检索结果-内蒙古大学图书馆

arXiv 2021年

作者： Qin, Xuebin Fan, Deng-Ping Huang, Chenyang Diagne, Cyril Zhang, Zichen Sant'Anna, Adrià Cabeza Suàrez, Albert Jagersand, Martin Shao, Ling The Department of Computing Science University of Alberta EdmontonABT6G 2R3 Canada Abu Dhabi United Arab Emirates The Department of Computing Science University of Alberta EdmontonAB Canada Init ML The Department of Computing Science University of Alberta EdmontonAB Canada The Department of Computer Science Polytechnic University of Catalonia BarcelonaTech Barcelona Spain The Department of Software Engineering Polytechnic University of Catalonia BarcelonaTech Barcelona Spain The Department of Computing Science University of Alberta EdmontonAB Canada

Although deep models have greatly improved the accuracy and robustness of image segmentation, obtaining segmentation results with highly accurate boundaries and fine structures is still a challenging problem. In this paper, we propose a simple yet powerful Boundary-Aware Segmentation Network (BASNet), which comprises a predict-refine architecture and a hybrid loss, for highly accurate image segmentation. The predict-refine architecture consists of a densely supervised encoder-decoder network and a residual refinement module, which are respectively used to predict and refine a segmentation probability map. The hybrid loss is a combination of the binary cross entropy, structural similarity and intersection-over-union losses, which guide the network to learn three-level (i.e., pixel-, patch- and map- level) hierarchy representations. We evaluate our BASNet on two reverse tasks including salient object segmentation, camouflaged object segmentation, showing that it achieves very competitive performance with sharp segmentation boundaries. Importantly, BASNet runs at over 70 fps on a single GPU which benefits many potential real applications. Based on BASNet, we further developed two (close to) commercial applications: AR COPY & PASTE, in which BASNet is integrated with augmented reality for "COPYING" and "PASTING" real-world objects, and OBJECT CUT, which is a web-based tool for automatic object background removal. Both applications have already drawn huge amount of attention and have important real-world impacts. The code and two applications will be publicly available at: https://***/NathanUA/BASNet. © 2021, CC BY.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Information Freshness-Oriented Relay Selection in Two-Way Relay Networks: A Multi-Armed Bandit Approach

Information Freshness-Oriented Relay Selection in Two-Way Re...

引用

Consumer Communications and Networking Conference, CCNC IEEE

作者： Guanyu Chen Tse-Tin Chan Haoyuan Pan Kin-Hon Ho College of Computer Science and Software Engineering Shenzhen University Shenzhen China Department of Mathematics and Information Technology The Education University of Hong Kong Hong Kong SAR China Department of Computing The Hang Seng University of Hong Kong Hong Kong SAR China

We study the relay selection problem for information freshness-oriented two-way relay networks (TWRNs) operated with physical-layer network coding (PNC). Information freshness is quantified by age of information (AoI), defined as the time elapsed since the generation time of the latest received information update. Since PNC leads to mutual wireless interference in TWRNs, this complicates the relay selection for users. To address this problem, this paper formulates relay selection as a multi-armed bandit (MAB) to dynamically learn the optimal mapping between users and relays. Specifically, the two end users act as agents, interacting with the environment, receiving feedback as rewards in the MAB, and then optimizing the system-level AoI performance through the learning experience. Simulation results demonstrate that the proposed MAB approach significantly outperforms the conventional relay selection scheme.

关键词： Wireless communication Protocols Heuristic algorithms Simulation Relay networks (telecommunication) Interference Network coding

来源：评论

学校读者我要写书评

暂无评论

AD-PU: A Novel Approach for Automated Identification of the Outliers in User Interface Testing (UAT)

AD-PU: A Novel Approach for Automated Identification of the ...

引用

International Automatic Testing Conference, AUTOTESTCON

作者： S.M.N.S.K Seneviratne Victoria Penenco Dharshana Kasthurirathna Faculty of Graduate Studies and Research Sri Lanka Institute of Information Technology Sri Lanka UAT London Stock Exchange Group London Dept. of Computer Science and Software Engineering Faculty of Computing Sri Lanka Institute of Information Technology Sri Lanka

User acceptance testing (UAT) is the process that validates the system under test (SUT) behaves according to the business requirements. A User would use the graphical user interface to interact with the underlying code. With the improvement of various devices, end-user testing has become even more complex and time consuming. Every user has a unique interaction pattern. Due to this expected test coverage would not be met by focusing only on the functionality itself. This research is to address the issue of UAT test automation coverage and reduce defect leakage in production environments. The proposed automation solution is to identify more defects in the UAT static testing phase and make the system under test more user friendly before handing the product to the consumers. The proposed solution use Machine learning approach to identify user behaviors that does not match the proposed new functionality. The proposed AD-PU model would evaluate non-prominent user behaviours as per perceived usefulness which would effect the decision to accept the functionality as user acceptable or not.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Boundary-Guided Learning for Gene Expression Prediction in Spatial Transcriptomics

Boundary-Guided Learning for Gene Expression Prediction in S...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Mingcheng Qu Yuncong Wu Donglin Di Anyang Su Tonghua Su Yang Song Lei Fan Faculty of Computing Harbin Institute of Technology Harbin China School of Astronautics Harbin Institute of Technology Harbin China Space AI Li Auto Beijing China College of Software Jilin University Changchun China Computer Science and Engineering UNSW Sydney Australia

ISBN: (数字)9798350386226

ISBN: (纸本)9798350386233

Spatial transcriptomics (ST) has emerged as an advanced technology that provides spatial context to gene expression. Recently, deep learning-based methods have shown the capability to predict gene expression from WSI data using ST data. Existing approaches typically extract features from images and the neighboring regions using pretrained models, and then develop methods to fuse this information to generate the final output. However, these methods often fail to account for the cellular structure similarity, cellular density and the interactions within the *** this paper, we propose a framework named BG-TRIPLEX, which leverages boundary information extracted from pathological images as guiding features to enhance gene expression prediction from WSIs. Specifically, our model consists of three branches: the spot, in-context and global branches. In the spot and in-context branches, boundary information, including edge and nuclei characteristics, is extracted using pretrained models. These boundary features guide the learning of cellular morphology and the characteristics of microenvironment through Multi-Head Cross-Attention. Finally, these features are integrated with global features to predict the final *** experiments were conducted on three public ST datasets. The results demonstrate that our BG-TRIPLEX consistently outperforms existing methods in terms of Pearson Correlation Coefficient (PCC). This method highlights the crucial role of boundary features in understanding the complex interactions between WSI and gene expression, offering a promising direction for future research. Codes are available at: https://***/WcloudC0416/BG-TRIPLEX

关键词： Learning systems Pathology Technological innovation Image edge detection Transcriptomics Morphology Predictive models Feature extraction Gene expression Data mining

来源：评论

学校读者我要写书评

暂无评论

Error mitigation for quantum kernel based machine learning methods on IonQ and IBM quantum computers

arXiv

引用

arXiv 2022年

作者： Moradi, Sasan Brandner, Christoph Coggins, Macauley Wille, Robert Drexler, Wolfgang Papp, Laszlo Center for Medical Physics and Biomedical Engineering Medical University of Vienna Vienna Austria Quantum Computing UK Scarborough North Yorkshire United Kingdom Technical University of Munich Design Automation Munich Germany Software Competence Center Hagenberg GmbH Hagenberg Austria

Kernel methods are the basis of most classical machine learning algorithms such as Gaussian Process (GP) and Support Vector Machine (SVM). computing kernels using noisy intermediate scale quantum (NISQ) devices has attracted considerable attention due to recent progress in the design of NISQ devices. However noise and errors on current NISQ devices can negatively affect the predicted kernels. In this paper we utilize two quantum kernel machine learning (ML) algorithms to predict the labels of a Breast Cancer dataset on two different NISQ devices: quantum kernel Gaussian Process (qkGP) and quantum kernel Support Vector Machine (qkSVM). We estimate the quantum kernels on the 11 qubit IonQ and the 5 qubit IBMQ Belem quantum devices. Our results demonstrate that the predictive performances of the error mitigated quantum kernel machine learning algorithms improve significantly compared to their non-error mitigated counterparts. On both NISQ devices the predictive performances became comparable to those of noiseless quantum simulators and their classical counterparts. © 2022, CC BY.

关键词： Errors

来源：评论

学校读者我要写书评

暂无评论

Using Metamorphic Relation Violation Regions to Support a Simulation Framework for the Process of Metamorphic Testing

Using Metamorphic Relation Violation Regions to Support a Si...

引用

IEEE Annual International Computer software and Applications Conference (COMPSAC)

作者： Zhihao Ying Anthony Bellotti Dave Towey Tsong Yueh Chen Zhi Quan Zhou School of Computer Science University of Nottingham Ningbo China Zhejiang People&#x0027 s Republic of China Department of Computer Science and Software Engineering Swinburne University of Technology Hawthorn VIC Australia School of Computing and Information Technology University of Wollongong Wollongong NSW Australia

ISBN: (数字)9781665488105

ISBN: (纸本)9781665488112

Metamorphic testing (MT) has been growing in pop-ularity, but it can still be quite challenging and time-consuming to assess its performance. Typical approaches to performance assessment can require a series of steps, and depend on a variety of factors, often requiring serendipity. This can be a bottleneck for some aspects of MT research. Central to MT, metamorphic relations (MRs) represent necessary properties of the system under test (SUT). In traditional software testing, simulations are often employed to examine and compare the performance of dif-ferent testing strategies. However, these simulations are typically designed based on the assumed availability (and applicability) of a test oracle - a mechanism to decide the correctness of the SUT output or behaviour. A key reason for the popularity of MT is its proven record of effective software testing, without the need for a test oracle. This strength, however, also means that traditional ways of using simulations to analyse software testing approaches are not applicable for MT. This lack of cheap and fast ways to conduct simulation analyses of MT is a hurdle for many aspects of MT research, and may be an obstacle to its more widespread adoption. To address this, in this paper we introduce the concept of MR-violation regions (MRVRs), and show how they can be used for a certain category of MRs, Deterministic MRs (DMRs), to build simulation tools for MT. We analyse the differences between MRVRs and traditional, oracle-defined failure regions; and report on a preliminary case study exploring MRVRs in numerical-input-domain systems from previous MT studies. We anticipate that the proposed MT simulation framework may facilitate more research into MT, and may help lead to its more widespread adoption.

关键词： software testing Analytical models Strips Conferences Computational modeling software quality Pressing

来源：评论

学校读者我要写书评

暂无评论

Secure and Efficient Multi-Attribute Range Queries based on Comparable Inner Product Encoding

Secure and Efficient Multi-Attribute Range Queries based on ...

引用

IEEE Conference on Communications and Network Security (CNS)

作者： Qin Liu SiXia Wu Shuyu Pei Jie Wu Tao Peng Guojun Wang College of Computer Science and Electronic Engineering Hunan University P. R. China Center for Networked Computing Temple University Philadelphia PA USA School of Computer Science and Educational Software Guangzhou University P. R. China

Encryption, a powerful tool for data security, has been widely applied to protect sensitive data stored on untrusted cloud servers. One important problem in such an environment is how to support advanced query predicates, such as range queries, over an encrypted data set in an efficient and secure way. Order-preserving encryption (OPE) produces ciphertexts that preserve the order of their plaintexts and performs range queries directly on ciphertexts. However, ideally secure OPE schemes are inefficient (interactive and stateful), because they either ask for extensive client-to-server interactions or require a large persistent client storage that relates to the size of the data set. In this paper, we propose a comparable inner product encoding (CIPE) scheme to support multi-attribute range queries over encrypted data. Our main idea is to encode data and query values as encrypted vectors so that order comparison is realized by calculating the vector's inner product. Compared with existing OPE schemes, our scheme has the following merits: 1) High efficiency. It allows a client to retrieve data of interest in one round without maintaining any local state. 2) Enhanced security. It achieves ideal security while effectively resisting inference attacks that existing OPE schemes are vulnerable to. Extensive experiments conducted on a realworld, large-scale data set verify the effectiveness of our scheme.

关键词： Servers Indexes Cloud computing Encryption Data privacy

来源：评论

学校读者我要写书评

暂无评论

A Novel Self-Adaptive Fault-Tolerant Mechanism and Its Application for a Dynamic Pervasive computing Environment

A Novel Self-Adaptive Fault-Tolerant Mechanism and Its Appli...

引用

IEEE International Symposium on Object/Component/Service-Oriented Real-Time Distributed computing Workshops (ISORCW)

作者： Haibin Cai Chao Peng Linhua Jiang Yue Zhang Shanghai Key Laboratory of Trustworthy Computing Beijing Jiaotong University Beijing China State Key Laboratory of Rail Traffic Control and Safety Beijing Jiaotong University Beijing China Software Engineering Institute East China Jiao Tong University Shanghai China

In pervasive computing system, the increasing dynamic and complexity of software and hardware resources and frequentative interaction among function components make fault-tolerant design very challenging. In this paper, we propose a novel self-adaptive fault-tolerant mechanism for a dynamic pervasive computing environment such as mobile ad hoc network. In our approach, the self-adaptive fault-tolerant mechanism is dynamically built according to various types of detected faults based on continuous monitoring and analysis of the component states. We put forward the architecture of fault-tolerant system and the policy-based fault-tolerant scheme, which adopts three-dimensional array of core features to capture spatial and temporal variability and the Event-Condition-Action rules. The mentioned mechanism has been designed and implemented as self-adaptive fault-tolerant middleware, shortly called SAFTM, on a preliminary prototype for a dynamic pervasive computing environment such as mobile ad hoc network. We have performed the experiments to evaluate the efficiency of the fault-tolerant mechanism. The results of the experiments show that the performance of the self-adaptive fault tolerant mechanism is realistic.

关键词： Fault tolerance Fault tolerant systems Pervasive computing Monitoring Mobile communication Hardware

来源：评论

学校读者我要写书评

暂无评论

Performance and energy-aware bi-objective tasks scheduling for cloud data centers

引用

Procedia Computer Science 2022年 197卷 238-246页

作者： Huned Materwala Leila Ismail Intelligent Distributed Computing and Systems Research Laboratory Department of Computer Science and Software Engineering College of Information Technology United Arab Emirates University Al Ain Abu Dhabi 15551 United Arab Emirates National Water and Energy Center United Arab Emirates University Al Ain Abu Dhabi United Arab Emirates

Cloud computing enables remote execution of users’ tasks. The pervasive adoption of cloud computing in smart cities’ services and applications requires timely execution of tasks adhering to Quality of Services (QoS). However, the increasing use of computing servers exacerbates the issues of high energy consumption, operating costs, and environmental pollution. Maximizing the performance and minimizing the energy in the cloud data center is challenging. In this paper, we propose a performance and energy optimization bi-objective algorithm to trade off the contradicting performance and energy objectives. An evolutionary algorithm-based multi-objective optimization is for the first time proposed using system performance counters. The performance of the proposed model is evaluated using a realistic cloud dataset in a cloud computing environment. Our experimental results achieve higher performance and lower energy consumption compared to a state-of-the-art algorithm.

关键词： Autonomous agents cloud computing energy-efficiency evolutionary algorithm genetic algorithm quality of service multi-objective optimization performance

来源：评论

学校读者我要写书评

暂无评论

Why Does Little Robustness Help? A Further Step Towards Understanding Adversarial Transferability

arXiv

引用

arXiv 2023年

作者： Zhang, Yechao Hu, Shengshan Zhang, Leo Yu Shi, Junyu Li, Minghui Liu, Xiaogeng Wan, Wei Jin, Hai School of Cyber Science and Engineering Huazhong University of Science and Technology China School of Software Engineering Huazhong University of Science and Technology China School of Information and Communication Technology Griffith University Australia School of Computer Science and Technology Huazhong University of Science and Technology China National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Hubei Key Laboratory of Distributed System Security China Hubei Engineering Research Center on Big Data Security China Cluster and Grid Computing Lab

Adversarial examples for deep neural networks (DNNs) have been shown to be transferable: examples that successfully fool one white-box surrogate model can also deceive other black-box models with different architectures. Although a bunch of empirical studies have provided guidance on generating highly transferable adversarial examples, many of these findings fail to be well explained and even lead to confusing or inconsistent advice for practical use. In this paper, we take a further step towards understanding adversarial transferability, with a particular focus on surrogate aspects. Starting from the intriguing "little robustness" phenomenon, where models adversarially trained with mildly perturbed adversarial samples can serve as better surrogates for transfer attacks, we attribute it to a trade-off between two dominant factors: model smoothness and gradient similarity. Our research focuses on their joint effects on transferability, rather than demonstrating the separate relationships alone. Through a combination of theoretical and empirical analyses, we hypothesize that the data distribution shift induced by off-manifold samples in adversarial training is the reason that impairs gradient similarity. Building on these insights, we further explore the impacts of prevalent data augmentation and gradient regularization on transferability and analyze how the trade-off manifest in various training methods, thus building a comprehensive blueprint for the regulation mechanisms behind transferability. Finally, we provide a general route for constructing superior surrogates to boost transferability, which optimizes both model smoothness and gradient similarity simultaneously, e.g., the combination of input gradient regularization and sharpness-aware minimization (SAM), validated by extensive experiments. In summary, we call for attention to the united impacts of these two factors for launching effective transfer attacks, rather than optimizing one while ignoring the other,

关键词： Deep neural networks

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：