检索结果-内蒙古大学图书馆

A Multi-Objective Data Placement Method for IoT Applications Over Big Data Using NSGA-II

学校读者我要写书评

暂无评论

A Multi-Objective Data Placement Method for IoT Applications...

IEEE/ACM Int'l Conference on & Int'l Conference on Cyber, Physical and Social Computing (CPSCom) Green Computing and Communications (GreenCom)

作者： Xiaolong Xu Renhao Gu Yuan Yuan Kai Peng Yadang Chen Wanchun Dou Alex X. Liu Department of Computer Science and Engineering Michigan State University MI USA Jiangsu Engineering Centre of Network Monitoring Nanjing University of Information Science and Technology Nanjing China College of Engineering Huaqiao University Quanzhou Fujian China State Key Laboratory for Novel Software Technology Nanjing University Nanjing China

The Internet of Things has been developing fast since it connects various devices for human beings to use, monitor or configure these devices, which brings great convenience. Generally, the big data generated by the sensors of IoT applications needs to be collected, stored and processed to realize the services of such applications. For the execution of task from the IoT applications, it may need a variety of datasets for tasks to access and process. However, it is still a challenge to realize the data placement method when taking into account the resource utilization and the energy consumption in data centers along with the data access time for the task sets to access the datasets. In view of this challenge, a multi-objectives data placement method for IoT applications over big data is proposed in this paper. Technically, multi-objectives are analyzed first. Then a heuristic data placement method is designed based on Non-Dominated Sorting Genetic Algorithm II (NSGA-II). Consequentially, experimental evaluation and comparison analysis are conducted to validate the efficiency and effectiveness of our proposed method.

关键词： Manganese Handheld computers Internet of Things Switches Green computing Social computing Blockchain

Joint learning of discriminative low-dimensional image representations based on dictionary learning and two-layer orthogonal projections

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Wei, Xian Shen, Hao Li, Yuanxiang Tang, Xuan Jin, Bo Zhao, Lijun Murphey, Yi Lu Fujian Institute of Research on the Structure of Matter Chinese Academy of Sciences China Technical University of Munich Germany and fortiss GmbH Munich Germany Shanghai Key Lab for Trustworthy Computing School of Computer Science and Software Engineering East China Normal University China School of Aeronautics & Astronautics Shanghai Jiao Tong University Shanghai200240 China State Key Laboratory of Robotics and System Harbin Institute of Technology Harbin150006 China Department of Electrical and Computer Engineering University of Michigan-Dearborn DearbornMI48128 United States

This work investigates the problem of efficiently learning discriminative low-dimensional representations of multi-class large-scale image objects. We propose a generic deep learning approach by taking advantages of Convolutional Neural Networks (CNN), sparse dictionary learning, and orthogonal projections. CNN is not only powerful on feature extraction, but also robust to spatial variance and changes. Sparse dictionary learning is well known for disentangling nonlinear underlying discriminative factors in data. The orthogonal projection is a notable efficient tool to project multi-class data onto low dimensional discriminative subspace. The proposed procedure can be summarized as follows. At first, a CNN is employed to extract high-dimensional (HD) preliminary convolutional features. Secondly, to avoid the high computational cost of direct sparse coding on HD CNN features, we present to learn sparse representation (SR) in an orthogonal projected space over a task-driven sparsifying dictionary. We then exploit the discriminative projection on SR. The whole learning process is treated as a joint optimization problem of trace quotient maximization, which involves the CNN parameters, the orthogonal projection on CNN features, the dictionary and the discriminative projection on sparse codes. The related cost function is well defined on product manifold of the Stiefel manifold, the Oblique manifold, and the Grassmann manifold. It is optimized via a geometrical stochastic gradient descent algorithm. Finally, the quality of dictionary and projections learned by the proposed approach is further investigated in terms of image classification. The experimental results show that the approach can achieve a strongly competitive performance with state-of-the-art image classification methods. Copyright © 2019, The Authors. All rights reserved.

关键词： Convolution

Multiple piecewise constant with geodesic active contours (MPC-GAC) framework for interactive image segmentation using graph cut optimization

学校读者我要写书评

暂无评论

Image and Vision Computing 2018年

作者： Tao, Wenbing Tai, Xue-Cheng School of Computer Science and Technology Huazhong University of Science and Technology Wuhan 430074 China China Division of Mathematical Sciences School of Physical and Mathematical Sciences Nanyang Technological University Singapore 637616 Singapore Department of Mathematics University of Bergen 5007 Bergen Norway Norway State Key Laboratory for Novel Software Technology Nanjing University Nanjing 210093 China China

This paper proposes an improved variational model, multiple piecewise constant with geodesic active contour (MPC-GAC) model, which generalizes the region-based active contour model by Chan and Vese, 2001 [11] and merges the edge-based active contour by Caselles et al., 1997 [7] to inherit the advantages of region-based and edge-based image segmentation models. We show that the new MPC-GAC energy functional can be iteratively minimized by graph cut algorithms with high computational efficiency compared with the level set framework. This iterative algorithm alternates between the piecewise constant functional learning and the foreground and background updating so that the energy value gradually decreases to the minimum of the energy functional. The k-means method is used to compute the piecewise constant values of the foreground and background of image. We use a graph cut method to detect and update the foreground and background. Numerical experiments show that the proposed interactive segmentation method based on the MPC-GAC model by graph cut optimization can effectively segment images with inhomogeneous objects and background. © 2011.

关键词： Image segmentation

Deep discrete supervised hashing

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Jiang, Qing-Yuan Cui, Xue Li, Wu-Jun National Key Laboratory for Novel Software Technology Department of Computer Science and Technology Nanjing University Nanjing210023 China

Hashing has been widely used for large-scale search due to its low storage cost and fast query speed. By using supervised information, supervised hashing can significantly outperform unsupervised hashing. Recently, discrete supervised hashing and deep hashing are two representative progresses in supervised hashing. On one hand, hashing is essentially a discrete optimization problem. Hence, utilizing supervised information to directly guide discrete (binary) coding procedure can avoid sub-optimal solution and improve the accuracy. On the other hand, deep hashing, which integrates deep feature learning and hash-code learning into an end-to-end architecture, can enhance the feedback between feature learning and hash-code learning. The key in discrete supervised hashing is to adopt supervised information to directly guide the discrete coding procedure in hashing. The key in deep hashing is to adopt the supervised information to directly guide the deep feature learning procedure. However, there have not existed works which can use the supervised information to directly guide both discrete coding procedure and deep feature learning procedure in the same framework. In this paper, we propose a novel deep hashing method, called deep discrete supervised hashing (DDSH), to address this problem. DDSH is the first deep hashing method which can utilize supervised information to directly guide both discrete coding procedure and deep feature learning procedure, and thus enhance the feedback between these two important procedures. Experiments on three real datasets show that DDSH can outperform other state-of-the-art baselines, including both discrete hashing and deep hashing baselines, for image retrieval. Copyright © 2017, The Authors. All rights reserved.

关键词： Hash functions

A Simple Analysis for Exp-concave Empirical Minimization with Arbitrary Convex Regularizer

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Yang, Tianbao Li, Zhe Zhang, Lijun Department of Computer Science University of Iowa National Key Laboratory for Novel Software Technology Nanjing University

In this paper, we present a simple analysis of fast rates with high probability of empirical minimization for stochastic composite optimization over a finite-dimensional bounded convex set with exponential concave loss functions and an arbitrary convex regularization. To the best of our knowledge, this result is the first of its kind. As a byproduct, we can directly obtain the fast rate with high probability for exponential concave empirical risk minimization with and without any convex regularization, which not only extends existing results of empirical risk minimization but also provides a unified framework for analyzing exponential concave empirical risk minimization with and without any convex regularization. Our proof is very simple only exploiting the covering number of a finite-dimensional bounded set and a concentration inequality of random vectors. Copyright © 2017, The Authors. All rights reserved.

关键词： Stochastic systems

Deep Attentive Features for Prostate Segmentation in 3D Transrectal Ultrasound

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Wang, Yi Dou, Haoran Hu, Xiaowei Zhu, Lei Yang, Xin Xu, Ming Qin, Jing Heng, Pheng-Ann Wang, Tianfu Ni, Dong National-Regional Key Technology Engineering Laboratory for Medical Ultrasound Guangdong Key Laboratory for Biomedical Measurements and Ultrasound Imaging School of Biomedical Engineering Health Science Center Shenzhen University Shenzhen China Lab Shenzhen China Department of Computer Science and Engineering The Chinese University of Hong Kong Hong Kong Centre for Smart Health School of Nursing The Hong Kong Polytechnic University Hong Kong Department of Medical Ultrasonics The First Affiliated Hospital Institute of Diagnostic and Interventional Ultrasound Sun Yat-Sen University Guangzhou China

Automatic prostate segmentation in transrectal ultrasound (TRUS) images is of essential importance for image-guided prostate interventions and treatment planning. However, developing such automatic solutions remains very challenging due to the missing/ambiguous boundary and inhomogeneous intensity distribution of the prostate in TRUS, as well as the large variability in prostate shapes. This paper develops a novel 3D deep neural network equipped with attention modules for better prostate segmentation in TRUS by fully exploiting the complementary information encoded in different layers of the convolutional neural network (CNN). Our attention module utilizes the attention mechanism to selectively leverage the multilevel features integrated from different layers to refine the features at each individual layer, suppressing the non-prostate noise at shallow layers of the CNN and increasing more prostate details into features at deep layers. Experimental results on challenging 3D TRUS volumes show that our method attains satisfactory segmentation performance. The proposed attention mechanism is a general strategy to aggregate multi-level deep features and has the potential to be used for other medical image segmentation tasks. The code is publicly available at https://***/wulalago/DAF3D. © 2019, CC BY.

关键词： Deep neural networks

Amplified locality-sensitive hashing for privacy-preserving distributed service recommendation 10th

学校读者我要写书评

暂无评论

Amplified locality-sensitive hashing for privacy-preserving ...

10th International Conference on Security, Privacy and Anonymity in Computation, Communication and Storage, SpaCCS 2017

作者： Qi, Lianyong Dou, Wanchun Zhang, Xuyun Yu, Shui School of Information Science and Engineering Qufu Normal University Rizhao276826 China State Key Laboratory for Novel Software Technology Department of Computer Science and Technology Nanjing University Nanjing210023 China Department of Electrical and Computer Engineering University of Auckland Auckland1023 New Zealand School of Information Technology Deakin University Melbourne3125 Australia

ISBN: (纸本)9783319723884

With the ever-increasing volume of services registered in various web communities, service recommendation techniques, e.g., Collaborative Filtering (i.e., CF) have provided a promising way to alleviate the heavy burden on the service selection decisions of target users. However, traditional CF-based service recommendation approaches often assume that the recommendation bases, i.e., historical service quality data are centralized, without considering the distributed service recommendation scenarios as well as the resulted privacy leakage risks. In view of this shortcoming, Locality-Sensitive Hashing (LSH) technique is recruited in this paper to protect the private information of users when distributed service recommendations are made. Furthermore, LSH is essentially a probability-based search technique and hence may generate "False-positive" or "False-negative" recommended results;therefore, we amplify LSH by AND/OR operations to improve the recommendation accuracy. Finally, through a set of experiments deployed on a real distributed service quality dataset, i.e., WS-DREAM, we validate the feasibility of our proposed recommendation approach named DistSRAmplify-LSH in terms of recommendation accuracy and efficiency while guaranteeing privacy-preservation in the distributed environment. © 2017, Springer International Publishing AG.

关键词： Collaborative filtering

Data Collection Strategy in Low Duty Cycle Wireless Sensor Networks with Mobile Sink

学校读者我要写书评

暂无评论

International Journal of Communications, Network and System sciences 2017年第5期10卷 227-239页

作者： Xiaofeng Tang Li Xie State Key Laboratory of Novel Software Technology Nanjing University Nanjing China Department of Computer Science and Technology Nanjing University Nanjing China

The lifetime of wireless sensor networks can be improved by imposing low duty cycle, but doing so could not solve unbalanced energy consumption and will increase transmission latency. To avoid this, this paper gives a new method to collect data by mobile sink. The proper data collection route is selected according to the sink speed and buffer size of the sensors. The sensors only wake up when the sink approaches them. When certain sensors detect an emergency, the sink catches the message quickly and moves to the hotspot to decrease message relay in the network. The result of simulation by OPNET shows that this protocol can reduce transmission data in the network and prolong the network lifetime.

关键词： Wireless Sensor Networks Low Duty Cycle Mobile Sink

Multiobjective optimization differential evolution enhanced with principle component analysis for constrained optimization

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Huang, Wei Xu, Tao He, Jun Li, Kangshun Tianjin Key Laboratory of Intelligent and Novel Software Technology School of Computer Science and Engineering Tianjin University of Technology China Department of Computer Science Aberystwyth University AberystwythSY23 3DB United Kingdom School of Science and Technology Nottingham Trent University NottinghamNG11 8NS United Kingdom College of Mathematics and Informatics South China Agricultural University Guangzhou510642 China

Multiobjective optimization evolutionary algorithms have been successfully applied to solving constrained optimization problems. This paper proposes a new multiobjective optimization differential evolution algorithm for constrained optimization. Through a study of fitness landscapes using principle component analysis, we discover a statistic method of identifying the valley direction in a valley landscape. Based on this discovery, a new search operator called PCA-projection is constructed which projects an individual to a position along the valley direction. Then multiobjective optimization differential evolution using this projection operator is designed for constrained optimization. A comparative experiment has been implemented between the proposed algorithm and a state-of-the-art multiobjective differential evolution algorithm on a standard set of 24 benchmarks. Experimental results show that the new algorithm makes a significant improvement in terms of solution accuracy. The proposed algorithm is also competitive with ten evolutionary algorithms participated in an IEEE CEC 2006 competition and is ranked third in terms of the final rank. Copyright © 2018, The Authors. All rights reserved.

关键词： Multiobjective optimization