TY - GEN
T1 - Post-harvest Soybean Meal Loss in Transportation
T2 - 6th International Conference on Intelligent Computing and Optimization, ICO 2023
AU - Wijayanto, Emmanuel Jason
AU - Halim, Siana
AU - Widyadana, I. Gede Agus
N1 - Publisher Copyright:
© 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.
PY - 2023
Y1 - 2023
N2 - A poultry company in Indonesia has a problem, i.e., losing raw material, the so-called Soybean Meal (SBM), during transportation from the port to the factory. To reduce material loss, the company created a raw material transport (RMT) system, which recorded the time and activities during loading-unloading and transporting the material from the port to the factory warehouses. Therefore, this study aims to mine the data on the loss of raw materials through RMT. The application used is Orange data mining to find the relationship between lost material and other attributes, create clusters, and classify the standardized lost. The clustering exhibits two classes, namely, the standard and non-standard conditions. The classification process uses five different algorithms. The random forest algorithm was chosen because it produces the second-best AUC value and can produce a classification visualization through a decision tree. This classification process also produces rules based on the decision tree.
AB - A poultry company in Indonesia has a problem, i.e., losing raw material, the so-called Soybean Meal (SBM), during transportation from the port to the factory. To reduce material loss, the company created a raw material transport (RMT) system, which recorded the time and activities during loading-unloading and transporting the material from the port to the factory warehouses. Therefore, this study aims to mine the data on the loss of raw materials through RMT. The application used is Orange data mining to find the relationship between lost material and other attributes, create clusters, and classify the standardized lost. The clustering exhibits two classes, namely, the standard and non-standard conditions. The classification process uses five different algorithms. The random forest algorithm was chosen because it produces the second-best AUC value and can produce a classification visualization through a decision tree. This classification process also produces rules based on the decision tree.
KW - Classification
KW - Clustering
KW - Data mining
KW - Random forest
UR - http://www.scopus.com/inward/record.url?scp=85180533326&partnerID=8YFLogxK
U2 - 10.1007/978-3-031-50327-6_33
DO - 10.1007/978-3-031-50327-6_33
M3 - Conference contribution
AN - SCOPUS:85180533326
SN - 9783031503269
T3 - Lecture Notes in Networks and Systems
SP - 316
EP - 324
BT - Intelligent Computing and Optimization - Proceedings of the 6th International Conference on Intelligent Computing and Optimization 2023 ICO2023
A2 - Vasant, Pandian
A2 - Shamsul Arefin, Mohammad
A2 - Panchenko, Vladimir
A2 - Thomas, J. Joshua
A2 - Munapo, Elias
A2 - Weber, Gerhard-Wilhelm
A2 - Rodriguez-Aguilar, Roman
PB - Springer Science and Business Media Deutschland GmbH
Y2 - 27 April 2023 through 28 April 2023
ER -