检索结果-内蒙古大学图书馆

An electrical Impedance Imaging System Towards Edge Intelligence for Non-Destructive Testing of Concrete

Tsinghua Science and Technology 2024年第3期29卷 883-896页

作者： Abolfazl Roshanpanah Mahdi Abbasi Hani Attar Ayman Amer Mohammad R.Khosravi Ahmed A.Solyman Department of Electrical Engineering Islamic Azad UniversityScience and Research BranceTehran ***Iran Department of Computer Engineering Bu-Ali Sina UniversityHamedan ***Iran Department of Energy Engineering Zarqa UniversityZarqa 13110Jordan Department of Computer Engineering Persian Gulf UniversityBushehr ***Iran Department of Electrical and Electronics Engineering Faculty of Engineering and ArchitectureNişantaşıUniversityIstanbul 34398Turkey

In the construction industry,to prevent accidents,non-destructive tests are necessary and *** impedance tomography is a new technology in non-invasive imaging in which the image of the inner part of conductive bodies is reconstructed by the arrays of external electrodes that are connected on the periphery of the *** equipment is cheap,fast,and edge *** this imaging method,the image of electrical conductivity distribution(or its opposite;electrical impedance)of the internal parts of the target object is *** image reconstruction process is performed by injecting a precise electric current to the peripheral boundaries of the object,measuring the peripheral voltages induced from it and processing the collected *** an electrical impedance tomography system,the voltages measured in the peripheral boundaries have a non-linear equation with the electrical conductivity *** paper presents a cheap electrical Impedance Tomography(EIT)instrument for detecting impurities in the concrete.A voltage-controlled current source,a micro-controller,a set of multiplexers,a set of electrodes,and a personal computer constitute the structure of the *** conducted tests on concrete with impurities show that the designed EIT system can reveal impurities with a good accuracy in a reasonable time.

关键词： non-destructive testing system concrete electrical impedance tomography

来源：评论

学校读者我要写书评

暂无评论

A Study on Efficiency Improvements of DNN Accelerators via Denormalized Arithmetic Elimination 38

A Study on Efficiency Improvements of DNN Accelerators via D...

引用

38th International Conference on VLSI Design, VLSID 2025

作者： Kharitonov, Alexander Kundu, Sandip Institute of Computer Architecture & Computer Engineering University of Stuttgart Stuttgart Germany University of Massachusetts Department of Electrical & Computer Engineering Amherst United States

ISBN: (纸本)9798331522445

Deep Neural Networks (DNNs) excel in tasks such as vision and speech processing, driving their widespread use. A key operation in DNNs is convolution, which is often implemented using General Matrix Multiplication (GEMM). Modern CPUs incorporate hardware accelerators for faster GEMM operation. Reduced precision floating-point (RPF) formats such as bfloat16 and TensorFloat32 are popular in machine learning, offering a balance between classification accuracy, dynamic range for training gradients, and hardware efficiency compared to traditional IEEE 754 32-bit or 64-bit floating-point numbers. While RPF is well-studied in the context of DNNs, a major complexity arises from handling denormalized numbers. This paper investigates their impact on DNNs and finds that removing denormalized number support from hardware accelerators does not affect classification accuracy, while allowing significant improvements in hardware efficiency and performance. With proliferation of data centers to accommodate the growing number of DNN applications, power reductions at the GEMM level can significantly improve cluster-wide efficiency, promoting sustainability. Our results indicate that eliminating denormalized arithmetic leads to significant improvements in multiplier circuit efficiency, with reductions of up to 46% in area (LUT count), 28% in longest path delay, and 59% in power consumption, all while maintaining DNN classification accuracy. © 2025 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Joint Biomedical Entity and Relation Extraction Based on Multi-Granularity Convolutional Tokens Pairs of Labeling

引用

computers, Materials & Continua 2024年第9期80卷 4325-4340页

作者： Zhaojie Sun Linlin Xing Longbo Zhang Hongzhen Cai Maozu Guo Department of Computer Science and Technology Shandong University of TechnologyZibo255000China Department of Agricultural Engineering and Food Science Shandong University of TechnologyZibo255000China Department of Electrical and Information Engineering Beijing University of Civil Engineering and ArchitectureBeijing100044China

Extracting valuable information frombiomedical texts is one of the current research hotspots of concern to a wide range of *** biomedical corpus contains numerous complex long sentences and overlapping relational triples,making most generalized domain joint modeling methods difficult to apply effectively in this *** a complex semantic environment in biomedical texts,in this paper,we propose a novel perspective to perform joint entity and relation extraction;existing studies divide the relation triples into several steps or ***,the three elements in the relation triples are interdependent and inseparable,so we regard joint extraction as a tripartite classification *** the same time,fromthe perspective of triple classification,we design amulti-granularity 2D convolution to refine the word pair table and better utilize the dependencies between biomedical word ***,we use a biaffine predictor to assist in predicting the labels of word pairs for relation *** model(MCTPL)Multi-granularity Convolutional Tokens Pairs of Labeling better utilizes the elements of triples and improves the ability to extract overlapping triples compared to previous ***,we evaluated our model on two publicly accessible *** experimental results show that our model’s ability to extract relation triples on the CPI dataset improves the F1 score by 2.34%compared to the current optimal *** the DDI dataset,the F1 value improves the F1 value by 1.68%compared to the current optimal *** model achieved state-of-the-art performance compared to other baseline models in biomedical text entity relation extraction.

关键词： Deep learning biomedical joint extraction triple classification multi-granularity 2D convolution

来源：评论

学校读者我要写书评

暂无评论

Pattern Generation for Efficient Acceptability Verification of Approximate Circuits

Pattern Generation for Efficient Acceptability Verification ...

引用

2024 International VLSI Symposium on Technology, Systems and Applications, VLSI TSA 2024

作者： Chao, Wei-Ji Kourfali, Alexandra Lylina, Natalia Wu, Jun-Tsung Yang, Jing-An Wang, Chih-Hao Hsieh, Tong-Yu Wunderlich, Hans-Joachim National Sun Yat-sen University Department of Electrical Engineering Taiwan Institute of Computer Architecture and Computer Engineering University of Stuttgart Germany

ISBN: (纸本)9798350360349

Approximate computing allows designers to trade-off precision with hardware cost and power consumption. The possible degree of approximation relies on a realistic quality assessment with functional input sequences and metrics to quantify the error magnitude. The complete exploration of the input space is impracticable in most cases but a partial input sequence might underestimate the severity of possible errors. The paper at hand presents an approach to generate patterns for efficient acceptability verification of an approximate circuit and to complement conventional quality assessment methods. A modified miter design indicates the differences between the approximate and the precise circuit, and an existing ATPG flow is used to maximize the differences. A case study on JPEG2000 decoder validates that our approach can efficiently and effectively identify unacceptable approximate results where conventional image quality assessment methods failed. © 2024 IEEE.

关键词： Timing circuits

来源：评论

学校读者我要写书评

暂无评论

Course construction based on FD-QM standards and analysis and mining of course data 24

Course construction based on FD-QM standards and analysis an...

引用

2024 International Conference on Intelligent Education and computer Technology, IECT 2024

作者： Lv, Cheng Department of Computer Science School of Electrical and Information Engineering Beijing University of Civil Engineering and Architecture Beijing100044 China

ISBN: (纸本)9798400709920

In response to the shortcomings of the SPOC course "Introduction to Computational Thinking"at Beijing University of Civil engineering and architecture, the teaching team has transformed and improved the course design and practice based on the existing High quality undergraduate courses in Beijing universities and Beijing Curriculum Ideological and Political Demonstration Course. We aim to maintain consistency and linkage in learning objectives, learning assessments, teaching materials, learning activities, and course technology under the principle of consistent construction. Learning objectives are clearer and more measurable;learning assessment is more scientific, diverse, and reliable;Curriculum resources can meet the needs of students at different levels and majors;learning activities can fully mobilize students' subjective initiative;Curriculum technology helps to achieve learning objectives, and can reflect the characteristics of the discipline, with universality and progressiveness. Through the construction and practice of the FD-QM standard, the course team has established the principles of course standardization, clarified the direction of course material construction, drawn a knowledge graph of course knowledge points, accurately grasped the degree of learning objectives, upgraded the "characteristic"teaching resource library, enhanced student interest, and integrated ideological and political education into the curriculum, ultimately achieving a comprehensive improvement in the quality of course teaching. © 2024 ACM.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Analysis and Practice of Ideological and Political Education in computer Public Basic Courses in architecture Universities Based on Machine Learning and Deep Learning 24

Analysis and Practice of Ideological and Political Education...

引用

2024 Guangdong-Hong Kong-Macao Greater Bay Area International Conference on Education Digitalization and computer Science, EDCS 2024

作者： Lv, Cheng Department of Computer Science School of Electrical and Information Engineering Beijing University of Civil Engineering and Architecture Beijing100044 China

ISBN: (纸本)9798400710360

In response to the shortcomings of ideological and political education in the computer basic course of our school, the teaching team has conducted in-depth research on the connotation of ideological and political education in the course, accurately grasped the direction of ideological and political education in the course, innovatively proposed the"progressive method of ideological and political education", and constructed an integrated curriculum system of ideological and political education in the course;Using Orange3 software and machine learning algorithms to deeply explore the ideological and political elements of the curriculum, constructing an analytical model, formulating personalized teaching and learning strategies, and constructing a double-layer teaching evaluation system that emphasizes both morality and ability. Through the analysis of course data, it is shown that the effectiveness of ideological and political education in the curriculum has been comprehensively improved, and the quality of teaching has been comprehensively enhanced. © 2024 Copyright held by the owner/author(s).

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Training Neuro-Fuzzy by Using Meta-Heuristic Algorithms for MPPT

引用

computer Systems Science & engineering 2023年第4期45卷 69-84页

作者： Ceren Baştemur Kaya Ebubekir Kaya Göksel Gökkuş Department of Computer Technologies Nevsehir Vocational CollegeNevsehir Haci Bektas Veli UniversityNevşehir50300Turkey Department of Computer Engineering Faculty of Engineering and ArchitectureNevsehir Haci Bektas Veli UniversityNevşehir50300Turkey Department of Electrical and Electronics Engineering Faculty of Engineering and ArchitectureNevsehir Haci Bektas Veli UniversityNevşehir50300Turkey

It is one of the topics that have been studied extensively on maximum power point tracking(MPPT)*** or soft computing methods are used for *** soft computing approaches are more effective than traditional approaches,studies on MPPT have shifted in this *** study aims comparison of performance of seven meta-heuristic training algorithms in the neuro-fuzzy training for *** meta-heuristic training algorithms used are particle swarm optimization(PSO),harmony search(HS),cuckoo search(CS),artificial bee colony(ABC)algorithm,bee algorithm(BA),differential evolution(DE)and flower pollination algorithm(FPA).The antecedent and conclusion parameters of neuro-fuzzy are determined by these *** data of a 250 W photovoltaic(PV)is used in the *** effective MPPT,different neuro-fuzzy structures,different membership functions and different control parameter values are evaluated in *** training algorithms are compared in terms of solution quality and convergence *** strengths and weaknesses of these algorithms are *** is seen that the type and number of membership function,colony size,number of generations affect the solution quality and convergence speed of the training *** a result,it has been observed that CS and ABC algorithm are more effective than other algorithms in terms of solution quality and convergence in solving the related problem.

关键词： Optimization meta-heuristic algorithm neuro-fuzzy MPPT photovoltaic system

来源：评论

学校读者我要写书评

暂无评论

Assessing the operational design domain of lane support system for automated vehicles in different weather and road conditions

引用

Journal of Traffic and Transportation engineering(English Edition) 2022年第4期9卷 631-644页

作者： Giuseppina Pappalardo Riccardo Caponetto Rosario Varrica Salvatore Cafiso Department of Civil Engineering and Architecture University of CataniaCatania 95125Italy Department of Electrical Electronic and Computer EngineeringUniversity of CataniaCatania 95125Italy

With the growing rate of automated vehicles(AVs)at the lower level of automation,the experimental tests are also in progress with vehicles at higher *** the absence of extended digital infrastructures and deployment of level 5 full automated vehicles,the physical infrastructure is required to maintain a fundamental role to enable their introduction in public *** paper focuses on lane support system(LSS)whose operational design domain(ODD)is strongly connected to the road characteristics and *** experimental test was carried out with a state of the art,and LSS and advanced technologies were used for road monitoring on different roads under various environmental conditions including dry,wet pavements and *** applied the generalized estimation equation for logistic regression to account within-cluster homogeneity which is induced by repeated measures on the same road *** models allow the identification of variables that are significant for the LSS fault probability among various effects of road features including marking,pavement distress,weather conditions,horizontal curvature,and cross *** pointed out the relevance of the wet retro-reflection of marking(RLw)and the horizontal curvature in the definition of ODD for *** values have been proposed for the tested *** pavement doesn’t affect the LSS performance when compared to the dry *** was shown to be critical even with very good road characteristics.

关键词： Lane support system Physical infrastructure Operational design domain Weather condition

来源：评论

学校读者我要写书评

暂无评论

Intrusion Detection System Through Deep Learning in Routing MANET Networks

引用

Intelligent Automation & Soft Computing 2023年第7期37卷 269-281页

作者： Zainab Ali Abbood DoguÇagdaşAtilla Çagatay Aydin Department Electrical and Computer Engineering Altinbas UniversityIstanbulTurkey Department Computer Technology Engineering Al-Esraa UniversityBaghdadIraq Electric Autonomous and Unmanned Vehicles Application and Research CentreAltinbas UniversityIstanbulTurkey Faculty of Engineering and Architecture Altinbas UniversityIstanbulTurkey Department Electrical and Electronics Engineering Ege UniversityIzmirTurkey

Deep learning(DL)is a subdivision of machine learning(ML)that employs numerous algorithms,each of which provides various explanations of the data it consumes;mobile ad-hoc networks(MANET)are growing in *** reasons including node mobility,due to MANET’s potential to provide small-cost solutions for real-world contact challenges,decentralized management,and restricted bandwidth,MANETs are more vulnerable to security *** protecting MANETs from attack,encryption and authentication schemes have their ***,deep learning(DL)approaches in intrusion detection sys-tems(IDS)can adapt to the changing environment of MANETs and allow a sys-tem to make intrusion decisions while learning about its mobility in the *** are a secondary deﬁance system for mobile ad-hoc networks *** since they monitor network trafﬁc and report anything ***,many scientists have employed deep neural networks(DNNs)to address intrusion detection *** paper used MANET to recognize com-plex patterns by focusing on security standards through efﬁciency determination and identifying malicious nodes,and mitigating network attacks using the three algorithms presented Cascading Back Propagation Neural Network(CBPNN),Feedforward-Neural-Network(FNN),and Cascading-Back-Propagation-Neural-Network(CBPNN)(FFNN).In addition to Convolutional-Neural-Network(CNN),these primary forms of deep neural network(DNN)building designs are widely used to improve the performance of intrusion detection systems(IDS)and the use of IDS in conjunction with machine learning(ML).Further-more,machine learning(ML)techniques than their statistical and logical methods provide MANET network learning capabilities and encourage adaptation to differ-ent *** with another current model,The proposed model has better average receiving packet(ARP)and end-to-end(E2E)*** results have been obtained from CBP,FFNN and CNN 74%,82%and 85%,respectively,by the ti

关键词： ARP CBPNN CNN DNN DL E2E FFNN IDS ML MANET security

来源：评论

学校读者我要写书评

暂无评论

A Robust Hybrid Control Model Implementation for Autonomous Vehicles 8

A Robust Hybrid Control Model Implementation for Autonomous ...

引用

8th International Artificial Intelligence and Data Processing Symposium, IDAP 2024

作者： Al-Jumaili, Mustafa Hamid Ozok, Yasa Eksioglu Ibrahim, Abdullahi Abdu Bayat, Oguz Altinbas University Electrical and Computer Engineering Department Istanbul Turkey Ramadi Iraq Altinbas University Electrical and Electronics Engineering Department Istanbul Turkey Beykoz University Faculty of Engineering and Architecture Istanbul Turkey

ISBN: (纸本)9798331531492

This work presents a robust control strategy for controlling autonomous vehicles under various conditions. This approach makes use of two controllers to guarantee excellent performance and a few faults when the car is traveling. Model Predictive and Stanley based controller (MPS) is the name of the new control system. This combines the functionality of a Stanley controller with a model predictive controller. The suggested approach tries to address these issues and provides a high-performance control system. Utilizing the finest aspects of both controllers and attempting to improve the other, this hybrid approach to integrating two well-known controllers provides advantages. The MPS is put to the test on straight and curvy roads in a variety of scenarios for both path-following and vehicle control. This controller has demonstrated excellent performance and adaptability to handle various autonomous driving conditions. When the findings are compared to earlier controller kinds, the suggested system performs better. © 2024 IEEE.

关键词： Predictive control systems

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：