scispace - formally typeset
Search or ask a question
Author

Bernd Meijerink

Bio: Bernd Meijerink is an academic researcher from University of Twente. The author has contributed to research in topics: Geocast & Shortest-path tree. The author has an hindex of 2, co-authored 5 publications receiving 11 citations.

Papers
More filters
Proceedings ArticleDOI
13 Jun 2019
TL;DR: This paper discusses how information communicated through vehicular networking can be used for controlling an autonomous vehicle in a multi-lane highway environment and proposes directions for additional research to improve the performance of the driving algorithm.
Abstract: Most of the research in automated driving currently involves using the on-board sensors on the vehicle to collect information regarding surrounding vehicles to maneuver around them. In this paper we discuss how information communicated through vehicular networking can be used for controlling an autonomous vehicle in a multi-lane highway environment. A driving algorithm is designed using deep Q learning, a type of reinforcement learning. In order to train and test driving algorithms, we deploy a simulated traffic system, using SUMO (Simulation of Urban Mobility). The performance of the driving algorithm is tested for perfect knowledge regarding surrounding vehicles. Furthermore, the impact of limited communication range and random packet loss is investigated. Currently the performance of the driving algorithm is far from ideal with the collision ratios being quite high. We propose directions for additional research to improve the performance of the algorithm.

11 citations

Journal ArticleDOI
TL;DR: This paper presents and implements two algorithms for geographic routing that are based purely on distance-vector data and another, more complicated algorithm based on path data, and shows that the algorithms converge relatively quickly following link drops.

4 citations

Proceedings ArticleDOI
01 Dec 2019
TL;DR: This paper proposes a slightly modified CBF algorithm for road side infrastructure to enable infrastructure assisted forwarding for geocast messages, without modifying theCBF algorithm in the vehicles.
Abstract: Geocast is an important forwarding method for vehicular networks. One standard of vehicular communication is ETSI ITS-G5 GeoNetworking. One of the forwarding methods for geocast in this standard is Contention Based Forwarding (CBF). CBF is dependent on a favourable vehicle distribution to forward messages over multiple hops. A method to extend the effective range of vehicles is to use road side infrastructure to help forward messages. We propose a slightly modified CBF algorithm for road side infrastructure to enable infrastructure assisted forwarding for geocast messages, without modifying the CBF algorithm in the vehicles. In this paper we show that such a relatively small modification can significantly increase delivery rates while also reducing wireless load and delivery delays.

2 citations

Posted Content
TL;DR: This paper designs an algorithm that can deliver shortest path tree like forwarding while relying purely on distributed data without central knowledge, and presents two algorithms based purely on distance vector data and path data.
Abstract: Geocast is the concept of sending data packets to nodes in a specified geographical area instead of nodes with a specific address. To route geocast messages to their destination we need a geographic routing algorithm that can route packets efficiently to the devices inside the destination area. Our goal is to design an algorithm that can deliver shortest path tree like forwarding while relying purely on distributed data without central knowledge. In this paper, we present two algorithms for geographic routing. One based purely on distance vector data, and one more complicated algorithm based on path data. In our evaluation, we show that our purely distance vector based algorithm can come close to shortest path tree performance when a small number of routers are present in the destination area. We also show that our path based algorithm can come close to the performance of a shortest path tree in almost all geocast situations.

2 citations

01 Jan 2016
TL;DR: In this article, the eDNS protocol is extended with nearest neighbor resolution support, and a prototype server is developed that uses bounding box propagation between servers for delegation, and experiments confirm that distributing location records over multiple servers improves performance.
Abstract: In the domain of vehicular networking, it is of significant relevance to be able to address vehicles based on their geographical position rather than the network address. The integration of geocasting (i.e. the dissemination of messages to all nodes within a specific geographical region) into the existing addressing scheme of the Internet is challenging, due to its logical hierarchy. One solution to Internet-based geographical addressing is eDNS, an extension to the DNS protocol. It adds support for querying geographical locations as a supplement to logical domain names. In this work, eDNS is extended with nearest neighbor resolution support, and further, a prototype server is developed that uses bounding box propagation between servers for delegation. Our experiments confirm that distributing location records over multiple servers improves performance.

Cited by
More filters
Journal ArticleDOI
TL;DR: A comprehensive survey of the interactions between resilient CPS using ML and resilient ML when applied in CPS can be found in this article, which concludes with a number of research trends and promising future research directions.
Abstract: Cyber Physical Systems (CPS) are characterized by their ability to integrate the physical and information or cyber worlds. Their deployment in critical infrastructure have demonstrated a potential to transform the world. However, harnessing this potential is limited by their critical nature and the far reaching effects of cyber attacks on human, infrastructure and the environment. An attraction for cyber concerns in CPS rises from the process of sending information from sensors to actuators over the wireless communication medium, thereby widening the attack surface. Traditionally, CPS security has been investigated from the perspective of preventing intruders from gaining access to the system using cryptography and other access control techniques. Most research work have therefore focused on the detection of attacks in CPS. However, in a world of increasing adversaries, it is becoming more difficult to totally prevent CPS from adversarial attacks, hence the need to focus on making CPS resilient. Resilient CPS are designed to withstand disruptions and remain functional despite the operation of adversaries. One of the dominant methodologies explored for building resilient CPS is dependent on machine learning (ML) algorithms. However, rising from recent research in adversarial ML, we posit that ML algorithms for securing CPS must themselves be resilient. This paper is therefore aimed at comprehensively surveying the interactions between resilient CPS using ML and resilient ML when applied in CPS. The paper concludes with a number of research trends and promising future research directions. Furthermore, with this paper, readers can have a thorough understanding of recent advances on ML-based security and securing ML for CPS and countermeasures, as well as research trends in this active research area.

68 citations

Journal ArticleDOI
TL;DR: A comprehensive survey of the interactions between resilient CPS using ML and resilient ML when applied in CPS can be found in this article, which concludes with a number of research trends and promising future research directions.
Abstract: Cyber Physical Systems (CPS) are characterized by their ability to integrate the physical and information or cyber worlds. Their deployment in critical infrastructure have demonstrated a potential to transform the world. However, harnessing this potential is limited by their critical nature and the far reaching effects of cyber attacks on human, infrastructure and the environment. An attraction for cyber concerns in CPS rises from the process of sending information from sensors to actuators over the wireless communication medium, thereby widening the attack surface. Traditionally, CPS security has been investigated from the perspective of preventing intruders from gaining access to the system using cryptography and other access control techniques. Most research work have therefore focused on the detection of attacks in CPS. However, in a world of increasing adversaries, it is becoming more difficult to totally prevent CPS from adversarial attacks, hence the need to focus on making CPS resilient. Resilient CPS are designed to withstand disruptions and remain functional despite the operation of adversaries. One of the dominant methodologies explored for building resilient CPS is dependent on machine learning (ML) algorithms. However, rising from recent research in adversarial ML, we posit that ML algorithms for securing CPS must themselves be resilient. This article is therefore aimed at comprehensively surveying the interactions between resilient CPS using ML and resilient ML when applied in CPS. The paper concludes with a number of research trends and promising future research directions. Furthermore, with this article, readers can have a thorough understanding of recent advances on ML-based security and securing ML for CPS and countermeasures, as well as research trends in this active research area.

57 citations

Patent
13 Jun 2007
TL;DR: A network, such as wired and/or wireless LAN, is configured to have both point-to-point and point- to-multipoint connections.
Abstract: A network, such as wired and/or wireless LAN, is configured to have both point-to-point and point-to-multipoint connections. The point-to-multipoint connection(s) is used to communicate information between a plurality of the stations (or modem, or transceivers) in the network, whereas the point-to-point connection(s) are used to communicate information between only 2 stations in the network with the ability to, for example, maximize performance (rate/reach/BER/latency/etc) between those two stations. A master station allocates one or more frequency bands to the various point-to-multipoint and point-to-point connections.

24 citations

Journal ArticleDOI
TL;DR: This paper provides a comprehensive literature survey of the intersection between machine learning for autonomous driving and vehicular communications, explaining how vehicle-to-vehicle (V2V) and vehicle- to-everything ( V2X) communications are used to improve machine learning in AVs, answering five major questions regarding such systems.
Abstract: By enabling autonomous vehicles (AVs) to share data while driving, 5G vehicular communications allow AVs to collaborate on solving common autonomous driving tasks. AVs often rely on machine learning models to perform such tasks; as such, collaboration requires leveraging vehicular communications to improve the performance of machine learning algorithms. This paper provides a comprehensive literature survey of the intersection between machine learning for autonomous driving and vehicular communications. Throughout the paper, we explain how vehicle-to-vehicle (V2V) and vehicle-to-everything (V2X) communications are used to improve machine learning in AVs, answering five major questions regarding such systems. These questions include: 1) How can AVs effectively transmit data wirelessly on the road? 2) How do AVs manage the shared data? 3) How do AVs use shared data to improve their perception of the environment? 4) How do AVs use shared data to drive more safely and efficiently? and 5) How can AVs protect the privacy of shared data and prevent cyberattacks? We also summarize data sources that may support research in this area and discuss the future research potential surrounding these five questions.

23 citations

Journal ArticleDOI
TL;DR: This survey provided the technical direction for researchers on routing protocols for VANET using QoS using the major techniques in cross-layer protocol design and various performance parameters used in QoS routing protocols.
Abstract: VANET (Vehicular Ad Hoc Network) is a significant term in ITS (intelligent transportation systems). VANETs are also mentioned as ITN (intelligent transportation Networks), which are used to enhance road safety in growing technology. The connectivity of nodes is a challenging one because of its high mobility and the sparse network connectivity must be handled properly during its initial deployment of a VANET for avoiding accidents. Quality of service (QoS) in VANET becomes a significant term because of its increasing dare about unique features, like poor link quality, high mobility, and inadequate transporting distance. Routing is the foremost issue in the wireless ad hoc network, which is used to transmit data packets significantly. This paper provides a crucial review of the classification of existing QoS routing protocols, cross-layer design approach and classification, and various performance parameters used in QoS routing protocols. The corresponding cross-layer protocols are overviewed, followed by the major techniques in cross-layer protocol design. Moreover, VANET is presented with many exclusive networking research challenges in precise areas such as security, QoS, mobility, effective channel utilization, and scalability. Finally, the paper concluded by various comparison discussion, issues, and challenges of several routing protocols for VANET. No. of publications over the period from 2010 to 2019 in various scientific sources also showed in this review. This survey provided the technical direction for researchers on routing protocols for VANET using QoS.

11 citations