检索结果-内蒙古大学图书馆

21st IEEE International Conference on Communication Technology, ICCT 2021

作者： Wang, Fei Si, Pengbo Sun, Enchang Su, Yuzhao Beijing University of Technology Faculty of Information Technology Beijing China

ISBN: (纸本)9781665432061

Global air transport carries about 7.3 billion pieces of luggage each year and up to 56 percent of travelers prefer obtaining real-time baggage tracking information throughout their trip. However, the traditional baggage tracking scheme is generally based on optical scanning and centralized storage systems, which suffers from low efficiency and information leakage. In this paper, a blockchain and edge computing based IOT system for tracking of airport baggage (BEI-TAB) is proposed. Through the combination of radio frequency identification technology (RFID) and blockchain, real-time baggage processing information is automatically stored in blockchain. In addition, we deploy Interplanetary File System (IPFS) at edge nodes with ciphertext policy attribute-based encryption (CP-ABE) to store basic baggage information. Only hash values returned by the IPFS network are kept in blockchain, enhancing the scalability of the system. Furthermore, a multi-channel scheme is designed to realize the physical isolation of data, and to rapidly process multiple types of data and business requirements in parallel. To the best of our knowledge, it is the first architecture that integrates RFID, IPFS, CP-ABE with blockchain technologies to facilitate secure, decentralized, and real-time characteristics for storing and sharing data for baggage tracking. We have deployed a testbed with both software and hardware to evaluate the proposed system, considering the performances of transaction processing time and speed. © 2021 IEEE.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Communication-avoiding kernel ridge regression on parallel and distributed systems

引用

CCF TRANSACTIONS ON HIGH PERFORMANCE COMPUTING 2021年第3期3卷 252-270页

作者： You, Yang Huang, Jingyue Hsieh, Cho-Jui Vuduc, Richard Demmel, James Natl Univ Singapore Dept Comp Sci Singapore Singapore Fudan Univ Sch Data Sci Shanghai Peoples R China Univ Calif Los Angeles Dept Comp Sci Los Angeles CA 90024 USA Georgia Inst Technol Coll Comp Atlanta GA 30332 USA Univ Calif Berkeley Div Comp Sci Berkeley CA 94720 USA

Kernel ridge regression (KRR) is a fundamental method in machine learning. Given an n-by-d data matrix as input, a traditional implementation requires Theta(n(2)) memory to form an n-by-n kernel matrix and Theta(n(3)) flops to compute the final model. These time and storage costs prohibit KRR from scaling up to large datasets. For example, even on a relatively small dataset (a 520k-by-90 input requiring 357 MB), KRR requires 2 TB memory just to store the kernel matrix. The reason is that n usually is much larger than d for real-world applications. On the other hand, weak scaling becomes a problem: if we keep d and n/p fixed as p grows (p is the number of machines), the memory needed grows as Theta(p) per processor and the flops as Theta(p(2)) per processor. In the perfect weak scaling situation, both the memory needed and the flops grow as Theta(1) per processor (i.e. memory and flops are constant). The traditional distributed KRR implementation (DKRR) only achieved 0.32% weak scaling efficiency from 96 to 1536 processors. We propose two new methods to address these problems: the balanced KRR (BKRR) and K-means KRR (KKRR). These methods consider alternative ways to partition the input dataset into pdifferent parts, generating pdifferent models, and then selecting the best model among them. Compared to a conventional implementation, KKRR2 (optimized version of KKRR) improves the weak scaling efficiency from 0.32 to 38% and achieves a 591x speedup for getting the same accuracy by using the same data and the same hardware (1536 processors). BKRR2 (optimized version of BKRR) achieves a higher accuracy than the current fastest method using less training time for a variety of datasets. For the applications requiring only approximate solutions, BKRR2 improves the weak scaling efficiency to 92% and achieves 3505x speedup (theoretical speedup: 4096x). The source code of this paper is available at https://***/similar to youyang/***.

关键词： distributed machine learning Knights landing Scalable algorithm

来源：评论

学校读者我要写书评

暂无评论

Trustworthy distributed Deep Neural Network Training in an Edge Device Network

Trustworthy Distributed Deep Neural Network Training in an E...

引用

IEEE International Conference on Big Data

作者： Sudipta Saha Shubha Haiying Shen Department of Computer Science University of Virginia USA

ISBN: (纸本)9781665480468

With the increased usage of edge devices having local computation capabilities, deep neural network (DNN) training in a network of edge devices becomes promising. Several recent works have proposed fully edge-based distributed training systems for situations when the communication to cloud is unstable or intermittent. However, such distributed systems become vulnerable when there are untrusted devices that launch data and model poisoning attacks during training, deteriorating the accuracy of the DNN model. To handle this challenge, we propose a Trustworthy distributed system for Machine learning training in an edge device network (TrustMe). TrustMe realizes both data and model parallelisms. It detects the untrusted devices producing illegitimate outputs. Next, it reassigns the training tasks of the untrusted devices to other trusted devices in such a way that the reassignment and the training that is restarted after the reassignment require minimal time. Our container-based emulation and real device experiments demonstrate that TrustMe achieves up to 12% higher accuracy and 45% less training time compared to existing methods in the presence of untrusted devices.

关键词： Training Deep learning Image edge detection Neural networks Emulation distributed databases parallel processing

来源：评论

学校读者我要写书评

暂无评论

ODRE workshop: Probabilistic Dynamic Hard real-time Scheduling in HPC 23

ODRE Workshop: Probabilistic Dynamic Hard Real-Time Scheduli...

引用

IEEE 23rd International Symposium on real-time distributed Computing (ISORC)

作者： Hofer, Florian Sehr, Martin A. Russo, Barbara Sangiovanni-Vincentelli, Alberto Free Univ Bolzano Bozen Fac Comp Sci Bolzano Italy Siemens Corp Corp Technol Berkeley CA 94704 USA Univ Calif Berkeley EECS Dept Berkeley CA 94720 USA

ISBN: (纸本)9781728169583

Industry 4.0 is changing fundamentally the way data is collected, stored and analyzed in industrial processes. While this change enables novel application such as flexible manufacturing of highly customized products, the real-time control of these processes, however, has not yet realized its full potential. We believe that modern virtualization techniques, specifically application containers, present a unique opportunity to decouple control functionality from associated hardware. Through it, we can fully realize the potential for highly distributed and transferable industrial processes even with real-time constraints arising from time-critical sub-processes. In this paper, we present a specifically developed orchestration tool to manage the challenges and opportunities of shifting industrial control software from dedicated hardware to bare-metal servers or (edge) cloud computing platforms. Using off-the-shelf technology, the proposed tool can manage the execution of containerized applications on shared resources without compromising hard real-time execution determinism. Through first experimental results, we confirm the viability and analyzed the behavior of resource shared systems with strict real-time requirements. We then describe experiments set out to deliver expected results and gather performance, application scope and limits of the presented approach.

关键词： Industry 4.0 CPS Virtualization real-time Container Orchestration Determinism

来源：评论

学校读者我要写书评

暂无评论

Efficient distance join query processing in distributed spatial data management systems

引用

INFORMATION SCIENCES 2020年 512卷 985-1008页

作者： Garcia-Garcia, Francisco Corral, Antonio Iribarne, Luis Vassilakopoulos, Michael Manolopoulos, Yannis Univ Almeria Dept Informat Almeria Spain Univ Thessaly Dept Elect & Comp Engn Volos Greece Open Univ Cyprus Sch Nat & Appl Sci Nicosia Cyprus

Due to the ubiquitous use of spatial data applications and the large amounts of such data these applications use, the processing of large-scale distance joins in distributed systems is becoming increasingly popular. Distance Join Queries (DJQs) are important and frequently used operations in numerous applications, including data mining, multimedia and spatial databases. DJQs (e.g., k Nearest Neighbor Join Query, k Closest Pair Query, epsilon Distance Join Query, etc.) are costly operations, since they involve both the join and distance-based search, and performing DJQs efficiently is a challenging task. Recent Big Data developments have motivated the emergence of novel technologies for distributed processing of large-scale spatial data in clusters of computers, leading to distributed Spatial Data Management systems (DSDMSs). distributed cluster-based computing systems can be classified as Hadoop-based or Spark-based systems. Based on this classification, in this paper, we compare two of the most recent and leading DSDMSs, SpatialHadoop and LocationSpark, by evaluating the performance of several existing and newly proposed parallel and distributed DJQ algorithms under various settings with large spatial real-world datasets. A general conclusion arising from the execution of the distributed DJQ algorithms studied is that, while SpatialHadoop is a robust and efficient system when large spatial datasets are joined (since it is built on top of the mature Hadoop platform), LocationSpark is the clear winner in total execution time efficiency when medium spatial datasets are combined (due to in-memory processing provided by Spark). However, LocationSpark requires higher memory allocation when large spatial datasets are involved in DJQs (even more so when k and epsilon are large). Finally, this detailed performance study has demonstrated that the new distributed DJQ algorithms we have proposed are efficient, robust and scalable with respect to different parameters, such as d

关键词： Distance join Spatial data processing Space partitioning SpatialHadoop LocationSpark Spatial query evaluation

来源：评论

学校读者我要写书评

暂无评论

Cloud-based computational model predictive control using a parallel multi-block ADMM approach

arXiv

引用

arXiv 2022年

作者： Ma, Yaling Gao, Runze Dai, Li Wu, Jinxian Xia, Yuanqing The School of Automation Beijing Institute of Technology Beijing100081 China

Heavy computational load for solving nonconvex problems for large-scale systems or systems with real-time demands at each sample step has been recognized as one of the reasons for preventing a wider application of nonlinear model predictive control (NMPC). To improve the real-time feasibility of NMPC with input nonlinearity, we devise an innovative scheme called cloud-based computational model predictive control (MPC) by using an elaborately designed parallel multi-block alternating direction method of multipliers (ADMM) algorithm. This novel parallel multi-block ADMM algorithm is tailored to tackle the computational issue of solving a nonconvex problem with nonlinear constraints. It is ensured that the designed algorithm converges to a locally optimal solution of the optimization problem under reasonable assumptions by using the Kurdyka-Lojasiewicz property. With the help of this distributed optimization algorithm, a computational MPC scheme is developed, which can transform the NMPC optimization problem into a set of subproblems only associated with the decision variables at one prediction step. Through the parallel computing algorithm, the computational MPC can deal with large computational loads caused by high dimensional optimization problems, and improve computational efficiency. Furthermore, to allow for a more efficient implementation of the developed computational MPC and alleviate local calculation loads, a cloud-based computational MPC architecture is devised, which makes significantly better use of computational resources provided by a cloud server. An important advantage of this architecture with Docker container to implement parallelization is that it does not lead to large increases in the solution time regardless of how long the prediction horizon is set. Finally, the developed cloud-based computational MPC architecture is trialed on a group of plug-in hybrid electric vehicles (PHEVs). Copyright © 2022, The Authors. All rights reserved.

关键词： Model predictive control

来源：评论

学校读者我要写书评

暂无评论

Cooperative multi-agent actor-critic control of traffic network flow based on edge computing

引用

FUTURE GENERATION COMPUTER systems-THE INTERNATIONAL JOURNAL OF ESCIENCE 2021年 123卷 128-141页

作者： Zhang, Yongnan Zhou, Yonghua Lu, Huapu Fujita, Hamido Beijing Jiaotong Univ Sch Elect & Informat Engn Beijing Peoples R China Tsinghua Univ Inst Transportat Engn Beijing Peoples R China Iwate Prefectural Univ Fac Software & Informat Sci Takizawa Iwate Japan Univ Granada Andalusian Res Inst Data Sci & Computat Intellige Granada Spain

Most of the existing traffic signal control strategies are hard to satisfy the real-time requirements of traffic big data analysis, knowledge reasoning and decision making for sophisticated traffic dynamics and heterogeneous intersection structures in the context of Internet of Vehicles (IoV). In this paper, we attempt to propose a cooperative multi-agent actor-critic (CMAC) deep reinforcement learning (DRL) approach with value decomposition based on edge computing architecture. The intuition behind CMAC is to decompose the global actor-critic learning tasks into several local actor-critic sub-problems with respect to each intersection. Each agent searches the local optimal decision by actor-critic network that takes the discrete state encoding about several consecutive frames of image-like traffic states as the inputs of the network. Among them, the green ratio output strategy considering multiple constraints is formulated in the output layer of the actor network, so that the continuous control of traffic signals using multi-agent DRL (MADRL) can be realized. Furthermore, a cooperative mechanism that considers contribution weight distributions of local agents to the global traffic pattern is proposed to coordinate multiple local agents to evolve toward global optimization. Especially, some parallel training tasks of CMAC with a large number of computing loads are deployed on the cloud side in the edge computing architecture to accelerate learning and reconstructing knowledge. The well-trained multi-agent model is downloaded from the cloud side into the edge side for real-time decision making of traffic network flow adaptive control. Simulation results with regard to a realistic traffic network demonstrate that the proposed CMAC approach under edge computing architecture outperforms the value-decomposition based multi-agent actor-critic (VMAC), independent multi-agent actor-critic (IMAC), and the fixed timing control (FTC) in terms of alleviating traffic congestion.

关键词： distributed deep reinforcement learning Edge computing Traffic network flow control Cooperative multi-agent actor-critic framework

来源：评论

学校读者我要写书评

暂无评论

Truly Scalable real-time Coincidence Processor based on Serial and parallel Hybrid Architecture

Truly Scalable Real-time Coincidence Processor based on Seri...

引用

IEEE Symposium on Nuclear Science (NSS/MIC)

作者： Mingyue Cui Zhixiang Zhao Huifan Qu Qiu Huang School of Biomedical Engineering Shanghai Jiao Tong University Shanghai China

Many PET systems use coincidence processors based on a serial architecture for coincidence detection, but this single-threaded coincidence detection has high latency and may even lose events in the case of a high event rate. The parallel coincidence processor has high event processing efficiency. However, the increase in detectors leads to a rapid expansion in the usage of hardware resources. In this study, we investigate a coincidence processor based on a serial and parallel hybrid architecture. The proposed processor first groups and merges data streams to reduce the number of them then uses serial processing to detect coincidence events within the merged data streams. After that, the processor uses a homogeneously distributed coincidence detection network to achieve parallel coincidence detection between different streams. The hybrid architecture of the coincidence processor saves hardware resource usage when the number of input data streams is high. When the coincidence processor has 10 input channels in the second stage of coincidence detection, it can achieve a maximum data transfer rate of 400M events/s and has a coincidence detection efficiency larger than 99.97%. The hybrid architecture of the coincidence processor presented in this paper enables real-time coincidence detection for systems with high event rates such as the long-axis PET while saving lots of hardware resources.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Task Allocation in distributed real time Database systems in IoT 1

引用

4th International Conference on Internet of Things and Connected Technologies (ICIoTCT)

作者： Choudhary, Shetan Ram Jha, C. K. Banasthali Vidyapith Bioinformat Ctr PO Banasthali Vidyapith Banasthali 304022 Rajasthan India Banasthali Vidyapith Dept Comp Sci PO Banasthali Vidyapith Vanasthali 304022 Rajasthan India

ISBN: (数字)9783030398750

ISBN: (纸本)9783030398750;9783030398743

In present scenario, distributed and parallel systems in the form of grid, cloud and even cloud based Internet of things (IoT) are cater the needs of demand for computing capacity. Internet of Things (IoT) is a new come up to connect objects/things and therefore transmit information between a variety of entities of the corporeal world or to the control centers where interpret this information. By use of available resources are play very crucial role to ensure systems schedule. In distributed (real time) database system, data allocation is one of the major problems. It affects the efficiency of the access to the requested data and thereby has large impact on the performance of the whole system. The data allocation involves data splitting, fragment replication, allocation choice to name a few issues. The distributed database system design putting all these factors together into consideration is complex and a Non-deterministic Polynomial (NP) hard. By applying Genetic Algorithm (GA), this work presents a virtual machine (VM) scheduling model to address the job allocation problem aiming to minimize the turnaround time. GA helps to attain a reasonable time for the query execution. The results of experiments have been examined to appraise the efficiency of our approach by comparing with best fit VM scheduling approach.

关键词： Task allocation distributed (real time) database systems Genetic Algorithm (GA) Task allocation model Task scheduling Turnaround time (TAT)

来源：评论

学校读者我要写书评

暂无评论

A distributed user-oriented IoT-based Air Pollution Monitoring

A distributed user-oriented IoT-based Air Pollution Monitori...

引用

IEEE International workshop on Computer-Aided Modeling, Analysis, and Design of Communication Links and Networks, CAMAD

作者： José Jorge Figueroa Figueroa Hao Shen Hamed Ahmadi Berk Canberk School of Physics Engineering and Technology University of York York UK Edinburgh Napier University United Kingdom

Environmental health services are paramount for ensuring the Quality of Life (QoL) in cities, with urban design playing a pivotal role. The rapid urbanization of cities globally has exacerbated air pollution, posing severe health risks to residents. Air quality is closely tied to human health, and elevated pollutant levels can lead to various illnesses, particularly affecting vulnerable populations. Indoor and outdoor air pollution is a leading cause of premature deaths in some regions. To address these challenges, governments and organizations are investing in air quality monitoring. This paper presents an IoT-based Air Pollution Monitor (APMIoT) comprising Raspberry Pico W embedded wireless systems and multiple sensors. These APMIoT modules transmit real-time data to a cloud server architecture, enabling the computation of pollutant indices and an Air Quality Index (AQI). Users can monitor and compare air quality data through an intuitive dashboard interface. The APMIoT includes key sensor modules for measuring particle matter, humidity, temperature, GPS coordinates, total volatile organic compounds (TVOC), and CO2 levels. It utilizes FreeRTOS for modular programming, ensuring independent handling of various processes. ThingSpeak serves as the cloud server, collecting, analysing, and visualizing data from single and multiple APMIoT devices. Custom analytics provide in-depth pollutant analysis and AQI representation. Testing demonstrates system reliability and alignment with external AQI data sources. This paper underscores the importance of open-source, customizable air quality monitoring systems for both indoor and outdoor settings. It offers a robust tool for environmental monitoring and air quality assessment, essential for managing urban health and well-being effectively.

关键词：

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：