检索结果-内蒙古大学图书馆

17th IEEE International conference on Emerging eLearning Technologies and Applications, ICETA 2019

作者： Frniak, M. Kamencay, P. Markovic, M. Dubovan, J. Dado, M. University of Zilina Department of Multimedia and Information-communication Technologies Zilina Slovakia

ISBN: (纸本)9781728149677

this article is aimed to new methods of measurement, transfer and processing of data from complex system of FibreBragg Grating (FBG) sensors. State of the art technologies and algorithms for vehicle recognition and categorisation in university campus are used. Content of the Article is divided into two parts. the first part is devoted to fibre optic FBG sensors and their basic properties. the second part ofarticle is dedicated to visual data processing by neural networks for visual vehicle categorisation as visual confirmation of data from the fibre Bragg grating sensor arrays. Experimental results show that using AlexNet neural network can be achieved an accuracy for categorization of vehicles of 87.1%. Research is done under the grant project dealing with coexistence of photonic sensor systems and photonic networks within the Internet of things. © 2019 IEEE.

关键词： Vehicles

来源：评论

学校读者我要写书评

暂无评论

***: A Zero-Energy Neural Network Accelerator for Embedded Sensing and Inference systems 19

***: A Zero-Energy Neural Network Accelerator for Embedded S...

引用

17th ACM conference on Embedded Networked Sensor systems (SenSys)

作者： Lee, Seulki Nirjon, Shahriar Univ N Carolina Chapel Hill NC 27515 USA

ISBN: (纸本)9781450369503

We introduce *** a co-processor architecture consisting of a main microcontroller (MCU) that executes scaled-down versions of a deep neural network(1) (DNN) inference task, and an accelerator microcontroller that is powered by harvested energy and follows the intermittent computing paradigm [76]. the goal of the accelerator is to enhance the inference performance of the DNN that is running on the main microcontroller. *** opportunistically accelerates the run-time performance of a DNN via one of its four acceleration modes: extended inference, expedited inference, ensemble inference, and latent training. To enable these modes, we propose two sets of algorithms: (1) energy and intermittence-aware DNN inference and training algorithms, and (2) a fast and high-precision adaptive fixed-point arithmetic that beats existing floating-point and fixed-point arithmetic in terms of speed and precision, respectively, and achieves the best of both. To evaluate ***, we implement low-power image and audio recognition applications and demonstrate that their inference speedup increases by 1.6x and 1.7x, respectively, and the inference accuracy increases by 10% and 16%, respectively, when compared to battery-powered single-MCU systems.

关键词： Accelerator Deep neural networks Zero energy Batteryless

来源：评论

学校读者我要写书评

暂无评论

High-performance tensor decoder on GPUs for wireless camera networks in IoT 21

High-performance tensor decoder on GPUs for wireless camera ...

引用

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： Li, Hai Zhang, Tao Zhang, Runjia Liu, Xiao-Yang School of Computer Engineering and Science Shanghai University China Department of Electrical Engineering Columbia University United States Shanghai Institute for Advanced Communication and Data Science China

ISBN: (纸本)9781728120584

With the rapid development of the Internet of things, tensor-based coding and decoding algorithms are widely used in wireless camera networks. Recently, a novel video decoder based on the low-tubal-rank tensor model has been proposed, which achieves better quality of services than conventional schemes. However, the tensor decoding algorithm is compute-intensive, rendering it impractical for real-time applications. In this paper, we propose effective strategies to accelerate the tensor decoder on GPUs (Graphics processing Units). We implement the tensor decoding algorithm on the GPU architecture, and propose optimization strategies to eliminate data reorganizing overhead, provide batched complex matrix computations, and reduce memory consumption as well as computation overhead. With real video data, the GPU algorithm achieves an average of 237.44X and up to 312.39X speedups on a Tesla V100 GPU versus the CPU algorithm on a multi-core CPU, while preserving similar recovery errors. the recovered video by this high performance GPU tensor decoder shows good visual effects. © 2019 IEEE.

关键词： Graphics processing unit

来源：评论

学校读者我要写书评

暂无评论

Wireless Capsule Endoscopic image Enhancement Method Based on Histogram Correction and Unsharp Masking in Wavelet Domain 17

Wireless Capsule Endoscopic Image Enhancement Method Based o...

引用

17th IEEE International New Circuits and systems conference (NEWCAS)

作者： Long, Mingzhu Xie, Xiang Li, Guolin Wang, Zhihua Tsinghua Univ Inst Microelect Beijing Peoples R China Tsinghua Univ Grad Sch Shenzhen Shenzhen Peoples R China Tsinghua Univ Dept Elect Engn Beijing Peoples R China

ISBN: (纸本)9781728110318

Due to the limited illumination and complex environment in the gastrointestinal (GI) tract, endoscopic images are usually not clear enough to be interpreted by doctors or used for further processing. In order to solve this problem, a method based on histogram correction and unsharp masking in the wavelet domain is proposed in this paper, to improve the contrast and reveal details of endoscopic images. the HSI color space is adopted for color naturalness, and a logarithm based histogram correction method (LHCM) is proposed to improve the contrast and avoid aritifacts. Details are further enhanced by unsharp masking. Experimental results show that performance of the proposed method is better compared with the state-of-art methods. It can be applied to general images and have good effects as well.

关键词： wireless capsule endoscopy image enhancement logarithm transformation histogram equalization unsharp masking

来源：评论

学校读者我要写书评

暂无评论

Multi-objective optimization on multistage half-band FIR filter design using simulated annealing algorithm 21

Multi-objective optimization on multistage half-band FIR fil...

引用

作者： Zhang, Jin Hu, Wei Wang, Yonghao Zhu, Xiangyu College of Computer Science and Technology Wuhan University of Science and Technology China Hubei Province Key Laboratory of Intelligent Information Processing Real-time Industrial System Wuhan China Digital Media Technology Lab Birmingham City University Birmingham United Kingdom

ISBN: (纸本)9781728120584

the design of a finite impulse response (FIR) digital filter is essentially a multi-parameter and multi-objective optimization problem, different optimization techniques can be utilized to minimize the latency in the live audio processing chain by minimization or maximization of the objective function. Using cascaded FIR filters as anti-aliasing and anti-image filters for high-resolution audio conversion are common. We can optimize the parameters of each stage to achieve the overall performance requirements. the method of modified Simulated Annealing (SA) Algorithm is proposed to resize the best distribution of passband ripple, transition band and stopband attenuation for each level of Multi-stage filter. It shows the proposed a new multi-stage filter design method improves the efficiency of the designed filter in terms of filter cost and group delay comparing with traditional design. © 2019 IEEE.

关键词： FIR filters

来源：评论

学校读者我要写书评

暂无评论

thematic Mapping and Evaluation of Temporary Sequence of Multi-zone Satellite images 17th

Thematic Mapping and Evaluation of Temporary Sequence of Mul...

引用

17th Russian conference on Artificial Intelligence (RCAI)

作者： Dementiev, Vitaliy Frenkel, Andrey Kondratiev, Dmitriy Streltsova, Anastasia Ulyanovsk State Tech Univ Ulyanovsk Russia

the goal of this paper is to present and compare algorithms for thematic mapping of multispectral satellite images. the paper proposes a nonlinear multi-dimensional filter to combine the results of processing of sever... 详细信息

ISBN: (纸本)9783030307639;9783030307622

关键词： Earth remote sensing Satellite monitoring image sequence processing Least squares method Segmentation

来源：评论

学校读者我要写书评

暂无评论

QBS-tree: A spatial index with high update efficiency for real-time processing system 21

QBS-tree: A spatial index with high update efficiency for re...

引用

作者： Zhang, Zonglei Fang, Junhua Chen, Wei Zhang, Detian Liu, An Li, Zhixu School of Computer Science Technology Soochow University Suzhou China

ISBN: (纸本)9781728120584

Along with the popularization of big data applications, real-time data analysis is playing an increasingly important role in data analytic applications. the distributed parallel processing framework is a good choice for real-time big data processing, since it provides an effective solution which facilitates processing of massive data stream with low latency. Furthermore, among the real-time applications, location based service is recognized as the most challenging one, especially under expectation on fast response to distribution change and minimal resource consumption. We find that the fundamental reason for this is that the index performance is a stumbling block. Specifically, the original intention of index design is to speed up retrieval speed;in other words, the index is more useful for operations that have more queries than updates. However, in the distributed parallel processing framework, each incoming tuple is both a query request and an update request. In this paper, we propose a new tree index, quad balanced space tree called QBS-tree, to solve this problem, with practical algorithms to support dynamic index items assignment for distributed parallel processing framework. Specifically, make tree index's tolerability to the index items' unbalanced distribution in space be more resilient through a configurable balance factor. In addition, through the lazy update mechanism, let some updates offset each other and the upper node's update covers the underlying node's. Experiments show that QBS-tree responds to a new tuple 1300 times faster than the traditional tree index. © 2019 IEEE.

关键词： Location based services

来源：评论

学校读者我要写书评

暂无评论

Minimum cost task assignment for vehicle-based crowdsensing with deterministic and nondeterministic trajectory 21

Minimum cost task assignment for vehicle-based crowdsensing ...

引用

作者： Tu, Meimei Li, Peng Zhang, Tao Zhou, Qiang Liu, Qin College of Computer Science and Technology Wuhan University of Science and Technology China Hubei Province Key Laboratory of Intelligent Information Processing Real-time Industrial System China Department of Computer Science New York Institute of Technology United States School of Cyber Science and Engineering Wuhan University China

ISBN: (纸本)9781728120584

Vehicle-based crowdsensing (VCS) is a special case in crowdsourcing, and task assignment is a basic and important problem. In this paper, we investigate the minimum cost task assignment (MCTA) problem for vehicle-based crowdsensing. the VCS platform hopes to recruit some vehicles to complete given spatial-temporal tasks with the minimum cost. As vehicle trajectories are dynamic, we divide the MCTA problem into two sub-problems, the deterministic trajectory (D-MCTA) problem, and nondeterministic trajectory (N-MCTA) problem. For D-MCTA problem, we prove that the D-MCTA problem is NP-hard, and we propose a greedy algorithm to solve this problem. For N-MCTA problem, firstly, we determine the probability of each vehicle's trajectory through the logistic regression method. then, we exploit the semi-Markov method to calculate the probability of each vehicle executing the task. Moreover, a greedy algorithm is proposed and the theoretical analysis is given. Finally, extensive simulations have been conducted to show the performance of our proposed algorithms is superior to the other algorithms. © 2019 IEEE.

关键词： Vehicles

来源：评论

学校读者我要写书评

暂无评论

Medical concept extraction using smartphone and natural language processing techniques 19

Medical concept extraction using smartphone and natural lang...

引用

17th ACM International conference on Mobile systems, Applications, and Services, MobiSys 2019

作者： Abbas, Asim Ansaar, Muhammad Zaki Lee, Sungyoung Kyung Hee University Yongin-si Gyeonggi-do Korea Republic of

ISBN: (纸本)9781450366618

Over the past few decade, smartphone technology has played a vital role in the healthcare domain. In this paper, we proposed a methodology to allow end users to automatically process the medical text image using a camera or enter text manually. then the system output allows to extract medical concepts, its semantic type and entity type from medical text apply Natural processing Language techniques from UMLS medical dictionary. the medical text can be a health report, a clinical case, or other kinds of a text containing medically related information. the aim of this kind of methodology of the mobile application is to contribute in the area of natural language processing (NLP), intelligent system and to increase the medical students and bioinformatics researchers interest to quickly accessing information about medical data. © 2019 Copyright held by the owner/author(s).

关键词： Smartphones

来源：评论

学校读者我要写书评

暂无评论

Collaborative approach for a safe driving distance using stereoscopic image processing

引用

FUTURE GENERATION COMPUTER systems-thE INTERNATIONAL JOURNAL OF ESCIENCE 2019年 95卷 880-889页

作者： Olaverri-Monreal, Cristina Krizek, Gerd Ch. Michaeler, Florian Lorenz, Rene Pichler, Matthias Univ Appl Sci Tech Wien Hochstadtpl 6 A-1200 Vienna Austria

Disregard for the rules regarding the minimum safety distance can make the avoidance of a rear-end collision nearly impossible. In a joint effort to enhance safety and improve the decision making processes on an individual level, we contribute to the state of the art with an innovative and affordable system that identifies vehicles and provides a rear-end distance warning system capable of recognizing dangerous situations, and which can also inform other vehicles of the danger, independent of their communication capabilities or equipment. Vision sensors garner information through the stereoscopic capturing and processing of images by rear cameras to calculate the distance between the leading and following vehicles. Visual data related to the safety distance is provided to the following vehicle in real-time, relying on an asynchronous collaborative process. A detailed error analysis of the distance calculation is provided based on the measurement procedure and roadway geometry. Relying on the communication between the two vehicles, an in-vehicle system was compared to the rear-mounted distance warning system under lab-controlled conditions. Both human-machine interaction paradigms were evaluated in terms of their impact on driver response. Results showed that both systems influenced the driver in keeping a time gap of two seconds. (C) 2018 the Authors. Published by Elsevier B.V.

关键词： Cooperative systems Tailgating Safety distance image capturing

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：