检索结果-内蒙古大学图书馆

Automated Clustering and Knowledge Acquisition Support for Beginners

学校读者我要写书评

暂无评论

Procedia computer Science 2020年 176卷 1596-1605页

作者： Ryota Kamoshida Fuyuki Ishikawa Research & Development Group Hitachi Ltd. Tokyo Japan Department of Informatics The University of Electro-Communications Tokyo Japan Information Systems Architecture Science Research Division National Institute of Informatics Tokyo Japan

Although automated machine learning (AutoML) is receiving attention in the field of data science, most AutoML open source software focuses on supervised learning tasks, and little attention has been given to unsupervised learning tasks. Moreover, AutoML has a disadvantage in that it tends to deprive users of a chance to acquire knowledge about machine learning and data science because it usually works as a black box. The purpose of this study is to help inexperienced data scientists and machine learning engineers conduct clustering data analysis, which is an unsupervised learning task, while simultaneously enabling them to acquire knowledge about clustering data analysis by extending our existing AutoML software, the machine learning support system (MALSS). The MALSS helps with clustering data analysis by automatically determining the optimal number of clusters, which is one of the main purposes of clustering data analysis. Furthermore, the MALSS helps users to acquire knowledge about clustering data analysis by generating a report after automated clustering data analysis is conducted. We validated the effectiveness of our approach by using open datasets and by running an experiment on a crowdsourcing platform.

关键词： Automated machine learning Clustering.xmData analysis Data analysis Software engineering education

Self-Adjusting Network Slicing for Dynamic Heterogeneous Task Offloading in UAV-Enabled Mobile Edge Computing

学校读者我要写书评

暂无评论

IEEE Transactions on Cognitive Communications and Networking 2025年

作者： Li, Xulong Mao, Wencan Xu, Xinyi Liu, Yaxi Zhang, Huifeng Huangfu, Wei Long, Keping University of Science and Technology Beijing School of Computer and Communication Engineering Beijing100083 China National Institute of Informatics Information Systems Architecture Science Research Division Tokyo101-8430 Japan Zhejiang Lab Hangzhou311500 China

Unmanned aerial vehicle (UAV)-enabled mobile edge computing (MEC) has received wide attention for its ability to significantly reduce latency with flexible mobile aerial nodes. However, the existing works merely consider a fixed periodic network slicing and usually neglect the characterization of computing tasks in practical applications. Motivated by this, we envision a novel scenario where the dynamics and heterogeneity of users and tasks are considered in UAV-enabled MEC networks. We propose a novel self-adjusting two-timescale network slicing scheme based on the internal mechanism in deep reinforcement learning (DRL) to automatically determine whether and when network slicing needs to be reconstructed. Such a novel scheme balances reconstruction cost and system performance compared with traditional fixed schemes. We build an optimization to minimize total system cost for joint UAV trajectory planning and resource allocation at both network and user slice levels. To tackle this problem, we design a novel self-adjusting two-timescale proximal policy optimization (PPO) algorithm that utilizes the property of the critic network, referred to as SaTPPO. Experiment results manifest the effectiveness of the proposed SaTPPO, and it has a lower system cost than the traditional fixed schemes. Moreover, the proposed SaTPPO outperforms the state-of-the-art baselines concerning effectiveness and efficiency. © 2015 IEEE.

关键词： Micro air vehicle (MAV)

Indoor 3D Visible Light Positioning Analysis with Channel Estimation Errors

学校读者我要写书评

暂无评论

Indoor 3D Visible Light Positioning Analysis with Channel Es...

International Conference on systems, Signals and Image Processing, IWSSIP

作者： Dimitrios Bozanis Nikos G. Evgenidis Vasilis K. Papanikolaou Pavlos S. Bouzinis Sotiris A. Tegos Alexis A. Dowhuszko Panagiotis D. Diamantoulakis George K. Karagiannidis Department of Electrical and Computer Engineering Wireless Communications and Information Processing Group (WCIP) Aristotle University of Thessaloniki Thessaloniki Greece Institute for Digital Communications (IDC) Friedrich-Alexander Universitat Erlangen-Nurnberg (FAU) Germany Department of Applied Informatics University of Macedonia Thessaloniki Greece Department of Communications and Networking Aalto University Espoo Finland Cyber Security Systems and Applied AI Research Center Lebanese American University (LAU) Lebanon

Since radio-frequency signals are affected signifi-cantly by multipath fading, the localization accuracy they offer cannot meet the sixth generations (6G) demanding specifications. On the other hand, visible light positioning (VLP) has emerged as a low cost alternative that takes into account the highly deterministic channel characteristics of visible light communications to provide cm-level accuracy provided that the investigated spaces are adequately covered by LEDs. However, imperfect channel state information and modeling can lead to positioning errors. In this paper, localization accuracy is quantified in terms of channel estimation errors via low complexity lateration algorithm. The channel estimation errors can be caused by a variety of issues and the provided analysis is general so that it can be easily applied to a plethora of applications. Finally, Monte Carlo simulations validate the proposed method and offer valuable insights for the design and performance bounds of VLP systems.

关键词：

DoS-Aware Quantized Control of Nonlinear systems via Linearization ⁎

学校读者我要写书评

暂无评论

IFAC-PapersOnLine 2020年第2期53卷 3054-3059页

作者： Rui Kato Ahmet Cetinkaya Hideaki Ishii Department of Computer Science Tokyo Institute of Technology Yokohama 226-8502 Japan Information Systems Architecture Science Research Division National Institute of Informatics Tokyo 101-8430 Japan

This paper deals with a quantized feedback stabilization problem of nonlinear networked control systems via linearization. In particular, we study circumstances where the communication channel is interrupted by Denial-of-Service (DoS) attacks and its data rate is limited. We employ a deterministic DoS attack model which constraints the amount of attacks only by their frequency and duration, allowing us to capture a large class of potential attacks. To achieve asymptotic stabilization, we propose a resilient dynamic quantizer in the sense that it does not saturate in the presence of packet losses caused by DoS attacks. A sufficient condition for stability is derived by restricting the average frequency and duration of attacks. Since our result only guarantees local stability, we explicitly investigate an estimate of the region of attraction, which may be reduced by attacks. A simulation example is presented for demonstration of our results.

关键词： DoS attacks quantized control nonlinear systems stability analysis linearization

Inverse learning of black-box aggregator for robust Nash equilibrium

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Chen, Guanpu Xu, Gehui He, Fengxiang Tao, Dacheng Parisini, Thomas Johansson, Karl Henrik Division of Decision and Control Systems School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Stockholm100 44 Sweden Digital Futures Stockholm100 44 Sweden Artificial Intelligence and its Applications Institute School of Informatics University of Edinburgh EdinburghEH8 9AB United Kingdom College of Computing & Data Science Nanyang Technological University Singapore639798 Singapore Department of Electrical and Electronic Engineering Imperial College London LondonSW7 2AZ United Kingdom Department of Engineering and Architecture University of Trieste Trieste34127 Italy

In this note, we investigate the robustness of Nash equilibria (NE) in multi-player aggregative games with coupling constraints. There are many algorithms for computing an NE of an aggregative game given a known aggregator. When the coupling parameters are affected by uncertainty, robust NE need to be computed. We consider a scenario where players' weight in the aggregator is unknown, making the aggregator kind of "a black box". We pursue a suitable learning approach to estimate the unknown aggregator by proposing an inverse variational inequality-based relationship. We then utilize the counterpart to reconstruct the game and obtain first-order conditions for robust NE in the worst case. Furthermore, we characterize the generalization property of the learning methodology via an upper bound on the violation probability. Simulation experiments show the effectiveness of the proposed inverse learning approach. Copyright © 2024, The Authors. All rights reserved.

关键词： Inverse problems

Transformative Effects of ChatGPT on Modern Education: Emerging Era of AI Chatbots

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Gill, Sukhpal Singh Xu, Minxian Patros, Panos Wu, Huaming Kaur, Rupinder Kaur, Kamalpreet Fuller, Stephanie Singh, Manmeet Arora, Priyansh Parlikad, Ajith Kumar Stankovski, Vlado Abraham, Ajith Ghosh, Soumya K. Lutfiyya, Hanan Kanhere, Salil S. Bahsoon, Rami Rana, Omer Dustdar, Schahram Sakellariou, Rizos Uhlig, Steve Buyya, Rajkumar School of Electronic Engineering and Computer Science Queen Mary University of London London United Kingdom Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen China Raygun Performance Monitoring Wellington New Zealand Center for Applied Mathematics Tianjin University Tianjin China Department of Science Kings Education London United Kingdom Cymax Group Technologies BC Canada QM Academy Queen Mary University of London London United Kingdom Jackson School of Geosciences University of Texas at Austin AustinTX United States Centre for Climate Change Research Indian Institute of Tropical Meteorology Pune India Microsoft Hyderabad India Institute for Manufacturing Department of Engineering University of Cambridge Cambridge United Kingdom Faculty of Computer and Information Science University of Ljubljana Ljubljana Slovenia Machine Intelligence Research Labs AuburnWA United States Department of Computer Science and Engineering Indian Institute of Technology Kharagpur India Department of Computer Science University of Western Ontario London Canada Sydney Australia School of Computer Science University of Birmingham United Kingdom School of Computer Science and Informatics Cardiff University Cardiff United Kingdom Distributed Systems Group Vienna University of Technology Vienna Austria Department of Computer Science University of Manchester Oxford Road Manchester United Kingdom Laboratory School of Computing and Information Systems The University of Melbourne Australia

ChatGPT, an AI-based chatbot, was released to provide coherent and useful replies based on analysis of large volumes of data. In this article, leading scientists, researchers and engineers discuss the transformative effects of ChatGPT on modern education. This research seeks to improve our knowledge of ChatGPT capabilities and its use in the education sector, identifying potential concerns and challenges. Our preliminary evaluation concludes that ChatGPT performed differently in each subject area including finance, coding and maths. While ChatGPT has the ability to help educators by creating instructional content, offering suggestions and acting as an online educator to learners by answering questions and promoting group work, there are clear drawbacks in its use, such as the possibility of producing inaccurate or false data and circumventing duplicate content (plagiarism) detectors where originality is essential. The often reported "hallucinations" within Generative AI in general, and also relevant for ChatGPT, can render its use of limited benefit where accuracy is essential. What ChatGPT lacks is a stochastic measure to help provide sincere and sensitive communication with its users. Academic regulations and evaluation practices used in educational institutions need to be updated, should ChatGPT be used as a tool in education. To address the transformative effects of ChatGPT on the learning environment, educating teachers and students alike about its capabilities and limitations will be crucial. © 2023, CC0.

关键词： Machine learning

Recording provenance of workflow runs with RO-Crate

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Leo, Simone Crusoe, Michael R. Rodríguez-Navas, Laura Sirvent, Raül Kanitz, Alexander De Geest, Paul Wittner, Rudolf Pireddu, Luca Garijo, Daniel Fernández, José M. Colonnelli, Iacopo Gallo, Matej Ohta, Tazro Suetake, Hirotaka Capella-Gutierrez, Salvador de Wit, Renske Kinoshita, Bruno P. Soiland-Reyes, Stian CA Pula Italy Vrije Universiteit Amsterdam Amsterdam Netherlands DTL Projects Netherlands Forschungszentrum Jülich Germany Barcelona Supercomputing Center Barcelona Spain Biozentrum University of Basel Basel Switzerland Swiss Institute of Bioinformatics Lausanne Switzerland VIB Data Core Gent Belgium Faculty of Informatics Masaryk University Brno Czech Republic Institute of Computer Science Masaryk University Brno Czech Republic BBMRI-ERIC Graz Austria Ontology Engineering Group Universidad Politécnica de Madrid Madrid Spain Computer Science Department Università degli Studi di Torino Torino Italy Database Center for Life Science Joint Support-Center for Data Science Research Research Organization of Information and Systems Shizuoka Japan Institute for Advanced Academic Research Chiba University Chiba Japan Sator Incorporated Tokyo Japan Department of Computer Science The University of Manchester Manchester United Kingdom Informatics Institute University of Amsterdam Amsterdam Netherlands

Recording the provenance of scientific computation results is key to the support of traceability, reproducibility and quality assessment of data products. Several data models have been explored to address this need, providing representations of workflow plans and their executions as well as means of packaging the resulting information for archiving and sharing. However, existing approaches tend to lack interoperable adoption across workflow management systems. In this work we present Workflow Run RO-Crate, an extension of RO-Crate (Research Object Crate) and *** to capture the provenance of the execution of computational workflows at different levels of granularity and bundle together all their associated objects (inputs, outputs, code, etc.). The model is supported by a diverse, open community that runs regular meetings, discussing development, maintenance and adoption aspects. Workflow Run RO-Crate is already implemented by several workflow management systems, allowing interoperable comparisons between workflow runs from heterogeneous systems. We describe the model, its alignment to standards such as W3C PROV, and its implementation in six workflow systems. Finally, we illustrate the application of Workflow Run RO-Crate in two use cases of machine learning in the digital image analysis domain. © 2023, CC BY.

关键词： Workflow management

PhenoProfiler: Advancing Phenotypic Learning for Image-based Drug Discovery

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Li, Bo Zhang, Bob Zhang, Chengyang Zhou, Minghao Huang, Weiliang Wang, Shihang Wang, Qing Li, Mengran Zhang, Yong Song, Qianqian PAMI Research Group Department of Computer and Information Science University of Macau Taipa China Beijing Key Laboratory of Multimedia and Intelligent Software Technology Beijing Institute of Artificial Intelligence Beijing University of Technology Beijing China Department of Health Outcomes and Biomedical Informatics College of Medicine University of Florida Florida United States Faculty of Applied Sciences Macao Polytechnic University Taipa China School of Intelligent Systems Engineering Sun Yat-sen University Guangdong China Department of Cancer Biology Wake Forest School of Medicine Winston SalemNC United States

In the field of image-based drug discovery, capturing the phenotypic response of cells to various drug treatments and perturbations is a crucial step. This process involves transforming high-throughput cellular images into quantitative representations for downstream analysis. However, existing methods require computationally extensive and complex multi-step procedures, which can introduce inefficiencies, limit generalizability, and increase potential errors. To address these challenges, we present PhenoProfiler, an innovative model designed to efficiently and effectively extract morphological representations, enabling the elucidation of phenotypic changes induced by treatments. PhenoProfiler is designed as an end-to-end tool that processes whole-slide multi-channel images directly into low-dimensional quantitative representations, eliminating the extensive computational steps required by existing methods. It also includes a multi-objective learning module to enhance robustness, accuracy, and generalization in morphological representation learning. PhenoProfiler is rigorously evaluated on large-scale publicly available datasets, including over 230,000 whole-slide multi-channel images in end-to-end scenarios and more than 8.42 million single-cell images in non-end-to-end settings. Across these benchmarks, PhenoProfiler consistently outperforms state-of-the-art methods by up to 20%, demonstrating substantial improvements in both accuracy and robustness. Furthermore, PhenoProfiler uses a tailored phenotype correction strategy to emphasize relative phenotypic changes under treatments, facilitating the detection of biologically meaningful signals. UMAP visualizations of treatment profiles demonstrate PhenoProfiler’s ability to effectively cluster treatments with similar biological annotations, thereby enhancing interpretability. These findings establish PhenoProfiler as a scalable, generalizable, and robust tool for phenotypic learning, offering transformative advancement

关键词： Benchmarking

A Consensus Privacy Metrics Framework for Synthetic Data

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Pilgram, Lisa Dankar, Fida K. Drechsler, Jörg Elliot, Mark Domingo-Ferrer, Josep Francis, Paul Kantarcioglu, Murat Kong, Linglong Malin, Bradley Muralidhar, Krishnamurty Myles, Puja Prasser, Fabian Raisaro, Jean Louis Yan, Chao El Emam, Khaled School of Epidemiology and Public Health University of Ottawa ON Canada CHEO Research Institute ON Canada Department of Nephrology and Medical Intensive Care Charité – Universitätsmedizin Berlin Berlin Germany Department for Statistical Methods Institute for Employment Research Nuernberg Germany Institute for Statistics Ludwig-Maximilians-Universität Munich Germany Joint Program in Survey Methodology University of Maryland United States The Cathie Marsh Institute Research School of Social Sciences University of Manchester Manchester United Kingdom Department of Computer Engineering and Mathematics Universitat Rovira i Virgili Catalonia Tarragona Spain Max Planck Institute for Software Systems Germany Department of Computer Science Virginia Tech United States Department of Mathematical and Statistical Sciences University of Alberta Alberta Canada Department of Biomedical Informatics Vanderbilt University Medical Center NashvilleTN United States Department of Biostatistics Vanderbilt University Medical Center NashvilleTN United States Department of Computer Science Vanderbilt University NashvilleTN United States Department of Marketing and Supply Chain Management University of Oklahoma Oklahoma United States Medicines and Healthcare products Regulatory Agency London United Kingdom Berlin Institute of Health at Charité Universitätsmedizin Berlin Medical Informatics Group Berlin Germany Biomedical Data Science Center University Hospital Lausanne Lausanne Switzerland

Synthetic data generation is one approach for sharing individual-level data. However, to meet legislative requirements, it is necessary to demonstrate that the individuals’ privacy is adequately protected. There is no consolidated standard for measuring privacy in synthetic data. Through an expert panel and consensus process, we developed a framework for evaluating privacy in synthetic data. Our findings indicate that current similarity metrics fail to measure identity disclosure, and their use is discouraged. For differentially private synthetic data, a privacy budget other than close to zero was not considered interpretable. There was consensus on the importance of membership and attribute disclosure, both of which involve inferring personal information about an individual without necessarily revealing their identity. The resultant framework provides precise recommendations for metrics that address these types of disclosures effectively. Our findings further present specific opportunities for future research that can help with widespread adoption of synthetic data. © 2025, CC BY.

关键词： Differential privacy