检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Zeydan, Engin Vaca-Rubio, Cristian J. Blanco, Luis Pereira, Roberto Caus, Marius Aydeger, Abdullah Barcelona08860 Spain Dept. of Electrical Engineering and Computer Science Florida Institute of Technology MelbourneFL United States

In this paper, we present an innovative federated learning (FL) approach that utilizes Kolmogorov-Arnold Networks (KANs) for classification tasks. By utilizing the adaptive activation capabilities of KANs in a federated framework, we aim to improve classification capabilities while preserving privacy. The study evaluates the performance of federated KANs (F-KANs) compared to traditional federated Multi-Layer Perceptrons (F-MLPs) on classification task. The results show that the F-KANs model significantly outperforms the F-MLP model in terms of accuracy, precision, recall, F1 score and stability, and achieves better performance, paving the way for more efficient and privacy-preserving predictive analytics. Copyright © 2024, The Authors. All rights reserved.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Composite metamorphic relations for integration testing 22

Composite metamorphic relations for integration testing

引用

8th International Conference on computer technology Applications, ICCTA 2022

作者： Iakusheva, Sofia Khritankov, Anton Phystech School of Applied Mathematics and Informatics Moscow Institute of Physics and Technology Russia Faculty of Computer Science Dept. of Software Engineering Hse University Russia

ISBN: (纸本)9781450396226

Metamorphic testing is a testing method for problems without test oracles. Integration testing allows for detecting errors in complex systems that may not be found during the testing of their components. In this paper, we propose a novel approach that applies metamorphic testing in integration testing. The main idea is to develop a composite metamorphic relation for the system represented as an acyclic graph. This relation is a logical function of metamorphic relations for the parts of the system (vertices of the graph). It takes into account the features of the parts. Also, it can simplify the search for failure by identifying the subsystem with error. In this paper's theoretical part, we describe an algorithm of relation design. Then, we apply our method to a bioinformatics system for comparative genetic analysis of tissues using production tools. This experiment proves our method can be applied to real-life pipelines and find errors in them. © 2022 ACM.

关键词： Integration testing

来源：评论

学校读者我要写书评

暂无评论

Towards Standardized Manufacturing as a Service through Asset Administration Shell and International Data Spaces Connectors 48

Towards Standardized Manufacturing as a Service through Asse...

引用

48th Annual Conference of the IEEE Industrial Electronics Society, IECON 2022

作者： Inigo, Miguel A. Legaristi, Jon Larrinaga, Felix Perez, Alain Cuenca, Javier Kremer, Blanca Montejo, Elena Porto, Alain Mondragon S.Coop. Innovation and Technology Dept. Spain Mondragon University Electronics and Computer Science Dept. Mondragón Arrasate Spain Ikerlan Research Centre Brta Ict Dept. Spain Ideko Research Centre Brta Ict and Automation Dept. Elgoibar Spain

ISBN: (数字)9781665480253

ISBN: (纸本)9781665480253

This paper presents an industrial scenario that simulates a Manufacturing as a Service system for the execution of remote production orders built upon the implementation of emerging Asset Administration Shell (AAS) capabilities and International Data Space connectors. Static and dynamic information from industrial assets (presses and laser cutting machines) are modelled with new AAS submodels and the result is stored in an AAS manager/registration system. A manufacturing orchestrator discovers assets through the registry and completes production orders. The AAS registry allows the selection of assets with capabilities to perform tasks and also shares the AAS catalogue available in the system. The catalogue is shared with external parties through Data Space Connectors. Third party companies can launch manufacturing orders remotely using the same connectors. The paper validates the implementation of AAS components and IDS connectors in a manufacturing context where remote production orders can be securely activated. © 2022 IEEE.

关键词： Standardization

来源：评论

学校读者我要写书评

暂无评论

Adaptive Control Using a Quaternion Wavelet Neural Network

Adaptive Control Using a Quaternion Wavelet Neural Network

引用

International Workshop on Robot Motion and Control (RoMoCo)

作者： Gerardo Martínez-Terán Eduardo Bayro-Corrochano Dept. Electrical Engineering and Computer Science CINVESTAV Guadalajara Mexico Institute of Automatic Control and Robotics Poznan University of Technology

ISBN: (数字)9798350393965

ISBN: (纸本)9798350393972

Robotics and haptic systems have allowed new and diverse applications in the field of medicine, such as assisted surgery and teleoperation which have increasingly stringent requirements for accuracy, convergence, and low computational consumption. In this paper an adaptive PID control law (Proportional Integral Derivative controller, PID), of indirect architecture is presented for movement paths in a haptic system of open chain, where the identification of the plant is through a quaternionic wavelet neural network (Quaternion Wavelet Neural Network, QWNN) for tune the PID values, this allows the optimal movement into the regions of the workspace.

关键词： Uncertainty Quaternions Neural networks Surgery Robustness Haptic interfaces Topology

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Algorithm to Dual Sparse Sampling Measurement in Time-Resolved Electromagnetic Near-Field Scanning

A Hybrid Algorithm to Dual Sparse Sampling Measurement in Ti...

引用

IEEE International Symposium on Electromagnetic Compatibility (EMC)

作者： Yanming Zhang Steven Gao Lijun Jiang Dept. of Electronic Engineering Chinese University of Hong Kong Hong Kong Dept. of Electrical and Computer Engineering Missouri University of Science and Technology Rolla MO USA

ISBN: (数字)9798350360394

ISBN: (纸本)9798350360400

Time-resolved electromagnetic near-field scanning is vital for antenna measurement and addressing complex electromagnetic interference and compatibility issues. However, the swift acquisition of high-resolution spatiotemporal data remains challenging due to physical constraints, such as moving the probe position and allowing sufficient time for sampling. This paper introduces a novel hybrid approach that combines Kriging for sparse spatial measurement, compressed sensing (CS) for sparse temporal sampling, and dynamic mode decomposition (DMD) for a comprehensive analysis of dual-sparse sampling electromagnetic near-field data. CS optimizes sparse sampling in the time domain, capitalizing on the inherent sparsity within electromagnetic radiated signals, resulting in reliable representation of time-domain signals and reducing the required time samples. Latin hypercube sampling guides the probe position, facilitating sparse measurement in the space domain. DMD extracts meaningful insights from the resulting sparse spatiotemporal data, producing sparse dynamic modes and temporal evolution information. Subsequently, Kriging is employed to infer missing spatial measurements for each sparse dynamic mode. Finally, the entire spatiotemporal signals are reconstructed based on interpolated dynamic modes and temporal evolution information. Validation of the proposed method is demonstrated with an example using crossed dipole antennas as the device under test. The Kriging-CS-DMD framework effectively reconstructs electromagnetic fields with precision while concurrently reducing the measurement workload in both the time and space domains. This methodology holds promise for various applications, including space-time-modulated electronic devices.

关键词： Antenna measurements Time measurement Spatiotemporal phenomena Sensors Electromagnetic fields Data mining Electromagnetics Time-domain analysis Probes Compressed sensing

来源：评论

学校读者我要写书评

暂无评论

Augmented Reality-Based Navigation: Bridging Indoor and Outdoor Environments through Immersal Integration

Augmented Reality-Based Navigation: Bridging Indoor and Outd...

引用

IEEE International Symposium on Consumer Electronics (ISCE)

作者： Zacky Maulana Achmad Sritrusta Sukaridhoto Muhammad Agus Zainuddin Aurent Savila Ardian Firmansyah Septa Mega Saputra Dept. of Informatics and Computer Engineering Politeknik Elektronika Negeri Surabaya Surabaya Indonesia Dept. of Multimedia Creative Technology Politeknik Elektronika Negeri Surabaya Surabaya Indonesia

ISBN: (数字)9798350365191

ISBN: (纸本)9798350365207

A navigation system is an essential tool designed to assist users in determining and following a route from one location to another. Navigation systems are typically categorized into two types: outdoor navigation systems designed for open areas and indoor navigation systems used within enclosed spaces. However, transitioning between indoor and outdoor environments has limitations, often requiring users to switch applications, such as using GPS for outdoor navigation and a different application for indoor navigation. Therefore, we propose the integration of indoor and outdoor navigation based on Augmented Reality. The development of AR navigation system begins with the creation of 3D assets of the Politeknik Elektronika Negeri Surabaya (PENS) campus, which is the site of our research including three buildings for indoor navigation and the connecting roads between the buildings for outdoor navigation. The development of this navigation system uses the Immersal SDK as a library for Spatial Mapping, Localization and System Integration. Several features are included, such as indoor-outdoor navigation, multilevel floor navigation, and zero additional devices. The system testing results are based on user testing, integration testing, and multilevel floor testing. From User Testing with PIECES Framework, 32 respondents expressed satisfaction with the proposed system. Integration Testing showed that the system could navigate between indoor and outdoor environments. And Multilevel Floor Testing demonstrated that the system could navigate within buildings with multiple floors.

关键词： Location awareness Three-dimensional displays Navigation Indoor navigation Buildings Switches Stairs Floors Augmented reality Testing

来源：评论

学校读者我要写书评

暂无评论

Automatic Short Answer Grading Using a LSTM Based Approach

Automatic Short Answer Grading Using a LSTM Based Approach

引用

Applied Intelligence and Computing (AIC), IEEE World Conference on

作者： Udit Kr Chakraborty Anurag Mishra Head of Dept. of Computer Science and Engineering Sikkim Manipal Institute of Technology Sikkim Manipal University Sikkim India Dept. of Computer Science and Engineering Sikkim Manipal Institute of Technology Sikkim Manipal University Sikkim India

Short Answer Grading is an emerging application of Natural Language Processing and text processing. Automated Short Answer Grading (ASAG) is the process of evaluating student-written short responses using computer techniques like Machine learning. The ASAG task has been studied for a long time, but because of the difficulties in the research, it still attracts attention. One of the primary limitations of ASAG is the scarcity of domain-relevant training data. The job of ASAG can be approached using a variety of methods, which can be broadly divided between traditional methods using hand-crafted features and methods based on deep learning. Due to the growing popularity of this field, researchers have been using Deep Learning Approaches to address this challenge over the past five years. This paper explores the methods of creating an LSTM model, to test how close this approach will bring the machine score to that of the Human Score.

关键词：

来源：评论

学校读者我要写书评

暂无评论

UniFaaS: Programming across Distributed Cyberinfrastructure with Federated Function Serving

arXiv

引用

arXiv 2024年

作者： Li, Yifei Chard, Ryan Babuji, Yadu Chard, Kyle Foster, Ian Li, Zhuozhao Dept. of Computer Science and Engineering Southern University of Science and Technology Shenzhen China Data Science and Learning Division Argonne National Laboratory LemontIL United States Dept. of Computer Science University of Chicago ChicagoIL United States

Modern scientific applications are increasingly decomposable into individual functions that may be deployed across distributed and diverse cyberinfrastructure such as supercomputers, clouds, and accelerators. Such applications call for new approaches to programming, distributed execution, and function-level management. We present UniFaaS, a parallel programming framework that relies on a federated function-as-a-service (FaaS) model to enable composition of distributed, scalable, and high-performance scientific workflows, and to support fine-grained function-level management. UniFaaS provides a unified programming interface to compose dynamic task graphs with transparent wide-area data management. UniFaaS exploits an observe-predict-decide approach to efficiently map workflow tasks to target heterogeneous and dynamic resources. We propose a dynamic heterogeneity-aware scheduling algorithm that employs a delay mechanism and a re-scheduling mechanism to accommodate dynamic resource capacity. Our experiments show that UniFaaS can efficiently execute workflows across computing resources with minimal scheduling overhead. We show that UniFaaS can improve the performance of a real-world drug screening workflow by as much as 22.99% when employing an additional 19.48% of resources and a montage workflow by 54.41% when employing an additional 47.83% of resources across multiple distributed clusters, in contrast to using a single cluster. Copyright © 2024, The Authors. All rights reserved.

关键词： Scheduling algorithms

来源：评论

学校读者我要写书评

暂无评论

Enhancing Medical Image Analysis: Leveraging Transfer Learning in Convolutional Neural Networks for Tuberculosis Detection

Enhancing Medical Image Analysis: Leveraging Transfer Learni...

引用

International Conference for Convergence of technology (I2CT)

作者： Piyush Pankaj Dahiwadkar Hrishin Mandar Bhamre Aarti Sahitya Dept. of Computer Engineering K.J. Somaiya Institute of Technology Sion (Affiliated to Mumbai University) Mumbai India

ISBN: (数字)9798350394474

ISBN: (纸本)9798350394481

Advancements in medical imaging have paved the way for image-based computer-aided diagnosis (CADx) systems, revolutionizing the detection of lung abnormalities, including lung nodules and diffuse lung diseases. This paper explores the potential of convolutional neural networks (CNNs) in image-based CADx without the reliance on image-feature extraction, presenting a powerful alternative to feature-based CADx methods. Additionally, we introduce an image-based computer-aided detection (CADe) algorithm employing regions with CNN features (R-CNN) for precise identification of lung abnormalities. We conduct comprehensive evaluations of our image-based CADx utilizing CNN and CADe employing R-CNN, demonstrating their effectiveness across various lung abnormalities.

关键词： Solid modeling Tuberculosis Pulmonary diseases Transfer learning Neural networks Lung Streaming media

来源：评论

学校读者我要写书评

暂无评论

Semantic clustering of images using semantic similarity measures: A comparative study

Semantic clustering of images using semantic similarity meas...

引用

International Conference on Image and Signal Processing and their Applications (ISPA)

作者： Abdelmadjid Youcefa Oussama Aiadi Belal Khaldi Mohammed Lamine Kherfi Dept. of Electronics and Telecommunications University Kasdi Marbah Ouargla Ouargla Algeria Dept. of Computer Science and Information Technology University Kasdi Marbah Ouargla Ouargla Algeria

ISBN: (数字)9798350309249

ISBN: (纸本)9798350309256

In the last decade, the increasing popularity of image sharing applications over the web has led to a huge rising in the size of the personal image collections. While conventional content-based image retrieval systems suffer from the commonly acknowledged semantic difference between low-level image features and high-level semantics, using textual information associated with images could be a good alternative. Therefore, in order to facilitate the navigation through these collections, and extracting meaningful information from them rapidly and accurately, semantic clustering of images based on textual information could help performing such an important task. In this study, we present a comparative study of several semantic similarity metrics for image datasets clustering. In particular, we evaluate the performance of eight measures namely Path, Resnik, Wu-Palmer, Lin, Jiang-Conrath, Leacock-Chodorow, Li, and Wpath. We conduct our experiments on three public datasets. The experimental results revealed that Resnik and Wpath Similarity measures whith accuracy (78% and 77.67% respectively) outperform the remaining metrics and yield more coherent and fast clustering solutions.

关键词： Atmospheric measurements Navigation Semantics Image retrieval Signal processing Feature extraction Particle measurements

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：