检索结果-内蒙古大学图书馆

ieee International conference on Big Data

作者： David Tatis Heidy Sierra Emmanuel Arzuaga Laboratory for Applied Remote-Sensing Imaging and Photonics University of Puerto Rico Mayaguez

ISBN: (数字)9781728162515

ISBN: (纸本)9781728162522

Properties in material composition and crystal structures have been explored by density functional theory (DFT) calculations, using databases such as the open Quantum Materials Database (OQMD). Databases like these have been used currently for the training of advanced machine learning and deep neural network models, the latter providing higher performance when predicting properties of materials. However, current alternatives have shown a deterioration in accuracy when increasing the number of layers in their architecture (over-fitting problem). As an alternative method to address this problem, we have implemented residual neural network architectures based on Merge and Run networks, IRNet and UNet to improve performance while relaxing the observed network depth limitation. The evaluation of the proposed architectures include a 9:1 ratio to train and test as well as 10 fold cross validation. In the experiments we found that our proposed architectures based on IRNet and UNet are able to obtain a lower Mean Absolute Error (MAE) than current strategies. The full implementation (Python, Tensorflow and Keras) and the trained networks will be available online for community validation and advancing the state of the art from our findings.

关键词： Training Databases Neural networks Computer architecture Big Data Predictive models Residual neural networks

来源：评论

学校读者我要写书评

暂无评论

SDN/NFV-based M-CORD for Achieving Scalability in Deploying NB-IoT Gateways

SDN/NFV-based M-CORD for Achieving Scalability in Deploying ...

引用

ieee Pacific Rim conference on Communications, Computers and Signal Processing (PACRIM)

作者： Sinh, Do Le, Luong-Vy Lin, Bao-Shah Paul Tung, Li-Ping Natl Chiao Tung Univ Dept Comp Sci Hsinchu Taiwan Natl Chiao Tung Univ Coll Elect & Comp Engn Hsinchu Taiwan Natl Chiao Tung Univ Microelect & Informat Res Ctr Hsinchu Taiwan

ISBN: (纸本)9781728127941

The deployment of IoT (Internet of Things) gateways opens new challenges for 50 networks to meet the rapid increase in IoT devices, services, and protocols at a high scalability level. To deal with those challenges, recently, NB-Narrow Band IoT (NB-IoT) gateway and M-CORD (Central Office Re-architected as a Datacenter for mobile networks) have been considered as key technologies for developing 5G architectures. in this study, we first propose a comprehensive architecture integrated NB-IoT gateways and M-CORD to meet diversified requirements of 5G and loT services. Next, Software Defined network (SDN) and network Function Virtualization (NFV) are applied to build various virtual network functions (VNFs) on M-CORD Mobile Edges. And then, based on these functions, we perform offloading functions of an NB-IoT gateway to an M-CORD Mobile Edge. After that, a network QoS control application is deployed to perform on demand QoS control for multi-tenancy IoT services with different requirements. Finally, several experiments are implemented on a real NB-IoT gateway and our testbed environment, and the results are also presented.

关键词： Software Defined network (SDN) network Function Virtualization (NFV) Internet of Things (IoT) Wireless Sensor network (WSN) P4 PSA (Portable Switch Architecture) ONOS (open network Operating System)

来源：评论

学校读者我要写书评

暂无评论

Approximate Deep network Embedding for Mining Large-scale Graphs 1

Approximate Deep Network Embedding for Mining Large-scale Gr...

引用

1st ieee International conference on Cognitive Machine Intelligence (CogMI)

作者： Zhou, Yang Liu, Ling Auburn Univ Auburn AL USA Georgia Inst Technol Atlanta GA USA

ISBN: (纸本)9781728167374

In the Big Data era, we are witnessing the flood of big graph data in terms of volume, variety, and velocity. The use of online social media and online shopping sites has provided access to a huge volume of interactions among information entities and objects. Scaling compute-intensive graph analysis applications on huge graphs with millions or billions of vertices and edges is widely recognized as a challenging big data research problem. A lot of research efforts in network embedding aim to learn low-dimensional representation of big graphs, enable easy integration with existing graph mining algorithms, and thus allow to achieve acceptable quality of big graph analysis on network embedding results with superior efficiency and scalability. However, how to enhance network embedding itself in terms of both efficiency and scalability is still an open problem. We are still short of efficient and scalable network embedding techniques to scale themselves on big graphs with millions or billions of vertices and edges, with the awareness of the intrinsic global and local characteristics of graph data. Most network embedding techniques exploit shallow-structured architectures, and thus lead to sub-optimal network representations. We also see lots of potential to utilize approximation theories and deep learning techniques to elevate both efficiency and scalability. In order to promote big network embedding from theoretical points of view, by representing graph data in deep learning architectures, we develop a suite of competitive learning-based approximate deep network embedding techniques that are able to leverage both efficiency and scalability of network embedding while preserving the computational utility with three major components. First, we propose a dynamic competitive learning-based algorithm to combine global network embedding and local network embedding into a unified model to utilize the advantages of both techniques. Second, we develop a network embedding-based alg

关键词： network embedding deep learning competitive learning global network embedding local network embedding neuron ranking

来源：评论

学校读者我要写书评

暂无评论

A Semantic Framework for the Design of Distributed Reactive Real-Time Languages and Applications

引用

ieee ACCESS 2020年 8卷 143862-143880页

作者： Sanabria-Ardila, Mateo Navarro, Luis Daniel Benavides Diaz-Lopez, Daniel Garzon-Alfonso, Wilmer Escuela Colombiana Ingn Julio Garavito Bogota 111166 Colombia Univ Rosario Sch Engn Sci & Technol Bogota 111711 Colombia

The proliferation of on-demand internet services delivered over a network of a heterogeneous set of computing devices has created the need for high-performing dynamic systems in real-time. Services such as audio and video streaming, self-driving cars, the Internet of things (IoT), or instant communication on social networks have forced system designers to rethink the architectures and tools for implementing computer systems. Reactive programming has been advocated as a programming paradigm suitable for implementing dynamic applications with complex and heterogeneous architectural needs. However, there is no consensus on the core set of features that a reactive framework must-have. Furthermore, the current set of features proposed in reactive tools seems very restricted to cope with the actual needs for concurrency and distribution in modern systems. In this paper, several alternative semantics for distributed reactive languages are investigated, addressing complex open issues such as glitch avoidance, explicit distribution support, and constructs for explicit time management. First, we propose a reactive event-based programming language with explicit support for distribution, concurrency, and explicit time manipulation (ReactiveXD). Second, we present a reactive event-based semantic framework called Distributed Reactive Rewriting Framework (DRRF). The framework uses rewriting logic to model the components of a distributed base application, observables, and observers, and predicates supporting explicit time manipulation. Finally, to validate the proposal, the paper discusses the specification of the semantics of ReactiveXD and a scenario describing a case of intrusion detection on IoT networks.

关键词： programming Semantics Real-time systems Internet of Things Computer languages Observers Tools Distributed computing the Internet of Things (IoT) logical clocks Maude real-time languages reactive programming rewriting logic cybersecurity applications

来源：评论

学校读者我要写书评

暂无评论

P4-BNG: Central Office network Functions on Programmable Packet Pipelines 15

P4-BNG: Central Office Network Functions on Programmable Pac...

引用

15th Int Conf on network and Serv Management (CNSM) / 1st Int Workshop on Analyt for Serv and Application Management (AnServApp) / Int Workshop on High-Precision networks Operat and Control, Segment Routing and Serv Function Chaining (HiPNet+SR/SFC)

作者： Kundel, Ralf Nobach, Leonhard Blendin, Jeremias Kolbe, Hans-Joerg Schyguda, Georg Gurevich, Vladimir Koldehofe, Boris Steinmetz, Ralf Tech Univ Darmstadt Multimedia Commun Lab Darmstadt Germany Deutsch Telekom Tech GmbH Fixed Mobile Engn Deutschland Darmstadt Germany Barefoot Networks Santa Clara CA USA

ISBN: (纸本)9783903176249

Large-scale telecommunications providers have to continuously challenge and evolve their network infrastructure to efficiently serve growing markets demands. They must increase performance, lower time-to-market, provide new services, and lower the cost of the infrastructure and its operation. network Functions Virtualization (NFV) on commodity hardware offers an attractive, low-cost platform to establish innovations much faster than with purpose-built hardware products. Unfortunately, implementing NFV on commodity processors does not match the performance requirements of the high-throughput data plane components in large carrier access networks. In this article, we propose a way to offer residential network access with programmable packet processing architectures. Based on the highly flexible P4 programming language, we present a design and open source implementation of a BNG data plane that meets the challenging demands of Broadband network Gateways in carrier-grade environments. The proposed evaluation results show the desired performance characteristics and our proposed design together with upcoming P4 hardware can offer a giant leap towards highest performance NFV network access.

关键词： NFV P4 Access networks network Functions Hardware Acceleration Computer networks

来源：评论

学校读者我要写书评

暂无评论

Leveraging Deep Learning to Predict Cyberattack with Traffic Whitelist for Optical Fronthaul networks in 5G and Beyond

Leveraging Deep Learning to Predict Cyberattack with Traffic...

引用

Asia Communications and Photonics conference (ACP)

作者： Zhao, Guanliang Yang, Hui Yu, Ao Zhu, Yueyan Li, Kai Zhang, Jie Beijing Univ Posts & Telecommun State Key Lab Informat Photon & Opt Commun Beijing Peoples R China

This paper proposes a deep learning cyberattack prediction mechanism in 5G and Beyond optical fronthaul networks. Experiments and simulations verify that this mechanism improves high accuracy and efficiency in a new g... 详细信息

ISBN: (纸本)9781943580705

关键词： network architecture

来源：评论

学校读者我要写书评

暂无评论

Towards an Integration of AES Cryptography into Deluge Dissemination Protocol for Securing IoTs Reconfiguration

Towards an Integration of AES Cryptography into Deluge Disse...

引用

ieee - RIVF International conference on Computing and Communication Technologies (RIVF)

作者： Dang Huynh-Van Ngan Le-Thi-Chau Khoa Ngo-Khanh Quan Le-Trung Vietnam Natl Univ Ho Chi Minh City Univ Informat Technol Dept Comp Networks Ho Chi Minh City Vietnam

ISBN: (纸本)9781538693131

In IoT-based system, over-the-air (OTA) programming or IoTs reconfiguration plays a vital role, especially in large-scale deployments. OTA programming allows IoTs devices to be replaced and upgraded the running applications or image by the newer versions without effort on manually install one by one device. However, the development of OTA programming also meets many challenges due to the limitations of memory resources, battery energy as well as communication support of small and constraint devices. Therefore, designing OTA programming solutions supported by a strong security mechanism has been still an open issue. In this paper, an integration of AES cryptography into a well-known network programming protocol (Deluge on TinyOS 2.x) is presented. The paper not only explains Deluge protocol's operation, messages format but also provides numerical results when running this enhancement with real IoTs devices (Telosb mote on TinyOS 2.x). The developed solution can be deployed in the real IoT-based systems for securely re-configuring IoT devices and the presented empirical results can be used as a dataset for research community to compare in other environments.

关键词： Over-the-air programming AES cryptography IoTs reconfiguration Deluge TinyOS

来源：评论

学校读者我要写书评

暂无评论

The Case for Writing network Drivers in High-Level programming Languages

The Case for Writing Network Drivers in High-Level Programmi...

引用

ACM/ieee Symposium on architectures for networking and Communications Systems (ANCS)

作者： Emmerich, Paul Ellmann, Simon Bonk, Fabian Egger, Alex Garcia Sanchez-Torija, Esau Guenzel, Thomas Di Luzio, Sebastian Obada, Alexandru Stadlmeier, Maximilian Voit, Sebastian Carle, Georg Tech Univ Munich Munich Germany Univ Politecn Cataluna Barcelona Spain Ludwig Maximilians Univ Munchen Munich Germany

ISBN: (纸本)9781728143873

Drivers are written in C or restricted subsets of C++ on all production-grade server, desktop, and mobile operating systems. They account for 66% of the code in Linux, but 39 out of 40 security bugs related to memory safety found in Linux in 2017 are located in drivers. These bugs could have been prevented by using high-level languages for drivers. We present user space drivers for the Intel ixgbe 10 Gbit/s network cards implemented in Rust, Go, C#, Java, OCaml, Haskell, Swift, JavaScript, and Python written from scratch in idiomatic style for the respective languages. We quantify costs and benefits of using these languages: High-level languages are safer (fewer bugs, more safety checks), but run-time safety checks reduce throughput and garbage collection leads to latency spikes. Out-of-order CPUs mitigate the cost of safety checks: Our Rust driver executes 63% more instructions per packet but is only 4% slower than a reference C implementation. Go's garbage collector keeps latencies below 100 mu s even under heavy load. Other languages fare worse, but their unique properties make for an interesting case study. All implementations are available as free and open source at https://***/ixy-languages/ixy-languages.

关键词： Rust Go C# Java OCaml Haskell Swift JavaScript Python

来源：评论

学校读者我要写书评

暂无评论

Soft open Point–Energy Storage Collaborative Planning Based on Second-Order Cone programming

Soft Open Point–Energy Storage Collaborative Planning Based...

引用

ieee Student conference on Electric Machines and Systems

作者： Shaoqing Si Yumin Zhang Xingquan Ji Bo Xu College of Electrical Engineering and Automation Shandong University of Science and Technology Qingdao Shandong China State Grid Energy Research Institute Co. Beijing China

ISBN: (数字)9781728156224

ISBN: (纸本)9781728156231

With the application of power electronic technology in the power distribution system, soft open point (SOP) has attracted wide attention because of its flexible control of power flow. Considering the interaction between different operating entities, SOP-energy storage system (ESS) collaborative planning is proposed. The objective is minimizing the sum of investment and maintenance cost of SOP, investment and operation cost of ESS, and operation loss of distribution network. The constraints include the system operation status, system power balance, operation status of each component, installation location and capacity of each component. Then the non-convex nonlinear programming model is relaxed into a mixed-integer second-order cone programming (MISOCP) problem. Finally, the proposed collaborative planning model is verified to effectively reduce investment costs and improve voltage quality through the ieee-33 system.

关键词： Systems operation Collaboration Power distribution programming Power electronics Planning Investment

来源：评论

学校读者我要写书评

暂无评论

Application of Fuzzy Answer set programming in Hybrid Deep Neural-Symbolic Architecture

Application of Fuzzy Answer set Programming in Hybrid Deep N...

引用

Convergence in Engineering (ICCE), ieee International conference for

作者： Sandip Paul Kumar Sankar Ray Diganta Saha Indian Statistical Institute Kolkata India Jadavpur University Kolkata India

ISBN: (数字)9781728173405

ISBN: (纸本)9781728173412

Hybrid deep neural-symbolic architecture for event-detection employs a deep neural network at the back-end to perform low-level reasoning and a symbolic logical module to perform high-level cognitive reasoning. The currently known hybrid architectures use classical Answer Set programming(ASP), which is unable to perform fuzzy reasoning with uncertainty. Moreover these systems don't extract new rules from the available data. On the other hand, there are neuro-fuzzy systems that can extract fuzzy rules from data by means of Gaussian Restricted Boltzman Machines (GRBM). Both the aspects should be merged together to achieve human-like intelligent reasoning and learning from environment. But the success of such an integration depends upon the chosen logical system, that can support fuzzy reasoning with uncertainty, as well as, can support the extracted knowledge from GRBM. This work investigates the feasibility of using interval-valued fuzzy logic programming for this purpose. This work focuses on the theoretical aspects from logic programming perspective.

关键词： Cognition Uncertainty Data mining Feature extraction Training Neural networks Computer architecture

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：