Zero-Shot Traffic Identification with Attribute and Graph-Based Representations for Edge Computing
Abstract
:1. Introduction
- Conceptually, we propose a ZSL-based framework for general encrypted traffic classification that uses attribute representations as intermediates to address the challenge of predicting unknown categories. This framework enables knowledge transfer from known to unknown categories through attribute-based representations, effectively enhancing model generalization.
- Methodologically, the framework leverages traffic attribute representations to transform traditional classification labels into attribute labels that facilitate knowledge transfer. These attributes, which include basic traffic characteristics, are integrated with traffic behavior representations to enable robust classification of unknown categories.
- Innovatively, a novel burst-based traffic interaction graph is introduced to capture detailed traffic interaction features, where nodes represent datagrams and edges encode the interaction relationships between endpoints.
- Experimentally, extensive experiments on public datasets demonstrate that AG-ZSL achieves state-of-the-art performance in both fine-grained classification and zero-shot prediction.
2. Related Work
2.1. Traffic Classification
2.1.1. Statistic Methods
2.1.2. Machine Learning Methods
2.1.3. Deep Learning Methods
2.2. Zero-Shot Learning
3. Preliminary
3.1. Traffic Interaction Graph
3.2. Attribute Description
3.3. Goal
4. The Proposed Framework
4.1. Model Training
4.1.1. Traffic Behavior Representation
4.1.2. Attribute Representation
4.2. Zero-Shot Prediction
Algorithm 1: Gradient Rejection Strategy |
5. Experiment
5.1. Dataset
5.2. Implementation
5.2.1. Hyperparamters Setting
5.2.2. Experiment Setting
5.2.3. Attribute Label Threshold Setting
5.3. Experiments Results
5.3.1. Fine-Grained Classification Experiments
5.3.2. Zero-Shot Prediction Experiments
5.3.3. Evaluation of Complexity
6. Conclusions
Author Contributions
Funding
Data Availability Statement
Conflicts of Interest
Appendix A. Attribute Label
Scenario | |||||
---|---|---|---|---|---|
D1 | D1 | ||||
No. | Attribute Label | No. | Attribute Label | No. | Attribute Label |
1 | chat_spike_fast_normal_TCP | 1 | injection_steady_fast_malware_DNS | 21 | polling_steady_slow_malware_DNS |
2 | audio_steady_fast_normal_TCP | 2 | injection_steady_slow_malware_HTTP | 22 | injection_spike_fast_malware_TCP |
3 | file_burst_fast_normal_UDP | 3 | control_burst_fast_malware_TCP | 23 | polling_burst_slow_malware_TCP |
4 | audio_steady_slow_normal_SSH | 4 | injection_steady_slow_malware_UDP | 24 | control_spike_fast_malware_UDP |
5 | audio_steady_slow_normal_TCP | 5 | control_steady_slow_malware_UDP | 25 | polling_spike_slow_malware_HTTP |
6 | audio_burst_slow_normal_TCP | 6 | polling_burst_fast_malware_TCP | 26 | polling_spike_slow_malware_SSH |
7 | chat_steady_slow_normal_TCP | 7 | polling_spike_fast_malware_HTTP | 27 | injection_burst_slow_malware_TCP |
8 | audio_spike_fast_normal_UDP | 8 | injection_burst_fast_malware_TCP | 28 | polling_steady_fast_malware_SSH |
9 | file_spike_fast_normal_TCP | 9 | polling_burst_fast_malware_HTTP | 29 | polling_burst_fast_malware_UDP |
10 | email_spike_fast_normal_UDP | 10 | injection_steady_fast_malware_TCP | 30 | injection_steady_slow_malware_FTP |
11 | chat_spike_fast_normal_HTTP | 11 | polling_burst_slow_malware_UDP | 31 | control_burst_slow_malware_HTTP |
12 | video_spike_slow_normal_HTTP | 12 | polling_steady_slow_malware_FTP | 32 | polling_burst_slow_malware_HTTP |
13 | audio_steady_slow_normal_UDP | 13 | injection_steady_fast_malware_HTTP | 33 | polling_burst_slow_malware_IMAP |
14 | email_burst_fast_normal_UDP | 14 | polling_burst_fast_malware_POP3 | 34 | polling_steady_fast_malware_HTTP |
15 | audio_burst_fast_normal_UDP | 15 | control_spike_slow_malware_UDP | 35 | injection_burst_slow_malware_UDP |
16 | file_burst_fast_normal_UDP | 16 | control_spike_fast_malware_TCP | 36 | polling_spike_fast_malware_TCP |
17 | chat_spike_slow_normal_UDP | 17 | control_spike_slow_malware_HTTP | ||
18 | audio_burst_fast_normal_TCP | 18 | polling_steady_slow_malware_UDP | ||
19 | vedio_burst_slow_normal_UDP | 19 | polling_spike_fast_malware_POP3 | ||
20 | vedio_spike_slow_normal_TCP | 20 | polling_steady_slow_malware_NTP |
References
- Xu, S.-J.; Geng, G.-G.; Jin, X.-B.; Liu, D.-J.; Weng, J. Seeing Traffic Paths: Encrypted Traffic Classification With Path Signature Features. IEEE Trans. Inf. Forensics Secur. 2022, 17, 2166–2181. [Google Scholar] [CrossRef]
- He, M.; Huang, Y.; Wang, X.; Wei, P.; Wang, X. A Lightweight and Efficient IoT Intrusion Detection Method Based on Feature Grouping. IEEE Internet Things J. 2024, 11, 2935–2949. [Google Scholar] [CrossRef]
- Wang, X.; Lu, Z.; Wang, X.; He, M.; Wang, X. GETRF: A General Framework for Encrypted Traffic Identification With Robust Representation Based on Datagram Structure. IEEE Trans. Cogn. Commun. Netw. 2024, 10, 2045–2060. [Google Scholar] [CrossRef]
- Yao, H.; Liu, C.; Zhang, P.; Wu, S.; Jiang, C.; Yu, S. Identification of Encrypted Traffic Through Attention Mechanism Based Long Short Term Memory. IEEE Trans. Big Data 2022, 8, 241–252. [Google Scholar] [CrossRef]
- Han, D.; Wang, Z.; Chen, W.; Wang, K.; Yu, R.; Wang, S.; Zhang, H.; Wang, Z.; Jin, M.; Yang, J. Anomaly Detection in the Open World: Normality Shift Detection, Explanation, and Adaptation. In Proceedings of the 30th Annual Network and Distributed System Security Symposium (NDSS), San Diego, CA, USA, 27 February–3 March 2023. [Google Scholar]
- Fu, C.; Li, Q.; Shen, M.; Xu, K. Realtime Robust Malicious Traffic Detection via Frequency Domain Analysis. In Proceedings of the 2021 ACM SIGSAC Conference on Computer and Communications Security, Virtual, 15–19 November 2021; ACM: New York, NY, USA, 2021; pp. 3431–3446. [Google Scholar] [CrossRef]
- Bhat, S.; Lu, D.; Kwon, A.; Devadas, S. Var-CNN: A Data-Efficient Website Fingerprinting Attack Based on Deep Learning. Proc. Priv. Enhancing Technol. 2019, 2019, 292–310. [Google Scholar] [CrossRef]
- Hu, Y.; Cheng, G.; Chen, W.; Jiang, B. Attribute-Based Zero-Shot Learning for Encrypted Traffic Classification. IEEE Trans. Netw. Serv. Manag. 2022, 19, 4583–4599. [Google Scholar] [CrossRef]
- Yang, L.; Finamore, A.; Jun, F.; Rossi, D. Deep Learning and Zero-Day Traffic Classification: Lessons Learned From a Commercial-Grade Dataset. IEEE Trans. Netw. Serv. Manag. 2021, 18, 4103–4118. [Google Scholar] [CrossRef]
- Zhang, J.; Li, F.; Ye, F.; Wu, H. Autonomous Unknown-Application Filtering and Labeling for DL-based Traffic Classifier Update. In Proceedings of the IEEE INFOCOM 2020—IEEE Conference on Computer Communications, Virtual, 6–9 July 2020; pp. 397–405. [Google Scholar]
- Chen, C.-Y.; Li, C.-T. ZS-BERT: Towards Zero-Shot Relation Extraction with Attribute Representation Learning. arXiv 2021, arXiv:2104.04697. [Google Scholar] [CrossRef]
- Lampert, C.H.; Nickisch, H.; Harmeling, S. Learning to detect unseen object classes by between-class attribute transfer. In Proceedings of the 2009 IEEE Conference on Computer Vision and Pattern Recognition, Miami, FL, USA, 20–25 June 2009; pp. 951–958. [Google Scholar]
- Fu, C.; Li, Q.; Xu, K. Detecting Unknown Encrypted Malicious Traffic in Real Time via Flow Interaction Graph Analysis. arXiv 2023, arXiv:2301.13686. [Google Scholar] [CrossRef]
- Zhao, S.; Zhang, Y.; Sang, Y. Towards Unknown Traffic Identification via Embeddings and Deep Autoencoders. In Proceedings of the 2019 26th International Conference on Telecommunications (ICT), Hanoi, Vietnam, 8–10 April 2019; pp. 85–89. [Google Scholar] [CrossRef]
- Wang, H.; Wang, Y.; Guo, Y. Unknown network attack detection method based on reinforcement zero-shot learning. J. Phys. Conf. Ser. 2022, 2303, 012008. [Google Scholar] [CrossRef]
- Wu, B.; Gysel, P.; Divakaran, D.M.; Gurusamy, M. ZEST: Attention-based Zero-Shot Learning for Unseen IoT Device Classification. arXiv 2024, arXiv:2310.08036. [Google Scholar] [CrossRef]
- Lin, X.; Xiong, G.; Gou, G.; Li, Z.; Shi, J.; Yu, J. ET-BERT: A Contextualized Datagram Representation with Pre-training Transformers for Encrypted Traffic Classification. In Proceedings of the WWW ’22: Proceedings of the ACM Web Conference 20, Lyon France, 25–29 April 2022; ACM: New York, NY, USA, 2022; pp. 633–642. [Google Scholar] [CrossRef]
- Lei, T.; Zhang, Y.; Wang, S.I.; Dai, H.; Artzi, Y. Simple Recurrent Units for Highly Parallelizable Recurrence. arXiv 2018, arXiv:1709.02755. [Google Scholar] [CrossRef]
- Taylor, V.F.; Spolaor, R.; Conti, M.; Martinovic, I. Robust Smartphone App Identification via Encrypted Network Traffic Analysis. IEEE Trans. Inf. Forensics Secur. 2018, 13, 63–78. [Google Scholar] [CrossRef]
- Al-Naami, K.; Chandra, S.; Mustafa, A.; Khan, L.; Lin, Z.; Hamlen, K.; Thuraisingham, B. Adaptive Encrypted Traffic Fingerprinting with Bi-Directional Dependence. In Proceedings of the 32nd Annual Conference on Computer Security Applications, ACSAC ’16, Los Angeles, CA, USA, 5–8 December 2016; pp. 177–188. [Google Scholar] [CrossRef]
- Panchenko, A.; Lanze, F.; Pennekamp, J.; Engel, T.; Zinnen, A.; Henze, M.; Wehrle, K. Website Fingerprinting at Internet Scale. In Proceedings of the Network and Distributed System Security Symposium (NDSS), San Diego, CA, USA, 21–24 February 2016. [Google Scholar]
- Wang, W.; Zhu, M.; Wang, J.; Zeng, X.; Yang, Z. End-to-End Encrypted Traffic Classification with One-Dimensional Convolution Neural Networks. In Proceedings of the 2017 IEEE International Conference on Intelligence and Security Informatics (ISI), Beijing, China, 22–24 July 2017; pp. 43–48. [Google Scholar]
- Luo, Y.; He, M.; Wang, X.; Jin, L. Network Flow Detection of Semantic Relationship Between Flow and Byte. In Proceedings of the 2022 IEEE Eighth International Conference on Big Data Computing Service and Applications (BigDataService), Newark, CA, USA, 15–18 August 2022; pp. 179–180. [Google Scholar]
- Huoh, T.-L.; Luo, Y.; Li, P.; Zhang, T. Flow-Based Encrypted Network Traffic Classification With Graph Neural Networks. IEEE Trans. Netw. Serv. Manag. 2023, 20, 1224–1237. [Google Scholar] [CrossRef]
- Guarino, I.; Aceto, G.; Ciuonzo, D.; Montieri, A.; Persico, V.; Pescapè, A. Contextual counters and multimodal Deep Learning for activity-level traffic classification of mobile communication apps during COVID-19 pandemic. Comput. Netw 2022, 219, 109452. [Google Scholar] [CrossRef] [PubMed]
- He, H.Y.; Yang, Z.G.; Chen, X.N. PERT: Payload Encoding Representation from Transformer for Encrypted Traffic Classification. In Proceedings of the 2020 ITU Kaleidoscope: Industry-Driven Digital Transformation (ITU K), Online, 7–11 December 2020; pp. 1–8. [Google Scholar]
- Huoh, T.-L.; Luo, Y.; Zhang, T. Encrypted Network Traffic Classification Using a Geometric Learning Model. In Proceedings of the 2021 IFIP/IEEE International Symposium on Integrated Network Management (IM), Bordeaux, France, 17–21 May 2021; pp. 376–383. [Google Scholar]
- Shen, M.; Zhang, J.; Zhu, L.; Xu, K.; Du, X. Accurate Decentralized Application Identification via Encrypted Traffic Analysis Using Graph Neural Networks. IEEE Trans. Inf. Forensics Secur. 2021, 16, 2367–2380. [Google Scholar] [CrossRef]
- Yang, Y.; Lyu, R.; Gao, Z.; Rui, L.; Yan, Y. Semisupervised Graph Neural Networks for Traffic Classification in Edge Networks. Discret. Dyn. Nat. Soc. 2023, 2023, 2879563. [Google Scholar] [CrossRef]
- Pang, B.; Fu, Y.; Ren, S.; Wang, Y.; Liao, Q.; Jia, Y. CGNN: Traffic Classification with Graph Neural Network. arXiv 2021, arXiv:2110.09726. [Google Scholar] [CrossRef]
- Chen, L.; Chen, D.; Shang, Z.; Wu, B.; Zheng, C.; Wen, B.; Zhang, W. Multi-Scale Adaptive Graph Neural Network for Multivariate Time Series Forecasting. arXiv 2023, arXiv:2201.04828. [Google Scholar] [CrossRef]
- Sirinam, P.; Mathews, N.; Rahman, M.S.; Wright, M. Triplet Fingerprinting: More Practical and Portable Website Fingerprinting with N-shot Learning. In Proceedings of the 2019 ACM SIGSAC Conference on Computer and Communications Security (CCS ’19), London, UK, 11–15 November 2019; ACM: New York, NY, USA, 2019. 18p. [Google Scholar] [CrossRef]
- Hamilton, W.L.; Ying, R.; Leskovec, J. Inductive Representation Learning on Large Graphs. arXiv 2018, arXiv:1706.02216. [Google Scholar] [CrossRef]
- He, K.; Zhang, X.; Ren, S.; Sun, J. Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification. arXiv 2015, arXiv:1502.01852. [Google Scholar] [CrossRef]
- Habibi Lashkari, A.; Draper Gil, G.; Mamun, M.; Ghorbani, A. Characterization of Encrypted and VPN Traffic Using Time-Related Features. In Proceedings of the 2016 International Conference on Information Systems Security and Privacy (ICISSP), Rome, Italy, 19–21 February 2016; pp. 407–414. [Google Scholar]
- Moustafa, N.; Ahmed, M.; Ahmed, S. Data Analytics-Enabled Intrusion Detection: Evaluations of ToN_IoT Linux Datasets. In Proceedings of the 2020 IEEE 19th International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom), Guangzhou, China, 29 December 2020–1 January 2021; pp. 727–735. [Google Scholar]
- Liu, C.; He, L.; Xiong, G.; Cao, Z.; Li, Z. FS-Net: A Flow Sequence Network For Encrypted Traffic Classification. In Proceedings of the IEEE INFOCOM 2019—IEEE Conference on Computer Communications, Paris, France, 29 April 2019–2 May 2019; pp. 1171–1179. [Google Scholar]
Category | Method | Classifier | Raw Data | Burst | Sequential Information | Zero-Shot Prediction |
---|---|---|---|---|---|---|
Statistic method | DPI | - | - | - | - | - |
Machine learning method | CUMUL | SVM | - | - | - | - |
AppScanner | Random Forest, SVM | - | - | - | - | |
BIND | SVM, Random Forest | - | √ | - | - | |
Deep learning mehtod | CNN | CNN | √ | - | - | - |
Var-CNN | CNN | √ | - | - | - | |
FS-Net | BiGRU | √ | - | - | - | |
MIMETIC-ALL | CNN + BiGRU | √ | √ | - | - | |
TF | Triplet network | √ | - | √ | √ | |
Geometric Learnng Model | GNN | √ | √ | √ | - | |
GraphDApp | GNN | √ | √ | √ | - | |
Flow-Based GNN | GNN | √ | - | √ | - | |
ZSL framework | FAE-G + SRU | √ | - | √ | √ | |
AG-ZSL | GNN + SRU | √ | √ | √ | √ |
Dataset | Ground Truth | Attibute Label | ||||
---|---|---|---|---|---|---|
Action | Mode | Type | Protocol | Frequency | ||
ISCX-VPN | facebook, aim, skype, gmail, youtube, icq, vimeo, spotify, twitter, netflix, hangouts, torrent | vedio, audio, file, chat, emaiil | burst, spike, steady | normal | tcp, udp, http, ssh, ntp, dns, pop3, imap | fast, slow |
ToN-IoT | scanning, XSS, DDoS, Dos, MITM, injection, backdoor, runsomware, password | polling, injection, control | burst, spike, steady | malware | tcp, udp, http, dns, ntp, ssh, pop3, imap, ftp | fast, slow |
Dataset | # Flow | # Packet | # Ground-Truth Label | # Attribute Label |
---|---|---|---|---|
4753 | 60,471 | 12 | 20 | |
3326 | 36,249 | 9 | 36 |
Hyperparamters | Search Range | Final |
---|---|---|
Depth of GraphSAGE | [2, 3, 4, 5] | 3 |
Embedding Size of GraphSAGE | [64, 128, 256] | 256 |
Number of Neighbors | [5, 10, 15, 20] | 5 |
Learning rage | [0.0001, …, 0.005] | 0.001 |
Hidden Unit Size of SRU | [128, 256, 512] | 512 |
Dropout | [0, …, 0.5] | 0.1 |
Activation Functions | [Tanh, PReLu, Relu] | PReLu |
Batch Size | [30, …, 300] | 64 |
Optimizer | [Adam, RMSProp, SGD] | Adam |
The threshold for the burst | [0, …, 1.0] | >0.6 |
The threshold for the spike | [0, …, 1.0] | >0.9 |
The threshold for the steady | [0, …, 1.0] | <=0.9 |
The threshold for the fast | [0, …, 10] | >3 |
The threshold for the slow | [0, …, 1.0] | <=3 |
Dataset | Method | Accuracy | Recall | Precision | F1 |
---|---|---|---|---|---|
TF | 0.9171 | 0.9257 | 0.9182 | 0.9220 | |
FS-Net | 0.9133 | 0.9254 | 0.9168 | 0.9211 | |
AG-ZSL | 0.9571 | 0.9613 | 0.9578 | 0.9596 | |
TF | 0.9213 | 0.9213 | 0.9268 | 0.92412 | |
FS-Net | 0.9146 | 0.9146 | 0.9201 | 0.9174 | |
AG-ZSL | 0.9659 | 0.9659 | 0.9676 | 0.9667 |
Method | AG-ZSL | TF | FS-NET | ||||||
---|---|---|---|---|---|---|---|---|---|
Attribute | Accuracy | Recall | Precision | Accuracy | Recall | Precision | Accuracy | Recall | Precision |
chat_spike_fast_normal_TCP | 0.8915 | 0.9036 | 0.7666 | 0.8701 | 0.8340 | 0.7913 | 0.8103 | 0.8213 | 0.7862 |
audio_steady_fast_normal_TCP | 0.9177 | 0.9253 | 0.9155 | 0.8428 | 0.5726 | 0.6891 | 0.8603 | 0.6706 | 0.7032 |
file_burst_fast_normal_UDP | 0.8616 | 0.8213 | 0.8389 | 0.8769 | 0.7913 | 0.8205 | 0.7483 | 0.6433 | 0.7699 |
audio_steady_slow_normal_SSH | 0.8841 | 0.8387 | 0.8292 | 0.8723 | 0.8920 | 0.7995 | 0.8406 | 0.6856 | 0.6321 |
audio_steady_slow_normal_TCP | 0.9113 | 0.8862 | 0.8063 | 0.8491 | 0.6716 | 0.7042 | 0.8527 | 0.7666 | 0.6967 |
audio_burst_slow_normal_TCP | 0.9201 | 0.8901 | 0.8865 | 0.8482 | 0.7426 | 0.6712 | 0.7633 | 0.8516 | 0.7453 |
chat_steady_slow_normal_TCP | 0.8712 | 0.8122 | 0.8977 | 0.8735 | 0.8083 | 0.8433 | 0.7630 | 0.7723 | 0.7906 |
audio_spike_fast_normal_UDP | 0.7522 | 0.6130 | 0.7190 | 0.7302 | 0.5233 | 0.6234 | 0.7105 | 0.5150 | 0.6358 |
chat_spike_slow_normal_UDP | 0.8083 | 0.7434 | 0.7540 | 0.7141 | 0.6215 | 0.6523 | 0.6488 | 0.6276 | 0.6520 |
audio_burst_fast_normal_TCP | 0.7786 | 0.7556 | 0.7577 | 0.7212 | 0.7113 | 0.7417 | 0.6581 | 0.7066 | 0.7359 |
vedio_burst_slow_normal_UDP | 0.7570 | 0.7101 | 0.7246 | 0.7363 | 0.7234 | 0.7281 | 0.6529 | 0.7313 | 0.7160 |
vedio_spike_slow_normal_TCP | 0.7370 | 0.7072 | 0.716 | 0.7363 | 0.6063 | 0.6212 | 0.7226 | 0.5896 | 0.5568 |
Summary (Unseen classes) | 0.7702 | 0.7290 | 0.7380 | 0.7269 | 0.6656 | 0.6858 | 0.6706 | 0.6637 | 0.6651 |
Summary (All classes) | 0.8408 | 0.8005 | 0.8010 | 0.8059 | 0.7081 | 0.7238 | 0.7526 | 0.698 | 0.7017 |
Methods | Paramters | Training Time | Interfence Time | Overall Time | Performance (D1) | |||||
---|---|---|---|---|---|---|---|---|---|---|
Fine-Grained Classification | Zero-Shot Prediction | |||||||||
Accuracy | Recall | Precision | Accuracy | Recall | Precision | |||||
AG-ZSL | 62 MB | 1 | 1 | 2 | 0.9571 | 0.9613 | 0.9578 | 0.8408 | 0.8005 | 0.8010 |
TF | 6 MB | 0.93 | 0.95 | 1.88 | 0.9171 | 0.9257 | 0.9182 | 0.8059 | 0.7081 | 0.7238 |
FS-Net | 15 MB | 0.84 | 0.98 | 1.82 | 0.9133 | 0.9254 | 0.9168 | 0.7526 | 0.6980 | 0.7017 |
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. |
© 2025 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
Lu, Z.; Chang, Z.; He, M.; Song, L. Zero-Shot Traffic Identification with Attribute and Graph-Based Representations for Edge Computing. Sensors 2025, 25, 545. https://doi.org/10.3390/s25020545
Lu Z, Chang Z, He M, Song L. Zero-Shot Traffic Identification with Attribute and Graph-Based Representations for Edge Computing. Sensors. 2025; 25(2):545. https://doi.org/10.3390/s25020545
Chicago/Turabian StyleLu, Zikui, Zixi Chang, Mingshu He, and Luona Song. 2025. "Zero-Shot Traffic Identification with Attribute and Graph-Based Representations for Edge Computing" Sensors 25, no. 2: 545. https://doi.org/10.3390/s25020545
APA StyleLu, Z., Chang, Z., He, M., & Song, L. (2025). Zero-Shot Traffic Identification with Attribute and Graph-Based Representations for Edge Computing. Sensors, 25(2), 545. https://doi.org/10.3390/s25020545