检索结果-内蒙古大学图书馆

arXiv 2021年

作者： Yang, Kunping Tong, Xin-Yi Xia, Gui-Song Shen, Weiming Zhang, Liangpei State Key Lab. of Liesmars Wuhan University Wuhan430072 China Wessling82234 Germany Technical University of Munich Munchen80333 Germany National Engineering Research Center for Multimedia Software School of Computer Science Institute of Artificial Intelligence

Targeting at depicting land covers with pixel-wise semantic categories, semantic segmentation in remote sensing images needs to portray diverse distributions over vast geographical locations, which is difficult to be achieved by the homogeneous pixel-wise forward paths in the architectures of existing deep models. Although several algorithms have been designed to select pixel-wise adaptive forward paths for natural image analysis, it still lacks theoretical supports on how to obtain optimal selections. In this paper, we provide mathematical analyses in terms of the parameter optimization, which guides us to design a method called Hidden Path Selection Network (HPS-Net). With the help of hidden variables derived from an extra mini-branch, HPS-Net is able to tackle the inherent problem about inaccessible global optimums by adjusting the direct relationships between feature maps and pixel-wise path selections in existing algorithms, which we call hidden path selection. For the better training and evaluation, we further refine and expand the 5-class Gaofen Image Dataset (GID-5) to a new one with 15 land-cover categories, i.e., GID-15. The experimental results on both GID-5 and GID-15 demonstrate that the proposed modules can stably improve the performance of different deep structures, which validates the proposed mathematical analyses. Copyright © 2021, The Authors. All rights reserved.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Supercomputer Supported Online Deep Learning Techniques for High Throughput EEG Prediction

Supercomputer Supported Online Deep Learning Techniques for ...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Xiang Li Yazhou Zhang Jing Li Shandong Computer Science Center (National Supercomputing Center in Jinan) Qilu University of Technology (Shandong Academy of Sciences) China State Key Lab. for Novel Software Technology Nanjing University and Software Engineering College Zhengzhou University of Light Industry China Jiuquan Satellite Launch Center China

ISBN: (纸本)9781665429825

Electroencephalogram (EEG) is a precise reflection of the brain activities and has been widely studied in clinical medicine, neuroscience, brain interface, etc. Intelligent prediction of the EEG’s evolution accurately plays important roles in several application areas, such as epilepsy seizure forecasting and neonatal brain monitoring. Nevertheless, when the prediction service is deployed as a business service on the Cloud and open for public usage, there are several problems that need to be resolved: (i) how to design a computation platform to process the high-throughput multi-source EEG data, which arrives sequentially and increases rapidly when the services are rapidly promoted, namely tackling the ‘high-throughput computing’ problem; (ii) how to develop a deep learning model to capture the complex EEG distribution as well as the anomaly patterns that could evolve dynamically, namely tackling the ‘concept drift’ problem for non-stationary EEG signals. To tackle these challenges, we propose an Evolutive Convolutional Neural Network (ECNN) and the corresponding supercomputer supported distributed computation system. The ECNN model can dynamically reweighting the sub-structure of the model from data streams in an online learning fashion, by which the capacity scalab.lity and sustainability are introduced into the model. As far as we know, it is the first work that introduce supercomputer supported online deep learning techniques into EEG prediction research.

关键词： Deep learning Computational modeling Predictive models Brain modeling Throughput Prediction algorithms Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

Private Estimation of Symptom Distribution for Infectious Disease Analysis in Edge Computing

Private Estimation of Symptom Distribution for Infectious Di...

引用

IEEE/IFIP International Conference on Embedded and Ubiquitous Computing, EUC

作者： Xiaotong Wu Xiaolong Xu Shaohua Wan Lianyong Qi State Key Lab. for Novel Software Technology Nanjing University P.R. China School of Computer and Electronic Information Nanjing Normal University P.R. China School of Computer and Software Nanjing University of Information Science & Technology P.R. China School of Information and Safety Engineering Zhongnan University of Economics and Law P.R. China School of Information Science and Engineering Qufu Normal University PR. China

ISBN: (纸本)9781665400374

Distribution estimation of physical symptom is a powerful statistical technique to monitor and predict the situation of infectious diseases. With the widespread popularization of smart devices, edge computing is an efficient computing paradigm, which takes advantage of these devices to implement the safe and fast collection and distribution analysis of physical symptoms. However, the sharing of individuals' data, especially of sensitive information (e.g., age, symptom), inevitably raises the great privacy concerns of people due to the possible leakage and the illegal utilization. It is necessary and important to not only implement the highly intelligent epidemic analysis, but also guarantee the privacy of data. In this paper, we focus on locally private distribution estimation of physical symptom with attribute constraints in edge computing. At first, we present an edge-computing-based framework for distribution estimation of physical symptoms, in which each component undertakes the respective task. Then, we propose a naive privacy algorithm, i.e., NAIVEPRIVDISTEST, to directly perturb the values of quasi-identifying attributes and physical symptoms. Finally, extensive experiments demonstrate that NAIVEPRIVDISTEST has the accurate distribution estimation under the privacy constraints.

关键词： Privacy Data privacy Infectious diseases Estimation Ubiquitous computing Smart devices Computational complexity

来源：评论

学校读者我要写书评

暂无评论

PAC Model Checking of Black-Box Continuous-Time Dynamical Systems

arXiv

引用

arXiv 2020年

作者： Xue, Bai Zhang, Miaomiao Easwaran, Arvind Li, Qin State Key Lab. of Computer Science Institute of Software CAS University of Chinese Academy of Sciences Beijing China School of Software Engineering Tongji University China Singapore Shanghai Key Laboratory of Trustworthy Computing East China Normal University Shanghai China

In this paper we present a novel model checking approach to finite-time safety verification of black-box continuous-time dynamical systems within the framework of probably approximately correct (PAC) learning. The black-box dynamical systems are the ones, for which no model is given but whose states changing continuously through time within a finite time interval can be observed at some discrete time inst.nts for a given input. The new model checking approach is termed as PAC model checking due to incorporation of learned models with correctness guarantees expressed using the terms error probability and confidence. Based on the error probability and confidence level, our approach provides statistically formal guarantees that the time-evolving trajectories of the black-box dynamical system over finite time horizons fall within the range of the learned model plus a bounded interval, contributing to insights on the reachability of the black-box system and thus on the satisfiability of its safety requirements. The learned model together with the bounded interval is obtained by scenario optimization, which boils down to a linear programming problem. Three examples demonstrate the performance of our approach. Copyright © 2020, The Authors. All rights reserved.

关键词： Dynamical systems

来源：评论

学校读者我要写书评

暂无评论

Sum of squares: a new metric for NFV service chain placement in edge computing environments and efficient heuristic algorithms

引用

CCF Transactions on Networking 2020年第2期3卷 140-153页

作者： Chen, Zhiqi Zhang, Sheng Qian, Zhuzhong Wang, Can Xiao, Mingjun Wu, Jie Lu, Sanglu State Key Lab. for Novel Software Technology Nanjing University Nanjing P.R. China School of Computer Science and Technology/Suzhou Institute for Advanced Study University of Science and Technology of China Hefei China Center for Networked Computing Temple University Philadelphia USA

Both network function virtualization (NFV) and edge computing (EC), especially the latter, are attracting more and more attention in recent years. A growing number of network service providers are migrating their services from the cloud to the edge for better QoS services, while the recent researches on NFV also concentrate on deploying NFV services in edge computing networks. However, NFV deployment in edge networks is a troublesome challenge and is fairly alien from conventional NFV deployment problems in data centres. Edge network differs from the data center network in the following two aspects: firstly, edge nodes are constrained in computing capacity, and secondly, the network connections between edge nodes are unstable and dynamic, which may show large variance over time. This means edge computing should be designed for high-efficient use of physical edge nodes’ resources. To address the challenges above, we investigate a new NFV Service Chain Placement problem in edge computing environments (NSCP-EC) in this paper. We first prove that the NSCP-EC problem is NP-complete. Then we propose a new metric which can better measure the capacity utilization rate of physical resources, and analyze its advantages with details. Based on the new metric, we propose two heuristic but efficient algorithms called MINI and MINI-tree. To confirm the performance of the two algorithms, we conduct simulations. The result demonstrates that MINI gains an advantage over genetic algorithm (GA) and MINI-tree orevails over MINI in tree topology conditions in the aspects of physical resource utilization, acceptance rate and running time. Both theoretical analysis and simulation results confirm the feasibility of the algorithms.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Inner-approximating Reach-avoid Sets for Discrete-time Polynomial Systems

Inner-approximating Reach-avoid Sets for Discrete-time Polyn...

引用

IEEE Conference on Decision and Control

作者： Bai Xue Naijun Zhan Martin Fränzle State Key Lab. of Computer Science Institute of Software CAS Beijing China University of Chinese Academy of Sciences Beijing China Carl von Ossietzky Universität Oldenburg Oldenburg Germany

ISBN: (数字)9781728174471

ISBN: (纸本)9781728174488

In this paper we propose a computational method based on semi-definite programming for synthesizing infinite-time reach-avoid sets in discrete-time polynomial systems. An infinite-time reach-avoid set is a set of initial states making the system eventually, i.e., within finite time enter the target set while remaining inside another specified (safe) set during each time step preceding the target hit. The reach-avoid set is first characterized equivalently as a strictly positive sub-level of a bounded value function, which in turn is shown to be a solution to a system of derived equations. The derived equations are further relaxed into a system of inequalities, which is encoded into semi-definite constraints based on the sum-of-squares decomposition for multivariate polynomials, such that the problem of synthesizing inner-approximations of the reach-avoid set can be addressed via solving a semi-definite programming problem. Two examples demonstrate the proposed approach.

关键词： Trajectory Mathematical model Programming 3G mobile communication Switches Tools software

来源：评论

学校读者我要写书评

暂无评论

Align deep features for oriented object detection

arXiv

引用

arXiv 2020年

作者： Han, Jiaming Ding, Jian Li, Jie Xia, Gui-Song State Key Lab. LIESMARS and the Institute of Artificial Intelligence Wuhan University Wuhan430079 China Shanghai Aerospace Electronic Technology Institute Shanghai China National Engineering Research Center for Multimedia Software School of Computer Science and Institute of Artificial Intelligence State Key Lab. LIESMARS Wuhan University Wuhan430072 China

—The past decade has witnessed significant progress on detecting objects in aerial images that are often distributed with large scale variations and arbitrary orientations. However most of existing methods rely on heuristically defined anchors with different scales, angles and aspect ratios and usually suffer from severe misalignment between anchor boxes and axis-aligned convolutional features, which leads to the common inconsistency between the classification score and localization accuracy. To address this issue, we propose a Single-shot Alignment Network (S2A-Net) consisting of two modules: a Feature Alignment Module (FAM) and an Oriented Detection Module (ODM). The FAM can generate high-quality anchors with an Anchor Refinement Network and adaptively align the convolutional features according to the anchor boxes with a novel Alignment Convolution. The ODM first adopts active rotating filters to encode the orientation information and then produces orientation-sensitive and orientation-invariant features to alleviate the inconsistency between classification score and localization accuracy. Besides, we further explore the approach to detect objects in large-size images, which leads to a better trade-off between speed and accuracy. Extensive experiments demonstrate that our method can achieve state-of-the-art performance on two commonly used aerial objects datasets (i.e., DOTA and HRSC2016) while keeping high efficiency1 Copyright © 2020, The Authors. All rights reserved.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Overlapped Mobile Charging for Sensor Networks

Overlapped Mobile Charging for Sensor Networks

引用

International Conference on Distributed Computing Systems

作者： Sheng Zhang Yu Liang Zhuzhong Qian Mingjun Xiao Jidong Ge Jie Wu Sanglu Lu State Key Lab. for Novel Software Technology Nanjing University P.R. China School of Computer Science and Technology / Suzhou Institute for Advanced Study University of Science and Technology of China P.R. China Temple University USA

ISBN: (数字)9781728170022

ISBN: (纸本)9781728170039

In this paper, we consider a fundamental problem: given one mobile charger that can charge multiple sensor nodes simultaneously, how we can schedule it to charge a given WSN to maximize the energy usage effectiveness (EUE)? We propose a novel charging paradigm-Overlapped Mobile Charging (OMC)- the first of its kind to the best of our knowledge. Firstly, OMC clusters sensor nodes into multiple non-overlapped sets using k-means evaluated by the Davies-Bouldin Index, such that the sensor nodes in each set have similar recharging cycles. Secondly, for each set of sensor nodes, OMC further divides them into multiple overlapped groups, and charges each group at different locations for different time durations to make sure that each overlapped sensor node just receives its required energy from multiple charging locations.

关键词： Wireless sensor networks Schedules Conferences Indexes Distributed computing

来源：评论

学校读者我要写书评

暂无评论

Optimal algorithm for profiling dynamic arrays with finite values 22

Optimal algorithm for profiling dynamic arrays with finite v...

引用

22nd International Conference on Extending Database Technology, EDBT 2019

作者： Yang, Dingcheng Yu, Wenjian Deng, Junhui Liu, Shenghua BNRist Dept. Computer Science and Tech. Tsinghua Univ. Beijing China CAS Key Lab. Network Data Science and Tech. Inst. Computing Technology Chinese Academy of Sciences Beijing China

ISBN: (纸本)9783893180813

How can one quickly answer the most and top popular objects at any time, given a large log stream in a system of billions of users? It is equivalent to find the mode and top-frequent elements in a dynamic array corresponding to the log stream. However, most existing work either restrain the dynamic array within a sliding window, or do not take advantages of only one element can be added or removed in a log stream. Therefore, we propose a profiling algorithm, named S-Profile, which is of O(1) time complexity for every updating of the dynamic array, and optimal in terms of computational complexity. With the profiling results, answering the queries on the statistics of dynamic array becomes trivial and fast. With the experiments of various settings of dynamic arrays, our accurate S-Profile algorithm outperforms the existing methods, showing at least 2X speedup to the heap based approach and 13X speedup to the balanced tree based approach. © 2019 Copyright held by the owner/author(s).

关键词： Trees (mathematics)

来源：评论

学校读者我要写书评

暂无评论

Multi-user Edge-assisted Video Analytics Task Offloading Game based on Deep Reinforcement Learning

Multi-user Edge-assisted Video Analytics Task Offloading Gam...

引用

International Conference on Parallel and Distributed Systems (ICPADS)

作者： Yu Chen Sheng Zhang Mingjun Xiao Zhuzhong Qian Jie Wu Sanglu Lu State Key Lab. for Novel Software Technology Nanjing University P.R. China School of Computer Science and Technology / Suzhou Institute for Advanced Study University of Science and Technology of China P.R. China Center for Networked Computing Temple University

ISBN: (数字)9781728190747

ISBN: (纸本)9781728183824

With the development of deep learning, artificial intelligence applications and services have boomed in the recent years, including recommendation systems, personal assistant and video analytics. Similar to other services in the edge computing environment, artificial intelligence computing tasks are pushed to the network edge. In this paper, we consider the multi-user edge-assisted video analytics task offloading (MEVAO) problem, where users have video analytics tasks with various accuracy requirements. All users independently choose their accuracy decisions, satisfying the accuracy requirement, and offload the video data to the edge server. With the utility function designed based on the features of video analytics, we model MEVAO as a game theory problem and achieve the Nash equilibrium. For the flexibility of making accuracy decisions under different circumstances, a deep reinforcement learning approach is applied to our problem. Our proposed design has much better performance compared with some other approaches in the extensive simulations.

关键词： Visual analytics Reinforcement learning Games Nash equilibrium Servers Task analysis Artificial intelligence

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：