2026-04-17T08:08:02Zhttps://recercat.cat/oai/request

oai:recercat.cat:2117/4466502026-01-13T04:21:17Zcom_2072_1033col_2072_452950

00925njm 22002777a 4500 dc Karna, Ashutosh author Gibert, Karina author 2024 This study focuses on developing an intelligent decision support system (IDSS) that helps a human operator make data-driven decisions. To put IDSS in production, it is necessary to develop two additional components: one oriented to recognize the cluster of new data and the other a knowledge-based resulting from the interpretation of clusters and further association of actions to each cluster, constituting a knowledge base with the alerts and recommendations associated to every profile. Bootstrap-CURE technique is used to handle the initial component, whereas a meta-clustering framework is suggested for interpreting the clusters and providing recommendations. A detailed strategy is presented for handling a print job, examining patterns, and executing actions through IDSS, thus improving predictive accuracy and operational efficiency. Two distinct machine learning models were developed, one to detect the operational mode and another to choose the best meta-cluster for the type of printing jobs and detained steps are provided for implementing the recommendations. Peer Reviewed Postprint (published version) Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial::Aprenentatge automàtic Clustering 3D printers Pattern discovery Bootstrap clustering Intelligent decision support system From clustering to intelligent decision support system: An application to 3D printing