检索结果-内蒙古大学图书馆

Graph Networks as a Universal Machine Learning Framework for Molecules and Crystals

CHEMISTRY OF MATERIALS 2019年第9期31卷 3564-3572页

作者： Chen, Chi Ye, Weike Zuo, Yunxing Zheng, Chen Ong, Shyue Ping Univ Calif San Diego Dept NanoEngn 9500 Gilman DrMail Code 0448 La Jolla CA 92093 USA

Graph networks are a new machine learning (ML) paradigm that supports both relational reasoning and combinatorial generalization. Here, we develop universal MatErials Graph Network (MEGNet) models for accurate property prediction in both molecules and crystals. We demonstrate that the MEGNet models outperform prior ML models such as the SchNet in 11 out of 13 properties of the QM9 molecule data set. Similarly, we show that MEGNet models trained on similar to 60 000 crystals in the Materials Project substantially outperform prior ML models in the prediction of the formation energies, band gaps, and elastic moduli of crystals, achieving better than density functional theory accuracy over a much larger data set. We present two new strategies to address data limitations common in materials science and chemistry. First, we demonstrate a physically intuitive approach to unify four separate molecular MEGNet models for the internal energy at 0 K and room temperature, enthalpy, and Gibbs free energy into a single free energy MEGNet model by incorporating the temperature, pressure, and entropy as global state inputs. Second, we show that the learned element embeddings in MEGNet models encode periodic chemical trends and can be transfer-learned from a property model trained on a larger data set (formation energies) to improve property models with smaller amounts of data (band gaps and elastic moduli).

关键词： Internal energy Elastic Modulus computer programming languages molecules Dataset energy of formation crystals Universal motors materials science Gibbs free energy

来源：评论

学校读者我要写书评

暂无评论

Machine Learning in Seismology: Turning Data into Insights

引用

SEISMOLOGICAL RESEARCH LETTERS 2019年第1期90卷 3-14页

作者： Kong, Qingkai Trugman, Daniel T. Ross, Zachary E. Bianco, Michael J. Meade, Brendan J. Gerstoft, Peter Univ Calif Berkeley Berkeley Seismol Lab 209 McCone Hall Berkeley CA 94720 USA Los Alamos Natl Lab POB 1663 Los Alamos NM 87545 USA CALTECH Seismol Lab Pasadena CA 91125 USA Univ Calif San Diego Scripps Inst Oceanog 9500 Gilman Dr La Jolla CA 92093 USA Harvard Univ Dept Earth & Planetary Sci Cambridge MA 02138 USA

This article provides an overview of current applications of machine learning (ML) in seismology. ML techniques are becoming increasingly widespread in seismology, with applications ranging from identifying unseen signals and patterns to extracting features that might improve our physical understanding. The survey of the applications in seismology presented here serves as a catalyst for further use of ML. Five research areas in seismology are surveyed in which ML classification, regression, clustering algorithms show promise: earthquake detection and phase picking, earthquake early warning (EEW), ground-motion prediction, seismic tomography, and earthquake geodesy. We conclude by discussing the need for a hybrid approach combining data-driven ML with traditional physical modeling.

关键词： computer programming languages Insight seismology Machine Learning MACHINE APPLICATIONS Earthquakes

来源：评论

学校读者我要写书评

暂无评论

Numerical investigations on multi-channel wideband chaotic signal generation by a multi-transverse mode vertical-cavity surface-emitting laser subject to chaotic optical injection

引用

APPLIED OPTICS 2019年第30期58卷 8160-8166页

作者： Yang, Wenyan Xia, Guangqiong Jiang, Zaifu Jayaprasath, Elumalai Hu, Chunxia Wu, Zhengmao Southwest Univ Sch Phys Sci & Technol Chongqing 400715 Peoples R China Chongqing Univ Sci & Technol Sch Phys Chongqing 401331 Peoples R China Chongqing Univ Posts & Telecom Coll Mobile Telecommun Chongqing 401520 Peoples R China

A multi-channel wideband chaotic signal generation scheme is proposed and numerically investigated based on a slave multi-transverse mode vertical-cavity surface-emitting laser (SL) subject to chaotic optical injection from a master multi-transverse mode vertical-cavity surface-emitting laser (ML) with optical feedback. Taking two low-order transverse modes, LP01 and LP11, as an example for numerical calculations, the simulated results show that under suitable optical feedback both the LP01 and LP11 modes (two-channel) of a ML can be driven into the chaotic states where their bandwidths are relatively narrowat a level about 8 GHz. Further injecting the two chaotic signals into a SL, for the case of the globally chaotic optical injection, the SL can output two-channel chaotic signals with wide bandwidths above 20 GHz under appropriate operation parameters. Moreover, the case of SL with mode-selective chaotic optical injection is also analyzed. (C) 2019 Optical Society of America.

关键词： Bandwidth computer programming languages broadband Surface emitting lasers optical OPERATING PARAMETER 2-channel signals SIGNAL GENERATION Optical feedback Injections

来源：评论

学校读者我要写书评

暂无评论

An implementation method for the supervisory control of time-driven systems applied to high-voltage direct current transmission grids

引用

CONTROL ENGINEERING PRACTICE 2019年 82卷 97-107页

作者： Romero-Rodriguez, Miguel Delpoux, Romain Pietrac, Laurent Dai, Jing Benchaib, Abdelkrim Niel, Eric SuperGrid Inst SAS F-69611 Villeurbanne France Univ Lyon CNRS INSA Lyon AMPERE F-69621 Villeurbanne France UPMC Univ Paris 06 Univ Paris Saclay Univ Paris SudSorbonne Univ Grp Elect Engn Paris GeePsUMR CNRS 8507Cent Sup F-91192 Gif Sur Yvette France GE Grid Solut F-91300 Massy France

In recent years, the growth of renewable energy production has encouraged the development of new technologies, such as High-Voltage Direct Current (HVDC) networks, that enhance the integration of such energy sources to power transmission grids. However, this type of technology introduces new challenges in the way power transmission systems are controlled and operated, as faster and more complex control strategies will be needed in a domain which nowadays relies heavily on human decisions. In this context, Discrete Event Systems (DES) modeling and Supervisory Control Theory (SCT) are powerful tools for the development of a supervisory control to be deployed in the grid. This paper presents an application of the SCT to HVDC grids and proposes an implementation method for the resulting supervisors. The proposed method is capable of integrating decentralized and discrete-event controllers that interact with the continuous-time physical system. The language chosen for the implementation is C code, as it can be easily incorporated in power system simulation software, such as EMTP-RV. The method is validated by the simulation of the start-up of a point-to-point link in the EMTP-RV software.

关键词： Discrete event systems Supervisory control theory Control implementation HVDC transmission systems EMTP-RV computer programming languages

来源：评论

学校读者我要写书评

暂无评论

Mechanical properties of molybdenum diselenide revealed by molecular dynamics simulation and support vector machine

引用

PHYSICAL CHEMISTRY CHEMICAL PHYSICS 2019年第18期21卷 9159-9167页

作者： Wang, Xinyu Hong, Yang Wang, Man Xin, Gongming Yue, Yanan Zhang, Jingchao Shandong Univ Inst Thermal Sci & Technol Jinan 250061 Shandong Peoples R China Univ Nebraska Dept Chem Lincoln NE 68588 USA Shandong Univ Sch Energy & Power Engn Jinan 250061 Shandong Peoples R China Wuhan Univ Sch Power & Mech Engn Key Lab Hydraul Machinery Transients MOE Wuhan 430072 Hubei Peoples R China Univ Nebraska Holland Comp Ctr Lincoln NE 68588 USA

Despite the spurring interests in two-dimensional transition metal dichalcogenide (TMDC) materials, knowledge on the mechanical properties of one of their important member, i. e., molybdenum diselenide (MoSe2) is scarce and remains an open topic. In this work, the mechanical properties of h-MoSe2 and t-MoSe2 were systematically investigated using classical molecular dynamics (MD) simulations combined with machine learning (ML) techniques. The effects of chirality, temperature and strain rate on fracture strain, fracture strength and Young's modulus were characterized in both armchair and zigzag directions. For h-MoSe2, the fracture strengths were 13.6 and 13.0 GPa for armchair and zigzag chiralities, respectively, at 1 K and strain rate of 5 x 10(-4) ps(-1);the corresponding fracture strains were 0.23 and 0.27. The Young's moduli in armchair and zigzag directions exhibited similar values of 100.9 and 99.5 GPa, respectively. For t-MoSe2, much lower fracture strengths of 6.1 and 6.3 GPa, fracture strains of 0.13 and 0.15, and Young's moduli of 83.7 and 83.0 GPa were predicted under the same conditions. A total of 700 MD simulation cases were calculated under different impact factors and initial conditions, which were subsequently fed into the support vector machine (SVM) algorithm for ML modeling. After training, the ML model could predict the mechanical properties of both MoSe2 types given only the input features such as chirality, temperature and strain rate.

关键词： strain rate Bone Fracture Molecular Dynamics Simulation computer programming languages ZIGZAG armchairs Elastic Modulus impact factor Mechanical properties Fracture strength STRAIN AT BREAK kinetic simulation Molybdenum cracks Support Vector Network

来源：评论

学校读者我要写书评

暂无评论

Machine learning-resistant pseudo-random number generator

引用

ELECTRONICS LETTERS 2019年第9期55卷 515-+页

作者： Wen, Yiming Yu, Weize Old Dominion Univ Dept Elect & Comp Engn Norfolk VA 23529 USA

Conventional pseudo-random number generator (PRNG) is vulnerable to machine learning (ML) attacks since algorithms are used to generate the random number. Physical unclonable function (PUF) is a kind of hardware security primitive that can also be cracked by ML attacks. However, the main security difference between a regular PRNG and a PUF is that training the output data of a regular PRNG is sufficient to break the PRNG while the challenge-to-response pairs of a PUF must be available for a successful training. In order to design a ML-resistant PRNG, in this Letter, the output data of a regular PRNG is fed into a PUF to generate the encrypted data first. Then the encrypted data is added to the output data of the other regular PRNG to create the output data for the ML-resistant PRNG. Since the input challenge of the PUF is concealed, the adversary is unable to model the PUF with ML techniques. The result shows that the training accuracy of a single output bit of the ML-resistant PRNG is only about 52.6% even if 200,000 data are sampled for training. In contrast, only 50,000 data are adequate to break a regular PRNG if ML attacks are executed.

关键词： computer programming languages Output Regular number generator Pseudorandom number generator

来源：评论

学校读者我要写书评

暂无评论

Planning a teacher staff competence structure robust to unexpected personnel absence

引用

IFAC-PapersOnLine 2019年第13期52卷 2740-2745页

作者： Szwarc, Eryk Bocewicz, Grzegorz Irena-Bach-Dabrowska Dept. of Computer Science and Management Koszalin University of Technology Poland Finance and Management Faculty WSB University of Gdansk al. Grunwaldzka 238A Gdansk80-266 Poland

Teachers' absences are a common disruption to the provision of academic courses. They make it necessary to modify teacher assignment, which amounts to finding suitable substitutions. Sometimes it happens that the competences of the available teachers, with given constraints, e.g. teaching hour limits, are not sufficient to find an admissible assignment modification. Therefore, it is desirable to develop a so-called robust teaching staff competence structure. In the case of teachers' absences, a robust competence structure is a structure that allows one to find a modification of the assignment under every possible scenario of disruption. In other words, the following question is considered: does there exist, and if so, what is the competence structure robust to the disruption caused by an unexpected personnel absence? The number of potential solution variants is related to the number of competences that can be improved. For each variant, there could exist many cases of teacher absence (absence of one teacher, two teachers, etc.). Moreover, for these, there could also exist many assignment modification variants. This an NP-hard problem. In the context of the scale of problems encountered in practice, searching for solutions using well-known algorithms (based on an exhaustive search) is a time-consuming process which does not guarantee that an admissible solution will be found. In the present study, a sufficient condition is proposed, the fulfilment of which guarantees the existence of a non-empty set of admissible solutions. Declarative modelling and computer implementation in the form of constraint logic programming (CLP) have been applied. The potential of the proposed solution is illustrated with examples. © 2019, IFAC (International Federation of Automatic Control) Hosting by Elsevier Ltd. All rights reserved.

关键词： Logic programming computer programming languages NP hard Personnel Robustness (control systems) Academic course computer implementations Constraint Logic programming Declarative modelling Sufficient condition Teacher absence Teacher assignment Teaching staff

来源：评论

学校读者我要写书评

暂无评论

Flowchart-Based Cross-Language Source Code Similarity Detection

引用

SCIENTIFIC programming 2020年第1期2020卷

作者： Zhang, Feng Li, Guofan Liu, Cong Song, Qian Shandong Univ Sci & Technol Coll Comp Sci & Engn Qingdao 266590 Peoples R China Shandong Key Lab Wisdom Mine Informat Technol Qingdao 266590 Peoples R China Shandong Univ Technol Sch Comp Sci & Technol Zibo 255000 Peoples R China

Source code similarity detection has various applications in code plagiarism detection and software intellectual property protection. In computer programming teaching, students may convert the source code written in one programming language into another language for their code assignment submission. Existing similarity measures of source code written in the same language are not applicable for the cross-language code similarity detection because of syntactic differences among different programming languages. Meanwhile, existing cross-language source similarity detection approaches are susceptible to complex code obfuscation techniques, such as replacing equivalent control structure and adding redundant statements. To solve this problem, we propose a cross-language code similarity detection (CLCSD) approach based on code flowcharts. In general, two source code fragments written in different programming languages are transformed into standardized code flowcharts (SCFC), and their similarity is obtained by measuring their corresponding SCFC. More specifically, we first introduce the standardized code flowchart (SCFC) model to be the uniform flowcharts representation of source code written in different languages. SCFC is language-independent, and therefore, it can be used as the intermediate structure for source code similarity detection. Meanwhile, transformation techniques are given to transform source code written in a specific programming language into an SCFC. Second, we propose the SCFC-SPGK algorithm based on the shortest path graph kernel to measure the similarity between two SCFCs. Thus, the similarity between two pieces of source code in different programming languages is given by the similarity between SCFCs. Experimental results show that compared with existing approaches, CLCSD has higher accuracy in cross-language source code similarity detection. Furthermore, CLCSD cannot only handle common source code obfuscation techniques used by students in computer p

关键词： computer programming languages

来源：评论

学校读者我要写书评

暂无评论

Predictive use cases of CNN based multi label classification for programming languages

Predictive use cases of CNN based multi label classification...

引用

International Conference on Computing, Communication, and Intelligent Systems (ICCCIS)

作者： Satyarth Upadhyaya Anish Parajuli Subarna Shakya Department of Electronics and Computer Engineering Institute of Engineering Pulchowk Campus Lalitpur Nepal

ISBN: (纸本)9781728148274

Multi-label classification refers to classifying data into two or more, usually independent, set of output labels. This approach is suitable for deep learning applications in multi-faceted subjects like software development, where it is desirable to yield multiple outcomes. This paper proposes a CNN based deep learning model on public datasets of programming language platforms like GitHub and Stack Overflow to infer intelligence to aid decision making process regarding the choice of programming languages for a given software development requirement. For this research, we've developed a training model with pre-trained vector embedding layer and multi-channel one dimensional CNN layers, followed by Multi Layer Perceptron layer to provide multi label outputs. We have managed to achieve 92%, 98% accuracy and 22%, 4% loss with our two experimental setups for Github and Stack Overflow respectively. The model performed well when tested on software development requirements. Stack Overflow dataset was observed to be noticeably better performing than the Github dataset for actual software development use cases. The implications of these models were also found to be good for trend prediction and source code use cases.

关键词： Natural language processing Multi-label text classification Convolution neural network Word embedding. global vectors computer programming languages Natural Language Processing Software design computer software Dataset decision making process multilayers

来源：评论

学校读者我要写书评

暂无评论

Towards a Formal Specification of Multi-Paradigm Modelling 22

Towards a Formal Specification of Multi-Paradigm Modelling

引用

ACM/IEEE 22nd International Conference on Model Driven Engineering languages and Systems Companion (MODELS-C)

作者： Amrani, Moussa Blouin, Dominique Heinrich, Robert Rensink, Arend Vangheluwe, Hans Wortmann, Andreas Univ Namur NaDI Fac Sci Namur Belgium Inst Polytech Paris Telecom Paris LTCI Paris France KIT Inst Program Struct & Data Org Karlsruhe Germany Univ Twente Formal Methods & Tools Twente Netherlands Univ Antwerp Flanders Make Modelling Simulat & Design Lab Antwerp Belgium Rhein Westfal TH Aachen Software Engn Aachen Germany

ISBN: (纸本)9781728151250

The notion of a programming paradigm is used to classify programming languages and their accompanying workflows based on their salient features. Similarly, the notion of a modelling paradigm can be used to characterise the plethora of modelling approaches used to engineer complex Cyber-Physical Systems (CPS). Modelling paradigms encompass formalisms, abstractions, workflows and supporting tool(chain)s. A precise definition of this modelling paradigm notion is lacking however. Such a definition will increase insight, will allow for formal reasoning about the consistency of modelling frameworks and may serve as the basis for the construction of new modelling, simulation, verification, synthesis, ...environments to support design of CPS. We present a formal framework aimed at capturing the notion of modelling paradigm, as a first step towards a comprehensive formalisation of multi-paradigm modelling. Our formalisation is illustrated by CookieCAD, a simple computer-Aided Design paradigm used in the development of cookie stencils.

关键词： Modeling Formal specifications computer programming languages Workflow Plethora Support Tool First Step

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：