Following are relevant references for the features included in Mimer along with practical applications of the platform
Mimer is a decision support system that implements many of the ideas proposed in:
Smedberg, Henrik, and Sunith Bandaru. "Interactive knowledge discovery and knowledge visualization for decision support in multi-objective optimization." European Journal of Operational Research 306, no. 3 (2023): 1311-1329. Available from: https://assar.his.se/mimer/questionnaire.
Mimer has also been evaluated through a user study. The task descriptions and evaluation form for the user study is available here: https://form.jotform.com/231872917458367.
Mimer includes several methods for knowledge discovery
The Flexible Pattern Mining (FPM) procedure offers a way to generate decision rules based on selection made in the solutions. The FPM procedure is detailed in:
Bandaru, Sunith, Amos HC Ng, and Kalyanmoy Deb. "Data mining methods for knowledge discovery in multi-objective optimization: Part B-New developments and applications." Expert Systems with Applications 70 (2017): 119-138. Available from: https://doi.org/10.1016/j.eswa.2016.10.016.
The InfS-P and InfS-R methods for finding important variables related to diversity on the Pareto-front (InfS-P), and convergence towards the Pareto-front (InfS-R) are detailed in:
Smedberg, Henrik, and Sunith Bandaru. "Finding influential variables in multi-objective optimization problems." In 2020 IEEE symposium series on computational intelligence (SSCI), pp. 173-180. IEEE, 2020. Available from: https://doi.org/10.1109/SSCI47803.2020.9308383.
Mimer has been applied for knowledge discovery in several industrial studies.
Mimer was used to gain crucial insights into the solutions generated by considering productivity and ergonomic factors for worker well-being in a real industrial use-case involving welding operations at a station in a production line. Using the knowledge discovery methods in Mimer, the authors found distinct patterns in the setup of the station corresponding to different clusters of solutions.
Iriondo Pascual, Aitor, Henrik Smedberg, Dan Högberg, Anna Syberfeldt, and Dan Lämkull. "Enabling Knowledge Discovery in Multi-Objective Optimizations of Worker Well-Being and Productivity." Sustainability 14, no. 9 (2022): 4894. Available from: https://doi.org/10.3390/su14094894.
Mimer was used for knowledge discovery in two cases of Reconfigurable Manufacturing Systems (RMS). The authors used Mimer to find knowledge pertaining to certain manufacturing tasks in different scenarios of the RMS.
Diaz, Carlos Alberto Barrera, Henrik Smedberg, Sunith Bandaru, and Amos HC Ng. "Enabling Knowledge Discovery from Simulation-Based Multi-Objective Optimization in Reconfigurable Manufacturing Systems." In 2022 Winter Simulation Conference (WSC), pp. 1794-1805. IEEE, 2022. Available from: https://doi.org/10.1109/WSC57314.2022.10015335.
Barrera-Diaz, Carlos Alberto, Amir Nourmohammadi, Henrik Smedberg, Tehseen Aslam, and Amos HC Ng. "An enhanced simulation-based multi-objective optimization approach with knowledge discovery for reconfigurable manufacturing systems." Mathematics 11, no. 6 (2023): 1527. Available from: https://doi.org/10.3390/math11061527.
The knowledge discovered using Mimer has also been used for offline Knowledge-Driven Optimization (KDO), where knowledge from different initial scenarios was used to improve the convergence of new scenarios.
Smedberg, Henrik, Carlos Alberto Barrera-Diaz, Amir Nourmohammadi, Sunith Bandaru, and Amos HC Ng. "Knowledge-Driven Multi-Objective Optimization for Reconfigurable Manufacturing Systems." Mathematical and Computational Applications 27, no. 6 (2022): 106. Available from: https://doi.org/10.3390/mca27060106