检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Papamarkou, Theodore Birdal, Tolga Bronstein, Michael Carlsson, Gunnar Curry, Justin Gao, Yue Hajij, Mustafa Kwitt, Roland Liò, Pietro Di Lorenzo, Paolo Maroulas, Vasileios Miolane, Nina Nasrin, Farzana Ramamurthy, Karthikeyan Natesan Rieck, Bastian Scardapane, Simone Schaub, Michael T. Veličković, Petar Wang, Bei Wang, Yusu Wei, Guo-Wei Zamzmi, Ghada Department of Mathematics The University of Manchester Manchester United Kingdom Department of Computing Imperial College London London United Kingdom Department of Computer Science University of Oxford Oxford United Kingdom Department of Mathematics Stanford University Stanford United States BlueLightAI Inc United States University at Albany New York United States School of Software Tsinghua University Beijing China University of San Francisco San Francisco United States Department of Artificial Intelligence and Human Interfaces University of Salzburg Austria Department of Computer Science and Technology University of Cambridge Cambridge United Kingdom Department of Information Engineering Electronics and Telecommunications Sapienza University of Rome Rome Italy Department of Mathematics University of Tennessee Knoxville United States Department of Electrical and Computer Engineering UC Santa Barbara Santa Barbara United States Department of Mathematics University of Hawai‘i at Mānoa HI United States IBM Corporation New York United States Helmholtz Munich Munich Germany Technical University of Munich Munich Germany RWTH Aachen University Aachen Germany Google Deep-Mind United Kingdom School of Computing University of Utah Utah United States Computer Science and Engineering Department University of California San Diego San Diego United States Department of Mathematics Michigan State University East LansingMI United States University of South Florida Florida United States

Topological deep learning (TDL) is a rapidly evolving field that uses topological features to understand and design deep learning models. This paper posits that TDL is the new frontier for relational learning. TDL may complement graph representation learning and geometric deep learning by incorporating topological concepts, and can thus provide a natural choice for various machine learning settings. To this end, this paper discusses open problems in TDL, ranging from practical benefits to theoretical foundations. For each problem, it outlines potential solutions and future research opportunities. At the same time, this paper serves as an invitation to the scientific community to actively participate in TDL research to unlock the potential of this emerging field. © 2024, CC BY-NC-ND.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

DEMONSTRATING DATA-TO-KNOWLEDGE PIPELINES FOR CONNECTING PRODUCTION SITES IN THE WORLD WIDE LAB A PREPRINT

arXiv

引用

arXiv 2024年

作者： Gorisen, Leon Schneider, Jan-Niklas Behery, Mohamed Brauner, Philipp Lennartz, Moritz Kotter, David Kaster, Thomas Petrovic, Oliver Hinke, Christian Gries, Thomas Lakemeyer, Gerhard Ziefle, Martina Brecher, Christian Hafner, Constantin Chair for Laser Technology RWTH Aachen University Aachen52074 Germany Knowledge Based Systems Group RWTH Aachen University Aachen52074 Germany Communication Science RWTH Aachen University Aachen52074 Germany Chair of Textile Technology RWTH Aachen University Aachen52074 Germany Laboratory for Machine Tools and Production Engineering RWTH Aachen University Aachen52074 Germany Human Computer Interaction Center RWTH Aachen University Aachen52074 Germany Fraunhofer Institute for Laser Technology Aachen52074 Germany

The digital transformation of production requires new methods of data integration and storage, as well as decision making and support systems that work vertically and horizontally throughout the development, production, and use cycle. In this paper, we propose Data-to-Knowledge (and Knowledge-to-Data) pipelines for production as a universal concept building on a network of Digital Shadows (a concept augmenting Digital Twins). We show a proof of concept that builds on and bridges existing infrastructure to 1) capture and semantically annotates trajectory data from multiple similar but independent robots in different organisations and use cases in a data lakehouse and 2) an independent process that dynamically queries matching data for training an inverse dynamics foundation model for robotic control. The article discusses the challenges and benefits of this approach and how Data-to-Knowledge pipelines contribute efficiency gains and industrial scalability in a World Wide Lab as a research outlook. Copyright © 2024, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A SURVEY ON BRAIN-INSPIRED DEEP LEARNING VIA PREDICTIVE CODING

arXiv

引用

arXiv 2023年

作者： Salvatori, Tommaso Mali, Ankur Buckley, Christopher L. Lukasiewicz, Thomas Rao, Rajesh P.N. Friston, Karl Ororbia, Alexander VERSES AI Research Lab Los AngelesCA United States Institute of Logic and Computation Vienna University of Technology Austria University of South Florida TampaFL33620 United States Sussex AI Group Department of Informatics University of Sussex Brighton United Kingdom Department of Computer Science University of Oxford United Kingdom Paul G. Allen School of Computer Science and Engineering University of Washington SeattleWA United States The Wellcome Centre for Human Neuroimaging Queen Square Institute of Neurology University College London United Kingdom The Neural Adaptive Computing Laboratory Rochester Institute of Technology RochesterNY14623 United States

Artificial intelligence (AI) is rapidly becoming one of the key technologies of this century. The majority of results in AI thus far have been achieved using deep neural networks trained with the error backpropagation learning algorithm. However, such an algorithm has always been considered biologically implausible. To this end, recent works have studied learning algorithms for deep neural networks inspired by the neurosciences. One such theory, called predictive coding (PC), has shown promising properties that make it potentially valuable for the machine learning community: it can model information processing in different areas of the brain, can be used in cognitive control and robotics, has a solid mathematical foundation in variational inference, and performs its computations asynchronously. Inspired by such properties, works that propose novel PC-like algorithms are starting to be present in multiple sub-fields of machine learning and artificial intelligence at large. Here, we survey such efforts by first providing a broad overview of the history of PC to provide a common ground for the understanding of the recent developments, then by surveying current efforts and results, and concluding with a large discussion of possible implications and ways forward. Copyright © 2023, The Authors. All rights reserved.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

A fuzzy logic-based secure hierarchical routing scheme using firefly algorithm in Internet of Things for healthcare

引用

Scientific Reports 2023年第1期13卷 1-23页

作者： Hosseinzadeh, Mehdi Yoo, Joon Ali, Saqib Lansky, Jan Mildeova, Stanislava Yousefpoor, Mohammad Sadegh Ahmed, Omed Hassan Rahmani, Amir Masoud Tightiz, Lilia Institute of Research and Development Duy Tan University Da Nang Viet Nam School of Medicine and Pharmacy Duy Tan University Da Nang Viet Nam School of Computing Gachon University 1342 Seongnamdaero Seongnam 13120 South Korea Department of Information Systems College of Economics and Political Science Sultan Qaboos University Al Khoudh Muscat Oman Department of Computer Science and Mathematics Faculty of Economic Studies University of Finance and Administration Prague Czech Republic Department of Computer Engineering Dezful Branch Islamic Azad University Dezful Iran Department of Information Technology University of Human Development Sulaymaniyah Iraq Future Technology Research Center National Yunlin University of Science and Technology Yunlin Taiwan

The Internet of Things (IoT) is a universal network to supervise the physical world through sensors installed on different devices. The network can improve many areas, including healthcare because IoT technology has the potential to reduce pressure caused by aging and chronic diseases on healthcare systems. For this reason, researchers attempt to solve the challenges of this technology in healthcare. In this paper, a fuzzy logic-based secure hierarchical routing scheme using the firefly algorithm (FSRF) is presented for IoT-based healthcare systems. FSRF comprises three main frameworks: fuzzy trust framework, firefly algorithm-based clustering framework, and inter-cluster routing framework. A fuzzy logic-based trust framework is responsible for evaluating the trust of IoT devices on the network. This framework identifies and prevents routing attacks like black hole, flooding, wormhole, sinkhole, and selective forwarding. Moreover, FSRF supports a clustering framework based on the firefly algorithm. It presents a fitness function that evaluates the chance of IoT devices to be cluster head nodes. The design of this function is based on trust level, residual energy, hop count, communication radius, and centrality. Also, FSRF involves an on-demand routing framework to decide on reliable and energy-efficient paths that can send the data to the destination faster. Finally, FSRF is compared to the energy-efficient multi-level secure routing protocol (EEMSR) and the enhanced balanced energy-efficient network-integrated super heterogeneous (E-BEENISH) routing method based on network lifetime, energy stored in IoT devices, and packet delivery rate (PDR). These results prove that FSRF improves network longevity by 10.34% and 56.35% and the energy stored in the nodes by 10.79% and 28.51% compared to EEMSR and E-BEENISH, respectively. However, FSRF is weaker than EEMSR in terms of security. Furthermore, PDR in this method has dropped slightly (almost 1.4%) compared to that in EE

关键词：

来源：评论

学校读者我要写书评

暂无评论

A cluster-based trusted routing method using fire hawk optimizer (FHO) in wireless sensor networks (WSNs)

引用

Scientific Reports 2023年第1期13卷 1-20页

Today, wireless sensor networks (WSNs) are growing rapidly and provide a lot of comfort to human life. Due to the use of WSNs in various areas, like health care and battlefield, security is an important concern in the data transfer procedure to prevent data manipulation. Trust management is an affective scheme to solve these problems by building trust relationships between sensor nodes. In this paper, a cluster-based trusted routing technique using fire hawk optimizer called CTRF is presented to improve network security by considering the limited energy of nodes in WSNs. It includes a weighted trust mechanism (WTM) designed based on interactive behavior between sensor nodes. The main feature of this trust mechanism is to consider the exponential coefficients for the trust parameters, namely weighted reception rate, weighted redundancy rate, and energy state so that the trust level of sensor nodes is exponentially reduced or increased based on their hostile or friendly behaviors. Moreover, the proposed approach creates a fire hawk optimizer-based clustering mechanism to select cluster heads from a candidate set, which includes sensor nodes whose remaining energy and trust levels are greater than the average remaining energy and the average trust level of all network nodes, respectively. In this clustering method, a new cost function is proposed based on four objectives, including cluster head location, cluster head energy, distance from the cluster head to the base station, and cluster size. Finally, CTRF decides on inter-cluster routing paths through a trusted routing algorithm and uses these routes to transmit data from cluster heads to the base station. In the route construction process, CTRF regards various parameters such as energy of the route, quality of the route, reliability of the route, and number of hops. CTRF runs on the network simulator version 2 (NS2), and its performance is compared with other secure routing approaches with regard to energy, throughp

关键词：

来源：评论

学校读者我要写书评

暂无评论

GazeGAN: A robust generative adversarial saliency model based on invariance analysis of human gaze during scene free viewing

arXiv

引用

arXiv 2019年

作者： Che, Zhaohui Borji, Ali Zhai, Guangtao Min, Xiongkuo Guo, Guodong Le Callet, Patrick Institute of Image Communication and Network Engineering Shanghai Key Laboratory of Digital Media Processing and Transmissions Shanghai Jiao Tong University Shanghai200240 China MarkableAI United States Institute of Deep Learning Baidu Research Department of Computer Science and Electrical Engineering West Virginia University MorgantownWV United States Equipe Image Perception et Interaction Laboratoire des Sciences du Numérique de Nantes Université de Nantes France

—Data size is the bottleneck for developing deep saliency models, because collecting eye-movement data is very time-consuming and expensive. Most of current studies on human attention and saliency modeling have used high-quality stereotype stimuli. In real world, however, captured images undergo various types of transformations. Can we use these transformations to augment existing saliency datasets? Here, we first create a novel saliency dataset including fixations of 10 observers over 1900 images degraded by 19 types of transformations. Second, by analyzing eye movements, we find that observers look at different locations over transformed versus original images. Third, we utilize the new data over transformed images, called data augmentation transformation (DAT), to train deep saliency models. We find that label-preserving DATs with negligible impact on human gaze boost saliency prediction, whereas some other DATs that severely impact human gaze degrade the performance. These label-preserving valid augmentation transformations provide a solution to enlarge existing saliency datasets. Finally, we introduce a novel saliency model based on generative adversarial network (dubbed GazeGAN). A modified U-Net is proposed as the generator of the GazeGAN, which combines classic "skip connections" with a novel "center-surround connection (CSC)", in order to leverage multi-level features. We also propose a histogram loss based on Alternative Chi-Square Distance (ACS HistLoss) to refine the saliency map in terms of luminance distribution. Extensive experiments and comparisons over 3 datasets indicate that GazeGAN achieves the best performance in terms of popular saliency evaluation metrics, and is more robust to various perturbations. We also provide a comprehensive quantitative comparison of 22 state-of-the-art saliency models on distorted images, which contributes a robustness benchmark for saliency community. Our code and data are available at: https://***/CZHQuality/

关键词： Luminance

来源：评论

学校读者我要写书评

暂无评论

Preface

Communications in Computer and Information Science

引用

Communications in computer and Information science 2020年 1219 CCIS卷 v-vi页

作者： Ziefle, Martina Maciaszek, Leszek A. Human-Computer Interaction Center RWTH Aachen University AachenNordrhein-Westfalen Germany Institute of Business Informatics Wroclaw University of Economics Wroclaw Poland Department of Computing Macquarie University SydneyNSW Australia

来源：评论

学校读者我要写书评

暂无评论

Tablet-based strength-balance training to motivate and improve adherence to exercise in independently living older people: Part 2 of a phase ii preclinical exploratory trial

引用

Journal of Medical Internet Research 2014年第6期16卷 e159页

作者： Van Het Reve, Eva Silveira, Patrícia Daniel, Florian Casati, Fabio De Bruin, Eling D. Institute of Human Movement Sciences and Sport Department of Health Sciences and Technology ETH Zurich Zurich 8093 Wolfgang-Pauli-Strasse 27 Switzerland University of Trento Department of Information Engineering and Computer Science Trento Italy CAPHRI School for Public Health and Primary Care Department of Epidemiology Maastricht University Maastricht Netherlands Centre for Evidence Based Physiotherapy Maastricht University Maastricht Netherlands

Home-based exercise programs can improve physical functioning and health status of elderly people. Successful implementation of exercise interventions for older people presents major challenges and supporting elderly people properly while doing their home-based exercises is essential for training success. We developed a tablet-based system-ActiveLifestyle-that offers older adults a home-based strength-balance training program with incorporated motivation strategies and support features. Objective: The goal was to compare 3 different home-based training programs with respect to their effect on measures of gait quality and physical performance through planned comparisons between (1) tablet-based and brochure-based interventions, (2) individual and social motivation strategies, and (3) active and inactive participants. Methods: A total of 44 autonomous-living elderly people (mean 75, SD 6 years) were assigned to 3 training groups: social (tablet guided, n=14), individual (tablet guided, n=13), and brochure (brochure guided, n=17). All groups joined a 12-week progressive home-based strength-balance training program. Outcome measures were gait performance under single and dual task conditions, dual task costs of walking, falls efficacy, and physical performance as measured by the Short Physical Performance Battery (SPPB). Furthermore, active (≥75% program compliance) and inactive (<75% program compliance) individuals were compared based on their characteristics and outcome measures. Results: The tablet groups showed significant improvements in single and dual task walking, whereas there were no significant changes observable in the brochure group. Between-groups comparisons revealed significant differences for gait velocity (U=138.5;P=.03, r=.33) and cadence (U=138.5, P=.03 r=.34) during dual task walking at preferred speed in favor of the tablet groups. The brochure group had more inactive participants, but this did not reach statistical significance (U=167, P=.06, r=.2

关键词： Aging Delivery of health care Exercise therapy Gait Tablet

来源：评论

学校读者我要写书评

暂无评论

Spiral-Phased Laguerre-Gaussian Modes Generation in SWDM over Few Mode Fiber based on Electrical Equalization

引用

Journal of Physics: Conference Series 2020年第2期1529卷

作者： Alaan Ghazi Alaa Fareed Tendai Masunda S. A. Aljunid Syed Zulkarnain Syed Idrus Angela Amphawan Aras Al-dawoodi C. B. M Rashidi Ibrahim Eskandar Ibrahim Fadhel School of Human Development & Techno-communication Universiti Malaysia Perlis Malaysia School of Computer and Communication Engineering Universiti Malaysia Perlis Malaysia Computer Technical Engineering Alkitab University Iraq School of Computing Universiti Utara Malaysia Malaysia Research Laboratory of Electronics Massachusetts Institute of Technology Cambridge Massachusetts USA Computer Science Department College of Computer Science and Information Technology Kirkuk University Iraq Department of Computer and Information Systems National Institute of Administrative Science Yemen

Space division multiplexing, in conjunction with wavelength division multiplexing, is a powerful mechanism that increases spatial channels significantly in a single optical fiber. Spiral Phased-Laguerre-Gaussian (SP-LG) modes indicate that they effectively reduce mode coupling, thereby increasing the channel response and performance positively. However, mode-coupling influence optical fiber system leads to inter-symbol interference (ISI) between the channels and reduces both capacity and distance. In this paper, we apply the SP-LG modes in a space wavelength division multiplexing over a few-mode fiber system. The results demonstrate significant improvements in reducing channels effects and ISI. The performance evaluations are based on the bit-error-rate (BER), eye diagram and spectrum analyzer.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Systematic review of Multi-Mode Fiber based on Dimensional Code in Optical-CDMA

引用

Journal of Physics: Conference Series 2021年第1期1860卷

作者： Alaan Ghazi S.A. Aljunid Syed Zulkarnain Syed Idrus C.B.M Rashidi Aras Al-dawoodi Baban A. Mahmood Alaa Fareed Mohammed U. Zaenal Nameer Hashim Qasim Ranjdr M. Rafeeq Faculty of Applied and Human Sciences University Malaysia Perlis Malaysia School of Computer and Communication Engineering University Malaysia Perlis Malaysia Computer Technical Engineering Al-Qalam university College Iraq Computer Science Department College of Computer Science and Information Technology Kirkuk University Kirkuk Iraq School of Computing University Utara Malaysia Malaysia

This paper deals with optical code division multiple access (optical-CDMA) and provides a general analysis of multi-mode fiber (MMF). The purpose of this work is to classify the works in the literature that are related to Optical-CDMA based on MMF and to find the limitation of the researches done in this field. Several challenges that occur in the medium such as multiple-access interference (MAI), pulse dispersion (PD) and nonlinearity in optical fibers deteriorate system performances and become a major performance-limiting factor.

关键词：

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：