Higgs
收藏OpenML2022-06-21 更新2024-05-23 收录
下载链接:
https://www.openml.org/search?type=data&sort=runs&status=active&id=44077
下载链接
链接失效反馈官方服务:
资源简介:
Dataset used in the tabular data benchmark https://github.com/LeoGrin/tabular-benchmark, transformed in the same way. This dataset belongs to the "regression on numerical features" benchmark. Original description:
This is a smaller version of the original dataset, containing 1M rows.
**Author**: Daniel Whiteson, University of California Irvine
**Source**: [UCI](https://archive.ics.uci.edu/ml/datasets/HIGGS)
**Please cite**: Baldi, P., P. Sadowski, and D. Whiteson. Searching for Exotic Particles in High-energy Physics with Deep Learning. Nature Communications 5 (July 2, 2014).
**Higgs Boson detection data**. The data has been produced using Monte Carlo simulations. The first 21 features (columns 2-22) are kinematic properties measured by the particle detectors in the accelerator. The last seven features are functions of the first 21 features; these are high-level features derived by physicists to help discriminate between the two classes. There is an interest in using deep learning methods to obviate the need for physicists to manually develop such features. The last 500,000 examples are used as a test set.
**Note: This is the UCI Higgs dataset, same as version 1, but it fixes the definition of the class attribute, which is categorical, not numeric.**
### Attribute Information
* The first column is the class label (1 for signal, 0 for background)
* 21 low-level features (kinematic properties): lepton pT, lepton eta, lepton phi, missing energy magnitude, missing energy phi, jet 1 pt, jet 1 eta, jet 1 phi, jet 1 b-tag, jet 2 pt, jet 2 eta, jet 2 phi, jet 2 b-tag, jet 3 pt, jet 3 eta, jet 3 phi, jet 3 b-tag, jet 4 pt, jet 4 eta, jet 4 phi, jet 4 b-tag
* 7 high-level features derived by physicists: m_jj, m_jjj, m_lv, m_jlv, m_bb, m_wbb, m_wwbb.
For more detailed information about each feature see the original paper.
Relevant Papers:
Baldi, P., P. Sadowski, and D. Whiteson. Searching for Exotic Particles in High-energy Physics with Deep Learning. Nature Communications 5 (July 2, 2014).
本数据集用于表格数据基准测试(tabular data benchmark),基准仓库地址为https://github.com/LeoGrin/tabular-benchmark,且采用与该基准完全一致的预处理流程。本数据集归属「数值特征回归(regression on numerical features)」基准任务范畴。原始数据集说明如下:
本数据集为原始数据集的精简版本,共计100万条样本行。
**作者**:丹尼尔·怀特森(Daniel Whiteson),加州大学欧文分校
**来源**:[UCI机器学习仓库](https://archive.ics.uci.edu/ml/datasets/HIGGS)
**引用要求**:巴尔迪(P. Baldi)、萨多夫斯基(P. Sadowski)与怀特森(D. Whiteson). 利用深度学习在高能物理中搜寻奇异粒子. 自然通讯, 5(2014年7月2日).
**希格斯玻色子探测数据集**。数据通过蒙特卡洛(Monte Carlo)模拟生成。前21个特征(第2至22列)为加速器粒子探测器测得的运动学特性。最后7个特征为前21个特征的函数;这些是物理学家推导得到的高阶特征,用于辅助区分两类样本。本研究旨在利用深度学习方法,免去物理学家手动构造此类特征的工作。后500,000条样本用作测试集。
**备注**:本数据集即UCI希格斯数据集,与版本1一致,但修正了类别属性的定义——该属性为分类变量,而非数值变量。
### 属性说明
* 第一列为类别标签(1代表信号样本,0代表背景样本)
* 21个低阶特征(运动学特性):轻子横向动量(lepton pT)、轻子赝快度(lepton eta)、轻子方位角(lepton phi)、缺失能量幅值(missing energy magnitude)、缺失能量方位角(missing energy phi)、喷注1横向动量(jet 1 pt)、喷注1赝快度(jet 1 eta)、喷注1方位角(jet 1 phi)、喷注1b标签(jet 1 b-tag)、喷注2横向动量(jet 2 pt)、喷注2赝快度(jet 2 eta)、喷注2方位角(jet 2 phi)、喷注2b标签(jet 2 b-tag)、喷注3横向动量(jet 3 pt)、喷注3赝快度(jet 3 eta)、喷注3方位角(jet 3 phi)、喷注3b标签(jet 3 b-tag)、喷注4横向动量(jet 4 pt)、喷注4赝快度(jet 4 eta)、喷注4方位角(jet 4 phi)、喷注4b标签(jet 4 b-tag)
* 7个由物理学家推导的高阶特征:m_jj、m_jjj、m_lv、m_jlv、m_bb、m_wbb、m_wwbb。
如需了解各特征的详细信息,请参阅原始论文。
相关论文:
巴尔迪(P. Baldi)、萨多夫斯基(P. Sadowski)与怀特森(D. Whiteson). 利用深度学习在高能物理中搜寻奇异粒子. 自然通讯, 5(2014年7月2日).
创建时间:
2022-06-21



