Enhancing IoT Device Classification with Hybrid Stacked Ensembles of Machine Learning Classifiers


  • Ganesh S. Pise Research Scholar Smt. Kashibai Navale College of Engineering Pune 1, Assistant Professor in Pune Institute of Computer Technology Pune
  • Sachin D. Babar Department of Computer Engineering Sinhgad Institute of Technology Lonavala, Research Guide Smt. Kashibai Navale College of Engineering Pune
  • Parikshit N. Mahalle Department of Artificial Intelligent and Data Science, Vishwakarma Institute of Information Technology


IoT Device Classification, Hybrid Stacked Ensembles, Machine Learning Classifiers, Random For, XGBoost, Accuracy Enhancement


Due to the rapid proliferation of Internet of Things (IoT) devices, there have been challenges in their classification. To increase the IoT device classification's precision, here proposed a novel approach that combines the capabilities of several ML classifiers. The model's first development phaseinvolves gathering a well-balanced and diverse dataset that includes various IoT device samples from different sources. The researchers then decided to integrate the learning strategy using an ensemble learning framework. The combination of XGBoost and Random Forest's strengths allowed to perform well with the other ML classifiers. The research focused on optimizing the performance of the classifiers through data preprocessing and engineering. It also utilized cross-validation methods to fine-tune the models. Doing so prevented overfitting and generalized the results. The proposed model was evaluated using a standard benchmark, and its performance was compared with that of modern top-of-the line ensembles and individual classifiers, as well as other state-of-art methods. The results of the comparison revealed that the hybrid-stacked model performed remarkably well at over 93.62% accuracy. To ensure the model's generalizability and practicality, the research utilized a hybrid-stacked ensemble to perform prediction on new data. The MLP classifier was used for this purpose. The findings of the evaluation reinforced the proposed model's accuracy and its potential for practical implementation. The findings of the study revealed that the hybrid structure of the RF and XGBoost, performed well in the classification of various IoT devices. 93.62% accuracy rate indicated the importance of using ensembles in improving the performance of these systems. The study's findings have important implications for various sectors, such as healthcare, smart homes, and industrial automation, where the accuracy of identifying IoT devices is crucial.


Download data is not yet available.


S. Bhattacharya and M. Pandey, “Issues and Challenges in Incorporating the Internet of Things with the Healthcare Sector,” 2021, pp. 639–651.

A. J. Pinheiro, J. de M. Bezerra, C. A. P. Burgardt, and D. R. Campelo, “Identifying IoT devices and events based on packet length from encrypted traffic,” Comput. Commun., vol. 144, no. May, pp. 8–17, 2019, doi: 10.1016/j.comcom.2019.05.012.

B. A. Desai, D. M. Divakaran, I. Nevat, G. W. Peter, and M. Gurusamy, “A feature-ranking framework for IoT device classification,” 2019 11th Int. Conf. Commun. Syst. Networks, COMSNETS 2019, vol. 2061, pp. 64–71, 2019, doi: 10.1109/COMSNETS.2019.8711210.

R. R. Chowdhury and P. E. Abas, “A survey on device fingerprinting approach for resource-constraint IoT devices: Comparative study and research challenges,” Internet of Things (Netherlands), vol. 20, no. October, p. 100632, 2022, doi: 10.1016/j.iot.2022.100632.

O. Salman, I. H. Elhajj, A. Chehab, and A. Kayssi, “A machine learning based framework for IoT device identification and abnormal traffic detection,” Trans. Emerg. Telecommun. Technol., vol. 33, no. 3, pp. 1–15, 2022, doi: 10.1002/ett.3743.

V. Khetani, Y. Gandhi, S. Bhattacharya, S. N. Ajani, and S. Limkar, “INTELLIGENT SYSTEMS AND APPLICATIONS IN ENGINEERING Cross-Domain Analysis of ML and DL : Evaluating their Impact in Diverse Domains,” vol. 11, pp. 253–262, 2023.

I. Cvitić, D. Peraković, M. Periša, and B. Gupta, “Ensemble machine learning approach for classification of IoT devices in smart home,” Int. J. Mach. Learn. Cybern., vol. 12, no. 11, pp. 3179–3202, 2021, doi: 10.1007/s13042-020-01241-0.

W. Li, H. Chu, B. Huang, Y. Huan, L. Zheng, and Z. Zou, “Enabling on-device classification of ECG with compressed learning for health IoT,” Microelectronics J., vol. 115, no. July, p. 105188, 2021, doi: 10.1016/j.mejo.2021.105188.

M. Miettinen, S. Marchal, I. Hafeez, N. Asokan, A. R. Sadeghi, and S. Tarkoma, “IoT SENTINEL: Automated Device-Type Identification for Security Enforcement in IoT,” Proc. - Int. Conf. Distrib. Comput. Syst., pp. 2177–2184, 2017, doi: 10.1109/ICDCS.2017.283.

H. Lee, “Framework and development of fault detection classification using IoT device and cloud environment,” J. Manuf. Syst., vol. 43, pp. 257–270, 2017, doi: 10.1016/j.jmsy.2017.02.007.

Y. Meidan et al., “ProfilIoT: A machine learning approach for IoT device identification based on network traffic analysis,” Proc. ACM Symp. Appl. Comput., vol. Part F1280, pp. 506–509, 2017, doi: 10.1145/3019612.3019878.

G. Vaidya, A. Nambi, T. V. Prabhakar, T. Vasanth Kumar, and S. Sudhakara, “Towards generating a reliable device-specific identifier for IoT devices,” Pervasive Mob. Comput., vol. 76, p. 101445, 2021, doi: 10.1016/j.pmcj.2021.101445.

U. Khalil, A. Ahmad, A. H. Abdel-Aty, M. Elhoseny, M. W. A. El-Soud, and F. Zeshan, “Identification of trusted IoT devices for secure delegation,” Comput. Electr. Eng., vol. 90, no. January, p. 106988, 2021, doi: 10.1016/j.compeleceng.2021.106988.

B. Chakraborty, D. M. Divakaran, I. Nevat, G. W. Peters, and M. Gurusamy, “Cost-Aware Feature Selection for IoT Device Classification,” IEEE Internet Things J., vol. 8, no. 14, pp. 11052–11064, 2021, doi: 10.1109/JIOT.2021.3051480.

L. Fan et al., “EvoIoT: An evolutionary IoT and non-IoT classification model in open environments,” Comput. Networks, vol. 219, no. 30, p. 109450, 2022, doi: 10.1016/j.comnet.2022.109450.

E. S. Babu et al., “Blockchain-based Intrusion Detection System of IoT urban data with device authentication against DDoS attacks,” Comput. Electr. Eng., vol. 103, no. October, p. 108287, 2022, doi: 10.1016/j.compeleceng.2022.108287.

A. Zohourian et al., “IoT Zigbee device security: A comprehensive review,” Internet of Things (Netherlands), vol. 22, no. May, p. 100791, 2023, doi: 10.1016/j.iot.2023.100791.

Sumitra and M. V. Shenoy, “HFedDI: A novel privacy preserving horizontal federated learning based scheme for IoT device identification,” J. Netw. Comput. Appl., vol. 214, no. March, p. 103616, 2023, doi: 10.1016/j.jnca.2023.103616.

AMI, “IOT device identification | Kaggle.” [Online]. Available: https://www.kaggle.com/datasets/fanbyprinciple/iot-device-identification.

P. R. Chandre, P. N. Mahalle, and G. R. Shinde, “Machine Learning Based Novel Approach for Intrusion Detection and Prevention System: A Tool Based Verification,” in 2018 IEEE Global Conference on Wireless Computing and Networking (GCWCN), Nov. 2018, pp. 135–140, doi: 10.1109/GCWCN.2018.8668618.




How to Cite

Pise , G. S. ., Babar, S. D. ., & Mahalle, P. N. . (2023). Enhancing IoT Device Classification with Hybrid Stacked Ensembles of Machine Learning Classifiers. International Journal of Intelligent Systems and Applications in Engineering, 12(4s), 95–105. Retrieved from https://ijisae.org/index.php/IJISAE/article/view/3755



Research Article