Optimized Intrusion Detection for IoMT Networks with Tree-Based Machine Learning and Filter-Based Feature Selection
Abstract
:1. Introduction
- We propose an optimized Intrusion Detection for IoMT Networks with tree-based machine learning on a balanced CICIDS2017 dataset. These algorithms include Decision Tree, Random Forest, XGBoost, and CatBoost.
- We apply filter-based feature selection methods to determine the relative importance of features. These methods are Mutual Information and the XGBoost method named (MI-XGBoost).
- We apply the mathematical set (intersection theory) concept to find the most common features between the chosen one after applying MI-XGBoost. This approach aims to extract the minimal set of the most relevant features.
- We evaluate the performance of our proposed model in terms of accuracy, F1 score, recall, precision, TPR, and FPR. Then, we use k = tenfold cross-validation to validate our model.
- We compare our model with recent related works.
2. Related Works
3. Research Methodology
4. Overview of the Proposed Model
4.1. Dataset Description
4.2. The Flow of the Proposed Model
- Data cleaning and pre-processing: This is an important step for ensuring the accuracy and reliability of the proposed model. The CICIDS2017 dataset is often incomplete or imbalanced, which could affect the performance of the proposed IDS; thus, the dataset must be pre-processed. To do so, the initial step to pre-process the data in our model involves removing null values and removing duplicate records. Additionally, to ensure that all features contribute equally to the model’s training, we apply Max-Min to standardize the feature range. Finally, to deal with an imbalanced dataset, the class weight is used.
- Feature selection: Feature selection is a critical component of our proposed model. This step aims to reduce the computational complexity of the model and enhances its performance by focusing on the relevant features. Thus, we apply MI and XGBoost for feature selection. Then, we reduce the number of selected features by using a mathematical set theory intersection to create a unified subset of relevant features.
- Tree-based machine learning classification: We use well-known tree classifiers such as DT, RF, XGBoost, and CatBoost to classify network data into benign and malicious. These classifiers are chosen for our model based on their robustness in handling complicated and non-linear patterns in network traffic, as well as their efficiency in processing large amounts of data. By exploiting different aspects of the data, each classifier enhances the overall detection capability of the intrusion detection system (IDS) and increases the precision and dependability of our intrusion detection.
4.2.1. Data Cleaning and Pre-Processing
- Data Cleaning:After combining the eight files into a single dataset, various methods were employed on the CICIDS2017 dataset, including data cleansing and the elimination of null values and duplicates.
- Data Pre-processing:As real-world data are often inadequate and mismatched, pre-processing the data is essential. Pre-processing the dataset is crucial for improving its quality by eliminating noise, addressing missing values, standardizing or normalizing features, and readying the data for analysis or model training. Many techniques have been proposed to pre-process data, including scaling. Scaling is a pre-processing technique that involves applying certain scalers to the numerical characteristics of a dataset to optimize it for machine learning algorithms [38]. The failure to utilize scaling for pre-processing the dataset may result in unsatisfactory model performance, skewed predictions, and erroneous interpretations of the model’s behavior. Scaling is a crucial pre-processing step in many machine learning workflows, as it guarantees dependable and precise model training and predictions. Thus, we first divided the dataset into 30% as a testing set and 70% as a training set, then Max-Min was used in the pre-processing step to scale the features of the dataset to a specified range, usually from 0 to 1 [39]. This technique standardizes the range of features to guarantee they are all on the same scale. This avoids larger-scale features from overpowering smaller-scale traits in model training. Additionally, to improve the performance of the model, class weight was used to address class imbalance issues in datasets where one class is significantly more common than the others. This involves assigning higher significance to data from the minority class and lower significance to samples from the majority class during model training. Eventually, Max-Min scaling standardizes the features, whereas class weight considers dataset imbalance. Collectively, they can improve the resilience and adaptability of the machine learning model. The main objective of using balanced data for model training is to increase the classification accuracy of the systems, thus boosting performance [40].
4.2.2. Feature Selection
- Mutual InformationOne of the most useful metrics for assessing the interdependence of variables is mutual information (MI). MI generates a non-negative result, and the two observed variables are statistically independent if the Mutual Information is zero. If it is greater than zero, it indicates a stronger relationship between the two variables [43]. Thus, we used it in our model to determine the most relevant features. Figure 4 presents the top 30 selected features by applying MI.
- XGBoostThe fundamental concept of the XGBoost method is sequentially training a set of tree models, progressively improving their accuracy by including a penalty parameter to manage the model complexity [44]. The XGBoost technique computes a score for each feature of the used dataset. The measure is used to evaluate the importance of each feature. So, we can determine the importance of inputs in the learning and classification processes. Figure 5 demonstrates the top 30 features selected by applying XGBoost to the CICIDS2017 dataset.
4.2.3. Tree-Based ML Classifiers
- Decision TreeThe Decision Tree classifier operates using the divide-and-conquer strategy. This classifier is categorized as non-parametric supervised learning [46]. By employing Decision Tree, it can distinguish between pure and impure subsets of data [47]. The procedure is terminated after the pure subsets have been acquired, or it is repeated.
- Random ForestThe Random Forest classifier was defined by Breiman in 2001. Fernández-Delgado et al. in [48] emphasized that Random Forest is a remarkably efficient classification method for several practical issues. It is comprised of a forest of Decision Trees. This classifier builds Decision Trees by randomly selecting data and making predictions for each tree.
- XGBoostXGBoost is a newer tree classifier that can scale to large-scale data [49]. This technique has gained wide acceptance in various fields, such as cyber security, due to its exceptional effectiveness and high performance [50]. XGBoost enhances accuracy by combining multiple Decision Trees and reducing the processing time [47].
- CatBoostThe CatBoost algorithm is a potent machine learning technique that produces exceptional results in various applications. Even though CatBoost is primarily intended to manage category features, it can also handle continuous or numerical attributes. The CatBoost model is a unique feature integrated into the gradient-boosting Decision Tree technique [32].Overall, Decision Tree classifiers offer a straightforward and comprehensible approach to intrusion detection, allowing analysts to comprehend the decision-making process and identify important factors that affect classification. They provide valuable insights for detecting and dealing with security issues in networks.
5. Environment Tools
6. Evaluation Metrics and Results
6.1. Evaluation Metrics
- Accuracy: This metric measures the model’s capacity to accurately classify benign instances as displayed in Equation (3):
- Recall: Also known as the detection rate or sensitivity, this metric measures the model’s ability to recognize attacks as displayed in Equation (4):
- Precision: This metric refers to the model’s capacity to produce accurate predictions, specifically, the number of correctly detected positive predictions (attacks), as displayed in Equation (5):
- F1-measure: This metric effectively addresses the trade-off between recall and precision by balancing them over all instances. This is demonstrated in Equation (6):
- False positive rate (FPR): This metric measures the percentage of assault cases classified as normal by the model. This is demonstrated in Equation (7):
- True positive rate (TPR): This metric represents the probability that a true positive will be correctly identified as positive. This is demonstrated in Equation (8):
- Receiver operating characteristics area under the curve (ROC AUC): This metric works as an indicator of the efficiency of a test across different threshold configurations. A higher level indicates a test that is more useful, with values ranging from 0.0% to 100%. A high ROC value indicates a highly successful classification model. In addition, the evaluation of a model includes the consideration of specificity (TPR) and sensitivity (also known as the true negative rate or TNR), where sensitivity is comparable to recall. This is demonstrated in Equation (9):
6.2. Experiment Results
7. A Comparison of the Proposed Model with Other State-of-the-Art Methods
8. Conclusions
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Conflicts of Interest
References
- Halder, S.; Ghosal, A.; Conti, M. Efficient physical intrusion detection in Internet of Things: A Node deployment approach. Comput. Netw. 2019, 154, 28–46. [Google Scholar] [CrossRef]
- Kumar, P.; Gupta, G.P.; Tripathi, R. An ensemble learning and fog-cloud architecture-driven cyber-attack detection framework for IoMT networks. Comput. Commun. 2021, 166, 110–124. [Google Scholar] [CrossRef]
- Balandina, E.; Balandin, S.; Koucheryavy, Y.; Mouromtsev, D. IoT use cases in healthcare and tourism. In Proceedings of the 2015 IEEE 17th Conference on Business Informatics, Lisbon, Portugal, 13–16 July 2015; IEEE: Piscataway, NJ, USA, 2015; Volume 2, pp. 37–44. [Google Scholar]
- Thomasian, N.M.; Adashi, E.Y. Cybersecurity in the internet of medical things. Health Policy Technol. 2021, 10, 100549. [Google Scholar] [CrossRef]
- Tunc, M.A.; Gures, E.; Shayea, I. A survey on iot smart healthcare: Emerging technologies, applications, challenges, and future trends. arXiv 2021, arXiv:2109.02042. [Google Scholar]
- Kilincer, I.F.; Ertam, F.; Sengur, A.; Tan, R.S.; Acharya, U.R. Automated detection of cybersecurity attacks in healthcare systems with recursive feature elimination and multilayer perceptron optimization. Biocybern. Biomed. Eng. 2023, 43, 30–41. [Google Scholar] [CrossRef]
- Si-Ahmed, A.; Al-Garadi, M.A.; Boustia, N. Survey of Machine Learning based intrusion detection methods for Internet of Medical Things. Appl. Soft Comput. 2023, 140, 110227. [Google Scholar] [CrossRef]
- Singh, L.; Kanstrup, M.; Depa, K.; Falk, A.C.; Lindström, V.; Dahl, O.; Göransson, K.E.; Rudman, A.; Holmes, E.A. Digitalizing a brief intervention to reduce intrusive memories of psychological trauma for health care staff working during COVID-19: Exploratory pilot study with nurses. JMIR Form. Res. 2021, 5, e27473. [Google Scholar] [CrossRef]
- Rbah, Y.; Mahfoudi, M.; Balboul, Y.; Fattah, M.; Mazer, S.; Elbekkali, M.; Bernoussi, B. Machine learning and deep learning methods for intrusion detection systems in iomt: A survey. In Proceedings of the 2022 2nd International Conference on Innovative Research in Applied Science, Engineering and Technology (IRASET), Meknes, Morocco, 3–4 March 2022; IEEE: Piscataway, NJ, USA, 2022; pp. 1–9. [Google Scholar]
- Kim, J.; Campbell, A.S.; de Ávila, B.E.F.; Wang, J. Wearable biosensors for healthcare monitoring. Nat. Biotechnol. 2019, 37, 389–406. [Google Scholar] [CrossRef] [PubMed]
- Caldwell, Z.B. The case for a security metric framework to rate cyber security effectiveness for Internet of Medical Things (IoMT). In Women Securing the Future with TIPPSS for Connected Healthcare: Trust, Identity, Privacy, Protection, Safety, Security; Springer: Berlin/Heidelberg, Germany, 2022; pp. 63–81. [Google Scholar]
- Hatzivasilis, G.; Soultatos, O.; Ioannidis, S.; Verikoukis, C.; Demetriou, G.; Tsatsoulis, C. Review of security and privacy for the Internet of Medical Things (IoMT). In Proceedings of the 2019 15th International Conference on Distributed Computing in Sensor Systems (DCOSS), Santorini, Greece, 29–31 May 2019; IEEE: Piscataway, NJ, USA, 2019; pp. 457–464. [Google Scholar]
- Market.us. Internet of Medical Things Statistics. 2024. Available online: https://media.market.us/internet-of-medical-things-statistics/ (accessed on 1 April 2024).
- Gupta, R.; Tanwar, S.; Tyagi, S.; Kumar, N. Machine learning models for secure data analytics: A taxonomy and threat model. Comput. Commun. 2020, 153, 406–440. [Google Scholar] [CrossRef]
- Haji, S.H.; Ameen, S.Y. Attack and anomaly detection in iot networks using machine learning techniques: A review. Asian J. Res. Comput. Sci. 2021, 9, 30–46. [Google Scholar] [CrossRef]
- Ahmed, M.; Byreddy, S.; Nutakki, A.; Sikos, L.F.; Haskell-Dowland, P. ECU-IoHT: A dataset for analyzing cyberattacks in Internet of Health Things. Ad Hoc Netw. 2021, 122, 102621. [Google Scholar] [CrossRef]
- Morgan, S. Hackerpocalypse: A Cybercrime Report. 2016. Available online: https://cybersecurityventures.com/hackerpocalypse-cybercrime-report-2016/ (accessed on 13 November 2020).
- Hernandez-Jaimes, M.L.; Martinez-Cruz, A.; Ramírez-Gutiérrez, K.A.; Feregrino-Uribe, C. Artificial intelligence for IoMT security: A review of intrusion detection systems, attacks, datasets, and Cloud-Fog-Edge architectures. Internet Things 2023, 23, 100887. [Google Scholar] [CrossRef]
- Yaacoub, J.P.A.; Noura, M.; Noura, H.N.; Salman, O.; Yaacoub, E.; Couturier, R.; Chehab, A. Securing internet of medical things systems: Limitations, issues and recommendations. Future Gener. Comput. Syst. 2020, 105, 581–606. [Google Scholar] [CrossRef]
- IT Governance USA. Indiana Hospital Pays $55,000 after Ransomware Attack. 2023. Available online: https://www.itgovernanceusa.com/blog/indiana-hospital-pays-55000-after-ransomware-attack (accessed on 10 June 2024).
- IT Governance USA. FBI Investigates Cyberattack on US Healthcare Systems. 2023. Available online: https://www.itgovernanceusa.com/blog/fbi-investigates-cyberattack-on-us-healthcare-systems (accessed on 29 August 2024).
- Iwendi, C.; Anajemba, J.H.; Biamba, C.; Ngabo, D. Security of things intrusion detection system for smart healthcare. Electronics 2021, 10, 1375. [Google Scholar] [CrossRef]
- Albulayhi, K.; Abu Al-Haija, Q.; Alsuhibany, S.A.; Jillepalli, A.A.; Ashrafuzzaman, M.; Sheldon, F.T. IoT intrusion detection using machine learning with a novel high performing feature selection method. Appl. Sci. 2022, 12, 5015. [Google Scholar] [CrossRef]
- Hady, A.A.; Ghubaish, A.; Salman, T.; Unal, D.; Jain, R. Intrusion detection system for healthcare systems using medical and network data: A comparison study. IEEE Access 2020, 8, 106576–106584. [Google Scholar] [CrossRef]
- Kamalov, F.; Pourghebleh, B.; Gheisari, M.; Liu, Y.; Moussa, S. Internet of medical things privacy and security: Challenges, solutions, and future trends from a new perspective. Sustainability 2023, 15, 3317. [Google Scholar] [CrossRef]
- Mhawi, D.N.; Aldallal, A.; Hassan, S. Advanced feature-selection-based hybrid ensemble learning algorithms for network intrusion detection systems. Symmetry 2022, 14, 1461. [Google Scholar] [CrossRef]
- Albulayhi, K.; Sheldon, F.T. An adaptive deep-ensemble anomaly-based intrusion detection system for the internet of things. In Proceedings of the 2021 IEEE World AI IoT Congress (AIIoT), Seattle, WA, USA, 10–13 May 2021; IEEE: Piscataway, NJ, USA, 2021; pp. 0187–0196. [Google Scholar]
- Panwar, S.S.; Raiwani, Y.; Panwar, L.S. An Intrusion Detection Model for CICIDS-2017 Dataset Using Machine Learning Algorithms. In Proceedings of the 2022 International Conference on Advances in Computing, Communication and Materials (ICACCM), Dehradun, India, 10–11 November 2022; IEEE: Piscataway, NJ, USA, 2022; pp. 1–10. [Google Scholar]
- Gu, J.; Lu, S. An effective intrusion detection approach using SVM with naïve Bayes feature embedding. Comput. Secur. 2021, 103, 102158. [Google Scholar] [CrossRef]
- Jairu, P.; Mailewa, A.B. Network anomaly uncovering on CICIDS-2017 dataset: A supervised artificial intelligence approach. In Proceedings of the 2022 IEEE International Conference on Electro Information Technology (eIT), Mankato, MN, USA, 19–21 May 2022; IEEE: Piscataway, NJ, USA, 2022; pp. 606–615. [Google Scholar]
- Stiawan, D.; Idris, M.Y.B.; Bamhdi, A.M.; Budiarto, R.; Kurniabudi; Darmawijoyo. CICIDS-2017 dataset feature analysis with information gain for anomaly detection. IEEE Access 2020, 8, 132911–132921. [Google Scholar]
- Saheed, Y.K.; Abiodun, A.I.; Misra, S.; Holone, M.K.; Colomo-Palacios, R. A machine learning-based intrusion detection for detecting internet of things network attacks. Alex. Eng. J. 2022, 61, 9395–9409. [Google Scholar] [CrossRef]
- Omuya, E.O.; Okeyo, G.O.; Kimwele, M.W. Feature selection for classification using principal component analysis and information gain. Expert Syst. Appl. 2021, 174, 114765. [Google Scholar] [CrossRef]
- Thamilarasu, G.; Odesile, A.; Hoang, A. An intrusion detection system for internet of medical things. IEEE Access 2020, 8, 181560–181576. [Google Scholar] [CrossRef]
- Šabić, E.; Keeley, D.; Henderson, B.; Nannemann, S. Healthcare and anomaly detection: Using machine learning to predict anomalies in heart rate data. AI Soc. 2021, 36, 149–158. [Google Scholar] [CrossRef]
- He, D.; Qiao, Q.; Gao, Y.; Zheng, J.; Chan, S.; Li, J.; Guizani, N. Intrusion detection based on stacked autoencoder for connected healthcare systems. IEEE Netw. 2019, 33, 64–69. [Google Scholar] [CrossRef]
- Ayyagari, M.R.; Kesswani, N.; Kumar, M.; Kumar, K. Intrusion detection techniques in network environment: A systematic review. Wirel. Netw. 2021, 27, 1269–1285. [Google Scholar] [CrossRef]
- Alkanjr, B.; Alshammari, T. Iobt intrusion detection system using machine learning. In Proceedings of the 2023 IEEE 13th Annual Computing and Communication Workshop and Conference (CCWC), Las Vegas, NV, USA, 8–11 March 2023; IEEE: Piscataway, NJ, USA, 2023; pp. 0886–0892. [Google Scholar]
- Alserhani, F.; Aljared, A. Evaluating Ensemble Learning Mechanisms for Predicting Advanced Cyber Attacks. Appl. Sci. 2023, 13, 13310. [Google Scholar] [CrossRef]
- Alalwany, E.; Mahgoub, I. Classification of normal and malicious traffic based on an ensemble of machine learning for a vehicle can-network. Sensors 2022, 22, 9195. [Google Scholar] [CrossRef] [PubMed]
- Gupta, K.; Sharma, D.K.; Gupta, K.D.; Kumar, A. A tree classifier based network intrusion detection model for Internet of Medical Things. Comput. Electr. Eng. 2022, 102, 108158. [Google Scholar] [CrossRef]
- RM, S.P.; Maddikunta, P.K.R.; Parimala, M.; Koppu, S.; Gadekallu, T.R.; Chowdhary, C.L.; Alazab, M. An effective feature engineering for DNN using hybrid PCA-GWO for intrusion detection in IoMT architecture. Comput. Commun. 2020, 160, 139–149. [Google Scholar]
- Alotaibi, Y.; Ilyas, M. Ensemble-learning framework for intrusion detection to enhance internet of things’ devices security. Sensors 2023, 23, 5568. [Google Scholar] [CrossRef] [PubMed]
- Kasongo, S.M.; Sun, Y. Performance analysis of intrusion detection systems using a feature selection method on the UNSW-NB15 dataset. J. Big Data 2020, 7, 105. [Google Scholar] [CrossRef]
- Rashid, M.; Kamruzzaman, J.; Imam, T.; Wibowo, S.; Gordon, S. A tree-based stacking ensemble technique with feature selection for network intrusion detection. Appl. Intell. 2022, 52, 9768–9781. [Google Scholar] [CrossRef]
- Myles, A.J.; Feudale, R.N.; Liu, Y.; Woody, N.A.; Brown, S.D. An introduction to decision tree modeling. J. Chemom. J. Chemom. Soc. 2004, 18, 275–285. [Google Scholar] [CrossRef]
- Kaushik, B.; Sharma, R.; Dhama, K.; Chadha, A.; Sharma, S. Performance evaluation of learning models for intrusion detection system using feature selection. J. Comput. Virol. Hacking Tech. 2023, 19, 529–548. [Google Scholar] [CrossRef]
- Fernández-Delgado, M.; Cernadas, E.; Barro, S.; Amorim, D. Do we need hundreds of classifiers to solve real world classification problems? J. Mach. Learn. Res. 2014, 15, 3133–3181. [Google Scholar]
- Dhaliwal, S.S.; Nahid, A.A.; Abbas, R. Effective intrusion detection system using XGBoost. Information 2018, 9, 149. [Google Scholar] [CrossRef]
- Chen, Z.; Jiang, F.; Cheng, Y.; Gu, X.; Liu, W.; Peng, J. XGBoost classifier for DDoS attack detection and analysis in SDN-based cloud. In Proceedings of the 2018 IEEE International Conference on Big Data and Smart Computing (Bigcomp), Shanghai, China, 15–17 January 2018; IEEE: Piscataway, NJ, USA, 2018; pp. 251–256. [Google Scholar]
- Ozdogan, E. A Comprehensive Analysis of the Machine Learning Algorithms in IoT IDS Systems. IEEE Access 2024, 12, 46785–46811. [Google Scholar] [CrossRef]
- Sah, G.; Banerjee, S.; Singh, S. Intrusion detection system over real-time data traffic using machine learning methods with feature selection approaches. Int. J. Inf. Secur. 2023, 22, 1–27. [Google Scholar] [CrossRef]
- Phulre, A.K.; Jain, S.; Jain, G. Evaluating Security enhancement through Machine Learning Approaches for Anomaly Based Intrusion Detection Systems. In Proceedings of the 2024 IEEE International Students’ Conference on Electrical, Electronics and Computer Science (SCEECS), Bhopal, India, 24–25 February 2024; IEEE: Piscataway, NJ, USA, 2024; pp. 1–5. [Google Scholar]
Day Activity | Traffic Type |
---|---|
Monday | Benign |
Tuesday | Benign, FTP-Patator, SSH-Patator |
Wednesday | Benign, DoS GoldenEye, DoS Hulk, Dos Slowhttptest, Dos Slowlories, Heartbleed |
Thursday (Morning) | Benign, Web Attack XSS, Web Attack Brute Force, Web Attack Sql Injection |
Thursday (Afternoon) | Benign, Infilration |
Friday (Morning) | Benign, Botnet. |
Friday (Afternoon) | Benign, PortScan |
Friday (Afternoon) | Benign, DDos |
Model | Accuracy | Precision | Recall | F1 Score |
---|---|---|---|---|
DT | 0.9987 | 0.9948 | 0.9980 | 0.9964 |
RF | 0.9989 | 0.9954 | 0.9981 | 0.9967 |
XGBoost | 0.9987 | 0.9957 | 0.9970 | 0.9963 |
CatBoost | 0.9969 | 0.9829 | 0.9990 | 0.9909 |
Model | Accuracy % | ROC | DR % | FAR |
---|---|---|---|---|
DT | 98.12 | 0.9505 | 98.74 | 0.049 |
RF | 98.14 | 0.960 | 98.55 | 0.039 |
XGBoost | 98.63 | 0.992 | 98.77 | 0.0205 |
CatBoost | 98.79 | 0.9794 | 98.70 | 0.007 |
Study | Year | Dataset | Balanced | FS Methods | Num of FS | ML-Classifier | Accuracy | IoMT | Cross-Validation |
---|---|---|---|---|---|---|---|---|---|
[26] | 2022 | CICIDS2017 | × | (CFS–FPA) | 30 | SVM, RF, NB and KNN | 99.7 | × | ✓ |
[52] | 2022 | CICIDS2017 NSL-KDD | × | RFE (best FST) | 8 | DT, NB, and KNN | 99.98 | × | ✓ |
[51] | 2024 | CICIDS2017 | ✓ | ANOVA | 10 | SVC, DT, RF, GNB, AdaBoost, XGBoost and LR | 97.23 | × | × |
[53] | 2024 | CICIDS2017 | - | - | - | RF and DT | 98.12 | × | ✓ |
Our work | 2024 | CICIDS2017 | ✓ | MI-XGboost | 15 | DT, RF, XGboost, and Catboost | 98.79 | ✓ | ✓ |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2024 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Balhareth, G.; Ilyas, M. Optimized Intrusion Detection for IoMT Networks with Tree-Based Machine Learning and Filter-Based Feature Selection. Sensors 2024, 24, 5712. https://doi.org/10.3390/s24175712
Balhareth G, Ilyas M. Optimized Intrusion Detection for IoMT Networks with Tree-Based Machine Learning and Filter-Based Feature Selection. Sensors. 2024; 24(17):5712. https://doi.org/10.3390/s24175712
Chicago/Turabian StyleBalhareth, Ghaida, and Mohammad Ilyas. 2024. "Optimized Intrusion Detection for IoMT Networks with Tree-Based Machine Learning and Filter-Based Feature Selection" Sensors 24, no. 17: 5712. https://doi.org/10.3390/s24175712
APA StyleBalhareth, G., & Ilyas, M. (2024). Optimized Intrusion Detection for IoMT Networks with Tree-Based Machine Learning and Filter-Based Feature Selection. Sensors, 24(17), 5712. https://doi.org/10.3390/s24175712