DOI : https://doi.org/10.18517/ijaseit.15.3.13070

Drift Management in ML-Based IoT Device Classification: A Survey and Evaluation

Quadri Waseem (1), Wan Isni Sofiah Wan Din (2), Towfeeq Fairooz (3), Ahmad Tajudin Baharin (4)
(1) Faculty of Computing, Universiti Malaysia Pahang Al-Sultan Abdullah (UMPSA), Pahang, Malaysia
(2) Faculty of Computing, Universiti Malaysia Pahang Al-Sultan Abdullah (UMPSA), Pahang, Malaysia
(3) School of Computing, Ulster University, Belfast, United Kingdom
(4) Faculty of Computer Science and Information Technology, University Tun Hussien Onn Malaysia, Malaysia
Fulltext View | Download
How to cite (IJASEIT) :
[1]
Q. Waseem, W. I. S. Wan Din, T. Fairooz, and A. T. Baharin, “Drift Management in ML-Based IoT Device Classification: A Survey and Evaluation”, Int. J. Adv. Sci. Eng. Inf. Technol., vol. 15, no. 3, pp. 780–790, Jun. 2025.
Citation Format :
The fast-moving adaptation of the Internet of Things (IoT) and its devices has revolutionized the way we interact with connected systems and perceive the world around us. With the increasing deployment of IoT in various domains such as smart homes, healthcare, industrial automation, and intelligent transportation, ensuring the proper classification and management of IoT devices is essential. Accurate classification plays a crucial role in network management, security enforcement, Quality of Service (QoS), and overall system performance optimization. However, the dynamic nature of IoT environments presents a significant challenge for effective IoT device classification, specifically in the form of drift. Drift occurs when device characteristics and behaviors change over time, making it challenging to maintain accurate classification. This issue is particularly prevalent in applications like smart homes, smart infrastructures, smart cities, and industrial IoT, where diverse and evolving devices contribute to data variability and uncertainty. This survey examines the application of machine learning techniques in mitigating drift in IoT device classification, with a focus on prevention, detection, adaptation, and mitigation strategies. Additionally, we discuss the open challenges and limitations of existing machine learning (ML)-based models used for drift management, as well as future research directions. By analyzing the current landscape of drift management in IoT, this research survey provides valuable insights. It highlights critical gaps that need to be addressed for more robust and efficient IoT classification models.

I. Zhou et al., "Internet of Things 2.0: Concepts, applications, and future directions," IEEE Access, vol. 9, pp. 70961-71012, May 2021, doi: 10.1109/access.2021.3078549.

H. Mehmood et al., "Concept drift adaptation techniques in distributed environment for real-world data streams," Smart Cities, vol. 4, no. 1, pp. 349-371, 2021, doi: 10.3390/smartcities4010021.

L. Yang et al., "CADE: Detecting and explaining concept drift samples for security applications," in Proc. 30th USENIX Secur. Symp. (USENIX Security 21), 2021, pp. 2327-2344.

C. Gundogan et al., "Reliable firmware updates for the information-centric internet of things," in Proc. 8th ACM Conf. Inf.-Centric Netw., 2021, pp. 59-70, doi: 10.1145/3460417.3482974.

H. Tahaei et al., "The rise of traffic classification in IoT networks: A survey," J. Netw. Comput. Appl., vol. 154, 2020, doi:10.1016/j.jnca.2020.102538.

T. S. Sethi and M. Kantardzic, "On the reliable detection of concept drift from streaming unlabeled data," Expert Syst. Appl., vol. 82, pp. 77-99, 2017, doi: 10.1016/j.eswa.2017.04.008.

D. M. V. Sato et al., "A survey on concept drift in process mining," ACM Comput. Surv., vol. 54, no. 9, 2021, doi:10.1145/3472752.

N. F. Idris and M. A. Ismail, "A review of homogenous ensemble methods on the classification of breast cancer data," Przeglad Elektrotechniczny, no. 1, pp. 1-10, 2024, doi: 10.15199/48.2024.01.21.

N. S. Nordin and M. A. Ismail, "A hybridization of butterfly optimization algorithm and harmony search for fuzzy modelling in phishing attack detection," Neural Comput. Appl., vol. 35, no. 7, pp. 5501-5512, 2023, doi: 10.1007/s00521-022-07957-0.

A. Yeshchenko et al., "Comprehensive process drift detection with visual analytics," in Proc. Int. Conf. Conceptual Model., 2019, pp. 119-135, doi: 10.1007/978-3-030-33223-5_11.

N. L. Ab Ghani, I. A. Aziz, and M. Mehat, "Concept drift detection on unlabeled data streams: A systematic literature review," in Proc. IEEE Conf. Big Data Anal. (ICBDA), 2020, pp. 61-65, doi:10.1109/icbda50157.2020.9289802.

F. Bayram, B. S. Ahmed, and A. Kassler, "From concept drift to model degradation: An overview on performance-aware drift detectors," Knowl.-Based Syst., vol. 245, 2022, doi:10.1016/j.knosys.2022.108632.

M. Han et al., "A survey of active and passive concept drift handling methods," Comput. Intell., vol. 38, no. 4, pp. 1492-1535, 2022, doi:10.1111/coin.12520.

A. L. Suarez-Cetrulo, D. Quintana, and A. Cervantes, "A survey on machine learning for recurring concept drifting data streams," Expert Syst. Appl., vol. 213, 2023, doi: 10.1016/j.eswa.2022.118934.

F. Alwahedi et al., "Machine learning techniques for IoT security: Current research and future vision with generative AI and large language models," Internet Things Cyber-Phys. Syst., vol. 5, pp. 1-15, 2024, doi: 10.1016/j.iotcps.2023.12.003.

A. Javed et al., "Machine learning and deep learning approaches in IoT," PeerJ Comput. Sci., vol. 9, 2023, doi: 10.7717/peerj-cs.1204.

Y. Liu et al., "Machine learning for the detection and identification of internet of things devices: A survey," IEEE Internet Things J., vol. 9, no. 1, pp. 298-320, 2021, doi: 10.1109/JIOT.2021.3099028.

H. Jmila et al., "A survey of smart home IoT device classification using machine learning-based network traffic analysis," IEEE Access, vol. 10, pp. 97117-97141, 2022, doi: 10.1109/access.2022.3205023.

N. N. M. Azam et al., "Classification of COVID-19 symptoms using multilayer perceptron," Iraqi J. Comput. Sci. Math., vol. 4, no. 4, pp. 100-110, 2023, doi: 10.52866/ijcsm.2023.04.04.009.

B. M. Alencar et al., "Fog-DeepStream: A new approach combining LSTM and concept drift for data stream analytics on fog computing," Internet Things, vol. 24, 2023, doi:10.1016/j.iot.2023.100731.

A. Pesaranghader, H. L. Viktor, and E. Paquet, "McDiarmid drift detection methods for evolving data streams," in Proc. Int. Joint Conf. Neural Netw. (IJCNN), 2018, pp. 1–9, doi: 10.1109/ijcnn.2018.8489260.

B. H. Schwengber et al., "A method aware of concept drift for online botnet detection," in Proc. IEEE Global Commun. Conf. (GLOBECOM), 2020, pp. 1–6, doi: 10.1109/globecom42002.2020.9347990.

Q. Xiang et al., "Concept drift adaptation methods under the deep learning framework: A literature review," Appl. Sci., vol. 13, no. 11, p. 6515, 2023, doi: 10.3390/app13116515.

G. Xie et al., "A selective transfer learning method for concept drift adaptation," in Adv. Neural Netw. (ISNN), vol. 10262, Springer, 2017, pp. 353–361, doi: 10.1007/978-3-319-59081-3_42.

W. Li et al., "DDG-DA: Data distribution generation for predictable concept drift adaptation," in Proc. AAAI Conf. Artif. Intell., vol. 36, no. 4, 2022, pp. 4092–4100, doi: 10.1609/aaai.v36i4.20327.

H. Yu et al., "Meta-ADD: A meta-learning based pre-trained model for concept drift active detection," Inf. Sci., vol. 608, pp. 996–1009, 2022, doi: 10.1016/j.ins.2022.07.022.

L. Xu et al., "ADTCD: An adaptive anomaly detection approach towards concept drift in IoT," IEEE Internet Things J., early access, 2023, doi: 10.1109/JIOT.2023.3265964.

W. Ding et al., "Trend drift discovery for individual highway drivers through ensemble learning," UMBC Faculty Collection, 2022.

D. M. Manias, A. Chouman, and A. Shami, "A model drift detection and adaptation framework for 5G core networks," in Proc. IEEE Mediterr. Conf. Commun. Netw. (MeditCom), 2022, pp. 197–202, doi: 10.1109/MeditCom55741.2022.9928669.

Q. Hao and Z. Rong, "IoTTFID: An incremental IoT device identification model based on traffic fingerprint," IEEE Access, vol. 11, pp. 58 456–58 468, 2023, doi: 10.1109/access.2023.3284542.

A. Liu et al., "Regional concept drift detection and density synchronized drift adaptation," in Proc. Int. Joint Conf. Artif. Intell. (IJCAI), 2017, pp. 2280–2286, doi: 10.24963/ijcai.2017/317.

R. S. Barros et al., "RDDM: Reactive drift detection method," Expert Syst. Appl., vol. 90, pp. 344–355, 2017, doi: 10.1016/j.eswa.2017.08.023.

S. Marathe et al., "CurrentSense: A novel approach for fault and drift detection in environmental IoT sensors," in Proc. ACM/IEEE Int. Conf. Internet Things Design Implement. (IoTDI), 2021, pp. 93–105, doi: 10.1145/3450268.3453535.

M. Asghari, D. Sierra-Sosa, M. Telahun, A. Kumar, and A. S. Elmaghraby, "Aggregate density-based concept drift identification for dynamic sensor data models," Neural Comput. Appl., vol. 33, pp. 3267–3279, 2021, doi: 10.1007/s00521-020-05190-1.

J. Lu et al., "Learning under concept drift: A review," IEEE Trans. Knowl. Data Eng., vol. 31, no. 12, pp. 2346–2363, Dec. 2019, doi: 10.1109/tkde.2018.2876857.

X. Liu, S. H. Hussein, K. H. Ghazali, T. M. Tung, and Z. M. Yaseen, "Optimized adaptive neuro-fuzzy inference system using metaheuristic algorithms: Application of shield tunneling ground surface settlement prediction," Complexity, vol. 2021, doi: 10.1155/2021/6666699.

F. E. Casado et al., "Concept drift detection and adaptation for federated and continual learning," Multimedia Tools Appl., pp. 1–23, 2022, doi: 10.1007/s11042-022-13843-7.

T. Chow, U. Raza, I. Mavromatis, and A. Khan, "Flare: Detection and mitigation of concept drift for federated learning-based IoT deployments," arXiv, preprint arXiv:2305.08504, 2023. [Online]. Available: https://arxiv.org/abs/2305.08504.

A. Antolini et al., "Combined HW/SW drift and variability mitigation for PCM-based analog in-memory computing for neural network applications," IEEE J. Emerg. Sel. Topics Circuits Syst., vol. 13, no. 1, pp. 395–407, Mar. 2023, doi: 10.1109/jetcas.2023.3241750.

L. Fan et al., "EvoIoT: An evolutionary IoT and non-IoT classification model in open environments," Comput. Netw., vol. 219, Dec. 2022, doi: 10.1016/j.comnet.2022.109450.

L. Yang, D. M. Manias, and A. Shami, "PWPAE: An ensemble framework for concept drift adaptation in IoT data streams," in Proc. IEEE Global Commun. Conf. (GLOBECOM), 2021, pp. 1–6, doi: 10.1109/globecom46510.2021.9685338.

R. Jordaney et al., "Transcend: Detecting concept drift in malware classification models," in Proc. 26th USENIX Secur. Symp. (USENIX Security 17), 2017, pp. 625–642.

I. Mavromatis et al., "LE3D: A lightweight ensemble framework of data drift detectors for resource-constrained devices," in Proc. IEEE 20th Consum. Commun. Netw. Conf. (CCNC), 2023, pp. 611–619, doi: 10.1109/ccnc51644.2023.10060415.

N. Okui, M. Nakahara, Y. Miyake, and A. Kubota, "Identification of an IoT device model in the home domain using IPFIX records," in Proc. IEEE 46th Annu. Comput. Softw. Appl. Conf. (COMPSAC), 2022, pp. 583–592, doi: 10.1109/compsac54236.2022.00104.

A. Chowdhury, S. A. Raut, and H. S. Narman, "DA-DRLS: Drift adaptive deep reinforcement learning-based scheduling for IoT resource management," J. Netw. Comput. Appl., vol. 138, pp. 51–65, 2019, doi: 10.1016/j.jnca.2019.04.010.

Q. Chen et al., "IoTID: Robust IoT device identification based on feature drift adaptation," in Proc. IEEE Global Commun. Conf. (GLOBECOM), 2021, pp. 1–6, doi: 10.1109/globecom46510.2021.9685693.

C.-C. Lin, D.-J. Deng, C.-H. Kuo, and L. Chen, "Concept drift detection and adaptation in big imbalance industrial IoT data using an ensemble learning method of offline classifiers," IEEE Access, vol. 7, pp. 56 198–56 207, 2019, doi: 10.1109/access.2019.2912631.

O. A. Wahab, "Intrusion detection in the IoT under data and concept drifts: Online deep learning approach," IEEE Internet Things J., vol. 9, no. 20, pp. 19 706–19 716, Oct. 2022, doi: 10.1109/jiot.2022.3167005.

L. Yang and A. Shami, "A lightweight concept drift detection and adaptation framework for IoT data streams," IEEE Internet Things Mag., vol. 4, no. 2, pp. 96–101, Jun. 2021, doi: 10.1109/iotm.0001.2100012.

F. Bayram et al., "DA-LSTM: A dynamic drift-adaptive learning framework for interval load forecasting with LSTM networks," Eng. Appl. Artif. Intell., vol. 123, Aug. 2023, doi: 10.1016/j.engappai.2023.106480.

B. Bayram, B. Köroğlu, and M. Gönen, "Improving fraud detection and concept drift adaptation in credit card transactions using incremental gradient boosting trees," in Proc. 19th IEEE Int. Conf. Mach. Learn. Appl. (ICMLA), 2020, pp. 545–550, doi: 10.1109/icmla51294.2020.00091.

M. Jain, G. Kaur, and V. Saxena, "A K-means clustering and SVM based hybrid concept drift detection technique for network anomaly detection," Expert Syst. Appl., vol. 193, May 2022, doi: 10.1016/j.eswa.2022.116510.

M. Stallmann, A. Wilbik, and G. Weiss, "Towards unsupervised sudden data drift detection in federated learning with fuzzy clustering," in Proc. IEEE Int. Conf. Fuzzy Syst. (FUZZ-IEEE), 2024, pp. 1-8, doi:10.1109/fuzz-ieee60900.2024.10611883.

S. Dong, Q. Wang, S. Sahri, T. Palpanas, and D. Srivastava, "Efficiently mitigating the impact of data drift on machine learning pipelines," Proc. VLDB Endow., vol. 17, no. 11, pp. 3072-3081, Jul. 2024, doi: 10.14778/3681954.3681984.

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

Authors who publish with this journal agree to the following terms:

    1. Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
    2. Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
    3. Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).