检索结果-内蒙古大学图书馆

TDFI: Two-stage Deep Learning Framework for Friendship Inference via Multi-source Information

学校读者我要写书评

暂无评论

TDFI: Two-stage Deep Learning Framework for Friendship Infer...

IEEE Annual Joint Conference: INFOCOM, IEEE computer and Communications Societies

作者： Yi Zhao Meina Qiao Haiyang Wang Rui Zhang Dan Wang Ke Xu Qi Tan Beijing National Research Center for Information Science and Technology (BNRist) P.R. China School of Automation Science and Electrical Engineering Beihang University P.R. China Department of Computer Science University of Minnesota at Duluth USA School of Computer Science and Center for OPTIMA Northwestern Polytechnical University P.R. China Department of Computing The Hong Kong Polytechnic University Hong Kong

Due to the explosive growth of social network services, friendship inference has been widely adopted by Online Social Service Providers (OSSPs) for friend recommendation. The conventional techniques, however, have limitations in accuracy or scalability to handle such a large yet sparse multi-source data. For example, the OSSPs will be required to manually give the order in which the various information is applied. This unavoidably reduces the applicability of existing friend recommendation systems. To address this issue, we propose a Two-stage Deep learning framework for Friendship Inference (TDFI). This approach can utilize multi-source information simultaneously with low complexity. In particular, we apply an Extended Adjacency Matrix (EAM) to represent the multi-source information. We then adopt an improved Deep AutoEncoder Network (iDAEN) to extract the fused feature vector for each user. The TDFI framework also provides an improved Deep Siamese Network (iDSN) to measure user similarity from iDAEN. Finally, we evaluate the effectiveness and robustness of TDFI on three large-scale real-world datasets. It shows that TDFI can effectively handle the sparse multi-source data while providing better accuracy for friend recommendation.

关键词： Feature extraction Complexity theory Deep learning Scalability computer science Facebook

Critical success factors to improve the game development process from a developer's perspective

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Aleem, Saiqa Capretz, Luiz Fernando Ahmed, Faheem Department of Electrical and Computer Engineering University of Western Ontario LondonON Canada Department of Computing Science Thompson River University KamloopsBC Canada

The growth of the software game development industry is enormous and is gaining importance day by day. This growth imposes severe pressure and a number of issues and challenges on the game development community. Game development is a complex process, and one important game development choice is to consider the developer perspective to produce good-quality software games by improving the game development process. The objective of this study is to provide a better understanding of the developer's dimension as a factor in software game success. It focusses mainly on an empirical investigation of the effect of key developer factors on the software game development process and eventually on the quality of the resulting game. A quantitative survey was developed and conducted to identify key developer factors for an enhanced game development process. For this study, the developed survey was used to test the research model and hypotheses. The results provide evidence that game development organizations must deal with multiple key factors to remain competitive and to handle high pressure in the software game industry. The main contribution of this paper is to investigate empirically the influence of key developer factors on the game development process. Copyright © 2018, The Authors. All rights reserved.

关键词： Surveys

Machine-learning enables Image reconstruction and classification in a "see-through"camera

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Pan, Zhimeng Rodriguez, Brian Menon, Rajesh School of Computing University of Utah 50 Central Campus Dr Salt Lake CityUT84112 United States Department of Electrical and Computer Engineering University of Utah 50 Central Campus Dr Salt Lake CityUT84112 United States Banjo Inc. Park CityUT

We demonstrate that image reconstruction can be achieved via a convolutional neural network for a "see-through" computational camera comprised of a transparent window and CMOS image sensor. Furthermore, we compared classification results using a classifier network for the raw sensor data vs the reconstructed images. The results suggest that similar classification accuracy is likely possible in both cases with appropriate network optimizations. All networks were trained and tested for the MNIST (6 classes), EMNIST and the Kanji49 datasets. Copyright © 2019, The Authors. All rights reserved.

关键词： Image reconstruction

DBFT: A Byzantine Fault Tolerant Protocol with Graceful Performance Degradation

学校读者我要写书评

暂无评论

DBFT: A Byzantine Fault Tolerant Protocol with Graceful Perf...

Reliable Distributed Systems

作者： Jingjing Zhang Yingyao Rong Jiannong Cao Chunming Rong Jing Bian Weigang Wu School of Data and Comp. Sci. Sun Yat-Sen University Guangzhou China Department of Computing Hong Kong Polytechnic University HongKong Electrical Engineering & Computer Science Department University of Stavanger Stavanger Norway Guangdong Province Key Lab of Big Data Analysis and Proc. Sun Yat-sen University Guangzhou China

ISBN: (数字)9781728142227

ISBN: (纸本)9781728142234

The surging interest in blockchain has revitalized the search for efficient Byzantine fault-tolerant (BFT) protocols, which are used for blockchains to achieve consensus among replicated data blocks. Most existing BFT protocols perform well in fault-free cases, but they usually suffer from serious performance degradation when faults occur. In this paper, we present DBFT, a BFT protocol that realizes graceful performance degradation in normal cases. The major novelty of DBFT lies in the double-response mechanism, which lets replica nodes deterministically respond to clients twice: one is after the speculative execution phase and the other is after the commitment phase. The double-response mechanism can handle inconsistency in speculative execution, so as to alleviate performance degradation caused by faults. Moreover, DBFT does not involve clients in critical consensus operations so as to reduce the load of clients. The correctness properties, i.e., safety and liveness, of DBFT is rigorously proved. The performance of DBFT is evaluated via experiments and the results show that, DBFT outperforms similar BFT protocols obviously in normal cases.

关键词： cryptographic protocols fault tolerance degradation of performance Fault tolerance cryptographic protocols speculative execution protocols customers Clients Reaction Mechanisms

Blockchain-based firmware update scheme tailored for autonomous vehicles

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Baza, Mohamed Nabil, Mahmoud Lasla, Noureddine Fidan, Kemal Mahmoud, Mohamed Abdallah, Mohamed Department of Electrical and Computer Engineering Tennessee Tech University CookevilleTN United States Division of Information and Computing Technology College of Science and Engineering HBKU Doha Qatar Department of Electrical Engineering and Computer Science University of Tennessee KnoxvilleTN United States

Recently, Autonomous Vehicles (AVs) have gained extensive attention from both academia and industry. AVs are a complex system composed of many subsystems, making them a typical target for attackers. Therefore, the firmware of the different subsystems needs to be updated to the latest version by the manufacturer to fix bugs and introduce new features, e.g., using security patches. In this paper, we propose a distributed firmware update scheme for the AVs' subsystems, leveraging blockchain and smart contract technology. A consortium blockchain made of different AVs manufacturers is used to ensure the authenticity and integrity of firmware updates. Instead of depending on centralized third parties to distribute the new updates, we enable AVs, namely distributors, to participate in the distribution process and we take advantage of their mobility to guarantee high availability and fast delivery of the updates. To incentivize AVs to distribute the updates, a reward system is established that maintains a credit reputation for each distributor account in the blockchain. A zero-knowledge proof protocol is used to exchange the update in return for a proof of distribution in a trustless environment. Moreover, we use attribute-based encryption (ABE) scheme to ensure that only authorized AVs will be able to download and use a new update. Our analysis indicates that the additional cryptography primitives and exchanged transactions do not affect the operation of the AVs network. Also, our security analysis demonstrates that our scheme is efficient and secure against different attacks. Copyright © 2018, The Authors. All rights reserved.

关键词： Smart contract

Faster cnns with direct sparse convolutions and guided pruning 5

学校读者我要写书评

暂无评论

Faster cnns with direct sparse convolutions and guided pruni...

5th International Conference on Learning Representations, ICLR 2017

作者： Park, Jongsoo Li, Hai Li, Sheng Wen, Wei Chen, Yiran Tang, Ping Tak Peter Dubey, Pradeep Intel Labs Department of Electrical and Computing Engineering University of Pittsburgh United States Department of Electrical and Computer Engineering Duke University United States

Phenomenally successful in practical inference problems, convolutional neural networks (CNN) are widely deployed in mobile devices, data centers, and even supercomputers. The number of parameters needed in CNNs, however, are often large and undesirable. Consequently, various methods have been developed to prune a CNN once it is trained. Nevertheless, the resulting CNNs offer limited benefits. While pruning the fully connected layers reduces a CNN's size considerably, it does not improve inference speed noticeably as the compute heavy parts lie in convolutions. Pruning CNNs in a way that increase inference speed often imposes specific sparsity structures, thus limiting the achievable sparsity levels. We present a method to realize simultaneously size economy and speed improvement while pruning CNNs. Paramount to our success is an efficient general sparse-with-dense matrix multiplication implementation that is applicable to convolution of feature maps with kernels of arbitrary sparsity patterns. Complementing this, we developed a performance model that predicts sweet spots of sparsity levels for different layers and on different computer architectures. Together, these two allow us to demonstrate 3.1-7.3× convolution speedups over dense convolution in AlexNet, on Intel Atom, Xeon, and Xeon Phi processors, spanning the spectrum from mobile devices to supercomputers. © ICLR 2019 - Conference Track Proceedings. All rights reserved.

关键词： Convolution

Petri Net Control Method for Pipe-line Systems and Its Implementation via CIF3 ⁎

学校读者我要写书评

暂无评论

IFAC-PapersOnLine 2019年第24期52卷 261-266页

作者： YuHao Fu JiLiang Luo Huifeng Wu Jianhong Ye Yi-sheng Huang College Information Science and Engineering Huaqiao University Xiamen 361021 China College Information Science and Engineering Huaqiao University Xiamen 361021 China and also with Fujian Engineering Research Center of Motor Control and System Optimal Schedule Xiamen 361021 China Institute of Intelligent and Software Technology Hangzhou Dianzi University Hangzhou 310018 China Computer Science and Technology Huaqiao University Xiamen 361021 China and also with Fujian Provincial Key Laboratory of Data Intensive Computing Quanzhou 362000 China Department of Electrical Engineering National Ilan University Taiwan

As for a pipe-line system subjected to complex operations, an approach is proposed to synthesize the controller via Petri nets (PNs) such that the plant is run as concurrently as possible and the loads of equipments are balanced. A P-timed and labeled PN is designed to model the whole process of a pipe-line system, where tasks, including transporting material from one tank to another and cleaning tank, are represented by operational places, and level sensors amounted in tanks are represented by labels assigned to transitions. Further, monitor places are designed to resolve the conflict relations among tasks due to the shared valves and pipes. An method is presented to translate an PN controller into a CIF3 (Compositional Interchange Format) model, which can be converted into a PLC program in the CIF3 tool. A beer filtration plant is taken as an example to illustrate the approach, and its simulation experiments are carried out to verify the theoretic results.

关键词： Chemical plant Valve control Petri net CIF3

PRUNE: Dynamic and decidable dataflow for signal processing on heterogeneous platforms

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Boutellier, Jani Wu, Jiahao Huttunen, Heikki Bhattacharyya, Shuvra S. Laboratory of Pervasive Computing Tampere University of Technology Finland Department of Electrical and Computer Engineering University of Maryland United States Laboratory of Signal Processing Tampere University of Technology Finland Department of Electrical and Computer Engineering University of Maryland United States Laboratory of Pervasive Computing Tampere University of Technology Finland

The majority of contemporary mobile devices and personal computers are based on heterogeneous computing platforms that consist of a number of CPU cores and one or more Graphics Processing Units (GPUs). Despite the high volume of these devices, there are few existing programming frameworks that target full and simultaneous utilization of all CPU and GPU devices of the platform. This article presents a dataflow-flavored Model of Computation (MoC) that has been developed for deploying signal processing applications to heterogeneous platforms. The presented MoC is dynamic and allows describing applications with data dependent run-time behavior. On top of the MoC, formal design rules are presented that enable application descriptions to be simultaneously dynamic and decidable. Decidability guarantees compile-time application analyzability for deadlock freedom and bounded memory. The presented MoC and the design rules are realized in a novel Open Source programming environment "PRUNE" and demonstrated with representative application examples from the domains of image processing, computer vision and wireless communications. Experimental results show that the proposed approach outperforms the state-of-the-art in analyzability, flexibility and performance. Copyright © 2018, The Authors. All rights reserved.

关键词： computer aided design

PnP-AdaNet: Plug-and-play adversarial domain adaptation network with a benchmark at cross-modality cardiac segmentation

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Dou, Qi Ouyang, Cheng Chen, Cheng Chen, Hao Glocker, Ben Zhuang, Xiahai Heng, Pheng-Ann Department of Computer Science and Engineering Chinese University of Hong Kong Department of Computing Imperial College London Department of Electrical Engineering and Computer Science University of Michigan Department of Computing Imperial College London Department of Computer Science and Engineering Chinese University of Hong Kong Imsight Medical Technology Co Ltd. China Department of Computing Imperial College London School of Data Science Fudan University China

Deep convolutional networks have demonstrated the state-of-the-art performance on various medical image computing tasks. Leveraging images from different modalities for the same analysis task holds clinical benefits. However, the generalization capability of deep models on test data with different distributions remain as a major challenge. In this paper, we propose the PnP-AdaNet (plug-and-play adversarial domain adaptation network) for adapting segmentation networks between different modalities of medical images, e.g., MRI and CT. We propose to tackle the significant domain shift by aligning the feature spaces of source and target domains in an unsupervised manner. Specifically, a domain adaptation module flexibly replaces the early encoder layers of the source network, and the higher layers are shared between domains. With adversarial learning, we build two discriminators whose inputs are respectively multi-level features and predicted segmentation masks. We have validated our domain adaptation method on cardiac structure segmentation in unpaired MRI and CT. The experimental results with comprehensive ablation studies demonstrate the excellent efficacy of our proposed PnP-AdaNet. Moreover, we introduce a novel benchmark on the cardiac dataset for the task of unsupervised cross-modality domain adaptation. We will make our code and database publicly available, aiming to promote future studies on this challenging yet important research topic in medical imaging. Copyright © 2018, The Authors. All rights reserved.

关键词： Magnetic resonance imaging