The Wound-Retire concurrency control protocol was proposed to reduce contention for hotspots in in-memory databases. It enhances throughput under high-contention scenarios by allowing transactions to release their locks earlier (referred to as Retire), thereby reducing the wait times for other transactions. However, the proactive early release of locks introduces additional overhead, making it less efficient than other lock-based protocols in low-contention scenarios. Moreover, the wound strategy it adopts, while effective at preventing deadlocks, may lead to unnecessary transaction aborts. To address these issues, this paper proposes the Rebirth-Retire concurrency control protocol as an enhancement to the Wound-Retire protocol. In this protocol, a lock is retired by a younger transaction that requests it, which reduces unnecessary retire costs in low-contention scenarios. Additionally, rather than aborting younger transactions, older transactions are assigned larger times-tamps (referred to as Rebirth), unless doing so would result in a deadlock. Experimental evaluations demonstrate that the Rebirth-Retire protocol achieves better throughput and lower abort rate than the Wound-Retire protocol across varying levels of contention workloads.

Accurate gross tumor volume (GTV) segmentation is essential for effective radiotherapy in nasopharyngeal carcinoma (NPC). However, challenges arise due to the nasopharyngeal region's complex anatomy and the annotated data scarcity. Our study presents a dual-attention-based enhanced unified network (DAEU-Net) designed for precise NPC GTV segmentation utilizing 3D T1, T2, and T1C-weighted MR images. Our approach involves splitting large-scale MR data into multiple patches and then training every patch independently. This approach effectively captures localized and detailed information without downscaling the image resolution. The DAEU-Net integrates channel-attention and pixel-attention modules within the encoder section, eliminating background noise and reducing information loss by enhancing the network's focus on detailed features. The decoder section incorporates bottleneck residual blocks to enhance the computing efficiency and robustness of the network. The proposed methodology surpasses the state-of-the-art models with a respective average symmetric surface distance (ASSD) of 0.920 +/- 0.386 mm, 0.987 +/- 0.421 mm, and 1.043 +/- 0.457 mm and a dice similarity coefficient (DSC) of 0.896, 0.871, and 0.851, respectively. Multi-viewed animated MR images in three orthogonal dimensions (axial, sagittal, and coronal) with predicted NPC tumors and real GTV masks were shown to assist in comprehending the tumor's precise location. Our approach can significantly improves NPC tumor delineation, aids in automated tumor lesion segmentation, and reduces the annotation workload for oncologists.

Existing databases supporting Online Transaction Processing (OLTP) workloads based on non-volatile memory (NVM) almost all use Multi-Version Concurrency Control (MVCC) protocol to ensure data consistency. MVCC allows multiple transactions to execute concurrently without lock conflicts, reducing the wait time between read and write operations, and thereby significantly increasing the throughput of NVM OLTP engines. However, it requires garbage collection (GC) to clean up the obsolete tuple versions to prevent storage overflow, which consumes additional system resources. Furthermore, existing GC approaches in NVM OLTP engines are inefficient because they are based on methods designed for dynamic random access memory (DRAM) OLTP engines, without considering the significant differences in read/write bandwidth and cache line size between NVM and DRAM. These approaches either involve excessive random NVM access (traversing tuple versions) or lead to too many additional NVM write operations, both of which degrade the performance and durability of NVM. In this paper, we propose TB-Collect, a high-performance GC approach specifically designed for NVM OLTP engines. On the one hand, TB-Collect separates tuple headers and contents, storing data in an append-only manner, which greatly reduces NVM writes. On the other hand, TB-Collect performs GC at the block level, eliminating the need to traverse tuple versions and improving the utilization of reclaimed space. We have implemented TB-Collect on DBx1000 and MySQL. Experimental results show that TB-Collect achieves 1.15 to 1.58 times the throughput of existing methods when running TPCC and YCSB workloads.

Main memory databases are increasingly preferred in modern applications for real-time data processing due to their exceptional throughput performance. However, implementing index organization within these engines presents significant challenges. This paper addresses these challenges by introducing a novel index organization, the B ^ε -organized table, which leverages the B ^ε -tree index and an optimization algorithm combined with Markov Decision Processes. The B ^ε -organized table enables efficient data access by storing the latest versions in the leaf nodes of the B ^ε -tree index and incorporating two effective contention management mechanisms. The Markov Decision Process-based optimization algorithm identifies optimal configurations for achieving high performance with the B ^ε -organized table across diverse workloads. We have integrated the B ^ε -organized table into a widely studied open-source main memory database system. Our extensive experimental results, conducted using standard benchmarks, demonstrate that the B ^ε -organized table outperforms state-of-the-art storage organizations-such as heap organization and conventional index organization-achieving up to 1.7 × higher performance under TPC-C workloads and up to 2.5 × higher performance under YCSB workloads.

Existing databases supporting Online Transaction Processing (OLTP) workloads based on non-volatile memory (NVM) have not fully leveraged hardware characteristics, resulting in an imbalance between throughput and recovery performance. In this paper, we conclude with the reason why existing designs fail to achieve both: placing indexes on NVM results in numerous random writes and write amplification for index updates, leading to a decrease in system performance. Placing indexes on dynamic random access memory (DRAM) results in much time consumption for rebuilding indexes during recovery. To address this issue, we propose FIR, an NVM OLTP Engine with the fast rebuilding of the DRAM indexes, achieving instant system recovery while maintaining high throughput. Firstly, we design an index checkpoint strategy. During recovery, the indexes are quickly rebuilt by the bottom-up algorithm with index checkpoints. Then, to achieve instant recovery of the entire engine after rebuilding indexes, we optimize the existing log-free design by leveraging time-ordered storage, which significantly reduces the number of NVM writes. We also implement garbage collection based on data redistribution, enhancing system availability. The experimental results demonstrate that FIR achieves 98% of the performance of state-of-the-art OLTP Engine when running TPCC and YCSB. And the recovery speed of FIR is 43.6×–54.5× faster, achieving near-instantaneous recovery.

Large-scale data-intensive applications need massive real-time data processing.Recent hybrid DRAM-PM main memory database systems provide an effective approach by persisting data to persistent memory (PM) in an append-based manner for efficient storage while maintaining the primary database copy in DRAM for high throughput rates.However, they can not achieve high performance under a hybrid workload because they are unaware of the impact of pointer chasing.In this work, we investigate the impact of chasing pointers on modern main memory database systems to eliminate this bottleneck.We propose Index-Organized storage model that supports efficient reads and updates.We combine two techniques, i.e., cacheline-aligned node layout and cache prefetching, to accelerate pointer chasing, reducing memory access latency. We present four optimizations, i.e., pending versions, fine-grained memory management, Index-SSN, and cacheline-aligned writes, for supporting efficient transaction processing and fast logging.We implement our proposed storage model based on an open-sourced main memory database system.We extensively evaluate performance on a 20-core system featuring Intel Optane DC Persistent Memory Modules. Our experiments reveal that the Index-Organized approach achieves up to 3$\times$ speedup compared to traditional storage models (row-store, column-store, and row+column).

Existing databases supporting OLTP workloads based on non-volatile memory (NVM) almost all use Multi-Version Concurrency Control (MVCC) protocol to ensure data consistency. MVCC allows multiple transactions to execute concurrently without lock conflicts, reducing the wait time between read and write operations, and thereby significantly increasing the throughput of NVM OLTP engines. However, it requires garbage collection (GC) to clean up the obsolete tuple versions to prevent storage overflow, which consumes additional system resources. Even more, existing GC approaches are inefficient because they are based on schemes from dynamic random access memory (DRAM) OLTP engines, without considering the significant differences in random read/write speeds and coarser read/write granularity of NVM compared to DRAM. These approaches either involve excessive random access (traversing tuple versions) or result in too many write operations, both of which degrade the performance and durability of NVM. In this paper, we propose TB-Collect, a high-performance GC approach specifically designed for NVM OLTP engines. On the one hand, TB-Collect separates tuple headers and contents, storing data in an append-only manner, which greatly reduces NVM writes. On the other hand, TB-Collect performs GC at the block level, eliminating the need to traverse tuple versions and improving the utilization of reclaimed space. We have implemented TB-Collect on DBx1000. Experimental results show that TB-Collect achieves 1.4x the throughput of state-of-the-art designs when running TPCC and YCSB workloads.

BackgroundPancreatic ductal adenocarcinoma (PDAC), a leading cause of cancer mortality, has a complex pathogenesis involving various immune cells, including B cells and their subpopulations. Despite emerging research on the role of these cells within the tumor microenvironment (TME), the detailed molecular interactions with tumor-infiltrating immune cells (TIICs) are not fully understood.MethodsWe applied CIBERSORT to quantify TIICs and naive B cells, which are prognostic for PDAC. Marker genes from scRNA-seq and modular genes from weighted gene co-expression network analysis (WGCNA) were integrated to identify naive B cell-related genes. A prognostic signature was constructed utilizing ten machine-learning algorithms, with validation in external cohorts. We further assessed the immune cell diversity, ESTIMATE scores, and immune checkpoint genes (ICGs) between patient groups stratified by risk to clarify the immune landscape in PDAC.ResultsOur analysis identified 994 naive B cell-related genes across single-cell and bulk transcriptomes, with 247 linked to overall survival. We developed a 12-gene prognostic signature using Lasso and plsRcox algorithms, which was confirmed by 10-fold cross-validation and showed robust predictive power in training and real-world cohorts. Notably, we observed substantial differences in immune infiltration between patients with high and low risk.ConclusionOur study presents a robust prognostic signature that effectively maps the complex immune interactions in PDAC, emphasizing the critical function of naive B cells and suggesting new avenues for immunotherapeutic interventions. This signature has potential clinical applications in personalizing PDAC treatment, enhancing the understanding of immune dynamics, and guiding immunotherapy strategies.

A rapidly spreading epidemic, COVID-19 had a serious effect on millions and took many lives. Therefore, for individuals with COVID-19, early discovery is essential for halting the infection's progress. To quickly and accurately diagnose COVID-19, imaging modalities, including computed tomography (CT) scans and chest X-ray radiographs, are frequently employed. The potential of artificial intelligence (AI) approaches further explored the creation of automated and precise COVID-19 detection systems. Scientists widely use deep learning techniques to identify coronavirus infection in lung imaging. In our paper, we developed a novel light CNN model architecture with watershed-based region-growing segmentation on Chest X-rays. Both CT scans and X-ray radiographs were employed along with 5-fold cross-validation. Compared to earlier state-of-the-art models, our model is lighter and outperformed the previous methods by achieving a mean accuracy of 98.8% on X-ray images and 98.6% on CT scans, predicting the rate of 0.99% and 0.97% for PPV (Positive predicted Value) and NPV (Negative predicted Value) rate of 0.98% and 0.99%, respectively.

Spark是基于Map/Reduce计算模型进行大规模数据处理的分布式系统,每个任务都会被分为很多Map处理和Reduce处理在各个节点上并行执行.Shuffle操作是用于连接Map处理和Reduce处理的桥梁.在对两个大表进行Join操作的过程中,如果两表Join列不完全匹配,Spark中现有的Join实现算法会对大量数据进行shuffle操作,严重影响执行效率.提出一种基于Semi Join思想的Join实现算法——Semi Sort Merge Join,通过对左表Join列数据所构建的HashMap对右表数据进行过滤,可以有效减少Shuffle操作过程中所需传输的数据量.算法分析和实验结果表明,对于Join列数据不完全匹配的大表间Join操作,该算法能有效减少Shuffle操作的开销,右表与左表匹配数据量越少,算法优化的效果越明显.

Many distributed database systems that guarantee high concurrency and scalability adopt read-write separation architecture. Simultaneously, these systems need to store massive amounts of data daily, requiring different mechanisms for storing and accessing data, such as hot and cold data access strategies. Unlike distributed storage systems, the distributed database splits a table into sub-tables or shards, and the request frequency of each sub-table is not the same within a specific time. Therefore, it is not only necessary to design hot-to-cold approaches to reduce storage overhead, but also cold-to-hot methods to ensure high concurrency of those systems. We present a new redundant strategy named CBase-EC, using erasure codes to trade the performances of transaction processing and storage efficiency for CBase database systems developed for financial scenarios of the Bank. Two algorithms are proposed: the hot-cold tablets (shards) recognition algorithm and the hot-cold dynamic conversion algorithm. Then we adopt two optimization approaches to improve CBase-EC performance. In the experiment, we compare CBase-EC with three-replicas in CBase. The experimental results show that although the transaction processing performance declined by no more than 6%, the storage efficiency increased by 18.4%.

传统的数据库系统围绕单次查询的模型构建,独立地执行并发查询.由于该模型的限制,传统数据库无法一次对多个查询进行优化.多查询共享技术旨在共享查询之间的公共部分,从而达到提高系统整体响应时间和吞吐量的目的.将多查询执行模式分为两类,介绍了各自的原型系统——基于全局查询计划的多查询原型系统和以运算符为中心的多查询原型系统,并且讨论了两种系统的优势以及所适用场景.在之后的内容中,将多查询共享技术按照查询的各个阶段分为查询编译阶段中的多查询共享技术以及查询执行阶段中的多查询共享技术两大类.以这两个方向为线索,梳理了多查询计划的表示方法、多查询表达式合并、多查询共享算法、多查询优化等各种方向的研究成果.在此基础上,还介绍了共享查询技术在关系数据库和非关系数据库中的应用.最后,分析了共享查询技术面临的机遇和挑战.

Edge computing, as an emerging computing paradigm, aims to reduce network bandwidth transmission overhead while storing and processing data on edge nodes. However, the storage strategies required for edge nodes are different from those for existing data centers. Erasure code (EC) strategies have been applied in some decentralized storage systems to ensure the privacy and security of data storage. Product-matrix (PM) regenerating codes (RGCs) as a state-of-the-art EC family are designed to minimize the repair bandwidth overhead or minimize the storage overhead. Nevertheless, the high complexity of the PM framework contains more finite-domain multiplication operations than classical ECs, which heavily consumes computational resources at the edge nodes. In this paper, a theoretical derivation of each step of the PM minimum storage regeneration (PM-MSR) and PM minimum bandwidth regeneration (PM-MBR) codes is performed and the XOR complexity over finite fields is analyzed. On this basis, a new construct called product bitmatrix (PB) is designed to reduce the complexity of XOR operations in the PM framework, and two heuristics are used to further reduce the XOR numbers of the PB-MSR and PB-MBR codes, respectively. The evaluation results show that the PB construction significantly reduces the XOR number compared to the PM-MSR, PM-MBR, Reed–Solomon (RS), and Cauchy RS codes while retaining optimal performance and reliability.

The emergence of smart contract promotes the popularity of blockchain applications, leading the dramatically growth of Ethereum blockchain data size. The analysis on blockchain data is urgently needed for users, e.g., collecting statistics of tokens, monitoring the status of Ethereum blockchain. However, Ethereum could only support simple searches on blockchain data on account of its storage model. This paper proposes the EBTree, an index for Ethereum blockchain Data, and implements it based on Ethereum client (Geth1.8). With the properties of B+ tree, EBTree could support real-time top-k, range, equivalent search on Ethereum blockchain data. Besides, EBTree takes up relatively small s-torage space because it only stores the identifiers of blockchain data. Meanwhile, considering of the time intervals of mining block and synchronizing data from Ethereum network, the time of insertion in EBTree has little influence on the performance of Ethereum client. We conduct experiments to evaluate the performance of EBTree. According to the result of experiments, EBTree shows great performance on searches and insertion at low cost of storage.

A hypernymy (“is-a”) relation is an important concept in Natural Language Processing (NLP). It is used to describe the subordination relation between two concepts. The accurate prediction of hypernymy relations is important for mining the inherent hierarchy of concepts and building large-scale semantic networks, ontologies, knowledge graphs and other knowledge-intensive systems. Most traditional hypernymy prediction algorithms rely on relatively fixed language patterns, which have drawbacks such as the low coverage and the high degree of manual intervention. In addition, the textual patterns are highly correlated with the language itself. For languages with low regularity such as Chinese, pattern-based methods are not sufficiently accurate. With the rapid development of deep learning techniques in NLP, word embeddings are frequently employed to model 计 算 机 学 报 网络出版时间:2019-10-31 13:48:00 网络出版地址:http://kns.cnki.net/kcms/detail/11.1826.TP.20191031.1234.002.html

The emerging decentralized storage systems (DSSs), such as InterPlanetary File System (IPFS), Storj, and Sia, provide people with a new storage model. Instead of being centrally managed, the data are sliced up and distributed across the nodes of the network. Furthermore, each data object is uniquely identified by a cryptographic hash (ObjectId) and can only be retrieved by ObjectId. Compared with the search functions provided by the existing centralized storage systems, the application scenarios of the DSSs are subject to certain restrictions. In this paper, we first apply decentralized B+Tree and HashMap to the DSSs to provide keyword search. Both indexes are kept in blocks. Since these blocks may be scattered on multiple nodes, we ensure that all operations involve as few blocks as possible to reduce network cost and response time. In addition, the version control and version merging algorithms are designed to effectively organize the indexes and facilitate data integration. The experimental results prove that our indexes have excellent availability and scalability.

The emergence of smart contract promotes the popularity of blockchain applications, leading the dramatically growth of Ethereum blockchain data size. The analysis on blockchain data is urgently needed for users, e.g., collecting statistics of tokens, monitoring the status of Ethereum blockchain. However, Ethereum could only support simple searches on blockchain data on account of its storage model. This paper proposes the EBTree, an index for Ethereum blockchain Data, and implements it based on Ethereum client (Geth1.8). With the properties of B+ tree, EBTree could support real-time top-k, range, equivalent search on Ethereum blockchain data. Besides, EBTree takes up relatively small s-torage space because it only stores the identifiers of blockchain data. Meanwhile, considering of the time intervals of mining block and synchronizing data from Ethereum network, the time of insertion in EBTree has little influence on the performance of Ethereum client. We conduct experiments to evaluate the performance of EBTree. According to the result of experiments, EBTree shows great performance on searches and insertion at low cost of storage.

单体架构下的分布式事务是一个服务内访问多个数据源的分布式事务,可以采用传统分布式事务处理模型——DTP(Distributed Transaction Processing)模型来解决。在微服务的架构下,可能会出现跨服务、跨资源的分布式事务。在解决这类分布式事务时,微服务追求系统的可用性和最终一致性而非数据的强一致性。针对不同的微服务分布式事务场景,介绍不同的分布式事务处理模型,包括可靠消息模型、业务补偿模型和TCC(TryConfirm/Cancel)模型,并总结每种模型的处理流程和优缺点。对TCC模型在性能上和可移植性上提出优化方案。

微服务架构降低应用模块之间的耦合度,有利于复杂应用系统的开发、部署和运维.但相比于单体应用其资源的访问控制也变得更加复杂.对微服务架构下的资源访问控制需求进行分析,提出一种基于角色的访问控制模型——MSAM(Microservice of Authority Management).该模型具有对用户授予和屏蔽权限、数据权限和服务实例权限等特征,能够很好地满足微服务架构下的资源访问控制需求.讨论访问控制模型的实现,对比集中式鉴权与独立式鉴权两种实现的优缺点,说明不同实现方式所适用的场景.