检索结果-内蒙古大学图书馆

21st IEEE international Conference on high performance computing and Communications, 17th IEEE international Conference on Smart City and 5th IEEE international Conference on Data Science and Systems, HPCC/SmartCity/DSS 2019

作者： Chen, Jie Xiao, Zhu Wang, Dong Long, Wangchen Havyarimana, Vincent College of Computer Science and Electronic Engineering Hunan University Changsha China Department of Applied Sciences Ecole Normale Supérieure Bujumbura Burundi

ISBN: (纸本)9781728120584

During the process of modern industrialization and urbanization, it has become one of the major daily activities that people drive private cars to fulfill their travel demands. The trajectory data generated during the usage of private cars plays as the intuitive embodiment of people's travel behavior. In particular, the stay behavior, i.e., people need to stay and take time carrying out their own activities when they drive to a specific location, contains crucial information for understanding users' travel behavior and mobility motivations. In this paper, via leveraging the private car trajectory data, we strive to propose a novel approach to percept and predict stay of interests, called SOI. The goal is to predict the stay interest of a private car user will stay to a given location, this is important information for vehicle services such as travel semantic analysis and smart recommendation service. Specifically, we first propose a stay behavior perception method to detect stay behavior from large-scale private car trajectory dataset. Then, we design a spatiotemporal factor extraction method considering the spatial aggregation, time period and spatiotemporal similarity correlation of stay behaviors, which can reduce the sparsity and non-stationary problems of stay behavior data. Furthermore, we propose a prediction method based gradient boosting decision trees to estimate the future stay interest of private car users' stay behavior. We conduct extensive experiments based on the real-life private car trajectory dataset. For the stay interest prediction of stay behavior, achieve prediction precision of 0.89 and recall of 0.85. To the best of authors' knowledge, this is the first work in literature that exploits private car trajectory data and discovers the stay behavior of private car users and hence provides new perspective for understanding people's travel behavior. © 2019 IEEE.

关键词： Data mining

来源：评论

学校读者我要写书评

暂无评论

LstM with Adam Optimization-Powered high Accuracy Preeclampsia Classification 21

LSTM with Adam Optimization-Powered High Accuracy Preeclamps...

引用

21st international Electronics symposium, IES 2019

作者： Sakinah, Nur Tahir, Muhlis Badriyah, Tessy Syarif, Iwan Politeknik Elektronika Negeri Surabaya Graduate Program of Engineering Technology Surabaya Indonesia Computer Graphic Engineering Technology Study Program Politeknik Negeri Sambas Kalimantan Barat Indonesia

ISBN: (纸本)9781728144498

Preeclampsia is a pregnancy complication characterized by high blood pressure and signs of damage to another organ system, most often the liver and kidneys. Preeclampsia usually begins after 20 weeks of pregnancy in women whose blood pressure had been normal. To anticipate the risk of preeclampsia and prevent the death of pregnant women, a predictive system is needed for preeclampsia. to predict this, the data obtained will be studied to recognize patterns for predicting preeclampsia. Artificial neural network is one method that has the ability to learn patterns from a data. The system built in this study is to use the artificial neural network method by using the architecture of Long Short-Term Memory (LstM) Neural Networks. But this technique requires the right parameters to get accurate predictions. In this paper analyze several parameters such as number of time series patterns, number of hidden neurons, max epoch, and composition of training and test data on the accuracy of the predictions obtained. The results of the analysis showed that the system built was able to predict Preeclampsia well, with an average accuracy rate of 90.22% for data testing. © 2019 IEEE.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Smart Contract-based Hierarchical Auction Mechanism for Edge computing in Blockchain-empowered IoT

Smart Contract-based Hierarchical Auction Mechanism for Edge...

引用

IEEE international symposium on World of Wireless Mobile and Multimedia Networks (WoWMoM)

作者： Hui Lin Zetao Yang Zicong Hong Shenghui Li Wuhui Chen School of Data and Computer Science Sun Yat-sen University Guangdong China National Engineering Research Center of Digital Life Sun Yat-sen University Guangdong China

ISBN: (数字)9781728173740

ISBN: (纸本)9781728173757

Edge computing is a promising paradigm to expand the capability of Internet of Things (IoT) devices by computation offloading. To establish a distributed ledger to provide a secure and trusted environment for the resource allocation between edge servers and IoT devices, the emerging blockchain technology has attracted a lot of attention recently. However, in practice, edge resource allocation in IoT devices often involves multi-layer structures, which poses a challenge due to information incompleteness among different layers. Moreover, how to design a suitable and efficient blockchain framework for hierarchical resource allocation markets is a critical issue. In this paper, we apply blockchain to propose a secure and efficient hierarchical resource allocation framework for edge computing. First, we study the edge computing resource allocation problem in the hierarchical market of IoT devices, in which the IoT devices beyond the coverage of Access Points can participate in the resource allocation through middlemen. To solve the problem, a smart contract-based hierarchical auction mechanism is developed. The edge computing resources allocated in the top market can be continually reallocated to the sub-markets based on the mechanism, which then leads an efficient solution that maximizes the social welfare of the whole participants. Moreover, the mechanism is implemented as a smart contract in the blockchain, which enforces the rule of the hierarchical auction in a non-deniable and automated manner. Finally, the extensive simulations demonstrate the correctness and performance of the proposed mechanism.

关键词： Resource management Edge computing Servers Contracts Internet of Things

来源：评论

学校读者我要写书评

暂无评论

An edge computing architecture in the Internet of Things 21

An edge computing architecture in the Internet of Things

引用

21st IEEE international symposium on Real-Time computing (ISORC)

作者： Martin, Cristian Diaz, Manuel Rubio, Bartolome Univ Malaga Dept Languages & Comp Sci Malaga Spain

ISBN: (纸本)9781538658475

In the last few years, the Internet of Things (IoT) has emerged as the new disruptive technology to change the world. Cloud computing has accompanied this field to overcome its processing and storage limitations. However, this evolution has originated a huge increase in IoT devices and data that will create a bottleneck for current networks, in addition to a lack of low latency in cloud communications. Edge computing has been developed to address this challenge, moving the processing to the edge of the network. In this paper, an edge computing architecture is presented to overcome these challenges. The architecture, based on our previous work on the lambda-CoAP architecture, covers the whole vision of an edge computing deployment, from IoT devices, to the edge Smart Gateways and up to a cloud infrastructure.

关键词： computer architecture Cloud computing Logic gates Containers Edge computing Virtualization Real-time systems"

来源：评论

学校读者我要写书评

暂无评论

Transitive Closure Based Schedule of Loop Nest statement Instances 21st

Transitive Closure Based Schedule of Loop Nest Statement Ins...

引用

21st international Multi-Conference on Advanced computer Systems, ACS 2018

作者： Bielecki, Wlodzimierz Palkowski, Marek Faculty of Computer Science and Information Systems West Pomeranian University of Technology in Szczecin Zolnierska 49 Szczecin71210 Poland

ISBN: (纸本)9783030033132

A novel algorithm of loop nest statement instance scheduling is presented. It is based on the transitive closure of dependence graphs. The algorithm is implemented in the publicly available optimizing TRACO compiler, which allows for automatic parallelization of program loop nests and automatic generation of parallel compilable code in the OpenMP standard. Results of an experimental study demonstrate that the algorithm is able to generate parallel code for popular benchmarks and this code achieves satisfactory speed-up on modern machines. The computational complexity of the approach is low. Future algorithm improvements are discussed. © 2019, Springer Nature Switzerland AG.

关键词： Program compilers

来源：评论

学校读者我要写书评

暂无评论

94 GHz Radar Used for Perimeter Surveillance with Wide Target Clarification

94 GHz Radar Used for Perimeter Surveillance with Wide Targe...

引用

international Radar symposium (IRS)

作者： W. Johannes M. Caris S. stanko Fraunhofer Institute for High Frequency Physics and Radar Techniques FHR Wachtberg Germany

ISBN: (数字)9788394942151

ISBN: (纸本)9781728157863

The ground based mobile perimeter surveillance of many military and civil infrastructures to detect and track potential threatening targets on ground or in the air is still a very important capability of sensor systems. Such dangerous targets can be suicide attackers or drones, which violate the privacy of individuals or which can be used for spying, smuggling, or acts of terrorism. To demonstrate the possibilities of current technologies and processing methods, a high performance mechanically scanning surveillance radar sensor and a high-resolution camera were successfully combined for these applications. Both sensors have a high measurement update rate of up to 1.6 Hz. The most remarkable feature is the use of a 94 GHz radar sensor with 3D localization, georeferencing, extended Doppler analysis, RCS calibration and multi target tracking for stand-off monitoring in real-time of an area of interest. Furthermore, the real-time images of the multi-sensor system are transferred from the operator's computer to several mobile devices to disseminate an overview of the situation. The implementation of the real-time data processing and the real time data visualization plus the intuitive system control was done successfully. The stored radar and camera data can be used for the conservation of evidence, for further offline processing and for algorithm development.

关键词： Radar cross-sections Laser radar Surveillance Radar Cameras Real-time systems Doppler radar

来源：评论

学校读者我要写书评

暂无评论

performance Analysis and Optimization of Automotive GPUs

Performance Analysis and Optimization of Automotive GPUs

引用

international symposium on computer architecture and high performance computing (SBAC-PAD)

作者： Fabio Mazzocchetti Pedro Benedicte Hamid Tabani Leonidas Kosmidis Jaume Abella Francisco J. Cazorla Barcelona Supercomputing Center Universitat Politècnica de Catalunya

Advanced Driver Assistance Systems (ADAS) and Autonomous Driving (AD) have drastically increased the performance demands of automotive systems. Suitable high-performance platforms building upon Graphic Processing Units (GPUs) have been developed to respond to this demand, being NVIDIA Jetson TX2 a relevant representative. However, whether high-performance GPU configurations are appropriate for automotive setups remains as an open question. This paper aims at providing light on this question by modelling an automotive GPU (Jetson TX2), analyzing its microarchitectural parameters against relevant benchmarks, and identifying specific configurations able to meaningfully increase performance within similar cost envelopes, or to decrease costs preserving original performance levels. Overall, our analysis opens the door to the optimization of automotive GPUs for further system efficiency.

关键词： Graphics processing units Automotive engineering Benchmark testing computer architecture Autonomous vehicles Hardware Optimization

来源：评论

学校读者我要写书评

暂无评论

Faster Function Blocks for Precision Timed Industrial Automation 21

Faster Function Blocks for Precision Timed Industrial Automa...

引用

21st IEEE international symposium on Real-Time computing (ISORC)

作者： Pearce, Hammond Roop, Partha Biglari-Abhari, Morteza Schoeberl, Martin Univ Auckland Dept Elect & Comp Engn Auckland New Zealand Tech Univ Denmark Dept Appl Math & Comp Sci Lyngby Denmark

ISBN: (纸本)9781538658475

In industrial automation, safety-critical control systems need robust timing guarantees in addition to functional correctness. Unfortunately, devices that are typically used in this domain, such as Programmable Logic Controllers, often feature architectures that are not amenable to static timing analysis, for instance relying on general purpose microprocessors or embedded operating systems. As a result, designers often rely on timing values gained from simple measurement of running applications, an approach that only provides very weak guarantees at best. The synchronous approach for IEC 61499 Function Blocks, in contrast, has been demonstrated to be time predictable when run on appropriate hardware, such as simple microprocessors. However, simple microprocessors are often not fast or powerful enough for modern automation requirements. In this paper, we examine how the performance of synchronous IEC 61499 can be improved through the usage of the multi-core T-CREst architecture, data scratchpads, and an optimised compiler. Overall, our improvements resulted in 60% shorter worst-case execution times.

关键词： IEC standards Timing computer architecture Hardware Program processors Semantics Automation"

来源：评论

学校读者我要写书评

暂无评论

Enabling machine learning in X-ray-based procedures via realistic simulation of image formation

引用

international JOURNAL OF computer ASSIstED RADIOLOGY AND SURGERY 2019年第9期14卷 1517-1528页

作者： Unberath, Mathias Zaech, Jan-Nico Gao, Cong Bier, Bastian Goldmann, Florian Lee, Sing Chun Fotouhi, Javad Taylor, Russell Armand, Mehran Navab, Nassir Johns Hopkins Univ Dept Comp Sci Baltimore MD 21218 USA Johns Hopkins Univ Lab Computat Sensing Robot Baltimore MD 21218 USA Johns Hopkins Univ Comp Aided Med Procedures Baltimore MD 21218 USA Johns Hopkins Univ Appl Phys Lab Laurel MD USA

Purpose Machine learning-based approaches now outperform competing methods in most disciplines relevant to diagnostic radiology. Image-guided procedures, however, have not yet benefited substantially from the advent of deep learning, in particular because images for procedural guidance are not archived and thus unavailable for learning, and even if they were available, annotations would be a severe challenge due to the vast amounts of data. In silico simulation of X-ray images from 3D CT is an interesting alternative to using true clinical radiographs since labeling is comparably easy and potentially readily available. Methods We extend our framework for fast and realistic simulation of fluoroscopy from high-resolution CT, called DeepDRR, with tool modeling capabilities. The framework is publicly available, open source, and tightly integrated with the software platforms native to deep learning, i.e., Python, PyTorch, and PyCuda. DeepDRR relies on machine learning for material decomposition and scatter estimation in 3D and 2D, respectively, but uses analytic forward projection and noise injection to ensure acceptable computation times. On two X-ray image analysis tasks, namely (1) anatomical landmark detection and (2) segmentation and localization of robot end-effectors, we demonstrate that convolutional neural networks (ConvNets) trained on DeepDRRs generalize well to real data without re-training or domain adaptation. To this end, we use the exact same training protocol to train ConvNets on naive and DeepDRRs and compare their performance on data of cadaveric specimens acquired using a clinical C-arm X-ray system. Results Our findings are consistent across both considered tasks. All ConvNets performed similarly well when evaluated on the respective synthetic testing set. However, when applied to real radiographs of cadaveric anatomy, ConvNets trained on DeepDRRs significantly outperformed ConvNets trained on naive DRRs (p<0.01). Conclusion Our findings for both tas

关键词： Monte Carlo simulation Artificial intelligence computer assisted surgery Robotic surgery Segmentation Image guidance

来源：评论

学校读者我要写书评

暂无评论

Rigel: A Framework for OpenMP performanceTuning

Rigel: A Framework for OpenMP PerformanceTuning

引用

IEEE international Conference on high performance computing and Communications (HPCC)

作者： Piyumi Rameshka Pasindu Senanayake Thulana Kannangara Praveen Seneviratne Sanath Jayasena Tharindu Rusira Mary Hall Dept of Computer Science Engineering University of Moratuwa Katubedda Sri Lanka School of Computing University of Utah Salt Lake City UT

ISBN: (纸本)9781728120591

OpenMP allows developers to harness the power of shared memory multiprocessing in C and C++ applications, but the performance gained with OpenMP is highly sensitive to the underlying hardware, making performance portability across different hardware architectures fragile. For example, in mapping a parallel for loop to hardware, OpenMP 4 offers commands for exploiting vector instructions (simd directives) and automatic GPU offloading (target directives), as well as schedule directives for CPU load balancing. These benefits come with a cost. A developer has to be well aware of the architecture details, and the application, and must iteratively tune to determine the best combination of pragma directives delivering higher performance for the given target architecture. Hence in this paper we introduce Rigel, a framework that automates these decisions to arrive at optimized OpenMP annotated code. Given a code segment with inherent parallelism, our framework uses separate machine learning classification models to predict the anticipated benefit of each optimization. Both Vector Classification and GPU Offloading Classification models perform with average accuracies of 83%. Succeeding the classification process, code segments are optimized accordingly. Our results show that GPU offloading optimization lead to an average speedup of 8x over default non-optimized CPU parallel execution (pragma omp parallel for) and average Vector optimization speedup is 6x compared to LLVM Clang 4.0 auto-vectorization. Furthermore Scheduling mechanism selection process results in overall accuracy of 90%.

关键词： Feature extraction Graphics processing units Optimization Hardware Machine learning Tuning 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：