.png){kind=icon}
返回
Combined Bivariate Performance Measure
.png){kind=icon}
PRE
AI
DOI：10.1109/TIM.2024.3480231.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
The combined bivariate performance measure (CBPM) introduces a novel performance metric for evaluating a system or process that encompasses two conflicting performance measures. While machine learning (ML) research often deals with training time, it is not typically included as a performance metric due to the challenge of simultaneously presenting these conflicting performances. The article proposes a simple but groundbreaking performance measurement framework that reconciles the compromised value of system performance from these two conflicting performances. This framework can be readily adapted for choosing the highest performing systems among the candidates. The CBPM represents the most advanced integrated performance measure, offering a single value for easy comparison across different ML systems.
Keyword:
Market research
Training
Accuracy
Time measurement
Machine learning
Convolutional neural networks
Performance evaluation
Computational modeling
Credit cards
Visualization
Decision support system
machine learning (ML)
performance evaluation
performance measure
期刊
IF:
5.9
论文数:
2.0W
被引数:
5.8W
机构
引用论文
An Enhanced Machine Learning-Based Biometric Authentication System Using RR-Interval Framed Electrocardiograms使用RR间隔帧心电图的基于增强机器学习的生物特征认证系统.png)
IEEE ACCESS
OAAI
IEEE ACCESSIF3.6
OAAI分享收藏Cutting Force Embedded Manifold Learning for Condition Monitoring of Vertical Machining Center用于立式加工中心状态监测的切削力嵌入式流形学习
PREAI
分享收藏A Multiple Classifiers System for Anomaly Detection in Credit Card Data With Unbalanced and Overlapped Classes具有不平衡和重叠课程的信用卡数据异常检测的多分类器系统IEEE ACCESSOAAI
IEEE ACCESSIF3.6
OAAI分享收藏A Machine Learning Framework for Biometric Authentication Using ElectrocardiogramIEEE ACCESSOAAI
IEEE ACCESSIF3.6
OAAI分享收藏Credit Card Fraud Detection Using State-of-the-Art Machine Learning and Deep Learning Algorithms使用最先进的机器学习和深度学习算法进行信用卡欺诈检测IEEE ACCESS
OAAI
IEEE ACCESSIF3.6
OAAI分享收藏
查看更多内容