检索结果-内蒙古大学图书馆

13th Web Information Systems and Applications Conference, WISA 2016

作者： Wang, Xiongbin Liu, Chen Zhu, Meiling Beijing Key Laboratory on Integration and Analysis of Large-scale Stream Data North China University of Technology Beijing China Cloud Computing Research Center North China University of Technology Beijing China School of Computer Science and Technology Tianjin University Tianjin China

ISBN: (纸本)9781509054374

Traveling companions are object groups that move together in a period of time. To quickly identify traveling companions from a special kind of streaming traffic data, called Automatic Number Plate Recognition (ANPR) data, this paper proposes a framework and several algorithms to discover companion vehicles. Compared to related approaches, our main contribution is that the framework can instantly detect suspicious companion vehicles with their probabilities when they pass through monitoring cameras. Our framework can be used in many time-sensitive scenarios like taking surveillance on the suspect trackers for specific vehicles. Experiments show that our approach can process streaming ANPR data directly and discover the companion vehicles in nearly real time. © 2016 IEEE.

关键词： Vehicles

来源：评论

学校读者我要写书评

暂无评论

Simulation and analysis of isolated word speech recognition

引用

International Journal of Simulation: Systems, Science and Technology 2016年第44期17卷 34.1-34.7页

作者： Fang, Yinglan Han, Bing Hou, Ruizhen Beijing Key Laboratory on Integration and Analysis of Large-scale Stream Data School of Computer North China University of Technology Beijing100144 China

Based on the Dynamic Time Warping (DTW) algorithm, we propose an improved isolated word speech recognition and simulation. In this paper we analyze the traditional endpoint detection algorithm and propose an improved version. The recognition algorithm uses the dynamic time regularization technique based on template matching in order to improve the traditional algorithm of long search path and search time. We use Matlab software to achieve the training and recognition of speech signals. The simulation results show that the improved algorithm has higher recognition rate and recognition speed than the traditional algorithm. © 2016, UK Simulation Society. All rights reserved.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

An Adaptive Replica Mechanism for Real-Time stream Processing

An Adaptive Replica Mechanism for Real-Time Stream Processin...

引用

Symposia and Workshops on Ubiquitous, Autonomic and Trusted Computing, UIC-ATC

作者： Weilong Ding Zhuofeng Zhao Yanbo Han Beijing Key Laboratory on Integration and Analysis of Large-scale Stream Data Beijing China Research Center for Cloud Computing North China University of Technology Beijing China

In Internet of Things, many applications are modeled as the continuous stream processing of the senor data, the replica mechanism is required to guarantee availability. However, the replicas' backup, placement bring the latency at run-time due to the resources consumption from memory, bandwidth. In this paper, a mechanism is proposed as greedy fashion by the resources cost to place replicas, which could tradeoff between the availability, overheads in the system. The extensive experiments show that the availability of the proposed mechanism can be provided in a more stable manner than the traditional random placement under the same conditions.

关键词： Bandwidth Resource management Indexes Programming Materials requirements planning Real-time systems Cameras

来源：评论

学校读者我要写书评

暂无评论

A Framework for Passengers Demand Prediction and Recommendation

A Framework for Passengers Demand Prediction and Recommendat...

引用

IEEE International Conference on Services Computing (SCC)

作者： Kai Zhang Zhiyong Feng Shizhan Chen Keman Huang Guiling Wang Tianjin Key Laboratory of Cognitive Computing and Application Tianjin China School of Computer Science and Technologv Tianjin University Tianjin China School of Computer Software Tianjin University Tianjin China Beijing Key Laboratory on Integration and Analysis of Large-scale Stream Data Beijing China

With the rapid development of mobile internet and wireless network technologies, more and more people use the mobile app to call a taxicab to pick them up. Therefore, understanding the passengers' travel demand becomes crucial to improve the utilization of the taxicabs and reduce their cost. In this paper, based on spatio-temporal clustering, we propose a demand hotspots prediction framework to generate recommendation for taxi drivers. Specially, an adaptive prediction approach is presented to demand hotspots and their hotness, and then combing the driver's location and the hotness, top candidates are recommended and visually presented to drivers. Based on the dataset provided by CAR INC., the experiment shows that our approach gains a significant improvement in hotspots prediction and recommendation, with 15.21% improvement on average f-measure for prediction and 79.6% hit ratio for recommendation.

关键词： Public transportation Trajectory Vehicles Global Positioning System Mobile communication Clustering algorithms Filtering algorithms

来源：评论

学校读者我要写书评

暂无评论

Classification Based on Multilayer Extreme Learning Machine for Motor Imagery Task from EEG Signals

引用

Procedia Computer Science 2016年 88卷 176-184页

作者： Lijuan Duan Menghu Bao Jun Miao Yanhui Xu Juncheng Chen College of Computer Science and Technology Beijing University of Technology Beijing 100124 China Beijing Key Laboratory of Trusted Computing National Engineering Laboratory for Critical Technologies of Information Security Classified Protection Beijing 100124 China Key Lab of Intelligent Information Processing of Chinese Academy of Sciences (CAS) Institute of Computing Technology CAS Beijing 100190 China Beijing Key Laboratory on Integration and Analysis of Large-scale Stream Data Beijing 100124 China

Classification of motor imagery electroencephalogram (EEG) is one of the most important technologies for BCI. To improve the accuracy, this paper introduces a classification system based on Multilayer Extreme Learning Machine (ML-ELM). In the system, the combination of PCA and LDA is chosen as the method of feature extraction and the ML-ELM is used to classify. The ML-ELM has not only the advantage which ELM has but also better performance than ELM. In the experiment, our method is compared with the methods based on ELM, such as kernel-ELM, Constrained-ELM and V-ELM, and some state-of–the-art methods on the same dataset. The experimental results show that ML-ELM is much more suitable for motor imagery EEG data and has better performance than the others.

关键词： Electroencephalogram Classification Motor Imagery Extreme Learning Machine Multilayer Extreme Learning Machine

来源：评论

学校读者我要写书评

暂无评论

Simulate Human Saccadic Scan-Paths in Target Searching

引用

International Journal of Intelligence Science 2016年第1期6卷 1-9页

作者： Lijuan Duan Jun Miao David M. W. Powers Jili Gu Laiyun Qing Beijing Key Laboratory of Trusted Computing Beijing Key Laboratory on Integration and Analysis of Large-Scale Stream Data College of Computer Science and Technology Beijing University of Technology Beijing China National Engineering Laboratory for Critical Technologies of Information Security Classified Protection Beijing China Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences(CAS) Institute of Computing Technology CAS Beijing China School of Computer Science Engineering & Maths Flinders University of South Australia Adelaide South Australia Beijing Samsung Telecom R&D Center Beijing China University of Chinese Academy of Sciences Beijing China

Human saccade is a dynamic process of information pursuit. There are many methods using either global context or local context cues to model human saccadic scan-paths. In contrast to them, this paper introduces a model for gaze movement control using both global and local cues. To test the performance of this model, an experiment is done to collect human eye movement data by using an SMI iVIEW X Hi-Speed eye tracker with a sampling rate of 1250 Hz. The experiment used a two-by-four mixed design with the location of the targets and the four initial positions. We compare the saccadic scan-paths generated by the proposed model against human eye movement data on a face benchmark dataset. Experimental results demonstrate that the simulated scan-paths by the proposed model are similar to human saccades in term of the fixation order, Hausdorff distance, and prediction accuracy for both static fixation locations and dynamic scan-paths.

关键词： Saccadic Scan-Paths Eye Movement Fixation Locations Dynamic Scan-Paths

来源：评论

学校读者我要写书评

暂无评论

A User-Relationship-Based Cache Replacement Strategy for Mobile Social Network

A User-Relationship-Based Cache Replacement Strategy for Mob...

引用

Japan-China Joint Workshop on Frontier of Computer Science and Technology (FCST)

作者： Qiyuan Xing Jing Wang Yue Li Yanbo Han Beijing Key Laboratory on Integration and Analysis of Large-scale Stream Data North China University of Technology Beijing China

ISBN: (纸本)9781467392969

In recent years, mobile applications grew rapidly with the development of Android and iOS platforms. Most of applications on these smart phones generate and make use of user-generated data. When users need relative data, it is not very realistic to request from the server every time. So a suitable cache technology is required. Traditional cache technologies pay more attention on data access time, frequency or data space, but do not consider data generators' relationships with each other. In mobile social network environment, data access is closely related to users' relationships, so this factor is suitable to be used in cache technologies. In this paper, we proposed a user-relationship-based cache replacement strategy. We combined user relationship with the classic cache algorithm LRU. Not only the access times of each data blocks are considered, but also users' relationships are computed by the closeness between data requesters and generators. The experiment results show that our replacement strategy can improve the cache hit ratio in mobile social environment.

关键词： Mobile communication Mobile computing Servers Wireless communication Twitter Mobile applications

来源：评论

学校读者我要写书评

暂无评论

Sparse representation based CSI indoor localization method

引用

Ruan Jian Xue Bao/Journal of Software 2016年 27卷 21-27页

作者： Ma, Li Wang, Shan-Ting Ma, Dong-Chao Zhang, Yong-Mei College of Computer Science and Technology North China University of Technology Beijing100144 China College of Electronic Information Engineering North China University of Technology Beijing100144 China Beijing Key Laboratory on Integration and Analysis of Large-scale Stream Data North China University of Technology Beijing100144 China

Precise indoor positioning has important application value. GPS and other systems in the room often can be affected by many factors, and therefore may fail to provide accurate positioning. How to accurately locate the indoor environment location has become the focus of research and application. By analyzing the radio channel state information (CSI) of ordinary wireless device, indoor environment sensing technology can be realized without having to carry devices. The technology can provide personalized service based on location and apply to many kinds of location tracking and sensing. In order to solve the multipath effect and temporary noise impact on precise indoor positioning, this paper proposes a CSI indoor positioning method based on sparse representation. The method reduces the influence of multipath effect by utilizing the frequency diversity provided by CSI and the spatial diversity provided by multiple antennas. Furthermore, sparse representation method is employed to eliminate the fingerprint noise and to improve the algorithm's robustness and anti noise ability. CSI's sensitive phase feature is also exploited to improve the location accuracy. Using router as signal transmitter, 802.11n CSI-TOOL for collecting CSI, an experimental environment is created with desktop computers and Intel 5300. The test results show that, compared with the typical algorithms, the proposed algorithm can improve the accuracy and precision of positioning. The average precision is about 0.5m and accuracy reaches 91%. © Copyright 2016, Institute of Software, the Chinese Academy of Sciences. All rights reserved.

关键词： Channel state information

来源：评论

学校读者我要写书评

暂无评论

data Services for Carpooling Based on large-scale Traffic data analysis

Data Services for Carpooling Based on Large-Scale Traffic Da...

引用

IEEE International Conference on Services Computing (SCC)

作者： Zhongmei Zhang Guiling Wang Bo Cao Yanbo Han Beijing Key Laboratory on Integration and Analysis of Large-scale Stream Data North China University of Technology Beijing China School of Computer Science and Technology Tianjin University Tianjin China North China University of Technology Beijing Beijing CN

With the social development and vehicle increasing, traffic congestion becomes a pressing problem. Carpooling is one solution for traffic congestion. This paper begins with a motivation case and proposes a service-based method to automatically identify vehicles which travel together (i.e., Traveling companion) and provide carpooling candidates for users in heavy urban traffic. This paper focuses on services design and implementation of the carpooling functions in a distributed parallel computing environment. Through a comprehensive evaluation by experiments, our proposal is shown to deliver good efficiency and effectiveness.

关键词： Vehicles Trajectory Servers Licenses Sensors Distributed databases Web services

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：