal analysis HPO-BiLSTM ICEEMDAN industry load forecasting

来源：评论

学校读者我要写书评

暂无评论

Using an optical fiber passive depolarizer to suppress the polarization dependence of stimulated Raman scattering gain in hydrogen sensor system 4

Using an optical fiber passive depolarizer to suppress the p...

引用

4th International Computational Imaging Conference, CITA 2024

作者： Shuzhi, Yao Xuan, Zheng Yong, Yang Meng, Jiang Hui, Gao Meng, Zhang Xuefeng, Wang Beijing Institute of Aerospace Control Device Beijing100094 China Beijing Optical Fiber Sensing System Engineering Technology Research Center Beijing100094 China

ISBN: (纸本)9781510688834

Optical fiber hydrogen sensors have recently received great attention because of the advantages of essential safety, anti-electromagnetic interference, corrosion resistance, suitable for long distance detection and so on. A new type of optical fiber hydrogen sensors based on stimulated Raman scattering spectroscopy and nanofiber was proposed several yeas ago which can realize ultra-fast, ultra-sensitive hydrogen detection with ultra-wide dynamic range. However, the Raman gain depends on the polarization states of the pump and Stokes beams and the Raman signal will drift when the fiber status or the environment temperature are changed. In this paper, we propose and demonstrate an optical fiber passive depolarizer to suppress the polarization dependence of stimulated Raman scattering gain in the aforementioned hydrogen sensor system. The depolarizer mainly consists of two fiber polarization beam splitters(PBSs) and a piece of delay fiber. The angle of incidence for any PBS is 45° and the delay fiber length is much longer than the coherent length of the input beam. The input beam is split into two beams by PBS1 one of which transfers through the delay fiber. Then these two beams are combined by PBS2 to obtain the output beam composed of two orthogonal beams with equal power, and their phase relationship changes randomly. By inserting the depolarizer into the pump beam path, the Raman signal will not be influenced by the changes of the fiber status or the environment temperature. This achievement would be very useful for real application of the hydrogen sensor in long distance detection and multi-channel sensing system. © 2025 SPIE.

关键词： Stimulated Raman scattering

来源：评论

学校读者我要写书评

暂无评论

Copper-catalyzed Larock-type cyclization/debenzylation of yne-allylic esters with aliphatic amines

引用

science China Chemistry 2025年

作者： Rongkang Huang Yuepeng Lu Feng Xu Jianhang Huang Cuiju Zhu Hao Xu Engineering Research Center of Photoenergy Utilization for Pollution Control and Carbon Reduction State Key Laboratory of Green Pesticide College of Chemistry Central China Normal University

Herein, we describe a strategy for constructing pyrroles via a copper-catalyzed [4 + 1] annulation of yne-allylic esters and aliphatic amines. The key innovation of this approach is the development of copper-ammonium intermediates that facilitate selective C–N bond cleavage under mild conditions. This method demonstrates broad applicability, accommodating both aliphatic secondary amines and aliphatic primary amines, while exhibiting excellent tolerance toward a wide range of functional groups. Furthermore, the ease of subsequent transformations underscores its potential utility in the synthesis of bioactive compounds. Preliminary mechanistic investigations suggest the involvement of a copper-ammonium species, providing insight into the reaction's underlying process.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Masses of Ground States of Triply Heavy Tetraquarks

引用

Physics of Particles and Nuclei 2025年第2期56卷 330-334页

作者： Galkin, V.O. Savchenko, E.M. Federal Research Center Computer Science and Control Russian Academy of Sciences Moscow 119333 Russian Federation Faculty of Physics Moscow State University Moscow 119991 Russian Federation

Abstract: Masses of ground states of triply heavy tetraquarks are calculated within the relativistic quark model based on the quasipotential approach and the diquark–antidiquark picture of tetraquarks. The relativistic diquark–antidiquark interaction quasipotential takes into account the internal structure of the diquark and antidiquark and all relativistic corrections. The calculated masses are compared to fall-apart decay thresholds into a meson pair, and conclusions are drawn about the possibility of detecting such states. © Pleiades Publishing, Ltd. 2025.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Compaction as a cost-effective strategy to upgrade the disposal of MSWI fly ash:feasibility and potential

引用

Frontiers of Environmental science & engineering 2025年第3期19卷 145-158页

作者： Shijin Dai Fafa Xia Bo Yang Deli Wu Dongjie Niu Youcai Zhao Xunchang Fei Zhanbo Cheng Hongping He Baoan District City Appearance and Environment Comprehensive Management Service Center Shenzhen 518101China College of Environmental Science and Engineering Tongji UniversityShanghai 200092China College of Chemistry and Environmental Engineering Shenzhen UniversityShenzhen 518060China Shanghai Institute of Pollution Control and Ecological Security Shanghai 200092China School of Civil and Environmental Engineering Nanyang Technological UniversitySingapore 639798Singapore

Landfilling remains the primary disposal method for fly ash produced from municipal solid waste incineration(MSWI)following stabilization/***,the increasing generation of stabilized fly ash(SFA)is accelerating the depletion of landfill ***,the small particle size and low bulk density of SFA present significant environmental risks during handling and *** mitigate these issues,a cost-effective compaction method was introduced into the SFA disposal *** results show that SFA from both grate furnaces and fluidized bed incinerators exhibited high porosity,loose structure,and irregular particle morphology,indicating substantial potential for *** parameters influencing compaction effectiveness included compaction pressure,holding duration,and moisture content,with optimal values identified as 100–200 MPa,20 s,and 10%–15%moisture,respectively,depending on the incinerator *** compaction treatment,the density of SFA more than doubled,while its volume was reduced by over 60%,significantly increasing landfill capacity and enhancing the efficiency of SFA *** compaction process was effectively modeled using the Huang Peiyun equation for gerate furnace ash and the Heckel equation for fluidized bed ***,the unconfined compressive strength and three-point bending strength of compacted SFA met the MU10 standard for lime-sand bricks,making the material suitable for transportation and ***,the compaction-based disposal method for SFA demonstrated clear techno-economic advantages and significant potential for broader application in waste management strategies.

关键词： Stabilized fly ash Compaction process Volume reduction Disposal upgrading

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：