检索结果-内蒙古大学图书馆

arXiv 2020年

作者： Li, Xiaoming Chen, Chaofeng Zhou, Shangchen Lin, Xianhui Zuo, Wangmeng Zhang, Lei Faculty of Computing Harbin Institute of Technology China Department of Computer Science University of Hong Kong Hong Kong School of Computer Science and Engineering Nanyang Technological University Singapore DAMO Academy Alibaba Group China Peng Cheng Lab Shenzhen China Department of Computing Hong Kong Polytechnic University Hong Kong

Recent reference-based face restoration methods have received considerable attention due to their great capability in recovering high-frequency details on real low-quality images. However, most of these methods require a high-quality reference image of the same identity, making them only applicable in limited scenes. To address this issue, this paper suggests a deep face dictionary network (termed as DFDNet) to guide the restoration process of degraded observations. To begin with, we use K-means to generate deep dictionaries for perceptually significant face components (i.e., left/right eyes, nose and mouth) from high-quality images. Next, with the degraded input, we match and select the most similar component features from their corresponding dictionaries and transfer the high-quality details to the input via the proposed dictionary feature transfer (DFT) block. In particular, component AdaIN is leveraged to eliminate the style diversity between the input and dictionary features (e.g., illumination), and a confidence score is proposed to adaptively fuse the dictionary feature to the input. Finally, multi-scale dictionaries are adopted in a progressive manner to enable the coarse-to-fine restoration. Experiments show that our proposed method can achieve plausible performance in both quantitative and qualitative evaluation, and more importantly, can generate realistic and promising results on real degraded images without requiring an identity-belonging reference. The source code and models are available at https://***/csxmli2016/DFDNet. Copyright © 2020, The Authors. All rights reserved.

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Lattice investigations of the chimera baryon spectrum in the Sp(4) gauge theory

引用

Physical Review D 2024年第9期109卷 094512-094512页

作者： Ed Bennett Deog Ki Hong Ho Hsiao Jong-Wan Lee C.-J. David Lin Biagio Lucini Maurizio Piai Davide Vadacchino Swansea Academy of Advanced Computing Swansea University Fabian Way SA1 8EN Swansea Wales United Kingdom Department of Physics Pusan National University Busan 46241 Korea Extreme Physics Institute Pusan National University Busan 46241 Korea Institute of Physics National Yang Ming Chiao Tung University 1001 Ta-Hsueh Road Hsinchu 30010 Taiwan Particle Theory and Cosmology Group Center for Theoretical Physics of the Universe Institute for Basic Science (IBS) Daejeon 34126 Korea Center for High Energy Physics Chung-Yuan Christian University Chung-Li 32023 Taiwan Centre for Theoretical and Computational Physics National Yang Ming Chiao Tung University 1001 Ta-Hsueh Road Hsinchu 30010 Taiwan Department of Mathematics Faculty of Science and Engineering Swansea University Fabian Way SA1 8EN Swansea Wales United Kingdom Department of Physics Faculty of Science and Engineering Swansea University Singleton Park SA2 8PP Swansea Wales United Kingdom Centre for Mathematical Sciences University of Plymouth Plymouth PL4 8AA United Kingdom

We report the results of lattice numerical studies of the Sp(4) gauge theory coupled to fermions (hyperquarks) transforming in the fundamental and two-index antisymmetric representations of the gauge group. This strongly coupled theory is the minimal candidate for the ultraviolet completion of composite Higgs models that facilitate the mechanism of partial compositeness for generating the top-quark mass. We measure the spectrum of the low-lying, half-integer spin, bound states composed of two fundamental and one antisymmetric hyperquarks, dubbed chimera baryons, in the quenched approximation. In this first systematic, nonperturbative study, we focus on the three lightest parity-even chimera-baryon states, in analogy with QCD, denoted as ΛCB, ΣCB (both with spin 1/2), and ΣCB* (with spin 3/2). The spin-1/2 such states are candidates of the top partners. The extrapolation of our results to the continuum and massless-hyperquark limit is performed using formulas inspired by QCD heavy-baryon Wilson chiral perturbation theory. Within the range of hyperquark masses in our simulations, we find that ΣCB is not heavier than ΛCB.

关键词： Composite models Extensions of Higgs sector Lattice field theory Strong interaction

来源：评论

学校读者我要写书评

暂无评论

How Trustworthy are Performance Evaluations for Basic Vision Tasks?

arXiv

引用

arXiv 2020年

作者： Nguyen, Tran Thien Dat Rezatofighi, Hamid Vo, Ba-Ngu Vo, Ba-Tuong Savarese, Silvio Reid, Ian School of Electrical Engineering Computing and Mathematical Sciences Curtin University Australia Faculty of Information Technology Monash University Australia Stanford University United States School of Computer Science University of Adelaide Australia

This paper examines performance evaluation criteria for basic vision tasks involving sets of objects namely, object detection, instance-level segmentation and multi-object tracking. The rankings of algorithms by an existing criterion can fluctuate with different choices of parameters, e.g. Intersection over Union (IoU) threshold, making their evaluations unreliable. More importantly, there is no means to verify whether we can trust the evaluations of a criterion. This work suggests a notion of trustworthiness for performance criteria, which requires (i) robustness to parameters for reliability, (ii) contextual meaningfulness in sanity tests, and (iii) consistency with mathematical requirements such as the metric properties. We observe that these requirements were overlooked by many widely-used criteria, and explore alternative criteria using metrics for sets of shapes. We also assess all these criteria based on the suggested requirements for trustworthiness. Copyright © 2020, The Authors. All rights reserved.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Multicriteria decision-making framework for robust energy management AI solutions

引用

Sustainable Futures 2025年 10卷

作者： Salem Garfan A.H. Alamoodi Suliana Sulaiman O.S. Albahri A.S. Albahri Iman Mohamad Sharaf Faculty of Computing and Meta-Technology (FKMT) Universiti Pendidikan Sultan Idris Perak Malaysia Applied Science Research Center Applied Science Private University Amman Jordan GUST Engineering and Applied Innovation Research Center (GEAR) Gulf University for Science and Technology Mishref Kuwait Computer Techniques Engineering Department Mazaya University College Nasiriyah Iraq Victorian Institute of Technology Melbourne Australia Technical Engineering College Imam Ja'afar Al-Sadiq University (IJSU) Baghdad Iraq University of Information Technology and Communications (UOITC) Baghdad Iraq Department of Basic Sciences Higher Technological Institute Tenth of Ramadan City Egypt

In recent years, global attention has been shifted toward energy issues, prompting significant support from major countries toward nearly zero-energy structures. However, this transition faces challenges, particularly regarding the financial implications of implementation despite diverse methodologies. The emergence of artificial intelligence (AI) has catalyzed advancements in energy conservation and management, leading to the development of numerous smart energy management systems leveraging the internet of things and AI methodologies. Various machine learning (ML) models have been utilized for energy-saving and consumption prediction solutions, posing challenges in selecting the most effective model. Multicriteria decision-making (MCDM) models offer a solution to this challenge and have been applied across domains, including energy management. This study aims to utilize MCDM approaches, specifically the fuzzy-weighted zero-inconsistency (FWZIC) and combinative distance-based assessment (CODAS) methods, to select the best energy management ML model. The study used data for eight ML alternatives based on the assessments by three field experts with respect to five criteria. The results of the criteria evaluation weights indicate that robustness ( C 1 ) received the highest criterion weight with a value of 0.298 . The results of the alternative evaluation indicated the hybrid artificial neural network ( A 1 ) as the best model for performance. Additionally, a comparison analysis was performed between FWZIC and various criteria weighting methods, as well as between CODAS and different alternative ranking methods. This framework enables decisionmakers to consider an AI solution that optimizes for accuracy, costs, and resilience in a move towards zero-energy infrastructure.

关键词： MCDM FWZIC CODAS Energy management Machine learning IoT

来源：评论

学校读者我要写书评

暂无评论

Fungal automata

arXiv

引用

arXiv 2020年

作者： Adamatzky, Andrew Goles, Eric Martínez, Genaro J. Tsompanas, Michail-Antisthenis Tegelaar, Martin Wosten, Han A.B. Unconventional Computing Laboratory UWE Bristol United Kingdom Faculty of Engineering and Science University of Adolfo Ibáñez Santiago Chile High School of Computer Science National Polytechnic Institute Mexico Microbiology Department University of Utrecht Utrecht Netherlands

We study a cellular automaton (CA) model of information dynamics on a single hypha of a fungal mycelium. Such a filament is divided in compartments (here also called cells) by septa. These septa are invaginations of the cell wall and their pores allow for flow of cytoplasm between compartments and hyphae. The septal pores of the fungal phylum of the Ascomycota can be closed by organelles called Woronin bodies. Septal closure is increased when the septa become older and when exposed to stress conditions. Thus, Woronin bodies act as informational flow valves. The one dimensional fungal automata is a binary state ternary neighbourhood CA, where every compartment follows one of the elementary cellular automata (ECA) rules if its pores are open and either remains in state ‘0’ (first species of fungal automata) or its previous state (second species of fungal automata) if its pores are closed. The Woronin bodies closing the pores are also governed by ECA rules. We analyse a structure of the composition space of cell-state transition and pore-state transitions rules, complexity of fungal automata with just few Woronin bodies, and exemplify several important local events in the automaton dynamics. Copyright © 2020, The Authors. All rights reserved.

关键词： Cellular automata

来源：评论

学校读者我要写书评

暂无评论

Learning Uncertainties in Wheel Odometry for Vehicular Localisation in GNSS Deprived Environments

Learning Uncertainties in Wheel Odometry for Vehicular Local...

引用

International Conference on Machine Learning and Applications (ICMLA)

作者： Uche Onyekpe Vasile Palade Stratis Kanarachos Stavros-Richard G. Christopoulos Research Centre for Data Science and Institute for Future Transport and Cities Coventry University Coventry United Kingdom Research Centre for Data Science Coventry University Coventry United Kingdom Faculty of Engineering and Computing Coventry University Coventry United Kingdom

ISBN: (数字)9781728184708

ISBN: (纸本)9781728184715

Inertial Navigation Systems (INS) are commonly used to localise vehicles in the absence of Global Navigation Satellite Systems (GNSS) signals. However, they are plagued by noises, which grow exponentially over time during the triple integration computation, leading to a poor navigation solution. We explore the wheel encoder as an alternative to the accelerometer of the INS for positional tracking, and for the first time investigate the capability of deep learning using the Long Short-Term Memory (LSTM) neural network to learn the uncertainty inherent in the wheel speed measurements. These uncertainties could be manifested as changes in the tyre size or pressure, or wheel slips as a result of worn out tyres or wet/muddy road drive. The proposed solution has less integration steps in its computation, therefore providing the potential for a more accurate positioning estimation. Through a performance evaluation on several challenging scenarios for vehicular driving, such as hard braking, quick changes in vehicular acceleration, and wet/muddy road driving, we show that the wheel speed-based positioning approach is able to achieve up to 81.46 % improvement compared to the INS accelerometer approach.

关键词： Accelerometers Global navigation satellite system Uncertainty Roads Wheels Tires Velocity measurement

来源：评论

学校读者我要写书评

暂无评论

Deriving QoE in systems: from fundamental relationships to a QoE-based Service-level Quality Index

引用

Quality and User Experience 2020年第1期5卷 1-17页

作者： Hoßfeld, Tobias Heegaard, Poul E. Skorin-Kapov, Lea Varela, Martín University of Würzburg Chair of Communication Networks Würzburg Germany NTNU - Norwegian University of Science and Technology Department of Information Security and Communication Technology Trondheim Norway University of Zagreb Faculty of Electrical Engineering and Computing Zagreb Croatia Profilence Oulu Finland

With Quality of Experience (QoE) research having made significant advances over the years, service and network providers aim at user-centric evaluation of the services provided in their system. The question arises how to derive QoE in systems. In the context of subjective user studies conducted to derive relationships between influence factors and QoE, user diversity leads to varying distributions of user rating scores for different test conditions. Such models are commonly exploited by providers to derive various QoE metrics in their system, such as expected QoE, or the percentage of users rating above a certain threshold. The question then becomes how to combine (a) user rating distributions obtained from subjective studies, and (b) system parameter distributions, so as to obtain the actual observed QoE distribution in the system? Moreover, how can various QoE metrics of interest in the system be derived? We prove fundamental relationships for the derivation of QoE in systems, thus providing an important link between the QoE community and the systems community. In our numerical examples, we focus mainly on QoE metrics. We furthermore provide a more generalized view on quantifying the quality of systems by defining a QoE-based Service-level Quality Index. This index exploits the fact that quality can be seen as a proxy measure for utility. Following the assumption that not all user sessions should be weighted equally, we aim to provide a generic framework that can be utilized to quantify the overall utility of a service delivered by a system.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An iris segmentation technique using black hole search method and canny edge detector

引用

AIP Conference Proceedings 2024年第1期2867卷

作者： Sani Sufyan Bature Danlami Muktar Sapi’ee Jamel Ibrahim M. Sulaiman Sukono Sukono Aceng Sambas Department of Computer Science Yusuf Maitama Sule University Kano Nigeria Faculty of Computer Science and Information Technology Universiti Tun Hussien On Malaysia Johor Malaysia Institute of Strategic Industrial Decision Modelling (ISIDM) School of Quantitative Sciences Universiti Utara Malaysia UUM Sintok 06010 Kedah Malaysia Department of Mathematics Universitas Padjadjaran Sumedang Indonesia Faculty of Informatics and Computing Universiti Sultan Zainal Abidin Campus Besut 22200 Terengganu Malaysia Department of Mechanical Engineering Universitas Muhammadiyah Tasikmalaya Tasikmalaya Indonesia

Biometric is the most fundamental and efficient technique used in terms of recognizing individuals uniquely. As we have two types of biometric; one on physical and the other in terms behavioral characteristics. Iris segmentation is a crucial stage in iris recognition systems since it determines the accuracy of all future phases and can be segmented using a variety of techniques. There are different iris segmentation techniques, but the most widely used ones are the circular Hough transform and Daugman’s algorithm which are commonly employed in commercial and research problems involving iris recognition systems. In iris recognition system, the time it took to detect the iris and the accuracy with which it was located are both important aspects. Due to low in terms of accuracy we have suggested a different approach of iris segmentation based on the black hole search method and canny edge detector in this research. The proposed approach is tested using CASIA and MMU Database iris images. This technique is effective in terms of the time it takes to detect an eye’s iris, as it directly utilizes intensity and shape. Also, we can detect the iris of an eye much faster than the standard technique with the help of image processing.

关键词：

来源：评论

学校读者我要写书评

暂无评论

CaneFX-An Interactive White Cane Learning Tool for People with Visual Impairment

CaneFX-An Interactive White Cane Learning Tool for People wi...

引用

IEEE Region 10 Humanitarian Technology Conference (R10-HTC)

作者： Derrick Kuo Xiong Ling Bee Theng Lau Aylwin Bing Chun Chai Lil Deverell Michael Evans Faculty of Engineering Computing and Science Swinburne University of Technology Sarawak Campus Kuching Sarawak Malaysia Faculty of Health Arts and Design Swinburne University of Technology Hawthorn Campus Orientation and Mobility (O&M) Specialist Guide Dogs Victoria Australia

ISBN: (数字)9781728111100

ISBN: (纸本)9781728111117

This paper discusses an interactive white cane learning tool for children with visual impairment to familiarize themselves with the use of the white cane. A prototype, named CaneFX, was designed based on motion capture technology which utilizes an accelerometer to understand the motion of the white cane. A microcontroller was implemented to process the data obtained from the accelerometer. Three modes were implemented to detect different white cane motions which are sweeping, tapping and hitting motions and for each motion, a sound is associated with it. Experimental testing was conducted to find an optimal setup of the proposed prototype and evaluate its usability. The results show that the prototype is capable of detecting the motions in real-time with high accuracy on a rough floor surface.

关键词： Visualization Prototypes Tools Real-time systems Usability Floors Testing

来源：评论

学校读者我要写书评

暂无评论

Review mobile sensing in substance use research: A scoping review

引用

Telemedicine and e-Health 2020年第10期26卷 1191-1196页

作者： Lauvsnes, Anders Dahlen Forsmo Langaas, Mette Toussaint, Pieter Grawe, Rolf W. Department of Mental Health Faculty of Medicine and Health Sciences Norwegian University of Science and Technology PO Box 8905 TrondheimNO-7491 Norway NKS Kvamsgrindkollektivet AS Trondheim Norway Department of Mathematical Sciences Faculty of Information Technology and Electrical Engineering Norwegian University of Science and Technology Trondheim Norway Norwegian Computing Center Oslo Norway Department of Computer Science Faculty of Information Technology and Electrical Engineering Norwegian University of Science and Technology Trondheim Norway SINTEF SINTEF Digital Trondheim Norway Divison of Psychiatry Department of Research and Development St. Olavs University Hospital Trondheim Norway

Background: Addictive disorders and substance use are significant health challenges worldwide, and relapse is a core component of addictive disorders. The dynamics surrounding relapse and especially the immediate period before it occurs is only partly understood, much due to difficulties collecting reliable and sufficient data from this narrow period. Mobile sensing has been an important way to improve data quality and enhance predictive capabilities for symptom worsening within physical and mental health care, but is less developed within substance use research. Methodology: This scoping review aimed to reviewing the currently available research on mobile sensing of substance use and relapse in substance use disorders. The search was conducted in January 2019 using PubMed and Web of science. Results: Six articles were identified, all concerning subjects using alcohol. In the studies a range of mobile sensors and derived aggregated features were employed. Data collected through mobile sensing were predominantly used to make dichotomous inference on ongoing substance use or not and in some cases on the quantity of substance intake. Only one of the identified studies predicted later substance use. A range of statistical machine learning techniques was employed. Conclusions: The research on mobile sensing in this field remains scarce. The issues requiring further attention include more research on clinical populations in naturalistic settings, use of a priori knowledge in statistical modeling, focus on prediction of substance use rather than purely identification, and finally research on other substances than alcohol. © 2020 Mary Ann Liebert, Inc.

关键词： Telemedicine

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：