首页/论文/physics/0408124

arXiv physics/04081242004-08physics.data-anhep-ex

Boosted决策树作为人工神经网络的替代用于颗粒识别

Boosted Decision Trees as an Alternative to Artificial Neural Networks for Particle Identification

Byron P. Roe, Hai-Jun Yang, Ji Zhu, Yong Liu, Ion Stancu, Gordon McGregor

备注：: 6 pages, 5 figures; Accepted for publication in Nucl. Inst. & Meth. A
发表信息：: Nucl.Instrum.Meth. A543 (2005) 577-584
DOI：: 10.1016/j.nima.2004.12.018

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

摘要英文摘要相关论文

摘要：

使用人工神经网络和提升决策树的粒子识别的功效进行了比较。在MiniBooNE的背景下进行的比较，在费米实验室的实验寻找中微子振荡。基于模拟数据的Monte Carlo样本研究，在MiniBooNE实验中，Boosting算法的粒子识别性能优于人工神经网络。虽然本文中的测试是针对一个实验的，但预计提升算法将在物理学中得到广泛的应用。

英文摘要：

The efficacy of particle identification is compared using artificial neutral networks and boosted decision trees. The comparison is performed in the context of the MiniBooNE, an experiment at Fermilab searching for neutrino oscillations. Based on studies of Monte Carlo samples of simulated data, particle identification with boosting algorithms has better performance than that with artificial neural networks for the MiniBooNE experiment. Although the tests in this paper were for one experiment, it is expected that boosting algorithms will find wide application in physics.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

阅读原文

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

本文内容

摘要英文摘要相关论文

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

继续探索

相关论文

基于Boosted决策树的MiniBooNE颗粒识别方法研究

Studies of Boosted Decision Trees for MiniBooNE Particle Identification

在费米国家加速器实验室（Fermilab）运行的中微子振荡MiniBooNE实验中，将提升决策树应用于粒子识别。许多尝试是为了调整提升决策树，比较各种提升算法的性能，并选择最佳性能的输入变量。

2005-08-08physics.data-an

人工神经网络和Boosted决策树的稳定性和鲁棒性研究

Studies of Stability and Robustness for Artificial Neural Networks and Boosted Decision Trees

在本文中，我们比较了性能，稳定性和鲁棒性的人工神经网络（ANN）和提升决策树（BDT）使用MiniBooNE蒙特卡罗样本。这些方法试图在给定多个识别变量的情况下对事件进行分类。我们在以前的出版物中讨论了BDT算法。本文通过对测试样本的输入变量进行涂抹和移位来进行测试。基于这些研究，BDT具有更好的颗粒识别性能比人工神经网络，通过移动或涂抹测试结果的变量得到的分类的退化是较小的BDT比人工神经网络。

2007-02-08physics.data-an

通过最小化N-隶属度来最大化Boosted Top识别

Maximizing Boosted Top Identification by Minimizing N-subjettiness

N-从属性是一种喷流形状，旨在识别顶夸克等增强强子物体。给定射流内的N个子射流轴，N-子射流度将射流成分到它们最近的子射流轴的角距离相加。在这里，我们推广和改善N-subjettiness最小化所有可能的subjet方向，使用一个新的变种的k-均值聚类算法。在BOOST 2010研讨会的增强顶级基准样本上，我们证明了3-subjettiness与2-subjettiness比率的简单切割产生20%（50%）的标记效率，0.23%（4.1%）的假率，使N-subjettiness成为高效的增强顶级标记器。N-subjettiness可以通过调整角度加权指数进行修改，我们发现，射流加宽措施是首选的提升顶部搜索。我们还探讨了多变量技术，并表明，使用修改后的Fisher判别式，额外的改进是可能的。最后，我们简要地提到我们的最小化过程可以扩展到整个事件，允许事件形状N-jettiness作为一个固定的N锥射流算法。

2011-09-15hep-exhep-phphysics.data-an

基于级联训练的重口味标签的多变量方法

A multivariate approach to heavy flavour tagging with cascade training

本文比较了人工神经网络和提升决策树的性能，有和没有级联训练，在对撞机实验中标记b-喷流。它示出，使用蒙特卡罗模拟的$WH \to lνq\bar{q}$事件，对于50%的B-标记效率，光喷射拒绝功率由提升决策树没有级联训练是约55%高于人工神经网络。级联训练技术可以在此b标记效率水平下分别将提升决策树和人工神经网络的性能提高约35%和80%。我们的结论是级联训练的提升决策树方法是最有前途的技术，在对撞机实验标记重口味。

2007-11-28physics.data-an

用于粒子识别的级联训练技术

Cascade Training Technique for Particle Identification

级联训练技术，这是在我们的工作中开发的MiniBooNE颗粒识别已被发现是一个非常有效的方式来提高选择性能，特别是当非常低的背景污染水平是理想的。在此基于MiniBooNE检测器蒙特卡罗模拟，使用人工神经网络和提升决策树作为示例，给出了该技术的详细描述。

2006-11-27hep-exphysics.data-an

Reweighting with Boosted Decision Trees

Machine learning tools are commonly used in modern high energy physics (HEP) experiments. Different models, such as boosted decision trees (BDT) and artificial neural networks (ANN), are widely used in analyses and even in the software triggers. In most cases, these are classification models used to select the "signal" events from data. Monte Carlo simulated events typically take part in training of these models. While the results of the simulation are expected to be close to real data, in practical cases there is notable disagreement between simulated and observed data. In order to use availa…

2016-08-20hep-exphysics.data-anstat.ML

更多相关论文收起更多论文

使用机器学习在GlueX探测器中进行粒子识别

Particle identification in the GlueX detector with machine learning

本研究利用多层感知器和提升决策树等机器学习算法增强GlueX实验的粒子识别方法，显著提高了在Monte Carlo模拟数据中识别带电和中性粒子的准确性。

2025-09-17hep-exnucl-exphysics.data-an

基于人工神经网络的$b$喷流识别算法在CDF实验中的应用

An artificial neural network based $b$ jet identification algorithm at the CDF Experiment

我们提出了一个新的多元$b$喷流识别算法（“$b$标签”）在CDF实验中使用的费米实验室Tevatron的发展和验证。在对撞机实验中，$b$标记器允许人们区分含有$B$强子的粒子喷流和其他喷流。采用前馈神经网络架构，这个标签是独一无二的，它强调使用来自个人轨道的信息。该标记器不仅包含多变量技术的通常优点，例如最大限度地利用射流中的信息和可调纯度/效率操作点，而且还能够仅用单个跟踪来评估射流。为了证明标记器的有效性，我们采用了一种新的方法，其中我们计算的假标签率和标签效率作为一个较低的阈值在$Z+1$喷气机和$t\bar{t}$候选样本，丰富的光味和$b$喷气机，分别喷气机的神经网络输出值的位置的函数。

2011-10-21hep-exphysics.data-an

Deep Neural Network as an alternative to Boosted Decision Trees for PID

Sapienza Universita di Roma（罗马大学）

In this paper we recreate, and improve, the binary classification method for particles proposed in Roe et al. (2005) paper "Boosted decision trees as an alternative to artificial neural networks for particle identification". Such particles are tau neutrinos, which we will refer to as background, and electronic neutrinos: the signal we are interested in. In the original paper the preferred algorithm is a Boosted decision tree. This is due to its low effort tuning and good overall performance at the time. Our choice for implementation is a deep neural network, faster and more promising in perfor…

2021-04-28cs.LGphysics.comp-phphysics.data-an

在高能物理中基于FPGA的深度提升决策树的纳秒级机器学习回归

Nanosecond machine learning regression with deep boosted decision trees in FPGA for high energy physics

提出基于fwXmachina软件包的深度提升决策树FPGA架构，通过并行决策路径和可变位优化方案，在LHC实验中实现O(10) ns延迟和O(0.1)%资源占用的超快物理量回归估计。

2022-07-12hep-exphysics.data-anphysics.ins-det

光子谱仪PHOS中的人工神经网络直接光子识别

Direct Photon Identification with Artificial Neural Network in the Photon Spectrometer PHOS

在LHC对撞机ALICE实验的PHOS谱仪中，提出了一种区分直接光子和中性π介子背景的神经网络方法。神经网络已被训练来区分不同类别的事件，通过分析的能量轮廓张量的集群在其本征向量坐标系。蒙特卡罗模拟表明，在能量高达120 GeV的范围内，该方法使$π^0$ -介子被错误识别为光子的概率相对于直接光子识别效率降低了一个数量级.

2004-10-29physics.data-anphysics.ins-det

Pattern Recognition Techniques for the Identification of Activities of Daily Living using Mobile Device Accelerometer

This paper focuses on the recognition of Activities of Daily Living (ADL) applying pattern recognition techniques to the data acquired by the accelerometer available in the mobile devices. The recognition of ADL is composed by several stages, including data acquisition, data processing, and artificial intelligence methods. The artificial intelligence methods used are related to pattern recognition, and this study focuses on the use of Artificial Neural Networks (ANN). The data processing includes data cleaning, and the feature extraction techniques to define the inputs for the ANN. Due to the …

2017-10-31cs.CYphysics.data-an

Data Fusion on Motion and Magnetic Sensors embedded on Mobile Devices for the Identification of Activities of Daily Living

Instituto de Telecomunicações, Universidade da Beira Interior（贝拉内政大学电信研究所）；Altranportugal（葡萄牙阿尔特兰公司）；Universidade Lusófona de Humanidades e Tecnologias（卢索福纳人文与科技大学）；Universidad de Alicante（阿利坎特大学）；Università Politecnica delle Marche（马尔凯理工大学）

Several types of sensors have been available in off-the-shelf mobile devices, including motion, magnetic, vision, acoustic, and location sensors. This paper focuses on the fusion of the data acquired from motion and magnetic sensors, i.e., accelerometer, gyroscope and magnetometer sensors, for the recognition of Activities of Daily Living (ADL) using pattern recognition techniques. The system developed in this study includes data acquisition, data processing, data fusion, and artificial intelligence methods. Artificial Neural Networks (ANN) are included in artificial intelligence methods, whic…

2017-10-31cs.CVcs.CYphysics.data-an

A robust solution of a statistical inverse problem in multiscale computational mechanics using an artificial neural network

Univ Gustave Eiffel（古斯塔夫·埃菲尔大学）

This work addresses the inverse identification of apparent elastic properties of random heterogeneous materials using machine learning based on artificial neural networks. The proposed neural network-based identification method requires the construction of a database from which an artificial neural network can be trained to learn the nonlinear relationship between the hyperparameters of a prior stochastic model of the random compliance field and some relevant quantities of interest of an ad hoc multiscale computational model. An initial database made up with input and target data is first gene…

2021-02-11cs.LGeess.SPphysics.class-ph