This conference proceedings contains 76 papers from a conference on advances in data engineering theory. Topics discussed include integrity constraints, spatial query processing, object oriented programming languages,...
详细信息
ISBN:
(纸本)0818635703
This conference proceedings contains 76 papers from a conference on advances in data engineering theory. Topics discussed include integrity constraints, spatial query processing, object oriented programming languages, database techniques for new engineering applications, main memory management, object oriented programming language implementation, schema and file management, query optimization and evaluation, concurrency control, query languages. federated database systems, temporal query languages, large-object support, object oriented models, parallel query processing, transitive closure and backup, federated object oriented interfaces, transaction synchronization and recovery, database engineering, deductive database implementation, extended serializability, knowledge bases, multidatabase languages, and application modeling.
In today's Internet applications or sensor networks we often encounter large amounts of data spread over many physically distributed nodes. The sheer volume of the data and bandwidth constraints make it impractica...
详细信息
ISBN:
(纸本)9781424454440
In today's Internet applications or sensor networks we often encounter large amounts of data spread over many physically distributed nodes. The sheer volume of the data and bandwidth constraints make it impractical to send all the data to one central node for query processing. Finding distributed icebergs-elements that may have low frequency at individual nodes but high aggregate frequency-is a problem that arises commonly in practice. In this paper we present a novel algorithm with two notable properties. First, its accuracy guarantee and communication cost are independent of the way in which element counts (for both icebergs and non-icebergs) are split amongst the nodes. Second, it works even when each distributed data set is a stream (i.e., one pass data access only). Our algorithm builds upon sketches constructed for the estimation of the second frequency moment (F-2) of data streams. The intuition of our idea is that when there are global icebergs in the union of these data streams the F-2 of the union becomes very large. This quantity can be estimated due to the summable nature of F-2 sketches. Our key innovation here is to establish tight theoretical guarantees of our algorithm, under certain reasonable assumptions, using an interesting combination of convex ordering theory and large deviation techniques.
The proceedings contain 28 papers. The special focus in this conference is on parallel and distributed Computing, applications and Technologies. The topics include: Insider Trading Detection Algorithm in Industrial Ch...
ISBN:
(纸本)9789819982103
The proceedings contain 28 papers. The special focus in this conference is on parallel and distributed Computing, applications and Technologies. The topics include: Insider Trading Detection Algorithm in Industrial Chain Based on Logistics Time Interval Characteristics;link Attributes Based Multi-service Routing for Software-Defined Satellite Networks;A Fuzzy Logical RAT Selection Scheme in SDN-Enabled 5G HetNets;SSR-MGTI: Self-attention Sequential Recommendation Algorithm Based on Movie Genre Time Interval;fine Time Granularity Allocation Optimization of Multiple Networks Industrial Chains in Task processing Systems;Ε-Maximum Critic Deep Deterministic Policy Gradient for Multi-agent Reinforcement Learning;effective Density-Based Concept Drift Detection for Evolving Data Streams;an End-to-End Multiple Hyper-parameters Prediction Method for distributed Constraint Optimization Problem;Formalization and Verification of the Zab Protocol Using CSP;dynamic Priority Coflow Scheduling in Optical Circuit Switched Networks;Deep Reinforcement Learning Based Multi-WiFi Offloading of UAV Traffic;Triple-Path RNN Network: A Time-and-Frequency Joint Domain Speech Separation Model;design of Query Based Gallery Selector and Mask-Aware Loss for Person Search;a Privacy-Preserving Blockchain Scheme for the Reliable Exchange of IoT Data;R-RPT-A Reliable Routing Protocol for Industrial Wireless Sensor Networks;action Segmentation Based on Encoder-Decoder and Global Timing Information;Security Challenges and Lightweight Cryptography in IoT: Comparative Study and Testing Method for PRESENT-32bit Cipher;The Prediction Model of Water Level in Front of the Check Gate of the LSTM Neural Network Based on AIW-CLPSO;Using MPIs Non-Blocking Allreduce for Health Checks in Dynamic Simulations;parallelizable Loop Detection using Pre-trained Transformer Models for Code Understanding;list-Based Workflow Scheduling Utilizing Deep Reinforcement Learning.
Modern microprocessors employ multi cores to accelerate computations, and parallelizing multiple queries execution to exploit multi-core parallelism has become a challenge for moving objects database applications. To ...
详细信息
As multi-core technology is currently deployed in computer industry primarily for limiting power consumption and improving system throughput, continued performance improvement of a single application on such systems r...
详细信息
Current high performance computing systems all rely on parallelprocessingtechniques to achieve high performance. With the parallel computer systems scaling up, the new generation of high performance computers puts m...
详细信息
ISBN:
(纸本)9781605580777
Current high performance computing systems all rely on parallelprocessingtechniques to achieve high performance. With the parallel computer systems scaling up, the new generation of high performance computers puts more emphasis on "high productivity" [1], rather than "high performance" as in the past. These new systems will not only meet the traditional requirements of computing performance, but also address the ongoing technical challenges in the current high-end computing domain regarding energy consumption, reliability, etc. For energy consumption, with the computer system scaling up, it increases dramatically [2]. High energy consumption means high maintenance cost and low system stability. For example, the peak energy consumption of the Earth Simulator and BlueGene/L is 18MW and 1.6MW respectively. For reliability, with the complexity of a computer system increasing, its meantimebetween-failure (MTBF) is becoming significantly shorter than what is required by many current high performance computing applications [3], such as BlueGene/L. Therefore, energy optimization techniques and fault tolerance techniques should be introduced to computer systems to achieve low energy consumption and high reliability. To improve the productivity of high performance computing systems, we need to find a proper way to measure it. Unfortunately, traditional measurement models can not evaluate the system productivity comprehensively and effectively [4]. To address this issue, this paper proposes an effective scalability metric for high performance computing systems based on Gustafson speedup law. The metric makes a good balance among runtime productivity factors including computing performance, energy consumption and reliability. The contribution of our work lies in the following three aspects. First, in order to measure the scalability of an energyconsumption optimized parallel program, we should consider not only whether the program computing performance is scalable, but also w
Java streams enable an easy-to-use functional-like programming style that transparently supports parallel execution. This paper presents an approach that improves the performance of stream-based Java applications. The...
详细信息
ISBN:
(纸本)9783031061561;9783031061554
Java streams enable an easy-to-use functional-like programming style that transparently supports parallel execution. This paper presents an approach that improves the performance of stream-based Java applications. The approach enables the effective usage of Java for HPC applications, due to data locality improvements (i.e., support for efficient data layouts), without losing the object-oriented view of data in the code. The approach extends the Java collections API to hide additional details concerning the data layout, enabling the transparent use of more memory-friendly data layouts. The enhanced Java Collection API enables an easy adaptation of existing Java codes making those Java codes suitable for HPC. Performance results show that improving the data locality can provide a two-fold performance gain in sequential stream applications, which translated into a similar gain over parallel stream implementations. Moreover, the performance is comparable to similar C implementations using OpenMP.
This paper describes the techniques and methodologies employed during parallelization of the Molecular Dynamics (MD) code GROMOS87, with the specific requirement that the program run efficiently on a range of distribu...
详细信息
Some systems use machine learning techniques such as support vector machines to estimate human motions using acceleration sensors. These systems must acquire acceleration data to build a model. Therefore, it is diffic...
详细信息
ISBN:
(纸本)9780769549521;9781467362399
Some systems use machine learning techniques such as support vector machines to estimate human motions using acceleration sensors. These systems must acquire acceleration data to build a model. Therefore, it is difficult to estimate a newly observed person's motions promptly. Moreover, a newly observed person must carry out sufficiently diverse and numerous motions to build a model. These are heavy burdens that must be borne to observe people. As described in this paper, we propose a method for sensor data processing using similarity in feature of motions between observed persons. This method is designed to achieve a balance between providing motion estimation for a newly observed person promptly and for maintaining precision of motion estimation. In this method, the system can estimate a newly observed person's motions initially because the system uses a similar observed persons' standard. We implement a prototype system to evaluate this method. The system estimates human motions using the acceleration sensor. We perform some initial experiments using this prototype system.
A difficulty in the software design for real-time, distributed systems in which data (or job) rate and response time are critical, is that performance is dependent upon the partitioning and allocation of software modu...
详细信息
A difficulty in the software design for real-time, distributed systems in which data (or job) rate and response time are critical, is that performance is dependent upon the partitioning and allocation of software modules as well as the performance of those modules. In order to assess these factors, better techniques and tools are needed. This research considers the expansion of a performance modelling approach that can be used for this area. The approach is that of analytic approximation of queueing networks. The primary contributions of this research are: inclusion of communication cost estimates between modules in separate processors;consideration of parallel control branches and their synchronization. A possible application methodology and the related modelling approach are described.
暂无评论