PWPAE: An Ensemble Framework for Concept Drift Adaptation in IoT Data Streams

As the number of Internet of Things (IoT) devices and systems have surged, IoT data analytics techniques have been developed to detect malicious cyber-attacks and secure IoT systems; however, concept drift issues often occur in IoT data analytics, as IoT data is often dynamic data streams that change over time, causing model degradation and attack detection failure. This is because traditional data analytics models are static models that cannot adapt to data distribution changes. In this paper, we propose a Performance Weighted Probability Averaging Ensemble (PWPAE) framework for drift adaptive IoT anomaly detection through IoT data stream analytics. Experiments on two public datasets show the effectiveness of our proposed PWPAE method compared against state-of-the-art methods.

[1]  Ibrar Yaqoob,et al.  Big IoT Data Analytics: Architecture, Opportunities, and Open Research Challenges , 2017, IEEE Access.

[2]  Heitor Murilo Gomes,et al.  Streaming Random Patches for Evolving Data Stream Classification , 2019, 2019 IEEE International Conference on Data Mining (ICDM).

[3]  Abdallah Shami,et al.  Distance-Based Anomaly Detection for Industrial Surfaces Using Triplet Networks , 2020, 2020 11th IEEE Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON).

[4]  Hanan Lutfiyya,et al.  DNS Typo-Squatting Domain Detection: A Data Analytics & Machine Learning Based Approach , 2018, 2018 IEEE Global Communications Conference (GLOBECOM).

[5]  Abdallah Shami,et al.  MTH-IDS: A Multitiered Hybrid Intrusion Detection System for Internet of Vehicles , 2021, IEEE Internet of Things Journal.

[6]  Geoffrey I. Webb,et al.  Extremely Fast Decision Tree , 2018, KDD.

[7]  Ali A. Ghorbani,et al.  Toward Generating a New Intrusion Detection Dataset and Intrusion Traffic Characterization , 2018, ICISSP.

[8]  Abdallah Shami,et al.  Making a Case for Federated Learning in the Internet of Vehicles and Intelligent Transportation Systems , 2021, IEEE Network.

[9]  Abdallah Moubayed,et al.  Clustering Enabled Classification using Ensemble Feature Selection for Intrusion Detection , 2019, 2019 International Conference on Computing, Networking and Communications (ICNC).

[10]  Qusay H. Mahmoud,et al.  A Scheme for Generating a Dataset for Anomalous Activity Detection in IoT Networks , 2020, Canadian Conference on AI.

[11]  Hyunbum Kim,et al.  CONTVERB: Continuous Virtual Emotion Recognition Using Replaceable Barriers for Intelligent Emotion-Based IoT Services and Applications , 2020, IEEE Network.

[12]  Guangquan Zhang,et al.  Learning under Concept Drift: A Review , 2019, IEEE Transactions on Knowledge and Data Engineering.

[13]  Abdallah Shami,et al.  Detecting Botnet Attacks in IoT Environments: An Optimized Machine Learning Approach , 2020, 2020 32nd International Conference on Microelectronics (ICM).

[14]  Geoff Holmes,et al.  Leveraging Bagging for Evolving Data Streams , 2010, ECML/PKDD.

[15]  João Gama,et al.  Learning with Drift Detection , 2004, SBIA.

[16]  Abdallah Shami,et al.  Concept Drift Detection in Federated Networked Systems , 2021, ArXiv.

[17]  Tree-Based Intelligent Intrusion Detection System in Internet of Vehicles , 2019, 2019 IEEE Global Communications Conference (GLOBECOM).

[18]  Scott Wares,et al.  Data stream mining: methods and challenges for handling concept drift , 2019, SN Applied Sciences.

[19]  Abdallah Shami,et al.  A Lightweight Concept Drift Detection and Adaptation Framework for IoT Data Streams , 2021, IEEE Internet of Things Magazine.

[20]  Hyunbum Kim,et al.  A Virtual Emotion Detection System With Maximum Cumulative Accuracy in Two-Way Enabled Multi Domain IoT Environment , 2021, IEEE Communications Letters.

[21]  Talel Abdessalem,et al.  Adaptive random forests for evolving data stream classification , 2017, Machine Learning.

[22]  Abdallah Shami,et al.  Machine learning towards intelligent systems: applications, challenges, and opportunities , 2021, Artif. Intell. Rev..

[23]  Hesham F. A. Hamed,et al.  Intrusion detection systems for IoT-based smart environments: a survey , 2018, Journal of Cloud Computing.

[24]  Talel Abdessalem,et al.  Scikit-Multiflow: A Multi-output Streaming Framework , 2018, J. Mach. Learn. Res..

[25]  Abdallah Shami,et al.  Multi-Stage Optimized Machine Learning Framework for Network Intrusion Detection , 2020, IEEE Transactions on Network and Service Management.

[26]  Zhihai Wang,et al.  Online Ensemble Using Adaptive Windowing for Data Streams with Concept Drift , 2016, Int. J. Distributed Sens. Networks.

[27]  João Gama,et al.  Ensemble learning for data stream analysis: A survey , 2017, Inf. Fusion.

[28]  Parisa Heidari,et al.  Multi-Perspective Content Delivery Networks Security Framework Using Optimized Unsupervised Anomaly Detection , 2021, IEEE Transactions on Network and Service Management.

[29]  Ricard Gavaldà,et al.  Learning from Time-Changing Data with Adaptive Windowing , 2007, SDM.