Tsinghua Science and Technology

SPECIAL SECTION ON PARALLEL AND DISTRIBUTED COMPUTING,APPLICATIONS AND TECHNOLOGIES

  • MIX-RS:A Multi-Indexing System Based on HDFS for Remote Sensing Data Storage

    Jiashu Wu;Jingpan Xiong;Hao Dai;Yang Wang;Chengzhong Xu;

    A large volume of Remote Sensing(RS) data has been generated with the deployment of satellite technologies.The data facilitate research in ecological monitoring,land management and desertification,etc.The characteristics of RS data(e.g.,enormous volume,large single-file size,and demanding requirement of fault tolerance) make the Hadoop Distributed File System(HDFS) an ideal choice for RS data storage as it is efficient,scalable,and equipped with a data replication mechanism for failure resilience.To use RS data,one of the most important techniques is geospatial indexing.However,the large data volume makes it time-consuming to efficiently construct and leverage.Considering that most modern geospatial data centres are equipped with HDFS-based big data processing infrastructures,deploying multiple geospatial indices becomes natural to optimise the efficacy.Moreover,because of the reliability introduced by high-quality hardware and the infrequently modified property of the RS data,the use of multi-indexing will not cause large overhead.Therefore,we design a framework called Multi-IndeXing-RS(MIX-RS) that unifies the multi-indexing mechanism on top of the HDFS with data replication enabled for both fault tolerance and geospatial indexing efficiency.Given the fault tolerance provided by the HDFS,RS data are structurally stored inside for faster geospatial indexing.Additionally,multi-indexing enhances efficiency.The proposed technique naturally sits on top of the HDFS to form a holistic framework without incurring severe overhead or sophisticated system implementation efforts.The MIX-RS framework is implemented and evaluated using real remote sensing data provided by the Chinese Academy of Sciences,demonstrating excellent geospatial indexing performance.

    2022年06期 v.27 881-893页 [查看摘要][在线阅读][下载 2479K]
    [下载次数:59 ] |[网刊下载次数:0 ] |[引用频次:0 ] |[阅读次数:24 ]
  • Hybrid Navigation Method for Multiple Robots Facing Dynamic Obstacles

    Kaidong Zhao;Li Ning;

    With the continuous development of robotics and artificial intelligence,robots are being increasingly used in various applications.For traditional navigation algorithms,such as Dijkstra and A*,many dynamic scenarios in life are difficult to cope with.To solve the navigation problem of complex dynamic scenes,we present an improved reinforcement-learning-based algorithm for local path planning that allows it to perform well even when more dynamic obstacles are present.The method applies the gmapping algorithm as the upper layer input and uses reinforcement learning methods as the output.The algorithm enhances the robots' ability to actively avoid obstacles while retaining the adaptability of traditional methods.

    2022年06期 v.27 894-901页 [查看摘要][在线阅读][下载 1871K]
    [下载次数:42 ] |[网刊下载次数:0 ] |[引用频次:0 ] |[阅读次数:17 ]
  • A Two-Stage Method for Routing in Field-Programmable Gate Arrays with Time-Division Multiplexing

    Peihuang Huang;Longkun Guo;Long Sun;Xiaoyan Zhang;

    Emerging applications widely use field-programmable gate array(FPGA) prototypes as a tool to verify modern very-large-scale integration(VLSI) circuits,imposing many problems,including routing failure caused by the limited number of connections among blocks of FPGAs therein.Such a shortage of connections can be alleviated through time-division multiplexing(TDM),by which multiple signals sharing an identical routing channel can be transmitted.In this context,the routing quality dominantly decides the performance of such systems,proposing the requirement of minimizing the signal delay between FPGA pairs.This paper proposes algorithms for the routing problem in a multi-FPGA system with TDM support,aiming to minimize the maximum TDM ratio.The algorithm consists of two major stages:(1) A method is proposed to set the weight of an edge according to how many times it is shared by the routing requirements and consequently to compute a set of approximate minimum Steiner trees.(2) A ratio assignment method based on the edge-demand framework is devised for assigning ratios to the edges respecting the TDM ratio constraints.Experiments were conducted against the public benchmarks to evaluate our proposed approach as compared with all published works,and the results manifest that our method achieves a better TDM ratio in comparison.

    2022年06期 v.27 902-911页 [查看摘要][在线阅读][下载 618K]
    [下载次数:22 ] |[网刊下载次数:0 ] |[引用频次:0 ] |[阅读次数:16 ]
  • Plausible Heterogeneous Graph k-Anonymization for Social Networks

    Kaiyang Li;Ling Tian;Xu Zheng;Bei Hui;

    The inefficient utilization of ubiquitous graph data with combinatorial structures necessitates graph embedding methods,aiming at learning a continuous vector space for the graph which is amenable to be adopted in traditional machine learning algorithms in favor of vector representations.Graph embedding methods build an important bridge between social network analysis and data analytics as social networks naturally generate an unprecedented volume of graph data continuously.Publishing social network data not only bring benefit for public health,disaster response,commercial promotion,and many other applications,but also give birth to threats that jeopardize each individual's privacy and security.Unfortunately,most existing works in publishing social graph embedding data only focus on preserving social graph structure with less attention paid to the privacy issues inherited from social networks.To be specific,attackers can infer the presence of a sensitive relationship between two individuals by training a predictive model with the exposed social network embedding.In this paper,we propose a novel link-privacy preserved graph embedding framework using adversarial learning,which can reduce adversary's prediction accuracy on sensitive links while persevering sufficient non-sensitive information such as graph topology and node attributes in graph embedding.Extensive experiments are conducted to evaluate the proposed framework using ground truth social network datasets.

    2022年06期 v.27 912-924页 [查看摘要][在线阅读][下载 771K]
    [下载次数:8 ] |[网刊下载次数:0 ] |[引用频次:0 ] |[阅读次数:13 ]

REGULAR ARTICLES

  • Multi-Clock Snapshot Isolation Concurrency Control for NVM Database

    Xuyang Liu;Kang Chen;Mengxing Liu;Shiyu Cai;Yongwei Wu;Weimin Zheng;

    Multi-Clock Snapshot Isolation(MCSI) is a concurrency control mechanism that implements snapshot isolation on a single-layer Non-Volatile Memory(NVM) database.It stores a single copy of data by using multi-version storage to ensure durability and runtime access.With multi-clock transaction timestamp assignment,MCSI can efficiently generate snapshots with vector clocks and use per-thread transaction status arrays to identify uncommitted versions in NVM.For evaluation,we compared MCSI with the PostgreSQL-style concurrency control used in the single-layer NVM database N2DB.The maximum transaction throughput of MCSI is 101%–195% higher than that of N2DB for the YCSB workloads,and 25%–49% higher for the TPC-C workloads.Moreover,the transaction latency of MCSI remains relatively stable as the thread count increases.With 18 worker threads,the average transaction latency of MCSI is 65%–84% lower than that of N2DB for the YCSB workloads and 16%–43% lower for the TPC-C workloads.

    2022年06期 v.27 925-938页 [查看摘要][在线阅读][下载 1465K]
    [下载次数:24 ] |[网刊下载次数:0 ] |[引用频次:0 ] |[阅读次数:16 ]
  • Optimizing the Perceptual Quality of Time-Domain Speech Enhancement with Reinforcement Learning

    Xiang Hao;Chenglin Xu;Lei Xie;Haizhou Li;

    In neural speech enhancement,a mismatch exists between the training objective,i.e.,Mean-Square Error(MSE),and perceptual quality evaluation metrics,i.e.,perceptual evaluation of speech quality and short-time objective intelligibility.We propose a novel reinforcement learning algorithm and network architecture,which incorporate a non-differentiable perceptual quality evaluation metric into the objective function using a dynamic filter module.Unlike the traditional dynamic filter implementation that directly generates a convolution kernel,we use a filter generation agent to predict the probability density function of a multivariate Gaussian distribution,from which we sample the convolution kernel.Experimental results show that the proposed reinforcement learning method clearly improves the perceptual quality over other supervised learning methods with the MSE objective function.

    2022年06期 v.27 939-947页 [查看摘要][在线阅读][下载 626K]
    [下载次数:19 ] |[网刊下载次数:0 ] |[引用频次:0 ] |[阅读次数:16 ]
  • Observation-Driven Multiple UAV Coordinated Standoff Target Tracking Based on Model Predictive Control

    Shun Sun;Yu Liu;Shaojun Guo;Gang Li;Xiaohu Yuan;

    An observation-driven method for coordinated standoff target tracking based on Model Predictive Control(MPC) is proposed to improve observation of multiple Unmanned Aerial Vehicles(UAVs) while approaching or loitering over a target.After acquiring a fusion estimate of the target state,each UAV locally measures the observation capability of the entire UAV system with the Fisher Information Matrix(FIM) determinant in the decentralized architecture.To facilitate observation optimization,only the FIM determinant is adopted to derive the performance function and control constraints for coordinated standoff tracking.Additionally,a modified iterative scheme is introduced to improve the iterative efficiency,and a consistent circular direction control is established to maintain long-term observation performance when the UAV approaches its target.Sufficient experiments with simulated and real trajectories validate that the proposed method can improve observation of the UAV system for target tracking and adaptively optimize UAV trajectories according to sensor performance and UAV-target geometry.

    2022年06期 v.27 948-963页 [查看摘要][在线阅读][下载 3337K]
    [下载次数:26 ] |[网刊下载次数:0 ] |[引用频次:0 ] |[阅读次数:18 ]
  • Self-Renewal Consortium Blockchain Based on Proof of Rest and Strong Smart Contracts

    Wenyu Shen;Xuebing Huang;Yunshan Fu;Yongwei Hou;Li Ling;

    Focusing on the business alliance scenario in blockchains,this paper proposes a new consensus mechanism named proof of rest(PoR) and strong smart contracts.The block structure and logic of PoR consensus are described.And a consortium blockchain system supporting strong smart contracts is designed.We modify the difficulty value algorithm based on proof of work(PoW) and add adjustable parameters.The longer a node rests after creating a block,the less difficult it is to create another new block,hence the term PoR.The penalty for slack nodes,the joining and quitting of nodes,and the adjustment of the expected block creation time can all be accomplished using the strong smart contracts,so the consortium blockchain can realize self-renewal.

    2022年06期 v.27 964-972页 [查看摘要][在线阅读][下载 728K]
    [下载次数:18 ] |[网刊下载次数:0 ] |[引用频次:0 ] |[阅读次数:13 ]
  • A Survey of Human Action Recognition and Posture Prediction

    Nan Ma;Zhixuan Wu;Yiu-ming Cheung;Yuchen Guo;Yue Gao;Jiahong Li;Beiyan Jiang;

    Human action recognition and posture prediction aim to recognize and predict respectively the action and postures of persons in videos.They are both active research topics in computer vision community,which have attracted considerable attention from academia and industry.They are also the precondition for intelligent interaction and human-computer cooperation,and they help the machine perceive the external environment.In the past decade,tremendous progress has been made in the field,especially after the emergence of deep learning technologies.Hence,it is necessary to make a comprehensive review of recent developments.In this paper,firstly,we attempt to present the background,and then discuss research progresses.Secondly,we introduce datasets,various typical feature representation methods,and explore advanced human action recognition and posture prediction algorithms.Finally,facing the challenges in the field,this paper puts forward the research focus,and introduces the importance of action recognition and posture prediction by taking interactive cognition in self-driving vehicle as an example.

    2022年06期 v.27 973-1001页 [查看摘要][在线阅读][下载 1519K]
    [下载次数:65 ] |[网刊下载次数:0 ] |[引用频次:0 ] |[阅读次数:17 ]
  • Indoor Human Fall Detection Algorithm Based on Wireless Sensing

    Chao Wang;Lin Tang;Meng Zhou;Yinfan Ding;Xueyong Zhuang;Jie Wu;

    As the main health threat to the elderly living alone and performing indoor activities,falls have attracted great attention from institutions and society.Currently,fall detection systems are mainly based on wear sensors,environmental sensors,and computer vision,which need to be worn or require complex equipment construction.However,they have limitations and will interfere with the daily life of the elderly.On the basis of the indoor propagation theory of wireless signals,this paper proposes a conceptual verification module using Wi-Fi signals to identify human fall behavior.The module can detect falls without invading privacy and affecting human comfort and has the advantages of noninvasive,robustness,universality,and low price.The module combines digital signal processing technology and machine learning technology.This paper analyzes and processes the channel state information(CSI) data of wireless signals,and the local outlier factor algorithm is used to find the abnormal CSI sequence.The support vector machine and extreme gradient boosting algorithms are used for classification,recognition,and comparative research.Experimental results show that the average accuracy of fall detection based on wireless sensing is more than 90%.This work has important social significance in ensuring the safety of the elderly.

    2022年06期 v.27 1002-1015页 [查看摘要][在线阅读][下载 1760K]
    [下载次数:16 ] |[网刊下载次数:0 ] |[引用频次:0 ] |[阅读次数:19 ]