检索结果-内蒙古大学图书馆

2011 8th International Conference on Fuzzy systems and Knowledge Discovery, FSKD 2011, Jointly with the 2011 7th International Conference on Natural Computation, ICNC'11

作者： Jan, Sadaqat Li, Maozhen Al-Sultany, Ghaidaa Al-Raweshidy, Hamed School of Engineering and Design Brunel University Uxbridge Middlesex UB8 3PH United Kingdom Key Laboratory of Embedded Systems and Service Computing Ministry of Education Tongji University China

ISBN: (纸本)9781612841816

Recent advances in mobile technologies have emerged new challenges for researchers. File management and retrieval on resource-limited devices has become a challenging problem as these devices are now equipped with larger storage capacities. This paper presents an overview about the possibilities of implementing Semantic Web Technologies in order to facilitate the file retrieval on resource-limited devices. We have proposed a semantic based file retrieval framework which utilizes a generic ontology in file search process. The search module is implemented in Java ME platforms as a case study. Performance of the proposed search module is evaluated through experimental tests along with probabilistic evaluations. The implemented module not only automates file retrieval process but also shows significant improvement in file retrieval efficiency by utilizing the knowledge of employed ontology in the search module. © 2011 IEEE.

关键词： Ontology

来源：评论

学校读者我要写书评

暂无评论

Accelerating large-scale human action recognition with GPU-based spark 17th

Accelerating large-scale human action recognition with GPU-b...

引用

17th Pacific-Rim Conference on Multimedia, PCM 2016

作者： Wang, Hanli Zheng, Xiaobin Xiao, Bo Department of Computer Science and Technology Tongji University Shanghai China Key Laboratory of Embedded System and Service Computing Ministry of Education Tongji University Shanghai China

ISBN: (纸本)9783319488950

In this paper, a large-scale human action recognition system is proposed which is built upon the combination of the rising big data processing technology Spark and the powerful Graphics Processing Unit (GPU) in order to fully utilize the efficient in-memory computing ability of Spark and the fine-grained parallel computing capacity of GPU for visual data processing. A number of key algorithms for human action recognition including trajectory based feature extraction, Gaussian Mixture Model (GMM) generation and Fisher Vector (FV) encoding are performed with the proposed GPU-based Spark framework. The experimental results on the benchmark human action dataset Hollywood-2 demonstrate that the proposed GPU-based Spark framework is able to dramatically accelerate the process of human action recognition. © Springer International Publishing AG 2016.

关键词： MapReduce

来源：评论

学校读者我要写书评

暂无评论

SFedXL: Semi-Synchronous Federated Learning With Cross-Sharpness and Layer-Freezing

引用

IEEE Internet of Things Journal 2025年

作者： Zhao, Mingxiong Zhao, Shihao Feng, Chenyuan Yang, Howard H. Niyato, Dusit Quek, Tony Q. S. Yunnan University National Pilot School of Software Kunming650500 China Ministry of Education Engineering Research Center of Integration and Application of Digital Learning Technology Beijing100039 China Ministry of Education Engineering Research Center of Cyberspace Kunming650504 China Yunnan University of Finance and Economics Yunnan Key Laboratory of Service Computing Kunming650221 China EURECOM Sophia Antipolis06410 France Zhejiang University University of Illinois Urbana-Champaign Institute Zhejiang University Haining314400 China Nanyang Technological University School of Computer Science and Engineering 639798 Singapore Singapore University of Technology and Design Information Systems Technology and Design Pillar 487372 Singapore

Federated learning (FL) emerges as a potential solution for enabling multiple terminal devices to collaboratively accomplish computational tasks within an Unmanned Aerial Vehicle (UAV) swarm. However, traditional FL approaches, predicated on synchronous data aggregation, are not feasible for a UAV swarm owing to the inherently variable and dynamic nature of their communication networks compared with terrestrial systems. Furthermore, the data procured by UAVs is often highly heterogeneous, attributable to disparities in deployment environments and device attributes. Considering the distinct flight paths and unique operational conditions encountered by different UAVs, a considerable amount of data remains unlabeled. To tackle the challenges associated with asynchronous operations and the prevalence of unlabeled data, we introduce a novel framework termed Semi-synchronous FL with Cross-Sharpness and Layer-Freezing (SFedXL), tailored for a UAV swarm. In particular, we devise a cross-sharpness model training strategy aimed at optimizing the utilization of both labeled and unlabeled datasets. Additionally, we propose an innovative semi-synchronous model aggregation protocol, complemented by client-specific layer-freezing and client cluster scheduling, designed to expedite the training process. Our simulation results indicate that the proposed algorithm surpasses current FL methods in terms of object recognition accuracy and communication efficiency, albeit with a trade-off of increased local computation latency. © 2014 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

An Effective Principal Curves Extraction Algorithm for Complex Distribution Dataset 1

引用

5th International Conference on Rough Set and Knowledge Technology (RSKT)

作者： Zhang, Hongyun Miao, Duoqian Sun, Lijun Ye, Ying The Key Laboratory of Embedded System and Service Computing Ministry of Education China Tongji University Shanghai 201804 China School of Electronic and Information Engineering Tongji University Shanghai 201804 China

ISBN: (数字)9783642162480

ISBN: (纸本)9783642162473

This paper proposes a new method for finding principal curves from complex distribution dataset. Motivated by solving the problem, which is that existing methods did not perform well on finding principal curve in complex distribution dataset with high curvature, high dispersion and self-intersecting, such as spiral-shaped curves, Firstly, rudimentary principal graph of data set is created based on the thinning algorithm, and then the contiguous vertices are merged. Finally the fitting-and-smoothing step introduced by Kegl is improved to optimize the principal graph, and Kegl's restructuring step is used to rectify imperfections of principal graph. Experimental results indicate the effectiveness of the proposed method on finding principal curves in complex distribution dataset.

关键词： Principal curves Complex distribution dataset Thinning algorithm Fitting-smoothing step Image skeletonization

来源：评论

学校读者我要写书评

暂无评论

Improving bag-of-words representation with efficient twin feature integration 15

Improving bag-of-words representation with efficient twin fe...

引用

7th International Conference on Internet Multimedia computing and service, ICIMCS 2015

作者： Wang, Lei Wang, Hanli Department of Computer Science and Technology Tongji University Shanghai China Key Laboratory of Embedded System and Service Computing Ministry of Education Tongji University Shanghai China

ISBN: (纸本)9781450335287

In recent years, the Bag-of-Words (BoW) model has been widely used in most state-of-the-art large-scale image re-trieval systems. However, the standard BoW based systems suffer from low discriminative power of local features as well as quantization errors that significantly affect the retrieval performance. In this paper, twin feature is employed and well combined with two advanced techniques including Ham-ming Embedding (HE) and Multiple Assignment (MA) to construct a discriminative image retrieval system on BoW representation in an efficient way. Experimental results on two benchmark datasets Oxford5k and Paris6k demonstrate that the proposed technique can greatly refine the visual matching process and enhance the final performance for im-age retrieval. © 2015 ACM.

关键词： Image retrieval

来源：评论

学校读者我要写书评

暂无评论

Low frequency analysis of resting-state fMRI

Low frequency analysis of resting-state fMRI

引用

2012 International Conference on Computer Science and Information Processing, CSIP 2012

作者： He, Lianghua Ji, Hongfei Wan, Meng Liu, Shuang Key Laboratory of Embedded System and Service Computing Ministry of Education Tongji University Shanghai China Center for Science and Technology Development of the Ministry Education Beijing China

ISBN: (纸本)9781467314114

Resting state functional magnetic resonance imaging (rsfMRI) is a relatively new and an powerful method for evaluating regional interactions that occur when a participant is not performing an explicit task. Because of sensitiveness to time delay and length of time courses, respectively, traditional methods of correlation and coherence based on region of interest are not very suitable for rsfMRI. In this paper, we analyzed low frequency property of rsfMRI data. Firstly, we calculated the low frequency of resting-state Blood-Oxygenation-Level-Dependent(BOLD) signal on every voxel using Welch method, based on which we analyzed the statistical distribution cross subjects and voxels. The low frequency feature is proved by a series of experiments to be more robust and consistent comparing with coorelation in time domain and coherency in frequency domain. We found that the property of low frequency statistical distribution is dominant on narrow band, which is around 0.0137HZ. © 2012 IEEE.

关键词： Frequency domain analysis

来源：评论

学校读者我要写书评

暂无评论

Discretized Gaussian Mixture Hyperprior for Learned Image Compression with Mask Module

Discretized Gaussian Mixture Hyperprior for Learned Image Co...

引用

2022 IEEE International Conference on Multimedia and Expo, ICME 2022

作者： Wang, Shengkai Wang, Hanli Tongji University Department of Computer Science and Technology Shanghai China Tongji University Key Laboratory of Embedded System and Service Computing Ministry of Education Shanghai China

ISBN: (数字)9781665485630

ISBN: (纸本)9781665485630

Learned image compression approaches have shown great potential with promising results. However, according to the commonly used measurement methods, there still lies a performance gap between learned compression methods and the latest compression standard versatile video coding (VVC), because of the remaining redundancy existing in contemporary algorithms. To obtain a more accurate entropy model for rate estimation, discretized Gaussian mixture hyperprior is proposed in this work to parameterize the distribution of latent codes. In addition, a proposed mask module is exploited to enhance the feature extraction ability of the encoder and adaptively allocate bit rates. In this case, the proposed learned image compression model achieves the state-of-the-art performance among the existing learned compression methods and most compression standards on both Kodak24 and CLIC Mobile Validation datasets. The proposed model also outperforms VVC under several bitrate scenarios. © 2022 IEEE.

关键词： Image compression

来源：评论

学校读者我要写书评

暂无评论

Behavioral authentication method for mobile gesture against resilient user posture 3

Behavioral authentication method for mobile gesture against ...

引用

2016 3rd International Conference on systems and Informatics, ICSAI 2016

作者： Liu, Qiang Wang, Mimi Zhao, Peihai Yan, Chungang Ding, Zhijun Department of Computer Science and Technology Tongji University Shanghai China Key Laboratory of Embedded System and Service Computing Tongji University Ministry of Education Shanghai China

ISBN: (纸本)9781509055210

The password pattern has become a widely used mobile authentication method. However, there are still some potential security problems since the passwords are easy to be cracked by some malicious software. An important research direction of improving its security is adding behavior pattern into the password pattern. The existing methods mainly used user's gesture behavior data such as the location, pressure and contact area of finger collected by touch screen to build a behavior authentication model, which did not consider the influence of user's posture on user's gesture behavior. This paper aims to propose a gesture authentication construction method that is resilient against the change of user's posture. Firstly, for the posture behavior data collected by mobile's orientation sensor and acceleration sensor, we use K-means algorithm to get user's postures. Secondly, we train a gesture authentication sub-model for each posture based on the data collected by touch screen. Finally, we give a behavior authentication method based on these models. Our experimental result shows that the method achieves an effect of 4.36% False Acceptance Rate (FAR) and 5.03% False Rejection Rate (FRR) © 2016 IEEE.

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

Design and implementation of communication module in passive ultrasonic sensor networks

Design and implementation of communication module in passive...

引用

2010 International Conference on Computer, Mechatronics, Control and Electronic Engineering, CMCE 2010

作者： Han, Lina Zhao, Rui Key Laboratory of Embedded System and Service Computing Ministry of Education Tongji University Shanghai China Third Research Institute of The Ministry of Public Security Shanghai China

ISBN: (纸本)9781424479566

Passive sensor networks can achieve accurate detection of target under complex environment. In order to adapt to different communication demands of sensor networks in different environments, this paper designed and implemented a wireless and wired mixed communication module, that is, a communication system combined short-distance wireless communication based on radio frequency technology with broadband cable communication. Simulation results show that our system can achieve the desired requirements in different circumstances. © 2010 IEEE.

关键词： Ultrasonic applications

来源：评论

学校读者我要写书评

暂无评论

Application of SIRUS in credit card fraud detection 1

引用

7th International Conference on Computational Data and Social Networks, CSoNet 2018

作者： Zhang, Yuwei Liu, Guanjun Luan, Wenjing Yan, Chungang Jiang, Changjun Department of Computer Science and Technology Tongji University Shanghai201804 China Key Laboratory of Embedded System and Service Computing Ministry of Education Shanghai201804 China

ISBN: (数字)9783030046484

ISBN: (纸本)9783030046477

Credit card fraud problem is very common in recent years. It not only causes economic loss to people, but also causes trust crisis to enterprises. Due to the imbalance of data, fraud detection has always been tricky. In our previous work, we proposed a method of dealing with the class imbalance problem based on stacking ensemble learning and inverse random undersampling method (SIRUS). First, the inverse random undersampling method is used to generate multiple data subsets from the original data set. Then we use the stacking ensemble learning method for each data subset to train several different learners (also called first-level learners), and then the results generated by each first-level learner are taken as features to train a meta learner. We apply SIRUS to detect the credit card fraud in this paper. Our dataset comes from a financial company in China. A variety of measurements such as recall, precision, accuracy, F-measure, and G-mean to illustrate the effectiveness of our method in fraud detection. © Springer Nature Switzerland AG 2018.

关键词： Learning systems

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

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

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：