# Ensemble-Based Hybrid Context-Aware Misbehavior Detection Model for Vehicular Ad Hoc Network

^{1}

^{2}

^{3}

^{*}

## Abstract

**:**

## 1. Introduction

## 2. Related Work

## 3. Materials and Methods

#### 3.1. Data Collection Phase

#### 3.2. Features Derivation Phase

#### 3.2.1. Data-Centric-Based Features

#### 3.2.2. Behavioral-Based Features Set

#### 3.3. Context Representation Phase

#### 3.4. Multifaceted Vehicles Evaluation and Pre-Detection Phase

#### 3.5. Ensemble Learning Phase

#### 3.6. Decision Phase

## 4. Performance Evaluation

#### 4.1. Experimental Setup

#### 4.1.1. Sample Selection

#### 4.1.2. Simulation of Environmental Noises

#### 4.1.3. Simulation of Message Losses

#### 4.1.4. Simulation of Misbehaving Vehicles

#### 4.2. Performance Metrics

## 5. Results

## 6. Discussion

## 7. Conclusions and Future Work

## Author Contributions

## Funding

## Acknowledgments

## Conflicts of Interest

## References

- WHO. 10 Facts on Global Road Safety. 2013. Available online: http://www.who.int/features/factfiles/roadsafety/en/ (accessed on 20 June 2019).
- Wahab, O.A.; Mourad, A.; Otrok, H.; Bentahar, J. CEAP: SVM-based intelligent detection model for clustered vehicular ad hoc networks. Expert Syst. Appl.
**2016**, 50, 40–54. [Google Scholar] [CrossRef] - Arnott, R.; de Palma, A.; Lindsey, R. Economics of a bottleneck. J. Urban Econ.
**1990**, 27, 111–130. [Google Scholar] [CrossRef] - Sweet, M. Does traffic congestion slow the economy? J. Plan. Lit.
**2011**, 26, 391–404. [Google Scholar] [CrossRef] - Williams, B.M.; Guin, A. Traffic Management Center Use of Incident Detection Algorithms: Findings of a Nationwide Survey. IEEE Trans. Intell. Transp. Syst.
**2007**, 8, 351–358. [Google Scholar] [CrossRef] - Vahdat-Nejad, H.; Ramazani, A.; Mohammadi, T.; Mansoor, W. A survey on context-aware vehicular network applications. Veh. Commun.
**2016**, 3, 43–57. [Google Scholar] [CrossRef] - Heijden, R.W.; Kargl, F. Open Issues in Differentiating Misbehavior and Anomalies for VANETs; Vehicular Lab, University of Luxembourg: Luxembourg, 2014. [Google Scholar]
- Santamaria, A.F.; Sottile, C.; De Rango, F.; Voznak, M. Road Safety Alerting System with Radar and GPS Cooperation in a VANET Environment. In Proceedings of the Wireless Sensing, Localization, and Processing Ix, Baltimore, MD, USA, 5–9 May 2014; Volume 9103. [Google Scholar]
- Uzcategui, R.; Acosta-Marum, G. Wave: A tutorial. IEEE Commun. Mag.
**2009**, 47, 126–133. [Google Scholar] [CrossRef] - Dietzel, S. Graph-Based Metrics for Insider Attack Detection in VANET Multihop Data Dissemination Protocols. IEEE Trans. Veh. Technol.
**2013**, 62, 1505–1518. [Google Scholar] [CrossRef] - Huang, C.M.; Lin, S.Y. Cooperative vehicle collision warning system using the vector-based approach with dedicated short range communication data transmission. IET Intell. Transp. Syst.
**2014**, 8, 124–134. [Google Scholar] [CrossRef] - Le, L.; Festag, A.; Baldessari, R.; Zhang, W. Vehicular wireless short-range communication for improving intersection safety. IEEE Commun. Mag.
**2009**, 47, 104–110. [Google Scholar] - Kato, S.; Tsugawa, S.; Tokuda, K.; Matsui, T.; Fujii, H. Vehicle control algorithms for cooperative driving with automated vehicles and intervehicle communications. IEEE Trans. Intell. Transp. Syst.
**2002**, 3, 155–161. [Google Scholar] [CrossRef] - Milan, V.; Shladover, S.E.; Spring, J.; Nowakowski, C.; Kawazoe, H.; Nakamura, M. Cooperative Adaptive Cruise Control in Real Traffic Situations. IEEE Trans. Intell. Transp. Syst.
**2014**, 15, 296–305. [Google Scholar] [CrossRef] - Li, L.; Wen, D.; Zheng, N.N.; Shen, L.C. Cognitive Cars: A New Frontier for ADAS Research. IEEE Trans. Intell. Transp. Syst.
**2012**, 13, 395–407. [Google Scholar] [CrossRef] - NHTSA. Vehicle Safety Communications Project Task 3 Final Report, Identify Intelligent Vehicle Safety Applications Enabled by Dsrc; US Department of Transportation: Washington, DC, USA, 2005.
- Stübing, H. Car-to-X Communication: System Architecture and Applications. In Multilayered Security and Privacy Protection in Car-to-X Networks; Springer Fachmedien Wiesbaden: Wiesbaden, Germany, 2013; pp. 9–19. [Google Scholar]
- Liu, K.; Lim, H.B.; Frazzoli, E.; Ji, H.; Lee, V.C.S. Improving positioning accuracy using GPS pseudorange measurements for cooperative vehicular localization. IEEE Trans. Veh. Technol.
**2014**, 63, 2544–2556. [Google Scholar] [CrossRef] - Sakiz, F.; Sen, S. A survey of attacks and detection mechanisms on intelligent transportation systems: VANETs and IoV. Ad Hoc Netw.
**2017**, 61, 33–50. [Google Scholar] [CrossRef] - Bissmeyer, N.; Michael, W.; Frank, K. Misbehavior Detection and Attacker Identification in Vehicular Ad-Hoc Networks. Ph.D. Thesis, Technische Universität Darmstadt, Darmstadt, Germany, 2014. [Google Scholar]
- Leinmuller, T.; Schoch, E.; Kargl, F.; Maihöfer, C. Influence of falsified position data on geographic ad-hoc routing. In Security and Privacy in Ad-hoc and Sensor Networks; Springer: Berlin, Germany, 2005; pp. 102–112. [Google Scholar]
- Leinmuller, T.; Schoch, E. Greedy routing in highway scenarios: The impact of position faking nodes. In Proceedings of the Workshop On Intelligent Transportation (WIT 2006), Hamburg, Germany, 14–15 March 2006. [Google Scholar]
- Grover, J.; Gaur, M.S.; Laxmi, V. Position Forging Attacks in Vehicular Ad Hoc Networks: Implementation, Impact and Detection. In Proceedings of the 7th International Wireless Communications and Mobile Computing Conference (IWCMC), Istanbul, Turkey, 4–8 July 2011. [Google Scholar]
- Blum, J.; Eskandarian, A. The threat of intelligent collisions. IT Prof.
**2004**, 6, 24–29. [Google Scholar] [CrossRef] - Lo, N.-W.; Tsai, H.-C. Illusion Attack on VANET Applications—A Message Plausibility Problem. In Proceedings of the IEEE Globecom Workshops, Washington, DC, USA, 26–30 November 2007. [Google Scholar]
- Yu, B.; Xu, C.Z.; Xiao, B. Detecting Sybil attacks in VANETs. J. Parallel Distrib. Comput.
**2013**, 73, 746–756. [Google Scholar] [CrossRef] - Kakkasageri, M.S.; Manvi, S.S. Information management in vehicular ad hoc networks: A review. J. Netw. Comput. Appl.
**2014**, 39, 334–350. [Google Scholar] [CrossRef] - Chen, S.; Wang, W.; van Zuylen, H. A comparison of outlier detection algorithms for ITS data. Expert Syst. Appl.
**2010**, 37, 1169–1178. [Google Scholar] [CrossRef] - Firl, J.; Stübing, H.; Huss, S.A.; Stiller, C. MARV-X: Applying Maneuver Assessment for Reliable Verification of Car-to-X Mobility Data. IEEE Trans. Intell. Transp. Syst.
**2013**, 14, 1301–1312. [Google Scholar] [CrossRef] - Van der Heijden, R.W.; Stefan, D.; Tim, L.; Frank, K. Survey on Misbehavior Detection in Cooperative Intelligent Transportation Systems. IEEE Commun. Surv. Tutor.
**2019**, 21, 779–811. [Google Scholar] [CrossRef] - Ghaleb, F.A.; Zainal, A.; Rassam, M.A.; Saeed, F. Driving-situation-aware adaptive broadcasting rate scheme for vehicular ad hoc network. J. Intell. Fuzzy Syst.
**2018**, 35, 423–438. [Google Scholar] [CrossRef] - Zhengming, L.; Chunxiao, C.; Wong, D. AWF-NA: A Complete Solution for Tampered Packet Detection in VANETs. In Proceedings of the IEEE GLOBECOM 2008—2008 Global Telecommunications Conference, New Orleans, LO, USA, 30 November–4 December 2008. [Google Scholar]
- Hortelano, J.; Ruiz, J.C.; Manzoni, P. Evaluating the Usefulness of Watchdogs for Intrusion Detection in VANETs. In Proceedings of the 2010 IEEE International Conference on Communications Workshops, Capetown, South Africa, 23–27 May 2010. [Google Scholar]
- Daeinabi, A.; Rahbar, A.G. Detection of malicious vehicles (DMV) through monitoring in Vehicular Ad-Hoc Networks. Multimed. Tools Appl.
**2013**, 66, 325–338. [Google Scholar] [CrossRef] - Wahab, O.A.; Otrok, H.; Mourad, A. A cooperative watchdog model based on Dempster-Shafer for detecting misbehaving vehicles. Comput. Commun.
**2014**, 41, 43–54. [Google Scholar] [CrossRef] - Zhang, Y.; Lazos, L.; Kozma, W. AMD: Audit-Based Misbehavior Detection in Wireless Ad Hoc Networks. IEEE Trans. Mob. Comput.
**2016**, 15, 1893–1907. [Google Scholar] [CrossRef] - Ho, Y.-H.; Lin, C.-H.; Chen, L.-J. On-demand Misbehavior Detection for Vehicular Ad Hoc Network. Int. J. Distrib. Sens. Netw.
**2016**, 12, 1550147716673928. [Google Scholar] [CrossRef] - Ghosh, M.; Varghese, A.; Gupta, A.; Kherani, A.A.; Muthaiah, S.N. Detecting misbehaviors in VANET with integrated root-cause analysis. Ad Hoc Netw.
**2010**, 8, 778–790. [Google Scholar] [CrossRef] - Grover, J.; Laxmi, V.; Gaur, M.S. Misbehavior Detection Based on Ensemble Learning in VANET. In International Conference on Advanced Computing, Networking and Security. ADCONS 2011, Surathkal, India, December 16-18, 2011, Revised Selected Papers; Thilagam, P.S., Pais, A.R., Chandrasekaran, K., Balakrishnan, N., Eds.; Springer: Berlin/Heidelberg, Germany, 2012; pp. 602–611. [Google Scholar]
- Hussain, R.; Kim, S.; Oh, H. Privacy-Aware VANET Security: Putting Data-Centric Misbehavior and Sybil Attack Detection Schemes into Practice. In Information Security Applications; Lee, D., Yung, M., Eds.; Springer: Berlin/Heidelberg, Germany, 2012; pp. 296–311. [Google Scholar]
- Zaidi, K.; Milojevic, M.; Rakocevic, V.; Rajarajan, M. Data-centric Rogue Node Detection in VANETs. In Proceedings of the IEEE 13th International Conference on Trust, Security and Privacy in Computing and Communications, Beijing, China, 24–26 September 2014. [Google Scholar]
- Ruj, S.; Cavenaghi, M.A.; Huang, Z.; Nayak, A.; Stojmenovic, I. On data-centric misbehavior detection in VANETs. In Proceedings of the IEEE Vehicular Technology Conference (VTC Fall), San Francisco, CA, USA, 5–8 September 2011. [Google Scholar]
- Raya, M.; Papadimitratos, P.; Gligor, V.D.; Hubaux, J.-P. On Data-Centric Trust Establishment in Ephemeral Ad Hoc Networks. In Proceedings of the IEEE INFOCOM 2008—The 27th Conference on Computer Communications, Phoenix, AZ, USA, 13–18 April 2008. [Google Scholar]
- Zaidi, K.; Milojevic, M.B.; Rakocevic, V.; Nallanathan, A.; Rajarajan, M. Host-Based Intrusion Detection for VANETs: A Statistical Approach to Rogue Node Detection. IEEE Trans. Veh. Technol.
**2016**, 65, 6703–6714. [Google Scholar] [CrossRef] - Grover, J.; Kumar, D.; Sargurunathan, M.; Gaur, M.S.; Laxmi, V. Performance Evaluation and Detection of Sybil Attacks in Vehicular Ad-Hoc Networks. Recent Trends Netw. Secur. Appl.
**2010**, 89, 473–482. [Google Scholar] - Dietzel, S.; van der Heijden, R.; Decke, H.; Kargl, F. A flexible, subjective logic-based framework for misbehavior detection in V2V networks. In Proceedings of the IEEE 15th International Symposium on a World of Wireless, Mobile and Multimedia Networks (WoWMoM), Sydney, Australia, 19 June 2014. [Google Scholar]
- Golle, P.; Greene, D.; Staddon, J. Detecting and correcting malicious data in VANETs. In Proceedings of the 1st ACM International Workshop on Vehicular ad hoc Networks, Philadelphia, PA, USA, 1 October 2004; pp. 29–37. [Google Scholar]
- Yan, G.J.; Olariu, S.; Weigle, M.C. Providing Location Security in Vehicular Ad Hoc Networks. IEEE Wirel. Commun.
**2009**, 16, 48–53. [Google Scholar] [CrossRef] - Bissmeyer, N.; Njeukam, J.; Petit, J.; Bayarou, K.M. Central misbehavior evaluation for VANETs based on mobility data plausibility. In Proceedings of the Ninth ACM International Workshop on Vehicular Inter-networking, Systems, and Applications, Low Wood Bay, Lake District, UK, 25 June 2012; pp. 73–82. [Google Scholar]
- Leinmuller, T.; Schoch, E.; Kargl, F.; Maihöfer, C. Decentralized position verification in geographic ad hoc routing. Secur. Commun. Netw.
**2010**, 3, 289–302. [Google Scholar] [CrossRef] - Bissmeyer, N.; Stresing, C.; Bayarou, K.M. Intrusion detection in VANETs through verification of vehicle movement data. In Proceedings of the IEEE Vehicular Networking Conference (VNC), Jersey City, NJ, USA, 13–15 December 2010. [Google Scholar]
- Bissmeyer, N.; Schröder, K.H.; Petit, J.; Mauthofer, S.; Bayarou, K.M. Short paper: Experimental analysis of misbehavior detection and prevention in VANETs. In Proceedings of the Fifth IEEE Vehicular Networking Conference (VNC), Boston, MA, USA, 16–18 December 2013; pp. 198–201. [Google Scholar]
- Palomar, E.; de Fuentes, J.M.; González-Tablas, A.I.; Alcaide, A. Hindering false event dissemination in VANETs with proof-of-work mechanisms. Transp. Res. Part C Emerg. Technol.
**2012**, 23, 85–97. [Google Scholar] [CrossRef] - Van der Heijden, R.W.; Dietzel, S.; Leinmüller, T.; Kargl, F. Survey on Misbehavior Detection in Cooperative Intelligent Transportation Systems. arXiv
**2016**, arXiv:1610.06810. [Google Scholar] [CrossRef] - Schmidt, R.K.; Leinmüller, T.; Schoch, E.; Held, A.; Schäfer, G. Vehicle behavior analysis to enhance security in vanets. In Proceedings of the 4th IEEE Vehicle-to-Vehicle Communications Workshop (V2VCOM2008), Eindhoven, The Netherlands, 3 June 2008. [Google Scholar]
- Leinmuller, T.; Schoch, E.; Kargl, F. Position verification approaches for vehicular ad hoc networks. IEEE Wirel. Commun.
**2006**, 13, 16–21. [Google Scholar] [CrossRef] - Jaeger, A.; Bißmeyer, N.; Stübing, H.; Huss, S.A. A Novel Framework for Efficient Mobility Data Verification in Vehicular Ad-hoc Networks. Int. J. Intell. Transp. Syst. Res.
**2012**, 10, 11–21. [Google Scholar] [CrossRef] - Stübing, H.; Jaeger, A.; Schmidt, C.; Huss, S.A. Verifying mobility data under privacy considerations in car-to-x communication. In Proceedings of the 17th ITS World Congress, Busan, Korea, 25–29 October 2010. [Google Scholar]
- Stübing, H.; Firl, J.; Huss, S.A. A two-stage verification process for Car-to-X mobility data based on path prediction and probabilistic maneuver recognition. In Proceedings of the 2011 IEEE Vehicular Networking Conference (VNC), Amsterdam, The Netherlands, 14–16 November 2011. [Google Scholar]
- Ghaleb, F.A.; Razzaque, M.A.; Isnin, I.F. Security and privacy enhancement in VANETs using mobility pattern. In Proceedings of the 2013 Fifth International Conference on Ubiquitous and Future Networks (ICUFN), Da Nang, Vietnam, 2–5 July 2013. [Google Scholar]
- Firl, J.; Stübing, H.; Huss, S.A.; Stiller, C. Predictive maneuver evaluation for enhancement of Car-to-X mobility data. In Proceedings of the IEEE Intelligent Vehicles Symposium (IV), Alcala de Henares, Spain, 3–7 June 2012. [Google Scholar]
- Ghaleb, F.A.; Zainal, A.; Rassam, M.A. Mobility information estimation algorithm using Kalman-filter for vehicular ad hoc networks. Int. J. Inf. Comput. Secur.
**2016**, 8, 221–240. [Google Scholar] [CrossRef] - Stübing, H. Facility Layer Security: Mobility Data Verification. In Multilayered Security and Privacy Protection in Car-to-X Networks; Springer Fachmedien Wiesbaden: Berlin, Germany, 2013; pp. 45–80. [Google Scholar]
- Jwo, D.-J.; Cho, T.-S. A practical note on evaluating Kalman filter performance optimality and degradation. Appl. Math. Comput.
**2007**, 193, 482–505. [Google Scholar] [CrossRef] - Punzo, V.; Borzacchiello, M.T.; Ciuffo, B. On the assessment of vehicle trajectory data accuracy and application to the Next Generation SIMulation (NGSIM) program data. Transp. Res. Part C Emerg. Technol.
**2011**, 19, 1243–1262. [Google Scholar] [CrossRef] - Huang, H.; Zhang, D.; Zhu, Y.; Li, M.; Wu, M.-Y. A Metropolitan Taxi Mobility Model from Real GPS Traces. J. Univers. Comput. Sci.
**2012**, 18, 1072–1092. [Google Scholar] - Ghaleb, F.A.; Maarof, M.A.; Zainal, A.; Al-Rimy, B.A.S.; Saeed, F.; Al-Hadhrami, T. Hybrid and Multifaceted Context-Aware Misbehavior Detection Model for Vehicular Ad Hoc Network. IEEE Access
**2019**, 7, 159119–159140. [Google Scholar] [CrossRef] - Ghaleb, F.A.; Zainal, A.; Rassam, M.A.; Mohammed, F. An effective misbehavior detection model using artificial neural network for vehicular ad hoc network applications. In Proceedings of the 2017 IEEE Conference on Application, Information and Network Security (AINS), Miri, Malaysia, 13–14 November 2017. [Google Scholar]
- Ghaleb, F.A.; Maarof, M.A.; Zainal, A.; Rassam, M.A.; Saeed, F.; Alsaedi, M. Context-Aware Data-Centric Misbehaviour Detection Scheme for Vehicular Ad Hoc Networks using Sequential Analysis of the Temporal and Spatial Correlation of the Consistency between the Cooperative Awareness Messages. Veh. Commun.
**2019**, 20, 100186. [Google Scholar] [CrossRef] [Green Version] - Ghaleb, F.A.; Zainal, A.; Rassam, M.A.; Abraham, A. Improved vehicle positioning algorithm using enhanced innovation-based adaptive Kalman filter. Pervasive Mob. Comput.
**2017**, 40, 139–155. [Google Scholar] [CrossRef] - Engoulou, R.G.; Bellaïche, M.; Pierre, S.; Quintero, A. VANET security surveys. Comput. Commun.
**2014**, 44, 1–13. [Google Scholar] [CrossRef] - Boukerche, A.; Oliveira, H.A.B.F.; Nakamura, E.F.; Loureiro, A.A.F. Localization systems for wireless sensor networks. IEEE Wirel. Commun.
**2007**, 14, 6–12. [Google Scholar] [CrossRef] - Krell, M.M.; Tabie, M.; Woehrle, H.; Kirchner, E.A. Memory and Processing Efficient Formula for Moving Variance Calculation in EEG and EMG Signal Processing. In Proceedings of the International Congress on Neurotechnology, Electronics and Informatics (NEUROTECHNIX-2013), Vilamoura, Portugal, 19–20 September 2013. [Google Scholar]
- FHWA. Next Generation Simulation (NGSIM) Vehicle Trajctories Dataset. 2006. Available online: http://ngsim-community.org/ (accessed on 17 December 2015).
- Hou, Y.; Edara, P.; Sun, C. Modeling Mandatory Lane Changing Using Bayes Classifier and Decision Trees. IEEE Trans. Intell. Transp. Syst.
**2014**, 15, 647–655. [Google Scholar] [CrossRef] - Tian, X.Y.; Liu, Y.H.; Wang, J.; Deng, W.W.; Oh, H. Computational Security for Context-Awareness in Vehicular Ad-Hoc Networks. IEEE Access
**2016**, 4, 5268–5279. [Google Scholar] [CrossRef] - Erskine, S.K.; Elleithy, K.M. Real-Time Detection of DoS Attacks in IEEE 802.11 p Using Fog Computing for a Secure Intelligent Vehicular Network. Electronics
**2019**, 8, 776. [Google Scholar] [CrossRef] [Green Version] - Weideman, J.A.; Reddy, S.C. A MATLAB differentiation matrix suite. ACM Trans. Math. Softw.
**2000**, 26, 465–519. [Google Scholar] [CrossRef] [Green Version] - Hartigan, J.A.; Wong, M.A. Algorithm AS 136: A k-means clustering algorithm. J. R. Stat. Soc. Ser. C (Appl. Stat.)
**1979**, 28, 100–108. [Google Scholar] [CrossRef] - Drawil, N.M.; Basir, O. Intervehicle-Communication-Assisted Localization. IEEE Trans. Intell. Transp. Syst.
**2010**, 11, 678–691. [Google Scholar] [CrossRef] - Parker, R.; Valaee, S. Vehicular Node Localization Using Received-Signal-Strength Indicator. IEEE Trans. Veh. Technol.
**2007**, 56, 3371–3380. [Google Scholar] [CrossRef] - Qiu, H.J.F.; Ho, I.W.-H.; Tse, C.K.; Xie, Y. A Methodology for Studying 802.11p VANET Broadcasting Performance with Practical Vehicle Distribution. IEEE Trans. Veh. Technol.
**2015**, 64, 4756–4769. [Google Scholar] [CrossRef] - Mcquighan, P. SIMULATING THE POISSON PROCESS; Department of Mathematics, University of Chicago: Chicago, IL, USA, 2010. [Google Scholar]
- Park, Y.; Kim, H. Application-Level Frequency Control of Periodic Safety Messages in the IEEE WAVE. IEEE Trans. Veh. Technol.
**2012**, 61, 1854–1862. [Google Scholar] [CrossRef] - Ghafoor, K.; Lloret, J.; Bakar, K.A.; Sadiq, A.S.; Mussa, S.A.B. Beaconing Approaches in Vehicular Ad Hoc Networks: A Survey. Wirel. Pers. Commun.
**2013**, 73, 885–912. [Google Scholar] [CrossRef] - Ma, X.; Zhang, J.; Yin, X.; Trivedi, K.S. Design and Analysis of a Robust Broadcast Scheme for VANET Safety-Related Services. IEEE Trans. Veh. Technol.
**2012**, 61, 46–61. [Google Scholar] [CrossRef] - Nikaein, N.; Kanti, S.D.; Marecar, I.; Bonnet, C. Application Distribution Model and Related Security Attacks in VANET. In Proceedings of the International Conference on Graphic and Image Processing (Icgip 2012), Singapore, 5–7 October 2013. [Google Scholar]
- Chen, Y.-M.; Wei, Y.-C. A beacon-based trust management system for enhancing user centric location privacy in VANETs. J. Commun. Netw.
**2013**, 15, 153–163. [Google Scholar] [CrossRef]

**Figure 1.**The proposed misbehavior detection system model (ensemble-based hybrid context-aware misbehavior detection system (EHCA-MDS)).

**Figure 5.**Pseudocode for features derivation, context reference model construction, and the set of classification rules (HCA-MDS and DCA-MDS).

**Figure 7.**Average effectiveness of EHCA-MDS, HCA-MDS, CA-MDS, ECT-MDS and MDS baseline models in terms of the: (

**a**) Accuracy, (

**b**) False Positive Rate (FPR), (

**c**) Detection Rate (DR), and (

**d**) F-Measure.

**Figure 8.**Detailed comparison of EHCA-EC-MDS in terms of the: (

**a**) Accuracy, (

**b**) False Positive Rate (FPR), (

**c**) Detection Rate (DR), and (

**d**) F-Measure.

DFS# | Type | Name | Description | |
---|---|---|---|---|

DC1 | ${f}_{1}$ | Consistency | Latitude prediction error | Consistency-based feature: The difference between the received latitude with the predicted one using a Kalman filter in the DSA-ABR algorithm. |

DC2 | ${f}_{2}$ | Longitude prediction error | The difference between the received longitudes with the predicted one using a Kalman filter in the DSA-ABR algorithm. | |

DC3 | ${f}_{3}$ | Latitude speed Prediction error | Speeds errors towards latitude: the rate of latitude prediction error | |

DC4 | ${f}_{4}$ | Longitude speed prediction error | Predicted speed errors towards longitude: the rate of change of longitude prediction error | |

DC5 | ${f}_{5}$ | Plausibility | Communication Range | It is a plausibility-based feature, which is the distance between the sender and receiver. The distance between two vehicles can be calculated using the Euclidean distance formula distance function (e.g., Euclidean distance) [72]. |

DC6 | ${f}_{6}$ | Vehicle appearance distance | Similar to ${f}_{5}$ but it is calculated one time when a new vehicle enters the communication range of the subject vehicle | |

DC7 | ${f}_{7}$ | Overlapping Frequency | The number of overlap times with the neighboring vehicles |

BF# | Feature Name | Description | |
---|---|---|---|

BF1 | ${f}_{8}$ | Connection Length | The time difference between the first received mobility message from each neighboring vehicle and the current time epoch. |

BF2 | ${f}_{9}$ | Received Messages | The total number of messages that are received from each neighbor. |

BF3 | ${f}_{10}$ | Broadcasting Rate | The moving average of the number of received messages divided by the connection length. |

BF4 | ${f}_{11}$ | Broadcasting delay | The moving average of the differences between time of receiving the messages by the neighboring vehicles and their creation time in the subject vehicle. |

BF5 | ${f}_{12}$ | Jerk acceleration | The rate of change of acceleration |

BF6 | ${f}_{13}$ | Speed deviation | The divergence between the sender’s average speed and the median speed of all neighboring vehicles |

Symbol | Description |
---|---|

${f}_{e\left(k\right)}^{{v}_{i}}$ | Consistency features: innovation errors of vehicle (${v}_{i})$ at time epoch ($k$) |

${y}_{k}^{{v}_{i}}$ | Received mobility data |

${\stackrel{\u02c7}{y}}_{k|k-\tau \left(i\right)}^{{v}_{i}}$ | Predicted mobility data by Kalman filter |

${d}_{\left(i,j\right)}$ | The distance between the vehicle ${v}_{i}$ at position ${p}_{i}\left({x}_{i},{y}_{i}\right)$ and vehicle ${v}_{j}$ at position ${p}_{j}\left({x}_{j},{y}_{j}\right)$ |

$\tau \left(i\right)$ | The time epoch of last received mobility data |

${f}_{cr\left(k\right)}^{{v}_{i}}$ | Range-based features: the distance between the current vehicle and the neighboring vehicle |

$o{s}_{k}^{{v}_{i}}$ | Overlapping-based feature |

${d}_{min\left(i,j\right)}$ | The minimum accepted distance between vehicles ${v}_{i}and$ ${v}_{j}$ |

${f}_{j\left(k\right)}^{{v}_{i}}$ | Feature number $j$ for vehicle ${v}_{i}$ at time epoch $k$ |

${f}_{b\left(k\right)}^{{v}_{i}}$ | Behavioral features of the vehicle ${v}_{i}$ at time epoch $k$ |

$CR{M}_{\left(k\right)}$ | Context-reference model parameters |

${\varnothing}_{k}$ | Median of the vehicles’ temporal summaries |

${\delta}_{k}$ | The median absolute deviation of vehicles’ temporal summaries |

$HU{B}_{k}$ | Hampel upper bound, also called $CRU{B}_{\left(k\right)}$ context reference upper bound |

$HL{B}_{k}$ | Hampel lower bound, also called $CRL{B}_{\left(k\right)}$ context-reference lower bound |

$\beta $ | Tuning parameters |

${z}_{{f}_{j}\left(k\right)}^{{v}_{i}}$ | Vehicle ${v}_{i}$ Hampel-based Z-score with respect to feature ${f}_{j\left(k\right)}^{{v}_{i}}$ at time epoch $k$ |

${o}_{{f}_{j}\left(k\right)}^{{v}_{i}}$ | Classification rule |

Dataset | Host Vehicle Id | Vehicle Regime | Average Speed (m/s) | Duration (s) | Dataset Size CAMs | Total Neighbors |
---|---|---|---|---|---|---|

DS1 | 13 | Free-Flow | 16.8 | 94.8 | 113,258 | 177 |

DS2 | 252 | Free-Flow | 23.3 | 55.8 | 155,908 | 255 |

DS3 | 455 | Free-Flow | 21.6 | 60.3 | 145,904 | 260 |

DS4 | 2280 | Free-Flow | 24.0 | 54.1 | 197,511 | 270 |

DS5 | 5 | Lane-Change | 22.4 | 70.2 | 80,568 | 119 |

DS6 | 1133 | Lane-Change | 31.7 | 39.3 | 107,565 | 214 |

DS7 | 1687 | Lane-Change | 22.4 | 76.5 | 110,051 | 314 |

DS8 | 1 | Lane-Change | 18.0 | 88.4 | 88,971 | 134 |

DS9 | 268 | Flowing-Mode | 26.2 | 58.5 | 156,941 | 255 |

DS10 | 1066 | Flowing-Mode | 33.0 | 47.5 | 111,305 | 225 |

DS11 | 1964 | Flowing-Mode | 21.5 | 72.9 | 223,211 | 317 |

DS12 | 7 | Flowing-Mode | 22.5 | 71.1 | 85,244 | 127 |

DS13 | 1593 | Flowing-Mode | 21.1 | 74.2 | 186,260 | 294 |

DS14 | 2885 | Random-Flow | 16.5 | 94.5 | 150,127 | 200 |

DS15 | 1899 | Random-Flow | 19.9 | 78.8 | 231,867 | 331 |

DS16 | RSU | Mixed | 28.0 | 57.3 | 479,823 | 284 |

Model | Accuracy% | FPR% | DR% | Precision% | Recall% | F-Measure% |
---|---|---|---|---|---|---|

EHCA–MDS (Proposed) | 97.01 | 1.19 | 90.45 | 95.32 | 90.45 | 92.82 |

HCA–MDS (Proposed) | 93.51 | 4.45 | 86.11 | 85.00 | 86.11 | 84.44 |

DCA–MDS (Proposed) | 90.98 | 2.33 | 66.18 | 89.19 | 66.18 | 75.05 |

Bissmeyers’ ECT-MDS [20] | 74.79 | 2.98 | 30.65 | 83.50 | 30.65 | 44.49 |

Stübing’s MDS [58] | 87.37 | 4.79 | 62.55 | 86.91 | 62.55 | 71.60 |

Model | Accuracy | FPR | DR | Precision | Recall | F-Measure |
---|---|---|---|---|---|---|

HCA-MDS (Proposed) | 3.5 | −3.26 | 4.34 | 10.32 | 4.34 | 8.38 |

(3.74%) | (73.26%) | (5.04%) | (12.14%) | (5.04%) | (9.92%) | |

DCA-MDS (Proposed) | 6.03 | −1.14 | 24.27 | 6.13 | 24.27 | 17.77 |

(36.67%) | (36.67%) | (36.67%) | (36.67%) | (36.67%) | (36.67%) | |

Bissmeyers’ ECT-MDS [20] | 22.22 | −1.79 | 59.80 | 11.82 | 59.80 | 48.33 |

(29.71%) | (60.07%) | (195.11%) | (14.16%) | (195.11%) | (108.63%) | |

Stübing’s MDS baseline [58] | 9.64 | −3.60 | 27.90 | 8.41 | 27.90 | 21.22 |

(11.03%) | (75.16%) | (44.60%) | (9.68%) | (44.60%) | (29.64%) |

Model | Ensemble | Hybrid * | Context-Aware | Data-Centric | Trust-Based | Performance |
---|---|---|---|---|---|---|

EHCA-MDS | √ | √ | √ | √ | 92.82 | |

HCA-MDS | √ | √ | √ | 84.44 | ||

DCA-MDS | √ | √ | √ | 75.05 | ||

ECT-MDS | √ | √ | √ | 71.60 | ||

MDS Baseline | √ | 44.49 |

© 2019 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 (http://creativecommons.org/licenses/by/4.0/).

## Share and Cite

**MDPI and ACS Style**

Ghaleb, F.A.; Maarof, M.A.; Zainal, A.; Al-rimy, B.A.S.; Alsaeedi, A.; Boulila, W.
Ensemble-Based Hybrid Context-Aware Misbehavior Detection Model for Vehicular Ad Hoc Network. *Remote Sens.* **2019**, *11*, 2852.
https://doi.org/10.3390/rs11232852

**AMA Style**

Ghaleb FA, Maarof MA, Zainal A, Al-rimy BAS, Alsaeedi A, Boulila W.
Ensemble-Based Hybrid Context-Aware Misbehavior Detection Model for Vehicular Ad Hoc Network. *Remote Sensing*. 2019; 11(23):2852.
https://doi.org/10.3390/rs11232852

**Chicago/Turabian Style**

Ghaleb, Fuad A., Mohd Aizaini Maarof, Anazida Zainal, Bander Ali Saleh Al-rimy, Abdullah Alsaeedi, and Wadii Boulila.
2019. "Ensemble-Based Hybrid Context-Aware Misbehavior Detection Model for Vehicular Ad Hoc Network" *Remote Sensing* 11, no. 23: 2852.
https://doi.org/10.3390/rs11232852