检索结果-内蒙古大学图书馆

9th International Congress of Physics Engineering

作者： Granados, S.J. Tavera, R.F. Hernández, L.R.T. Cid, R.A. Velázquez, A.J.M. López, G.G. González, R.A.M. Universidad Autónoma Metropolitana Azcapotzalco DCBI CDMX Mexico

Using LabVIEW software, we built a set of images corresponding to cardiac sounds associated to diagnosed cardiac diseases. This constitutes an image database which facilitates phonocardiograms interpretation, also we ... 详细信息

关键词： computer programming languages

来源：评论

学校读者我要写书评

暂无评论

SourceFinder: Finding malware source-code from publicly available repositories

arXiv

引用

arXiv 2020年

作者： Rokon, Md Omar Faruk Islam, Risul Darki, Ahmad Papalexakis, Vagelis E. Faloutsos, Michalis CS UCR

Where can we find malware source code? This question is motivated by a real need: there is a dearth of malware source code, which impedes various types of security research. Our work is driven by the following insight: public archives, like GitHub, have a surprising number of malware repositories. Capitalizing on this opportunity, we propose, SourceFinder, a supervised-learning approach to identify repositories of malware source code efficiently. We evaluate and apply our approach using 97K repositories from GitHub. First, we show that our approach identifies malware repositories with 89% precision and 86% recall using a labeled dataset. Second, we use SourceFinder to identify 7504 malware source code repositories, which arguably constitutes the largest malware source code database. Finally, we study the fundamental properties and trends of the malware repositories and their authors. The number of such repositories appears to be growing by an order of magnitude every 4 years, and 18 malware authors seem to be "professionals" with well-established online reputation. We argue that our approach and our large repository of malware source code can be a catalyst for research studies, which are currently not possible. Copyright © 2020, The Authors. All rights reserved.

关键词： computer programming languages

来源：评论

学校读者我要写书评

暂无评论

Motor temperature based on lora and virtual instrument online monitoring system research 3

Motor temperature based on lora and virtual instrument onlin...

引用

3rd IEEE International Conference on Electronic Information Technology and computer Engineering, EITCE 2019

作者： Jiang, Shuanlei Cheng, Wei-Ming Shanghai University of Engineering Science School of Mechanical and Automotive Engineering Shang Hai China

ISBN: (纸本)9781728135847

Aiming at the problem of short transmission distance and weak anti-interference ability of medium and large-sized motors in temperature monitoring process, this paper presents an online monitoring system of motor temperature based on LoRa wireless communication and virtual instrument. The system converts the data collected by the temperature sensors in real time into a voltage signal that can be processed by the lower computer through the temperature signal conditioning circuit, and the lower computer performs the filter processing and the XOR check processing on a set of voltage signals after analog-digital conversion, and the processed data is packaged and sent to the upper computer through the LoRa module. In the upper computer software LabVIEW, the online monitoring of the temperature parameters of the motors during the running process, data storage and query, temperature compensation, upper threshold alarm and so on. The results show that the motors temperature online monitoring system based on LoRa and virtual instrument has the advantages of high measurement accuracy, strong real-time performance, long transmission distance and strong anti-interference ability. © 2019 IEEE.

关键词： computer programming languages

来源：评论

学校读者我要写书评

暂无评论

IFLBC: On the Edge Intelligence Using Federated Learning Blockchain Network

IFLBC: On the Edge Intelligence Using Federated Learning Blo...

引用

IEEE International Conference on Big Data Security on Cloud (BigDataSecurity), High Performance and Smart Computing (HPSC) and Intelligent Data and Security (IDS)

作者： Ronald Doku Danda B. Rawat EECS Department Howard University Data Science and Cybersecurity Center (DSC2) Washington USA

ISBN: (数字)9781728168739

ISBN: (纸本)9781728168746

Lately there has been an increase in the number of Machine Learning (ML) and Artificial Intelligence (AI) applications ranging from recommendation systems to face to speech recognition. At the helm of the advent of deep learning is the proliferation of data from diverse data sources ranging from Internet-of-Things (IoT) devices to self-driving automobiles. Tapping into this unlimited reservoir of information presents the problem of finding quality data out of a myriad of irrelevant ones, which to this day, has been a significant issue in data science with a direct ramification of this being the inability to generate quality ML models for useful predictive analysis. Edge computing has been deemed a solution to some of issues such as privacy, security, data silos and latency, as it ventures to bring cloud computing services closer to end-nodes. A new form of edge computing known as edge-AI attempts to bring ML, AI, and predictive analytics services closer to the data source (end devices). In this paper, we investigate an approach to bring edge-AI to end-nodes through a shared machine learning model powered by the blockchain technology and a federated learning framework called iFLBC edge. Our approach addresses the issue of the scarcity of relevant data by devising a mechanism known as the Proof of Common Interest (PoCI) to sieve out relevant data from irrelevant ones. The relevant data is trained on a model, which is then aggregated along with other models to generate a shared model that is stored on the blockchain. The aggregated model is downloaded by members of the network which they can utilize for the provision of edge intelligence to end-users. This way, AI can be more ubiquitous as members of the iFLBC network can provide intelligence services to end-users.

关键词： Artificial Intelligence Data sources Intelligence Machine Learning RUDDER Recommender systems computer programming languages Data science Artificial Insemination Speech recognition coboundary End users SCARCITY Proof Legal Services

来源：评论

学校读者我要写书评

暂无评论

SiMul: An Algorithm-Driven Approximate Multiplier Design for Machine Learning

引用

IEEE MICRO 2018年第4期38卷 50-59页

作者： Liu, Zhenhong Yazdanbakhsh, Amir Park, Taejoon Esmaeilzadeh, Hadi Kim, Nam Sung Univ Illinois Dept Elect & Comp Engn Urbana IL 61801 USA Georgia Inst Technol Alternat Comp Technol ACT Lab Atlanta GA 30332 USA Hanyang Univ Dept Robot Engn Seoul South Korea Hanyang Univ Collaborat AI Robot Engn CARE Ctr Seoul South Korea Univ Calif San Diego La Jolla CA 92093 USA

The need to support various machine learning (ML) algorithms on energy-constrained computing devices has steadily grown. In this article, we propose an approximate multiplier, which is a key hardware component in various ML accelerators. Dubbed SiMul, our approximate multiplier features user-controlled precision that exploits the common characteristics of ML algorithms. SiMul supports a tradeoff between compute precision and energy consumption at runtime, reducing the energy consumption of the accelerator while satisfying a desired inference accuracy requirement. Compared improves the energy efficiency of multiplication by 11.6x to 3.2x while achieving 81.7-percent to 98.5-percent precision for individual multiplication operations (96.0-, 97.8-, and 97.7-percent inference accuracy for three distinct applications, respectively, compared to the baseline inference accuracy of 98.3, 99.0, and 97.7 percent using precise multipliers). A neural accelerator implemented with our multiplier can provide 1.7x (up to 2.1x) higher energy efficiency over one implemented with the precise multiplier with a negligible impact on the accuracy of the output for various applications.

关键词： Approximation algorithms Inference algorithms Support vector machines Energy consumption Machine learning algorithms Artificial neural networks Approximate computing energy consumption computer programming languages Artificial neural networks Machine Learning Approximation algorithms Multiplying circuits Inference algorithms Machine learning algorithms Artificial Intelligence Support Vector Network Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

Multivariate Conversion of Moment Magnitude for Small-to-Moderate-Magnitude Earthquakes in Iran

引用

EARTHQUAKE SPECTRA 2018年第1期34卷 313-326页

作者： Kishida, Tadahiro Derakhshan, Sahar Muin, Sifat Darragh, Robert B. Bozorgnia, Yousef Kuehn, Nicolas Kwak, Dong Youp KUSTAR Abu Dhabi U Arab Emirates Univ Calif Berkeley Pacific Earthquake Engn Res Ctr Berkeley CA 94720 USA Univ South Carolina Hazards & Vulnerabil Res Inst Columbia SC USA Univ Calif Los Angeles Dept Civil & Environm Engn Los Angeles CA USA Pacific Engn & Anal El Cerrito CA USA RMS Inc Newark CA USA

Homogeneous estimates of moment magnitude (M) for small-to-moderate-magnitude (SMM) earthquakes are important to assess regional ground motion compared to global models. However, an estimate of M was available for only 6% of the shallow crustal earthquakes in Iran from 1973 to 2013 in the database developed by the Pacific Earthquake Engineering Research Center. Therefore, this study evaluates the existing conversion models, from ML, Ms, and mb, to M, for M > 4.0 using the Iranian data set. Correlations between the residuals of these conversions were computed. A weighted estimate for M is presented that combines these conversion models using these correlations based on multivariate statistics. The conversion to M was improved with smaller standard deviations, especially when ML and mb were both available. The inverse-variance-weighted approach, which is common in practice, underestimates the standard deviations because it neglects the positive correlations between these variables.

关键词： computer programming languages Iran Standard deviation Moment of force MOMENT MAGNITUDE Earthquakes

来源：评论

学校读者我要写书评

暂无评论

Reactivity of Amorphous Carbon Surfaces: Rationalizing the Role of Structural Motifs in Functionalization Using Machine Learning

引用

CHEMISTRY OF MATERIALS 2018年第21期30卷 7446-7455页

作者： Caro, Miguel A. Aarva, Anja Deringer, Volker L. Csanyi, Gabor Laurila, Tomi Aalto Univ Sch Elect Engn Dept Elect Engn & Automat Espoo 02150 Finland Aalto Univ Dept Appl Phys QTF Ctr Excellence Espoo 02150 Finland Univ Cambridge Engn Lab Cambridge CB2 1PZ England Univ Cambridge Dept Chem Cambridge CB2 1EW England

Systematic atomistic studies of surface reactivity for amorphous materials have not been possible in the past because of the complexity of these materials and the lack of the computer power necessary to draw representative statistics. With the emergence and popularization of machine learning (ML) approaches in materials science, systematic (and accurate) studies of the surface chemistry of disordered materials are now coming within reach. In this paper, we show how the reactivity of amorphous carbon (a-C) surfaces can be systematically quantified and understood by a combination of ML interatomic potentials, ML clustering techniques, and density functional theory calculations. This methodology allows us to process large amounts of atomic data to classify carbon atomic motifs on the basis of their geometry and quantify their reactivity toward hydrogen- and oxygen-containing functionalities. For instance, we identify subdivisions of sp and sp2 motifs with markedly different reactivities. We therefore draw a comprehensive, both qualitative and quantitative, picture of the surface chemistry of a-C and its reactivity toward -H, -O, -OH, and -COOH. While this paper focuses on a-C surfaces, the presented methodology opens up a new systematic and general way to study the surface chemistry of amorphous and disordered materials.

关键词： computer programming languages reactivity materials science Machine Learning subdivisions surface chemistry Amorphous carbon amorphous materials

来源：评论

学校读者我要写书评

暂无评论

Langmuir turbulence in horizontal salinity gradient

引用

OCEAN MODELLING 2018年 129卷 93-103页

作者： Fan, Yalin Jarosz, Ewa Yu, Zhitao Rogers, W. Erick Jensen, Tommy G. Liang, Jun-Hong US Naval Res Lab Oceanog Div Stennis Space Ctr MS 39529 USA Louisiana State Univ Baton Rouge LA 70803 USA

Langmuir circulation (LC) is believed to be one of the leading causes of turbulent mixing in the upper ocean. Large eddy simulation (LES) models that solve the Craik-Leibovich equations are used to study LC in the upper ocean, yielding new insights that could not be obtained from field observations or turbulent closure models alone. The present study expands our previous LES modeling investigations of LC to real ocean conditions with large-scale environmental motion due to strong horizontal density gradient, which is introduced to the LES model through scale separation analysis. The model is applied to field observations in the Gulf of Mexico when a measurement site was impacted by fresh water inflow. Model results suggest that LC can enhance turbulence in the water column and deepen the mixed layer (ML) with or without the large scale motions, being consistent with previous studies. The strong salinity gradient is shown to be able to reduce the mean flow in the ML, align Langmuir cells with the pressure gradient direction and inhibit turbulence in the ocean surface boundary layer.

关键词： Turbulent Flow Water column large sizes line controller Gulf of Mexico Average flow Lower Esophageal Sphincter FIELD MONITORING Langmuir circulation computer programming languages Upper ocean Density gradients turbulent mixing SALINITY GRADIENTS

来源：评论

学校读者我要写书评

暂无评论

Machine Learning of Partial Charges Derived from High-Quality Quantum-Mechanical Calculations

引用

JOURNAL OF CHEMICAL INFORMATION AND MODELING 2018年第3期58卷 579-590页

作者： Bleiziffer, Patrick Schaller, Kay Riniker, Sereina Swiss Fed Inst Technol Phys Chem Lab Vladimir Prelog Weg 2 CH-8093 Zurich Switzerland

Parametrization of small organic molecules for classical molecular dynamics simulations is not trivial. The vastness of the chemical space makes approaches using building blocks challenging. The most common approach is therefore an individual parametrization of each compound by deriving partial charges from semiempirical or ab initio calculations and inheriting the bonded and van der Waals (Lennard-Jones) parameters from a (bio)molecular force field. The quality of the partial charges generated in this fashion depends on the level of the quantum-chemical calculation as well as on the extraction procedure used. Here, we present a machine learning (ML) based approach for predicting partial charges extracted from density functional theory (DFT) electron densities. The training set was chosen with the goal to provide a broad coverage of the known chemical space of druglike molecules. In addition to the speed of the approach, the partial charges predicted by ML are not dependent on the three-dimensional conformation in contrast to the ones obtained by fitting to the electrostatic potential (ESP). To assess the quality and compatibility with standard force fields, we performed benchmark calculations for the free energy of hydration and liquid properties such as density and heat of vaporization.

关键词： CHARGES field theory (physics) computer programming languages Free energy latent heat of vaporization Machine Learning Artificial Intelligence Molecular Dynamics Simulation Partial parameterization

来源：评论

学校读者我要写书评

暂无评论

Translational Inelasticity of NO and CO in Scattering from Ultrathin Metallic Films of Ag/Au(111)

引用

JOURNAL OF PHYSICAL CHEMISTRY C 2018年第33期122卷 18942-18948页

作者： Steinsiek, Christoph Shirhattii, Pranav R. Geweke, Jan Lau, Jascha A. Altschaeffel, Jan Kandratsenka, Alexander Bartels, Christof Wodtke, Alec M. Georg August Univ Gottingen Inst Phys Chem Tammannstr 6 D-37077 Gottingen Germany Georg August Univ Gottingen Int Ctr Adv Studies Energy Convers Tammannstr 6 D-37077 Gottingen Germany Max Planck Inst Biophys Chem Dept Dynam Surfaces Fassberg 11 D-37077 Gottingen Germany Tata Inst Fundamental Res 36-P Gopanapally Village Hyderabad 500107 India Ecole Polytech Fed Lausanne Max Planck EPFL Ctr Mol Nanosci & Technol Inst Chem Sci & Engn ISIC Stn 6 CH-1015 Lausanne Switzerland Univ Freiburg Phys Inst Hermann Herder Str 3 D-79104 Freiburg Germany

We investigated translational inelasticity in molecular beam surface scattering of NO and CO from ultrathin metallic films of Ag with atomically defined thicknesses grown on single-crystal Au(111). For both molecules, we observe a gradual decrease of the mean final translational energy for Ag film thicknesses between 0 and 3 ML after which no thickness dependence is seen. For Ag films with thicknesses greater than 3 ML, observations are indistinguishable from those of scattering experiments performed on pure Ag crystal surfaces. The similar behavior of both molecules suggests that translational inelasticity is dominated by the mechanical properties of the surface. Theory predicts a thickness-dependent trend of the phonon spectrum that can qualitatively explain the observed behavior.

关键词： computer programming languages broadcasting Silver Metallic films phonon spectra molecules NOBELIUM ultrathin

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：