算法评价指标 - FAR,FRR,ERR (TP/FP/FN/TN)

偏执的太偏执、 2022-08-31 06:50 156阅读 0赞

# TP/FP/FN/TN #

![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L0NoYXJvbm1vbW8_size_16_color_FFFFFF_t_70]

*  **True positive**: having the condition and tested positive with the condition
 *  **False positive**: not having the condition but tested positive with the condition
 *  **True negative**: not having the condition and tested negative with the condition
 *  **False negative**: having the condition but tested negative with the condition

![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L0NoYXJvbm1vbW8_size_16_color_FFFFFF_t_70 1]

*  **Sensitivity (True positive rate, TPR)**: measures the proportion of positives that are correctly identified
 *  **Specificity (True negative rate,TNR)**: measures the proportion of negatives that are correctly identified

![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L0NoYXJvbm1vbW8_size_16_color_FFFFFF_t_70 2]

# FAR, FRR, ERR #

## FAR ##

FAR (False Accept Rate) refers to the possibility that an imposter is accepted by the system incorrectly, which may lead to security breach.

FAR(误接受率)指冒名顶替者被系统错误接受的可能性，这可能导致安全漏洞  
![在这里插入图片描述][e764953528174498bd6fda08d69c2756.png]

## FRR ##

The FRR (False Reject Rate) is the possibility that a legitimate user is rejected by the system when requesting protected resources.

FRR(误拒绝率)是合法用户请求受保护资源时被系统拒绝的可能性。  
![在这里插入图片描述][5bfbd696706045eebd7f3b7a6522e69b.png]

## ERR ##

在理想情况下，FAR和FRR均为零。但是在现实中这是不可能的，因为这两种误差是相互矛盾的，一种误差的减少会导致另一种误差的增加。因此，需要用EER (Equal Error Rate)来评估击键动力学认证系统的整体性能。

ERR是FRR等于FAR时的错误率，可以将FAR和FRR统一为一个参数，更好地代表系统的综合性能。一般来说，ERR越低，识别系统的性能越好。

![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L0NoYXJvbm1vbW8_size_16_color_FFFFFF_t_70 3]

[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L0NoYXJvbm1vbW8_size_16_color_FFFFFF_t_70]: /images/20220829/5a3270ab63e849f0bba94451fb56371b.png
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L0NoYXJvbm1vbW8_size_16_color_FFFFFF_t_70 1]: /images/20220829/e4afd9150f4d47659ce1870029f7f5d9.png
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L0NoYXJvbm1vbW8_size_16_color_FFFFFF_t_70 2]: /images/20220829/4e570557cf074aa482422d67b08ccaf9.png
[e764953528174498bd6fda08d69c2756.png]: /images/20220829/1d29c68e8a334629be099ecd8916c989.png
[5bfbd696706045eebd7f3b7a6522e69b.png]: /images/20220829/be22d8dcc1d64589915a5714dafbe428.png
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L0NoYXJvbm1vbW8_size_16_color_FFFFFF_t_70 3]: /images/20220829/7aedca30eae4458d8a5d9abbd06881f9.png