Anomaly classification in IIoT edge devices

Martha Lucía Rodríguez-López; Diana Patricia Tobón-Vallejo; Danny Alexandro Múnera-Ramírez

doi:10.17533/udea.redin.20250368

Autores/as

Martha Lucía Rodríguez-López Universidad de Antioquia https://orcid.org/0000-0001-9718-7673
Diana Patricia Tobón-Vallejo Universidad de Antioquia https://orcid.org/0000-0003-4659-7693
Danny Alexandro Múnera-Ramírez Universidad de Antioquia https://orcid.org/0000-0003-0762-0571

DOI:

https://doi.org/10.17533/udea.redin.20250368

Palabras clave:

Detección de anomalías, clasificación de anomalías, redes neuronales, nternet Industrial de las Cosas

Resumen

Una detección temprana de anomalías en Internet Industrial de las Cosas (IIoT) reduce los costos de mantenimiento, minimiza el tiempo de inactividad de la máquina y aumenta la seguridad de la planta. Un clasificador multiclase que detecta eventos, fallas o ataques libera al operador humano de la responsabilidad de identificar la causa de la anomalía, evitando desperdicio de tiempo que podría comprometer el rendimiento y la seguridad del proceso. Con estas cuestiones en mente, este artículo tiene como objetivo determinar si es posible diferenciar entre una falla de temperatura en un dispositivo IIoT, un ataque de negación de servicio a un broker MQTT y un evento causado por una aplicación que se ejecuta en el dispositivo de borde IIoT. Los datos utilizados para realizar la clasificación provienen de una Raspberry Pi 3, concretamente, datos de su CPU (temperatura, carga, memoria libre, paquetes Wi-Fi enviados y recibidos). Se entrenaron algoritmos del tipo k vecinos más cercanos (KNN), bosque aleatorio (RF), máquina de soporte vectorial (SVM) y un perceptrón multicapa (MLP). Teniendo en cuenta métricas como tasa de falsos positivos, tasa de falsos negativos, precisión, F1-score y el tiempo de ejecución, llegamos a la conclusión de que SVM y MLP fueron los mejores métodos para el caso de estudio, debido a la precisión (78,6 y 76,1, respectivamente) y el bajo tiempo de ejecución (17,3 ms y 0,35 ms).

|Resumen

= 98 veces | PDF (ENGLISH)

= 47 veces|

Descargas

Los datos de descargas todavía no están disponibles.

Biografía del autor/a

Martha Lucía Rodríguez-López, Universidad de Antioquia

Maestra en Ingeniería, Estudiante de Doctorado

Diana Patricia Tobón-Vallejo, Universidad de Antioquia

Doctor, Profesor Facultad de Ingeniería

Danny Alexandro Múnera-Ramírez, Universidad de Antioquia

Doctor, Profesor Facultad de Ingeniería

Citas

S. Alexandra and M. Vitaliy, “Approaches for data collection and process standardization in smart manufacturing: systematic literature review,” Journal of Industrial Information Integration, p. 100578, 2024. [Online]. Available: https://doi.org/10.1016/j.jii.2024.100578

A. Angelopoulos, E. T. Michailidis, N. Nomikos, P. Trakadas, A. Hatziefremidis, S. Voliotis, and T. Zahariadis, “Tackling faults in the industry 4.0 era—a survey of machine-learning solutions and key aspects,” Sensors, vol. 20, no. 1, p. 109, 2019. [Online]. Available: https://doi.org/10.3390/s20010109

M. Rodríguez, D. P. Tobón, and D. Múnera, “Anomaly classification in industrial internet of things: A review,” Intelligent Systems with Applications, p. 200232, 2023. [Online]. Available: https://doi.org/10.1016/j.iswa.2023.200232

C. Ni and S. C. Li, “Machine learning enabled industrial iot security: Challenges, trends and solutions,” Journal of Industrial Information Integration, p. 100549, 2024. [Online]. Available: https://doi.org/10.1016/j.jii.2023.100549

E. Luján, A. Otero, S. Valenzuela, E. Mocskos, L. A. Steffenel, and S. Nesmachnow, “An integrated platform for smart energy management: the cc-sem project,” Revista Facultad de Ingeniería Universidad de Antioquia, no. 97, pp. 41–55, 2020. [Online]. Available: https://www.doi.org/10.17533/udea.redin.20191147

M. Chen, S. Mao, and Y. Liu, “Big data: A survey,” Mobile networks and applications, vol. 19, no. 2, pp. 171–209, 2014. [Online]. Available: https://doi.org/10.1007/s11036-013-0489-0

A. Karkouch, H. Mousannif, H. Al Moatassime, and T. Noel, “Data quality in internet of things: A state-of-the-art survey,” Journal of Network and Computer Applications, vol. 73, pp. 57–81, 2016. [Online]. Available: https://doi.org/10.1016/j.jnca.2016.08.002

N. Ghosh, K. Maity, R. Paul, and S. Maity, “Outlier detection in sensor data using machine learning techniques for iot framework and wireless sensor networks: A brief study,” in 2019 International Conference on Applied Machine Learning (ICAML). IEEE, 2019, pp. 187–190. [Online]. Available: https://doi.org/10.1109/ICAML48257.2019.00043

N. Mohamudally and M. Peermamode-Mohaboob, “Building an anomaly detection engine (ade) for iot smart applications,” Procedia computer science, vol. 134, pp. 10–17, 2018. [Online]. Available: https://doi.org/10.1016/j.procs.2018.07.138

S. Afroz, S. A. Islam, S. N. Rafa, and M. Islam, “A two layer machine learning system for intrusion detection based on random forest and support vector machine,” in 2020 IEEE International Women in Engineering (WIE) Conference on Electrical and Computer Engineering (WIECON-ECE). IEEE, 2020, pp. 300–303. [Online]. Available: https://doi.org/10.1109/WIECON-ECE52138.2020.9397945

N. Moustafa, N. Koroniotis, M. Keshk, A. Y. Zomaya, and Z. Tari, “Explainable intrusion detection for cyber defences in the internet of things: Opportunities and solutions,” IEEE Communications Surveys & Tutorials, 2023. [Online]. Available: https://doi.org/10.1109/COMST.2023.3280465

Y. Wang, M. Perry, D. Whitlock, and J. W. Sutherland, “Detecting anomalies in time series data from a manufacturing system using recurrent neural networks,” Journal of Manufacturing Systems, 2020. [Online]. Available: https://doi.org/10.1016/j.jmsy.2020.12.007

C. EUREKA, G. de Antioquia et al., “Engineering for transformation,” in Expo Ingenieria. Fondo Editorial EIA, 2022. [Online]. Available: https://repositorio.ufps.edu.co/handle/ufps/6516

G. Tertytchny, N. Nicolaou, and M. K. Michael, “Classifying network abnormalities into faults and attacks in iot-based cyber physical systems using machine learning,” Microprocessors and Microsystems, vol. 77, p. 103121, 2020. [Online]. Available: https://doi.org/10.1016/j.micpro.2020.103121

L. E. Contreas-Bravo, N. Nieves-Pimiento, and K. González Guerrero, “Prediction of university-level academic performance through machine learning mechanisms and supervised methods,” Ingeniería, vol. 28, no. 1, 2023. [Online]. Available: https://doi.org/10.14483/23448393.19514

Z.-X. Guo and P.-L. Shui, “Anomaly based sea-surface small target detection using k-nearest neighbor classification,” IEEE Transactions on Aerospace and Electronic Systems, vol. 56, no. 6, pp. 4947–4964, 2020. [Online]. Available: https://doi.org/10.1109/TAES.2020.3011868

S. Rani, K. Tripathi, Y. Arora, and A. Kumar, “Analysis of anomaly detection of malware using knn,” in 2022 2nd International Conference on Innovative Practices in Technology and Management (ICIPTM), vol. 2. IEEE, 2022, pp. 774–779. [Online]. Available: https://doi.org/10.1109/ICIPTM54933.2022.9754044

A. Abid, A. Kachouri, A. B. F. Guiloufi, A. Mahfoudhi, N. Nasri, and M. Abid, “Centralized knn anomaly detector for wsn,” in 2015 IEEE 12th International Multi-Conference on Systems, Signals & Devices (SSD15). IEEE, 2015, pp. 1–4. [Online]. Available: https://doi.org/10.1109/SSD.2015.7348091

P. Naraei, A. Abhari, and A. Sadeghian, “Application of multilayer perceptron neural networks and support vector machines in classification of healthcare data,” in 2016 Future Technologies Conference (FTC). IEEE, 2016, pp. 848–852. [Online]. Available: https://doi.org/10.1109/FTC.2016.7821702

S. Shakya and S. Sigdel, “An approach to develop a hybrid algorithm based on support vector machine and naive bayes for anomaly detection,” in 2017 International Conference on Computing, Communication and Automation (ICCCA). IEEE, 2017, pp. 323–327. [Online]. Available: https://doi.org/10.1109/CCAA.2017.8229836

S. A. Arenas-Hoyos and Á. Bernal-Noreña, “Support vector machines implementation over integers modulo-m and residue number system,” Dyna, vol. 90, no. 226, pp. 17–26, 2023. [Online]. Available: https://doi.org/10.15446/dyna.v90n226.107112

Scikit-Learn, “sklearn.svm.SVC,” Scikit Learn, 2022, Online; accessed 10-August-2022. [Online]. Available: https://scikit-learn.org/stable/mod

T.-H. Lin and J.-R. Jiang, “Anomaly detection with autoencoder and random forest,” in 2020 International Computer Symposium (ICS). IEEE, 2020, pp. 96–99. [Online]. Available: https://doi.org/10.1109/ICS51289.2020.00028

K. Bhuva, K. Srivastava et al., “Comparative study of the machine learning techniques for predicting the employee attrition,” IJRAR-International Journal of Research and Analytical Reviews (IJRAR), vol. 5, no. 3, pp. 568–577, 2018.

R. Porteiro, L. Hernández-Callejo, and S. Nesmachnow, “Electricity demand forecasting in industrial and residential facilities using ensemble machine learning,” Revista Facultad de Ingeniería Universidad de Antioquia, no. 102, pp. 9–25, 2022. [Online]. Available: https://www.doi.org/10.17533/udea.redin.20200584

Y.-C. Lai, K.-Z. Zhou, S.-R. Lin, and N.-W. Lo, “F1ow-based anomaly detection using multilayer perceptron in software defined networks,” in 2019 42nd International Convention on Information and Communication Technology, Electronics and Microelectronics (MIPRO). IEEE, 2019, pp. 1154–1158. [Online]. Available: https://doi.org/10.23919/MIPRO.2019.8757199

H. Zhang, S. Shen, and Y. Shen, “Power system transient stability evaluation based on multilayer perceptron neural network,” in 2021 China Automation Congress (CAC). IEEE, 2021, pp. 3313–3316. [Online]. Available: https://doi.org/10.1109/CAC53003.2021.9727444 [28] T. Huuhtanen and A. Jung, “Anomaly location detection with electrical impedance tomography using multilayer perceptrons,” in 2020 IEEE 30th International Workshop on Machine Learning for Signal Processing (MLSP). IEEE, 2020, pp. 1–6. [Online]. Available: https://doi.org/10.1109/MLSP49062.2020.9231818

L. Van Efferen and A. M. Ali-Eldin, “A multi-layer perceptron approach for flow-based anomaly detection,” in 2017 international symposium on networks, computers and communications (ISNCC). IEEE, 2017, pp. 1–6. [Online]. Available: https://doi.org/10.1109/ISNCC.2017.8072036

S. Ranjeeth, V. A. K. Kandimalla et al., “Predicting diabetes using outlier detection and multilayer perceptron with optimal stochastic gradient descent,” in 2020 IEEE India Council International Subsections Conference (INDISCON). IEEE, 2020, pp. 51–56. [Online]. Available: https://doi.org/10.1109/INDISCON50162.2020.00023

X.-J. Shen, Y. Dong, J.-P. Gou, Y.-Z. Zhan, and J. Fan, “Least squares kernel ensemble regression in reproducing kernel hilbert space,” Neurocomputing, vol. 311, pp. 235–244, 2018. [Online]. Available: https://doi.org/10.1016/j.neucom.2018.05.065

B. B. Hazarika, D. Gupta, and P. Borah, “An intuitionistic fuzzy kernel ridge regression classifier for binary classification,” Applied Soft Computing, vol. 112, p. 107816, 2021. [Online]. Available: https://doi.org/10.1016/j.asoc.2021.107816

S. Akila and U. S. Reddy, “Credit card fraud detection using non-overlapped risk based bagging ensemble (nrbe),” in 2017 IEEE international conference on computational intelligence and computing research (ICCIC). IEEE, 2017, pp. 1–4. [Online]. Available: https://doi.org/10.1109/ICCIC.2017.8524418

Y. Zahid, M. A. Tahir, and M. N. Durrani, “Ensemble learning using bagging and inception-v3 for anomaly detection in surveillance videos,” in 2020 IEEE International Conference on Image Processing (ICIP). IEEE, 2020, pp. 588–592. [Online]. Available: https://doi.org/10.1109/ICIP40778.2020.9190673

X. Berger, “RPi-Monitor,” RPi-Monitor, 2018, [Online; accessed 10-August-2022]. [Online]. Available: https://xavierberger.github.io/RPi-Monitor-docs/index.html