检索结果-内蒙古大学图书馆

36th IEEE International Conference on Tools with Artificial Intelligence, ICTAI 2024

作者： Fang, Zhizhou Zdun, Uwe University of Vienna Research Group Software Architecture Faculty of Computer Science Austria University of Vienna Research Group Software Architecture Faculty of Computer Science Austria

ISBN: (纸本)9798331527235

This study introduces a novel two-stage method, GPAction, for detecting environment drift in reinforcement learning settings. We first train a Gaussian process predicting the reinforcement learning agents' actions and then detect environment drifts by monitoring the mean squared error between the predicted actions of a Gaussian process action predictor and actual actions. Our proposed method is evaluated against three baselines across four environments with continuous action spaces. Results demonstrate the superior performance of GPAction in detecting environment drift. In an ablation study, by analyzing the plots and AUC values of the MSEs, we show that our method GPAction can provide more distinguishable monitoring metrics than the Gaussian process state predictor. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Radial solution of the Logarithmic Laplacian system

引用

Applied mathematics(A Journal of Chinese Universities) 2024年第1期39卷 114-124页

作者： ZHANG Li-hong NIE Xiao-feng WANG Guo-tao Bashir Ahmad School of Mathematics and Computer Science Shanxi Normal UniversityLinfen 041004China Nonlinear Analysis and Applied Mathematics(NAAM)Research Group Department of MathematicsFaculty of ScienceKing Abdulaziz UniversityJeddah 21589Saudi Arabia.

The paper generalizes the direct method of moving planes to the Logarithmic Laplacian ***,some key ingredients of the method are discussed,for example,Narrow region principle and Decay at ***,the radial symmetry of th... 详细信息

关键词： the Logarithmic Laplacian system radial symmetry the direct method of moving planes

来源：评论

学校读者我要写书评

暂无评论

Online Prediction Threshold Optimization Under Semi-deferred Labelling

Online Prediction Threshold Optimization Under Semi-deferred...

引用

Workshops of the EDBT/ICDT 2024 Joint Conference, EDBT/ICDT-WS 2024

作者： Spenrath, Yorick Hassani, Marwan van Dongen, Boudewijn F. Process Analytics Group Faculty of Mathematics and Computer Science Eindhoven University of Technology Netherlands

In supermarket loyalty campaigns, shoppers collect stamps to redeem limited-time luxury products. Having an accurate prediction of which shoppers will eventually redeem is crucial to effective execution. With the ultimate goal of changing shopper behavior, it is important to ensure an adequate number of rewards and to be able to steer promising shoppers into joining the campaign and redeeming a reward. If information from previous campaigns is available, a prediction model can be built to predict the redemption probability, possibly also adapting the prediction threshold to determine predicted the label. During a running campaign, we only know a subset of the labels of the positive class (the so-far redeemers), and have no access to the labels of any example of the negative class (non-redeemers at the end of the campaign). The majority of the examples during the campaign do not have a label yet (shoppers that could still redeem but have not done so yet). This is a semi-deferred labelling setting and our goal is to improve the prediction quality using this limited information. Existing work on predicting (semi-deferred) labels either focuses on positive-unlabelled learning, which does not use existing models, or updates models after the prediction is made by assigning expected labels using unsupervised learning models. In this paper we present a framework for Online Prediction threshold optimization Under Semi-deferred labelling (OPUS). Our framework does not change the existing model, but instead adapts the prediction threshold that decides which probability is required for a positive label, based on the semi-deferred labels we already know. We apply OPUS to two real-world datasets: a supermarket with two campaigns and over 160 000 shoppers. © 2024 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Identification of Z Cam's Historical Counterpart: The Quest for an Ancient Nova

引用

Research in Astronomy and Astrophysics 2024年第12期24卷 31-42页

作者： Bo-Shun Yang Susanne M.Hoffmann University of Science and Technology of China Dept.of the History of Science and Scientific ArchaeologyHefei 230026China Friedrich Schiller University of Jena Faculty of Mathematics and Computer ScienceFUSION Group07737 JenaGermany

In recent astronomical discussions, attempts have been made to link the known dwarf nova Z Cam to historical celestial events, particularly the “guest star” phenomenon reported in China in 77 BCE. Despite other suggestions and the problems with regard to the location of the event in 77 BCE, its identification with Z Cam is used in the Variable Star Index of the AAVSO and in several research papers that aim to derive knowledge on the evolution of cataclysmic variables. Through the reconstruction of the super-constellation of the Purple Palace in the Han Dynasty, we found that Z Cam is actually located outside this enclosure, contradicting the records of the 77 BCE guest star being “within the Purple Palace.” With newly found text versions of the guest star in 77 BCE, we narrowed down the position given therein. Combining with a new analysis of accompanying divination text leads to the conclusion that this guest star was actually a comet. Finally, through meticulous examination and comparison, we conclude that the guest star of 369 CE appears the most plausible candidate for Z Cam's historical counterpart, aligning with both textual evidence and modern astronomical observations.

关键词： (stars) novae-cataclysmic variables-history and philosophy of astronomy-stars dwarf novae-stars evolution

来源：评论

学校读者我要写书评

暂无评论

MESSI: Task Mapping and Scheduling Strategy for FPGA-based Heterogeneous Real-Time Systems

引用

ACM Transactions on Design Automation of Electronic Systems 2025年第3期30卷 1-29页

作者： Ahmadi-Pour, Sallar Saha, Sangeet Mcdonald-Maier, Klaus Drechsler, Rolf Institute of Computer Science University of Bremen Faculty 3 Mathematics and Computer Science Bremen Bremen Germany Robotics and Embedded Systems Research Group University of Essex School of Computer Science and Electronic Engineering Colchester United Kingdom Cyber-Physical Systems DFKI Rheinland-Pfalz Kaiserslautern Germany

Continuous demands for improved performance within constrained resource budgets are driving a move from homogeneous to heterogeneous processing platforms for the implementation of today's Real-Time (RT) embedded systems. The applications executing on such systems are typically represented as a Precedence Task Graph (PTG), where a node represents a task or algorithm for one functionality and edges represent the complex interactions between multiple functionalities. Due to RT constraints, the task graph needs to be executed within a specified deadline. Although some existing studies have looked into solving this challenge, comprehensive studies that combine the theoretical features of RT task-graph mapping and scheduling with practical runtime architectural characteristics have mostly been ignored to date. Hence, in this article, we consider the challenge of scheduling an RT application modeled as a single PTG, with the objective of minimizing the overall execution time under Hardware (HW) resource and deadline constraints for heterogeneous Central Processing Unit (CPU) + Field Programmable Gate Array (FPGA) architectures. First, we introduce an optimal solution using Integer Linear Programming (ILP). However, this ILP-based optimal solution suffers from computational complexity and does not scale well even for moderately large problem sizes. Hence, we additionally propose heuristic algorithms for task mapping and scheduling. The efficiency of the proposed scheme, named MESSI, has been evaluated through experiments using PTG on a practical CPU+FPGA system regarding current technology restrictions. Our experiments demonstrate that performance gains of 55.6% and area usage reductions of 46.3% are possible compared to full Software (SW) and HW execution, respectively. © 2025 Copyright held by the owner/author(s). Publication rights licensed to ACM.

关键词： Integer programming

来源：评论

学校读者我要写书评

暂无评论

New exact solutions of the Mikhailov-Novikov-Wang equation via three novel techniques

引用

Journal of Ocean Engineering and science 2023年第1期8卷 103-110页

作者： Arzu Akbulut Melike Kaplan Mohammed K.A.Kaabar Mathematics-Computer Department Art-Science FacultyEski¸s ehir Osmangazi UniversityEski¸s ehirTurkey Department of Computer Engineering Engineering and Architecture FacultyKastamonu UniversityKastamonuTurkey Institute of Mathematical Sciences Faculty of ScienceUniversity of MalayaKuala Lumpur 50603Malaysia

The current work aims to present abundant families of the exact solutions of Mikhailov-Novikov-Wang equation via three different *** adopted methods are generalized Kudryashov method(GKM),exponential rational function method(ERFM),and modified extended tanh-function method(METFM).Some plots of some presented new solutions are represented to exhibit wave *** results in this work are essential to understand the physical meaning and behavior of the investigated equation that sheds light on the importance of investigating various nonlinear wave phenomena in ocean engineering and *** equation provides new insights to understand the relationship between the integrability and water waves’phenomena.

关键词： Exact solutions Generalized Kudryashov method Modified extended tanh-function method Symbolic computation PDEs

来源：评论

学校读者我要写书评

暂无评论

AIS - A Metric for Assessing the Impact of an Influencer’s Twitter Activity on the Price of a Cryptocurrency 29th

AIS - A Metric for Assessing the Impact of an Influencer...

引用

29th International Conference on Cooperative Information Systems, CoopIS 2023

作者： Miller, Kevin Böhmer, Kristof Faculty of Computer Science Research Group Software Architecture University of Vienna Währinger Straße 29 Vienna Austria

ISBN: (纸本)9783031468452

Individual users on social media platforms like Twitter can significantly volatile assets, including cryptocurrencies. However, current research has overlooked this aspect, focusing on sentiment analysis that includes all posts from all users. Making it challenging to detect trends caused by individuals. To address this gap, we introduce the Asset Influence Score (AIS), a percentage-based metric that assesses the likelihood of a newly issued tweet aligning with periods of heightened trading activity. By analyzing price data and tweets concurrently, we identify correlations that enable to predict the likelihood of specific users’ tweets co-occurring with increased trading activity. Evaluating the AIS using a publicly available prototype and Twitter data from 2020 to 2023, we find that using the AIS as a buy signal outperforms buy-and-hold and technical trading strategies while maintaining high liquidity. Demonstrating the applicability of AIS in improving trading decisions and identifying key individuals on social media platforms. © 2024, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Explicit iterative solution of a Caputo-Hadamard–type fractional turbulent flow model

Explicit iterative solution of a Caputo-Hadamard–type fract...

引用

作者： Zhang, Lihong Qin, Nan Ahmad, Bashir School of Mathematics and Computer Science Shanxi Normal University Linfen China Research Group Department of Mathematics Faculty of Science King Abdulaziz University Jeddah Saudi Arabia

In this article, by using the method of upper and lower solutions combined with the monotone iterative technique, we investigate a Caputo-Hadamard–type fractional turbulent flow model. We prove new comparison results and obtain explicit monotone iterative sequences converging to the extremal solutions and unique solution of the model problem. Examples illustrating the main results are also presented. © 2020 John Wiley & Sons, Ltd.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

Improving AutoML for LLMs via Knowledge-Based Meta-Learning 7

Improving AutoML for LLMs via Knowledge-Based Meta-Learning

引用

7th Doctoral Symposium on Natural Language Processing, NLP-DS 2024

作者： Estevanell-Valladares, Ernesto Luis Faculty of Mathematics and Computer Science University of Havana Cuba Natural Language Processing and Information Systems Group University of Alicante Spain

Recent advancements in Large Language Models (LLMs) such as BERT, GPT-4, and T5 have revolutionized the field of Natural Language Processing (NLP), unlocking numerous applications. However, finetuning these models for specific tasks remains a complex and resource-intensive process, often relying heavily on expert knowledge. This research proposes integrating meta-learning into Automatic Machine Learning (AutoML) systems to optimize LLM fine-tuning and pipeline construction. We hypothesize that knowledge-based meta-learning can overcome the inefficiencies of current AutoML approaches by embedding expert-derived heuristics into the optimization process. Our methodology involves compiling extensive LLM usage data, training meta-learning estimators, and integrating these into the AutoGOAL AutoML framework. By doing so, we aim to reduce computational costs and enhance the efficiency of LLM-based NLP applications. The proposed system will be evaluated against traditional AutoML methods and human experts on various text classification tasks to validate its effectiveness. This research can further democratize NLP by making advanced LLM capabilities more accessible and efficient. © 2024 Copyright for this paper by its authors.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

API Rate Limit Adoption – A pattern collection 28

API Rate Limit Adoption – A pattern collection

引用

28th European Conference on Pattern Languages of Programs, EuroPLoP 2023

作者： Serbout, Souhaila El Malki, Amine Pautasso, Cesare Zdun, Uwe Software Institute USI Lugano Switzerland University of Vienna Faculty of Computer Science Software Architecture Research Group Doctoral School Computer Science Vienna Austria

ISBN: (纸本)9798400700408

The API Rate Limit pattern controls the rate at which clients make API requests by counting the number of requests in a specified time interval and reacting against abusive clients, in order to protect the limited resources of the API from exhaustion and denial of service attacks. This practice helps service providers to prevent abuse and ensure fair resource allocation, maintain system stability, monitor and control service availability, protect against DDoS attacks In this research paper, we have identified patterns covering the API Rate Limit pattern adoption starting from its documentation to its implementation. Our objective is to elucidate the trade-offs associated with different identified patterns and offer guidance to developers in making informed decisions when choosing the most suitable Rate Limit method, scope, and granularity for their service. By providing a comprehensive overview of how to adopt the Rate Limit pattern, this paper aims to enhance the understanding of how APIs can be designed to facilitate high scalability, security, reliability, and service availability. Furthermore, we present each pattern along with known uses observed in real-world APIs and technologies. © 2023 Copyright held by the owner/author(s). Publication rights licensed to ACM.

关键词： System stability

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：