使用Z-归一化方法对数据进行了归一化，并将其分为两个数据集：一个包含10430个样本的训练集，以及一个包含10437个样本的测试集。

CLASS DISTRIBUTION (training set)
A: 4286
B: 5  
C: 103
D: 352
E: 1095
F: 1961
G: 446
H: 519
I: 831
W: 44
X: 522
Y: 266

Attribute Information:

F1：柱间距离
F2：上边缘
F3：较低的利润率
F4：剥削
F5：行数
F6：模数比
F7：行间间距
F8：重量
F9：峰值数
F10：模比/行间间距
类别：A、B、C、D、E、F、G、H、I、W、X、Y

Relevant Papers:

C. De??Stefano, M. Maniaci, F. Fontanella, A. Scotto??di??Freca,
Reliable writer identification in medieval manuscripts through page layout features: The 'Avila' Bible case, Engineering Applications of Artificial Intelligence, Volume 72, 2018, pp. 99-110.

C. De Stefano, F. Fontanella, M. Maniaci and A. Scotto di Freca, 'A Method for Scribe Distinction in Medieval Manuscripts Using Page Layout Features', Lecture Notes in Computer Science, G. Maino and G. Foresti (eds.), Springer-Verlag, vol. 6978, pp. 393-402.

Citation Request:

C. De??Stefano, M. Maniaci, F. Fontanella, A. Scotto??di??Freca, Reliable writer identification in medieval manuscripts through page layout features: The 'Avila' Bible case, Engineering Applications of Artificial Intelligence, Volume 72, 2018, pp. 99-110.