Search | Engineering

Subscribe Submit

Home Journals Focus Achievement Fronts About Us 中文版

Resource Type

Journal Article 958

Year

2023 68

2022 75

2021 62

2020 70

2019 47

2018 41

2017 42

2016 40

2015 49

2014 43

2013 38

2012 40

2011 34

2010 46

2009 44

2008 36

2007 34

2006 26

2005 26

2004 20

open ︾

Keywords

model 15

model test 15

numerical simulation 15

mathematical model 14

kinetic model 10

COVID-19 7

uncertainty 7

Deep learning 6

optimization 6

sensitivity analysis 6

constitutive model 5

China 4

Machine learning 4

development model 4

numerical model 4

sustainable development 4

FEM 3

artificial neural network 3

dynamic model 3

open ︾

Search scope:

排序： Display mode:

Strategies and Principles of Distributed Machine Learning on Big Data Review

Eric P. Xing,Qirong Ho,Pengtao Xie,Dai Wei

Engineering 2016, Volume 2, Issue 2, Pages 179-195 doi: 10.1016/J.ENG.2016.02.008

Abstract:

The rise of big data has led to new demands for machine learning (ML) systems to learn complex models, with millions to billions of parameters, that promise adequate capacity to digest massive datasets and offer powerful predictive analytics (such as high-dimensional latent features, intermediate representations, and decision functions) thereupon. In order to run ML algorithms at such scales, on a distributed cluster with tens to thousands of machines, it is often the case that significant engineering efforts are required—and one might fairly ask whether such engineering truly falls within the domain of ML research. Taking the view that “big” ML systems can benefit greatly from ML-rooted statistical and algorithmic insights—and that ML researchers should therefore not shy away from such systems design—we discuss a series of principles and strategies distilled from our recent efforts on industrial-scale ML solutions. These principles and strategies span a continuum from application, to engineering, and to theoretical research and development of big ML systems and architectures, with the goal of understanding how to make them efficient, generally applicable, and supported with convergence and scaling guarantees. They concern four key questions that traditionally receive little attention in ML research: How can an ML program be distributed over a cluster? How can ML computation be bridged with inter-machine communication? How can such communication be performed? What should be communicated between machines? By exposing underlying statistical and algorithmic characteristics unique to ML programs but not typically seen in traditional computer programs, and by dissecting successful cases to reveal how we have harnessed these principles to design and develop both high-performance distributed ML software as well as general-purpose ML frameworks, we present opportunities for ML researchers and practitioners to further shape and enlarge the area that lies between ML and systems.

Keywords： Machine learning Artificial intelligence big data Big model Distributed systems Principles Theory Data-parallelism Model-parallelism

HTML PDF Collect

Avision of post-exascale programming None

Ji-dong ZHAI, Wen-guang CHEN

Frontiers of Information Technology & Electronic Engineering 2018, Volume 19, Issue 10, Pages 1261-1266 doi: 10.1631/FITEE.1800442

Abstract: we discuss three significant programming challenges for future post-exascale systems: heterogeneity, parallelism

Keywords： Computing model Fault-tolerance Heterogeneous Parallelism Post-exascale

HTML PDF Collect

A survey on design and application of open-channel solid-state drives Review Article

Junchao CHEN, Guangyan ZHANG, Junyu WEI,gyzh@tsinghua.edu.cn

Frontiers of Information Technology & Electronic Engineering 2023, Volume 24, Issue 5, Pages 637-658 doi: 10.1631/FITEE.2200317

Abstract: Compared with traditional solid-state drives (SSDs), open-channel SSDs (OCSSDs) expose their internal physical layout and provide a host-based (FTL) that allows host-side software to control the internal operations such as (GC) and input/output (I/O) scheduling. In this paper, we comprehensively survey research works built on OCSSDs in recent years. We show how they leverage the features of OCSSDs to achieve high throughput, low latency, long lifetime, strong performance isolation, and high resource utilization. We categorize these efforts into five groups based on their optimization methods: adaptive interface customizing, rich FTL co-designing, exploiting, rational I/O scheduling, and efficient GC processing. We discuss the strengths and weaknesses of these efforts and find that almost all these efforts face a dilemma between performance effectiveness and management complexity. We hope that this survey can provide fundamental knowledge to researchers who want to enter this field and further inspire new ideas for the development of OCSSDs.

Keywords： Domain-specific storage Flash translation layer Garbage collection Internal parallelism Open-channel

HTML PDF Collect

Standard model of knowledge representation

Wensheng YIN

Frontiers of Mechanical Engineering 2016, Volume 11, Issue 3, Pages 275-288 doi: 10.1007/s11465-016-0372-3

Abstract: methods include predicate logic, semantic network, computer programming language, database, mathematical modelintrinsic link between various knowledge representation methods, a unified knowledge representation modelAccording to ontology, system theory, and control theory, a standard model of knowledge representationThe model is composed of input, processing, and output.In addition, the standard model of knowledge representation provides a way to solve problems of non-precision

Keywords： knowledge representation standard model ontology system theory control theory multidimensional representation

HTML PDF Collect

State of the Art of Compartment Fire Modeling

Zheng Xin,Yuan Hongyong

Strategic Study of CAE 2004, Volume 6, Issue 3, Pages 68-74

Abstract: The relevant underlying physical assumptions are presented first and the conventional model performance

Keywords： compartment field model zone model network model FZN (field zone and network) model empirical model

HTML PDF Collect

Elevated temperature creep model of parallel wire strands

Frontiers of Structural and Civil Engineering Pages 1060-1071 doi: 10.1007/s11709-023-0981-y

Abstract: analyze their creep behavior, this study experimentally investigated the elevated temperature creep modelThe parameters in the general empirical formula, the Bailey–Norton model, and the composite time-hardeningmodel were fitted based on the experimental results.By evaluating the accuracy and form of the models, the composite time-hardening model, which can simultaneously

Keywords： parallel wire strands experimental study elevated temperature creep model

HTML PDF Collect

Impact of crude distillation unit model accuracy on refinery production planning

Gang FU, Pedro A. Castillo CASTILLO, Vladimir MAHALEC

Frontiers of Engineering Management 2018, Volume 5, Issue 2, Pages 195-201 doi: 10.15302/J-FEM-2017052

Abstract: In this work, we examine the impact of crude distillation unit (CDU) model errors on the results of refinery-wideWe compare the swing cut+ bias CDU model with a recently developed hybrid CDU model (Fu et al., 2016)The hybrid CDU model computes material and energy balances, as well as product true boiling point (TBPCase studies of optimal operation computed using a planning model that is based on the swing cut+ biasCDU model and using a planning model that incorporates the hybrid CDU model are presented.

Keywords： impact of model accuracy on production planning swing cut+ bias CDU model hybrid CDU model refinery feedstock

HTML PDF Collect

Test-driven verification/validation of model transformations

László LENGYEL,Hassan CHARAF

Frontiers of Information Technology & Electronic Engineering 2015, Volume 16, Issue 2, Pages 85-97 doi: 10.1631/FITEE.1400111

Abstract: Why is it important to verify/validate model transformations?Verified/validated model transformations make it possible to ensure certain properties of the generatedFor example, a verified/validated model transformation can ensure the preservation of certain propertiesduring the model-to-model transformation.of a novel test-driven method for verifying/validating model transformations.

Keywords： Graph rewriting based model transformations Verification/validation Test-driven verification

HTML PDF Collect

Digital twin-assisted gearbox dynamic model updating toward fault diagnosis

Frontiers of Mechanical Engineering 2023, Volume 18, Issue 2, doi: 10.1007/s11465-023-0748-0

Abstract: One of the core challenges of intelligent fault diagnosis is that the diagnosis model requires numerousGenerating training data using a virtual model is a potential solution for addressing such a problem,and the construction of a high-fidelity virtual model is fundamental and critical for data generationIn this study, a digital twin-assisted dynamic model updating method for fault diagnosis is thus proposedhelical gearbox; the virtual data generated by this model can be used for gear fault diagnosis.

Keywords： digital twin gearbox model construction model updating physical–virtual interaction

HTML PDF Collect

Estimation of composite load model with aggregate induction motor dynamic load for an isolated hybrid

Nitin Kumar SAXENA,Ashwani Kumar SHARMA

Frontiers in Energy 2015, Volume 9, Issue 4, Pages 472-485 doi: 10.1007/s11708-015-0373-7

Abstract: The composite load is a combination of the static and dynamic load model.To develop this composite load model, the exponential load is used as a static load model and inductionmotors (IMs) are used as a dynamic load model.This aggregate model is used as a dynamic load model.of static load and for the fifth and third order IM dynamic load model using state space model.

Keywords： isolated hybrid power system (IHPS) composite load model static load dynamic load induction motor loadmodel aggregate load

HTML PDF Collect

Initiation of Setaria as a model plant

Xianmin DIAO,James SCHNABLE,Jeffrey L. BENNETZEN,Jiayang LI

Frontiers of Agricultural Science and Engineering 2014, Volume 1, Issue 1, Pages 16-20 doi: 10.15302/J-FASE-2014011

Abstract: Model organisms such as Arabidopsis ( ) and rice ( ) have proven essential for efficient scientific discoverysome important processes such as C photosynthesis are not found in either Arabidopsis or rice, so new modeldomesticated foxtail millet ( ) and its wild ancestor, green foxtail ( ), have recently been proposed as novel modelThis review outlines the development of these species as model organisms, and discusses current challengesand future potential of a Setaria model.

Keywords： Setaria foxtail millet C₄ photosynthesis model organism

HTML PDF Collect

A time−space porosity computational model for concrete under sulfate attack

Frontiers of Structural and Civil Engineering doi: 10.1007/s11709-023-0985-7

Abstract: This study proposes a mechanical–chemical model to simulate the spatiotemporal distribution of the porosityIn addition, the expansion strain at the macro-scale is obtained using a stress analysis model of compositeThe results demonstrate that the expansion strains calculated using the suggested model agree well withThe proposed model can forecast and assess the porosity of concrete covers and provide a credible approach

Keywords： deformation porosity internal expansion stress external sulfate attack mechanical–chemical coupling model

HTML PDF Collect

The Construction of Tetrahedral Model of Engineering Ethical Evaluation

Jin Wang

Frontiers of Engineering Management 2014, Volume 1, Issue 1, Pages 62-70 doi: 10.15302/J-FEM-2014009

Abstract: vividly expose the differences in people's way of understanding which inspires author's study of the modelWith four elements of the project —artifact, engineer, user and environment, a tetrahedral model of integrityIn this model, four "Lamps" — i. e, four elements of engineering — in four corners provide light whilefour "Mirrors" — the result of reflection of four elements — reflect whether the tetrahedral model can

Keywords： tetrahedral model ethical evaluation engineering Lamps and Mirrors

HTML PDF Collect

Four-protein model for predicting prognostic risk of lung cancer

Frontiers of Medicine 2022, Volume 16, Issue 4, Pages 618-626 doi: 10.1007/s11684-021-0867-0

Abstract: combined with CEA, CA125, and CYFRA21-1 were used to construct a recursive partitioning decision tree modelto establish a four-protein diagnostic model and predict the survival of patients with lung cancer.

Keywords： lung cancer HSP90β decision tree model prognosis

HTML PDF Collect

Probabilistic model for vessel-bridge collisions in the Three Gorges Reservoir

Bo GENG , Hong WANG , Junjie WANG ,

Frontiers of Structural and Civil Engineering 2009, Volume 3, Issue 3, Pages 279-285 doi: 10.1007/s11709-009-0044-z

Abstract: over the Yangtze River in the Three Gorges Reservoir, and an analysis of the geometric probabilistic modelvessels in collision probability calculation, the aberrancy angle and vessel velocity probabilistic modelrelated with impact force, a probabilistic model is established and also verified by goodness-of-fitThe vessel transit path distribution can be expressed by the normal distribution model.The aberrancy angle distribution of vessels accepts maximum I distribution model, and its distribution

Keywords： vessel-bridge collision probabilistic model parameter statistics