检索结果-内蒙古大学图书馆

Proceedings of the 58th Annual ACM/IEEE Design Automation Conference

作者： Georgios Zervakis Ourania Spantidi Iraklis Anagnostopoulos Hussam Amrouch Jörg Henkel Chair for Embedded Systems (CES) Karlsruhe Institute of Technology Karlsruhe Germany Department of Electrical Computer and Biomedical Engineering Southern Illinois University Carbondale U.S.A Department of Electrical Computer and Biomedical Engineering Southern Illinois University Carbondale U.S.A. Chair of Semiconductor Test and Reliability (STAR) University of Stuttgart Stuttgart Germany

ISBN: (纸本)9781665432740

In this work, we introduce a control variate approximation technique for low error approximate Deep Neural Network (DNN) accelerators. The control variate technique is used in Monte Carlo methods to achieve variance reduction. Our approach significantly decreases the induced error due to approximate multiplications in DNN inference, without requiring time-exhaustive retraining compared to state-of-the-art. Leveraging our control variate method, we use highly approximated multipliers to generate power-optimized DNN accelerators. Our experimental evaluation on six DNNs, for Cifar-10 and Cifar-100 datasets, demonstrates that, compared to the accurate design, our control variate approximation achieves same performance and 24% power reduction for a merely 0.16% accuracy loss.

关键词： approximate computing

来源：评论

学校读者我要写书评

暂无评论

NPU Thermal Management

NPU Thermal Management

引用

作者： Amrouch, Hussam Zervakis, Georgios Salamin, Sami Kattan, Hammam Anagnostopoulos, Iraklis Henkel, Jorg in the Computer Science Electrical Engineering Faculty University of Stuttgart Stuttgart Germany Chair for Embedded Systems Karlsruhe Institute of Technology Karlsruhe Germany Department of Electrical and Computer Engineering Southern Illinois University CarbondaleIL United States

Neural processing units (NPUs) are becoming an integral part in all modern computing systems due to their substantial role in accelerating neural networks (NNs). The significant improvements in cost-energy-performance stem from the massive array of multiply accumulate (MAC) units that remarkably boosts the throughput of NN inference. In this work, we are the first to investigate the thermal challenges that NPUs bring, revealing how MAC arrays, which form the heart of any NPU, impose serious thermal bottlenecks to on-chip systems due to their excessive power densities. For the first time, we explore: 1) the effectiveness of precision scaling and frequency scaling (FS) in temperature reductions and 2) how advanced on-chip cooling using superlattice thin-film thermoelectric (TE) open doors for new tradeoffs between temperature, throughput, cooling cost, and inference accuracy in NPU chips. Our work unveils that hybrid thermal management, which composes different means to reduce the NPU temperature, is a key. To achieve that, we propose and implement PFS-TE technique that couples precision and FS together with superlattice TE cooling for effective NPU thermal management. Using commercial signoff tools, we obtain accurate power and timing analysis of MAC arrays after a full-chip design is performed based on 14-nm Intel FinFET technology. Then, multiphysics simulations using finite-element methods are carried out for accurate heat simulations in the presence and absence of on-chip cooling. Afterward, comprehensive design-space exploration is presented to demonstrate the Pareto frontier and the existing tradeoffs between temperature reductions, power overheads due to cooling, throughput, and inference accuracy. Using a wide range of NNs trained for image classification, experimental results demonstrate that our novel NPU thermal management increases the inference efficiency (TOPS/Joule) by $1.33\times $ , $1.87\times $ , and $2\times $ under different temperature constrain

关键词： Temperature control

来源：评论

学校读者我要写书评

暂无评论

Quantitative Evaluation to Detect Crack Depth in Beams Based on CNN-RNN-LSTM Approach

Quantitative Evaluation to Detect Crack Depth in Beams Based...

引用

Self Sustainable Artificial Intelligence Systems (ICSSAS), International Conference on

作者： Mohammad Asif Gandhi A. N. Swaminathen Deepak T. Patil A Ravitheja R. Kamali Akshay Rajput Department of Mechanical Engineering Anjuman-I-Islam's Kalsekar Technical Campus Panvel Maharashtra India Adi Shankara Institute of Engineering and Technology Kerala India Bharati Vidyapeeth college of Architecture Navi Mumbai Maharashtra India Department of Civil Engineering SVR Engineering College Kurnool Andhra Pradesh India Department of Computer Science And Engineering Knowledge Institute of Technology Salem Tamilnadu India Department of Computer Science & Engineering Graphic Era Deemed to be University Dehradun Uttarakhand India

In this study, the proposed approach offers a novel hybrid image-based deep learning method for autonomous concrete fracture identification. Cracks are easier to spot and false positives are reduced with hybrid images that include visual and infrared thermography data. In specifically, a Visible and infrared camera as well as a line laser make up a hybrid imaging system for spatially scanning unmanned vehicles can efficiently assess large-scale concrete-made constructions like bridges and dams. Crack detection is a commonplace task in many industrial domains, however the current method of relying on expert judgment is typically laborious, time consuming, and inaccurate. The practical benefits of automated decision-making increase as the size of the target concrete construction grows. Cracks can be automatically identified and seen using the proposed method. Preprocessing, segmentation, feature extraction, and model training are the four components of the proposed method. It performs clever edge recognition, scaling, and greyscale conversion as part of its preparation. Improved K-Means segmentation is used for the separation. It employs GLCM for feature extraction, and CNN-RNN-LSTM for model training. The new method is compared to two established approaches, CNN-RNN and CNN-LSTM, and is found to be superior.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Smart Prediction Models for Energy Efficiency in Smart Residential Buildings: A Deep Learning Approach

Smart Prediction Models for Energy Efficiency in Smart Resid...

引用

2023 International Conference for Technological engineering and its Applications in Sustainable Development, ICTEASD 2023

作者： Vasantharaj, A. Ahamed, M. Irshad Prema, K. Mudigonda, Aditya Sapaev, J.B. Thandapani, Kavitha Kalaignar Karunanidhi Institute of Technology Information Electronics and Communication Engineering India E.G.S. Pillay Engineering College Department of Electronics and Communication Engineerin Tamilnadu Nagapattinam India Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Department of Computer Science and Engineering Tamil Nadu Chennai India JNIAS School of Planning and Architecture Telangana Hyderabad500034 India National Research University Tashkent Institute of Irrigation and Agricultural Mechanization Engineers Tashkent Uzbekistan Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Vgy Technology Avadi Department of Electronics and Communication Engineering Tamil Nadu Chennai600062 India

ISBN: (纸本)9798350336474

Using power in houses has given rise to several ecological issues, including air pollution. Predicting building energy use is essential for better regulating or reducing energy usage. Machine Learning (ML) techniques have been used to estimate the power use of operating buildings. However, there has been little research on using ML algorithms to anticipate the prospective energy usage of buildings during the initial design phase. When lowering energy-inefficient buildings, it is crucial to tackle the underlying issue: accurately anticipating energy consumption before construction. This is necessary to prevent the future development of environmentally detrimental buildings. This research introduces a new and innovative Hybrid Deep Learning Model for Predicting Energy Efficiency in Smart Residential Buildings (HDL-PEE-SRB). The suggested framework has two steps: cleaning the information and constructing the model. The information cleansing step utilizes pre-processing methods to manipulate the original information and incorporates lag values as supplementary characteristics. During model-building, the hybrid model undergoes training using the processed data. The HDL model combines fully linked layers, Unidirectional Long Short-Term Memory (Uni-LSTM), and bi-directional LSTMs (Bi-LSTM), which are stacked together. The suggested model is assessed using standard energy usage databases, demonstrating higher accuracy than commonly used HDL models. The proposed model surpasses other HDL models, demonstrating the most favorable performance with a MAPE of 1.94% and an accuracy of 98.06%. © 2023 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Ranked Hunger Games Search Algorithms with Gaussian Distribution-based Fitness Distance Balance Strategy 14

Ranked Hunger Games Search Algorithms with Gaussian Distribu...

引用

14th International Symposium on Computational Intelligence and Design, ISCID 2021

作者： Liu, Yanting Li, Jiayi Yi, Junyan Zhu, Chuan Xu, Zhe Changzhou College of Information Technology Changzhou213032 China University of Toyama Faculty of Engineering Toyama930-8555 Japan Beijing University of Civil Engineering and Architecture Beijing100044 China Changzhou Institute of Technology School of Computer Information Engineering Changzhou213032 China

ISBN: (纸本)9781665438568

Fitness-Distance Balance with Functional Weights (FW) is a new and improved selection method based on Fitness-Distance Balance (FDB). FDB can be used to solve the problem of premature convergence. And FW further improves the performance of FDB selection strategy by changing the weights in FDB from fixed values to randomly generated using distribution functions. Hunger Games Search (HGS) is a meta-heuristic algorithm created inspired by animal hunger behavior. HGS algorithm can get good performance when tested on various problems. But the HGS algorithm still has the problem of premature convergence and easily falls into local search. Therefore, we incorporate the FW selection strategy into the HGS algorithm and propose the FWHGS. and tested on the IEEE CEC2017 benchmark function, which has a great improvement compared to the HGS algorithm. © 2021 IEEE.

关键词： Distribution functions

来源：评论

学校读者我要写书评

暂无评论

Sources of optical radiation based on ZnTe/ZnSe/ZnS heterostructures

引用

Materials Today: Proceedings 2022年 62卷 5763-5766页

作者： Slyotov, Mykhailo Mazur, Tetiana Prokopiv, Volodymyr Slyotov, Oleksii Mazur, Myroslav Department of Optics Physical Publishing and Printing/Technical and Computer Science Institute Yuriy Fedkovych Chernivtsi National University 2 Kotsubinsky Str. Chernivtsi 58012 Ukraine Department of General and Applied Physics/Institute of Architecture Construction and Power Engineering Ivano-Frankisvsk National Technical University of Oil and Gas 15 Karpatska Str. Ivano-Frankivsk 76019 Ukraine Department of Solid State Physics and Chemistry/Faculty of Physics and Technology Vasyl Stefanyk Precarpathian National University 57 Shevchenko Str. Ivano-Frankivsk 76019 Ukraine

The heterostructures of zinc chalcogenides β-ZnTe/ZnSe/ZnS were obtained by isovalent substitution. The regimes for obtaining materials that ensured the stability of the cubic lattice of heterolayers of zinc chalcogenides β-ZnSe and β-ZnS were determined. The isovalent elements Se and S determined the solid-phase substitution and determined the formation of heterolayers in the lattice of the surface of the base crystal. The optical transmission, reflection, and photoluminescence spectra of the heterolayers are studied. The analysis of the results of studies of the energy structure of the obtained heterolayers was carried out, which indicates the correspondence of these heterolayers to the compounds of zinc selenide and zinc sulfide obtained by classical technological processes. They are also confirmed by the results of studies of the optical transmission of β-ZnSe and β-ZnS films specially obtained on transparent substrates under the same growing conditions as compared to isovalent substitution. © 2022

关键词： Light transmission

来源：评论

学校读者我要写书评

暂无评论

HealthyBlockchain for Global Patients

引用

computers, Materials & Continua 2021年第8期68卷 2431-2449页

作者： Shada A.Alsalamah Hessah A.Alsalamah Thamer Nouh Sara A.Alsalamah College of Computer and Information Sciences King Saud UniversityRiyadh11451Saudi Arabia Digital Health and Innovation Science DivisionWorld Health OrganizationGenevaCH-1211Switzerland MIT Department of Mechanical Engineering Massachusetts Institute of Technology(MIT)Cambridge02139MAUSA College of Engineering and Architecture Al Yamamah UniversityRiyadh11451Saudi Arabia Trauma and Acute Care Surgery Unit College of MedicineKing Saud UniversityRiyadh11451Saudi Arabia College of Computer and Information Sciences Al Imam Mohammad Ibn Saud Islamic UniversityRiyadh13318Saudi Arabia

An emerging healthcare delivery model is enabling a new era of clinical care based on well-informed decision-making *** healthcare information systems(HISs)fall short of adopting this model due to a conflict between information security needed to implement the new model and those already enforced locally to support traditional care ***,in recent times,the healthcare sector has shown a substantial interest in the potential of using blockchain technology for providing quality care to *** blockchain solution proposed so far has fully addressed emerging cross-organization information-sharing needs in *** this paper,we aim to study the use of blockchain in equipping struggling HISs to cope with the demands of the new healthcare delivery model,by proposing HealthyBlockchain as a granular patient-centered ledger that digitally tracks a patient’s medical transactions all along the treatment pathway to support the care *** patient-centered ledger is a neutral tamper-proof trail timestamp block sequence that governs distributed patient information across the decentralized discrete *** connects patients,clinicians,and healthcare providers to facilitate a transparent,trustworthy,and secure supporting platform.

关键词： Blockchain eHealth electronic health record global patient healthcare information system information security legacy system patient-centered care privacy smart contract trust

来源：评论

学校读者我要写书评

暂无评论

Designing Microservice Systems Using Patterns: An Empirical Study on Quality Trade-Offs

arXiv

引用

arXiv 2022年

作者： Vale, Guilherme Correia, Filipe Figueiredo Guerra, Eduardo Martins de Oliveira Rosa, Thatiane Fritzsch, Jonas Bogner, Justus Faculty of Engineering University of Porto INESCTEC Porto Portugal Computer Science Faculty Free University of Bozen-Bolzano Alto Adige Bolzano Italy Institute of Mathematics and Statistics University of São Paulo SP São Paulo Brazil Institute of Software Engineering University of Stuttgart Stuttgart Germany

The promise of increased agility, autonomy, scalability, and reusability has made the microservices architecture a de facto standard for the development of large-scale and cloud-native commercial applications. Software patterns are an important design tool, and often they are selected and combined with the goal of obtaining a set of desired quality attributes. However, from a research standpoint, many patterns have not been widely validated against industry practice, making them not much more than interesting theories. To address this, we investigated how practitioners perceive the impact of 14 patterns on 7 quality attributes. Hence, we conducted 9 semi-structured interviews to collect industry expertise regarding (1) knowledge and adoption of software patterns, (2) the perceived architectural trade-offs of patterns, and (3) metrics professionals use to measure quality attributes. We found that many of the trade-offs reported in our study matched the documentation of each respective pattern, and identified several gains and pains which have not yet been reported, leading to novel insight about microservice patterns. Copyright © 2022, The Authors. All rights reserved.

关键词： Reusability

来源：评论

学校读者我要写书评

暂无评论

Enhanced Lung Cancer Detection Using CNNs for Accurate and Efficient CT Image Classification

Enhanced Lung Cancer Detection Using CNNs for Accurate and E...

引用

Computing, Sciences and Communications (ICCSC), International Conference on

作者： Mohammad Bdair E D Kanmani Ruby Prachi Juyal Rakheeba Taseen A. Abirami A Soujanya School of Architecture Computing & Engineering University of East London London UK Department of ECE Vel Tech Rangarajan Dr Sagunthala R&D Institute of Science and Technology Chennai Tamil Nadu India Department of Allied Science (Mathematics) Graphic Era (Deemed to be University) Dehradun Uttarakhand India School of computer science and Engineering Presidency university Bangalore India Department of Mathematics Sona College of Technology Salem Tamil Nadu India Department of Computer Science and Engineering CVR College of Engineering Ibrahimpatnam (M) Telangana India

ISBN: (数字)9798350353648

ISBN: (纸本)9798350353655

Lung cancer must be detected as early as possible, but it may be difficult with existing methods since they often depend on human judgment and outdated image processing. These techniques take a lot of time and are prone to errors, which produces uneven outcomes. The research provides a unique deep learning-based method for classifying lung nodules from CT images using convolutional neural networks (CNNs). By automating feature extraction and categorization, the suggested technique greatly increases diagnostic precision. The result shows superior performance over existing systems is demonstrated by evaluation measures such as AUC-ROC, accuracy, sensitivity, and specificity. With a training duration of 12 hours, an AUC-ROC of 0.95, accuracy of 92%, sensitivity of 94%, specificity of 90%, and inference speed of 0.5 seconds per scan, the results demonstrate notable improvements in diagnostic efficiency and accuracy. Deep learning has the potential to revolutionize the diagnosis of lung cancer and enhance patient care, as demonstrated by the study.

关键词： Training Accuracy Lungs Computed tomography Lung cancer Sensitivity and specificity Feature extraction Data models Stability analysis Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

AdaptiveClick: Clicks-aware Transformer with Adaptive Focal Loss for Interactive Image Segmentation

arXiv

引用

arXiv 2023年

作者： Lin, Jiacheng Chen, Jiajun Yang, Kailun Roitberg, Alina Li, Siyu Li, Zhiyong Li, Shutao The College of Computer Science and Electronic Engineering Hunan University Changsha410082 China The School of Robotics The National Engineering Research Center of Robot Visual Perception and Control Technology Hunan University Changsha410082 China The Institute for Artificial Intelligence The University of Stuttgart Stuttgart70569 Germany The College of Electrical and Information Engineering The Key Laboratory of Visual Perception and Artificial Intelligence of Hunan Province Hunan University Changsha410082 China

Interactive Image Segmentation (IIS) has emerged as a promising technique for decreasing annotation time. Substantial progress has been made in pre- and post-processing for IIS, but the critical issue of interaction ambiguity, notably hindering segmentation quality, has been under-researched. To address this, we introduce ADAPTIVECLICK – a click-aware transformer incorporating an adaptive focal loss that tackles annotation inconsistencies with tools for mask- and pixel-level ambiguity resolution. To the best of our knowledge, AdaptiveClick is the first transformer-based, mask-adaptive segmentation framework for IIS. The key ingredient of our method is the Click-Aware Mask-adaptive transformer Decoder (CAMD), which enhances the interaction between click and image features. Additionally, AdaptiveClick enables pixel-adaptive differentiation of hard and easy samples in the decision space, independent of their varying distributions. This is primarily achieved by optimizing a generalized Adaptive Focal Loss (AFL) with a theoretical guarantee, where two adaptive coefficients control the ratio of gradient values for hard and easy pixels. Our analysis reveals that the commonly used Focal and BCE losses can be considered special cases of the proposed AFL. With a plain ViT backbone, extensive experimental results on nine datasets demonstrate the superiority of AdaptiveClick compared to state-of-the-art methods. The source code is publicly available at https://***/lab206/AdaptiveClick. Copyright © 2023, The Authors. All rights reserved.

关键词： Pixels

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：