FACILITATE THE PROCESS OF A HOLONIC MANUFACTURING SYSTEM BASED ON THE WHALE OPTIMIZATION ALGORITHM WITH RANDOM FOREST

SAFA H.  MAHMMOD; JIHAN A. A.  RASOOL

doi:10.26682/sjuod.2023.26.2.38

SAFA H. MAHMMOD Dept. of Computer, College of Science, University of Duhok, Kurdistan region-Iraq
JIHAN A. A. RASOOL Dept. of Computer, College of Science, University of Duhok, Kurdistan region-Iraq

DOI: https://doi.org/10.26682/sjuod.2023.26.2.38

Keywords: Holonic Manufacturing System, Random Forest, Grid Search, Binary Whale Optimization algorithm

Abstract

Current manufacturing systems face considerable challenges due to technological development and customer demand for products that grow nowadays. This growth requires manufacturing systems to improve and adapt their techniques, methods, and strategies. There have been many advancements in holonic control architectures, but there has not been much progress in holonic control methodologies. The optimization and decision-making in the control systems need to adjust to a particular manufacturing system, features of processing technologies, transportation infrastructure, and production environment. Thus, this paper focuses on facilitating and improving the process of decision-making in a holonic manufacturing control unit by applying data mining methods such as data preprocessing and Random Forest (RF). In addition, we used one of the swarm intelligence optimization algorithms for Feature Selection (FS) purposes, the Binary version of the Whale Optimization Algorithm (BWOA). Afterwards, apply the subset generated by feature selection to the random forest classifier and grid search technique to get the best prediction for decision-making purposes. The experiment result for the three datasets was glass identification with 93.2 % accuracy, car evaluation dataset with 98.8 % accuracy, and grape dataset with 100% accuracy. Therefore, combining the grid search technique and random forest followed by feature selection using BWOA yields promising results compared to other algorithms.

Downloads

Download data is not yet available.

References

Derigent, W., Cardin, O., and Trentesaux, D. (2021). "Industry 4.0: contributions of holonic manufacturing control architectures and future challenges", Journal of Intelligent Manufacturing, 32(7), 1797-1818.
Chen, R.-C., et al. (2020). "Selecting critical features for data classification based on machine learning methods." Journal of Big Data 7(1): 52.
Valckenaers, P. (2020). "Perspective on holonic manufacturing systems: PROSA becomes ARTI." Computers in Industry 120: 103226.
Abdel-Basset, M., Abdle-Fatah, L., and Sangaiah, A. K. (2019). "An improved Lévy based whale optimization algorithm for bandwidth-efficient virtual machine placement in cloud computing environment". Cluster Computing, 22, 8319-8334.
Khashman, A. and G. Sadikoglu (2019). Data Coding and Neural Network Arbitration for Feasibility Prediction of Car Marketing. 13th International Conference on Theory and Application of Fuzzy Systems and Soft Computing — ICAFS-2018: 249-255.
Sharawi, M., et al. (2017). Feature selection approach based on whale optimization algorithm. 2017 Ninth international conference on advanced computational intelligence (ICACI), IEEE.
Hussien, A. G., et al. (2017). A binary whale optimization algorithm with hyperbolic tangent fitness function for feature selection. 2017 Eighth international conference on intelligent computing and information systems (ICICIS), IEEE.
Ramanathan, T. T. and D. Sharma (2017). "Multiple classification using svm based multi knowledge based system." Procedia computer science 115: 307-311.
Mirjalili, S., and Lewis, A. (2016). "The whale optimization algorithm", Advances in engineering software, 95, 51-67.
Wang, L., and Haghighi, A. (2016). "Combined strength of holons, agents and function blocks in cyber-physical systems". Journal of manufacturing systems, 40, 25-34.
Zamani, H. and M.-H. Nadimi-Shahraki (2016). "Feature selection based on whale optimization algorithm for diseases diagnosis." International Journal of Computer Science and Information Security 14(9): 1243.
Ahmed, J. A. and A. M. A. Brifcani (2015). "A new internal architecture based on feature selection for holonic manufacturing system." International Journal of Mechanical, Aerospace, Industrial, Mechatronic and Manufacturing Engineering 2(8): 1431.
Kulluk, S., et al. (2012). "Training neural networks with harmony search algorithms for classification problems." Engineering Applications of Artificial Intelligence 25(1): 11-19.
Aldayel, M. S. (2012). K-Nearest Neighbor classification for glass identification problem. 2012 International Conference on Computer Systems and Industrial Informatics, IEEE.
Arora, R. (2012). "Comparative analysis of classification algorithms on different datasets using WEKA." International Journal of Computer Applications 54(13).
Shokouhifar, M. and S. Sabet (2010). A hybrid approach for effective feature selection using neural networks and artificial bee colony optimization. 3rd international conference on machine vision (ICMV 2010).
Giret, A. and V. Botti (2009). "Engineering holonic manufacturing systems." Computers in Industry 60(6): 428-440.
Leitão, P. (2008). Self-organization in manufacturing systems: Challenges and opportunities. 2008 Second IEEE International Conference on Self-Adaptive and Self-Organizing Systems Workshops, IEEE.
Aitkenhead, M. J. (2008). "A co-evolving decision tree classification method." Expert Systems with Applications 34(1): 18-25.
Zhong, P. and M. Fukushima (2007). "Regularized nonsmooth Newton method for multi-class support vector machines." Optimization Methods and Software 22(1): 225-236.
Colombo, A. W., et al. (2006). "An agent-based intelligent control platform for industrial holonic manufacturing systems." IEEE Transactions on Industrial Electronics 53(1): 322-337.
Athitsos, V. and S. Sclaroff (2005). Boosting nearest neighbor classifiers for multiclass recognition. 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05)-Workshops, IEEE.
Jiang, Y. and Z.-H. Zhou (2004). Editing training data for kNN classifiers with neural network ensemble. International symposium on neural networks, Springer.
Leitão, P. (2004). An agile and adaptive holonic architecture for manufacturing control, Instituto Politecnico de Braganca (Portugal).
Krawiec, K. (2002). "Genetic programming-based construction of features for machine learning and knowledge discovery tasks." Genetic Programming and Evolvable Machines 3(4): 329-343.
Wullink, G., et al. (2002). "A system architecture for holonic manufacturing planning and control (EtoPlan)." Robotics and computer-integrated manufacturing 18(3-4): 313-318.
Van Brussel, H., et al. (1998). "Reference architecture for holonic manufacturing systems: PROSA." Computers in Industry 37(3): 255-274.
J. Christensen, (1994). "Holonic Manufacturing Systems: Initial Architecture and Standards Directions", In: Proceedings of First European Conference on Holonic Manufacturing Systems, European HMS Consortium. Hanover; 1994. – P. 1–20.
German, B. (1987). Glass Identification. UCI Machine Learning Repository. https://doi.org/10.24432/C5WW2P.
Bohanec, Marko. (1997). Car Evaluation. UCI Machine Learning Repository. https://doi.org/10.24432/C5JP48.
Aeberhard, Stefan and Forina, M. (1991). Wine. UCI Machine Learning Repository. https://doi.org/10.24432/C5PC7J.