检索结果-内蒙古大学图书馆

Intelligent systems and Computational Networks (ICISCN), International Conference on

作者： Yin Wu Huicai Zhao Xingfu Huang Liqiong Huang Yuyang Hu Guangxi Power Grid Power Dispatching and Control Center Nanning China Guangxi Power Grid Limited Liability Company Nanning Power Supply Bureau Nanning China Guangxi Power Grid Limited Liability Company Guilin Power Supply Bureau Guilin China

ISBN: (数字)9798331529246

ISBN: (纸本)9798331529253

Intelligent substations use fiber optic as the information transmission medium, transforming the interconnection relationship between secondary devices into fiber optic connections. The corresponding secondary circuits and hardware platforms are replaced with virtual circuits and software templates, resulting in a significant change in maintenance work methods and higher requirements for operators' maintenance work. This article proposes an intelligent substation safety measure ticket generation algorithm based on multi-scale feature convolutional neural network (MSF-CNN) and inference machine. Firstly, a neural network model suitable for safety ticket generation was designed and trained. Combining the structural characteristics of DenseNet, multi-scale feature extraction and logical relationship modeling were achieved through multi-layer convolution, concatenation, and pooling processing. The model uses hyperbolic tangent function as the activation function to improve the accuracy of regression prediction. Secondly, a custom word vector and equipment association modeling method based on SCD file parsing are proposed for the electricity proprietary terms and multi item logical relationships involved in the safety measures ticket text, in order to improve data expression accuracy and model understanding ability. In addition, based on the functional correlation and input-output interaction characteristics of substation equipment, a three-layer neural network-based inference engine was constructed to generate maintenance safety measures for primary and secondary equipment. The experimental results showed that the MSF-CNN model performed the best in accuracy, recall, and F1 score, with an accuracy of 92.5%, recall of 90.8%, and F1 score of 91.6%.

关键词： optical fibers Substations Accuracy Neural networks Training data Data models Inference algorithms Safety Maintenance Engines

来源：评论

学校读者我要写书评

暂无评论

Locally-Adaptive Nonparametric Online Learning 34

Locally-Adaptive Nonparametric Online Learning

引用

34th Conference on Neural information processing systems (NeurIPS)

作者： Kuzborskij, Ilja Cesa-Bianchi, Nicolo DeepMind London England Univ Milan Dept Comp Sci Milan Italy Univ Milan DSRC Milan Italy

ISBN: (纸本)9781713829546

One of the main strengths of online algorithms is their ability to adapt to arbitrary data sequences. This is especially important in nonparametric settings, where performance is measured against rich classes of comparator functions that are able to fit complex environments. Although such hard comparators and complex environments may exhibit local regularities, efficient algorithms, which can provably take advantage of these local patterns, are hardly known. We fill this gap by introducing efficient online algorithms (based on a single versatile master algorithm) each adapting to one of the following regularities: (i) local Lipschitzness of the competitor function, (ii) local metric dimension of the instance sequence, (iii) local performance of the predictor across different regions of the instance space. Extending previous approaches, we design algorithms that dynamically grow hierarchical "-nets on the instance space whose prunings correspond to different "locality profiles" for the problem at hand. Using a technique based on tree experts, we simultaneously and efficiently compete against all such prunings, and prove regret bounds each scaling with a quantity associated with a different type of local regularity. When competing against "simple" locality profiles, our technique delivers regret bounds that are significantly better than those proven using the previous approach. On the other hand, the time dependence of our bounds is not worse than that obtained by ignoring any local regularities.

关键词： Comparators (optical)

来源：评论

学校读者我要写书评

暂无评论

processing Power-based Task Scheduling Technique for Cloud-Fog Environment

Processing Power-based Task Scheduling Technique for Cloud-F...

引用

IEEE Conference on Industrial Electronics and Applications (ICIEA)

作者： Norbu Z. Lepcha Malka N. Halgamuge Computer Science and Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai India Department of Information Systems and Business Analytics RMIT University Melbourne Australia

ISBN: (纸本)9781665409858

Internet of Things (IoT) applications have emerged as a critical component in improving people’s quality of life. The increasing volume of data generated by IoT devices, on the other hand, places a strain on the resources of traditional cloud data centres. This makes cloud data centres unable to meet the demands of IoT applications. Due to resource constraints and the massive connectivity of IoT devices, efficient task (incoming request) allocation is critical for service providers. We create a novel processing power-based task scheduling technique that employs a broker manager to distribute tasks and the process strategy across multiple devices. This is important in cloud technology because it enables organisations to effectively scale their processes. We use multithreading to parallelize processes and evaluate the performance of the proposed model using existing task allocation algorithms (i) round-robin, (ii) weighted round-robin, (iii) random allocation, (iv) genetic algorithm, and (v) dynamic algorithm. Our results show that when there are few tasks and one cluster has more processing capacity than the others, a weighted round-robin algorithm works well. The effectiveness of allocating based on weight shows no improvement in task completion time as task size increases. Using our proposed model, we show that the dynamic algorithm outperforms all other algorithms for task scheduling by 1.37 times for all task sizes.

关键词： Performance evaluation Cloud computing Data centers Job shop scheduling Heuristic algorithms Clustering algorithms Dynamic scheduling

来源：评论

学校读者我要写书评

暂无评论

CREMON: Cryptography Embedded on the Convolutional Neural Network Accelerator

引用

IEEE TRANSACTIONS ON CIRCUITS AND systems ii-EXPRESS BRIEFS 2020年第12期67卷 3337-3341页

作者： Choi, Yeongjae Sim, Jaehyeong Kim, Lee-Sup Korea Adv Inst Sci & Technol Sch Elect Engn Daejeon 34141 South Korea

Due to their excellent performance, tremendous progress has been made in the development of convolutional neural network (CNN) algorithms and efficient CNN accelerators for edge devices. At the same time, security concerns about CNN processing have increased regarding user privacy and safety. In this brief, we focus on developing an efficient data ciphering system embedded in a CNN accelerator. The number of operations of CNN and security workloads, AES-128 in our system, constantly changes during execution, thereby varying their relative ratio. To efficiently support various convolution/AES workloads, we propose CREMON, a reconfigurable system with a cryptography reconfigurable processing element (CRPE). A test chip with the proposed scheme was implemented and tested for performance verification. As a result, the CREMON prototype chip achieved state-of-the-art performance/area efficiency for AES and improved energy efficiency by up to 44.1% in processing CNN/AES workloads.

关键词： Convolution Kernel Hardware Engines Cryptography Throughput Security in CNN processing CNN accelerator AES hardware reconfigurable processor energy-efficient hardware

来源：评论

学校读者我要写书评

暂无评论

Mining Alarm Association Rules in optical Transmission Networks Using a Statistical Approach

Mining Alarm Association Rules in Optical Transmission Netwo...

引用

IEEE International Conference on High Performance Computing and Communications (HPCC)

作者： Miao Deng Peng Li Yu Liu Rongjing Zhu Yujie Zhang School of Computer Science and Technology Wuhan University of Science and Technology China Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System China

Due to the interconnection between devices in the optical transmission network (OTN), when one device fails and generates alarm information, a large number of other invalid alarms are generated in OTN. How to mining association rules in alarm data is an important problem. In this paper, we investigate the association rules mining problem based on a statistical method. First, we remove the chattering alarm in preprocess to reduce data redundancy. Second, we propose a statistics-based association rule mining algorithm. We use a sliding time window to scan the alarm data, and we exploit the matrix to record the corresponding results. According to the matrix, we calculate the support and confidence of association rules. Compared with other traditional association rule mining algorithms, the proposed algorithm does not need to set the minimum support artificially, and the obtained association rules have strong causality. Through extensive experiments on syn-thetic and real OTN alarm datasets, we verify the effectiveness of our proposed algorithm and the correctness of the obtained association rules.

关键词： optical interconnections Statistical analysis Redundancy optical fiber networks Adaptive optics Data mining optical devices

来源：评论

学校读者我要写书评

暂无评论

Evaluation of Geometric Data Registration of Small Objects from Non-Invasive Techniques: Applicability to the HBIM Field

引用

SENSORS 2023年第3期23卷 1730-1730页

作者： Moyano, Juan Cabrera-Revuelta, Elena Nieto-Julian, Juan E. Fernandez-Alconchel, Maria Fernandez-Valderrama, Pedro Univ Seville Dept Graph Express & Bldg Engn Ave Reina Mercedes 4A Seville 41012 Spain Univ Cadiz Dept Mech Engn & Ind Design 10 Ave Puerto Real Cadiz 11510 Spain

Reverse engineering and the creation of digital twins are advantageous for documenting, cataloging, and maintenance control tracking in the cultural heritage field. Digital copies of the objects into Building information Models (BIM) add cultural interest to every artistic work. Low-cost 3D sensors, particularly structured-light scanners, have evolved towards multiple uses in the entertainment market but also as data acquisition and processing techniques for research purposes. Nowadays, with the development of structured-light data capture technologies, the geometry of objects can be recorded in high-resolution 3D datasets at a very low cost. On this basis, this research addresses a small artifact with geometric singularities that is representative of small museum objects. For this, the precision of two structured-light scanners is compared with that of the photogrammetric technique based on short-range image capture: a high-cost Artec Spider 3D scanner, and the low-cost Revopoint POP 3D scanner. Data capture accuracy is evaluated through a mathematical algorithm and point set segmentation to verify the spatial resolution. In addition, the precision of the 3D model is studied through a vector analysis in a BIM environment, an unprecedented analysis until now. The work evaluates the accuracy of the devices through algorithms and the study of point density at the submillimeter scale. Although the results of the 3D geometry may vary in a morphometric analysis depending on the device records, the results demonstrate similar accuracies in that submillimeter range. Photogrammetry achieved an accuracy of 0.70 mm versus the Artec Spider and 0.57 mm against the Revopoint POP 3D scanner.

关键词： BIM small object structured-light systems 3D optical scanner point cloud sculpture cultural heritage

来源：评论

学校读者我要写书评

暂无评论

RNC: Efficient RRAM-aware NAS and Compilation for DNNs on Resource-Constrained Edge devices

RNC: Efficient RRAM-aware NAS and Compilation for DNNs on Re...

引用

IEEE International Conference on Computer Design: VLSI in Computers and Processors, (ICCD)

作者： Kam Chi Loong Shihao Han Sishuo Liu Ning Lin Zhongrui Wang Department of Electrical and Electronic Engineering The University of Hong Kong Hong Kong China ACCESS - AI Chip Center for Emerging Smart Systems Hong Kong Science Park Hong Kong China School of Astronautics Harbin Institute of Technology Harbin China School of Microelectronics Southern University of Science and Technology Shenzhen China

ISBN: (数字)9798350380408

ISBN: (纸本)9798350380415

Computing-in-memory (CIM) is an emerging computing paradigm, offering noteworthy potential for accelerating neural networks with high parallelism, low latency, and energy efficiency compared to conventional von Neumann architectures. However, existing research has primarily focused on hardware architecture and network co-design for large-scale neural networks, without considering resource constraints. In this study, we aim to develop edge-friendly deep neural networks (DNNs) for accelerators based on resistive random-access memory (RRAM). To achieve this, we propose an edge compilation and resource-constrained RRAM-aware neural architecture search (NAS) framework to search for optimized neural networks meeting specific hardware constraints. Our compilation approach integrates layer partitioning, duplication, and network packing to maximize the utilization of computation units. The resulting network architecture can be optimized for either high accuracy or low latency using a one-shot neural network approach with Pareto optimality achieved through the Non-dominated Sorted Genetic Algorithm ii (NSGA-ii). The compilation of mobile-friendly networks, like Squeezenet and MobilenetV3 small can achieve over 80% of utilization and over 6x speedup compared to ISAAC-like framework with different crossbar resources. The resulting model from NAS optimized for speed achieved 5x-30x speedup. The code for this paper is available at https://***/ArChiiii/rram_nas_comp_pack.

关键词： Computer architecture Parallel processing Network architecture In-memory computing Solids Hardware Common information Model (computing) Neural architecture search Low latency communication Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Best practices and current implementation of emerging smartphone- based (bio)sensors- Part 1: Data handling and ethics

引用

TRAC-TRENDS IN ANALYTICAL CHEMISTRY 2023年 158卷

作者： Ross, G. M. S. Zhao, Y. Bosman, A. J. Geballa-Koukoula, A. Zhou, H. Elliott, C. T. Nielen, M. W. F. Rafferty, K. Salentijn, G. IJ. Wageningen Univ & Res Wageningen Food Safety Res WFSR POB 230 NL-6700 AE Wageningen Netherlands Wageningen Univ Lab Organ Chem Stippeneng 4 NL-6708 WE Wageningen Netherlands Queens Univ Belfast Sch Elect Elect Engn & Comp Sci 16A Malone Rd Belfast BT9 5BN North Ireland Univ Leicester Sch Comp & Math Sci Univ Rd Leicester LE1 7RH England Queens Univ Belfast Inst Global Food Secur Sch Biol Sci 19 Chlorine Gardens Belfast BT9 5DL North Ireland Thammasat Univ Fac Sci & Technol Sch Food Sci & Technol 99 Mhu 18Phahonyothin Rd Pathum Thani 12120 Thailand Wageningen Univ & Res Wageningen Food Safety Res WFSR POB 230 NL-6700 AE Wageningen Netherlands

Smartphones are ubiquitous in modern society;in 2021, the number of active subscriptions surpassed 6 billion. These devices have become more than a means of communication;smartphones are powerful, continuously connected, miniaturized computers capable of passively and actively collecting (private) information for us and from us. Their implementation as detectors or instrumental interfaces in emerging smartphone-based (bio)sensors (SbSs) has facilitated a shift towards portable point-of-care platforms for healthcare and point-of-need systems for food safety, environmental monitoring, and forensic applications. These familiar, handheld devices have the capacity to popularize analytical chemistry by simplifying complicated laboratory protocols and automating advanced data handling without requiring expensive equipment or trained analysts. To elucidate the technological, legal, and ethical challenges associated with developing SbSs, we reviewed the existing literature (2016-2021), providing an in-depth critical analysis of state-of-the-art optical and electrochemical SbSs. This analysis revealed the key areas to consider for emerging SbSs, which we will address in a set of review papers. Part I (this review) will consider (i) how the SbS data are acquired and processed and (ii) the implementation of privacy and data protection strategies to keep this data secure. Part ii will then focus on (iii) the development and validation of biosensors and (iv) how to assess the usability and (potential) social impact of emerging SbSs. Finally, these insights are applied to generate proposed best practices to help guide the future ethical data handling and development of smartphone-based devices for analytical chemistry applications.(c) 2022 The Authors. Published by Elsevier B.V.

关键词： Data acquisition Data processing Artificial intelligence Privacy Security GDPR

来源：评论

学校读者我要写书评

暂无评论

Health supervisor: Mobile application for round-the-clock remote monitoring of the human functional state 2

Health supervisor: Mobile application for round-the-clock re...

引用

2nd International Workshop on Intelligent information Technologies and systems of information Security, IntellTSIS 2021

作者： Melnyk, Anatoliy Morozov, Yurii Havano, Bohdan Hupalo, Petro Intron ltd Kulparkivska str. 59 Lviv79015 Ukraine The John Paul II Catholic University of Lublin Al. Raclawickie 14 Lublin20-950 Poland

In this article, an application for smartphones that allows supervisors to observe constantly the functional state of their clients is proposed. The application is based on wireless devices and is designed to monitor the human functional state round-the-clock regardless of their location. The human functional state is estimated on the analysis of the following parameters: the oxygen level in the blood, pulse frequency and respiratory rate, continuously and remotely. These data from the pulse oximeter wirelessly connected to the client's smartphone will be sent to the server, where the supervisor will receive information about the client functional state and can decide on further activity. Importantly, in this way it will be possible to track the functional state in clients that need constant observation, at first with Covid-19 and with other diseases such as asthma, vascular diseases, and cancer. An article provides detail description of the proposed round-the-clock remote monitoring method, depicts the elements of the monitoring system and organization of the data transmission network, presents the structure of the round-the-clock remote monitoring system and the organization of remote monitoring by supervisors of client's functional state using the HealthSupervisor mobile application. The algorithms of data processing in HealthSupervisor mobile application are described and the main features and benefits of using the HealthSupervisor mobile application are presented. © 2021 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0). CEUR Workshop Proceedings (***)

关键词： Smartphones

来源：评论

学校读者我要写书评

暂无评论

Primer on silicon neuromorphic photonic processors: architecture and compiler

引用

NANOPHOTONICS 2020年第13期9卷 4055-4073页

作者： de Lima, Thomas Ferreira Tait, Alexander N. Mehrabian, Armin Nahmias, Mitchell A. Huang, Chaoran Peng, Hsuan-Tung Marquez, Bicky A. Miscuglio, Mario El-Ghazawi, Tarek Sorger, Volker J. Shastri, Bhavin J. Prucnal, Paul R. Queens Univ Dept Phys Engn Phys & Astron Kingston ON KL7 3N6 Canada Princeton Univ Dept Elect Engn Princeton NJ 08544 USA George Washington Univ Dept Elect & Comp Engn Washington DC 20052 USA

Microelectronic computers have encountered challenges in meeting all of today's demands for information processing. Meeting these demands will require the development of unconventional computers employing alternative processing models and new device physics. Neural network models have come to dominate modern machine learning algorithms, and specialized electronic hardware has been developed to implement them more efficiently. A silicon photonic integration industry promises to bring manufacturing ecosystems normally reserved for microelectronics to photonics. Photonic devices have already found simple analog signal processing niches where electronics cannot provide sufficient bandwidth and reconfigurability. In order to solve more complex information processing problems, they will have to adopt a processing model that generalizes and scales. Neuromorphic photonics aims to map physical models of optoelectronic systems to abstract models of neural networks. It represents a new opportunity for machine information processing on sub-nanosecond timescales, with application to mathematical programming, intelligent radio frequency signal processing, and real-time control. The strategy of neuromorphic engineering is to externalize the risk of developing computational theory alongside hardware. The strategy of remaining compatible with silicon photonics externalizes the risk of platform development. In this perspective article, we provide a rationale for a neuromorphic photonics processor, envisioning its architecture and a compiler. We also discuss how it can be interfaced with a general purpose computer, i.e. a CPU, as a coprocessor to target specific applications. This paper is intended for a wide audience and provides a roadmap for expanding research in the direction of transforming neuromorphic photonics into a viable and useful candidate for accelerating neuromorphic computing.

关键词： neuromorphic computing optical neural networks photonic integrated circuits silicon photonics ultrafast information processing

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：