|
UPSI Digital Repository (UDRep)
|
|
| ||||||||||||||||||||||||
| Abstract : Universiti Pendidikan Sultan Idris |
| Intrusion detection systems (IDSs) are commonly employed to mitigate network security threats in various fields, including federated learning applications within the Internet of Medical Things (IoMT). However, IDSs face challenges owing to the sheer volume of network traffic, high-dimensional datasets and the necessity for real-time detection. Although machine learning integration assists IDSs in overcoming these challenges, modelling difficulties persist due to varied evaluation criteria and levels of conflict and importance. Multi-criteria decision-making (MCDM) solutions have been utilised in IoMT and IDS, yet they fall short in capturing the subjective judgements of experts and rely on normalisation approaches, which can impact results. This study seeks to address these issues through the integration of robust MCDM methodologies, namely fuzzy-weighted zero-inconsistency (FWZIC) and fuzzy decision by opinion score method (FDOSM). Utilising rough Fermatean fuzzy sets (RFFSs), this integration produces precise solutions with reduced uncertainty. Our methodology involves adopting a decision matrix for IDS classifiers based on integrated evaluation criteria, followed by deriving new formulations and developments for RFFSs-based FDOSM and FWZIC for the modelling and weighting of criteria, respectively. Evaluations using datasets involving 125,973 records and 41 features across 17 evaluation criteria revealed that accuracysecurity and training timeperformance weights yielded the highest scores, whereas false negative ratesecurity and CPU timeperformance criteria received the lowest weights. The random forest emerged as the optimal IDS classifier. Systematic modelling, sensitivity analysis and comparative studies confirmed the robustness of our results. 2023, Crown. |
| References |
Liu D, Zhang Y, Wang W, Dev K, Khowaja SA (2021) Flexible data integrity checking with original data recovery in IoT-enabled maritime transportation systems. IEEE Trans Intell Transp Syst. https://doi.org/10.1109/TITS.2021.3125070 Wang W, Xu H, Alazab M, Gadekallu TR, Han Z, Su C (2021) Blockchain-based reliable and efficient certificateless signature for IIoT devices. IEEE Trans Ind Inform 18(10):7059–7067 Zhou X, Yang X, Ma J, Kevin I, Wang K (2021) Energy efficient smart routing based on link correlation mining for wireless edge computing in IoT. IEEE Internet Things J 9(16):14988–14997 Haughey J, Taylor K, Dohrmann M, Snyder G (2018) Medtech and the internet of medical things: how connected medical devices are transforming health care. Ed: Deloitte. pp 112 Qureshi F, Krishnan S (2018) Wearable hardware design for the internet of medical things (IoMT). Sensors 18(11):3812 Pham Q-V, Dev K, Maddikunta PKR, Gadekallu TR, HuynhThe T (2022) Fusion of federated learning and industrial internet of things: a survey. 212: 109048 Lian Z, Wang W, Su C (2021) COFEL: Communication-efficient and optimized federated learning with local differential privacy. In: ICC 2021-IEEE international conference on communications, pp 1–6: IEEE. https://doi.org/10.1109/ICC42927.2021.9500632 Song J, Wang W, Gadekallu TR, Cao J, Liu Y (2022) EPPDA: An efficient privacy-preserving data aggregation federated learning scheme. IEEE transactions on network science and engineering. pp 1–12. https://doi.org/10.1109/TNSE.2022.3153519 Taheri R, Shojafar M, Alazab M, Tafazolli R (2020) FED-IIoT: a robust federated malware detection architecture in industrial IoT. IEEE Trans Ind Inform 17(12):8442–8452 Zhang C, Xie Y, Bai H, Yu B, Li W, Gao Y (2021) A survey on federated learning. Knowl-Based Syst 216:106775 Mothukuri V, Khare P, Parizi RM, Pouriyeh S, Dehghantanha A, Srivastava G (2021) Federated learning-based anomaly detection for IOT security attacks. IEEE Internet Things J 9(4):2545–2554 Gong M, Xie Y, Pan K, Feng K, Qin AK (2020) A survey on differentially private machine learning. IEEE Comput Intell Mag 15(2):49–64 Powell K (2019) Nvidia clara federated learning to deliver ai to hospitals while protecting patient data. Nvidia Blog. pp 512 Agrawal S, et al (2021) Federated learning for intrusion detection system: Concepts, challenges and future directions. computer communications, vol 195, pp 346–361, arXiv preprint arXiv:2106.09527 Alamleh A et al (2023) Federated learning for IoMT applications: a standardisation and benchmarking framework of intrusion detection systems. IEEE J Biomed Health Inform 27(2):878–887 Papadopoulos P, Abramson W, Hall AJ, Pitropakis N, Buchanan WJ (2021) Privacy and trust redefined in federated machine learning. Mach Learn Knowl Extract 3(2):333–356 Base R, Mell P (2019) Special publication on intrusion detection systems. NIST Infidel, Inc., National Institute of Standards and Technology, Scotts Valley, CA. pp 120 Tang Z et al (2020) A multilayer neural network merging image preprocessing and pattern recognition by integrating diffusion and drift memristors. IEEE Trans Cognit Dev Syst 13(3):645–656 Hodo E, Bellekens X, Hamilton A, Tachtatzis C, Atkinson R (2020) Shallow and deep networks intrusion detection system: a taxonomy and survey. arXiv preprint arXiv:1701.02145. https://doi.org/10.48550/arXiv.1701.02145 Tang Z et al (2019) A hardware friendly unsupervised memristive neural network with weight sharing mechanism. Neurocomputing 332:193–202 Ahmad I, Basheri M, Iqbal MJ, Rahim A (2020) Performance comparison of support vector machine, random forest, and extreme learning machine for intrusion detection. IEEE access 6:33789–33795 Ghaznavi M, Shahriar N, Kamali S, Ahmed R, Boutaba R (2021) Distributed service function chaining. IEEE J Sel Areas Commun 35(11):2479–2489 Aleesa AM et al (2020) Review of intrusion detection systems based on deep learning techniques: coherent taxonomy, challenges, motivations, recommendations, substantial analysis and future directions. Neural Comput Appl 32:9827–9858 Ahmad I, Abdullah A, Alghamdi A (2010) Towards the selection of best neural network system for intrusion detection. Int J Phys Sci 5(12):1830–1839 Peng Y, Kou G, Wang G, Shi Y (2019) FAMCDM: a fusion approach of MCDM methods to rank multiclass classification algorithms. Omega 39(6):677–689 Robinson RR, Thomas C (2020) Ranking of machine learning algorithms based on the performance in classifying DDoS attacks. ieee recent advances in intelligent computational systems (RAICS), pp 185–190: IEEE Panigrahi R, Borah S (2019) Rank allocation to J48 group of decision tree classifiers using binary and multiclass intrusion detection datasets. Proc Comput Sci 132:323–332 Patsariya P, Singh RR (2019) Classifier rank identification using multi-criteria decision making method for intrusion detection dataset. Int J Innov Technol Explor Eng 9(1):1732–1738 Albahri A et al (2019) Based multiple heterogeneous wearable sensors: a smart real-time health monitoring structured for hospitals distributor. IEEE Access 7:37269–37323 Alsalem M et al (2019) Multiclass benchmarking framework for automated acute Leukaemia detection and classification based on BWM and group-VIKOR. J Med Syst 43(7):212 Mohammed K et al (2019) Real-time remote-health monitoring systems: a review on patients prioritisation for multiple-chronic diseases, taxonomy analysis, concerns and solution procedure. J Med Syst 43(7):223 Ibrahim N et al (2019) Multi-criteria evaluation and benchmarking for young learners’ English language mobile applications in terms of LSRW skills. IEEE Access 7(7):146620–146651 Mohammed K et al (2020) Novel technique for reorganisation of opinion order to interval levels for solving several instances representing prioritisation in patients with multiple chronic diseases. Comput Methods Programs Biomed 185:105151 Mohammed K et al (2020) A uniform intelligent prioritisation for solving diverse and big data generated from multiple chronic diseases patients based on hybrid decision-making and voting method. IEEE Access 8:91521–91530 Albahri O et al (2020) Helping doctors hasten COVID-19 treatment: towards a rescue framework for the transfusion of best convalescent plasma to the most critical patients based on biological requirements via ml and novel MCDM methods. Comput Methods Programs Biomed 196:105617 |
| This material may be protected under Copyright Act which governs the making of photocopies or reproductions of copyrighted materials. You may use the digitized material for private study, scholarship, or research. |