检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Ozbulak, Utku Anzaku, Esla Timothy Kang, Solha De Neve, Wesley Vankerschaver, Joris Center for Biosystems and Biotech Data Science Ghent University Global Campus Korea Republic of Department of Electronics and Information Systems Ghent University Belgium Department of Applied Mathematics Computer Science and Statistics Ghent University Belgium

Machine learning (ML) research strongly relies on benchmarks in order to determine the relative effectiveness of newly proposed models. Recently, a number of prominent research effort argued that a number of models that improve the state-of-the-art by a small margin tend to do so by winning what they call a "benchmark lottery". An important benchmark in the field of machine learning and computer vision is the ImageNet where newly proposed models are often showcased based on their performance on this dataset. Given the large number of self-supervised learning (SSL) frameworks that has been proposed in the past couple of years each coming with marginal improvements on the ImageNet dataset, in this work, we evaluate whether those marginal improvements on ImageNet translate to improvements on similar datasets or not. To do so, we investigate twelve popular SSL frameworks on five ImageNet variants and discover that models that seem to perform well on ImageNet may experience significant performance declines on similar datasets. Specifically, state-of-the-art frameworks such as DINO and Swav, which are praised for their performance, exhibit substantial drops in performance while MoCo and Barlow Twins displays comparatively good results. As a result, we argue that otherwise good and desirable properties of models remain hidden when benchmarking is only performed on the ImageNet validation set, making us call for more adequate benchmarking. To avoid the "benchmark lottery" on ImageNet and to ensure a fair benchmarking process, we investigate the usage of a unified metric that takes into account the performance of models on other ImageNet variant datasets. Copyright © 2025, The Authors. All rights reserved.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Computational methods for finding bi-regular cages

arXiv

引用

arXiv 2024年

作者： Goedgebeur, Jan Jooken, Jorik Van den Eede, Tibo Department of Computer Science KU Leuven Campus Kulak-Kortrijk Etienne Sabbelaan 53 Kortrijk8500 Belgium Department of Applied Mathematics Computer Science and Statistics Ghent University Krijgslaan 281-S9 Ghent9000 Belgium

An ptr,mu;gq-graph is a (simple, undirected) graph of girth g ≥ 3 with vertices of degrees r and m where 2 ≤ r MSC Codes 05C07, 05C35, 05C85, 68R10, 90C35 Copyright © 2024, The Authors. All rights reserved.

关键词： Graph algorithms

来源：评论

学校读者我要写书评

暂无评论

Computing Smallest Convex Intersecting Polygons

arXiv

引用

arXiv 2022年

作者： Antoniadis, Antonios de Berg, Mark Kisfaludi-Bak, Sándor Skarlatos, Antonis Department for Applied Mathematics University of Twente Netherlands Department of Mathematics and Computer Science TU Eindhoven Netherlands Department of Computer Science Aalto University Espoo Finland Department of Computer Science University of Salzburg Austria

A polygon C is an intersecting polygon for a set O of objects in R2 if C intersects each object in O, where the polygon includes its interior. We study the problem of computing the minimum-perimeter intersecting polygon and the minimum-area convex intersecting polygon for a given set O of objects. We present an FPTAS for both problems for the case where O is a set of possibly intersecting convex polygons in the plane of total complexity n. Furthermore, we present an exact polynomial-time algorithm for the minimum-perimeter intersecting polygon for the case where O is a set of n possibly intersecting segments in the plane. So far, polynomial-time exact algorithms were only known for the minimum perimeter intersecting polygon of lines or of disjoint segments. © 2022, CC BY.

关键词： Computational geometry

来源：评论

学校读者我要写书评

暂无评论

INFINITE GRIDS IN DIGRAPHS

arXiv

引用

arXiv 2024年

作者： Hamann, Matthias Heuer, Karl University of Hamburg Department of Mathematics Bundesstr. 55 Hamburg20146 Germany Technical University of Denmark Department of Applied Mathematics and Computer Science Richard Petersens Plads Building 322 Kongens Lyngby2800 Denmark

Halin proved that every graph with an end ω containing infinitely many pairwise disjoint rays admits a subdivision of the infinite quarter-grid as a subgraph where all rays from that subgraph belong to ω. We will prove a corresponding statement for digraphs, that is, we will prove that every digraph that has an end with infinitely many pairwise disjoint directed rays contains a subdivision of a grid-like digraph all of whose directed rays belong to that *** Codes 05C63, 05C20 (primary), 05C38 (secondary) © 2024, CC BY.

关键词： Graph theory

来源：评论

学校读者我要写书评

暂无评论

Driving Activity Classification Using Deep Residual Networks Based on Smart Glasses Sensors

引用

Intelligent Automation & Soft Computing 2023年第11期38卷 139-151页

作者： Narit Hnoohom Sakorn Mekruksavanich Anuchit Jitpattanakul Department of Computer Engineering Image Information and Intelligence LaboratoryFaculty of EngineeringMahidol UniversityNakhon Pathom73170Thailand Department of Computer Engineering School of Information and Communication TechnologyUniversity of PhayaoPhayaoThailand Department of Mathematics Faculty of Applied ScienceKing Mongkut’s University of Technology North BangkokBangkok10800Thailand Intelligent and Nonlinear Dynamic Innovations Research Center Science and Technology Research InstituteKing Mongkut’s University of Technology North BangkokBangkok10800Thailand

Accidents are still an issue in an intelligent transportation system,despite developments in self-driving technology(ITS).Drivers who engage in risky behavior account for more than half of all road *** a result,reckless driving behaviour can cause congestion and *** vision and multimodal sensors have been used to study driving behaviour categorization to lessen this *** research has also collected and analyzed a wide range of data,including electroencephalography(EEG),electrooculography(EOG),and photographs of the driver’s *** the other hand,driving a car is a complicated action that requires a wide range of body *** this work,we proposed a ResNet-SE model,an efﬁcient deep learning classiﬁer for driving activity clas-siﬁcation based on signal data obtained in real-world trafﬁc conditions using smart ***-to-end learning can be achieved by combining residual networks and channel attention approaches into a single learning *** data from 3-point EOG electrodes,tri-axial accelerometer,and tri-axial gyroscope from the Smart Glasses dataset was utilized in this *** performed various experiments and compared the proposed model to base-line deep learning algorithms(CNNs and LSTMs)to demonstrate its *** to the research results,the proposed model outperforms the previous deep learning models in this domain with an accuracy of 99.17%and an F1-score of 98.96%.

关键词： Smart glasses human activity recognition deep learning wearable sensors driving activity

来源：评论

学校读者我要写书评

暂无评论

A new multi-access technique OFDMA-RL for remote lab system

A new multi-access technique OFDMA-RL for remote lab system

引用

IEEE SSD International Multi-Conference on Systems, Signals and Devices

作者： Elmissaoui Taoufik Onyedeke Obinna Cyril Agbo Jonathan Chukwunwike Obayi Adaora Angela Nwangwu Emmanuel C Innov’Com lab SUP’COM University of Carthage & Higher Institute of Applied Mathematics and Computer Science University of Kairouan Tunisia Department of Computer Science University of Nigeria Nsukka

The Remote Lab System (RLS) is a special combination between software and materials to give the chance for students to access remotely the laboratory equipment. With this system universities will be able to build a full online license and master's degree. Actually, the operational remote lab allows students access the equipment remotely. The number of beneficiaries of remote lab services continues to increase. The reservation process and the limit of the slot time given for each student became weaknesses for the RLS. In this paper, we propose and test a famous technique to share remotely the laboratory equipment between students at the same time. In fact, we test the Orthogonal Frequency Division Multiple Access (OFDMA) and exploit the good user separation done by the OFDMA technique, and also each users is assigned a frequency. The identification of each user or equipment lab will be based on the assigned frequency. Applying OFDMA to manage multi- user of our RLS allows us more than one student access our equipment lab. The system OFDMA allows students reused some equipment lab in multiple practical work or shared it between multiple-users. The limitation of our software and equipment lab present a hard barrier for us to test our solution for more than three users at the same time. In order to let our system stable we decide to give the possibility for only two users sharing the laboratory equipment at the same time.

关键词：

来源：评论

学校读者我要写书评

暂无评论

CORD: Co-design of Resource Allocation and Deadline Decomposition with Generative Profiling

arXiv

引用

arXiv 2025年

作者： Gifford, Robert Eisenklam, Abby Bondar, Georgiy A. Cai, Yifan Sial, Tushar Phan, Linh Thi Xuan Halder, Abhishek Department of Computer and Information Science University of Pennsylvania United States Department of Applied Mathematics University of California Santa Cruz United States Department of Aerospace Engineering Iowa State University United States

As multicore hardware is becoming increasingly common in real-time systems, traditional scheduling techniques that assume a single worst-case execution time for a task are no longer adequate, since they ignore the impact of shared resources on execution time. When tasks execute concurrently on different cores, their execution times often vary substantially with their allocated budgets of shared resources, such as cache and memory bandwidth. Even under a specific resource allocation, the resource use pattern of a task also changes with time during a job execution. It is therefore important to consider the relationship between multicore resources and execution time in task modeling and scheduling algorithm design. In this paper, we propose a much more precise execution model for DAG-based real-time tasks that captures the time-varying resource use characteristics of a task under different budgets of shared resources. We present a generative resource profiling algorithm that efficiently predicts, from limited measurement data, the resource profile of a task at any time during its execution under a given resource budget. The generative profiles can then be used to construct the execution models for tasks, using which one can make informed resource allocation decisions. We further introduce a multicore resource allocation and deadline decomposition co-design technique for DAG-based tasks that leverages the generated execution models to jointly allocate resources and deadlines to subtasks, to maximize resource efficiency and schedulability. Our evaluation results show that our generative profiling algorithm achieves high accuracy while being efficient, and that our co-allocation technique substantially improves schedulability compared to a state-of-the-art deadline decomposition method. Copyright © 2025, The Authors. All rights reserved.

关键词： Budget control

来源：评论

学校读者我要写书评

暂无评论

Angklung Smart Band: An IoT-Based System to Support Music Activities for Elderly in Thailand

Angklung Smart Band: An IoT-Based System to Support Music Ac...

引用

2022 IEEE European Technology and Engineering Management Summit, E-TEMS 2022

作者： Hiranpanthaporn, Saranya Phoasavadi, Pornprapit Cooharojananone, Nagul Technopreneurship and Innovation Management Program Graduate School Chulalongkorn University Bangkok Bangkok Thailand Emili Sagol Creative Arts Research and Innovation for Well-being Center Chulalongkorn University Faculty of Fine and Applied Arts Department of Thai Music Bangkok Bangkok Thailand Chulalongkorn University Faculty of Science Department of Mathematics and Computer Science Bangkok Bangkok Thailand

ISBN: (数字)9781665411004

ISBN: (纸本)9781665411004

Organizing music activities for the elderly is another way that supports their well-being. Angklung, an Indonesian musical instrument, has been used for music activities for the elderly in Thailand with the hand signs method. Unfortunately, music activity is not widely used because the experts with the hand sign skills are few and not enough for demanding in the aging healthcare. At the same time, technologies of remote systems using the Internet of Things (IoT) have been developed to assist the elderly in supporting and improving their quality of life. This paper will introduce 'Angklung Smart Band,' an IoT-based system to support Angklung music activities for the elderly in Thailand. This work aims at setting up Angklung music activities for the elderly by using technology instead of hand signs. The system is composed of a web application, IoT devices, and Angklung musical instruments connected together via a wireless network. We did a preliminary study with the experts to improve experiences and system performance. After that, we asked the music experts to use the smart band to conduct the music activities experiment with the elderly for three days and give us feedback. The results found that the smart band could assist the Angklung music experts and help with the shortage of music expertise in aged care facilities or nursing homes. © 2022 IEEE.

关键词： Music

来源：评论

学校读者我要写书评

暂无评论

Performance evaluation of GPU-enhanced Jacobi algorithm implementations for optimizing CFD Poisson partial differential equation solving

Performance evaluation of GPU-enhanced Jacobi algorithm impl...

引用

International Conference on System Theory, Control, and Computing (ICSTCC)

作者： Sebastian Sbîrnă Liana-Simona Sbîrnă DTU Compute Department Institute of Applied Mathematics and Computer Science Technical University of Denmark Kongens Lyngby Denmark Department of Chemistry Faculty of Sciences University of Craiova Craiova Romania

ISBN: (数字)9798350364293

ISBN: (纸本)9798350364309

The current work presents an in-depth analysis of several optimizations using GPU parallel computing applied to the Jacobi method for solving Poisson partial differential equations in computational fluid dynamics (CFD). We expand on previous CPU-parallelized Jacobi algorithm research, exploring four GPU-optimized Jacobi method variants: single-threaded, multi-threaded, multi-GPU and a norm-based stopping criterion kernel. These implementations are benchmarked against a multi-threaded CPU baseline. Results indicate that, whereas the single-threaded GPU version is slower than the CPU baseline, multi-threaded GPU versions achieve significant speed gains, especially for larger grid sizes. The multi-GPU version doubles memory bandwidth, enhancing performance for extensive computations, despite overhead for smaller matrices. The norm-stopping criterion kernel offers early convergence for small matrices but at a high overhead cost. Profiling confirms a memory-bound bottleneck, suggesting single-precision and optimized memory access as improvements. Ultimately, multi-threaded GPU kernels substantially outperform the CPU baseline for large-scale CFD problems, establishing GPUs as efficient accelerators for the Jacobi algorithm.

关键词： Jacobian matrices Performance evaluation Runtime Computational fluid dynamics Graphics processing units Process control Bandwidth Switches Throughput Kernel

来源：评论

学校读者我要写书评

暂无评论

FreqRISE: Explaining time series using frequency masking

arXiv

引用

arXiv 2024年

作者： Brüsch, Thea Wickstrøm, Kristoffer Knutsen Schmidt, Mikkel N. Alstrøm, Tommy Sonne Jenssen, Robert Department of Applied Mathematics and Computer Science Technical University of Denmark Denmark Department of Physics and Technology UiT The Arctic University of Norway Norway Norwegian Computing Center Oslo Norway

Time-series data are fundamentally important for many critical domains such as healthcare, finance, and climate, where explainable models are necessary for safe automated decision making. To develop explainable artificial intelligence in these domains therefore implies explaining salient information in the time series. Current methods for obtaining saliency maps assume localized information in the raw input space. In this paper, we argue that the salient information of a number of time series is more likely to be localized in the frequency domain. We propose FreqRISE, which uses masking-based methods to produce explanations in the frequency and time-frequency domain, and outperforms strong baselines across a number of tasks. The source code is available here: https://***/theabrusch/FreqRISE © 2024, CC BY.

关键词： Time series

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：