Martin O.,Ingenieria de Los Procesos de Fabricacion |
Pereda M.,INSISOC |
Santos J.I.,INSISOC |
Journal of Materials Processing Technology | Year: 2014
Classification and regression tree (CART) and random forest techniques were proposed as pattern recognition tools for classification of ultrasonic oscillograms of resistance spot welding (RSW) joints. The results showed that CART models produced an acceptable error rate with high interpretability. These features may be used to understand and control the decision processes, instruct other human operators, compare margins of safety or modify them depending on the criticality of the industrial process. Compared with CART trees, random forests reduced the error rate at the cost of decreasing decision interpretability. The use of the agreement of the forest was proposed as a measure to reduce the workload of human operators, who would only have to focus on the analysis of ultrasonic oscillograms that are difficult to interpret. © 2014 Elsevier B.V.
Perez Rios J.,INSISOC |
Velasco Jimenez I.,INSISOC
Kybernetes | Year: 2015
Purpose – The purpose of this paper is to expose how organizational cybernetics (OC)-related concepts could be used in combination with information and communication technologies (ICT) to facilitate group discussions on complex issues, and to show its impact in a real case. Design/methodology/approach – A software inspired by OC and team syntegrity concepts has been developed with the aim of helping groups of people to deliberate around complex issues through the internet. Two groups of persons with similar backgrounds were chosen to pursue a deliberation process around the same issue. One had the support of ICT while the other did not. The authors used the same questionnaires with both groups, aimed at getting qualitative and quantitative information about the results obtained in each case. Findings – The results obtained show that the group working with ICT support did produce a better output (quality and quantity) than the group not supported with ICT as well as a higher degree of satisfaction in practically all indicators than the second group. Research limitations/implications – The authors are dealing with only one experiment and therefore cannot make a generalization. It would be desirable to repeat the experiment with various groups and in different contexts. Originality/value – An internet-based software inspired by OC concepts was created to facilitate the first phases (generation and aggregation of ideas) of a deliberation process and the authors measured, in an experiment with two groups of people with similar backgrounds, the impact of using it on the quality and quantity of information produced through the process. © 2015, Emerald Group Publishing Limited.