检索结果-内蒙古大学图书馆

arXiv 2019年

作者： Wang, Yu Zhou, Quan Liu, Jia Xiong, Jian Gao, Guangwei Wu, Xiaofu Latecki, Longin Jan National Engineering Research Center of Communications and Networking Nanjing University of Posts & Telecommunications China Key Lab. of Broadband Wireless Communications and Sensor Network Technology Nanjing University of Posts & Telecommunications China Institute of Advanced Technology Nanjing University of Posts & Telecommunications China Department of Computer and Information Sciences Temple University Philadelphia United States

The extensive computational burden limits the usage of CNNs in mobile devices for dense estimation tasks. In this paper, we present a lightweight network to address this problem, namely LEDNet, which employs an asymmetric encoder-decoder architecture for the task of real-time semantic segmentation. More specifically, the encoder adopts a ResNet as backbone network, where two new operations, channel split and shuffle, are utilized in each residual block to greatly reduce computation cost while maintaining higher segmentation accuracy. On the other hand, an attention pyramid network (APN) is employed in the decoder to further lighten the entire network complexity. Our model has less than 1M parameters, and is able to run at over 71 FPS in a single GTX 1080Ti GPU. The comprehensive experiments demonstrate that our approach achieves state-of-the-art results in terms of speed and accuracy trade-off on CityScapes dataset. Copyright © 2019, 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

Image watercolorization based on color intensity alteration

Image watercolorization based on color intensity alteration

引用

International Workshop on Advanced Image Technology (IWAIT)

作者： Chiou-Shann Fuh Tzu-Chia Tung Department of Computer Science and Information Engineering National Taiwan University Taipei Taiwan Graduate Institute of Networking and Multimedia National Taiwan University Taipei Taiwan

ISBN: (纸本)9781538626160

This paper presents a watercolor rendering technique that converts photographic images into watercolor painting. An image diffusion and mask filter algorithm are proposed. A heat transfer equation is used as the mage diffusion method and a statistic mask filter is applied to the photographic image processed by the heat transfer equation previously. Experimental results show that better color effect with natural appearance is achieved.

关键词： Rendering (computer graphics) Handheld computers Computational modeling Painting Animation Pigments

来源：评论

学校读者我要写书评

暂无评论

Named Entity Filters for Robust Machine Reading Comprehension

Named Entity Filters for Robust Machine Reading Comprehensio...

引用

International Conference on Technologies and Applications of Artificial Intelligence (TAAI)

作者： Yu-Yan Peng Yung-jen Hsu Graduate Institute of Networking and Multimedia National Taiwan University Taipei Taiwan Department of Computer Science and Information Engineering National Taiwan University Taipei Taiwan

The machine reading comprehension problem aims to extract crucial information from the given document to answer the relevant questions. Although many methods regarding the problem have been proposed, the similarity distraction problem inside remains unsolved. The similarity distraction problem addresses the error caused by some sentences being very similar to the question but not containing the answer. Named entities have the uniqueness which can be utilized to distinguish similar sentences to prevent models from being distracted. In this paper, named entity filters (NE filters) are proposed. NE filters can utilize the information of named entities to alleviate the similarity distraction problem. Experiment results in this paper show that the NE filter can enhance the robustness of the used model. The baseline model increases 5% to 10% F1 score on two adversarial SQuAD datasets without decreasing the F1 score on the original SQuAD dataset. Besides, by adding the NE filter, other existing models increases 5% F1 score on the adversarial datasets with less than 1% loss on the original one.

关键词： Robustness Predictive models Neural networks Encoding Probability distribution Fuses Data models

来源：评论

学校读者我要写书评

暂无评论

Adaptive Generation of Structured Medical Report Using NER Regarding Deep Learning

Adaptive Generation of Structured Medical Report Using NER R...

引用

International Conference on Technologies and Applications of Artificial Intelligence (TAAI)

作者： Cheng-Tse Wu Hsiao-Ko Chang Ji-Han Liu Jyh-Shing Roger Jang Department of Computer Science and Information Engineering National Taiwan University Taipei Taiwan Graduate Institute of Networking and Multimedia National Taiwan University Taipei Taiwan

The structured electronic medical record is the basis for computers to process and achieve the target of precise diagnosis and treatment automatically using the knowledge and features of the techniques such as machine learning and artificial intelligence (AI). Because of the increasing demands on improving the efficiency and the flexibility during the step or phase of classification and extraction, providing the expansion mechanism for the automatic adaption of new NER (Named Entity Recognition, NER) model training during the NER model training stage anytime when the new entities/tags shall be learned and classified and hence the related knowledge database (DB) shall be expanded automatically. The proposed method includes a training stage involving the step of adaptive improved NER model training for the chest x-ray medical reports/files and a test stage involving the step of the dependency parsing and the relation extracting to be perform sequentially, and thus the goals of automatic information extraction and structured medical report generation using the machine learning technique, and the optimization and accuracy improvement of the doctor's work and performance through referring to the structured medical report for diagnosis and treatment can be achieved.

关键词： Medical diagnostic imaging Training Medical services Adaptation models Lung Databases Electronic medical records

来源：评论

学校读者我要写书评

暂无评论

A Low Complexity ML Detection for Uplink Massive MIMO Systems with One-Bit ADCs

A Low Complexity ML Detection for Uplink Massive MIMO System...

引用

IEEE Conference on Vehicular Technology (VTC)

作者： Yo-Seb Jeon Namyoon Lee Song-Nam Hong Robert W. Heath Department of Electrical Engineering POSTECH Pohang Gyeongbuk Korea Department of Electrical and Computer Engineering Ajou University Suwon Gyeonggi Korea Wireless Networking and Communications Group University of Texas at Austin Austin TX USA

This paper presents a low complexity maximum likelihood detection (MLD) algorithm called one-bit-sphere-decoding for an uplink massive multiple-input multiple-output (MIMO) system with one-bit analog-to-digital converters (ADCs). The idea of the proposed algorithm is to estimate the transmitted symbol vector sent by uplink users (a codeword vector) by searching over a sphere, which contains a collection of codeword vectors close to the received signal vector at the base station in terms of a weighted Hamming distance. To reduce the computational complexity for the construction of the sphere, the proposed algorithm divides the received signal vector into multiple sub-vectors each with reduced dimension. Then, it generates multiple spheres in parallel, where each sphere is centered at the sub-vector and contains a list of sub-codeword vectors. Simulation results demonstrate that the proposed algorithm achieves near-MLD performance, while reducing the computational complexity compared to the existing MLD method.

关键词： MIMO communication Uplink Computational complexity Decoding Hamming distance Quantization (signal)

来源：评论

学校读者我要写书评

暂无评论

On the coexistence of nano networks: Sensing techniques for molecular communications

引用

IEEE Transactions on Molecular, Biological, and Multi-Scale Communications 2017年第4期3卷 209-223页

作者： Alizadeh, Ardalan Bahrami, Hamid Reza Maleki, Mehdi Tran, Nghi H. Mohseni, Pedram Department of Electrical and Computer Engineering University of Akron AkronOH44325 United States Department of Enterprise Networking - Wireless Access Point Cisco Systems Inc. San JoseCA95134 United States Department of Electrical Engineering and Computer Science Case Western Reserve University ClevelandOH44106 United States

Molecular communication is an emerging communication paradigm for biological nanomachines. The fast growth of molecular communication techniques in varieties of nanomedical applications can result in scenarios where there are more than one nanonetwork working in a biological environment. On the other hand, possible limitation on the type of molecules, used as information carriers, can result in coexistence problems in co-located molecular communication systems. This paper studies the coexistence problem of two nanonetworks, where one of the nanonetworks is able to intelligently sense the molecular channel and use the channel opportunistically for its own transmission. The sensing nanonetwork measures the concentration of molecules as a criterion to detect the channel white spaces by using a molecular energy detection scheme. When the molecular channel is available, the associated transmitter sends its information using the same carrier molecules. Depending on the availability of timing information at the sensing nanodevice, two synchronous and asynchronous sensing mechanisms are provided based on the likelihood ratio test as the optimal detection method. We also provide numerical simulations of the proposed sensing mechanisms to show that the coexistence of multiple molecular communications is feasible and can be efficiently implemented in nanonetworks. © 2015 IEEE.

关键词： Optimal detection

来源：评论

学校读者我要写书评

暂无评论

Load balancing for ultra-dense networks: A deep reinforcement learning based approach

arXiv

引用

arXiv 2019年

作者： Xu, Yue Xu, Wenjun Wang, Zhi Lin, Jiaru Cui, Shuguang Key Lab of Universal Wireless Communications Ministry of Education Beijing University of Posts and Telecommunications Beijing100876 China State Key Laboratory of Networking and Switching Technology Beijing University of Posts and Telecommunications Beijing100876 China Shenzhen Research Institute of Big Data School of Science and Engineering Chinese University of Hong Kong Shenzhen518172 China Department of Electrical and Computer Engineering University of California DavisCA95616 United States

—In this paper, we propose a deep reinforcement learning (DRL) based mobility load balancing (MLB) algorithm along with a two-layer architecture to solve the large-scale load balancing problem for ultra-dense networks (UDNs). Our contribution is three-fold. First, this work proposes a two-layer architecture to solve the large-scale load balancing problem in a self-organized manner. The proposed architecture can alleviate the global traffic variations by dynamically grouping small cells into self-organized clusters according to their historical loads, and further adapt to local traffic variations through intra-cluster load balancing afterwards. Second, for the intra-cluster load balancing, this paper proposes an off-policy DRL-based MLB algorithm to autonomously learn the optimal MLB policy under an asynchronous parallel learning framework, without any prior knowledge assumed over the underlying UDN environments. Moreover, the algorithm enables joint exploration with multiple behavior policies, such that the traditional MLB methods can be used to guide the learning process thereby improving the learning efficiency and stability. Third, this work proposes an offline-evaluation based safeguard mechanism to ensure that the online system can always operate with the optimal and well-trained MLB policy, which not only stabilizes the online performance but also enables the exploration beyond current policies to make full use of machine learning in a safe way. Empirical results verify that the proposed framework outperforms the existing MLB methods in general UDN environments featured with irregular network topologies, coupled interferences, and random user movements, in terms of the load balancing performance. Copyright © 2019, The Authors. All rights reserved.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

WebRTC Data Channels

引用

IEEE Communications Standards Magazine 2017年第2期1卷 28-35页

作者： Weinrank, Felix Becke, Martin Flohr, Julius Rathgeb, Erwin Rungeler, Irene Tuxen, Michael University of Applied Sciences Department of Electrical Engineering and Computer Science Münster University of Applied Sciences Germany Alfried Krupp von Bohlen und Halbach-Chr. for Computer Networking Technology at the University of Duisburg-Essen Germany

Browser-to-browser real-time communication is making rapid progress in the standardization process, both in the Internet engineering Task Force (IETF) and the World Wide Web Consortium (W3C). These advancements cover many aspects, such as interface definitions, protocol mechanisms and security. Many scenarios discussed show that interfaces and standards can serve as a foundation for interoperable real-time multimedia applications that are easy to implement. In addition to the transfer of real-time-media data, the currently discussed protocol stacks also support transfer of non-media data. This article gives a brief top-down discussion of how the standardization efforts reflect the use cases of non-media data transfer, which use cases could be addressed, and how technologies are applied to achieve the goals. Furthermore, it provides an insight into specific protocol mechanisms as well as unresolved issues for future work. © 2017 IEEE.

关键词： Real time systems

来源：评论

学校读者我要写书评

暂无评论

Alternative Handshake Mechanism for the Stream Control Transmission Protocol

Alternative Handshake Mechanism for the Stream Control Trans...

引用

IFIP networking Conference

作者： Felix Weinrank Irene Rüngeler Michael Tüxen Erwin P. Rathgeb Department of Electrical Engineering and Computer Science Münster University of Applied Sciences Steinfurt Germany Faculty of Business Administration and Economics Computer Networking Technology Group University of Duisburg-Essen Essen Germany

ISBN: (纸本)9781538662809;9783903176089

The Stream Control Transmission Protocol (SCTP) is a message and connection oriented transport protocol using a cookie based four-way handshake for connection establishment. The intention of the four-way handshake is to provide a robust protection against flooding attacks, like TCP SYN-flooding. Although it protects the memory resources on the server side, current implementations require a quite large amount of CPU resources. For some of SCTP's use-cases, like the underlying transport protocol for Web Real-Time Communication (WebRTC) Data-Channels, SCTP's cookie protection is unnecessary and its four-way handshake delays the connection setup *** have developed an alternative handshake method which offers a more lightweight cookie exchange and a zero round-trip time (RTT) connection setup capability while still being fully backwards compatible with the existing handshake procedure. We describe the alternative handshake procedure and its advantages in common use cases like short living connections and WebRTC Data-Channels. In addition, we evaluate the alternative handshake's benefit to the regular handshake with measurements using our FreeBSD kernel implementation.

关键词： Servers IP networks Transport protocols WebRTC Kernel Receivers

来源：评论

学校读者我要写书评

暂无评论

Deep reinforcement learning based dynamic trajectory control for UAV-assisted mobile edge computing

arXiv

引用

arXiv 2019年

作者： Wang, Liang Wang, Kezhi Pan, Cunhua Xu, Wei Aslam, Nauman Nallanathan, Arumugam The Department of Computer and In-formantion Science Northumbria University Newcastle upon TyneNE1 8ST United Kingdom School of Electronic Engineering and Computer Science Queen Mary University of London E1 4NS United Kingdom The National Mobile Communications Research Lab Southeast University Nanjing210096 China Henan Joint International Research Laboratory of Intelligent Networking and Data Analysis Zhengzhou University Zhengzhou450001 China

In this paper, we consider a platform of flying mobile edge computing (F-MEC), where unmanned aerial vehicles (UAVs) serve as equipment providing computation resource, and they enable task offloading from user equipment (UE). We aim to minimize energy consumption of all UEs via optimizing user association, resource allocation and the trajectory of UAVs. To this end, we first propose a Convex optimizAtion based Trajectory control algorithm (CAT), which solves the problem in an iterative way by using block coordinate descent (BCD) method. Then, to make the real-time decision while taking into account the dynamics of the environment (i.e., UAV may take off from different locations), we propose a deep Reinforcement leArning based Trajectory control algorithm (RAT). In RAT, we apply the Prioritized Experience Replay (PER) to improve the convergence of the training procedure. Different from the convex optimization based algorithm which may be susceptible to the initial points and requires iterations, RAT can be adapted to any taking off points of the UAVs and can obtain the solution more rapidly than CAT once training process has been completed. Simulation results show that the proposed CAT and RAT achieve the considerable performance and both outperform traditional algorithms. Copyright © 2019, The Authors. All rights reserved.

关键词： Unmanned aerial vehicles (UAV)

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：