id	author	title	date	pages	extension	mime	words	sentence	flesch	summary	cache	txt
ajst-391	Zhang, Suyu	Comparing SVM with BP to Identify the Young Females' Body Type	2022	5	.pdf	application/pdf	3007	216	66	The comparison between SVM and BP parts structure Success rate in training sample (%) Success rate in testing sample (%) SVM BP SVM BP Flank 5: 3 99.1 97.9 98.5 85.7 Bust 6: 3 99.6 97.6 99.3 92.0 Hip 3: 3 99.4 98.7 99.4 92.0 Abdomen 4: 2 99.7 98.2 98.8 91.9 From Table 2 we can see clearly that the average precisions of training sample are above 99 by using SVM algorithm which also indicates fine prediction. The result, which realizes auto-mapping from body data to specific estimation, has increase accuracy highly by using SVM.	cache/ajst-391.pdf	txt/ajst-391.txt