Skripsi
KLASIFIKASI TINGKAT KEKASARAN PERMUKAAN BAJA MENGGUNAKAN REGRESI LOGISTIK MULTINOMIAL DENGAN DISKRITISASI FUZZY
The manufacturing sector largely depends on machining operations, such as milling, which produces workpiece surfaces with a certain degree of roughness. Surface roughness is an important parameter for evaluating the quality of machining results. The purpose of this study is to classify the degree of steel surface roughness using the multinomial logistic regression method. The initial data in this study consists of numerical data comprising nine independent variables, namely cutting speed, feed rate, axial cutting depth, and surface roughness from point 1 to point 6, which were discretised into categorical data based on a combination of fuzzy membership curves (linear increasing, linear decreasing, and beta bell) and one dependent variable in the form of a label. A confusion matrix was used to evaluate the model's performance based on accuracy, precision, recall, specificity, and F1 score values. The multinomial logistic regression model with fuzzy discretisation produced an accuracy value of 88.33%, precision of 40.26%, recall of 41.68%, specificity of 91.27%, and an F1 score of 40.96%. This study concludes that the multinomial logistic regression method is quite effective in classifying the overall surface roughness of steel.
Inventory Code | Barcode | Call Number | Location | Status |
---|---|---|---|---|
2507004684 | T180353 | T1803532025 | Central Library (REFERENS) | Available but not for loan - Not for Loan |
No other version available