An Efficient Encrypted Speech Retrieval Based on Unsupervised Hashing and B+ Tree Dynamic Index

Existing speech retrieval systems are frequently confronted with expanding volumes of speech data.The dynamic updating strategy applied to construct the index can timely process to add or remove unnecessary speech data to meet users’real-time retrieval requirements.This study proposes an efficient method for retrieving encryption speech,using unsupervised deep hashing and B+ tree dynamic index,which avoid privacy leak-age of speech data and enhance the accuracy and efficiency of retrieval.The cloud’s encryption speech library is constructed by using the multi-threaded Dijk-Gentry-Halevi-Vaikuntanathan(DGHV)Fully Homomorphic Encryption(FHE)technique,which encrypts the original speech.In addition,this research employs Residual Neural Network18-Gated Recurrent Unit(ResNet18-GRU),which is used to learn the compact binary hash codes,store binary hash codes in the designed B+tree index table,and create a mapping relation of one to one between the binary hash codes and the corresponding encrypted speech.External B+tree index technology is applied to achieve dynamic index updating of the B+tree index table,thereby satisfying users’needs for real-time retrieval.The experimental results on THCHS-30 and TIMIT showed that the retrieval accuracy of the proposed method is more than 95.84%compared to the existing unsupervised hashing methods.The retrieval efficiency is greatly improved.Compared to the method of using hash index tables,and the speech data’s security is effectively guaranteed.

ZB^(+)-tree:一种ZNS SSD感知的新型索引结构

ZNS SSD是近年来提出的一种新型固态硬盘(solid state drive,SSD),它以分区(Zone)的方式管理和存取SSD内的数据.相比于传统SSD,ZNS SSD可以有效提升SSD的读写吞吐,降低写放大,减少SSD的预留空间.但是,ZNS SSD要求Zone内必须采用顺序写模式,并且Zone上的空间分配、垃圾回收等任务都需要用户自行控制.ZNS SSD的这些特性对于传统数据库系统的存储管理、索引、缓存等技术均提出了新的挑战.针对如何使传统的B^(+)-tree索引结构适配ZNS SSD的问题,提出了一种ZNS SSD感知的新型索引结构——ZB^(+)-tree(ZNS-aware B^(+)-tree).ZB^(+)-tree是目前已知的首个ZNS SSD感知的索引,它以B^(+)-tree为基础,利用ZNS SSD内部支持少量随机写的常规Zone(conventional zone,Cov-Zone)和只支持顺序写的顺序Zone(sequential zone,Seq-Zone),通过常规Zone来吸收对ZNS SSD的随机写操作.ZB^(+)-tree将索引节点分散存储在常规Zone和顺序Zone中,并为2种Zone内的节点分别设计了节点结构,使ZB^(+)-tree不仅能够吸收对索引的随机写操作,而且又可以保证顺序Zone内的顺序写要求.在实验中利用null_blk和libzbd模拟ZNS SSD设备,并将现有的CoW B^(+)-tree修改后作为对比索引.结果表明,ZB^(+)-tree在运行时间、空间利用率等多个指标上均优于CoW B^(+)-tree.

HyperTree:高并发B+树索引加速器

B+树是关系型数据库中用来加速查询的常用索引结构,通过构建平衡树维护关键属性的顺序.索引提升了数据库查询性能,但其严格的有序关系增加了数据库表的维护开销.特别是在大数据场景下,数据量激增使得索引查询和维序性能进一步下降.如何平衡B+树的查询和维序性能,以及在大数据场景下提升索引查询和维序的效率,对提升索引系统性能具有重要意义.由此设计了一种专用的B+树索引加速系统,对存储和计算进行协同优化,均衡提升索引查询和维序性能.利用内存突发读写高带宽的特性设计规则的树和节点存储格式以提升内存带宽利用效率,设计高效的同构计算架构和多数据通道以提升索引操作并行度.同时设计解耦合的子树结构缓解索引维护时的树读写冲突.实验结果表明,相比于CPU,B+树索引加速系统能够提升系统查询性能超过6.84倍,提升索引维序性能提升超过29.14倍.

一种wandering B+tree问题解决方法

为了应对磁盘和固态硬盘随机写和顺序写性能差异较大的问题,文件系统和块存储系统通常采用日志结构(log-structured)技术将随机写转换为顺序写.因此,对于日志结构存储系统数据和元数据的修改都以异地写的方式执行.在日志结构存储系统中,B+tree常被用于管理元数据,这就会导致wandering B+tree问题,即树结点异地更新会导致树结构递归更新.目前,现有工作主要通过分离树结点的逻辑索引和物理地址,并使用额外的数据结构和物理设备空间存放树结点逻辑索引和物理地址的映射,从而避免递归更新树结构.但现有方法既引入额外空间开销,又存在额外物理设备空间非顺序写的问题.提出IBT B+tree,将树结点逻辑索引和物理地址均存放在树结构中.同时,基于IBT B+tree结构引入dirty链表设计,并提出了非递归更新的IBT B+tree下刷算法.IBT B+tree既解决了wandering B+tree问题,又不引入额外的数据结构和物理设备空间,消除了固定物理设备空间的非顺序写.分别实现IBT B+tree和基于F2FS中NAT设计的B+tree,在此基础上设计实现Monty-Dev块存储系统以评价2棵B+tree.实验表明,在HDD和SSD介质上,IBT B+tree在写放大和下刷效率方面均优于NAT B+tree.

基于B^(*)-树的连续微流控生物芯片流层物理设计方法

作为连续微流控生物芯片设计中的关键步骤,流层物理设计是一个复杂的多目标优化问题,传统方法通常将其分为布局和布线2个阶段。为弥补这2个阶段之间的交互不足,提出了一种基于B^(*)-树的流层物理设计方法,以提高解的质量和求解效率。在布局阶段,采用Memetic算法更高效地搜索解空间。在布线阶段,使用考虑通道顺序的基于协商的算法,同时将布线信息反馈给布局阶段,以调整布局并减少拥挤区域和通道交叉。实验结果表明,与现有算法相比,所提算法在芯片面积、通道总长度以及通道交叉数量等方面取得了更优的效果。

LI-Tree:一个基于非易失性内存和轻量级B+树的学习索引

大数据背景下剧增的数据给经典的内存索引技术带来了巨大挑战,为了实现对海量数据的高性能索引,工业界和学术界分别从设备和结构角度推出了高性能大容量的非易失型内存(Non-Volatile Memory,NVM)和受机器学习启发的学习索引(Learned Index,LI).然而目前基于NVM的学习索引结构的相关研究非常稀少,在如何结合NVM和LI来高效地索引海量数据方面还有许多问题需要解决.本文提出了一种基于NVM的新型智能索引结构LI-Tree,充分发挥了两者的优势.具体的,LI-Tree可分为三层:由机器学习模型组成的能够提高LI-Tree单点性能的模型层、由静态数组构成的减少NVM写的数据索引层和由一系列轻量级B+树组成以避免模型层插入时频繁重训练的数据层.在真实设备上评估表明,LI-Tree相比传统B+树,插入、查询和删除性能分别提高了70%、30%和130%.另外,LI-Tree与学习索引结构ALEX,PGM-Index和XIndex对比,插入性能分别提升了80%,130%和150%.

基于深度哈希与VP-Tree的快速图像检索方法

针对高维特征图像检索中的精度和速度挑战,提出了一种结合深度哈希技术和VP-Tree索引的快速图像检索方法.该方法首先设计了一个轻量级的深度卷积编码网络,并在网络中引入了卷积块注意力模块和空间金字塔池化技术,以增强特征提取能力;然后通过该网络模型将图像数据集中每幅图像的高维特征转化为二进制哈希编码,并与其对应的图像编号组成一个哈希表;接着使用所有图像的哈希编码来构建一个VP-Tree,在执行图像检索时将使用待查询图像的哈希编码从VP-Tree中快速找到与其距离最近的节点;最后根据这些节点的哈希值从哈希表中取出对应的结果图像.实验结果表明,所提方法在保持高检索精度的同时显著提升了检索速度(在MNIST、FASHION-MNIST和CIFAR-10上的检索速度分别提高了24.17、8.61和4.01倍).

Quantification of Above-Ground Biomass and Carbon Sequestration Potential of Roadside Trees in the Plateau Department of Benin Republic

Roadside trees are effective natural solutions for mitigating climate change. Despite the usefulness of trees to carbon sequestration, there is a dearth of information on the estimation of biomass and carbon stock for roadside trees in the study area. This study aimed to estimate the carbon stock and carbon dioxide equivalent of roadside trees. A complete enumeration of trees was carried out in Kétou, Pobè and Sakété within the communes of the Plateau Department, Bénin Republic. Total height and diameter at breast height were measured from trees along the roads while individual wood density value was obtained from wood density database. The allometric method of biomass estimation was adopted for the research. The results showed that the total estimations for above-ground biomass, carbon stock and carbon equivalent from all the enumerated roadside trees were 154.53 mt, 72.63 mt and 266.55 mt, respectively. The results imply that the roadside trees contain a substantial amount of carbon stock that can contribute to climate change mitigation through carbon sequestration.

线粒体Cyt b基因在鲑科品种鉴定中的可靠性分析

为探究Cyt b基因在鲑科鱼类品种鉴定中的可靠性,本研究从GenBank数据库中下载9种鲑科鱼类品种的Cyt b基因序列共997条。以Cyt b全基因和文献报道的两组Cyt b基因短片段(359和200 bp)为研究对象,对其序列变异和分子系统进化树进行分析,并筛选鲑科鱼类品种的微型DNA条形码。结果表明,仅当选用200 bp片段时,银鲑的最大种内遗传距离大于最小种间遗传距离,不存在条形码间隙(barcode gap)。同时,根据分子系统进化树分析,同一品种在基于不同Cyt b基因片段的邻接树中均聚为单系,且每一个分支的结点置信度均大于70%。因此,Cyt b可以作为条形码基因用于鲑科鱼类品种鉴定。本研究筛选获得的微型DNA条形码对鲑科鱼类品种具有良好的特异性。

Retrieval of Antarctic sea ice freeboard and thickness from HY-2B satellite altimeter data

Antarctic sea ice is an important part of the Earth’s atmospheric system,and satellite remote sensing is an important technology for observing Antarctic sea ice.Whether Chinese Haiyang-2B(HY-2B)satellite altimeter data could be used to estimate sea ice freeboard and provide alternative Antarctic sea ice thickness information with a high precision and long time series,as other radar altimetry satellites can,needs further investigation.This paper proposed an algorithm to discriminate leads and then retrieve sea ice freeboard and thickness from HY-2B radar altimeter data.We first collected the Moderate-resolution Imaging Spectroradiometer ice surface temperature(IST)product from the National Aeronautics and Space Administration to extract leads from the Antarctic waters and verified their accuracy through Sentinel-1 Synthetic Aperture Radar images.Second,a surface classification decision tree was generated for HY-2B satellite altimeter measurements of the Antarctic waters to extract leads and calculate local sea surface heights.We then estimated the Antarctic sea ice freeboard and thickness based on local sea surface heights and the static equilibrium equation.Finally,the retrieved HY-2B Antarctic sea ice thickness was compared with the CryoSat-2 sea ice thickness and the Antarctic Sea Ice Processes and Climate(ASPeCt)ship-based observed sea ice thickness.The results indicate that our classification decision tree constructed for HY-2B satellite altimeter measurements was reasonable,and the root mean square error of the obtained sea ice thickness compared to the ship measurements was 0.62 m.The proposed sea ice thickness algorithm for the HY-2B radar satellite fills a gap in this application domain for the HY-series satellites and can be a complement to existing Antarctic sea ice thickness products;this algorithm could provide long-time-series and large-scale sea ice thickness data that contribute to research on global climate change.

Learned Index和B-Tree在不同分布数据上的性能对比及优化

Learned Index是一种通过训练模型来建立输入数据和存储位置之间映射关系的索引,它能学习到数据间分布的信息,而不同的数据分布将影响模型训练准确率和模型复杂度之间的平衡。为了探索Learned Index适用的场景,使用不同分布、不同数据量的数据对它和加以优化的可更新的自适应学习索引(ALEX)进行性能测试,并与B-Tree进行对比,最终发现Learned Index构建大批量数据的索引时间比B-Tree短,读操作性能、存储空间大小有明显的优势,但写操作性能较差,因此得出Learned Index更适用于大数据情景下的在线分析处理(OLAP)数据库,用于静态数据的存储和查询操作的结论。基于B-Tree的索引结构,对初版Learned Index的结构进行了优化和调整,最终使优化后Learned Index在大批量数据的读写操作性能上有明显提高,其中读操作最高达到原版Learned Index的2倍,写操作最高达到原版的3倍。

Cloud Data Encryption and Authentication Based on Enhanced Merkle Hash Tree Method

Many organizations apply cloud computing to store and effectively process data for various applications.The user uploads the data in the cloud has less security due to the unreliable verification process of data integrity.In this research,an enhanced Merkle hash tree method of effective authentication model is proposed in the multi-owner cloud to increase the security of the cloud data.Merkle Hash tree applies the leaf nodes with a hash tag and the non-leaf node contains the table of hash information of child to encrypt the large data.Merkle Hash tree provides the efficient mapping of data and easily identifies the changesmade in the data due to proper structure.The developed model supports privacy-preserving public auditing to provide a secure cloud storage system.The data owners upload the data in the cloud and edit the data using the private key.An enhanced Merkle hash tree method stores the data in the cloud server and splits it into batches.The data files requested by the data owner are audit by a third-party auditor and the multiowner authentication method is applied during the modification process to authenticate the user.The result shows that the proposed method reduces the encryption and decryption time for cloud data storage by 2–167 ms when compared to the existing Advanced Encryption Standard and Blowfish.

Hash Tree Based Trustworthiness Verification Mechanism in Virtual Environment

The trustworthiness of virtual machines is a big security issue in cloud computing. In this paper, we aimed at designing a practical trustworthiness mechanism in virtual environment. With the assist of a third certificate agent, the cloud user generates a trust base and extends it to its VMs. For each service running on the VM, a hash value is generated from all the necessary modules, and these hash values are organized and maintained with a specially designed hash tree whose root is extended from the user's trust base. Before the VM loads a service, the hash tree is verified from the coordinated hash value to check the trustworthiness of the service.

Genetic diversity and matrilineal structure in Chinese tree shrews inhabiting Kunming,China

Due to their special phylogenetic position in the Euarchontoglires and close affinity to primates,tree shrews have been proposed as an alternative experimental animal to primates in biomedical research.However,the population genetic structure of tree shrews has largely remained unknown and this has hindered the development of tree shrew breeding and selection.Here we sampled 80 Chinese tree shrews（Tupaia belangeri chinensis） in Kunming,China,and analyzed partial mtDNA control region sequence variation.Based on our samples and two published sequences from northern tree shrews（T.belangeri）,we identified 29 substitutions in the mtDNA control region fragment（～ 604 bp） across 82 individuals and defined 13 haplotypes.Seventeen samples were selected for sequencing of the cytochrome b（Cyt b;1134 bp） gene based on control region sequence variation and were analyzed in combination with 34 published sequences to solidify the phylogenetic pattern obtained from control region data.Overall,tree shrews from Kunming have high genetic diversity and present a remarkable long genetic distance to the two reported northern tree shrews outside China.Our results provide some caution when using tree shrews to establish animal models because of this apparent genetic difference.In addition,the high genetic diversity of Chinese tree shrews inhabiting Kunming suggests that systematic genetic investigations should be conducted before establishing an inbred strain for medical and biological research.

一种基于Cross-Product与HashTree的IP分类算法

在Cross-Product算法的基础上,结合哈希树(HashTree)数据结构,综合二者的优点,提出了一种新的IP分类算法CPHTIT(Cross-Product and HashTree with index table)。仿真结果表明CPHTIT在时间和空间上都达到了高速IP分类的要求,与现有经典算法Grid of Tries和Modular比较,其综合性能有所改进。

基于Hash B+树RFID复杂事件检测算法

在分析现有RFID复杂事件检测算法的基础上,提出一种基于Hash B+树复杂事件检测算法。根据原子事件在Hash表中映射的位置状态,决定原子事件插入的位置,降低数据操作的时间复杂度。同时引入插入优化算法及滑动窗口,删除中间结果中过期数据,以提高内存的利用率。实验结果表明该方法在保证复杂事件检测有效性的同时可提高其处理效率。

一种基于Hash_tree的产生关联规则的方法

介绍了一种基于Hash＿tree的产生关联规则的方法。在此方法中通过在候选集排序和在获得项集出现次数的时候采用了Hash＿tree的方法大大提高了算法实现的速度,并在实际应用中也取得了很好的效果。

一种新的分布式并行索引树——DPB^+-Tree

随着数据规模的增大,查询越来越复杂,分布式并行索引以其高性能而逐渐成为解决复杂查询问题的有效手段。本文提出一种适合于分布式并行的新索引树结构——DPB^+-Tree,该索引树以B^+树和 hash结构为基础,其叶子结点被组织为有n个散列表元的hash表链,从树的根结点到叶子结点,结点副本数量逐渐减少,并且其数量的变化是动态的。对DPB^+-Tree响应时间的仿真结果表明 DPB^+-Tree系统提高了系统的查询效率,与其它相关策略,如CPB方法比较具有较明显优势。

B^+-Tree的改进算法在可复用软构件库中的应用

文章通过对B+-Tree索引算法的改进,将其应用到可复用软构件库中。该改进算法继承了B+-Tree的优点,结合可复用软构件库的特点,将构件库多维数据索引转化为B+-Tree一维数据索引进行存储、查询。通过对比分析,证明了该构件库索引算法大大改进了构件库中构件的查找效率。

Hash表与B^+树相结合的高效目录索引结构

针对目前文件系统目录结构在处理大量文件,尤其是单个大目录时文件创建、查找和删除速度较慢的问题,提出一种面向Web服务器存储系统的目录索引结构。该结构利用Hash函数对变长关键字的压缩特性和Hash表的O(1)查找复杂度进行文件名的快速查找,并使用B+树高效索引目录的子索引节点。测试结果表明,该结构能够快速地处理大量文件,单个大文件夹下的文件查找速度相比Ext3提高了40%,文件创建、删除速度比Ext3和Reiserfs加快了73%。