Scientific Reports

Table 6 The quantitative indexes on different classifier.

From: Predicting road traffic accident severity from imbalanced data using VAE attention and GCN

Datasets	Methods	Classification indexes
Datasets	Methods	Accuracy	F1-score	Recall	Precision
CHILI	Ours	0.8469	0.8449	0.8469	0.8606
	SVM	0.7566	0.7487	0.7565	0.7563
	KNN	0.8395	0.8378	0.8395	0.8521
	Random Forest	0.8416	0.8416	0.8416	0.8518
	AdaBoost	0.6301	0.5561	0.6308	0.5503
	CNN	0.8204	0.8180	0.82033	0.8286
NEWYORK	Ours	0.8333	0.8399	0.83338	0.8334
	SVM	0.6562	0.6985	0.6563	0.6364
	KNN	0.8408	0.8445	0.8409	0.8420
	Random Forest	0.8459	0.8483	0.8459	0.8469
	AdaBoost	0.7711	0.7666	0.7711	0.7631
	CNN	0.8526	0.8624	0.8526	0.8551
BRONX	Ours	0.7915	0.7993	0.7915	0.7922
	SVM	0.6710	0.7012	0.6710	0.6432
	KNN	0.8023	0.8041	0.8023	0.8027
	Random Forest	0.8192	0.8272	0.8192	0.8217
	AdaBoost	0.7268	0.7391	0.7268	0.7274
	CNN	0.8336	0.8509	0.8336	0.8375

Significant values are in bold.

Back to article page

Search

Advanced search

Quick links