检索结果-内蒙古大学图书馆

Open and Closed Source Models for LLM-Generated Metaheuristics Solving engineering Optimization Problem 28th

Open and Closed Source Models for LLM-Generated Metaheuris...

28th European Conference on Applications of Evolutionary Computation, EvoApplications 2025, held as part of EvoStar 2025

作者： Senkerik, Roman Viktorin, Adam Kadavy, Tomas Kovac, Jozef Janku, Peter Pekar, Libor Guzowski, Hubert Smolka, Maciej Byrski, Aleksander Pluhacek, Michal A.I.Lab Faculty of Applied Informatics Tomas Bata University Zlin Czech Republic Department of Automation and Control Engineering Faculty of Applied Informatics Tomas Bata University Zlin Czech Republic Faculty of Computer Science AGH University of Krakow Krakow Poland Center of Excellence in Artificial Intelligence AGH University of Krakow Krakow Poland

ISBN: (纸本)9783031900648

This paper explores the applicability of generative AI (genAI), specifically Large Language Models (LLMs), for the automatic generation and configuration of metaheuristic algorithms to address a real-world engineering problem: the optimal parameter estimation of time-delay systems in interconnected heating-cooling loops. The study introduces a pioneering workflow and iterative architecture with feedback within the emerging field of genAI-driven optimization for real optimization problems, eliminating the need for manually crafted or modified algorithms. This automated system empowers domain experts in engineering to solve complex optimization problems with minimal knowledge of optimization algorithms, lowering the barrier to entry for sophisticated algorithm use. We demonstrate how LLMs can generate effective optimizers under conditions like connstrained optimization problems where the solution lies near the boundaries of the search space. Four state-of-the-art LLMs (closed and open-sourced) have been selected for experiments. These are GPT-4o, GPT-4o mini, Claude Sonnet 3.5 and Llama 3.1. All studied LLMs generated metaheuristics that outperformed the initialization baseline optimization method (Random Search and CMA-ES). Notably, the Claude Sonnet 3.5 model generated a metaheuristic with the best mean results, almost matching the performance of the tuned state-of-the-art DISH algorithm, as an example of adaptive Differential Evolution. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Time of arrival

来源：评论

学校读者我要写书评

暂无评论

Quantized Event-Based Sampled-Data Nonlinear Control for PEM Fuel Cell Air Supply

Quantized Event-Based Sampled-Data Nonlinear Control for PEM...

引用

IEEE Conference on Decision and Control

作者： P. Salucci M. Di Ferdinando M.D. Di Benedetto A. Balluchi S. Di Gennaro P. Pepe Department of Information Engineering Computer Science and Mathematics University of L’Aquila Via Vetoio Loc. Coppito L’Aquila Italy Center of Excellence DEWS Via Vetoio Loc. Coppito L’Aquila Italy Pure Power Control S.r.l. Via Carbonia 8 Cascina Pisa Italy

ISBN: (数字)9798350316339

ISBN: (纸本)9798350316346

The problem of oxygen starvation avoidance in air-feed proton exchange membrane fuel cells is widely known and studied in the literature because it crucially affects the performances of the overall system. To address this problem, many nonlinear control techniques have been provided which, however, do not take into account the effects on the performances induced by the digital hardware commonly used for the practical implementation of control strategies. In this paper, a methodology for the design of quantized sampled-data event-based stabilizers is proposed for a class of time-varying non-linear systems and applied to the problem of oxygen starvation and maximum net power achievement in Proton Exchange Membrane Fuel Cells (PEMFCs). In particular, by exploiting a Lyapunov-based approach and the stabilization in the sample-and-hold sense theory, it is shown that there exist a suitably fast sampling and an accurate quantization of the input/output channels such that the digital event-triggered implementation of a proposed continuous-time stabilizer ensures the semi-global practical stability property of the related closed-loop system. In the theory developed here, time-varying sampling periods and non-uniform quantization of the input/output channels are allowed. Simulations confirm the effectiveness of the theoretical results.

关键词： Protons Quantization (signal) Accuracy Event detection Design methodology Fuel cells Stability analysis Closed loop systems Time-varying systems Numerical stability

来源：评论

学校读者我要写书评

暂无评论

Distributed formation control of networked mechanical systems

arXiv

引用

arXiv 2022年

作者： Javanmardi, Najmeh Borja, P. Yazdanpanah, M.J. Scherpen, J.M.A. Control and Intelligent Processing Center of Excellence School of Electrical and Computer Engineering University of Tehran Tehran Iran Department of Cognitive Robotics Delft University of Technology Delft Netherlands Jan C. Wilems Center for Systems and Control ENTEG Faculty of Science and Engineering University of Groningen Groningen Netherlands

This paper investigates a distributed formation tracking control law for large-scale networks of mechanical systems. In particular, the formation network is represented by a directed communication graph with leaders and followers, where each agent is described as a port-Hamiltonian system with a constant mass matrix. Moreover, we adopt a distributed parameter approach to prove the scalable asymptotic stability of the network formation, i.e., the scalability with respect to the network size and the specific formation preservation. A simulation case illustrates the effectiveness of the proposed control approach. © 2022, CC BY.

关键词： Networked control systems

来源：评论

学校读者我要写书评

暂无评论

Activity and Resolution Aware Privacy Protection For Smart Water Meter Databases

SSRN

引用

SSRN 2023年

作者： Cardell-Oliver, Rachel Cominola, Andrea Hong, Jin Department of Computer Science and Software Engineering The University of Western Australia 25 Stirling Highway PerthWA6009 Australia Technische Universität Berlin and Einstein Center Digital Future Straße des 17. Juni 135 Berlin Berlin10623 Germany

Identifying water end-uses from household meter readings yields valuable commercial and environmental insights for both customers and water providers. But smart water meter databases may expose sensitive information about the activities of metered households, thus raising privacy concerns that limit the possibility of making smart meter data available for research and planning. This paper considers the case where a water provider wishes to publish a database of household water meter traces to be used by water analysts, who are often external entities. This scenario presents risks to privacy should an adversary gain access to this database, with the threat of uniquely identifying a household of interest and exposing their water use activities. To mitigate such risks, this paper proposes a process for activity-aware privacy protection and evaluates its effectiveness using real-world and synthetic databases. Our experimental analysis shows that water meter privacy-protection is strongly dependent on the type of activity, temporal resolution and population size. In the case of a high-resolution database, we found that a large base population, small published sample and 30 second resolution provided optimal trade-offs between privacy and information value. For a low-resolution database with a population of over 3500 households, 1 hour resolution provided strong information value and customisable privacy guarantees depending on the published sample size. © 2023, The Authors. All rights reserved.

关键词： Database systems

来源：评论

学校读者我要写书评

暂无评论

Report-Guided Cross-Modal Representation Learning for Predicting EGFR Mutations by Whole Slide Image

Report-Guided Cross-Modal Representation Learning for Predic...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Qi Qiao Jun Shi Zhiguo Jiang Wei Wang Haibo Wu Yushan Zheng School of Computer Science and Information Engineering Hefei University of Technology Hefei China School of Software Hefei University of Technology Hefei China Image Processing Center School of Astronautics Beihang University Beijing China Department of Pathology the First Affiliated Hospital of USTC Division of Life Sciences and Medicine University of Science and Technology of China Hefei China Intelligent Pathology Institute Division of Life Sciences and Medicine University of Science and Technology of China Hefei China School of Engineering Medicine Beijing Advanced Innovation Center for Biomedical Engineering Beihang University Beijing China

ISBN: (数字)9798350386226

ISBN: (纸本)9798350386233

Traditional PCR/NGS-based multigene panel testing is time-consuming and costly. Predicting EGFR mutations directly from H&E stained whole slide images (WSIs) can alleviate these limitations. Furthermore, histopathological reports contain valuable textual information that correlates with tissue areas in WSIs. However, recent research mainly analyses EGFR mutation status only from a single modality, ignoring rich information contained in reports. In this paper, we propose a report-guided cross-modal representation learning method for predicting EGFR mutations by WSIs. Specifically, we reconstruct report-level embeddings through exploring intrinsic relationships between diagnostic words in histopathological reports and tissue areas in WSIs. Finally, reconstructed histopathological report embedding and aggregated WSI embedding are fused for final prediction. More importantly, molecular testing report is also introduced as prior supervision information at the training stage to guarantee semantic consistency of fused feature and molecular report embedding. We evaluate our method on the TCGA-EGFR public benchmark dataset and an in-house clinical dataset (USTC-EGFR). Experimental results demonstrate that our method outperforms existing approaches in EGFR mutation prediction, highlighting the benefits of cross-modal learning in enhancing feature representational ability. The code is available at https://***/HFUT-miaLab/RCRL.

关键词： Representation learning Training Codes Supervised learning Semantics Medical treatment Benchmark testing Bioinformatics Image reconstruction Biomedical imaging

来源：评论

学校读者我要写书评

暂无评论

CTC Alignments Improve Autoregressive Translation

arXiv

引用

arXiv 2022年

作者： Yan, Brian Dalmia, Siddharth Higuchi, Yosuke Neubig, Graham Metze, Florian Black, Alan W. Watanabe, Shinji Language Technologies Institute Carnegie Mellon University United States Department of Communications and Computer Engineering Waseda University Japan Human Language Technology Center of Excellence Johns Hopkins University United States

Connectionist Temporal Classification (CTC) is a widely used approach for automatic speech recognition (ASR) that performs conditionally independent monotonic alignment. However for translation, CTC exhibits clear limitations due to the contextual and non-monotonic nature of the task and thus lags behind attentional decoder approaches in terms of translation quality. In this work, we argue that CTC does in fact make sense for translation if applied in a joint CTC/attention framework wherein CTC’s core properties can counteract several key weaknesses of pure-attention models during training and decoding. To validate this conjecture, we modify the Hybrid CTC/Attention model originally proposed for ASR to support text-to-text translation (MT) and speech-to-text translation (ST). Our proposed joint CTC/attention models outperform pure-attention baselines across six benchmark translation tasks. Copyright © 2022, The Authors. All rights reserved.

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

Learning Signed Hyper Surfaces for Oriented Point Cloud Normal Estimation

arXiv

引用

arXiv 2023年

作者： Li, Qing Feng, Huifang Shi, Kanle Gao, Yue Fang, Yi Liu, Yu-Shen Han, Zhizhong School of Software Tsinghua University Beijing China School of Computing and Artificial Intelligence Southwest Jiaotong University Chengdu China School of Computer and Software Engineering Xihua University Chengdu China Kuaishou Technology Beijing China Center for Artificial Intelligence and Robotics New York University Abu Dhabi Abu Dhabi United Arab Emirates Department of Computer Science Wayne State University Detroit United States

We propose a novel method called SHS-Net for point cloud normal estimation by learning signed hyper surfaces, which can accurately predict normals with global consistent orientation from various point clouds. Almost all existing methods estimate oriented normals through a two-stage pipeline, i.e., unoriented normal estimation and normal orientation, and each step is implemented by a separate algorithm. However, previous methods are sensitive to parameter settings, resulting in poor results from point clouds with noise, density variations and complex geometries. In this work, we introduce signed hyper surfaces (SHS), which are parameterized by multi-layer perceptron (MLP) layers, to learn to estimate oriented normals from point clouds in an end-to-end manner. The signed hyper surfaces are implicitly learned in a high-dimensional feature space where the local and global information is aggregated. Specifically, we introduce a patch encoding module and a shape encoding module to encode a 3D point cloud into a local latent code and a global latent code, respectively. Then, an attention-weighted normal prediction module is proposed as a decoder, which takes the local and global latent codes as input to predict oriented normals. Experimental results show that our algorithm outperforms the state-of-the-art methods in both unoriented and oriented normal estimation. © 2023, CC BY-NC-SA.

关键词： Surface reconstruction

来源：评论

学校读者我要写书评

暂无评论

Source Apportionment and Toxicity of Atmospheric Polycyclic Aromatic Hydrocarbons in a Megacity

SSRN

引用

SSRN 2024年

作者： Hsieh, Ming-Tsuen Wang, Chun-Hua Chang, Jin-Yu Chung, Wen-Yu Huang, Yu-Chen Lee, Chon-Lin Department of Marine Environment and Engineering National Sun Yat-sen University Kaohsiung Taiwan College of Medicine Chang Gung Memorial University Taiwan Department of Thoracic Medicine Chang Gung Memorial Hospital Taipei Taiwan Computer Science and Information Engineering National Kaohsiung University of Science and Technology Kaohsiung Taiwan Department of Public Health Kaohsiung Medical University Kaohsiung Taiwan National Sun Yat-sen University Kaohsiung Taiwan Center of Excellence for the Oceans National Taiwan Ocean University Keelung20224 Taiwan

Megacity residents may suffer adverse health effects, because polycyclic aromatic hydrocarbons associated with particulate matter (PM2.5-PAHs) are carcinogenic and the abundance of emission sources. In this study, we investigated the spatiotemporal distribution of PM2.5-PAHs in Taipei areas and estimated the potential sources using Principal Component Analysis-Absolute Principal Component Score (PCA-APCS) to evaluate the lifetime excess cancer risk (ECR). The mean concentration of PM2.5-PAHs was 1.11 ± 0.79 ng m-3, and the corresponding benzo[a]pyrene equivalent (BaPeq) was 0.1 ng m-3. The ECR was estimated to be 8.7 × 10-6, which was higher than the U.S. Environmental Protection Agency acceptable level, indicating a potential risk in Taipei. Among the potential sources, gasoline and diesel vehicle exhaust (traffic emissions) was the major contributor of PAHs (48%), followed by fossil fuel combustion (34%), biomass combustion (13%), and evaporated/unburned oil source (5%). In terms of BaPeq contribution, traffic emissions were the highest at 59%, and the highest ECR contribution from traffic emissions in densely populated urban centers was 3.09 x 10-5. To achieve the Sustainable Development Goal (SDG) of good health and well-being, priority should be given to controlling emissions from gasoline and diesel vehicles. This study contributes to a better understanding of the analysis of potential sources and provides information for policy decisions. © 2024, The Authors. All rights reserved.

关键词： Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

Event detection and evolution in multi-lingual social streams

引用

Frontiers of computer Science 2020年第5期14卷 213-227页

作者： Yaopeng Liu Hao Peng Jianxin Li Yangqiu Song Xiong Li Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang UniversityBeijing100083China State Key Laboratory of Software Development Environment Beihang UniversityBeijing100083China Department of Computer Science and Engineering HKUSTHong Kong99907China National Computer Network Emergency Response Technical Team/Coordination Center of China Beijing100029China

Real-life events are emerging and evolving in social and news *** methods have succeeded in capturing designed features of monolingual events,but lack of interpretability and multi-lingual *** this end,we propose a multi-lingual event mining model,namely MLEM,to automatically detect events and generate evolution graph in multilingual hybrid-length text streams including English,Chinese,French,German,Russian and ***,we merge the same entities and similar phrases and present multiple similarity measures by incremental word2vec *** propose an 8-tuple to describe event for correlation analysis and evolution graph *** evaluate the MLEM model using a massive human-generated dataset containing real world *** results show that our new model MLEM outperforms the baseline method both in efficiency and effectiveness.

关键词： event detection event evolution stream processing multi-lingual anomaly detection

来源：评论

学校读者我要写书评

暂无评论

The Metaverse: Survey, Trends, Novel Pipeline Ecosystem & Future Directions

arXiv

引用

arXiv 2023年

作者： Sami, H. Hammoud, A. Arafeh, M. Wazzeh, M. Arisdakessian, S. Chahoud, M. Wehbi, O. Ajaj, M. Mourad, A. Otrok, H. Abdel Wahab, O. Mizouni, R. Bentahar, J. Talhi, C. Dziong, Z. Damiani, E. Guizani, M. Concordia Institute for Information Systems Engineering Concordia University MontréalQC Canada Department of Electrical Engineering École de Technologie Supérieure Montréal Canada Department of Software and IT engineering École de Technologie Supérieure Montréal Canada Department of Computer and Software Engineering Polytechnique Montréal Montreal Canada Cyber Security Systems and Applied AI Research Center Department of CSM Lebanese American University Beirut Lebanon Division of Science New York University Abu Dhabi United Arab Emirates Department of EECS Khalifa University Abu Dhabi United Arab Emirates Department of ML Mohamed Bin Zayed University of Artificial Intelligence Abu Dhabi United Arab Emirates

The Metaverse offers a second world beyond reality, where boundaries are non-existent, and possibilities are endless through engagement and immersive experiences using the virtual reality (VR) technology. Many disciplines can benefit from the advancement of the Metaverse when accurately developed, including the fields of technology, gaming, education, art & culture, socialization, commerce, and businesses. Nevertheless, developing the Metaverse environment to its full potential is an ambiguous task that needs proper guidance and directions. Existing surveys on the Metaverse focus only on a specific aspect and discipline of the Metaverse and lack a holistic view of the entire process. Moreover, most surveys refrain from providing detailed guidance about the development process of the metaverse, including its impact on technologies, businesses, existing challenges, and potential research directions due to their lack of a macro and micro perception of such a topic. To this end, a more holistic, multi-disciplinary, in-depth, and academic and industry-oriented review is required to provide a thorough study of the Metaverse development pipeline and fill the gap in existing Metaverse surveys. To address these issues, we present in this survey a novel multi-layered pipeline ecosystem composed of (1) the Metaverse computing, networking, communications and hardware infrastructure, (2) environment digitization, and (3) user interactions. For every layer, we discuss the components that detail the steps of its development. Also, for each of these components, we examine the impact of a set of enabling technologies and empowering domains (e.g., Artificial Intelligence, Security & Privacy, Blockchain, Business, Ethics, and Social) on its advancement. In addition, we explain the importance of these technologies to support decentralization, interoperability, user experiences, interactions, and monetization. Our presented study highlights the existing challenges for each component, fo

关键词： Edge computing

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：