Jove
Visualize
联系我们
JoVE
x logofacebook logolinkedin logoyoutube logo
关于 JoVE
概览领导团队博客JoVE 帮助中心
作者
出版流程编辑委员会范围与政策同行评审常见问题投稿
图书馆员
用户评价订阅访问资源图书馆顾问委员会常见问题
研究
JoVE JournalMethods CollectionsJoVE Encyclopedia of Experiments存档
教育
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab Manual教师资源中心教师网站
使用条款与条件
隐私政策
政策

相关概念视频

Gas Chromatography: Types of Detectors-I01:21

Gas Chromatography: Types of Detectors-I

426
There are different types of detectors used in gas chromatography, each with its own specific properties that make it suitable for detecting certain types of analytes. The most commonly used detectors in GC are thermal conductivity detector (TCD), flame ionization detector (FID), and electron capture detector (ECD).
TCD is the earliest and most widely used detector that operates by measuring the changes in the thermal conductivity of the carrier gas. When a sample compound enters the detector,...
426

您也可能阅读

相关文章

通过共同作者、期刊和引用图与本文相关的文章。

排序
Same author

The effects of biochar on ryegrass growth and microbial diversity in ionic rare earth tailings soil.

Journal of environmental sciences (China)·2026
Same author

Shikonin inhibits multiple tumor malignant phenotypes and is associated with Hedgehog pathway downregulation in lung adenocarcinoma.

Scientific reports·2025
Same author

Application of <i>Panax ginseng</i> in the Treatment of Chronic Airway Diseases.

The American journal of Chinese medicine·2025
Same author

Black phosphorus nanosheets promote neuronal differentiation of neural stem cells through adhesion and pinocytosis for spinal cord injury repair.

Acta biomaterialia·2025
Same author

Rice B2 and B3 subgroup RAF kinases play central roles in both ABA and osmotic stress signaling.

Cell reports·2025
Same author

Synthesis and evaluation of a Gallium-68 labeled peptide for PET imaging of apoptosis in tumors.

Bioorganic chemistry·2025

相关实验视频

Updated: Jul 1, 2025

Fluorescent Paper Strips for the Detection of Diesel Adulteration with Smartphone Read-out
07:10

Fluorescent Paper Strips for the Detection of Diesel Adulteration with Smartphone Read-out

Published on: November 9, 2018

9.4K

一种用于检测信用卡欺诈问题的新方法.

HaiChao Du1,2,3, Li Lv1,3, Hongliang Wang1,3

  • 1Shenyang Institute of Computing Technology, Chinese Academy of Sciences, Shenyang, China.

PloS one
|March 6, 2024
PubMed
概括

本研究介绍了AE-XGB-SMOTE-CGAN,这是一种用于检测信用卡欺诈的新方法. 它有效地解决了阶级不平衡,提高了欺诈交易的准确性和检测率.

更多相关视频

Using Extraordinary Optical Transmission to Quantify Cardiac Biomarkers in Human Serum
09:23

Using Extraordinary Optical Transmission to Quantify Cardiac Biomarkers in Human Serum

Published on: December 13, 2017

6.3K
A Two-Step Pyrolysis-Gas Chromatography Method with Mass Spectrometric Detection for Identification of Tattoo Ink Ingredients and Counterfeit Products
08:07

A Two-Step Pyrolysis-Gas Chromatography Method with Mass Spectrometric Detection for Identification of Tattoo Ink Ingredients and Counterfeit Products

Published on: May 22, 2019

11.1K

相关实验视频

Last Updated: Jul 1, 2025

Fluorescent Paper Strips for the Detection of Diesel Adulteration with Smartphone Read-out
07:10

Fluorescent Paper Strips for the Detection of Diesel Adulteration with Smartphone Read-out

Published on: November 9, 2018

9.4K
Using Extraordinary Optical Transmission to Quantify Cardiac Biomarkers in Human Serum
09:23

Using Extraordinary Optical Transmission to Quantify Cardiac Biomarkers in Human Serum

Published on: December 13, 2017

6.3K
A Two-Step Pyrolysis-Gas Chromatography Method with Mass Spectrometric Detection for Identification of Tattoo Ink Ingredients and Counterfeit Products
08:07

A Two-Step Pyrolysis-Gas Chromatography Method with Mass Spectrometric Detection for Identification of Tattoo Ink Ingredients and Counterfeit Products

Published on: May 22, 2019

11.1K

科学领域:

  • 机器学习 机器学习
  • 数据科学数据科学数据科学
  • 网络安全 网络安全

背景情况:

  • 信用卡欺诈构成重大财务威胁,每年造成数十亿美元的损失.
  • 由于高度不平衡的数据集,检测欺诈是具有挑战性的,合法交易数量远远超过欺诈性交易.
  • 现有的过量采样技术往往产生不切实际或过度概括的样本,阻碍欺诈检测的有效性.

研究的目的:

  • 提出一种新的混合方法,基于SMOTE和CGAN (AE-XGB-SMOTE-CGAN) 的概率XGBoost的自动编码器,用于增强信用卡欺诈检测.
  • 解决信用卡欺诈数据集中的阶级失衡问题,使用协同的两阶段过量抽样方法.
  • 与现有的机器学习算法相比,提高欺诈检测系统的准确性和可靠性.

主要方法:

  • 使用自动编码器 (AE) 进行特征表示学习,从不平衡的数据集中提取相关模式.
  • 实施混合过量采样策略,结合合成少数人过量采样技术 (SMOTE) 和条件生成对抗网络 (CGAN).
  • 采用XGBoost分类器,用于最终分类欺诈性交易的概率值.

主要成果:

  • 与KNN和LightGBM相比,AE-XGB-SMOTE-CGAN算法在准确度 (ACC) 中显示了2%的改进.
  • 与KNN相比,在0.35值实现了30%高的马修相关系数 (MCC).
  • 该方法显示了增强的真正正和真负率,表明在识别欺诈和合法交易方面表现出色.

结论:

  • AE-XGB-SMOTE-CGAN是一种有前途且有效的信用卡欺诈检测方法,其性能优于传统算法.
  • 混合SMOTE-CGAN方法成功生成了现实的合成数据,减轻了阶级不平衡问题.
  • 拟议的方法为提高金融欺诈检测系统的准确性和可靠性提供了一个强大的解决方案.