Abstract
Industry 4.0 is a new industrial stage based on the revolution brought about by the integration of information and communication technologies (ICT) in conventional manufacturing systems, leading to the implementation of cyber-physical systems. With Industry 4.0 and cyber-physical systems, the number of sensors and thus the data from the monitoring of manufacturing machines is increasing. This implies an opportunity to leverage this data to improve production efficiency. One of these ways is by using it to detect unusual patterns, which can allow, among other things, the detection of machine malfunctions or cutting tool wear. In addition, this information can then be used to better schedule maintenance tasks and make the best possible use of resources. In this chapter, we will study unsupervised clustering techniques and others such as nearest neighbor methods or statistical techniques for anomaly detection that can be applied to machining process monitoring data.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Kibish, S.: A note about finding anomalies [Internet]. Medium. (2018). [Visited 23 May 2023]. Available on https://towardsdatascience.com/a-note-about-finding-anomalies-f9cedee38f0b
Berzal, F.: Partition based clustering. [Visited 23 May 2023]. Available on https://elvex.ugr.es/idbis/dm/slides/41%20Clustering%20-%20Partitional.pdf
Isaac, J.: Cluster jerarquico. (2021). [Visited 23 May 2023]. Available on https://rpubs.com/jaimeisaacp/760355
Bandaru, S., Kalyanmoy, D.: Towards automating the discovery of certain innovative design principles through a clustering-based optimization technique. Eng. Optim. 43, 911–941 (2011). https://doi.org/10.1080/0305215X.2010.528410
Sancho, F.: Self Organizing Maps (SOM) in NetLogo. (2021). [Visited 23 June 2023]. Available on https://www.cs.us.es/~fsancho/?e=136
K-means.: [Visited 13 November 2023]. Available on https://scikit-learn.org/stable/modules/generated/sklearn.cluster.KMeans.html
DATASET.: [Visited 13 November 2023]. Available on https://aseados.ucd.ie/datasets/SDN/
DBSCAN.: [Visited 13 November 2023]. Available on https://www.kaggle.com/code/meetnagadia/dbsc [Visited 13 November 2023]. Available on: an-clustering
SOM.: [Visited 13 November 2023]. Available on https://www.kaggle.com/code/asparago/unsupervised-learning-with-som
Masich, I., Rezova, N., Shkaberina, G., Mironov, S., Bartosh, M., Kazakovtsev, L.: Subgroup discovery in machine learning problems with formal concepts analysis and test theory algorithms. Algorithms 16, 246 (2023). https://doi.org/10.3390/a16050246
Liu, Y., Li, Z., Xiong, H., Gao, X., Wu, J.: Understanding of internal clustering validation measures. In: 2010 IEEE international conference on data mining, Sydney, NSW, Australia, pp. 911–916 (2010). https://doi.org/10.1109/ICDM.2010.35
Kashef, R.: Scattering-based quality measures. In: 2021 IEEE international IOT, electronics and mechatronics conference (IEMTRONICS), Toronto, ON, Canada, pp. 1–8 (2021). https://doi.org/10.1109/IEMTRONICS52119.2021.9422563
Soe, Y.N., Santosa, P.I., Hartanto, R.: DDoS attack detection based on simple ANN with SMOTE for IoT environment. Fourth International Conference on Informatics and Computing (ICIC) 2019, 1–5 (2019)
Joloudari, J.H., Marefat, A., Nematollahi, M.A., Oyelere, S.S., Hussain, S.: Effective class-imbalance learning based on SMOTE and convolutional neural networks. Appl. Sci. 13, 4006 (2023). https://doi.org/10.3390/app13064
DBSCAN.: [Visited 13 November 2023]. Available on https://scikit-learn.org/stable/modules/generated/sklearn.cluster.DBSCAN.html
MiniSOM.: [Visited 13 November 2023]. Available on https://pypi.org/project/MiniSom/
Jan, A., Muhammad Khan, G.: Real world anomalous scene detection and classification using multilayer deep neural networks. Int. J. Interact. Multimed. Artif. Intell. 8(2), 158–167 (2023). https://doi.org/10.9781/ijimai.2021.10.010
Deore, M., Kulkarni, U.: MDFRCNN: Malware detection using faster region proposals convolution neural network. Int. J. Interact. Multimed. Artif. Intell. 7 (4), 146–162 (2022). https://doi.org/10.9781/ijimai.2021.09.005
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this chapter
Cite this chapter
Higuera, J.R.B., Higuera, J.B., Montalvo, J.A.S., Crespo, R.G. (2024). Unsupervised Approaches in Anomaly Detection. In: Nayak, J., Naik, B., S, V., Favorskaya, M. (eds) Machine Learning for Cyber Physical System: Advances and Challenges. Intelligent Systems Reference Library, vol 60. Springer, Cham. https://doi.org/10.1007/978-3-031-54038-7_3
Download citation
DOI: https://doi.org/10.1007/978-3-031-54038-7_3
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-54037-0
Online ISBN: 978-3-031-54038-7
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)