检索结果-内蒙古大学图书馆

MOSSA: An Efficient Swarm Intelligent Algorithm to Solve Global Optimization and Carbon Fiber Drawing Process Problems

引用

IEEE Internet of Things Journal 2025年第9期12卷 11940-11953页

作者： Xue, Jiankai Zhang, Chenglong Wang, Muming Dong, Xuezhe Anhui University of Technology School of Computer Science and Technology Ma’anshan243032 China Chinese University of Hong Kong School of Data Science Shenzhen518172 China University of Science and Technology of China School of Information Science and Technology Hefei230026 China University of Calgary Department of Chemical and Petroleum Engineering CalgaryABT2N 1N4 Canada Hong Kong Polytechnic University Department of Applied Physics Hong Kong

In this article, the sparrow search algorithm (SSA) is extended to the multiobjective SSA (MOSSA) with the purpose of efficiently solving the multiobjective optimization problems (MOPs). First, the MOSSA adaptively evaluates nondominated sparrow individuals stored in the external archive (EA) by using an adaptive mesh approach, which is utilized to obtain the best producer. Second, the scrounger sparrows adjust their trajectories according to the location of the best producer, called the scrounger follow strategy, which can improve the quality of the solutions when solving MOPs. Then, the proposed scouter search strategy is capable of maintaining population diversity and accelerate convergence. Moreover, the EA is pruned with the aim of avoiding the waste of computing resources. Extensive experiments with 22 benchmark examples validate the effectiveness of our approach against six state-of-the-art optimization approaches. Finally, the MOSSA is applied in the carbon fiber drawing process problems and the stretching parameters obtained by the MOSSA is reasonable. © 201. IEEE.

关键词： Optimization algorithms

来源：评论

学校读者我要写书评

暂无评论

6DMA-Aided Cell-Free Massive MIMO Communication

引用

IEEE Wireless Communications Letters 2025年第5期14卷 1361-1365页

作者： Shi, Xiaoming Shao, Xiaodan Zheng, Beixiong Zhang, Rui The Chinese University of HongKong School of Science and Engineering Guangdong Shenzhen518172 China University of Waterloo Department of Electrical and Computer Engineering WaterlooONN2L 3G1 Canada South China University of Technology School of Microelectronics Guangzhou511442 China The Chinese University of HongKong School of Science and Engineering Shenzhen Research Institute of Big Data Guangdong Shenzhen518172 China National University of Singapore Department of Electrical and Computer Engineering Singapore117583 Singapore

In this letter, we propose a six-dimensional movable antenna (6DMA)-aided cell-free massive multiple-input multiple-output (MIMO) system to fully exploit its macro spatial diversity, where a set of distributed access points (APs), each equipped with multiple 6DMA surfaces, cooperatively serve all users in a given area. Connected to a central processing unit (CPU) via fronthaul links, 6DMA-APs can optimize their combining vectors for decoding the users' information based on either local channel state information (CSI) or global CSI shared among them. We aim to maximize the average achievable sum-rate via jointly optimizing the rotation angles of all 6DMA surfaces at all APs, based on the users' spatial distribution. Since the formulated problem is non-convex and highly non-linear, we propose a Bayesian optimization-based algorithm to solve it efficiently. Simulation results show that, by enhancing signal power and mitigating interference through reduced channel cross-correlation among users, 6DMA-APs with optimized rotations can significantly improve the average sum-rate, as compared to the conventional cell-free network with fixed-position antennas and that with only a single centralized AP with optimally rotated 6DMAs, especially when the user distribution is more spatially diverse. © 201. IEEE.

关键词： Convex optimization

来源：评论

学校读者我要写书评

暂无评论

Cooperative Multiagent Learning and Exploration With Min-Max Intrinsic Motivation

引用

IEEE Transactions on Cybernetics 2025年第6期55卷 2852-2864页

作者： Hou, Yaqing Kang, Jie Piao, Haiyin Zeng, Yifeng Ong, Yew-Soon Jin, Yaochu Zhang, Qiang Dalian University of Technology College of Computer Science and Technology Dalian116024 China Jilin University School of Artificial Intelligence Changchun130015 China Northumbria University Newcastle upon TyneNE1 8ST United Kingdom Nanyang Technological University School of Computing and Data Science Singapore Singapore Agency for Science Technology and Research Centre for Frontier Ai Research Institute of High Performance Computing Singapore Singapore Westlake University School of Engineering Hangzhou310030 China

In the field of multiagent reinforcement learning (MARL), the ability to effectively explore unknown environments and collect information and experiences that are most beneficial for policy learning represents a critical research area. However, existing work often encounters difficulties in addressing the uncertainties caused by state changes and the inconsistencies between agents' local observations and global information, which presents significant challenges to coordinated exploration among multiple agents. To address this issue, this article proposes a novel MARL exploration method with Min-Max intrinsic motivation (E2M) that promotes the learning of joint policies of agents by introducing surprise minimization and social influence maximization. Since the agent is subject to unstable state changes in the environment, we introduce surprise minimization by computing state entropy to encourage the agents to cope with more stable and familiar situations. This method enables surprise estimation based on the low-dimensional representation of states obtained from random encoders. Furthermore, to prevent surprise minimization from leading to conservative policies, we introduce mutual information between agents' behaviors as social influence. By maximizing social influence, the agents are encouraged to interact to facilitate the emergence of cooperative behavior. The performance of our proposed E2M is testified across a range of popular StarCraft II and Multiagent MuJoCo tasks. Comprehensive results demonstrate its effectiveness in enhancing the cooperative capability of the multiple agents. © 2025 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Predict+Optimize Problem in Renewable Energy Scheduling

引用

IEEE Access 2025年 13卷 60064-60087页

作者： Bergmeir, Christoph de Nijs, Frits Genov, Evgenii Sriramulu, Abishek Abolghasemi, Mahdi Bean, Richard Betts, John Bui, Quang Dinh, Nam Trong Einecke, Nils Esmaeilbeigi, Rasul Ferraro, Scott Galketiya, Priya Glasgow, Robert Godahewa, Rakshitha Kang, Yanfei Limmer, Steffen Magdalena, Luis Montero-Manso, Pablo Peralta, Daniel Kumar, Yogesh Pipada Sunil Rosales-Pérez, Alejandro Ruddick, Julian Stratigakos, Akylas Stuckey, Peter Tack, Guido Triguero, Isaac Yuan, Rui DaSCI Andalusian Institute in Data Science and Computational Intelligence Granada18071 Spain University of Granada Department of Computer Science and Artificial Intelligence Granada18071 Spain Monash University Department of Data Science and Artificial Intelligence MelbourneVIC3800 Australia Vrije Universiteit Brussel EVERGi MOBI Brussels1050 Belgium Queensland University of Technology Faculty of Science School of Mathematical Sciences BrisbaneQLD4000 Australia The University of Queensland Centre for Energy Data Innovation School of Information Technology and Electrical Engineering BrisbaneQLD4072 Australia The University of Adelaide School of Electrical and Electronics Engineering AdelaideSA5005 Australia Honda Research Institute Europe GmbH Offenbach63073 Germany Deakin University School of Information Technology MelbourneVIC3125 Australia Monash University Building and Property Division MelbourneVIC3800 Australia Beihang University School of Economics and Management Beijing100191 China Universidad Politécnica de Madrid E.T.S. Ingenieros Informáticos Madrid28660 Spain The University of Sydney Disciple of Business Analytics SydneyNSW2050 Australia Centro de Investigación en Matemáticas Department of Computer Science Monterrey66629 Mexico Mines Paris Sophia Antipolis06904 France Laboratory School of Computer Science NottinghamNG8 1BB United Kingdom

Predict+Optimize frameworks integrate forecasting and optimization to address real-world challenges such as renewable energy scheduling, where variability and uncertainty are critical factors. This paper benchmarks solutions from the IEEE-CIS Technical Challenge on Predict+Optimize for Renewable Energy Scheduling, focusing on forecasting renewable production and demand and optimizing energy cost. The competition attracted 49 participants in total. The top-ranked method employed stochastic optimization using LightGBM ensembles, and achieved at least a 2% reduction in energy costs compared to deterministic approaches, demonstrating that the most accurate point forecast does not necessarily guarantee the best performance in downstream optimization. The published data and problem setting establish a benchmark for further research into integrated forecasting-optimization methods for energy systems, highlighting the importance of considering forecast uncertainty in optimization models to achieve cost-effective and reliable energy management. The novelty of this work lies in its comprehensive evaluation of Predict+Optimize methodologies applied to a real-world renewable energy scheduling problem, providing insights into the scalability, generalizability, and effectiveness of the proposed solutions. Potential applications extend beyond energy systems to any domain requiring integrated forecasting and optimization, such as supply chain management, transportation planning, and financial portfolio optimization. © 201. IEEE.

关键词： Optimization Forecasting Renewable energy sources Benchmark testing Australia Scheduling Production Costs Artificial neural networks Stochastic processes

来源：评论

学校读者我要写书评

暂无评论

Comprehension and Knowledge

引用

Journal of Logic, Language and Information 2025年第1期34卷 169-196页

作者： Naumov, Pavel Ros, Kevin School of Electronics and Computer Science University of Southampton Southampton SO17 1BJ United Kingdom Siebel School of Computing and Data Science University of Illinois Urbana-Champaign Champaign 61801 United States

The ability of an agent to comprehend a sentence is tightly connected to the agent’s prior experiences and background knowledge. The article suggests to interpret comprehension as a modality and proposes a complete bimodal logical system that describes an interplay between comprehension and knowledge modalities. The main technical result is a completeness theorem for the proposed system © The Author(s) 2025.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Improving Power Consumption Efficiency and Cost Reduction Using Firefly Algorithm in Smart Home: A Multi-scenario Analysis 4th

Improving Power Consumption Efficiency and Cost Reduction Us...

引用

4th International Conference on Electronic Engineering and Renewable Energy Systems, ICEERE 2024

作者： Dhriyyef, Mohammed El Mehdi, Abdelmalek Benzaouia, Mohammed Hebal, Sara Smart ICT Laboratory National School of Applied Sciences Mohamed First University Oujda Morocco Renewable Energy Embedded System and Data Processing Laboratory National School of Applied Sciences Mohamed First University Oujda Morocco LRSD Laboratory Computer Science Department Ferhat ABBAS Sétif 1 Sétif Algeria

ISBN: (纸本)9789819799749

This paper proposes a multi-scenario analysis based on the Firefly Algorithm (FA) to optimize power consumption efficiency and electricity cost reduction in smart homes. It integrates demand side management (DSM), in particular demand response (DR), to encourage consumers to adjust their energy consumption during peak hours. A home energy management system (HEMS) is developed, optimizing appliance scheduling and air-conditioning system control while minimizing electricity costs and ensuring thermal comfort. Moreover, appliance comfort. Based on three scenarios reflecting different user priorities, significant reductions in electricity costs are achieved, ranging from 6.42 to 21., while maintaining user-defined comfort levels. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Smart homes

来源：评论

学校读者我要写书评

暂无评论

CRCL: Causal Representation Consistency Learning for Anomaly Detection in Surveillance Videos

引用

IEEE Transactions on Image Processing 2025年 34卷 2351-2366页

作者： Liu, Yang Wang, Hongjin Wang, Zepu Zhu, Xiaoguang Liu, Jing Sun, Peng Tang, Rui Du, Jianwei Leung, Victor C. M. Song, Liang Fudan University Academy for Engineering and Technology Shanghai200433 China University of Toronto Department of Computer Science TorontoONM5S 1A1 Canada Hunan University College of Electrical and Information Engineering Hunan Changsha410082 China Duke Kunshan University Division of Natural and Applied Sciences Jiangsu Suzhou215316 China University of California at Davis DataLab: Data Science and Informatics DavisCA95616 United States The University of British Columbia Department of Electrical and Computer Engineering VancouverBCV6T 1Z4 Canada Duke Kunshan University Division of Natural and Applied Sciences Suzhou215316 China Fudan University School of Information Science and Technology Shanghai200433 China China Mobile Chengdu Institute of Research and Development Chengdu610065 China

Video Anomaly Detection (VAD) remains a fundamental yet formidable task in the video understanding community, with promising applications in areas such as information forensics and public safety protection. Due to the rarity and diversity of anomalies, existing methods only use easily collected regular events to model the inherent normality of normal spatial-temporal patterns in an unsupervised manner. Although such methods have made significant progress benefiting from the development of deep learning, they attempt to model the statistical dependency between observable videos and semantic labels, which is a crude description of normality and lacks a systematic exploration of its underlying causal relationships. Previous studies have shown that existing unsupervised VAD models are incapable of label-independent data offsets (e.g., scene changes) in real-world scenarios and may fail to respond to light anomalies due to the overgeneralization of deep neural networks. Inspired by causality learning, we argue that there exist causal factors that can adequately generalize the prototypical patterns of regular events and present significant deviations when anomalous instances occur. In this regard, we propose Causal Representation Consistency Learning (CRCL) to implicitly mine potential scene-robust causal variable in unsupervised video normality learning. Specifically, building on the structural causal models, we propose scene-debiasing learning and causality-inspired normality learning to strip away entangled scene bias in deep representations and learn causal video normality, respectively. Extensive experiments on benchmarks validate the superiority of our method over conventional deep representation learning. Moreover, ablation studies and extension validation show that the CRCL can cope with label-independent biases in multi-scene settings and maintain stable performance with only limited training data available. © 1.92-201. IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Adaptive FTN Signaling Over Rapidly-Fading Channels

引用

IEEE Transactions on Communications 2025年

作者： Tong, Mingfei Huang, Xiaojing Zhang, J. Andrew Hanzo, Lajos The Global Big Data Technologies Center University of Technology Sydney Australia The School of Electronics and Computer Science University of Southampton SouthamptonSO17 1BJ United Kingdom

The research of faster-than-Nyquist (FTN) signaling has reached a state of maturity for considering practical multipath fading channels, rather than idealized additive white Gaussian noise channels only. To overcome fast-fading multipath propagations, conventional FTN systems tend to rely on channel coding techniques for cleaning up the residual errors, rather than harnessing Doppler effect mitigation. To circumvent this limitation, we propose an adaptive transmit precoding (ATPC) method associated with FTN signaling for applications in fast-fading multipath channels. Upon leveraging real-time channel state information fed back by the receiver, ATPC updates the modulation matrix to improve resilience against Doppler frequency shifts. To mitigate the inter-block interference and multipath effect, a cyclic prefix is inserted at the beginning of each transmission frame. In addition, we employ decision-directed successive interference cancellation for alleviating the inter-symbol interference stemming from FTN signaling and multipath effects. We also analyze the theoretical bit error rate (BER) performance and a pair of closed-form BER expressions are derived for extreme channel conditions, i.e., sufficiently large number of paths and sufficiently large Doppler frequency shift. Simulation results verify the effectiveness of the proposed ATPC method and demonstrate our performance improvements over conventional schemes. © 1.72-201. IEEE. All rights reserved.

关键词： Bit error rate

来源：评论

学校读者我要写书评

暂无评论

An artificial intelligence and blockchain technology-based data management framework for multicenter randomized controlled trials

引用

science Bulletin 2025年第6期70卷 856-860页

作者： Dongyuan Yun Xiaohang Wu Xi Chen Yahan Yang Yuanjun Shang Shaopeng Liu Dinesh Visva Gunasekeran Duoru Lin Lixue Liu Lanqin Zhao Wenben Chen Jingjing Chen Ling Jin Yuxuan Wu Jiaming Hong Weiling Hu Zhenzhe Lin Carol Y.Cheung Xiang Chen Peichen Xie Zhenzhen Liu Changhai Ding Patrick Yu-Wai-Man Keming Yu Daniel Shu Wei Ting Yizhi Liu Zibin Zheng Gansen Zhao Zhihua Xia Tien Yin Wong Haotian Lin on behalf of Advanced Technologies Improve Clinical Trial(ATICT)Group State Key Laboratory of Ophthalmology Zhongshan Ophthalmic CenterSun Yat-sen UniversityGuangdong Provincial Key Laboratory of Ophthalmology and Visual ScienceGuangdong Provincial Clinical Research Center for Ocular DiseasesGuangzhou 510000China School of Biomedical Engineering Sun Yat-sen UniversityGuangzhou 510000China School of Computer Science Guangdong Polytechnic Normal UniversityGuangzhou 510000China Singapore Eye Research Institute Singapore National Eye CenterSingapore999002Singapore School of Medical Information Engineering Guangzhou University of Chinese MedicineGuangzhou 510000China Department of Ophthalmology and Visual Sciences The Chinese University of Hong KongHong Kong 999077China Zhongshan School of Medicine Sun Yat-sen UniversityGuangzhou 510000China Clinical Research Center Zhujiang HospitalSouthern Medical UniversityGuangzhou 510000China Cambridge Center for Brain Repair and MRC Mitochondrial Biology Unit Department of Clinical NeurosciencesUniversity of CambridgeCambridgeCB20XYUnited Kingdom UCL Institute of Ophthalmology University College LondonLondonWC1E 6BTUnited Kingdom School of Data and Computer Science Sun Yat-sen UniversityGuangzhou 510000China School of Computer Science South China Normal UniversityGuangzhou 510000China College of Cyber Security Jinan UniversityGuangzhou 510000China Duke-NUS Medical School Singapore999002Singapore Tsinghua Medicine Tsinghua UniversityBeijing 100010China Hainan Eye Hospital and Key Laboratory of Ophthalmology Zhongshan Ophthalmic CenterSun Yat-sen UniversityHaikou 570100China Centre for Precision Medicine and Department of Genetics and Biomedical Informatics Zhongshan School of MedicineSun Yat-sen UniversityGuangzhou 510000China 不详

Randomized controlled trials(RCTs)provide optimal evidence of the effectiveness and safety of a new drug,a new medical device,or a new therapeutic strategy with the necessary scientific design[1..Traditional electronic data collection(EDC)systems for clinical trials primarily focus on data entry,validation,and compliance ***,their reliance on centralized architectures introduces vulnerabilities in data security and integrity。

关键词： Artificial Intelligence Multicenter Randomized Controlled Trials data Security scientific design traditional Blockchain Technology clinical trials randomized controlled trials rcts provide centralized architectures

来源：评论

学校读者我要写书评

暂无评论

Few-shot 3D Point Cloud Segmentation via Relation Consistency-guided Heterogeneous Prototypes

引用

IEEE Transactions on Multimedia 2025年

作者： Wei, Lili Lang, Congyan Xu, Zheming Liang, Liqian Liu, Jun Ministry of Education Key Laboratory of Big Data & Artificial Intelligence in Transportation China Beijing Jiaotong University School of Computer Science & Technology Beijing100044 China Lancaster University LA1 4YW Lancaster United Kingdom

Few-shot 3D point cloud semantic segmentation is a challenging task due to the lack of labeled point clouds (support set). To segment unlabeled query point clouds, existing prototype-based methods learn 3D prototypes from point features of the support set and then measure their distances to the query points. However, such homogeneous 3D prototypes are often of low quality because they overlook the valuable heterogeneous information buried in the support set, such as semantic labels and projected 2D depth maps. To address this issue, in this paper, we propose a novel Relation Consistency-guided Heterogeneous Prototype learning framework (RCHP), which improves prototype quality by integrating heterogeneous information using large multi-modal models (e.g. CLIP). RCHP achieves this through two core components: Heterogeneous Prototype Generation module which collaborates with 3D networks and CLIP to generate heterogeneous prototypes, and Heterogeneous Prototype Fusion module which effectively fuses heterogeneous prototypes to obtain high-quality prototypes. Furthermore, to bridge the gap between heterogeneous prototypes, we introduce a Heterogeneous Relation Consistency loss, which transfers more reliable inter-class relations (i.e., inter-prototype relations) from refined prototypes to heterogeneous ones. Extensive experiments conducted on five point cloud segmentation datasets, including four indoor datasets (S3DIS, ScanNet, SceneNN, NYU Depth V2) and one outdoor dataset (Semantic3D), demonstrate the superiority and generalization capability of our method, outperforming state-of-the-art approaches across all datasets. The code will be released as soon as the paper is accepted. © 1.99-201. IEEE.

关键词： Semantic Segmentation

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：